{"current_steps": 5, "total_steps": 76960, "loss": 12.8151, "lr": 2.598752598752599e-08, "epoch": 0.0012993762993762994, "percentage": 0.01, "elapsed_time": "0:00:00", "remaining_time": "4:05:28", "throughput": 451.42, "total_tokens": 432} {"current_steps": 10, "total_steps": 76960, "loss": 11.7776, "lr": 5.8471933471933477e-08, "epoch": 0.002598752598752599, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "2:56:41", "throughput": 615.53, "total_tokens": 848} {"current_steps": 15, "total_steps": 76960, "loss": 12.5996, "lr": 9.095634095634096e-08, "epoch": 0.0038981288981288983, "percentage": 0.02, "elapsed_time": "0:00:01", "remaining_time": "2:33:52", "throughput": 711.17, "total_tokens": 1280} {"current_steps": 20, "total_steps": 76960, "loss": 10.3592, "lr": 1.2344074844074844e-07, "epoch": 0.005197505197505198, "percentage": 0.03, "elapsed_time": "0:00:02", "remaining_time": "2:22:17", "throughput": 785.86, "total_tokens": 1744} {"current_steps": 25, "total_steps": 76960, "loss": 11.4489, "lr": 1.5592515592515593e-07, "epoch": 0.006496881496881497, "percentage": 0.03, "elapsed_time": "0:00:02", "remaining_time": "2:15:17", "throughput": 824.94, "total_tokens": 2176} {"current_steps": 30, "total_steps": 76960, "loss": 12.0689, "lr": 1.8840956340956344e-07, "epoch": 0.007796257796257797, "percentage": 0.04, "elapsed_time": "0:00:03", "remaining_time": "2:10:39", "throughput": 847.83, "total_tokens": 2592} {"current_steps": 35, "total_steps": 76960, "loss": 11.2658, "lr": 2.2089397089397092e-07, "epoch": 0.009095634095634096, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "2:07:25", "throughput": 873.94, "total_tokens": 3040} {"current_steps": 40, "total_steps": 76960, "loss": 10.6036, "lr": 2.533783783783784e-07, "epoch": 0.010395010395010396, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "2:04:53", "throughput": 891.02, "total_tokens": 3472} {"current_steps": 45, "total_steps": 76960, "loss": 10.4079, "lr": 2.858627858627859e-07, "epoch": 0.011694386694386695, "percentage": 0.06, "elapsed_time": "0:00:04", "remaining_time": "2:02:57", "throughput": 908.2, "total_tokens": 3920} {"current_steps": 50, "total_steps": 76960, "loss": 10.5629, "lr": 3.183471933471934e-07, "epoch": 0.012993762993762994, "percentage": 0.06, "elapsed_time": "0:00:04", "remaining_time": "2:01:24", "throughput": 922.32, "total_tokens": 4368} {"current_steps": 55, "total_steps": 76960, "loss": 9.256, "lr": 3.5083160083160086e-07, "epoch": 0.014293139293139294, "percentage": 0.07, "elapsed_time": "0:00:05", "remaining_time": "2:00:14", "throughput": 933.35, "total_tokens": 4816} {"current_steps": 60, "total_steps": 76960, "loss": 8.486, "lr": 3.8331600831600834e-07, "epoch": 0.015592515592515593, "percentage": 0.08, "elapsed_time": "0:00:05", "remaining_time": "1:59:10", "throughput": 946.36, "total_tokens": 5280} {"current_steps": 65, "total_steps": 76960, "loss": 7.4865, "lr": 4.1580041580041583e-07, "epoch": 0.016891891891891893, "percentage": 0.08, "elapsed_time": "0:00:05", "remaining_time": "1:58:15", "throughput": 952.33, "total_tokens": 5712} {"current_steps": 70, "total_steps": 76960, "loss": 7.5211, "lr": 4.482848232848233e-07, "epoch": 0.018191268191268192, "percentage": 0.09, "elapsed_time": "0:00:06", "remaining_time": "1:57:29", "throughput": 959.89, "total_tokens": 6160} {"current_steps": 75, "total_steps": 76960, "loss": 7.2602, "lr": 4.807692307692308e-07, "epoch": 0.01949064449064449, "percentage": 0.1, "elapsed_time": "0:00:06", "remaining_time": "1:56:47", "throughput": 966.68, "total_tokens": 6608} {"current_steps": 80, "total_steps": 76960, "loss": 6.8226, "lr": 5.132536382536383e-07, "epoch": 0.02079002079002079, "percentage": 0.1, "elapsed_time": "0:00:07", "remaining_time": "1:56:13", "throughput": 981.21, "total_tokens": 7120} {"current_steps": 85, "total_steps": 76960, "loss": 5.8078, "lr": 5.457380457380458e-07, "epoch": 0.02208939708939709, "percentage": 0.11, "elapsed_time": "0:00:07", "remaining_time": "1:55:41", "throughput": 986.08, "total_tokens": 7568} {"current_steps": 90, "total_steps": 76960, "loss": 5.6128, "lr": 5.782224532224532e-07, "epoch": 0.02338877338877339, "percentage": 0.12, "elapsed_time": "0:00:08", "remaining_time": "1:55:12", "throughput": 988.51, "total_tokens": 8000} {"current_steps": 95, "total_steps": 76960, "loss": 5.3646, "lr": 6.107068607068608e-07, "epoch": 0.02468814968814969, "percentage": 0.12, "elapsed_time": "0:00:08", "remaining_time": "1:54:46", "throughput": 994.47, "total_tokens": 8464} {"current_steps": 100, "total_steps": 76960, "loss": 4.6696, "lr": 6.431912681912682e-07, "epoch": 0.02598752598752599, "percentage": 0.13, "elapsed_time": "0:00:08", "remaining_time": "1:54:22", "throughput": 998.12, "total_tokens": 8912} {"current_steps": 105, "total_steps": 76960, "loss": 4.2801, "lr": 6.756756756756758e-07, "epoch": 0.02728690228690229, "percentage": 0.14, "elapsed_time": "0:00:09", "remaining_time": "1:54:00", "throughput": 1003.2, "total_tokens": 9376} {"current_steps": 110, "total_steps": 76960, "loss": 3.6646, "lr": 7.081600831600832e-07, "epoch": 0.028586278586278588, "percentage": 0.14, "elapsed_time": "0:00:09", "remaining_time": "1:53:43", "throughput": 1004.24, "total_tokens": 9808} {"current_steps": 115, "total_steps": 76960, "loss": 3.167, "lr": 7.406444906444907e-07, "epoch": 0.029885654885654887, "percentage": 0.15, "elapsed_time": "0:00:10", "remaining_time": "1:53:27", "throughput": 1002.04, "total_tokens": 10208} {"current_steps": 120, "total_steps": 76960, "loss": 2.8749, "lr": 7.731288981288983e-07, "epoch": 0.031185031185031187, "percentage": 0.16, "elapsed_time": "0:00:10", "remaining_time": "1:53:11", "throughput": 1003.17, "total_tokens": 10640} {"current_steps": 125, "total_steps": 76960, "loss": 2.3385, "lr": 8.056133056133057e-07, "epoch": 0.032484407484407486, "percentage": 0.16, "elapsed_time": "0:00:11", "remaining_time": "1:52:56", "throughput": 1005.76, "total_tokens": 11088} {"current_steps": 130, "total_steps": 76960, "loss": 1.8462, "lr": 8.380977130977132e-07, "epoch": 0.033783783783783786, "percentage": 0.17, "elapsed_time": "0:00:11", "remaining_time": "1:52:42", "throughput": 1008.18, "total_tokens": 11536} {"current_steps": 135, "total_steps": 76960, "loss": 1.671, "lr": 8.705821205821207e-07, "epoch": 0.035083160083160085, "percentage": 0.18, "elapsed_time": "0:00:11", "remaining_time": "1:52:29", "throughput": 1011.73, "total_tokens": 12000} {"current_steps": 140, "total_steps": 76960, "loss": 1.1814, "lr": 9.030665280665282e-07, "epoch": 0.036382536382536385, "percentage": 0.18, "elapsed_time": "0:00:12", "remaining_time": "1:52:17", "throughput": 1016.37, "total_tokens": 12480} {"current_steps": 145, "total_steps": 76960, "loss": 0.8406, "lr": 9.355509355509356e-07, "epoch": 0.037681912681912684, "percentage": 0.19, "elapsed_time": "0:00:12", "remaining_time": "1:52:06", "throughput": 1020.62, "total_tokens": 12960} {"current_steps": 150, "total_steps": 76960, "loss": 0.7208, "lr": 9.680353430353432e-07, "epoch": 0.03898128898128898, "percentage": 0.19, "elapsed_time": "0:00:13", "remaining_time": "1:51:56", "throughput": 1024.59, "total_tokens": 13440} {"current_steps": 155, "total_steps": 76960, "loss": 0.8895, "lr": 1.0005197505197507e-06, "epoch": 0.04028066528066528, "percentage": 0.2, "elapsed_time": "0:00:13", "remaining_time": "1:51:48", "throughput": 1023.42, "total_tokens": 13856} {"current_steps": 160, "total_steps": 76960, "loss": 0.548, "lr": 1.033004158004158e-06, "epoch": 0.04158004158004158, "percentage": 0.21, "elapsed_time": "0:00:13", "remaining_time": "1:51:40", "throughput": 1024.75, "total_tokens": 14304} {"current_steps": 165, "total_steps": 76960, "loss": 0.3001, "lr": 1.0654885654885656e-06, "epoch": 0.04287941787941788, "percentage": 0.21, "elapsed_time": "0:00:14", "remaining_time": "1:51:32", "throughput": 1023.74, "total_tokens": 14720} {"current_steps": 170, "total_steps": 76960, "loss": 0.3482, "lr": 1.097972972972973e-06, "epoch": 0.04417879417879418, "percentage": 0.22, "elapsed_time": "0:00:14", "remaining_time": "1:51:25", "throughput": 1024.88, "total_tokens": 15168} {"current_steps": 175, "total_steps": 76960, "loss": 0.2253, "lr": 1.1304573804573806e-06, "epoch": 0.04547817047817048, "percentage": 0.23, "elapsed_time": "0:00:15", "remaining_time": "1:51:16", "throughput": 1027.32, "total_tokens": 15632} {"current_steps": 180, "total_steps": 76960, "loss": 0.5573, "lr": 1.162941787941788e-06, "epoch": 0.04677754677754678, "percentage": 0.23, "elapsed_time": "0:00:15", "remaining_time": "1:51:09", "throughput": 1028.38, "total_tokens": 16080} {"current_steps": 185, "total_steps": 76960, "loss": 0.7184, "lr": 1.1954261954261955e-06, "epoch": 0.04807692307692308, "percentage": 0.24, "elapsed_time": "0:00:16", "remaining_time": "1:51:01", "throughput": 1030.67, "total_tokens": 16544} {"current_steps": 190, "total_steps": 76960, "loss": 0.5268, "lr": 1.227910602910603e-06, "epoch": 0.04937629937629938, "percentage": 0.25, "elapsed_time": "0:00:16", "remaining_time": "1:50:54", "throughput": 1029.82, "total_tokens": 16960} {"current_steps": 195, "total_steps": 76960, "loss": 0.3229, "lr": 1.2603950103950106e-06, "epoch": 0.05067567567567568, "percentage": 0.25, "elapsed_time": "0:00:16", "remaining_time": "1:50:46", "throughput": 1031.04, "total_tokens": 17408} {"current_steps": 200, "total_steps": 76960, "loss": 0.2941, "lr": 1.2928794178794181e-06, "epoch": 0.05197505197505198, "percentage": 0.26, "elapsed_time": "0:00:17", "remaining_time": "1:50:39", "throughput": 1033.08, "total_tokens": 17872} {"current_steps": 205, "total_steps": 76960, "loss": 0.334, "lr": 1.3253638253638254e-06, "epoch": 0.05327442827442828, "percentage": 0.27, "elapsed_time": "0:00:17", "remaining_time": "1:50:33", "throughput": 1034.96, "total_tokens": 18336} {"current_steps": 210, "total_steps": 76960, "loss": 0.3404, "lr": 1.357848232848233e-06, "epoch": 0.05457380457380458, "percentage": 0.27, "elapsed_time": "0:00:18", "remaining_time": "1:50:27", "throughput": 1035.93, "total_tokens": 18784} {"current_steps": 215, "total_steps": 76960, "loss": 0.3284, "lr": 1.3903326403326405e-06, "epoch": 0.055873180873180876, "percentage": 0.28, "elapsed_time": "0:00:18", "remaining_time": "1:50:21", "throughput": 1035.03, "total_tokens": 19200} {"current_steps": 220, "total_steps": 76960, "loss": 0.3493, "lr": 1.422817047817048e-06, "epoch": 0.057172557172557176, "percentage": 0.29, "elapsed_time": "0:00:18", "remaining_time": "1:50:15", "throughput": 1037.6, "total_tokens": 19680} {"current_steps": 225, "total_steps": 76960, "loss": 0.1682, "lr": 1.4553014553014554e-06, "epoch": 0.058471933471933475, "percentage": 0.29, "elapsed_time": "0:00:19", "remaining_time": "1:50:10", "throughput": 1037.59, "total_tokens": 20112} {"current_steps": 230, "total_steps": 76960, "loss": 0.3047, "lr": 1.487785862785863e-06, "epoch": 0.059771309771309775, "percentage": 0.3, "elapsed_time": "0:00:19", "remaining_time": "1:50:05", "throughput": 1038.32, "total_tokens": 20560} {"current_steps": 235, "total_steps": 76960, "loss": 0.3932, "lr": 1.5202702702702704e-06, "epoch": 0.061070686070686074, "percentage": 0.31, "elapsed_time": "0:00:20", "remaining_time": "1:50:02", "throughput": 1038.9, "total_tokens": 21008} {"current_steps": 240, "total_steps": 76960, "loss": 0.579, "lr": 1.552754677754678e-06, "epoch": 0.062370062370062374, "percentage": 0.31, "elapsed_time": "0:00:20", "remaining_time": "1:49:57", "throughput": 1038.04, "total_tokens": 21424} {"current_steps": 245, "total_steps": 76960, "loss": 1.2588, "lr": 1.5852390852390853e-06, "epoch": 0.06366943866943867, "percentage": 0.32, "elapsed_time": "0:00:21", "remaining_time": "1:49:53", "throughput": 1038.69, "total_tokens": 21872} {"current_steps": 250, "total_steps": 76960, "loss": 0.3716, "lr": 1.6177234927234926e-06, "epoch": 0.06496881496881497, "percentage": 0.32, "elapsed_time": "0:00:21", "remaining_time": "1:49:50", "throughput": 1040.66, "total_tokens": 22352} {"current_steps": 255, "total_steps": 76960, "loss": 0.7009, "lr": 1.6502079002079004e-06, "epoch": 0.06626819126819126, "percentage": 0.33, "elapsed_time": "0:00:21", "remaining_time": "1:49:45", "throughput": 1042.1, "total_tokens": 22816} {"current_steps": 260, "total_steps": 76960, "loss": 0.9143, "lr": 1.6826923076923077e-06, "epoch": 0.06756756756756757, "percentage": 0.34, "elapsed_time": "0:00:22", "remaining_time": "1:49:42", "throughput": 1043.36, "total_tokens": 23280} {"current_steps": 265, "total_steps": 76960, "loss": 0.5462, "lr": 1.7151767151767155e-06, "epoch": 0.06886694386694386, "percentage": 0.34, "elapsed_time": "0:00:22", "remaining_time": "1:49:38", "throughput": 1041.77, "total_tokens": 23680} {"current_steps": 270, "total_steps": 76960, "loss": 0.8815, "lr": 1.7476611226611226e-06, "epoch": 0.07016632016632017, "percentage": 0.35, "elapsed_time": "0:00:23", "remaining_time": "1:49:34", "throughput": 1041.72, "total_tokens": 24112} {"current_steps": 275, "total_steps": 76960, "loss": 0.288, "lr": 1.7801455301455303e-06, "epoch": 0.07146569646569646, "percentage": 0.36, "elapsed_time": "0:00:23", "remaining_time": "1:49:30", "throughput": 1040.25, "total_tokens": 24512} {"current_steps": 280, "total_steps": 76960, "loss": 0.6454, "lr": 1.8126299376299376e-06, "epoch": 0.07276507276507277, "percentage": 0.36, "elapsed_time": "0:00:23", "remaining_time": "1:49:27", "throughput": 1042.85, "total_tokens": 25008} {"current_steps": 285, "total_steps": 76960, "loss": 0.3728, "lr": 1.8451143451143454e-06, "epoch": 0.07406444906444906, "percentage": 0.37, "elapsed_time": "0:00:24", "remaining_time": "1:49:23", "throughput": 1043.38, "total_tokens": 25456} {"current_steps": 290, "total_steps": 76960, "loss": 0.4746, "lr": 1.8775987525987527e-06, "epoch": 0.07536382536382537, "percentage": 0.38, "elapsed_time": "0:00:24", "remaining_time": "1:49:20", "throughput": 1044.59, "total_tokens": 25920} {"current_steps": 295, "total_steps": 76960, "loss": 0.5626, "lr": 1.9100831600831605e-06, "epoch": 0.07666320166320166, "percentage": 0.38, "elapsed_time": "0:00:25", "remaining_time": "1:49:17", "throughput": 1045.02, "total_tokens": 26368} {"current_steps": 300, "total_steps": 76960, "loss": 0.7306, "lr": 1.9425675675675676e-06, "epoch": 0.07796257796257797, "percentage": 0.39, "elapsed_time": "0:00:25", "remaining_time": "1:49:14", "throughput": 1045.52, "total_tokens": 26816} {"current_steps": 305, "total_steps": 76960, "loss": 0.5197, "lr": 1.975051975051975e-06, "epoch": 0.07926195426195426, "percentage": 0.4, "elapsed_time": "0:00:26", "remaining_time": "1:49:11", "throughput": 1046.58, "total_tokens": 27280} {"current_steps": 310, "total_steps": 76960, "loss": 0.3768, "lr": 2.0075363825363827e-06, "epoch": 0.08056133056133057, "percentage": 0.4, "elapsed_time": "0:00:26", "remaining_time": "1:49:08", "throughput": 1046.98, "total_tokens": 27728} {"current_steps": 315, "total_steps": 76960, "loss": 0.376, "lr": 2.04002079002079e-06, "epoch": 0.08186070686070686, "percentage": 0.41, "elapsed_time": "0:00:26", "remaining_time": "1:49:05", "throughput": 1046.81, "total_tokens": 28160} {"current_steps": 320, "total_steps": 76960, "loss": 0.3699, "lr": 2.0725051975051977e-06, "epoch": 0.08316008316008316, "percentage": 0.42, "elapsed_time": "0:00:27", "remaining_time": "1:49:02", "throughput": 1046.02, "total_tokens": 28576} {"current_steps": 325, "total_steps": 76960, "loss": 0.2854, "lr": 2.1049896049896053e-06, "epoch": 0.08445945945945946, "percentage": 0.42, "elapsed_time": "0:00:27", "remaining_time": "1:49:00", "throughput": 1046.96, "total_tokens": 29040} {"current_steps": 330, "total_steps": 76960, "loss": 0.3273, "lr": 2.1374740124740124e-06, "epoch": 0.08575883575883576, "percentage": 0.43, "elapsed_time": "0:00:28", "remaining_time": "1:48:57", "throughput": 1047.93, "total_tokens": 29504} {"current_steps": 335, "total_steps": 76960, "loss": 0.2331, "lr": 2.1699584199584203e-06, "epoch": 0.08705821205821206, "percentage": 0.44, "elapsed_time": "0:00:28", "remaining_time": "1:48:55", "throughput": 1048.31, "total_tokens": 29952} {"current_steps": 340, "total_steps": 76960, "loss": 0.3314, "lr": 2.2024428274428275e-06, "epoch": 0.08835758835758836, "percentage": 0.44, "elapsed_time": "0:00:28", "remaining_time": "1:48:53", "throughput": 1049.72, "total_tokens": 30432} {"current_steps": 345, "total_steps": 76960, "loss": 0.2369, "lr": 2.234927234927235e-06, "epoch": 0.08965696465696466, "percentage": 0.45, "elapsed_time": "0:00:29", "remaining_time": "1:48:51", "throughput": 1050.4, "total_tokens": 30896} {"current_steps": 350, "total_steps": 76960, "loss": 0.2514, "lr": 2.2674116424116425e-06, "epoch": 0.09095634095634096, "percentage": 0.45, "elapsed_time": "0:00:29", "remaining_time": "1:48:49", "throughput": 1051.25, "total_tokens": 31360} {"current_steps": 355, "total_steps": 76960, "loss": 0.3967, "lr": 2.29989604989605e-06, "epoch": 0.09225571725571725, "percentage": 0.46, "elapsed_time": "0:00:30", "remaining_time": "1:48:47", "throughput": 1050.44, "total_tokens": 31776} {"current_steps": 360, "total_steps": 76960, "loss": 0.0192, "lr": 2.3323804573804576e-06, "epoch": 0.09355509355509356, "percentage": 0.47, "elapsed_time": "0:00:30", "remaining_time": "1:48:45", "throughput": 1050.68, "total_tokens": 32224} {"current_steps": 365, "total_steps": 76960, "loss": 0.7292, "lr": 2.364864864864865e-06, "epoch": 0.09485446985446985, "percentage": 0.47, "elapsed_time": "0:00:31", "remaining_time": "1:48:43", "throughput": 1050.54, "total_tokens": 32656} {"current_steps": 370, "total_steps": 76960, "loss": 1.5391, "lr": 2.3973492723492723e-06, "epoch": 0.09615384615384616, "percentage": 0.48, "elapsed_time": "0:00:31", "remaining_time": "1:48:40", "throughput": 1050.35, "total_tokens": 33088} {"current_steps": 375, "total_steps": 76960, "loss": 0.1892, "lr": 2.4298336798336802e-06, "epoch": 0.09745322245322245, "percentage": 0.49, "elapsed_time": "0:00:31", "remaining_time": "1:48:38", "throughput": 1050.16, "total_tokens": 33520} {"current_steps": 380, "total_steps": 76960, "loss": 0.5899, "lr": 2.4623180873180873e-06, "epoch": 0.09875259875259876, "percentage": 0.49, "elapsed_time": "0:00:32", "remaining_time": "1:48:36", "throughput": 1050.52, "total_tokens": 33968} {"current_steps": 385, "total_steps": 76960, "loss": 0.2018, "lr": 2.494802494802495e-06, "epoch": 0.10005197505197505, "percentage": 0.5, "elapsed_time": "0:00:32", "remaining_time": "1:48:34", "throughput": 1050.35, "total_tokens": 34400} {"current_steps": 390, "total_steps": 76960, "loss": 0.3079, "lr": 2.5272869022869024e-06, "epoch": 0.10135135135135136, "percentage": 0.51, "elapsed_time": "0:00:33", "remaining_time": "1:48:31", "throughput": 1051.2, "total_tokens": 34864} {"current_steps": 395, "total_steps": 76960, "loss": 1.3881, "lr": 2.55977130977131e-06, "epoch": 0.10265072765072765, "percentage": 0.51, "elapsed_time": "0:00:33", "remaining_time": "1:48:29", "throughput": 1050.51, "total_tokens": 35280} {"current_steps": 400, "total_steps": 76960, "loss": 0.6543, "lr": 2.5922557172557175e-06, "epoch": 0.10395010395010396, "percentage": 0.52, "elapsed_time": "0:00:34", "remaining_time": "1:48:27", "throughput": 1050.8, "total_tokens": 35728} {"current_steps": 405, "total_steps": 76960, "loss": 0.7843, "lr": 2.624740124740125e-06, "epoch": 0.10524948024948025, "percentage": 0.53, "elapsed_time": "0:00:34", "remaining_time": "1:48:25", "throughput": 1051.54, "total_tokens": 36192} {"current_steps": 410, "total_steps": 76960, "loss": 0.3982, "lr": 2.657224532224532e-06, "epoch": 0.10654885654885655, "percentage": 0.53, "elapsed_time": "0:00:34", "remaining_time": "1:48:23", "throughput": 1052.29, "total_tokens": 36656} {"current_steps": 415, "total_steps": 76960, "loss": 0.4756, "lr": 2.68970893970894e-06, "epoch": 0.10784823284823285, "percentage": 0.54, "elapsed_time": "0:00:35", "remaining_time": "1:48:22", "throughput": 1051.61, "total_tokens": 37072} {"current_steps": 420, "total_steps": 76960, "loss": 0.3814, "lr": 2.722193347193347e-06, "epoch": 0.10914760914760915, "percentage": 0.55, "elapsed_time": "0:00:35", "remaining_time": "1:48:20", "throughput": 1052.79, "total_tokens": 37552} {"current_steps": 425, "total_steps": 76960, "loss": 0.2489, "lr": 2.754677754677755e-06, "epoch": 0.11044698544698545, "percentage": 0.55, "elapsed_time": "0:00:36", "remaining_time": "1:48:18", "throughput": 1053.91, "total_tokens": 38032} {"current_steps": 430, "total_steps": 76960, "loss": 0.3363, "lr": 2.7871621621621623e-06, "epoch": 0.11174636174636175, "percentage": 0.56, "elapsed_time": "0:00:36", "remaining_time": "1:48:16", "throughput": 1053.25, "total_tokens": 38448} {"current_steps": 435, "total_steps": 76960, "loss": 0.2996, "lr": 2.81964656964657e-06, "epoch": 0.11304573804573805, "percentage": 0.57, "elapsed_time": "0:00:36", "remaining_time": "1:48:15", "throughput": 1055.24, "total_tokens": 38960} {"current_steps": 440, "total_steps": 76960, "loss": 0.3007, "lr": 2.8521309771309773e-06, "epoch": 0.11434511434511435, "percentage": 0.57, "elapsed_time": "0:00:37", "remaining_time": "1:48:13", "throughput": 1055.46, "total_tokens": 39408} {"current_steps": 445, "total_steps": 76960, "loss": 0.1994, "lr": 2.884615384615385e-06, "epoch": 0.11564449064449064, "percentage": 0.58, "elapsed_time": "0:00:37", "remaining_time": "1:48:11", "throughput": 1055.24, "total_tokens": 39840} {"current_steps": 450, "total_steps": 76960, "loss": 0.4265, "lr": 2.9170997920997924e-06, "epoch": 0.11694386694386695, "percentage": 0.58, "elapsed_time": "0:00:38", "remaining_time": "1:48:10", "throughput": 1056.24, "total_tokens": 40320} {"current_steps": 455, "total_steps": 76960, "loss": 0.4072, "lr": 2.9495841995842e-06, "epoch": 0.11824324324324324, "percentage": 0.59, "elapsed_time": "0:00:38", "remaining_time": "1:48:08", "throughput": 1056.38, "total_tokens": 40768} {"current_steps": 460, "total_steps": 76960, "loss": 0.1751, "lr": 2.982068607068607e-06, "epoch": 0.11954261954261955, "percentage": 0.6, "elapsed_time": "0:00:39", "remaining_time": "1:48:08", "throughput": 1056.8, "total_tokens": 41232} {"current_steps": 465, "total_steps": 76960, "loss": 0.9312, "lr": 3.014553014553015e-06, "epoch": 0.12084199584199584, "percentage": 0.6, "elapsed_time": "0:00:39", "remaining_time": "1:48:07", "throughput": 1056.83, "total_tokens": 41680} {"current_steps": 470, "total_steps": 76960, "loss": 0.2745, "lr": 3.047037422037422e-06, "epoch": 0.12214137214137215, "percentage": 0.61, "elapsed_time": "0:00:39", "remaining_time": "1:48:07", "throughput": 1056.86, "total_tokens": 42128} {"current_steps": 475, "total_steps": 76960, "loss": 0.2449, "lr": 3.0795218295218297e-06, "epoch": 0.12344074844074844, "percentage": 0.62, "elapsed_time": "0:00:40", "remaining_time": "1:48:06", "throughput": 1056.57, "total_tokens": 42560} {"current_steps": 480, "total_steps": 76960, "loss": 0.2718, "lr": 3.1120062370062372e-06, "epoch": 0.12474012474012475, "percentage": 0.62, "elapsed_time": "0:00:40", "remaining_time": "1:48:04", "throughput": 1056.74, "total_tokens": 43008} {"current_steps": 485, "total_steps": 76960, "loss": 0.6545, "lr": 3.1444906444906448e-06, "epoch": 0.12603950103950104, "percentage": 0.63, "elapsed_time": "0:00:41", "remaining_time": "1:48:03", "throughput": 1058.46, "total_tokens": 43520} {"current_steps": 490, "total_steps": 76960, "loss": 0.7367, "lr": 3.1769750519750523e-06, "epoch": 0.12733887733887733, "percentage": 0.64, "elapsed_time": "0:00:41", "remaining_time": "1:48:01", "throughput": 1058.6, "total_tokens": 43968} {"current_steps": 495, "total_steps": 76960, "loss": 0.3003, "lr": 3.2094594594594594e-06, "epoch": 0.12863825363825362, "percentage": 0.64, "elapsed_time": "0:00:41", "remaining_time": "1:48:00", "throughput": 1058.34, "total_tokens": 44400} {"current_steps": 500, "total_steps": 76960, "loss": 0.2641, "lr": 3.241943866943867e-06, "epoch": 0.12993762993762994, "percentage": 0.65, "elapsed_time": "0:00:42", "remaining_time": "1:47:59", "throughput": 1059.25, "total_tokens": 44880} {"current_steps": 505, "total_steps": 76960, "loss": 0.2329, "lr": 3.274428274428275e-06, "epoch": 0.13123700623700624, "percentage": 0.66, "elapsed_time": "0:00:42", "remaining_time": "1:47:57", "throughput": 1058.99, "total_tokens": 45312} {"current_steps": 510, "total_steps": 76960, "loss": 0.5172, "lr": 3.306912681912682e-06, "epoch": 0.13253638253638253, "percentage": 0.66, "elapsed_time": "0:00:43", "remaining_time": "1:47:56", "throughput": 1058.37, "total_tokens": 45728} {"current_steps": 515, "total_steps": 76960, "loss": 0.7481, "lr": 3.3393970893970896e-06, "epoch": 0.13383575883575882, "percentage": 0.67, "elapsed_time": "0:00:43", "remaining_time": "1:47:55", "throughput": 1058.46, "total_tokens": 46176} {"current_steps": 520, "total_steps": 76960, "loss": 0.4908, "lr": 3.3718814968814967e-06, "epoch": 0.13513513513513514, "percentage": 0.68, "elapsed_time": "0:00:44", "remaining_time": "1:47:54", "throughput": 1058.99, "total_tokens": 46640} {"current_steps": 525, "total_steps": 76960, "loss": 0.5315, "lr": 3.4043659043659046e-06, "epoch": 0.13643451143451144, "percentage": 0.68, "elapsed_time": "0:00:44", "remaining_time": "1:47:52", "throughput": 1059.13, "total_tokens": 47088} {"current_steps": 530, "total_steps": 76960, "loss": 0.4366, "lr": 3.436850311850312e-06, "epoch": 0.13773388773388773, "percentage": 0.69, "elapsed_time": "0:00:44", "remaining_time": "1:47:51", "throughput": 1059.24, "total_tokens": 47536} {"current_steps": 535, "total_steps": 76960, "loss": 0.4517, "lr": 3.4693347193347193e-06, "epoch": 0.13903326403326402, "percentage": 0.7, "elapsed_time": "0:00:45", "remaining_time": "1:47:51", "throughput": 1059.14, "total_tokens": 47984} {"current_steps": 540, "total_steps": 76960, "loss": 0.2912, "lr": 3.501819126819127e-06, "epoch": 0.14033264033264034, "percentage": 0.7, "elapsed_time": "0:00:45", "remaining_time": "1:47:50", "throughput": 1058.54, "total_tokens": 48400} {"current_steps": 545, "total_steps": 76960, "loss": 0.6241, "lr": 3.5343035343035348e-06, "epoch": 0.14163201663201663, "percentage": 0.71, "elapsed_time": "0:00:46", "remaining_time": "1:47:49", "throughput": 1058.66, "total_tokens": 48848} {"current_steps": 550, "total_steps": 76960, "loss": 0.2579, "lr": 3.566787941787942e-06, "epoch": 0.14293139293139293, "percentage": 0.71, "elapsed_time": "0:00:46", "remaining_time": "1:47:48", "throughput": 1058.82, "total_tokens": 49296} {"current_steps": 555, "total_steps": 76960, "loss": 0.4002, "lr": 3.5992723492723494e-06, "epoch": 0.14423076923076922, "percentage": 0.72, "elapsed_time": "0:00:46", "remaining_time": "1:47:46", "throughput": 1059.34, "total_tokens": 49760} {"current_steps": 560, "total_steps": 76960, "loss": 0.2637, "lr": 3.6317567567567565e-06, "epoch": 0.14553014553014554, "percentage": 0.73, "elapsed_time": "0:00:47", "remaining_time": "1:47:45", "throughput": 1059.5, "total_tokens": 50208} {"current_steps": 565, "total_steps": 76960, "loss": 0.3172, "lr": 3.6642411642411645e-06, "epoch": 0.14682952182952183, "percentage": 0.73, "elapsed_time": "0:00:47", "remaining_time": "1:47:43", "throughput": 1059.31, "total_tokens": 50640} {"current_steps": 570, "total_steps": 76960, "loss": 0.3157, "lr": 3.696725571725572e-06, "epoch": 0.14812889812889812, "percentage": 0.74, "elapsed_time": "0:00:48", "remaining_time": "1:47:42", "throughput": 1058.76, "total_tokens": 51056} {"current_steps": 575, "total_steps": 76960, "loss": 0.2728, "lr": 3.729209979209979e-06, "epoch": 0.14942827442827442, "percentage": 0.75, "elapsed_time": "0:00:48", "remaining_time": "1:47:41", "throughput": 1058.83, "total_tokens": 51504} {"current_steps": 580, "total_steps": 76960, "loss": 0.42, "lr": 3.7616943866943867e-06, "epoch": 0.15072765072765074, "percentage": 0.75, "elapsed_time": "0:00:49", "remaining_time": "1:47:40", "throughput": 1060.28, "total_tokens": 52016} {"current_steps": 585, "total_steps": 76960, "loss": 0.257, "lr": 3.7941787941787947e-06, "epoch": 0.15202702702702703, "percentage": 0.76, "elapsed_time": "0:00:49", "remaining_time": "1:47:39", "throughput": 1060.41, "total_tokens": 52464} {"current_steps": 590, "total_steps": 76960, "loss": 0.3028, "lr": 3.826663201663202e-06, "epoch": 0.15332640332640332, "percentage": 0.77, "elapsed_time": "0:00:49", "remaining_time": "1:47:38", "throughput": 1060.54, "total_tokens": 52912} {"current_steps": 595, "total_steps": 76960, "loss": 0.2497, "lr": 3.859147609147609e-06, "epoch": 0.1546257796257796, "percentage": 0.77, "elapsed_time": "0:00:50", "remaining_time": "1:47:36", "throughput": 1060.98, "total_tokens": 53376} {"current_steps": 600, "total_steps": 76960, "loss": 0.3422, "lr": 3.891632016632016e-06, "epoch": 0.15592515592515593, "percentage": 0.78, "elapsed_time": "0:00:50", "remaining_time": "1:47:35", "throughput": 1061.74, "total_tokens": 53856} {"current_steps": 605, "total_steps": 76960, "loss": 0.1665, "lr": 3.924116424116424e-06, "epoch": 0.15722453222453223, "percentage": 0.79, "elapsed_time": "0:00:51", "remaining_time": "1:47:34", "throughput": 1062.48, "total_tokens": 54336} {"current_steps": 610, "total_steps": 76960, "loss": 0.6221, "lr": 3.9566008316008315e-06, "epoch": 0.15852390852390852, "percentage": 0.79, "elapsed_time": "0:00:51", "remaining_time": "1:47:33", "throughput": 1062.91, "total_tokens": 54800} {"current_steps": 615, "total_steps": 76960, "loss": 0.281, "lr": 3.9890852390852394e-06, "epoch": 0.1598232848232848, "percentage": 0.8, "elapsed_time": "0:00:51", "remaining_time": "1:47:32", "throughput": 1063.28, "total_tokens": 55264} {"current_steps": 620, "total_steps": 76960, "loss": 0.4267, "lr": 4.0215696465696466e-06, "epoch": 0.16112266112266113, "percentage": 0.81, "elapsed_time": "0:00:52", "remaining_time": "1:47:30", "throughput": 1063.67, "total_tokens": 55728} {"current_steps": 625, "total_steps": 76960, "loss": 0.2341, "lr": 4.0540540540540545e-06, "epoch": 0.16242203742203742, "percentage": 0.81, "elapsed_time": "0:00:52", "remaining_time": "1:47:30", "throughput": 1063.74, "total_tokens": 56176} {"current_steps": 630, "total_steps": 76960, "loss": 0.2439, "lr": 4.086538461538462e-06, "epoch": 0.16372141372141372, "percentage": 0.82, "elapsed_time": "0:00:53", "remaining_time": "1:47:28", "throughput": 1063.83, "total_tokens": 56624} {"current_steps": 635, "total_steps": 76960, "loss": 0.2524, "lr": 4.119022869022869e-06, "epoch": 0.16502079002079, "percentage": 0.83, "elapsed_time": "0:00:53", "remaining_time": "1:47:27", "throughput": 1063.61, "total_tokens": 57056} {"current_steps": 640, "total_steps": 76960, "loss": 0.2135, "lr": 4.151507276507277e-06, "epoch": 0.16632016632016633, "percentage": 0.83, "elapsed_time": "0:00:54", "remaining_time": "1:47:26", "throughput": 1063.98, "total_tokens": 57520} {"current_steps": 645, "total_steps": 76960, "loss": 0.1677, "lr": 4.183991683991685e-06, "epoch": 0.16761954261954262, "percentage": 0.84, "elapsed_time": "0:00:54", "remaining_time": "1:47:25", "throughput": 1064.67, "total_tokens": 58000} {"current_steps": 650, "total_steps": 76960, "loss": 0.0035, "lr": 4.216476091476092e-06, "epoch": 0.16891891891891891, "percentage": 0.84, "elapsed_time": "0:00:54", "remaining_time": "1:47:24", "throughput": 1064.75, "total_tokens": 58448} {"current_steps": 655, "total_steps": 76960, "loss": 1.381, "lr": 4.248960498960499e-06, "epoch": 0.1702182952182952, "percentage": 0.85, "elapsed_time": "0:00:55", "remaining_time": "1:47:23", "throughput": 1065.12, "total_tokens": 58912} {"current_steps": 660, "total_steps": 76960, "loss": 0.8743, "lr": 4.281444906444906e-06, "epoch": 0.17151767151767153, "percentage": 0.86, "elapsed_time": "0:00:55", "remaining_time": "1:47:22", "throughput": 1064.56, "total_tokens": 59328} {"current_steps": 665, "total_steps": 76960, "loss": 0.3708, "lr": 4.313929313929314e-06, "epoch": 0.17281704781704782, "percentage": 0.86, "elapsed_time": "0:00:56", "remaining_time": "1:47:21", "throughput": 1064.04, "total_tokens": 59744} {"current_steps": 670, "total_steps": 76960, "loss": 0.708, "lr": 4.346413721413722e-06, "epoch": 0.1741164241164241, "percentage": 0.87, "elapsed_time": "0:00:56", "remaining_time": "1:47:20", "throughput": 1063.53, "total_tokens": 60160} {"current_steps": 675, "total_steps": 76960, "loss": 0.4418, "lr": 4.378898128898129e-06, "epoch": 0.1754158004158004, "percentage": 0.88, "elapsed_time": "0:00:56", "remaining_time": "1:47:19", "throughput": 1063.9, "total_tokens": 60624} {"current_steps": 680, "total_steps": 76960, "loss": 0.3896, "lr": 4.411382536382536e-06, "epoch": 0.17671517671517672, "percentage": 0.88, "elapsed_time": "0:00:57", "remaining_time": "1:47:18", "throughput": 1064.25, "total_tokens": 61088} {"current_steps": 685, "total_steps": 76960, "loss": 0.322, "lr": 4.443866943866944e-06, "epoch": 0.17801455301455302, "percentage": 0.89, "elapsed_time": "0:00:57", "remaining_time": "1:47:17", "throughput": 1063.76, "total_tokens": 61504} {"current_steps": 690, "total_steps": 76960, "loss": 0.2966, "lr": 4.476351351351351e-06, "epoch": 0.1793139293139293, "percentage": 0.9, "elapsed_time": "0:00:58", "remaining_time": "1:47:17", "throughput": 1063.56, "total_tokens": 61936} {"current_steps": 695, "total_steps": 76960, "loss": 0.4891, "lr": 4.508835758835759e-06, "epoch": 0.1806133056133056, "percentage": 0.9, "elapsed_time": "0:00:58", "remaining_time": "1:47:15", "throughput": 1064.2, "total_tokens": 62416} {"current_steps": 700, "total_steps": 76960, "loss": 0.1663, "lr": 4.541320166320166e-06, "epoch": 0.18191268191268192, "percentage": 0.91, "elapsed_time": "0:00:59", "remaining_time": "1:47:14", "throughput": 1064.28, "total_tokens": 62864} {"current_steps": 705, "total_steps": 76960, "loss": 0.2123, "lr": 4.573804573804574e-06, "epoch": 0.18321205821205822, "percentage": 0.92, "elapsed_time": "0:00:59", "remaining_time": "1:47:13", "throughput": 1064.63, "total_tokens": 63328} {"current_steps": 710, "total_steps": 76960, "loss": 0.4818, "lr": 4.606288981288981e-06, "epoch": 0.1845114345114345, "percentage": 0.92, "elapsed_time": "0:00:59", "remaining_time": "1:47:13", "throughput": 1064.41, "total_tokens": 63760} {"current_steps": 715, "total_steps": 76960, "loss": 0.4421, "lr": 4.6387733887733885e-06, "epoch": 0.1858108108108108, "percentage": 0.93, "elapsed_time": "0:01:00", "remaining_time": "1:47:12", "throughput": 1064.98, "total_tokens": 64240} {"current_steps": 720, "total_steps": 76960, "loss": 0.5733, "lr": 4.6712577962577965e-06, "epoch": 0.18711018711018712, "percentage": 0.94, "elapsed_time": "0:01:00", "remaining_time": "1:47:11", "throughput": 1064.76, "total_tokens": 64672} {"current_steps": 725, "total_steps": 76960, "loss": 0.4139, "lr": 4.703742203742204e-06, "epoch": 0.1884095634095634, "percentage": 0.94, "elapsed_time": "0:01:01", "remaining_time": "1:47:10", "throughput": 1064.81, "total_tokens": 65120} {"current_steps": 730, "total_steps": 76960, "loss": 0.5009, "lr": 4.7362266112266115e-06, "epoch": 0.1897089397089397, "percentage": 0.95, "elapsed_time": "0:01:01", "remaining_time": "1:47:09", "throughput": 1065.14, "total_tokens": 65584} {"current_steps": 735, "total_steps": 76960, "loss": 0.2901, "lr": 4.768711018711019e-06, "epoch": 0.191008316008316, "percentage": 0.96, "elapsed_time": "0:01:01", "remaining_time": "1:47:08", "throughput": 1065.22, "total_tokens": 66032} {"current_steps": 740, "total_steps": 76960, "loss": 0.3939, "lr": 4.801195426195426e-06, "epoch": 0.19230769230769232, "percentage": 0.96, "elapsed_time": "0:01:02", "remaining_time": "1:47:07", "throughput": 1065.8, "total_tokens": 66512} {"current_steps": 745, "total_steps": 76960, "loss": 0.4844, "lr": 4.8336798336798346e-06, "epoch": 0.1936070686070686, "percentage": 0.97, "elapsed_time": "0:01:02", "remaining_time": "1:47:06", "throughput": 1065.86, "total_tokens": 66960} {"current_steps": 750, "total_steps": 76960, "loss": 0.3656, "lr": 4.866164241164242e-06, "epoch": 0.1949064449064449, "percentage": 0.97, "elapsed_time": "0:01:03", "remaining_time": "1:47:05", "throughput": 1065.93, "total_tokens": 67408} {"current_steps": 755, "total_steps": 76960, "loss": 0.2991, "lr": 4.898648648648649e-06, "epoch": 0.1962058212058212, "percentage": 0.98, "elapsed_time": "0:01:03", "remaining_time": "1:47:05", "throughput": 1065.21, "total_tokens": 67808} {"current_steps": 760, "total_steps": 76960, "loss": 0.2255, "lr": 4.931133056133056e-06, "epoch": 0.19750519750519752, "percentage": 0.99, "elapsed_time": "0:01:04", "remaining_time": "1:47:04", "throughput": 1065.52, "total_tokens": 68272} {"current_steps": 765, "total_steps": 76960, "loss": 0.2025, "lr": 4.963617463617464e-06, "epoch": 0.1988045738045738, "percentage": 0.99, "elapsed_time": "0:01:04", "remaining_time": "1:47:03", "throughput": 1065.32, "total_tokens": 68704} {"current_steps": 770, "total_steps": 76960, "loss": 0.9298, "lr": 4.996101871101872e-06, "epoch": 0.2001039501039501, "percentage": 1.0, "elapsed_time": "0:01:04", "remaining_time": "1:47:02", "throughput": 1065.61, "total_tokens": 69168} {"current_steps": 775, "total_steps": 76960, "loss": 0.4523, "lr": 5.028586278586279e-06, "epoch": 0.2014033264033264, "percentage": 1.01, "elapsed_time": "0:01:05", "remaining_time": "1:47:01", "throughput": 1066.17, "total_tokens": 69648} {"current_steps": 780, "total_steps": 76960, "loss": 0.4008, "lr": 5.061070686070686e-06, "epoch": 0.20270270270270271, "percentage": 1.01, "elapsed_time": "0:01:05", "remaining_time": "1:47:00", "throughput": 1066.48, "total_tokens": 70112} {"current_steps": 785, "total_steps": 76960, "loss": 0.7618, "lr": 5.093555093555094e-06, "epoch": 0.204002079002079, "percentage": 1.02, "elapsed_time": "0:01:06", "remaining_time": "1:46:59", "throughput": 1066.54, "total_tokens": 70560} {"current_steps": 790, "total_steps": 76960, "loss": 0.6668, "lr": 5.126039501039501e-06, "epoch": 0.2053014553014553, "percentage": 1.03, "elapsed_time": "0:01:06", "remaining_time": "1:46:58", "throughput": 1067.08, "total_tokens": 71040} {"current_steps": 795, "total_steps": 76960, "loss": 0.508, "lr": 5.158523908523909e-06, "epoch": 0.2066008316008316, "percentage": 1.03, "elapsed_time": "0:01:06", "remaining_time": "1:46:58", "throughput": 1066.89, "total_tokens": 71472} {"current_steps": 800, "total_steps": 76960, "loss": 0.2602, "lr": 5.191008316008316e-06, "epoch": 0.2079002079002079, "percentage": 1.04, "elapsed_time": "0:01:07", "remaining_time": "1:46:57", "throughput": 1066.94, "total_tokens": 71920} {"current_steps": 805, "total_steps": 76960, "loss": 0.2711, "lr": 5.223492723492724e-06, "epoch": 0.2091995841995842, "percentage": 1.05, "elapsed_time": "0:01:07", "remaining_time": "1:46:56", "throughput": 1066.5, "total_tokens": 72336} {"current_steps": 810, "total_steps": 76960, "loss": 0.708, "lr": 5.255977130977131e-06, "epoch": 0.2104989604989605, "percentage": 1.05, "elapsed_time": "0:01:08", "remaining_time": "1:46:55", "throughput": 1066.31, "total_tokens": 72768} {"current_steps": 815, "total_steps": 76960, "loss": 0.5968, "lr": 5.288461538461538e-06, "epoch": 0.2117983367983368, "percentage": 1.06, "elapsed_time": "0:01:08", "remaining_time": "1:46:54", "throughput": 1066.36, "total_tokens": 73216} {"current_steps": 820, "total_steps": 76960, "loss": 0.3205, "lr": 5.320945945945946e-06, "epoch": 0.2130977130977131, "percentage": 1.07, "elapsed_time": "0:01:09", "remaining_time": "1:46:53", "throughput": 1066.89, "total_tokens": 73696} {"current_steps": 825, "total_steps": 76960, "loss": 0.19, "lr": 5.353430353430354e-06, "epoch": 0.2143970893970894, "percentage": 1.07, "elapsed_time": "0:01:09", "remaining_time": "1:46:53", "throughput": 1067.08, "total_tokens": 74160} {"current_steps": 830, "total_steps": 76960, "loss": 0.6299, "lr": 5.3859147609147614e-06, "epoch": 0.2156964656964657, "percentage": 1.08, "elapsed_time": "0:01:09", "remaining_time": "1:46:52", "throughput": 1067.16, "total_tokens": 74608} {"current_steps": 835, "total_steps": 76960, "loss": 0.6357, "lr": 5.4183991683991685e-06, "epoch": 0.216995841995842, "percentage": 1.08, "elapsed_time": "0:01:10", "remaining_time": "1:46:51", "throughput": 1066.98, "total_tokens": 75040} {"current_steps": 840, "total_steps": 76960, "loss": 0.2671, "lr": 5.450883575883576e-06, "epoch": 0.2182952182952183, "percentage": 1.09, "elapsed_time": "0:01:10", "remaining_time": "1:46:50", "throughput": 1067.5, "total_tokens": 75520} {"current_steps": 845, "total_steps": 76960, "loss": 0.1522, "lr": 5.483367983367984e-06, "epoch": 0.2195945945945946, "percentage": 1.1, "elapsed_time": "0:01:11", "remaining_time": "1:46:49", "throughput": 1067.79, "total_tokens": 75984} {"current_steps": 850, "total_steps": 76960, "loss": 0.5454, "lr": 5.5158523908523916e-06, "epoch": 0.2208939708939709, "percentage": 1.1, "elapsed_time": "0:01:11", "remaining_time": "1:46:48", "throughput": 1067.86, "total_tokens": 76432} {"current_steps": 855, "total_steps": 76960, "loss": 0.3526, "lr": 5.548336798336799e-06, "epoch": 0.22219334719334718, "percentage": 1.11, "elapsed_time": "0:01:11", "remaining_time": "1:46:47", "throughput": 1068.15, "total_tokens": 76896} {"current_steps": 860, "total_steps": 76960, "loss": 0.1899, "lr": 5.580821205821206e-06, "epoch": 0.2234927234927235, "percentage": 1.12, "elapsed_time": "0:01:12", "remaining_time": "1:46:46", "throughput": 1068.22, "total_tokens": 77344} {"current_steps": 865, "total_steps": 76960, "loss": 0.7414, "lr": 5.613305613305614e-06, "epoch": 0.2247920997920998, "percentage": 1.12, "elapsed_time": "0:01:12", "remaining_time": "1:46:46", "throughput": 1068.49, "total_tokens": 77808} {"current_steps": 870, "total_steps": 76960, "loss": 0.608, "lr": 5.645790020790021e-06, "epoch": 0.2260914760914761, "percentage": 1.13, "elapsed_time": "0:01:13", "remaining_time": "1:46:45", "throughput": 1068.75, "total_tokens": 78272} {"current_steps": 875, "total_steps": 76960, "loss": 0.3063, "lr": 5.678274428274429e-06, "epoch": 0.22739085239085238, "percentage": 1.14, "elapsed_time": "0:01:13", "remaining_time": "1:46:45", "throughput": 1069.11, "total_tokens": 78752} {"current_steps": 880, "total_steps": 76960, "loss": 0.2151, "lr": 5.710758835758836e-06, "epoch": 0.2286902286902287, "percentage": 1.14, "elapsed_time": "0:01:14", "remaining_time": "1:46:44", "throughput": 1069.36, "total_tokens": 79216} {"current_steps": 885, "total_steps": 76960, "loss": 1.2484, "lr": 5.743243243243244e-06, "epoch": 0.229989604989605, "percentage": 1.15, "elapsed_time": "0:01:14", "remaining_time": "1:46:43", "throughput": 1069.83, "total_tokens": 79696} {"current_steps": 890, "total_steps": 76960, "loss": 0.2694, "lr": 5.775727650727651e-06, "epoch": 0.2312889812889813, "percentage": 1.16, "elapsed_time": "0:01:14", "remaining_time": "1:46:42", "throughput": 1070.05, "total_tokens": 80160} {"current_steps": 895, "total_steps": 76960, "loss": 0.2226, "lr": 5.808212058212058e-06, "epoch": 0.23258835758835758, "percentage": 1.16, "elapsed_time": "0:01:15", "remaining_time": "1:46:42", "throughput": 1069.83, "total_tokens": 80592} {"current_steps": 900, "total_steps": 76960, "loss": 0.3326, "lr": 5.840696465696466e-06, "epoch": 0.2338877338877339, "percentage": 1.17, "elapsed_time": "0:01:15", "remaining_time": "1:46:41", "throughput": 1069.85, "total_tokens": 81040} {"current_steps": 905, "total_steps": 76960, "loss": 0.9515, "lr": 5.873180873180874e-06, "epoch": 0.2351871101871102, "percentage": 1.18, "elapsed_time": "0:01:16", "remaining_time": "1:46:41", "throughput": 1069.64, "total_tokens": 81472} {"current_steps": 910, "total_steps": 76960, "loss": 0.3746, "lr": 5.905665280665281e-06, "epoch": 0.23648648648648649, "percentage": 1.18, "elapsed_time": "0:01:16", "remaining_time": "1:46:40", "throughput": 1069.89, "total_tokens": 81936} {"current_steps": 915, "total_steps": 76960, "loss": 0.8797, "lr": 5.938149688149688e-06, "epoch": 0.23778586278586278, "percentage": 1.19, "elapsed_time": "0:01:17", "remaining_time": "1:46:39", "throughput": 1069.71, "total_tokens": 82368} {"current_steps": 920, "total_steps": 76960, "loss": 0.237, "lr": 5.970634095634095e-06, "epoch": 0.2390852390852391, "percentage": 1.2, "elapsed_time": "0:01:17", "remaining_time": "1:46:39", "throughput": 1069.64, "total_tokens": 82816} {"current_steps": 925, "total_steps": 76960, "loss": 0.3303, "lr": 6.003118503118503e-06, "epoch": 0.2403846153846154, "percentage": 1.2, "elapsed_time": "0:01:17", "remaining_time": "1:46:38", "throughput": 1069.67, "total_tokens": 83264} {"current_steps": 930, "total_steps": 76960, "loss": 0.3002, "lr": 6.035602910602911e-06, "epoch": 0.24168399168399168, "percentage": 1.21, "elapsed_time": "0:01:18", "remaining_time": "1:46:37", "throughput": 1069.92, "total_tokens": 83728} {"current_steps": 935, "total_steps": 76960, "loss": 0.2804, "lr": 6.0680873180873184e-06, "epoch": 0.24298336798336798, "percentage": 1.21, "elapsed_time": "0:01:18", "remaining_time": "1:46:36", "throughput": 1069.75, "total_tokens": 84160} {"current_steps": 940, "total_steps": 76960, "loss": 0.3103, "lr": 6.1005717255717255e-06, "epoch": 0.2442827442827443, "percentage": 1.22, "elapsed_time": "0:01:19", "remaining_time": "1:46:36", "throughput": 1070.2, "total_tokens": 84640} {"current_steps": 945, "total_steps": 76960, "loss": 0.3041, "lr": 6.1330561330561335e-06, "epoch": 0.2455821205821206, "percentage": 1.23, "elapsed_time": "0:01:19", "remaining_time": "1:46:35", "throughput": 1070.45, "total_tokens": 85104} {"current_steps": 950, "total_steps": 76960, "loss": 0.3037, "lr": 6.165540540540541e-06, "epoch": 0.24688149688149688, "percentage": 1.23, "elapsed_time": "0:01:19", "remaining_time": "1:46:34", "throughput": 1070.48, "total_tokens": 85552} {"current_steps": 955, "total_steps": 76960, "loss": 0.3463, "lr": 6.198024948024949e-06, "epoch": 0.24818087318087317, "percentage": 1.24, "elapsed_time": "0:01:20", "remaining_time": "1:46:33", "throughput": 1070.71, "total_tokens": 86016} {"current_steps": 960, "total_steps": 76960, "loss": 0.2979, "lr": 6.230509355509356e-06, "epoch": 0.2494802494802495, "percentage": 1.25, "elapsed_time": "0:01:20", "remaining_time": "1:46:32", "throughput": 1070.96, "total_tokens": 86480} {"current_steps": 965, "total_steps": 76960, "loss": 0.248, "lr": 6.262993762993763e-06, "epoch": 0.25077962577962576, "percentage": 1.25, "elapsed_time": "0:01:21", "remaining_time": "1:46:31", "throughput": 1071.0, "total_tokens": 86928} {"current_steps": 970, "total_steps": 76960, "loss": 0.3838, "lr": 6.295478170478171e-06, "epoch": 0.2520790020790021, "percentage": 1.26, "elapsed_time": "0:01:21", "remaining_time": "1:46:31", "throughput": 1071.01, "total_tokens": 87376} {"current_steps": 975, "total_steps": 76960, "loss": 0.2414, "lr": 6.327962577962578e-06, "epoch": 0.2533783783783784, "percentage": 1.27, "elapsed_time": "0:01:21", "remaining_time": "1:46:30", "throughput": 1071.44, "total_tokens": 87856} {"current_steps": 980, "total_steps": 76960, "loss": 0.3444, "lr": 6.360446985446986e-06, "epoch": 0.25467775467775466, "percentage": 1.27, "elapsed_time": "0:01:22", "remaining_time": "1:46:29", "throughput": 1071.83, "total_tokens": 88336} {"current_steps": 985, "total_steps": 76960, "loss": 0.4116, "lr": 6.392931392931394e-06, "epoch": 0.255977130977131, "percentage": 1.28, "elapsed_time": "0:01:22", "remaining_time": "1:46:29", "throughput": 1072.62, "total_tokens": 88848} {"current_steps": 990, "total_steps": 76960, "loss": 0.3022, "lr": 6.4254158004158e-06, "epoch": 0.25727650727650725, "percentage": 1.29, "elapsed_time": "0:01:23", "remaining_time": "1:46:28", "throughput": 1072.84, "total_tokens": 89312} {"current_steps": 995, "total_steps": 76960, "loss": 0.24, "lr": 6.457900207900208e-06, "epoch": 0.25857588357588357, "percentage": 1.29, "elapsed_time": "0:01:23", "remaining_time": "1:46:27", "throughput": 1072.85, "total_tokens": 89760} {"current_steps": 1000, "total_steps": 76960, "loss": 0.1437, "lr": 6.490384615384616e-06, "epoch": 0.2598752598752599, "percentage": 1.3, "elapsed_time": "0:01:24", "remaining_time": "1:46:26", "throughput": 1072.47, "total_tokens": 90176} {"current_steps": 1005, "total_steps": 76960, "loss": 0.8435, "lr": 6.522869022869023e-06, "epoch": 0.26117463617463615, "percentage": 1.31, "elapsed_time": "0:01:24", "remaining_time": "1:46:26", "throughput": 1072.29, "total_tokens": 90608} {"current_steps": 1010, "total_steps": 76960, "loss": 0.8849, "lr": 6.555353430353431e-06, "epoch": 0.2624740124740125, "percentage": 1.31, "elapsed_time": "0:01:24", "remaining_time": "1:46:25", "throughput": 1071.92, "total_tokens": 91024} {"current_steps": 1015, "total_steps": 76960, "loss": 0.3326, "lr": 6.587837837837837e-06, "epoch": 0.2637733887733888, "percentage": 1.32, "elapsed_time": "0:01:25", "remaining_time": "1:46:24", "throughput": 1071.74, "total_tokens": 91456} {"current_steps": 1020, "total_steps": 76960, "loss": 0.6236, "lr": 6.620322245322245e-06, "epoch": 0.26507276507276506, "percentage": 1.33, "elapsed_time": "0:01:25", "remaining_time": "1:46:24", "throughput": 1071.38, "total_tokens": 91872} {"current_steps": 1025, "total_steps": 76960, "loss": 0.9367, "lr": 6.652806652806653e-06, "epoch": 0.2663721413721414, "percentage": 1.33, "elapsed_time": "0:01:26", "remaining_time": "1:46:23", "throughput": 1071.23, "total_tokens": 92304} {"current_steps": 1030, "total_steps": 76960, "loss": 0.6496, "lr": 6.68529106029106e-06, "epoch": 0.26767151767151764, "percentage": 1.34, "elapsed_time": "0:01:26", "remaining_time": "1:46:22", "throughput": 1071.24, "total_tokens": 92752} {"current_steps": 1035, "total_steps": 76960, "loss": 0.5908, "lr": 6.717775467775468e-06, "epoch": 0.26897089397089397, "percentage": 1.34, "elapsed_time": "0:01:26", "remaining_time": "1:46:22", "throughput": 1071.45, "total_tokens": 93216} {"current_steps": 1040, "total_steps": 76960, "loss": 0.3757, "lr": 6.750259875259876e-06, "epoch": 0.2702702702702703, "percentage": 1.35, "elapsed_time": "0:01:27", "remaining_time": "1:46:21", "throughput": 1072.37, "total_tokens": 93744} {"current_steps": 1045, "total_steps": 76960, "loss": 0.2507, "lr": 6.7827442827442826e-06, "epoch": 0.27156964656964655, "percentage": 1.36, "elapsed_time": "0:01:27", "remaining_time": "1:46:20", "throughput": 1072.54, "total_tokens": 94208} {"current_steps": 1050, "total_steps": 76960, "loss": 0.3862, "lr": 6.8152286902286905e-06, "epoch": 0.27286902286902287, "percentage": 1.36, "elapsed_time": "0:01:28", "remaining_time": "1:46:21", "throughput": 1073.11, "total_tokens": 94720} {"current_steps": 1055, "total_steps": 76960, "loss": 0.2777, "lr": 6.847713097713098e-06, "epoch": 0.2741683991683992, "percentage": 1.37, "elapsed_time": "0:01:28", "remaining_time": "1:46:20", "throughput": 1073.28, "total_tokens": 95184} {"current_steps": 1060, "total_steps": 76960, "loss": 0.2769, "lr": 6.880197505197506e-06, "epoch": 0.27546777546777546, "percentage": 1.38, "elapsed_time": "0:01:29", "remaining_time": "1:46:20", "throughput": 1073.41, "total_tokens": 95648} {"current_steps": 1065, "total_steps": 76960, "loss": 0.28, "lr": 6.9126819126819135e-06, "epoch": 0.2767671517671518, "percentage": 1.38, "elapsed_time": "0:01:29", "remaining_time": "1:46:19", "throughput": 1073.41, "total_tokens": 96096} {"current_steps": 1070, "total_steps": 76960, "loss": 0.2845, "lr": 6.94516632016632e-06, "epoch": 0.27806652806652804, "percentage": 1.39, "elapsed_time": "0:01:29", "remaining_time": "1:46:19", "throughput": 1073.4, "total_tokens": 96544} {"current_steps": 1075, "total_steps": 76960, "loss": 0.2942, "lr": 6.977650727650728e-06, "epoch": 0.27936590436590436, "percentage": 1.4, "elapsed_time": "0:01:30", "remaining_time": "1:46:19", "throughput": 1073.49, "total_tokens": 97008} {"current_steps": 1080, "total_steps": 76960, "loss": 0.2714, "lr": 7.010135135135136e-06, "epoch": 0.2806652806652807, "percentage": 1.4, "elapsed_time": "0:01:30", "remaining_time": "1:46:18", "throughput": 1073.79, "total_tokens": 97488} {"current_steps": 1085, "total_steps": 76960, "loss": 0.2585, "lr": 7.042619542619543e-06, "epoch": 0.28196465696465695, "percentage": 1.41, "elapsed_time": "0:01:31", "remaining_time": "1:46:18", "throughput": 1073.7, "total_tokens": 97936} {"current_steps": 1090, "total_steps": 76960, "loss": 0.3446, "lr": 7.075103950103951e-06, "epoch": 0.28326403326403327, "percentage": 1.42, "elapsed_time": "0:01:31", "remaining_time": "1:46:18", "throughput": 1073.77, "total_tokens": 98400} {"current_steps": 1095, "total_steps": 76960, "loss": 0.2876, "lr": 7.107588357588357e-06, "epoch": 0.2845634095634096, "percentage": 1.42, "elapsed_time": "0:01:32", "remaining_time": "1:46:18", "throughput": 1073.5, "total_tokens": 98832} {"current_steps": 1100, "total_steps": 76960, "loss": 0.3803, "lr": 7.140072765072765e-06, "epoch": 0.28586278586278585, "percentage": 1.43, "elapsed_time": "0:01:32", "remaining_time": "1:46:17", "throughput": 1073.67, "total_tokens": 99296} {"current_steps": 1105, "total_steps": 76960, "loss": 0.3615, "lr": 7.172557172557173e-06, "epoch": 0.28716216216216217, "percentage": 1.44, "elapsed_time": "0:01:32", "remaining_time": "1:46:17", "throughput": 1073.49, "total_tokens": 99728} {"current_steps": 1110, "total_steps": 76960, "loss": 1.1691, "lr": 7.20504158004158e-06, "epoch": 0.28846153846153844, "percentage": 1.44, "elapsed_time": "0:01:33", "remaining_time": "1:46:16", "throughput": 1073.65, "total_tokens": 100192} {"current_steps": 1115, "total_steps": 76960, "loss": 1.2237, "lr": 7.237525987525988e-06, "epoch": 0.28976091476091476, "percentage": 1.45, "elapsed_time": "0:01:33", "remaining_time": "1:46:16", "throughput": 1073.67, "total_tokens": 100640} {"current_steps": 1120, "total_steps": 76960, "loss": 0.3541, "lr": 7.270010395010396e-06, "epoch": 0.2910602910602911, "percentage": 1.46, "elapsed_time": "0:01:34", "remaining_time": "1:46:15", "throughput": 1073.49, "total_tokens": 101072} {"current_steps": 1125, "total_steps": 76960, "loss": 0.2586, "lr": 7.302494802494802e-06, "epoch": 0.29235966735966734, "percentage": 1.46, "elapsed_time": "0:01:34", "remaining_time": "1:46:14", "throughput": 1073.68, "total_tokens": 101536} {"current_steps": 1130, "total_steps": 76960, "loss": 0.2367, "lr": 7.33497920997921e-06, "epoch": 0.29365904365904366, "percentage": 1.47, "elapsed_time": "0:01:34", "remaining_time": "1:46:14", "throughput": 1073.86, "total_tokens": 102000} {"current_steps": 1135, "total_steps": 76960, "loss": 0.456, "lr": 7.367463617463617e-06, "epoch": 0.29495841995842, "percentage": 1.47, "elapsed_time": "0:01:35", "remaining_time": "1:46:13", "throughput": 1074.72, "total_tokens": 102528} {"current_steps": 1140, "total_steps": 76960, "loss": 0.1665, "lr": 7.399948024948025e-06, "epoch": 0.29625779625779625, "percentage": 1.48, "elapsed_time": "0:01:35", "remaining_time": "1:46:12", "throughput": 1074.38, "total_tokens": 102944} {"current_steps": 1145, "total_steps": 76960, "loss": 0.3392, "lr": 7.432432432432433e-06, "epoch": 0.29755717255717257, "percentage": 1.49, "elapsed_time": "0:01:36", "remaining_time": "1:46:12", "throughput": 1074.38, "total_tokens": 103392} {"current_steps": 1150, "total_steps": 76960, "loss": 0.2933, "lr": 7.4649168399168396e-06, "epoch": 0.29885654885654883, "percentage": 1.49, "elapsed_time": "0:01:36", "remaining_time": "1:46:11", "throughput": 1074.55, "total_tokens": 103856} {"current_steps": 1155, "total_steps": 76960, "loss": 0.2889, "lr": 7.4974012474012475e-06, "epoch": 0.30015592515592515, "percentage": 1.5, "elapsed_time": "0:01:37", "remaining_time": "1:46:10", "throughput": 1074.55, "total_tokens": 104304} {"current_steps": 1160, "total_steps": 76960, "loss": 0.3154, "lr": 7.5298856548856555e-06, "epoch": 0.30145530145530147, "percentage": 1.51, "elapsed_time": "0:01:37", "remaining_time": "1:46:10", "throughput": 1074.88, "total_tokens": 104784} {"current_steps": 1165, "total_steps": 76960, "loss": 0.2627, "lr": 7.562370062370063e-06, "epoch": 0.30275467775467774, "percentage": 1.51, "elapsed_time": "0:01:37", "remaining_time": "1:46:09", "throughput": 1075.2, "total_tokens": 105264} {"current_steps": 1170, "total_steps": 76960, "loss": 0.2394, "lr": 7.5948544698544706e-06, "epoch": 0.30405405405405406, "percentage": 1.52, "elapsed_time": "0:01:38", "remaining_time": "1:46:08", "throughput": 1075.02, "total_tokens": 105696} {"current_steps": 1175, "total_steps": 76960, "loss": 0.2799, "lr": 7.627338877338877e-06, "epoch": 0.3053534303534304, "percentage": 1.53, "elapsed_time": "0:01:38", "remaining_time": "1:46:08", "throughput": 1075.51, "total_tokens": 106192} {"current_steps": 1180, "total_steps": 76960, "loss": 0.22, "lr": 7.659823284823286e-06, "epoch": 0.30665280665280664, "percentage": 1.53, "elapsed_time": "0:01:39", "remaining_time": "1:46:07", "throughput": 1075.35, "total_tokens": 106624} {"current_steps": 1185, "total_steps": 76960, "loss": 0.3004, "lr": 7.692307692307694e-06, "epoch": 0.30795218295218296, "percentage": 1.54, "elapsed_time": "0:01:39", "remaining_time": "1:46:07", "throughput": 1075.01, "total_tokens": 107040} {"current_steps": 1190, "total_steps": 76960, "loss": 0.4758, "lr": 7.7247920997921e-06, "epoch": 0.3092515592515592, "percentage": 1.55, "elapsed_time": "0:01:39", "remaining_time": "1:46:06", "throughput": 1075.02, "total_tokens": 107488} {"current_steps": 1195, "total_steps": 76960, "loss": 0.2583, "lr": 7.757276507276508e-06, "epoch": 0.31055093555093555, "percentage": 1.55, "elapsed_time": "0:01:40", "remaining_time": "1:46:05", "throughput": 1075.01, "total_tokens": 107936} {"current_steps": 1200, "total_steps": 76960, "loss": 0.3869, "lr": 7.789760914760916e-06, "epoch": 0.31185031185031187, "percentage": 1.56, "elapsed_time": "0:01:40", "remaining_time": "1:46:05", "throughput": 1075.16, "total_tokens": 108400} {"current_steps": 1205, "total_steps": 76960, "loss": 0.8237, "lr": 7.822245322245322e-06, "epoch": 0.31314968814968813, "percentage": 1.57, "elapsed_time": "0:01:41", "remaining_time": "1:46:04", "throughput": 1074.86, "total_tokens": 108816} {"current_steps": 1210, "total_steps": 76960, "loss": 0.1527, "lr": 7.85472972972973e-06, "epoch": 0.31444906444906445, "percentage": 1.57, "elapsed_time": "0:01:41", "remaining_time": "1:46:03", "throughput": 1075.19, "total_tokens": 109296} {"current_steps": 1215, "total_steps": 76960, "loss": 0.4133, "lr": 7.887214137214136e-06, "epoch": 0.3157484407484408, "percentage": 1.58, "elapsed_time": "0:01:42", "remaining_time": "1:46:03", "throughput": 1075.2, "total_tokens": 109744} {"current_steps": 1220, "total_steps": 76960, "loss": 0.5694, "lr": 7.919698544698544e-06, "epoch": 0.31704781704781704, "percentage": 1.59, "elapsed_time": "0:01:42", "remaining_time": "1:46:02", "throughput": 1075.5, "total_tokens": 110224} {"current_steps": 1225, "total_steps": 76960, "loss": 0.1444, "lr": 7.952182952182952e-06, "epoch": 0.31834719334719336, "percentage": 1.59, "elapsed_time": "0:01:42", "remaining_time": "1:46:01", "throughput": 1075.49, "total_tokens": 110672} {"current_steps": 1230, "total_steps": 76960, "loss": 0.2214, "lr": 7.98466735966736e-06, "epoch": 0.3196465696465696, "percentage": 1.6, "elapsed_time": "0:01:43", "remaining_time": "1:46:01", "throughput": 1075.49, "total_tokens": 111120} {"current_steps": 1235, "total_steps": 76960, "loss": 0.3206, "lr": 8.017151767151768e-06, "epoch": 0.32094594594594594, "percentage": 1.6, "elapsed_time": "0:01:43", "remaining_time": "1:46:00", "throughput": 1075.76, "total_tokens": 111600} {"current_steps": 1240, "total_steps": 76960, "loss": 0.2914, "lr": 8.049636174636176e-06, "epoch": 0.32224532224532226, "percentage": 1.61, "elapsed_time": "0:01:44", "remaining_time": "1:46:00", "throughput": 1076.37, "total_tokens": 112112} {"current_steps": 1245, "total_steps": 76960, "loss": 0.5559, "lr": 8.082120582120582e-06, "epoch": 0.32354469854469853, "percentage": 1.62, "elapsed_time": "0:01:44", "remaining_time": "1:45:59", "throughput": 1076.83, "total_tokens": 112608} {"current_steps": 1250, "total_steps": 76960, "loss": 0.1572, "lr": 8.11460498960499e-06, "epoch": 0.32484407484407485, "percentage": 1.62, "elapsed_time": "0:01:44", "remaining_time": "1:45:59", "throughput": 1076.5, "total_tokens": 113024} {"current_steps": 1255, "total_steps": 76960, "loss": 0.5412, "lr": 8.147089397089397e-06, "epoch": 0.32614345114345117, "percentage": 1.63, "elapsed_time": "0:01:45", "remaining_time": "1:45:58", "throughput": 1076.61, "total_tokens": 113488} {"current_steps": 1260, "total_steps": 76960, "loss": 0.347, "lr": 8.179573804573805e-06, "epoch": 0.32744282744282743, "percentage": 1.64, "elapsed_time": "0:01:45", "remaining_time": "1:45:58", "throughput": 1076.6, "total_tokens": 113936} {"current_steps": 1265, "total_steps": 76960, "loss": 0.4625, "lr": 8.212058212058212e-06, "epoch": 0.32874220374220375, "percentage": 1.64, "elapsed_time": "0:01:46", "remaining_time": "1:45:57", "throughput": 1077.06, "total_tokens": 114432} {"current_steps": 1270, "total_steps": 76960, "loss": 0.2708, "lr": 8.244542619542619e-06, "epoch": 0.33004158004158, "percentage": 1.65, "elapsed_time": "0:01:46", "remaining_time": "1:45:56", "throughput": 1077.65, "total_tokens": 114944} {"current_steps": 1275, "total_steps": 76960, "loss": 0.5073, "lr": 8.277027027027027e-06, "epoch": 0.33134095634095634, "percentage": 1.66, "elapsed_time": "0:01:47", "remaining_time": "1:45:56", "throughput": 1077.79, "total_tokens": 115408} {"current_steps": 1280, "total_steps": 76960, "loss": 0.2534, "lr": 8.309511434511436e-06, "epoch": 0.33264033264033266, "percentage": 1.66, "elapsed_time": "0:01:47", "remaining_time": "1:45:55", "throughput": 1077.62, "total_tokens": 115840} {"current_steps": 1285, "total_steps": 76960, "loss": 0.2028, "lr": 8.341995841995843e-06, "epoch": 0.3339397089397089, "percentage": 1.67, "elapsed_time": "0:01:47", "remaining_time": "1:45:55", "throughput": 1077.76, "total_tokens": 116304} {"current_steps": 1290, "total_steps": 76960, "loss": 1.1493, "lr": 8.37448024948025e-06, "epoch": 0.33523908523908524, "percentage": 1.68, "elapsed_time": "0:01:48", "remaining_time": "1:45:54", "throughput": 1077.75, "total_tokens": 116752} {"current_steps": 1295, "total_steps": 76960, "loss": 0.8717, "lr": 8.406964656964657e-06, "epoch": 0.33653846153846156, "percentage": 1.68, "elapsed_time": "0:01:48", "remaining_time": "1:45:53", "throughput": 1078.03, "total_tokens": 117232} {"current_steps": 1300, "total_steps": 76960, "loss": 0.3119, "lr": 8.439449064449065e-06, "epoch": 0.33783783783783783, "percentage": 1.69, "elapsed_time": "0:01:49", "remaining_time": "1:45:53", "throughput": 1078.31, "total_tokens": 117712} {"current_steps": 1305, "total_steps": 76960, "loss": 0.3574, "lr": 8.471933471933473e-06, "epoch": 0.33913721413721415, "percentage": 1.7, "elapsed_time": "0:01:49", "remaining_time": "1:45:52", "throughput": 1078.15, "total_tokens": 118144} {"current_steps": 1310, "total_steps": 76960, "loss": 0.6423, "lr": 8.504417879417879e-06, "epoch": 0.3404365904365904, "percentage": 1.7, "elapsed_time": "0:01:49", "remaining_time": "1:45:52", "throughput": 1077.99, "total_tokens": 118576} {"current_steps": 1315, "total_steps": 76960, "loss": 0.9245, "lr": 8.536902286902287e-06, "epoch": 0.34173596673596673, "percentage": 1.71, "elapsed_time": "0:01:50", "remaining_time": "1:45:51", "throughput": 1077.97, "total_tokens": 119024} {"current_steps": 1320, "total_steps": 76960, "loss": 0.4702, "lr": 8.569386694386695e-06, "epoch": 0.34303534303534305, "percentage": 1.72, "elapsed_time": "0:01:50", "remaining_time": "1:45:50", "throughput": 1077.82, "total_tokens": 119456} {"current_steps": 1325, "total_steps": 76960, "loss": 0.2245, "lr": 8.601871101871101e-06, "epoch": 0.3443347193347193, "percentage": 1.72, "elapsed_time": "0:01:51", "remaining_time": "1:45:50", "throughput": 1077.95, "total_tokens": 119920} {"current_steps": 1330, "total_steps": 76960, "loss": 0.7473, "lr": 8.634355509355511e-06, "epoch": 0.34563409563409564, "percentage": 1.73, "elapsed_time": "0:01:51", "remaining_time": "1:45:49", "throughput": 1077.64, "total_tokens": 120336} {"current_steps": 1335, "total_steps": 76960, "loss": 0.4736, "lr": 8.666839916839917e-06, "epoch": 0.34693347193347196, "percentage": 1.73, "elapsed_time": "0:01:52", "remaining_time": "1:45:49", "throughput": 1077.63, "total_tokens": 120784} {"current_steps": 1340, "total_steps": 76960, "loss": 0.4615, "lr": 8.699324324324325e-06, "epoch": 0.3482328482328482, "percentage": 1.74, "elapsed_time": "0:01:52", "remaining_time": "1:45:48", "throughput": 1077.47, "total_tokens": 121216} {"current_steps": 1345, "total_steps": 76960, "loss": 0.2166, "lr": 8.731808731808733e-06, "epoch": 0.34953222453222454, "percentage": 1.75, "elapsed_time": "0:01:52", "remaining_time": "1:45:48", "throughput": 1077.17, "total_tokens": 121632} {"current_steps": 1350, "total_steps": 76960, "loss": 0.5177, "lr": 8.76429313929314e-06, "epoch": 0.3508316008316008, "percentage": 1.75, "elapsed_time": "0:01:53", "remaining_time": "1:45:47", "throughput": 1077.01, "total_tokens": 122064} {"current_steps": 1355, "total_steps": 76960, "loss": 0.5488, "lr": 8.796777546777547e-06, "epoch": 0.35213097713097713, "percentage": 1.76, "elapsed_time": "0:01:53", "remaining_time": "1:45:46", "throughput": 1077.02, "total_tokens": 122512} {"current_steps": 1360, "total_steps": 76960, "loss": 0.426, "lr": 8.829261954261955e-06, "epoch": 0.35343035343035345, "percentage": 1.77, "elapsed_time": "0:01:54", "remaining_time": "1:45:46", "throughput": 1076.86, "total_tokens": 122944} {"current_steps": 1365, "total_steps": 76960, "loss": 0.3313, "lr": 8.861746361746362e-06, "epoch": 0.3547297297297297, "percentage": 1.77, "elapsed_time": "0:01:54", "remaining_time": "1:45:46", "throughput": 1076.55, "total_tokens": 123360} {"current_steps": 1370, "total_steps": 76960, "loss": 0.2855, "lr": 8.89423076923077e-06, "epoch": 0.35602910602910603, "percentage": 1.78, "elapsed_time": "0:01:55", "remaining_time": "1:45:45", "throughput": 1076.55, "total_tokens": 123808} {"current_steps": 1375, "total_steps": 76960, "loss": 0.2169, "lr": 8.926715176715176e-06, "epoch": 0.35732848232848236, "percentage": 1.79, "elapsed_time": "0:01:55", "remaining_time": "1:45:44", "throughput": 1076.4, "total_tokens": 124240} {"current_steps": 1380, "total_steps": 76960, "loss": 0.2462, "lr": 8.959199584199585e-06, "epoch": 0.3586278586278586, "percentage": 1.79, "elapsed_time": "0:01:55", "remaining_time": "1:45:44", "throughput": 1076.67, "total_tokens": 124720} {"current_steps": 1385, "total_steps": 76960, "loss": 0.018, "lr": 8.991683991683993e-06, "epoch": 0.35992723492723494, "percentage": 1.8, "elapsed_time": "0:01:56", "remaining_time": "1:45:43", "throughput": 1076.66, "total_tokens": 125168} {"current_steps": 1390, "total_steps": 76960, "loss": 0.9528, "lr": 9.0241683991684e-06, "epoch": 0.3612266112266112, "percentage": 1.81, "elapsed_time": "0:01:56", "remaining_time": "1:45:43", "throughput": 1076.93, "total_tokens": 125648} {"current_steps": 1395, "total_steps": 76960, "loss": 0.5186, "lr": 9.056652806652808e-06, "epoch": 0.3625259875259875, "percentage": 1.81, "elapsed_time": "0:01:57", "remaining_time": "1:45:42", "throughput": 1077.43, "total_tokens": 126160} {"current_steps": 1400, "total_steps": 76960, "loss": 0.4338, "lr": 9.089137214137216e-06, "epoch": 0.36382536382536385, "percentage": 1.82, "elapsed_time": "0:01:57", "remaining_time": "1:45:42", "throughput": 1077.42, "total_tokens": 126608} {"current_steps": 1405, "total_steps": 76960, "loss": 0.2978, "lr": 9.121621621621622e-06, "epoch": 0.3651247401247401, "percentage": 1.83, "elapsed_time": "0:01:57", "remaining_time": "1:45:41", "throughput": 1077.43, "total_tokens": 127056} {"current_steps": 1410, "total_steps": 76960, "loss": 0.1989, "lr": 9.15410602910603e-06, "epoch": 0.36642411642411643, "percentage": 1.83, "elapsed_time": "0:01:58", "remaining_time": "1:45:40", "throughput": 1077.42, "total_tokens": 127504} {"current_steps": 1415, "total_steps": 76960, "loss": 0.0043, "lr": 9.186590436590436e-06, "epoch": 0.36772349272349275, "percentage": 1.84, "elapsed_time": "0:01:58", "remaining_time": "1:45:40", "throughput": 1077.29, "total_tokens": 127936} {"current_steps": 1420, "total_steps": 76960, "loss": 0.576, "lr": 9.219074844074844e-06, "epoch": 0.369022869022869, "percentage": 1.85, "elapsed_time": "0:01:59", "remaining_time": "1:45:39", "throughput": 1077.15, "total_tokens": 128368} {"current_steps": 1425, "total_steps": 76960, "loss": 0.0015, "lr": 9.251559251559252e-06, "epoch": 0.37032224532224534, "percentage": 1.85, "elapsed_time": "0:01:59", "remaining_time": "1:45:39", "throughput": 1077.15, "total_tokens": 128816} {"current_steps": 1430, "total_steps": 76960, "loss": 0.4519, "lr": 9.28404365904366e-06, "epoch": 0.3716216216216216, "percentage": 1.86, "elapsed_time": "0:02:00", "remaining_time": "1:45:38", "throughput": 1077.13, "total_tokens": 129264} {"current_steps": 1435, "total_steps": 76960, "loss": 0.3652, "lr": 9.316528066528068e-06, "epoch": 0.3729209979209979, "percentage": 1.86, "elapsed_time": "0:02:00", "remaining_time": "1:45:38", "throughput": 1077.36, "total_tokens": 129744} {"current_steps": 1440, "total_steps": 76960, "loss": 0.4234, "lr": 9.349012474012476e-06, "epoch": 0.37422037422037424, "percentage": 1.87, "elapsed_time": "0:02:00", "remaining_time": "1:45:37", "throughput": 1077.49, "total_tokens": 130208} {"current_steps": 1445, "total_steps": 76960, "loss": 0.4155, "lr": 9.381496881496882e-06, "epoch": 0.3755197505197505, "percentage": 1.88, "elapsed_time": "0:02:01", "remaining_time": "1:45:36", "throughput": 1077.36, "total_tokens": 130640} {"current_steps": 1450, "total_steps": 76960, "loss": 0.2927, "lr": 9.41398128898129e-06, "epoch": 0.3768191268191268, "percentage": 1.88, "elapsed_time": "0:02:01", "remaining_time": "1:45:36", "throughput": 1077.35, "total_tokens": 131088} {"current_steps": 1455, "total_steps": 76960, "loss": 0.2669, "lr": 9.446465696465696e-06, "epoch": 0.3781185031185031, "percentage": 1.89, "elapsed_time": "0:02:02", "remaining_time": "1:45:35", "throughput": 1077.07, "total_tokens": 131504} {"current_steps": 1460, "total_steps": 76960, "loss": 0.2483, "lr": 9.478950103950104e-06, "epoch": 0.3794178794178794, "percentage": 1.9, "elapsed_time": "0:02:02", "remaining_time": "1:45:35", "throughput": 1077.19, "total_tokens": 131968} {"current_steps": 1465, "total_steps": 76960, "loss": 0.2152, "lr": 9.511434511434512e-06, "epoch": 0.38071725571725573, "percentage": 1.9, "elapsed_time": "0:02:02", "remaining_time": "1:45:34", "throughput": 1077.05, "total_tokens": 132400} {"current_steps": 1470, "total_steps": 76960, "loss": 0.689, "lr": 9.543918918918919e-06, "epoch": 0.382016632016632, "percentage": 1.91, "elapsed_time": "0:02:03", "remaining_time": "1:45:34", "throughput": 1077.17, "total_tokens": 132864} {"current_steps": 1475, "total_steps": 76960, "loss": 0.3742, "lr": 9.576403326403327e-06, "epoch": 0.3833160083160083, "percentage": 1.92, "elapsed_time": "0:02:03", "remaining_time": "1:45:33", "throughput": 1077.68, "total_tokens": 133376} {"current_steps": 1480, "total_steps": 76960, "loss": 0.4327, "lr": 9.608887733887734e-06, "epoch": 0.38461538461538464, "percentage": 1.92, "elapsed_time": "0:02:04", "remaining_time": "1:45:33", "throughput": 1077.4, "total_tokens": 133792} {"current_steps": 1485, "total_steps": 76960, "loss": 0.1998, "lr": 9.641372141372142e-06, "epoch": 0.3859147609147609, "percentage": 1.93, "elapsed_time": "0:02:04", "remaining_time": "1:45:32", "throughput": 1077.28, "total_tokens": 134224} {"current_steps": 1490, "total_steps": 76960, "loss": 0.5326, "lr": 9.67385654885655e-06, "epoch": 0.3872141372141372, "percentage": 1.94, "elapsed_time": "0:02:05", "remaining_time": "1:45:31", "throughput": 1077.42, "total_tokens": 134688} {"current_steps": 1495, "total_steps": 76960, "loss": 0.7441, "lr": 9.706340956340957e-06, "epoch": 0.3885135135135135, "percentage": 1.94, "elapsed_time": "0:02:05", "remaining_time": "1:45:31", "throughput": 1077.28, "total_tokens": 135120} {"current_steps": 1500, "total_steps": 76960, "loss": 0.4481, "lr": 9.738825363825365e-06, "epoch": 0.3898128898128898, "percentage": 1.95, "elapsed_time": "0:02:05", "remaining_time": "1:45:30", "throughput": 1077.13, "total_tokens": 135552} {"current_steps": 1505, "total_steps": 76960, "loss": 0.7465, "lr": 9.771309771309773e-06, "epoch": 0.3911122661122661, "percentage": 1.96, "elapsed_time": "0:02:06", "remaining_time": "1:45:30", "throughput": 1077.25, "total_tokens": 136016} {"current_steps": 1510, "total_steps": 76960, "loss": 0.3186, "lr": 9.803794178794179e-06, "epoch": 0.3924116424116424, "percentage": 1.96, "elapsed_time": "0:02:06", "remaining_time": "1:45:29", "throughput": 1077.11, "total_tokens": 136448} {"current_steps": 1515, "total_steps": 76960, "loss": 0.3949, "lr": 9.836278586278587e-06, "epoch": 0.3937110187110187, "percentage": 1.97, "elapsed_time": "0:02:07", "remaining_time": "1:45:29", "throughput": 1077.1, "total_tokens": 136896} {"current_steps": 1520, "total_steps": 76960, "loss": 0.2186, "lr": 9.868762993762993e-06, "epoch": 0.39501039501039503, "percentage": 1.98, "elapsed_time": "0:02:07", "remaining_time": "1:45:28", "throughput": 1077.34, "total_tokens": 137376} {"current_steps": 1525, "total_steps": 76960, "loss": 0.5653, "lr": 9.901247401247401e-06, "epoch": 0.3963097713097713, "percentage": 1.98, "elapsed_time": "0:02:07", "remaining_time": "1:45:28", "throughput": 1077.07, "total_tokens": 137792} {"current_steps": 1530, "total_steps": 76960, "loss": 0.2772, "lr": 9.933731808731809e-06, "epoch": 0.3976091476091476, "percentage": 1.99, "elapsed_time": "0:02:08", "remaining_time": "1:45:27", "throughput": 1076.93, "total_tokens": 138224} {"current_steps": 1535, "total_steps": 76960, "loss": 0.4003, "lr": 9.966216216216217e-06, "epoch": 0.3989085239085239, "percentage": 1.99, "elapsed_time": "0:02:08", "remaining_time": "1:45:27", "throughput": 1076.79, "total_tokens": 138656} {"current_steps": 1540, "total_steps": 76960, "loss": 0.3198, "lr": 9.998700623700625e-06, "epoch": 0.4002079002079002, "percentage": 2.0, "elapsed_time": "0:02:09", "remaining_time": "1:45:26", "throughput": 1076.91, "total_tokens": 139120} {"current_steps": 1545, "total_steps": 76960, "loss": 0.3247, "lr": 1.0031185031185033e-05, "epoch": 0.4015072765072765, "percentage": 2.01, "elapsed_time": "0:02:09", "remaining_time": "1:45:26", "throughput": 1076.91, "total_tokens": 139568} {"current_steps": 1550, "total_steps": 76960, "loss": 0.3817, "lr": 1.0063669438669439e-05, "epoch": 0.4028066528066528, "percentage": 2.01, "elapsed_time": "0:02:10", "remaining_time": "1:45:25", "throughput": 1077.03, "total_tokens": 140032} {"current_steps": 1555, "total_steps": 76960, "loss": 0.286, "lr": 1.0096153846153847e-05, "epoch": 0.4041060291060291, "percentage": 2.02, "elapsed_time": "0:02:10", "remaining_time": "1:45:25", "throughput": 1077.02, "total_tokens": 140480} {"current_steps": 1560, "total_steps": 76960, "loss": 0.279, "lr": 1.0128638253638253e-05, "epoch": 0.40540540540540543, "percentage": 2.03, "elapsed_time": "0:02:10", "remaining_time": "1:45:24", "throughput": 1076.76, "total_tokens": 140896} {"current_steps": 1565, "total_steps": 76960, "loss": 0.2592, "lr": 1.0161122661122661e-05, "epoch": 0.4067047817047817, "percentage": 2.03, "elapsed_time": "0:02:11", "remaining_time": "1:45:24", "throughput": 1076.62, "total_tokens": 141328} {"current_steps": 1570, "total_steps": 76960, "loss": 0.2813, "lr": 1.019360706860707e-05, "epoch": 0.408004158004158, "percentage": 2.04, "elapsed_time": "0:02:11", "remaining_time": "1:45:23", "throughput": 1076.73, "total_tokens": 141792} {"current_steps": 1575, "total_steps": 76960, "loss": 0.3268, "lr": 1.0226091476091476e-05, "epoch": 0.4093035343035343, "percentage": 2.05, "elapsed_time": "0:02:12", "remaining_time": "1:45:22", "throughput": 1076.97, "total_tokens": 142272} {"current_steps": 1580, "total_steps": 76960, "loss": 0.2892, "lr": 1.0258575883575884e-05, "epoch": 0.4106029106029106, "percentage": 2.05, "elapsed_time": "0:02:12", "remaining_time": "1:45:22", "throughput": 1077.22, "total_tokens": 142752} {"current_steps": 1585, "total_steps": 76960, "loss": 0.3351, "lr": 1.0291060291060291e-05, "epoch": 0.4119022869022869, "percentage": 2.06, "elapsed_time": "0:02:12", "remaining_time": "1:45:21", "throughput": 1077.22, "total_tokens": 143200} {"current_steps": 1590, "total_steps": 76960, "loss": 0.271, "lr": 1.03235446985447e-05, "epoch": 0.4132016632016632, "percentage": 2.07, "elapsed_time": "0:02:13", "remaining_time": "1:45:21", "throughput": 1077.22, "total_tokens": 143648} {"current_steps": 1595, "total_steps": 76960, "loss": 0.2133, "lr": 1.0356029106029107e-05, "epoch": 0.4145010395010395, "percentage": 2.07, "elapsed_time": "0:02:13", "remaining_time": "1:45:20", "throughput": 1077.44, "total_tokens": 144128} {"current_steps": 1600, "total_steps": 76960, "loss": 0.2743, "lr": 1.0388513513513514e-05, "epoch": 0.4158004158004158, "percentage": 2.08, "elapsed_time": "0:02:14", "remaining_time": "1:45:20", "throughput": 1077.44, "total_tokens": 144576} {"current_steps": 1605, "total_steps": 76960, "loss": 0.2322, "lr": 1.0420997920997922e-05, "epoch": 0.4170997920997921, "percentage": 2.09, "elapsed_time": "0:02:14", "remaining_time": "1:45:19", "throughput": 1077.31, "total_tokens": 145008} {"current_steps": 1610, "total_steps": 76960, "loss": 0.1371, "lr": 1.045348232848233e-05, "epoch": 0.4183991683991684, "percentage": 2.09, "elapsed_time": "0:02:15", "remaining_time": "1:45:19", "throughput": 1077.17, "total_tokens": 145440} {"current_steps": 1615, "total_steps": 76960, "loss": 0.1703, "lr": 1.0485966735966736e-05, "epoch": 0.4196985446985447, "percentage": 2.1, "elapsed_time": "0:02:15", "remaining_time": "1:45:18", "throughput": 1077.26, "total_tokens": 145904} {"current_steps": 1620, "total_steps": 76960, "loss": 0.1999, "lr": 1.0518451143451144e-05, "epoch": 0.420997920997921, "percentage": 2.1, "elapsed_time": "0:02:15", "remaining_time": "1:45:18", "throughput": 1077.62, "total_tokens": 146400} {"current_steps": 1625, "total_steps": 76960, "loss": 0.6232, "lr": 1.0550935550935552e-05, "epoch": 0.4222972972972973, "percentage": 2.11, "elapsed_time": "0:02:16", "remaining_time": "1:45:17", "throughput": 1077.72, "total_tokens": 146864} {"current_steps": 1630, "total_steps": 76960, "loss": 0.1925, "lr": 1.0583419958419958e-05, "epoch": 0.4235966735966736, "percentage": 2.12, "elapsed_time": "0:02:16", "remaining_time": "1:45:17", "throughput": 1077.71, "total_tokens": 147312} {"current_steps": 1635, "total_steps": 76960, "loss": 0.5416, "lr": 1.0615904365904366e-05, "epoch": 0.4248960498960499, "percentage": 2.12, "elapsed_time": "0:02:17", "remaining_time": "1:45:16", "throughput": 1077.58, "total_tokens": 147744} {"current_steps": 1640, "total_steps": 76960, "loss": 0.4471, "lr": 1.0648388773388774e-05, "epoch": 0.4261954261954262, "percentage": 2.13, "elapsed_time": "0:02:17", "remaining_time": "1:45:15", "throughput": 1077.94, "total_tokens": 148240} {"current_steps": 1645, "total_steps": 76960, "loss": 0.2304, "lr": 1.0680873180873182e-05, "epoch": 0.4274948024948025, "percentage": 2.14, "elapsed_time": "0:02:17", "remaining_time": "1:45:15", "throughput": 1077.7, "total_tokens": 148656} {"current_steps": 1650, "total_steps": 76960, "loss": 0.227, "lr": 1.071335758835759e-05, "epoch": 0.4287941787941788, "percentage": 2.14, "elapsed_time": "0:02:18", "remaining_time": "1:45:14", "throughput": 1077.58, "total_tokens": 149088} {"current_steps": 1655, "total_steps": 76960, "loss": 0.2969, "lr": 1.0745841995841996e-05, "epoch": 0.43009355509355507, "percentage": 2.15, "elapsed_time": "0:02:18", "remaining_time": "1:45:14", "throughput": 1077.56, "total_tokens": 149536} {"current_steps": 1660, "total_steps": 76960, "loss": 0.4131, "lr": 1.0778326403326404e-05, "epoch": 0.4313929313929314, "percentage": 2.16, "elapsed_time": "0:02:19", "remaining_time": "1:45:13", "throughput": 1077.43, "total_tokens": 149968} {"current_steps": 1665, "total_steps": 76960, "loss": 0.1475, "lr": 1.0810810810810812e-05, "epoch": 0.4326923076923077, "percentage": 2.16, "elapsed_time": "0:02:19", "remaining_time": "1:45:13", "throughput": 1077.66, "total_tokens": 150448} {"current_steps": 1670, "total_steps": 76960, "loss": 0.4126, "lr": 1.0843295218295218e-05, "epoch": 0.433991683991684, "percentage": 2.17, "elapsed_time": "0:02:20", "remaining_time": "1:45:12", "throughput": 1077.67, "total_tokens": 150896} {"current_steps": 1675, "total_steps": 76960, "loss": 0.4592, "lr": 1.0875779625779626e-05, "epoch": 0.4352910602910603, "percentage": 2.18, "elapsed_time": "0:02:20", "remaining_time": "1:45:12", "throughput": 1077.68, "total_tokens": 151344} {"current_steps": 1680, "total_steps": 76960, "loss": 0.5658, "lr": 1.0908264033264033e-05, "epoch": 0.4365904365904366, "percentage": 2.18, "elapsed_time": "0:02:20", "remaining_time": "1:45:11", "throughput": 1077.8, "total_tokens": 151808} {"current_steps": 1685, "total_steps": 76960, "loss": 0.4772, "lr": 1.094074844074844e-05, "epoch": 0.4378898128898129, "percentage": 2.19, "elapsed_time": "0:02:21", "remaining_time": "1:45:10", "throughput": 1078.14, "total_tokens": 152304} {"current_steps": 1690, "total_steps": 76960, "loss": 0.2322, "lr": 1.0973232848232848e-05, "epoch": 0.4391891891891892, "percentage": 2.2, "elapsed_time": "0:02:21", "remaining_time": "1:45:10", "throughput": 1078.14, "total_tokens": 152752} {"current_steps": 1695, "total_steps": 76960, "loss": 0.2961, "lr": 1.1005717255717256e-05, "epoch": 0.44048856548856546, "percentage": 2.2, "elapsed_time": "0:02:22", "remaining_time": "1:45:09", "throughput": 1078.26, "total_tokens": 153216} {"current_steps": 1700, "total_steps": 76960, "loss": 0.2933, "lr": 1.1038201663201664e-05, "epoch": 0.4417879417879418, "percentage": 2.21, "elapsed_time": "0:02:22", "remaining_time": "1:45:09", "throughput": 1078.03, "total_tokens": 153632} {"current_steps": 1705, "total_steps": 76960, "loss": 0.3081, "lr": 1.1070686070686072e-05, "epoch": 0.4430873180873181, "percentage": 2.22, "elapsed_time": "0:02:22", "remaining_time": "1:45:08", "throughput": 1077.81, "total_tokens": 154048} {"current_steps": 1710, "total_steps": 76960, "loss": 0.302, "lr": 1.1103170478170479e-05, "epoch": 0.44438669438669437, "percentage": 2.22, "elapsed_time": "0:02:23", "remaining_time": "1:45:07", "throughput": 1077.81, "total_tokens": 154496} {"current_steps": 1715, "total_steps": 76960, "loss": 0.2831, "lr": 1.1135654885654887e-05, "epoch": 0.4456860706860707, "percentage": 2.23, "elapsed_time": "0:02:23", "remaining_time": "1:45:07", "throughput": 1077.47, "total_tokens": 154896} {"current_steps": 1720, "total_steps": 76960, "loss": 0.282, "lr": 1.1168139293139293e-05, "epoch": 0.446985446985447, "percentage": 2.23, "elapsed_time": "0:02:24", "remaining_time": "1:45:06", "throughput": 1077.81, "total_tokens": 155392} {"current_steps": 1725, "total_steps": 76960, "loss": 0.2661, "lr": 1.12006237006237e-05, "epoch": 0.4482848232848233, "percentage": 2.24, "elapsed_time": "0:02:24", "remaining_time": "1:45:06", "throughput": 1077.91, "total_tokens": 155856} {"current_steps": 1730, "total_steps": 76960, "loss": 0.277, "lr": 1.1233108108108109e-05, "epoch": 0.4495841995841996, "percentage": 2.25, "elapsed_time": "0:02:25", "remaining_time": "1:45:05", "throughput": 1078.02, "total_tokens": 156320} {"current_steps": 1735, "total_steps": 76960, "loss": 0.2806, "lr": 1.1265592515592515e-05, "epoch": 0.45088357588357586, "percentage": 2.25, "elapsed_time": "0:02:25", "remaining_time": "1:45:05", "throughput": 1078.24, "total_tokens": 156800} {"current_steps": 1740, "total_steps": 76960, "loss": 0.2616, "lr": 1.1298076923076923e-05, "epoch": 0.4521829521829522, "percentage": 2.26, "elapsed_time": "0:02:25", "remaining_time": "1:45:04", "throughput": 1078.34, "total_tokens": 157264} {"current_steps": 1745, "total_steps": 76960, "loss": 0.2893, "lr": 1.1330561330561331e-05, "epoch": 0.4534823284823285, "percentage": 2.27, "elapsed_time": "0:02:26", "remaining_time": "1:45:04", "throughput": 1078.32, "total_tokens": 157712} {"current_steps": 1750, "total_steps": 76960, "loss": 0.3529, "lr": 1.1363045738045739e-05, "epoch": 0.45478170478170477, "percentage": 2.27, "elapsed_time": "0:02:26", "remaining_time": "1:45:03", "throughput": 1078.53, "total_tokens": 158192} {"current_steps": 1755, "total_steps": 76960, "loss": 0.4121, "lr": 1.1395530145530147e-05, "epoch": 0.4560810810810811, "percentage": 2.28, "elapsed_time": "0:02:27", "remaining_time": "1:45:03", "throughput": 1078.41, "total_tokens": 158624} {"current_steps": 1760, "total_steps": 76960, "loss": 0.3055, "lr": 1.1428014553014553e-05, "epoch": 0.4573804573804574, "percentage": 2.29, "elapsed_time": "0:02:27", "remaining_time": "1:45:02", "throughput": 1078.62, "total_tokens": 159104} {"current_steps": 1765, "total_steps": 76960, "loss": 0.415, "lr": 1.1460498960498961e-05, "epoch": 0.45867983367983367, "percentage": 2.29, "elapsed_time": "0:02:27", "remaining_time": "1:45:02", "throughput": 1078.5, "total_tokens": 159536} {"current_steps": 1770, "total_steps": 76960, "loss": 0.2133, "lr": 1.1492983367983369e-05, "epoch": 0.45997920997921, "percentage": 2.3, "elapsed_time": "0:02:28", "remaining_time": "1:45:01", "throughput": 1078.6, "total_tokens": 160000} {"current_steps": 1775, "total_steps": 76960, "loss": 0.2307, "lr": 1.1525467775467775e-05, "epoch": 0.46127858627858626, "percentage": 2.31, "elapsed_time": "0:02:28", "remaining_time": "1:45:01", "throughput": 1078.59, "total_tokens": 160448} {"current_steps": 1780, "total_steps": 76960, "loss": 0.2754, "lr": 1.1557952182952183e-05, "epoch": 0.4625779625779626, "percentage": 2.31, "elapsed_time": "0:02:29", "remaining_time": "1:45:00", "throughput": 1078.57, "total_tokens": 160896} {"current_steps": 1785, "total_steps": 76960, "loss": 0.299, "lr": 1.1590436590436591e-05, "epoch": 0.4638773388773389, "percentage": 2.32, "elapsed_time": "0:02:29", "remaining_time": "1:45:00", "throughput": 1078.63, "total_tokens": 161360} {"current_steps": 1790, "total_steps": 76960, "loss": 0.3227, "lr": 1.1622920997920998e-05, "epoch": 0.46517671517671516, "percentage": 2.33, "elapsed_time": "0:02:30", "remaining_time": "1:44:59", "throughput": 1078.71, "total_tokens": 161824} {"current_steps": 1795, "total_steps": 76960, "loss": 0.3732, "lr": 1.1655405405405405e-05, "epoch": 0.4664760914760915, "percentage": 2.33, "elapsed_time": "0:02:30", "remaining_time": "1:44:59", "throughput": 1078.78, "total_tokens": 162288} {"current_steps": 1800, "total_steps": 76960, "loss": 0.2413, "lr": 1.1687889812889813e-05, "epoch": 0.4677754677754678, "percentage": 2.34, "elapsed_time": "0:02:30", "remaining_time": "1:44:59", "throughput": 1078.97, "total_tokens": 162768} {"current_steps": 1805, "total_steps": 76960, "loss": 0.1531, "lr": 1.1720374220374221e-05, "epoch": 0.46907484407484407, "percentage": 2.35, "elapsed_time": "0:02:31", "remaining_time": "1:44:58", "throughput": 1079.17, "total_tokens": 163248} {"current_steps": 1810, "total_steps": 76960, "loss": 0.4559, "lr": 1.175285862785863e-05, "epoch": 0.4703742203742204, "percentage": 2.35, "elapsed_time": "0:02:31", "remaining_time": "1:44:57", "throughput": 1079.27, "total_tokens": 163712} {"current_steps": 1815, "total_steps": 76960, "loss": 0.3159, "lr": 1.1785343035343036e-05, "epoch": 0.47167359667359665, "percentage": 2.36, "elapsed_time": "0:02:32", "remaining_time": "1:44:57", "throughput": 1079.04, "total_tokens": 164128} {"current_steps": 1820, "total_steps": 76960, "loss": 0.3276, "lr": 1.1817827442827444e-05, "epoch": 0.47297297297297297, "percentage": 2.36, "elapsed_time": "0:02:32", "remaining_time": "1:44:56", "throughput": 1079.04, "total_tokens": 164576} {"current_steps": 1825, "total_steps": 76960, "loss": 0.3361, "lr": 1.1850311850311852e-05, "epoch": 0.4742723492723493, "percentage": 2.37, "elapsed_time": "0:02:32", "remaining_time": "1:44:56", "throughput": 1078.91, "total_tokens": 165008} {"current_steps": 1830, "total_steps": 76960, "loss": 0.2706, "lr": 1.1882796257796258e-05, "epoch": 0.47557172557172556, "percentage": 2.38, "elapsed_time": "0:02:33", "remaining_time": "1:44:55", "throughput": 1078.9, "total_tokens": 165456} {"current_steps": 1835, "total_steps": 76960, "loss": 0.2236, "lr": 1.1915280665280666e-05, "epoch": 0.4768711018711019, "percentage": 2.38, "elapsed_time": "0:02:33", "remaining_time": "1:44:55", "throughput": 1078.78, "total_tokens": 165888} {"current_steps": 1840, "total_steps": 76960, "loss": 0.3084, "lr": 1.1947765072765072e-05, "epoch": 0.4781704781704782, "percentage": 2.39, "elapsed_time": "0:02:34", "remaining_time": "1:44:55", "throughput": 1078.66, "total_tokens": 166320} {"current_steps": 1845, "total_steps": 76960, "loss": 0.2556, "lr": 1.198024948024948e-05, "epoch": 0.47946985446985446, "percentage": 2.4, "elapsed_time": "0:02:34", "remaining_time": "1:44:54", "throughput": 1078.86, "total_tokens": 166800} {"current_steps": 1850, "total_steps": 76960, "loss": 0.2024, "lr": 1.2012733887733888e-05, "epoch": 0.4807692307692308, "percentage": 2.4, "elapsed_time": "0:02:35", "remaining_time": "1:44:53", "throughput": 1078.85, "total_tokens": 167248} {"current_steps": 1855, "total_steps": 76960, "loss": 0.329, "lr": 1.2045218295218296e-05, "epoch": 0.48206860706860705, "percentage": 2.41, "elapsed_time": "0:02:35", "remaining_time": "1:44:53", "throughput": 1078.74, "total_tokens": 167680} {"current_steps": 1860, "total_steps": 76960, "loss": 0.1667, "lr": 1.2077702702702704e-05, "epoch": 0.48336798336798337, "percentage": 2.42, "elapsed_time": "0:02:35", "remaining_time": "1:44:52", "throughput": 1078.64, "total_tokens": 168112} {"current_steps": 1865, "total_steps": 76960, "loss": 0.3772, "lr": 1.2110187110187112e-05, "epoch": 0.4846673596673597, "percentage": 2.42, "elapsed_time": "0:02:36", "remaining_time": "1:44:52", "throughput": 1078.74, "total_tokens": 168576} {"current_steps": 1870, "total_steps": 76960, "loss": 0.3344, "lr": 1.2142671517671518e-05, "epoch": 0.48596673596673595, "percentage": 2.43, "elapsed_time": "0:02:36", "remaining_time": "1:44:51", "throughput": 1078.73, "total_tokens": 169024} {"current_steps": 1875, "total_steps": 76960, "loss": 0.2381, "lr": 1.2175155925155926e-05, "epoch": 0.4872661122661123, "percentage": 2.44, "elapsed_time": "0:02:37", "remaining_time": "1:44:51", "throughput": 1078.52, "total_tokens": 169440} {"current_steps": 1880, "total_steps": 76960, "loss": 0.3043, "lr": 1.2207640332640332e-05, "epoch": 0.4885654885654886, "percentage": 2.44, "elapsed_time": "0:02:37", "remaining_time": "1:44:50", "throughput": 1078.52, "total_tokens": 169888} {"current_steps": 1885, "total_steps": 76960, "loss": 0.3004, "lr": 1.224012474012474e-05, "epoch": 0.48986486486486486, "percentage": 2.45, "elapsed_time": "0:02:37", "remaining_time": "1:44:50", "throughput": 1078.52, "total_tokens": 170336} {"current_steps": 1890, "total_steps": 76960, "loss": 0.2659, "lr": 1.2272609147609148e-05, "epoch": 0.4911642411642412, "percentage": 2.46, "elapsed_time": "0:02:38", "remaining_time": "1:44:49", "throughput": 1078.61, "total_tokens": 170800} {"current_steps": 1895, "total_steps": 76960, "loss": 0.249, "lr": 1.2305093555093555e-05, "epoch": 0.49246361746361744, "percentage": 2.46, "elapsed_time": "0:02:38", "remaining_time": "1:44:49", "throughput": 1078.71, "total_tokens": 171264} {"current_steps": 1900, "total_steps": 76960, "loss": 0.2863, "lr": 1.2337577962577962e-05, "epoch": 0.49376299376299376, "percentage": 2.47, "elapsed_time": "0:02:39", "remaining_time": "1:44:48", "throughput": 1078.8, "total_tokens": 171728} {"current_steps": 1905, "total_steps": 76960, "loss": 0.3674, "lr": 1.2370062370062372e-05, "epoch": 0.4950623700623701, "percentage": 2.48, "elapsed_time": "0:02:39", "remaining_time": "1:44:48", "throughput": 1078.8, "total_tokens": 172176} {"current_steps": 1910, "total_steps": 76960, "loss": 0.3861, "lr": 1.2402546777546778e-05, "epoch": 0.49636174636174635, "percentage": 2.48, "elapsed_time": "0:02:40", "remaining_time": "1:44:47", "throughput": 1078.58, "total_tokens": 172592} {"current_steps": 1915, "total_steps": 76960, "loss": 0.8701, "lr": 1.2435031185031186e-05, "epoch": 0.49766112266112267, "percentage": 2.49, "elapsed_time": "0:02:40", "remaining_time": "1:44:47", "throughput": 1078.68, "total_tokens": 173056} {"current_steps": 1920, "total_steps": 76960, "loss": 0.2721, "lr": 1.2467515592515593e-05, "epoch": 0.498960498960499, "percentage": 2.49, "elapsed_time": "0:02:40", "remaining_time": "1:44:46", "throughput": 1078.76, "total_tokens": 173520} {"current_steps": 1925, "total_steps": 76960, "loss": 0.323, "lr": 1.25e-05, "epoch": 0.5002598752598753, "percentage": 2.5, "elapsed_time": "0:02:41", "remaining_time": "1:44:46", "throughput": 1078.74, "total_tokens": 173968} {"current_steps": 1930, "total_steps": 76960, "loss": 0.3638, "lr": 1.2532484407484407e-05, "epoch": 0.5015592515592515, "percentage": 2.51, "elapsed_time": "0:02:41", "remaining_time": "1:44:45", "throughput": 1078.83, "total_tokens": 174432} {"current_steps": 1935, "total_steps": 76960, "loss": 0.2279, "lr": 1.2564968814968817e-05, "epoch": 0.5028586278586279, "percentage": 2.51, "elapsed_time": "0:02:42", "remaining_time": "1:44:45", "throughput": 1078.93, "total_tokens": 174896} {"current_steps": 1940, "total_steps": 76960, "loss": 0.4306, "lr": 1.2597453222453223e-05, "epoch": 0.5041580041580042, "percentage": 2.52, "elapsed_time": "0:02:42", "remaining_time": "1:44:44", "throughput": 1078.82, "total_tokens": 175328} {"current_steps": 1945, "total_steps": 76960, "loss": 0.2341, "lr": 1.2629937629937629e-05, "epoch": 0.5054573804573804, "percentage": 2.53, "elapsed_time": "0:02:42", "remaining_time": "1:44:44", "throughput": 1078.91, "total_tokens": 175792} {"current_steps": 1950, "total_steps": 76960, "loss": 0.2839, "lr": 1.2662422037422039e-05, "epoch": 0.5067567567567568, "percentage": 2.53, "elapsed_time": "0:02:43", "remaining_time": "1:44:43", "throughput": 1078.91, "total_tokens": 176240} {"current_steps": 1955, "total_steps": 76960, "loss": 0.1848, "lr": 1.2694906444906447e-05, "epoch": 0.5080561330561331, "percentage": 2.54, "elapsed_time": "0:02:43", "remaining_time": "1:44:43", "throughput": 1078.79, "total_tokens": 176672} {"current_steps": 1960, "total_steps": 76960, "loss": 0.2749, "lr": 1.2727390852390853e-05, "epoch": 0.5093555093555093, "percentage": 2.55, "elapsed_time": "0:02:44", "remaining_time": "1:44:42", "throughput": 1078.98, "total_tokens": 177152} {"current_steps": 1965, "total_steps": 76960, "loss": 0.1397, "lr": 1.275987525987526e-05, "epoch": 0.5106548856548857, "percentage": 2.55, "elapsed_time": "0:02:44", "remaining_time": "1:44:42", "throughput": 1078.76, "total_tokens": 177568} {"current_steps": 1970, "total_steps": 76960, "loss": 0.2573, "lr": 1.2792359667359669e-05, "epoch": 0.511954261954262, "percentage": 2.56, "elapsed_time": "0:02:45", "remaining_time": "1:44:41", "throughput": 1078.64, "total_tokens": 178000} {"current_steps": 1975, "total_steps": 76960, "loss": 0.2861, "lr": 1.2824844074844075e-05, "epoch": 0.5132536382536382, "percentage": 2.57, "elapsed_time": "0:02:45", "remaining_time": "1:44:41", "throughput": 1078.6, "total_tokens": 178448} {"current_steps": 1980, "total_steps": 76960, "loss": 0.2399, "lr": 1.2857328482328481e-05, "epoch": 0.5145530145530145, "percentage": 2.57, "elapsed_time": "0:02:45", "remaining_time": "1:44:40", "throughput": 1078.59, "total_tokens": 178896} {"current_steps": 1985, "total_steps": 76960, "loss": 0.3686, "lr": 1.2889812889812891e-05, "epoch": 0.5158523908523909, "percentage": 2.58, "elapsed_time": "0:02:46", "remaining_time": "1:44:40", "throughput": 1078.58, "total_tokens": 179344} {"current_steps": 1990, "total_steps": 76960, "loss": 0.3409, "lr": 1.2922297297297297e-05, "epoch": 0.5171517671517671, "percentage": 2.59, "elapsed_time": "0:02:46", "remaining_time": "1:44:39", "throughput": 1078.87, "total_tokens": 179840} {"current_steps": 1995, "total_steps": 76960, "loss": 0.1412, "lr": 1.2954781704781704e-05, "epoch": 0.5184511434511434, "percentage": 2.59, "elapsed_time": "0:02:47", "remaining_time": "1:44:39", "throughput": 1078.75, "total_tokens": 180272} {"current_steps": 2000, "total_steps": 76960, "loss": 0.4739, "lr": 1.2987266112266113e-05, "epoch": 0.5197505197505198, "percentage": 2.6, "elapsed_time": "0:02:47", "remaining_time": "1:44:38", "throughput": 1078.84, "total_tokens": 180736} {"current_steps": 2005, "total_steps": 76960, "loss": 0.3564, "lr": 1.3019750519750521e-05, "epoch": 0.521049896049896, "percentage": 2.61, "elapsed_time": "0:02:47", "remaining_time": "1:44:38", "throughput": 1078.82, "total_tokens": 181184} {"current_steps": 2010, "total_steps": 76960, "loss": 0.2737, "lr": 1.3052234927234927e-05, "epoch": 0.5223492723492723, "percentage": 2.61, "elapsed_time": "0:02:48", "remaining_time": "1:44:38", "throughput": 1078.9, "total_tokens": 181648} {"current_steps": 2015, "total_steps": 76960, "loss": 0.3817, "lr": 1.3084719334719337e-05, "epoch": 0.5236486486486487, "percentage": 2.62, "elapsed_time": "0:02:48", "remaining_time": "1:44:37", "throughput": 1078.99, "total_tokens": 182112} {"current_steps": 2020, "total_steps": 76960, "loss": 0.34, "lr": 1.3117203742203743e-05, "epoch": 0.524948024948025, "percentage": 2.62, "elapsed_time": "0:02:49", "remaining_time": "1:44:37", "throughput": 1078.89, "total_tokens": 182544} {"current_steps": 2025, "total_steps": 76960, "loss": 0.2985, "lr": 1.314968814968815e-05, "epoch": 0.5262474012474012, "percentage": 2.63, "elapsed_time": "0:02:49", "remaining_time": "1:44:36", "throughput": 1078.68, "total_tokens": 182960} {"current_steps": 2030, "total_steps": 76960, "loss": 0.2667, "lr": 1.318217255717256e-05, "epoch": 0.5275467775467776, "percentage": 2.64, "elapsed_time": "0:02:50", "remaining_time": "1:44:36", "throughput": 1078.58, "total_tokens": 183392} {"current_steps": 2035, "total_steps": 76960, "loss": 0.2259, "lr": 1.3214656964656966e-05, "epoch": 0.5288461538461539, "percentage": 2.64, "elapsed_time": "0:02:50", "remaining_time": "1:44:35", "throughput": 1078.66, "total_tokens": 183856} {"current_steps": 2040, "total_steps": 76960, "loss": 0.2233, "lr": 1.3247141372141372e-05, "epoch": 0.5301455301455301, "percentage": 2.65, "elapsed_time": "0:02:50", "remaining_time": "1:44:35", "throughput": 1078.74, "total_tokens": 184320} {"current_steps": 2045, "total_steps": 76960, "loss": 0.3215, "lr": 1.3279625779625778e-05, "epoch": 0.5314449064449065, "percentage": 2.66, "elapsed_time": "0:02:51", "remaining_time": "1:44:34", "throughput": 1078.64, "total_tokens": 184752} {"current_steps": 2050, "total_steps": 76960, "loss": 0.1922, "lr": 1.3312110187110188e-05, "epoch": 0.5327442827442828, "percentage": 2.66, "elapsed_time": "0:02:51", "remaining_time": "1:44:34", "throughput": 1078.63, "total_tokens": 185200} {"current_steps": 2055, "total_steps": 76960, "loss": 0.3431, "lr": 1.3344594594594596e-05, "epoch": 0.534043659043659, "percentage": 2.67, "elapsed_time": "0:02:52", "remaining_time": "1:44:33", "throughput": 1078.52, "total_tokens": 185632} {"current_steps": 2060, "total_steps": 76960, "loss": 0.2792, "lr": 1.3377079002079002e-05, "epoch": 0.5353430353430353, "percentage": 2.68, "elapsed_time": "0:02:52", "remaining_time": "1:44:33", "throughput": 1078.42, "total_tokens": 186064} {"current_steps": 2065, "total_steps": 76960, "loss": 0.2746, "lr": 1.3409563409563412e-05, "epoch": 0.5366424116424117, "percentage": 2.68, "elapsed_time": "0:02:52", "remaining_time": "1:44:32", "throughput": 1078.23, "total_tokens": 186480} {"current_steps": 2070, "total_steps": 76960, "loss": 0.2795, "lr": 1.3442047817047818e-05, "epoch": 0.5379417879417879, "percentage": 2.69, "elapsed_time": "0:02:53", "remaining_time": "1:44:32", "throughput": 1078.2, "total_tokens": 186928} {"current_steps": 2075, "total_steps": 76960, "loss": 0.2861, "lr": 1.3474532224532224e-05, "epoch": 0.5392411642411642, "percentage": 2.7, "elapsed_time": "0:02:53", "remaining_time": "1:44:31", "throughput": 1078.29, "total_tokens": 187392} {"current_steps": 2080, "total_steps": 76960, "loss": 0.405, "lr": 1.3507016632016634e-05, "epoch": 0.5405405405405406, "percentage": 2.7, "elapsed_time": "0:02:54", "remaining_time": "1:44:31", "throughput": 1078.28, "total_tokens": 187840} {"current_steps": 2085, "total_steps": 76960, "loss": 0.3071, "lr": 1.353950103950104e-05, "epoch": 0.5418399168399168, "percentage": 2.71, "elapsed_time": "0:02:54", "remaining_time": "1:44:30", "throughput": 1078.45, "total_tokens": 188320} {"current_steps": 2090, "total_steps": 76960, "loss": 0.1696, "lr": 1.3571985446985446e-05, "epoch": 0.5431392931392931, "percentage": 2.72, "elapsed_time": "0:02:55", "remaining_time": "1:44:30", "throughput": 1078.53, "total_tokens": 188784} {"current_steps": 2095, "total_steps": 76960, "loss": 0.2452, "lr": 1.3604469854469856e-05, "epoch": 0.5444386694386695, "percentage": 2.72, "elapsed_time": "0:02:55", "remaining_time": "1:44:29", "throughput": 1078.43, "total_tokens": 189216} {"current_steps": 2100, "total_steps": 76960, "loss": 0.321, "lr": 1.3636954261954262e-05, "epoch": 0.5457380457380457, "percentage": 2.73, "elapsed_time": "0:02:55", "remaining_time": "1:44:29", "throughput": 1078.33, "total_tokens": 189648} {"current_steps": 2105, "total_steps": 76960, "loss": 0.498, "lr": 1.366943866943867e-05, "epoch": 0.547037422037422, "percentage": 2.74, "elapsed_time": "0:02:56", "remaining_time": "1:44:28", "throughput": 1078.32, "total_tokens": 190096} {"current_steps": 2110, "total_steps": 76960, "loss": 0.5702, "lr": 1.3701923076923078e-05, "epoch": 0.5483367983367984, "percentage": 2.74, "elapsed_time": "0:02:56", "remaining_time": "1:44:28", "throughput": 1078.58, "total_tokens": 190592} {"current_steps": 2115, "total_steps": 76960, "loss": 0.0351, "lr": 1.3734407484407486e-05, "epoch": 0.5496361746361746, "percentage": 2.75, "elapsed_time": "0:02:57", "remaining_time": "1:44:27", "throughput": 1078.48, "total_tokens": 191024} {"current_steps": 2120, "total_steps": 76960, "loss": 0.4396, "lr": 1.3766891891891892e-05, "epoch": 0.5509355509355509, "percentage": 2.75, "elapsed_time": "0:02:57", "remaining_time": "1:44:27", "throughput": 1078.37, "total_tokens": 191456} {"current_steps": 2125, "total_steps": 76960, "loss": 0.2458, "lr": 1.3799376299376299e-05, "epoch": 0.5522349272349273, "percentage": 2.76, "elapsed_time": "0:02:57", "remaining_time": "1:44:27", "throughput": 1078.44, "total_tokens": 191920} {"current_steps": 2130, "total_steps": 76960, "loss": 0.3172, "lr": 1.3831860706860708e-05, "epoch": 0.5535343035343036, "percentage": 2.77, "elapsed_time": "0:02:58", "remaining_time": "1:44:26", "throughput": 1078.53, "total_tokens": 192384} {"current_steps": 2135, "total_steps": 76960, "loss": 0.3236, "lr": 1.3864345114345115e-05, "epoch": 0.5548336798336798, "percentage": 2.77, "elapsed_time": "0:02:58", "remaining_time": "1:44:26", "throughput": 1078.61, "total_tokens": 192848} {"current_steps": 2140, "total_steps": 76960, "loss": 0.2624, "lr": 1.3896829521829521e-05, "epoch": 0.5561330561330561, "percentage": 2.78, "elapsed_time": "0:02:59", "remaining_time": "1:44:25", "throughput": 1078.96, "total_tokens": 193360} {"current_steps": 2145, "total_steps": 76960, "loss": 0.2816, "lr": 1.392931392931393e-05, "epoch": 0.5574324324324325, "percentage": 2.79, "elapsed_time": "0:02:59", "remaining_time": "1:44:25", "throughput": 1078.86, "total_tokens": 193792} {"current_steps": 2150, "total_steps": 76960, "loss": 0.2969, "lr": 1.3961798336798337e-05, "epoch": 0.5587318087318087, "percentage": 2.79, "elapsed_time": "0:03:00", "remaining_time": "1:44:24", "throughput": 1078.93, "total_tokens": 194256} {"current_steps": 2155, "total_steps": 76960, "loss": 0.2895, "lr": 1.3994282744282745e-05, "epoch": 0.560031185031185, "percentage": 2.8, "elapsed_time": "0:03:00", "remaining_time": "1:44:24", "throughput": 1079.04, "total_tokens": 194736} {"current_steps": 2160, "total_steps": 76960, "loss": 0.307, "lr": 1.4026767151767153e-05, "epoch": 0.5613305613305614, "percentage": 2.81, "elapsed_time": "0:03:00", "remaining_time": "1:44:24", "throughput": 1079.03, "total_tokens": 195184} {"current_steps": 2165, "total_steps": 76960, "loss": 0.3648, "lr": 1.405925155925156e-05, "epoch": 0.5626299376299376, "percentage": 2.81, "elapsed_time": "0:03:01", "remaining_time": "1:44:23", "throughput": 1079.02, "total_tokens": 195632} {"current_steps": 2170, "total_steps": 76960, "loss": 0.2859, "lr": 1.4091735966735967e-05, "epoch": 0.5639293139293139, "percentage": 2.82, "elapsed_time": "0:03:01", "remaining_time": "1:44:23", "throughput": 1078.82, "total_tokens": 196048} {"current_steps": 2175, "total_steps": 76960, "loss": 0.2661, "lr": 1.4124220374220377e-05, "epoch": 0.5652286902286903, "percentage": 2.83, "elapsed_time": "0:03:02", "remaining_time": "1:44:22", "throughput": 1078.72, "total_tokens": 196480} {"current_steps": 2180, "total_steps": 76960, "loss": 0.296, "lr": 1.4156704781704783e-05, "epoch": 0.5665280665280665, "percentage": 2.83, "elapsed_time": "0:03:02", "remaining_time": "1:44:22", "throughput": 1078.61, "total_tokens": 196912} {"current_steps": 2185, "total_steps": 76960, "loss": 0.26, "lr": 1.4189189189189189e-05, "epoch": 0.5678274428274428, "percentage": 2.84, "elapsed_time": "0:03:02", "remaining_time": "1:44:21", "throughput": 1078.69, "total_tokens": 197376} {"current_steps": 2190, "total_steps": 76960, "loss": 0.2552, "lr": 1.4221673596673599e-05, "epoch": 0.5691268191268192, "percentage": 2.85, "elapsed_time": "0:03:03", "remaining_time": "1:44:21", "throughput": 1078.59, "total_tokens": 197808} {"current_steps": 2195, "total_steps": 76960, "loss": 0.2951, "lr": 1.4254158004158005e-05, "epoch": 0.5704261954261954, "percentage": 2.85, "elapsed_time": "0:03:03", "remaining_time": "1:44:20", "throughput": 1078.57, "total_tokens": 198256} {"current_steps": 2200, "total_steps": 76960, "loss": 0.2793, "lr": 1.4286642411642411e-05, "epoch": 0.5717255717255717, "percentage": 2.86, "elapsed_time": "0:03:04", "remaining_time": "1:44:20", "throughput": 1078.56, "total_tokens": 198704} {"current_steps": 2205, "total_steps": 76960, "loss": 0.2825, "lr": 1.431912681912682e-05, "epoch": 0.5730249480249481, "percentage": 2.87, "elapsed_time": "0:03:04", "remaining_time": "1:44:20", "throughput": 1078.47, "total_tokens": 199136} {"current_steps": 2210, "total_steps": 76960, "loss": 0.2904, "lr": 1.4351611226611227e-05, "epoch": 0.5743243243243243, "percentage": 2.87, "elapsed_time": "0:03:05", "remaining_time": "1:44:19", "throughput": 1078.37, "total_tokens": 199568} {"current_steps": 2215, "total_steps": 76960, "loss": 0.2855, "lr": 1.4384095634095635e-05, "epoch": 0.5756237006237006, "percentage": 2.88, "elapsed_time": "0:03:05", "remaining_time": "1:44:19", "throughput": 1078.36, "total_tokens": 200016} {"current_steps": 2220, "total_steps": 76960, "loss": 0.2436, "lr": 1.4416580041580041e-05, "epoch": 0.5769230769230769, "percentage": 2.88, "elapsed_time": "0:03:05", "remaining_time": "1:44:18", "throughput": 1078.44, "total_tokens": 200480} {"current_steps": 2225, "total_steps": 76960, "loss": 0.2525, "lr": 1.4449064449064451e-05, "epoch": 0.5782224532224532, "percentage": 2.89, "elapsed_time": "0:03:06", "remaining_time": "1:44:18", "throughput": 1078.6, "total_tokens": 200960} {"current_steps": 2230, "total_steps": 76960, "loss": 0.2779, "lr": 1.4481548856548857e-05, "epoch": 0.5795218295218295, "percentage": 2.9, "elapsed_time": "0:03:06", "remaining_time": "1:44:17", "throughput": 1078.51, "total_tokens": 201392} {"current_steps": 2235, "total_steps": 76960, "loss": 0.3055, "lr": 1.4514033264033264e-05, "epoch": 0.5808212058212058, "percentage": 2.9, "elapsed_time": "0:03:07", "remaining_time": "1:44:17", "throughput": 1078.5, "total_tokens": 201840} {"current_steps": 2240, "total_steps": 76960, "loss": 0.2275, "lr": 1.4546517671517673e-05, "epoch": 0.5821205821205822, "percentage": 2.91, "elapsed_time": "0:03:07", "remaining_time": "1:44:16", "throughput": 1078.75, "total_tokens": 202336} {"current_steps": 2245, "total_steps": 76960, "loss": 0.2669, "lr": 1.457900207900208e-05, "epoch": 0.5834199584199584, "percentage": 2.92, "elapsed_time": "0:03:07", "remaining_time": "1:44:16", "throughput": 1078.66, "total_tokens": 202768} {"current_steps": 2250, "total_steps": 76960, "loss": 0.1707, "lr": 1.4611486486486486e-05, "epoch": 0.5847193347193347, "percentage": 2.92, "elapsed_time": "0:03:08", "remaining_time": "1:44:15", "throughput": 1078.57, "total_tokens": 203200} {"current_steps": 2255, "total_steps": 76960, "loss": 0.3244, "lr": 1.4643970893970896e-05, "epoch": 0.5860187110187111, "percentage": 2.93, "elapsed_time": "0:03:08", "remaining_time": "1:44:15", "throughput": 1078.49, "total_tokens": 203632} {"current_steps": 2260, "total_steps": 76960, "loss": 0.2726, "lr": 1.4676455301455302e-05, "epoch": 0.5873180873180873, "percentage": 2.94, "elapsed_time": "0:03:09", "remaining_time": "1:44:14", "throughput": 1078.57, "total_tokens": 204096} {"current_steps": 2265, "total_steps": 76960, "loss": 0.3612, "lr": 1.470893970893971e-05, "epoch": 0.5886174636174636, "percentage": 2.94, "elapsed_time": "0:03:09", "remaining_time": "1:44:14", "throughput": 1078.39, "total_tokens": 204512} {"current_steps": 2270, "total_steps": 76960, "loss": 0.2707, "lr": 1.4741424116424118e-05, "epoch": 0.58991683991684, "percentage": 2.95, "elapsed_time": "0:03:10", "remaining_time": "1:44:13", "throughput": 1078.39, "total_tokens": 204960} {"current_steps": 2275, "total_steps": 76960, "loss": 0.2752, "lr": 1.4773908523908526e-05, "epoch": 0.5912162162162162, "percentage": 2.96, "elapsed_time": "0:03:10", "remaining_time": "1:44:13", "throughput": 1078.3, "total_tokens": 205392} {"current_steps": 2280, "total_steps": 76960, "loss": 0.281, "lr": 1.4806392931392932e-05, "epoch": 0.5925155925155925, "percentage": 2.96, "elapsed_time": "0:03:10", "remaining_time": "1:44:12", "throughput": 1078.22, "total_tokens": 205824} {"current_steps": 2285, "total_steps": 76960, "loss": 0.2309, "lr": 1.4838877338877338e-05, "epoch": 0.5938149688149689, "percentage": 2.97, "elapsed_time": "0:03:11", "remaining_time": "1:44:12", "throughput": 1078.13, "total_tokens": 206256} {"current_steps": 2290, "total_steps": 76960, "loss": 0.2677, "lr": 1.4871361746361748e-05, "epoch": 0.5951143451143451, "percentage": 2.98, "elapsed_time": "0:03:11", "remaining_time": "1:44:11", "throughput": 1078.04, "total_tokens": 206688} {"current_steps": 2295, "total_steps": 76960, "loss": 0.1679, "lr": 1.4903846153846154e-05, "epoch": 0.5964137214137214, "percentage": 2.98, "elapsed_time": "0:03:12", "remaining_time": "1:44:11", "throughput": 1078.02, "total_tokens": 207136} {"current_steps": 2300, "total_steps": 76960, "loss": 0.3869, "lr": 1.493633056133056e-05, "epoch": 0.5977130977130977, "percentage": 2.99, "elapsed_time": "0:03:12", "remaining_time": "1:44:10", "throughput": 1078.02, "total_tokens": 207584} {"current_steps": 2305, "total_steps": 76960, "loss": 0.4048, "lr": 1.496881496881497e-05, "epoch": 0.599012474012474, "percentage": 3.0, "elapsed_time": "0:03:12", "remaining_time": "1:44:10", "throughput": 1078.26, "total_tokens": 208080} {"current_steps": 2310, "total_steps": 76960, "loss": 0.3918, "lr": 1.5001299376299376e-05, "epoch": 0.6003118503118503, "percentage": 3.0, "elapsed_time": "0:03:13", "remaining_time": "1:44:09", "throughput": 1078.24, "total_tokens": 208528} {"current_steps": 2315, "total_steps": 76960, "loss": 0.1838, "lr": 1.5033783783783784e-05, "epoch": 0.6016112266112266, "percentage": 3.01, "elapsed_time": "0:03:13", "remaining_time": "1:44:09", "throughput": 1078.22, "total_tokens": 208976} {"current_steps": 2320, "total_steps": 76960, "loss": 0.3114, "lr": 1.5066268191268192e-05, "epoch": 0.6029106029106029, "percentage": 3.01, "elapsed_time": "0:03:14", "remaining_time": "1:44:08", "throughput": 1078.14, "total_tokens": 209408} {"current_steps": 2325, "total_steps": 76960, "loss": 0.2641, "lr": 1.50987525987526e-05, "epoch": 0.6042099792099792, "percentage": 3.02, "elapsed_time": "0:03:14", "remaining_time": "1:44:08", "throughput": 1078.14, "total_tokens": 209856} {"current_steps": 2330, "total_steps": 76960, "loss": 0.2606, "lr": 1.5131237006237006e-05, "epoch": 0.6055093555093555, "percentage": 3.03, "elapsed_time": "0:03:15", "remaining_time": "1:44:07", "throughput": 1078.21, "total_tokens": 210320} {"current_steps": 2335, "total_steps": 76960, "loss": 0.1884, "lr": 1.5163721413721416e-05, "epoch": 0.6068087318087318, "percentage": 3.03, "elapsed_time": "0:03:15", "remaining_time": "1:44:07", "throughput": 1078.02, "total_tokens": 210736} {"current_steps": 2340, "total_steps": 76960, "loss": 0.3068, "lr": 1.5196205821205822e-05, "epoch": 0.6081081081081081, "percentage": 3.04, "elapsed_time": "0:03:15", "remaining_time": "1:44:07", "throughput": 1077.93, "total_tokens": 211168} {"current_steps": 2345, "total_steps": 76960, "loss": 0.4991, "lr": 1.5228690228690229e-05, "epoch": 0.6094074844074844, "percentage": 3.05, "elapsed_time": "0:03:16", "remaining_time": "1:44:06", "throughput": 1077.92, "total_tokens": 211616} {"current_steps": 2350, "total_steps": 76960, "loss": 0.3685, "lr": 1.5261174636174637e-05, "epoch": 0.6107068607068608, "percentage": 3.05, "elapsed_time": "0:03:16", "remaining_time": "1:44:06", "throughput": 1077.75, "total_tokens": 212032} {"current_steps": 2355, "total_steps": 76960, "loss": 0.3447, "lr": 1.5293659043659046e-05, "epoch": 0.612006237006237, "percentage": 3.06, "elapsed_time": "0:03:17", "remaining_time": "1:44:05", "throughput": 1077.91, "total_tokens": 212512} {"current_steps": 2360, "total_steps": 76960, "loss": 0.2675, "lr": 1.5326143451143453e-05, "epoch": 0.6133056133056133, "percentage": 3.07, "elapsed_time": "0:03:17", "remaining_time": "1:44:05", "throughput": 1077.99, "total_tokens": 212976} {"current_steps": 2365, "total_steps": 76960, "loss": 0.2879, "lr": 1.535862785862786e-05, "epoch": 0.6146049896049897, "percentage": 3.07, "elapsed_time": "0:03:17", "remaining_time": "1:44:04", "throughput": 1077.99, "total_tokens": 213424} {"current_steps": 2370, "total_steps": 76960, "loss": 0.2646, "lr": 1.539111226611227e-05, "epoch": 0.6159043659043659, "percentage": 3.08, "elapsed_time": "0:03:18", "remaining_time": "1:44:04", "throughput": 1078.0, "total_tokens": 213872} {"current_steps": 2375, "total_steps": 76960, "loss": 0.3186, "lr": 1.5423596673596675e-05, "epoch": 0.6172037422037422, "percentage": 3.09, "elapsed_time": "0:03:18", "remaining_time": "1:44:03", "throughput": 1077.92, "total_tokens": 214304} {"current_steps": 2380, "total_steps": 76960, "loss": 0.313, "lr": 1.545608108108108e-05, "epoch": 0.6185031185031185, "percentage": 3.09, "elapsed_time": "0:03:19", "remaining_time": "1:44:03", "throughput": 1077.9, "total_tokens": 214752} {"current_steps": 2385, "total_steps": 76960, "loss": 0.3159, "lr": 1.548856548856549e-05, "epoch": 0.6198024948024948, "percentage": 3.1, "elapsed_time": "0:03:19", "remaining_time": "1:44:02", "throughput": 1077.73, "total_tokens": 215168} {"current_steps": 2390, "total_steps": 76960, "loss": 0.2671, "lr": 1.5521049896049897e-05, "epoch": 0.6211018711018711, "percentage": 3.11, "elapsed_time": "0:03:20", "remaining_time": "1:44:02", "throughput": 1077.64, "total_tokens": 215600} {"current_steps": 2395, "total_steps": 76960, "loss": 0.3111, "lr": 1.5553534303534303e-05, "epoch": 0.6224012474012474, "percentage": 3.11, "elapsed_time": "0:03:20", "remaining_time": "1:44:01", "throughput": 1077.64, "total_tokens": 216048} {"current_steps": 2400, "total_steps": 76960, "loss": 0.2897, "lr": 1.5586018711018713e-05, "epoch": 0.6237006237006237, "percentage": 3.12, "elapsed_time": "0:03:20", "remaining_time": "1:44:01", "throughput": 1077.71, "total_tokens": 216512} {"current_steps": 2405, "total_steps": 76960, "loss": 0.2516, "lr": 1.561850311850312e-05, "epoch": 0.625, "percentage": 3.12, "elapsed_time": "0:03:21", "remaining_time": "1:44:00", "throughput": 1077.78, "total_tokens": 216976} {"current_steps": 2410, "total_steps": 76960, "loss": 0.297, "lr": 1.5650987525987525e-05, "epoch": 0.6262993762993763, "percentage": 3.13, "elapsed_time": "0:03:21", "remaining_time": "1:44:00", "throughput": 1077.86, "total_tokens": 217440} {"current_steps": 2415, "total_steps": 76960, "loss": 0.2932, "lr": 1.5683471933471935e-05, "epoch": 0.6275987525987526, "percentage": 3.14, "elapsed_time": "0:03:22", "remaining_time": "1:43:59", "throughput": 1078.02, "total_tokens": 217920} {"current_steps": 2420, "total_steps": 76960, "loss": 0.2659, "lr": 1.571595634095634e-05, "epoch": 0.6288981288981289, "percentage": 3.14, "elapsed_time": "0:03:22", "remaining_time": "1:43:59", "throughput": 1078.01, "total_tokens": 218368} {"current_steps": 2425, "total_steps": 76960, "loss": 0.2178, "lr": 1.5748440748440748e-05, "epoch": 0.6301975051975052, "percentage": 3.15, "elapsed_time": "0:03:22", "remaining_time": "1:43:58", "throughput": 1078.08, "total_tokens": 218832} {"current_steps": 2430, "total_steps": 76960, "loss": 0.3335, "lr": 1.5780925155925154e-05, "epoch": 0.6314968814968815, "percentage": 3.16, "elapsed_time": "0:03:23", "remaining_time": "1:43:58", "throughput": 1078.23, "total_tokens": 219312} {"current_steps": 2435, "total_steps": 76960, "loss": 0.251, "lr": 1.5813409563409563e-05, "epoch": 0.6327962577962578, "percentage": 3.16, "elapsed_time": "0:03:23", "remaining_time": "1:43:57", "throughput": 1078.3, "total_tokens": 219776} {"current_steps": 2440, "total_steps": 76960, "loss": 0.1823, "lr": 1.584589397089397e-05, "epoch": 0.6340956340956341, "percentage": 3.17, "elapsed_time": "0:03:24", "remaining_time": "1:43:57", "throughput": 1078.29, "total_tokens": 220224} {"current_steps": 2445, "total_steps": 76960, "loss": 0.2453, "lr": 1.587837837837838e-05, "epoch": 0.6353950103950103, "percentage": 3.18, "elapsed_time": "0:03:24", "remaining_time": "1:43:57", "throughput": 1078.28, "total_tokens": 220672} {"current_steps": 2450, "total_steps": 76960, "loss": 0.2864, "lr": 1.591086278586279e-05, "epoch": 0.6366943866943867, "percentage": 3.18, "elapsed_time": "0:03:25", "remaining_time": "1:43:56", "throughput": 1078.28, "total_tokens": 221120} {"current_steps": 2455, "total_steps": 76960, "loss": 0.2455, "lr": 1.5943347193347195e-05, "epoch": 0.637993762993763, "percentage": 3.19, "elapsed_time": "0:03:25", "remaining_time": "1:43:56", "throughput": 1078.12, "total_tokens": 221536} {"current_steps": 2460, "total_steps": 76960, "loss": 0.0644, "lr": 1.59758316008316e-05, "epoch": 0.6392931392931392, "percentage": 3.2, "elapsed_time": "0:03:25", "remaining_time": "1:43:55", "throughput": 1078.12, "total_tokens": 221984} {"current_steps": 2465, "total_steps": 76960, "loss": 0.1486, "lr": 1.600831600831601e-05, "epoch": 0.6405925155925156, "percentage": 3.2, "elapsed_time": "0:03:26", "remaining_time": "1:43:55", "throughput": 1078.12, "total_tokens": 222432} {"current_steps": 2470, "total_steps": 76960, "loss": 0.269, "lr": 1.6040800415800417e-05, "epoch": 0.6418918918918919, "percentage": 3.21, "elapsed_time": "0:03:26", "remaining_time": "1:43:54", "throughput": 1077.95, "total_tokens": 222848} {"current_steps": 2475, "total_steps": 76960, "loss": 0.5511, "lr": 1.6073284823284824e-05, "epoch": 0.6431912681912682, "percentage": 3.22, "elapsed_time": "0:03:27", "remaining_time": "1:43:54", "throughput": 1077.86, "total_tokens": 223280} {"current_steps": 2480, "total_steps": 76960, "loss": 0.4877, "lr": 1.6105769230769233e-05, "epoch": 0.6444906444906445, "percentage": 3.22, "elapsed_time": "0:03:27", "remaining_time": "1:43:53", "throughput": 1077.86, "total_tokens": 223728} {"current_steps": 2485, "total_steps": 76960, "loss": 0.4574, "lr": 1.613825363825364e-05, "epoch": 0.6457900207900208, "percentage": 3.23, "elapsed_time": "0:03:27", "remaining_time": "1:43:53", "throughput": 1077.77, "total_tokens": 224160} {"current_steps": 2490, "total_steps": 76960, "loss": 0.3178, "lr": 1.6170738045738046e-05, "epoch": 0.6470893970893971, "percentage": 3.24, "elapsed_time": "0:03:28", "remaining_time": "1:43:52", "throughput": 1077.77, "total_tokens": 224608} {"current_steps": 2495, "total_steps": 76960, "loss": 0.3177, "lr": 1.6203222453222456e-05, "epoch": 0.6483887733887734, "percentage": 3.24, "elapsed_time": "0:03:28", "remaining_time": "1:43:52", "throughput": 1077.99, "total_tokens": 225104} {"current_steps": 2500, "total_steps": 76960, "loss": 0.3131, "lr": 1.6235706860706862e-05, "epoch": 0.6496881496881497, "percentage": 3.25, "elapsed_time": "0:03:29", "remaining_time": "1:43:51", "throughput": 1077.98, "total_tokens": 225552} {"current_steps": 2505, "total_steps": 76960, "loss": 0.2897, "lr": 1.6268191268191268e-05, "epoch": 0.650987525987526, "percentage": 3.25, "elapsed_time": "0:03:29", "remaining_time": "1:43:51", "throughput": 1078.05, "total_tokens": 226016} {"current_steps": 2510, "total_steps": 76960, "loss": 0.2886, "lr": 1.6300675675675674e-05, "epoch": 0.6522869022869023, "percentage": 3.26, "elapsed_time": "0:03:30", "remaining_time": "1:43:50", "throughput": 1078.12, "total_tokens": 226480} {"current_steps": 2515, "total_steps": 76960, "loss": 0.2637, "lr": 1.6333160083160084e-05, "epoch": 0.6535862785862786, "percentage": 3.27, "elapsed_time": "0:03:30", "remaining_time": "1:43:50", "throughput": 1078.16, "total_tokens": 226944} {"current_steps": 2520, "total_steps": 76960, "loss": 0.25, "lr": 1.636564449064449e-05, "epoch": 0.6548856548856549, "percentage": 3.27, "elapsed_time": "0:03:30", "remaining_time": "1:43:50", "throughput": 1078.15, "total_tokens": 227392} {"current_steps": 2525, "total_steps": 76960, "loss": 0.3504, "lr": 1.6398128898128897e-05, "epoch": 0.6561850311850311, "percentage": 3.28, "elapsed_time": "0:03:31", "remaining_time": "1:43:49", "throughput": 1078.15, "total_tokens": 227840} {"current_steps": 2530, "total_steps": 76960, "loss": 0.234, "lr": 1.6430613305613306e-05, "epoch": 0.6574844074844075, "percentage": 3.29, "elapsed_time": "0:03:31", "remaining_time": "1:43:49", "throughput": 1078.06, "total_tokens": 228272} {"current_steps": 2535, "total_steps": 76960, "loss": 0.2303, "lr": 1.6463097713097712e-05, "epoch": 0.6587837837837838, "percentage": 3.29, "elapsed_time": "0:03:32", "remaining_time": "1:43:48", "throughput": 1078.03, "total_tokens": 228720} {"current_steps": 2540, "total_steps": 76960, "loss": 0.3079, "lr": 1.649558212058212e-05, "epoch": 0.66008316008316, "percentage": 3.3, "elapsed_time": "0:03:32", "remaining_time": "1:43:48", "throughput": 1078.02, "total_tokens": 229168} {"current_steps": 2545, "total_steps": 76960, "loss": 0.3265, "lr": 1.652806652806653e-05, "epoch": 0.6613825363825364, "percentage": 3.31, "elapsed_time": "0:03:32", "remaining_time": "1:43:47", "throughput": 1078.1, "total_tokens": 229632} {"current_steps": 2550, "total_steps": 76960, "loss": 0.2976, "lr": 1.6560550935550938e-05, "epoch": 0.6626819126819127, "percentage": 3.31, "elapsed_time": "0:03:33", "remaining_time": "1:43:47", "throughput": 1077.94, "total_tokens": 230048} {"current_steps": 2555, "total_steps": 76960, "loss": 0.3384, "lr": 1.6593035343035344e-05, "epoch": 0.6639812889812889, "percentage": 3.32, "elapsed_time": "0:03:33", "remaining_time": "1:43:47", "throughput": 1078.08, "total_tokens": 230528} {"current_steps": 2560, "total_steps": 76960, "loss": 0.3049, "lr": 1.6625519750519754e-05, "epoch": 0.6652806652806653, "percentage": 3.33, "elapsed_time": "0:03:34", "remaining_time": "1:43:46", "throughput": 1078.07, "total_tokens": 230976} {"current_steps": 2565, "total_steps": 76960, "loss": 0.2221, "lr": 1.665800415800416e-05, "epoch": 0.6665800415800416, "percentage": 3.33, "elapsed_time": "0:03:34", "remaining_time": "1:43:46", "throughput": 1078.36, "total_tokens": 231488} {"current_steps": 2570, "total_steps": 76960, "loss": 0.2649, "lr": 1.6690488565488567e-05, "epoch": 0.6678794178794178, "percentage": 3.34, "elapsed_time": "0:03:35", "remaining_time": "1:43:45", "throughput": 1078.57, "total_tokens": 231984} {"current_steps": 2575, "total_steps": 76960, "loss": 0.388, "lr": 1.6722972972972976e-05, "epoch": 0.6691787941787942, "percentage": 3.35, "elapsed_time": "0:03:35", "remaining_time": "1:43:45", "throughput": 1078.64, "total_tokens": 232448} {"current_steps": 2580, "total_steps": 76960, "loss": 0.3654, "lr": 1.6755457380457382e-05, "epoch": 0.6704781704781705, "percentage": 3.35, "elapsed_time": "0:03:35", "remaining_time": "1:43:44", "throughput": 1078.93, "total_tokens": 232960} {"current_steps": 2585, "total_steps": 76960, "loss": 0.3333, "lr": 1.678794178794179e-05, "epoch": 0.6717775467775468, "percentage": 3.36, "elapsed_time": "0:03:36", "remaining_time": "1:43:44", "throughput": 1078.99, "total_tokens": 233424} {"current_steps": 2590, "total_steps": 76960, "loss": 0.2411, "lr": 1.6820426195426195e-05, "epoch": 0.6730769230769231, "percentage": 3.37, "elapsed_time": "0:03:36", "remaining_time": "1:43:43", "throughput": 1078.91, "total_tokens": 233856} {"current_steps": 2595, "total_steps": 76960, "loss": 0.3625, "lr": 1.6852910602910605e-05, "epoch": 0.6743762993762994, "percentage": 3.37, "elapsed_time": "0:03:37", "remaining_time": "1:43:43", "throughput": 1078.91, "total_tokens": 234304} {"current_steps": 2600, "total_steps": 76960, "loss": 0.2624, "lr": 1.688539501039501e-05, "epoch": 0.6756756756756757, "percentage": 3.38, "elapsed_time": "0:03:37", "remaining_time": "1:43:42", "throughput": 1079.05, "total_tokens": 234784} {"current_steps": 2605, "total_steps": 76960, "loss": 0.2722, "lr": 1.6917879417879417e-05, "epoch": 0.6769750519750519, "percentage": 3.38, "elapsed_time": "0:03:38", "remaining_time": "1:43:42", "throughput": 1078.97, "total_tokens": 235216} {"current_steps": 2610, "total_steps": 76960, "loss": 0.2495, "lr": 1.6950363825363827e-05, "epoch": 0.6782744282744283, "percentage": 3.39, "elapsed_time": "0:03:38", "remaining_time": "1:43:41", "throughput": 1078.96, "total_tokens": 235664} {"current_steps": 2615, "total_steps": 76960, "loss": 0.2657, "lr": 1.6982848232848233e-05, "epoch": 0.6795738045738046, "percentage": 3.4, "elapsed_time": "0:03:38", "remaining_time": "1:43:41", "throughput": 1079.02, "total_tokens": 236128} {"current_steps": 2620, "total_steps": 76960, "loss": 0.3102, "lr": 1.701533264033264e-05, "epoch": 0.6808731808731808, "percentage": 3.4, "elapsed_time": "0:03:39", "remaining_time": "1:43:41", "throughput": 1079.08, "total_tokens": 236592} {"current_steps": 2625, "total_steps": 76960, "loss": 0.2256, "lr": 1.704781704781705e-05, "epoch": 0.6821725571725572, "percentage": 3.41, "elapsed_time": "0:03:39", "remaining_time": "1:43:40", "throughput": 1079.14, "total_tokens": 237056} {"current_steps": 2630, "total_steps": 76960, "loss": 0.1945, "lr": 1.7080301455301455e-05, "epoch": 0.6834719334719335, "percentage": 3.42, "elapsed_time": "0:03:40", "remaining_time": "1:43:40", "throughput": 1079.27, "total_tokens": 237536} {"current_steps": 2635, "total_steps": 76960, "loss": 0.3316, "lr": 1.711278586278586e-05, "epoch": 0.6847713097713097, "percentage": 3.42, "elapsed_time": "0:03:40", "remaining_time": "1:43:39", "throughput": 1079.19, "total_tokens": 237968} {"current_steps": 2640, "total_steps": 76960, "loss": 0.2234, "lr": 1.714527027027027e-05, "epoch": 0.6860706860706861, "percentage": 3.43, "elapsed_time": "0:03:40", "remaining_time": "1:43:39", "throughput": 1079.18, "total_tokens": 238416} {"current_steps": 2645, "total_steps": 76960, "loss": 0.2172, "lr": 1.7177754677754677e-05, "epoch": 0.6873700623700624, "percentage": 3.44, "elapsed_time": "0:03:41", "remaining_time": "1:43:38", "throughput": 1079.17, "total_tokens": 238864} {"current_steps": 2650, "total_steps": 76960, "loss": 0.3273, "lr": 1.7210239085239087e-05, "epoch": 0.6886694386694386, "percentage": 3.44, "elapsed_time": "0:03:41", "remaining_time": "1:43:38", "throughput": 1079.24, "total_tokens": 239328} {"current_steps": 2655, "total_steps": 76960, "loss": 0.2027, "lr": 1.7242723492723493e-05, "epoch": 0.689968814968815, "percentage": 3.45, "elapsed_time": "0:03:42", "remaining_time": "1:43:37", "throughput": 1079.37, "total_tokens": 239808} {"current_steps": 2660, "total_steps": 76960, "loss": 0.262, "lr": 1.7275207900207903e-05, "epoch": 0.6912681912681913, "percentage": 3.46, "elapsed_time": "0:03:42", "remaining_time": "1:43:37", "throughput": 1079.37, "total_tokens": 240256} {"current_steps": 2665, "total_steps": 76960, "loss": 0.1786, "lr": 1.730769230769231e-05, "epoch": 0.6925675675675675, "percentage": 3.46, "elapsed_time": "0:03:43", "remaining_time": "1:43:37", "throughput": 1079.28, "total_tokens": 240688} {"current_steps": 2670, "total_steps": 76960, "loss": 0.1528, "lr": 1.7340176715176716e-05, "epoch": 0.6938669438669439, "percentage": 3.47, "elapsed_time": "0:03:43", "remaining_time": "1:43:36", "throughput": 1079.12, "total_tokens": 241104} {"current_steps": 2675, "total_steps": 76960, "loss": 0.3362, "lr": 1.7372661122661125e-05, "epoch": 0.6951663201663202, "percentage": 3.48, "elapsed_time": "0:03:43", "remaining_time": "1:43:36", "throughput": 1079.11, "total_tokens": 241552} {"current_steps": 2680, "total_steps": 76960, "loss": 0.2792, "lr": 1.740514553014553e-05, "epoch": 0.6964656964656964, "percentage": 3.48, "elapsed_time": "0:03:44", "remaining_time": "1:43:35", "throughput": 1079.17, "total_tokens": 242016} {"current_steps": 2685, "total_steps": 76960, "loss": 0.3014, "lr": 1.7437629937629938e-05, "epoch": 0.6977650727650727, "percentage": 3.49, "elapsed_time": "0:03:44", "remaining_time": "1:43:35", "throughput": 1079.3, "total_tokens": 242496} {"current_steps": 2690, "total_steps": 76960, "loss": 0.2691, "lr": 1.7470114345114347e-05, "epoch": 0.6990644490644491, "percentage": 3.5, "elapsed_time": "0:03:45", "remaining_time": "1:43:34", "throughput": 1079.36, "total_tokens": 242960} {"current_steps": 2695, "total_steps": 76960, "loss": 0.1735, "lr": 1.7502598752598754e-05, "epoch": 0.7003638253638254, "percentage": 3.5, "elapsed_time": "0:03:45", "remaining_time": "1:43:34", "throughput": 1079.55, "total_tokens": 243456} {"current_steps": 2700, "total_steps": 76960, "loss": 0.0736, "lr": 1.753508316008316e-05, "epoch": 0.7016632016632016, "percentage": 3.51, "elapsed_time": "0:03:45", "remaining_time": "1:43:33", "throughput": 1079.47, "total_tokens": 243888} {"current_steps": 2705, "total_steps": 76960, "loss": 0.209, "lr": 1.756756756756757e-05, "epoch": 0.702962577962578, "percentage": 3.51, "elapsed_time": "0:03:46", "remaining_time": "1:43:33", "throughput": 1079.47, "total_tokens": 244336} {"current_steps": 2710, "total_steps": 76960, "loss": 0.2268, "lr": 1.7600051975051976e-05, "epoch": 0.7042619542619543, "percentage": 3.52, "elapsed_time": "0:03:46", "remaining_time": "1:43:33", "throughput": 1079.39, "total_tokens": 244768} {"current_steps": 2715, "total_steps": 76960, "loss": 0.5021, "lr": 1.7632536382536382e-05, "epoch": 0.7055613305613305, "percentage": 3.53, "elapsed_time": "0:03:47", "remaining_time": "1:43:32", "throughput": 1079.38, "total_tokens": 245216} {"current_steps": 2720, "total_steps": 76960, "loss": 0.3927, "lr": 1.7665020790020792e-05, "epoch": 0.7068607068607069, "percentage": 3.53, "elapsed_time": "0:03:47", "remaining_time": "1:43:32", "throughput": 1079.31, "total_tokens": 245648} {"current_steps": 2725, "total_steps": 76960, "loss": 0.1482, "lr": 1.7697505197505198e-05, "epoch": 0.7081600831600832, "percentage": 3.54, "elapsed_time": "0:03:48", "remaining_time": "1:43:31", "throughput": 1079.15, "total_tokens": 246064} {"current_steps": 2730, "total_steps": 76960, "loss": 0.3141, "lr": 1.7729989604989604e-05, "epoch": 0.7094594594594594, "percentage": 3.55, "elapsed_time": "0:03:48", "remaining_time": "1:43:31", "throughput": 1079.13, "total_tokens": 246512} {"current_steps": 2735, "total_steps": 76960, "loss": 0.2613, "lr": 1.7762474012474014e-05, "epoch": 0.7107588357588358, "percentage": 3.55, "elapsed_time": "0:03:48", "remaining_time": "1:43:30", "throughput": 1079.17, "total_tokens": 246976} {"current_steps": 2740, "total_steps": 76960, "loss": 0.2668, "lr": 1.779495841995842e-05, "epoch": 0.7120582120582121, "percentage": 3.56, "elapsed_time": "0:03:49", "remaining_time": "1:43:30", "throughput": 1079.04, "total_tokens": 247408} {"current_steps": 2745, "total_steps": 76960, "loss": 0.2972, "lr": 1.7827442827442827e-05, "epoch": 0.7133575883575883, "percentage": 3.57, "elapsed_time": "0:03:49", "remaining_time": "1:43:30", "throughput": 1079.14, "total_tokens": 247888} {"current_steps": 2750, "total_steps": 76960, "loss": 0.2253, "lr": 1.7859927234927236e-05, "epoch": 0.7146569646569647, "percentage": 3.57, "elapsed_time": "0:03:50", "remaining_time": "1:43:30", "throughput": 1079.2, "total_tokens": 248352} {"current_steps": 2755, "total_steps": 76960, "loss": 0.2343, "lr": 1.7892411642411642e-05, "epoch": 0.715956340956341, "percentage": 3.58, "elapsed_time": "0:03:50", "remaining_time": "1:43:29", "throughput": 1079.32, "total_tokens": 248832} {"current_steps": 2760, "total_steps": 76960, "loss": 0.2805, "lr": 1.7924896049896052e-05, "epoch": 0.7172557172557172, "percentage": 3.59, "elapsed_time": "0:03:50", "remaining_time": "1:43:29", "throughput": 1079.32, "total_tokens": 249280} {"current_steps": 2765, "total_steps": 76960, "loss": 0.3285, "lr": 1.795738045738046e-05, "epoch": 0.7185550935550935, "percentage": 3.59, "elapsed_time": "0:03:51", "remaining_time": "1:43:28", "throughput": 1079.44, "total_tokens": 249760} {"current_steps": 2770, "total_steps": 76960, "loss": 0.2911, "lr": 1.7989864864864868e-05, "epoch": 0.7198544698544699, "percentage": 3.6, "elapsed_time": "0:03:51", "remaining_time": "1:43:28", "throughput": 1079.47, "total_tokens": 250224} {"current_steps": 2775, "total_steps": 76960, "loss": 0.283, "lr": 1.8022349272349274e-05, "epoch": 0.7211538461538461, "percentage": 3.61, "elapsed_time": "0:03:52", "remaining_time": "1:43:28", "throughput": 1079.38, "total_tokens": 250656} {"current_steps": 2780, "total_steps": 76960, "loss": 0.3065, "lr": 1.805483367983368e-05, "epoch": 0.7224532224532224, "percentage": 3.61, "elapsed_time": "0:03:52", "remaining_time": "1:43:27", "throughput": 1079.23, "total_tokens": 251072} {"current_steps": 2785, "total_steps": 76960, "loss": 0.2556, "lr": 1.808731808731809e-05, "epoch": 0.7237525987525988, "percentage": 3.62, "elapsed_time": "0:03:53", "remaining_time": "1:43:27", "throughput": 1079.22, "total_tokens": 251520} {"current_steps": 2790, "total_steps": 76960, "loss": 0.2816, "lr": 1.8119802494802496e-05, "epoch": 0.725051975051975, "percentage": 3.63, "elapsed_time": "0:03:53", "remaining_time": "1:43:26", "throughput": 1079.28, "total_tokens": 251984} {"current_steps": 2795, "total_steps": 76960, "loss": 0.2547, "lr": 1.8152286902286903e-05, "epoch": 0.7263513513513513, "percentage": 3.63, "elapsed_time": "0:03:53", "remaining_time": "1:43:26", "throughput": 1079.2, "total_tokens": 252416} {"current_steps": 2800, "total_steps": 76960, "loss": 0.2933, "lr": 1.8184771309771312e-05, "epoch": 0.7276507276507277, "percentage": 3.64, "elapsed_time": "0:03:54", "remaining_time": "1:43:25", "throughput": 1079.2, "total_tokens": 252864} {"current_steps": 2805, "total_steps": 76960, "loss": 0.2712, "lr": 1.821725571725572e-05, "epoch": 0.728950103950104, "percentage": 3.64, "elapsed_time": "0:03:54", "remaining_time": "1:43:25", "throughput": 1079.26, "total_tokens": 253328} {"current_steps": 2810, "total_steps": 76960, "loss": 0.2355, "lr": 1.8249740124740125e-05, "epoch": 0.7302494802494802, "percentage": 3.65, "elapsed_time": "0:03:55", "remaining_time": "1:43:24", "throughput": 1079.11, "total_tokens": 253744} {"current_steps": 2815, "total_steps": 76960, "loss": 0.1787, "lr": 1.8282224532224535e-05, "epoch": 0.7315488565488566, "percentage": 3.66, "elapsed_time": "0:03:55", "remaining_time": "1:43:24", "throughput": 1078.97, "total_tokens": 254160} {"current_steps": 2820, "total_steps": 76960, "loss": 0.316, "lr": 1.831470893970894e-05, "epoch": 0.7328482328482329, "percentage": 3.66, "elapsed_time": "0:03:55", "remaining_time": "1:43:23", "throughput": 1078.91, "total_tokens": 254592} {"current_steps": 2825, "total_steps": 76960, "loss": 0.3617, "lr": 1.8347193347193347e-05, "epoch": 0.7341476091476091, "percentage": 3.67, "elapsed_time": "0:03:56", "remaining_time": "1:43:23", "throughput": 1078.78, "total_tokens": 255008} {"current_steps": 2830, "total_steps": 76960, "loss": 0.2134, "lr": 1.8379677754677753e-05, "epoch": 0.7354469854469855, "percentage": 3.68, "elapsed_time": "0:03:56", "remaining_time": "1:43:22", "throughput": 1078.71, "total_tokens": 255440} {"current_steps": 2835, "total_steps": 76960, "loss": 0.3154, "lr": 1.8412162162162163e-05, "epoch": 0.7367463617463618, "percentage": 3.68, "elapsed_time": "0:03:57", "remaining_time": "1:43:22", "throughput": 1078.78, "total_tokens": 255904} {"current_steps": 2840, "total_steps": 76960, "loss": 0.2149, "lr": 1.844464656964657e-05, "epoch": 0.738045738045738, "percentage": 3.69, "elapsed_time": "0:03:57", "remaining_time": "1:43:21", "throughput": 1078.78, "total_tokens": 256352} {"current_steps": 2845, "total_steps": 76960, "loss": 0.287, "lr": 1.8477130977130976e-05, "epoch": 0.7393451143451143, "percentage": 3.7, "elapsed_time": "0:03:58", "remaining_time": "1:43:21", "throughput": 1078.84, "total_tokens": 256816} {"current_steps": 2850, "total_steps": 76960, "loss": 0.2294, "lr": 1.8509615384615385e-05, "epoch": 0.7406444906444907, "percentage": 3.7, "elapsed_time": "0:03:58", "remaining_time": "1:43:20", "throughput": 1078.84, "total_tokens": 257264} {"current_steps": 2855, "total_steps": 76960, "loss": 0.2197, "lr": 1.854209979209979e-05, "epoch": 0.7419438669438669, "percentage": 3.71, "elapsed_time": "0:03:58", "remaining_time": "1:43:20", "throughput": 1078.84, "total_tokens": 257712} {"current_steps": 2860, "total_steps": 76960, "loss": 0.2226, "lr": 1.85745841995842e-05, "epoch": 0.7432432432432432, "percentage": 3.72, "elapsed_time": "0:03:59", "remaining_time": "1:43:19", "throughput": 1078.98, "total_tokens": 258192} {"current_steps": 2865, "total_steps": 76960, "loss": 0.2468, "lr": 1.8607068607068607e-05, "epoch": 0.7445426195426196, "percentage": 3.72, "elapsed_time": "0:03:59", "remaining_time": "1:43:19", "throughput": 1078.9, "total_tokens": 258624} {"current_steps": 2870, "total_steps": 76960, "loss": 0.2087, "lr": 1.8639553014553017e-05, "epoch": 0.7458419958419958, "percentage": 3.73, "elapsed_time": "0:04:00", "remaining_time": "1:43:18", "throughput": 1078.97, "total_tokens": 259088} {"current_steps": 2875, "total_steps": 76960, "loss": 0.2543, "lr": 1.8672037422037423e-05, "epoch": 0.7471413721413721, "percentage": 3.74, "elapsed_time": "0:04:00", "remaining_time": "1:43:18", "throughput": 1079.15, "total_tokens": 259584} {"current_steps": 2880, "total_steps": 76960, "loss": 0.3658, "lr": 1.8704521829521833e-05, "epoch": 0.7484407484407485, "percentage": 3.74, "elapsed_time": "0:04:00", "remaining_time": "1:43:18", "throughput": 1079.01, "total_tokens": 260000} {"current_steps": 2885, "total_steps": 76960, "loss": 0.2338, "lr": 1.873700623700624e-05, "epoch": 0.7497401247401247, "percentage": 3.75, "elapsed_time": "0:04:01", "remaining_time": "1:43:17", "throughput": 1079.07, "total_tokens": 260464} {"current_steps": 2890, "total_steps": 76960, "loss": 0.2234, "lr": 1.8769490644490646e-05, "epoch": 0.751039501039501, "percentage": 3.76, "elapsed_time": "0:04:01", "remaining_time": "1:43:17", "throughput": 1079.0, "total_tokens": 260896} {"current_steps": 2895, "total_steps": 76960, "loss": 0.127, "lr": 1.8801975051975052e-05, "epoch": 0.7523388773388774, "percentage": 3.76, "elapsed_time": "0:04:02", "remaining_time": "1:43:16", "throughput": 1079.0, "total_tokens": 261344} {"current_steps": 2900, "total_steps": 76960, "loss": 0.3835, "lr": 1.883445945945946e-05, "epoch": 0.7536382536382537, "percentage": 3.77, "elapsed_time": "0:04:02", "remaining_time": "1:43:16", "throughput": 1079.06, "total_tokens": 261808} {"current_steps": 2905, "total_steps": 76960, "loss": 0.3565, "lr": 1.8866943866943868e-05, "epoch": 0.7549376299376299, "percentage": 3.77, "elapsed_time": "0:04:03", "remaining_time": "1:43:15", "throughput": 1079.19, "total_tokens": 262288} {"current_steps": 2910, "total_steps": 76960, "loss": 0.2935, "lr": 1.8899428274428274e-05, "epoch": 0.7562370062370062, "percentage": 3.78, "elapsed_time": "0:04:03", "remaining_time": "1:43:15", "throughput": 1079.05, "total_tokens": 262704} {"current_steps": 2915, "total_steps": 76960, "loss": 0.2326, "lr": 1.8931912681912684e-05, "epoch": 0.7575363825363826, "percentage": 3.79, "elapsed_time": "0:04:03", "remaining_time": "1:43:14", "throughput": 1078.85, "total_tokens": 263104} {"current_steps": 2920, "total_steps": 76960, "loss": 0.2668, "lr": 1.896439708939709e-05, "epoch": 0.7588357588357588, "percentage": 3.79, "elapsed_time": "0:04:04", "remaining_time": "1:43:14", "throughput": 1078.71, "total_tokens": 263520} {"current_steps": 2925, "total_steps": 76960, "loss": 0.1773, "lr": 1.8996881496881496e-05, "epoch": 0.7601351351351351, "percentage": 3.8, "elapsed_time": "0:04:04", "remaining_time": "1:43:13", "throughput": 1078.62, "total_tokens": 263952} {"current_steps": 2930, "total_steps": 76960, "loss": 0.197, "lr": 1.9029365904365906e-05, "epoch": 0.7614345114345115, "percentage": 3.81, "elapsed_time": "0:04:05", "remaining_time": "1:43:13", "throughput": 1078.55, "total_tokens": 264384} {"current_steps": 2935, "total_steps": 76960, "loss": 0.3629, "lr": 1.9061850311850312e-05, "epoch": 0.7627338877338877, "percentage": 3.81, "elapsed_time": "0:04:05", "remaining_time": "1:43:13", "throughput": 1078.47, "total_tokens": 264816} {"current_steps": 2940, "total_steps": 76960, "loss": 0.308, "lr": 1.909433471933472e-05, "epoch": 0.764033264033264, "percentage": 3.82, "elapsed_time": "0:04:05", "remaining_time": "1:43:12", "throughput": 1078.4, "total_tokens": 265248} {"current_steps": 2945, "total_steps": 76960, "loss": 0.1857, "lr": 1.9126819126819128e-05, "epoch": 0.7653326403326404, "percentage": 3.83, "elapsed_time": "0:04:06", "remaining_time": "1:43:12", "throughput": 1078.32, "total_tokens": 265696} {"current_steps": 2950, "total_steps": 76960, "loss": 0.2956, "lr": 1.9159303534303534e-05, "epoch": 0.7666320166320166, "percentage": 3.83, "elapsed_time": "0:04:06", "remaining_time": "1:43:12", "throughput": 1078.31, "total_tokens": 266144} {"current_steps": 2955, "total_steps": 76960, "loss": 0.3214, "lr": 1.919178794178794e-05, "epoch": 0.7679313929313929, "percentage": 3.84, "elapsed_time": "0:04:07", "remaining_time": "1:43:11", "throughput": 1078.2, "total_tokens": 266576} {"current_steps": 2960, "total_steps": 76960, "loss": 0.2826, "lr": 1.922427234927235e-05, "epoch": 0.7692307692307693, "percentage": 3.85, "elapsed_time": "0:04:07", "remaining_time": "1:43:11", "throughput": 1078.13, "total_tokens": 267008} {"current_steps": 2965, "total_steps": 76960, "loss": 0.274, "lr": 1.9256756756756756e-05, "epoch": 0.7705301455301455, "percentage": 3.85, "elapsed_time": "0:04:08", "remaining_time": "1:43:10", "throughput": 1078.19, "total_tokens": 267472} {"current_steps": 2970, "total_steps": 76960, "loss": 0.2532, "lr": 1.9289241164241166e-05, "epoch": 0.7718295218295218, "percentage": 3.86, "elapsed_time": "0:04:08", "remaining_time": "1:43:10", "throughput": 1078.06, "total_tokens": 267888} {"current_steps": 2975, "total_steps": 76960, "loss": 0.3785, "lr": 1.9321725571725572e-05, "epoch": 0.7731288981288982, "percentage": 3.87, "elapsed_time": "0:04:08", "remaining_time": "1:43:10", "throughput": 1078.05, "total_tokens": 268336} {"current_steps": 2980, "total_steps": 76960, "loss": 0.2007, "lr": 1.9354209979209982e-05, "epoch": 0.7744282744282744, "percentage": 3.87, "elapsed_time": "0:04:09", "remaining_time": "1:43:09", "throughput": 1078.04, "total_tokens": 268784} {"current_steps": 2985, "total_steps": 76960, "loss": 0.1205, "lr": 1.9386694386694388e-05, "epoch": 0.7757276507276507, "percentage": 3.88, "elapsed_time": "0:04:09", "remaining_time": "1:43:09", "throughput": 1077.98, "total_tokens": 269216} {"current_steps": 2990, "total_steps": 76960, "loss": 0.2918, "lr": 1.9419178794178795e-05, "epoch": 0.777027027027027, "percentage": 3.89, "elapsed_time": "0:04:10", "remaining_time": "1:43:08", "throughput": 1077.78, "total_tokens": 269616} {"current_steps": 2995, "total_steps": 76960, "loss": 0.2949, "lr": 1.9451663201663204e-05, "epoch": 0.7783264033264033, "percentage": 3.89, "elapsed_time": "0:04:10", "remaining_time": "1:43:08", "throughput": 1077.71, "total_tokens": 270048} {"current_steps": 3000, "total_steps": 76960, "loss": 0.297, "lr": 1.948414760914761e-05, "epoch": 0.7796257796257796, "percentage": 3.9, "elapsed_time": "0:04:10", "remaining_time": "1:43:07", "throughput": 1077.71, "total_tokens": 270496} {"current_steps": 3005, "total_steps": 76960, "loss": 0.2336, "lr": 1.9516632016632017e-05, "epoch": 0.7809251559251559, "percentage": 3.9, "elapsed_time": "0:04:11", "remaining_time": "1:43:07", "throughput": 1077.71, "total_tokens": 270944} {"current_steps": 3010, "total_steps": 76960, "loss": 0.2706, "lr": 1.9549116424116426e-05, "epoch": 0.7822245322245323, "percentage": 3.91, "elapsed_time": "0:04:11", "remaining_time": "1:43:06", "throughput": 1077.77, "total_tokens": 271408} {"current_steps": 3015, "total_steps": 76960, "loss": 0.3264, "lr": 1.9581600831600833e-05, "epoch": 0.7835239085239085, "percentage": 3.92, "elapsed_time": "0:04:12", "remaining_time": "1:43:06", "throughput": 1077.77, "total_tokens": 271856} {"current_steps": 3020, "total_steps": 76960, "loss": 0.3284, "lr": 1.961408523908524e-05, "epoch": 0.7848232848232848, "percentage": 3.92, "elapsed_time": "0:04:12", "remaining_time": "1:43:05", "throughput": 1077.82, "total_tokens": 272320} {"current_steps": 3025, "total_steps": 76960, "loss": 0.2372, "lr": 1.964656964656965e-05, "epoch": 0.7861226611226612, "percentage": 3.93, "elapsed_time": "0:04:13", "remaining_time": "1:43:05", "throughput": 1077.89, "total_tokens": 272784} {"current_steps": 3030, "total_steps": 76960, "loss": 0.2561, "lr": 1.9679054054054055e-05, "epoch": 0.7874220374220374, "percentage": 3.94, "elapsed_time": "0:04:13", "remaining_time": "1:43:05", "throughput": 1077.88, "total_tokens": 273232} {"current_steps": 3035, "total_steps": 76960, "loss": 0.2564, "lr": 1.971153846153846e-05, "epoch": 0.7887214137214137, "percentage": 3.94, "elapsed_time": "0:04:13", "remaining_time": "1:43:04", "throughput": 1077.92, "total_tokens": 273696} {"current_steps": 3040, "total_steps": 76960, "loss": 0.3011, "lr": 1.974402286902287e-05, "epoch": 0.7900207900207901, "percentage": 3.95, "elapsed_time": "0:04:14", "remaining_time": "1:43:04", "throughput": 1077.99, "total_tokens": 274160} {"current_steps": 3045, "total_steps": 76960, "loss": 0.2239, "lr": 1.9776507276507277e-05, "epoch": 0.7913201663201663, "percentage": 3.96, "elapsed_time": "0:04:14", "remaining_time": "1:43:03", "throughput": 1077.85, "total_tokens": 274576} {"current_steps": 3050, "total_steps": 76960, "loss": 0.2096, "lr": 1.9808991683991683e-05, "epoch": 0.7926195426195426, "percentage": 3.96, "elapsed_time": "0:04:15", "remaining_time": "1:43:03", "throughput": 1077.85, "total_tokens": 275024} {"current_steps": 3055, "total_steps": 76960, "loss": 0.2809, "lr": 1.984147609147609e-05, "epoch": 0.793918918918919, "percentage": 3.97, "elapsed_time": "0:04:15", "remaining_time": "1:43:02", "throughput": 1077.77, "total_tokens": 275456} {"current_steps": 3060, "total_steps": 76960, "loss": 0.3673, "lr": 1.98739604989605e-05, "epoch": 0.7952182952182952, "percentage": 3.98, "elapsed_time": "0:04:15", "remaining_time": "1:43:02", "throughput": 1077.71, "total_tokens": 275888} {"current_steps": 3065, "total_steps": 76960, "loss": 0.2166, "lr": 1.9906444906444905e-05, "epoch": 0.7965176715176715, "percentage": 3.98, "elapsed_time": "0:04:16", "remaining_time": "1:43:01", "throughput": 1077.77, "total_tokens": 276352} {"current_steps": 3070, "total_steps": 76960, "loss": 0.3329, "lr": 1.9938929313929315e-05, "epoch": 0.7978170478170478, "percentage": 3.99, "elapsed_time": "0:04:16", "remaining_time": "1:43:01", "throughput": 1077.83, "total_tokens": 276816} {"current_steps": 3075, "total_steps": 76960, "loss": 0.2713, "lr": 1.9971413721413725e-05, "epoch": 0.7991164241164241, "percentage": 4.0, "elapsed_time": "0:04:17", "remaining_time": "1:43:00", "throughput": 1077.91, "total_tokens": 277280} {"current_steps": 3080, "total_steps": 76960, "loss": 0.2571, "lr": 2.000389812889813e-05, "epoch": 0.8004158004158004, "percentage": 4.0, "elapsed_time": "0:04:17", "remaining_time": "1:43:00", "throughput": 1077.91, "total_tokens": 277728} {"current_steps": 3085, "total_steps": 76960, "loss": 0.2178, "lr": 2.0036382536382537e-05, "epoch": 0.8017151767151767, "percentage": 4.01, "elapsed_time": "0:04:18", "remaining_time": "1:42:59", "throughput": 1078.03, "total_tokens": 278208} {"current_steps": 3090, "total_steps": 76960, "loss": 0.3397, "lr": 2.0068866943866947e-05, "epoch": 0.803014553014553, "percentage": 4.02, "elapsed_time": "0:04:18", "remaining_time": "1:42:59", "throughput": 1078.09, "total_tokens": 278672} {"current_steps": 3095, "total_steps": 76960, "loss": 0.2808, "lr": 2.0101351351351353e-05, "epoch": 0.8043139293139293, "percentage": 4.02, "elapsed_time": "0:04:18", "remaining_time": "1:42:58", "throughput": 1078.09, "total_tokens": 279120} {"current_steps": 3100, "total_steps": 76960, "loss": 0.1708, "lr": 2.013383575883576e-05, "epoch": 0.8056133056133056, "percentage": 4.03, "elapsed_time": "0:04:19", "remaining_time": "1:42:58", "throughput": 1077.96, "total_tokens": 279536} {"current_steps": 3105, "total_steps": 76960, "loss": 0.2772, "lr": 2.016632016632017e-05, "epoch": 0.806912681912682, "percentage": 4.03, "elapsed_time": "0:04:19", "remaining_time": "1:42:58", "throughput": 1077.9, "total_tokens": 279968} {"current_steps": 3110, "total_steps": 76960, "loss": 0.307, "lr": 2.0198804573804575e-05, "epoch": 0.8082120582120582, "percentage": 4.04, "elapsed_time": "0:04:20", "remaining_time": "1:42:57", "throughput": 1078.02, "total_tokens": 280448} {"current_steps": 3115, "total_steps": 76960, "loss": 0.3163, "lr": 2.0231288981288982e-05, "epoch": 0.8095114345114345, "percentage": 4.05, "elapsed_time": "0:04:20", "remaining_time": "1:42:57", "throughput": 1077.89, "total_tokens": 280864} {"current_steps": 3120, "total_steps": 76960, "loss": 0.1749, "lr": 2.026377338877339e-05, "epoch": 0.8108108108108109, "percentage": 4.05, "elapsed_time": "0:04:20", "remaining_time": "1:42:56", "throughput": 1077.89, "total_tokens": 281312} {"current_steps": 3125, "total_steps": 76960, "loss": 0.3363, "lr": 2.0296257796257798e-05, "epoch": 0.8121101871101871, "percentage": 4.06, "elapsed_time": "0:04:21", "remaining_time": "1:42:56", "throughput": 1077.89, "total_tokens": 281760} {"current_steps": 3130, "total_steps": 76960, "loss": 0.2545, "lr": 2.0328742203742204e-05, "epoch": 0.8134095634095634, "percentage": 4.07, "elapsed_time": "0:04:21", "remaining_time": "1:42:55", "throughput": 1077.95, "total_tokens": 282224} {"current_steps": 3135, "total_steps": 76960, "loss": 0.2516, "lr": 2.036122661122661e-05, "epoch": 0.8147089397089398, "percentage": 4.07, "elapsed_time": "0:04:22", "remaining_time": "1:42:55", "throughput": 1077.89, "total_tokens": 282656} {"current_steps": 3140, "total_steps": 76960, "loss": 0.2361, "lr": 2.039371101871102e-05, "epoch": 0.816008316008316, "percentage": 4.08, "elapsed_time": "0:04:22", "remaining_time": "1:42:54", "throughput": 1077.76, "total_tokens": 283072} {"current_steps": 3145, "total_steps": 76960, "loss": 0.1798, "lr": 2.0426195426195426e-05, "epoch": 0.8173076923076923, "percentage": 4.09, "elapsed_time": "0:04:23", "remaining_time": "1:42:54", "throughput": 1077.69, "total_tokens": 283504} {"current_steps": 3150, "total_steps": 76960, "loss": 0.2205, "lr": 2.0458679833679832e-05, "epoch": 0.8186070686070686, "percentage": 4.09, "elapsed_time": "0:04:23", "remaining_time": "1:42:53", "throughput": 1077.81, "total_tokens": 283984} {"current_steps": 3155, "total_steps": 76960, "loss": 0.2964, "lr": 2.0491164241164242e-05, "epoch": 0.8199064449064449, "percentage": 4.1, "elapsed_time": "0:04:23", "remaining_time": "1:42:53", "throughput": 1077.81, "total_tokens": 284432} {"current_steps": 3160, "total_steps": 76960, "loss": 0.2723, "lr": 2.0523648648648648e-05, "epoch": 0.8212058212058212, "percentage": 4.11, "elapsed_time": "0:04:24", "remaining_time": "1:42:52", "throughput": 1077.74, "total_tokens": 284864} {"current_steps": 3165, "total_steps": 76960, "loss": 0.1551, "lr": 2.0556133056133055e-05, "epoch": 0.8225051975051975, "percentage": 4.11, "elapsed_time": "0:04:24", "remaining_time": "1:42:52", "throughput": 1077.8, "total_tokens": 285328} {"current_steps": 3170, "total_steps": 76960, "loss": 0.2109, "lr": 2.0588617463617464e-05, "epoch": 0.8238045738045738, "percentage": 4.12, "elapsed_time": "0:04:25", "remaining_time": "1:42:52", "throughput": 1077.86, "total_tokens": 285792} {"current_steps": 3175, "total_steps": 76960, "loss": 0.221, "lr": 2.0621101871101874e-05, "epoch": 0.8251039501039501, "percentage": 4.13, "elapsed_time": "0:04:25", "remaining_time": "1:42:51", "throughput": 1077.92, "total_tokens": 286256} {"current_steps": 3180, "total_steps": 76960, "loss": 0.1535, "lr": 2.065358627858628e-05, "epoch": 0.8264033264033264, "percentage": 4.13, "elapsed_time": "0:04:25", "remaining_time": "1:42:51", "throughput": 1077.72, "total_tokens": 286656} {"current_steps": 3185, "total_steps": 76960, "loss": 0.2762, "lr": 2.068607068607069e-05, "epoch": 0.8277027027027027, "percentage": 4.14, "elapsed_time": "0:04:26", "remaining_time": "1:42:50", "throughput": 1077.66, "total_tokens": 287088} {"current_steps": 3190, "total_steps": 76960, "loss": 0.2546, "lr": 2.0718555093555096e-05, "epoch": 0.829002079002079, "percentage": 4.15, "elapsed_time": "0:04:26", "remaining_time": "1:42:50", "throughput": 1077.59, "total_tokens": 287520} {"current_steps": 3195, "total_steps": 76960, "loss": 0.2139, "lr": 2.0751039501039502e-05, "epoch": 0.8303014553014553, "percentage": 4.15, "elapsed_time": "0:04:27", "remaining_time": "1:42:49", "throughput": 1077.59, "total_tokens": 287968} {"current_steps": 3200, "total_steps": 76960, "loss": 0.3135, "lr": 2.0783523908523912e-05, "epoch": 0.8316008316008316, "percentage": 4.16, "elapsed_time": "0:04:27", "remaining_time": "1:42:49", "throughput": 1077.52, "total_tokens": 288400} {"current_steps": 3205, "total_steps": 76960, "loss": 0.331, "lr": 2.0816008316008318e-05, "epoch": 0.8329002079002079, "percentage": 4.16, "elapsed_time": "0:04:28", "remaining_time": "1:42:48", "throughput": 1077.52, "total_tokens": 288848} {"current_steps": 3210, "total_steps": 76960, "loss": 0.2927, "lr": 2.0848492723492724e-05, "epoch": 0.8341995841995842, "percentage": 4.17, "elapsed_time": "0:04:28", "remaining_time": "1:42:48", "throughput": 1077.4, "total_tokens": 289264} {"current_steps": 3215, "total_steps": 76960, "loss": 0.3089, "lr": 2.088097713097713e-05, "epoch": 0.8354989604989606, "percentage": 4.18, "elapsed_time": "0:04:28", "remaining_time": "1:42:47", "throughput": 1077.51, "total_tokens": 289744} {"current_steps": 3220, "total_steps": 76960, "loss": 0.2972, "lr": 2.091346153846154e-05, "epoch": 0.8367983367983368, "percentage": 4.18, "elapsed_time": "0:04:29", "remaining_time": "1:42:47", "throughput": 1077.51, "total_tokens": 290192} {"current_steps": 3225, "total_steps": 76960, "loss": 0.2616, "lr": 2.0945945945945947e-05, "epoch": 0.8380977130977131, "percentage": 4.19, "elapsed_time": "0:04:29", "remaining_time": "1:42:47", "throughput": 1077.38, "total_tokens": 290608} {"current_steps": 3230, "total_steps": 76960, "loss": 0.266, "lr": 2.0978430353430353e-05, "epoch": 0.8393970893970893, "percentage": 4.2, "elapsed_time": "0:04:30", "remaining_time": "1:42:46", "throughput": 1077.43, "total_tokens": 291072} {"current_steps": 3235, "total_steps": 76960, "loss": 0.2802, "lr": 2.1010914760914763e-05, "epoch": 0.8406964656964657, "percentage": 4.2, "elapsed_time": "0:04:30", "remaining_time": "1:42:46", "throughput": 1077.48, "total_tokens": 291536} {"current_steps": 3240, "total_steps": 76960, "loss": 0.2448, "lr": 2.104339916839917e-05, "epoch": 0.841995841995842, "percentage": 4.21, "elapsed_time": "0:04:30", "remaining_time": "1:42:45", "throughput": 1077.6, "total_tokens": 292016} {"current_steps": 3245, "total_steps": 76960, "loss": 0.2302, "lr": 2.1075883575883575e-05, "epoch": 0.8432952182952183, "percentage": 4.22, "elapsed_time": "0:04:31", "remaining_time": "1:42:45", "throughput": 1077.53, "total_tokens": 292448} {"current_steps": 3250, "total_steps": 76960, "loss": 0.2259, "lr": 2.1108367983367985e-05, "epoch": 0.8445945945945946, "percentage": 4.22, "elapsed_time": "0:04:31", "remaining_time": "1:42:44", "throughput": 1077.58, "total_tokens": 292912} {"current_steps": 3255, "total_steps": 76960, "loss": 0.2649, "lr": 2.114085239085239e-05, "epoch": 0.8458939708939709, "percentage": 4.23, "elapsed_time": "0:04:32", "remaining_time": "1:42:44", "throughput": 1077.59, "total_tokens": 293360} {"current_steps": 3260, "total_steps": 76960, "loss": 0.2184, "lr": 2.1173336798336797e-05, "epoch": 0.8471933471933472, "percentage": 4.24, "elapsed_time": "0:04:32", "remaining_time": "1:42:43", "throughput": 1077.59, "total_tokens": 293808} {"current_steps": 3265, "total_steps": 76960, "loss": 0.0923, "lr": 2.1205821205821207e-05, "epoch": 0.8484927234927235, "percentage": 4.24, "elapsed_time": "0:04:33", "remaining_time": "1:42:43", "throughput": 1077.59, "total_tokens": 294256} {"current_steps": 3270, "total_steps": 76960, "loss": 0.2919, "lr": 2.1238305613305613e-05, "epoch": 0.8497920997920998, "percentage": 4.25, "elapsed_time": "0:04:33", "remaining_time": "1:42:43", "throughput": 1077.82, "total_tokens": 294768} {"current_steps": 3275, "total_steps": 76960, "loss": 0.5244, "lr": 2.1270790020790023e-05, "epoch": 0.8510914760914761, "percentage": 4.26, "elapsed_time": "0:04:33", "remaining_time": "1:42:42", "throughput": 1077.88, "total_tokens": 295232} {"current_steps": 3280, "total_steps": 76960, "loss": 0.6269, "lr": 2.130327442827443e-05, "epoch": 0.8523908523908524, "percentage": 4.26, "elapsed_time": "0:04:34", "remaining_time": "1:42:42", "throughput": 1077.89, "total_tokens": 295680} {"current_steps": 3285, "total_steps": 76960, "loss": 0.1905, "lr": 2.133575883575884e-05, "epoch": 0.8536902286902287, "percentage": 4.27, "elapsed_time": "0:04:34", "remaining_time": "1:42:41", "throughput": 1078.07, "total_tokens": 296176} {"current_steps": 3290, "total_steps": 76960, "loss": 0.3013, "lr": 2.1368243243243245e-05, "epoch": 0.854989604989605, "percentage": 4.27, "elapsed_time": "0:04:35", "remaining_time": "1:42:40", "throughput": 1078.08, "total_tokens": 296624} {"current_steps": 3295, "total_steps": 76960, "loss": 0.3414, "lr": 2.140072765072765e-05, "epoch": 0.8562889812889813, "percentage": 4.28, "elapsed_time": "0:04:35", "remaining_time": "1:42:40", "throughput": 1078.14, "total_tokens": 297088} {"current_steps": 3300, "total_steps": 76960, "loss": 0.2927, "lr": 2.143321205821206e-05, "epoch": 0.8575883575883576, "percentage": 4.29, "elapsed_time": "0:04:35", "remaining_time": "1:42:40", "throughput": 1078.14, "total_tokens": 297536} {"current_steps": 3305, "total_steps": 76960, "loss": 0.3233, "lr": 2.1465696465696467e-05, "epoch": 0.8588877338877339, "percentage": 4.29, "elapsed_time": "0:04:36", "remaining_time": "1:42:39", "throughput": 1078.08, "total_tokens": 297968} {"current_steps": 3310, "total_steps": 76960, "loss": 0.2588, "lr": 2.1498180873180874e-05, "epoch": 0.8601871101871101, "percentage": 4.3, "elapsed_time": "0:04:36", "remaining_time": "1:42:39", "throughput": 1078.01, "total_tokens": 298400} {"current_steps": 3315, "total_steps": 76960, "loss": 0.4847, "lr": 2.1530665280665283e-05, "epoch": 0.8614864864864865, "percentage": 4.31, "elapsed_time": "0:04:37", "remaining_time": "1:42:38", "throughput": 1078.0, "total_tokens": 298848} {"current_steps": 3320, "total_steps": 76960, "loss": 0.3894, "lr": 2.156314968814969e-05, "epoch": 0.8627858627858628, "percentage": 4.31, "elapsed_time": "0:04:37", "remaining_time": "1:42:38", "throughput": 1078.0, "total_tokens": 299296} {"current_steps": 3325, "total_steps": 76960, "loss": 0.2775, "lr": 2.1595634095634096e-05, "epoch": 0.864085239085239, "percentage": 4.32, "elapsed_time": "0:04:38", "remaining_time": "1:42:37", "throughput": 1077.94, "total_tokens": 299728} {"current_steps": 3330, "total_steps": 76960, "loss": 0.2826, "lr": 2.1628118503118505e-05, "epoch": 0.8653846153846154, "percentage": 4.33, "elapsed_time": "0:04:38", "remaining_time": "1:42:37", "throughput": 1077.82, "total_tokens": 300144} {"current_steps": 3335, "total_steps": 76960, "loss": 0.2859, "lr": 2.166060291060291e-05, "epoch": 0.8666839916839917, "percentage": 4.33, "elapsed_time": "0:04:38", "remaining_time": "1:42:36", "throughput": 1077.94, "total_tokens": 300624} {"current_steps": 3340, "total_steps": 76960, "loss": 0.2705, "lr": 2.1693087318087318e-05, "epoch": 0.867983367983368, "percentage": 4.34, "elapsed_time": "0:04:39", "remaining_time": "1:42:36", "throughput": 1077.94, "total_tokens": 301072} {"current_steps": 3345, "total_steps": 76960, "loss": 0.1608, "lr": 2.1725571725571728e-05, "epoch": 0.8692827442827443, "percentage": 4.35, "elapsed_time": "0:04:39", "remaining_time": "1:42:35", "throughput": 1078.0, "total_tokens": 301536} {"current_steps": 3350, "total_steps": 76960, "loss": 0.3349, "lr": 2.1758056133056134e-05, "epoch": 0.8705821205821206, "percentage": 4.35, "elapsed_time": "0:04:40", "remaining_time": "1:42:35", "throughput": 1078.07, "total_tokens": 302000} {"current_steps": 3355, "total_steps": 76960, "loss": 0.8814, "lr": 2.179054054054054e-05, "epoch": 0.8718814968814969, "percentage": 4.36, "elapsed_time": "0:04:40", "remaining_time": "1:42:34", "throughput": 1078.0, "total_tokens": 302432} {"current_steps": 3360, "total_steps": 76960, "loss": 0.5668, "lr": 2.182302494802495e-05, "epoch": 0.8731808731808732, "percentage": 4.37, "elapsed_time": "0:04:40", "remaining_time": "1:42:34", "throughput": 1077.95, "total_tokens": 302864} {"current_steps": 3365, "total_steps": 76960, "loss": 0.2571, "lr": 2.1855509355509356e-05, "epoch": 0.8744802494802495, "percentage": 4.37, "elapsed_time": "0:04:41", "remaining_time": "1:42:33", "throughput": 1077.95, "total_tokens": 303312} {"current_steps": 3370, "total_steps": 76960, "loss": 0.2506, "lr": 2.1887993762993762e-05, "epoch": 0.8757796257796258, "percentage": 4.38, "elapsed_time": "0:04:41", "remaining_time": "1:42:33", "throughput": 1078.01, "total_tokens": 303776} {"current_steps": 3375, "total_steps": 76960, "loss": 0.3093, "lr": 2.1920478170478172e-05, "epoch": 0.877079002079002, "percentage": 4.39, "elapsed_time": "0:04:42", "remaining_time": "1:42:32", "throughput": 1078.01, "total_tokens": 304224} {"current_steps": 3380, "total_steps": 76960, "loss": 0.1953, "lr": 2.1952962577962578e-05, "epoch": 0.8783783783783784, "percentage": 4.39, "elapsed_time": "0:04:42", "remaining_time": "1:42:32", "throughput": 1078.01, "total_tokens": 304672} {"current_steps": 3385, "total_steps": 76960, "loss": 0.2708, "lr": 2.1985446985446988e-05, "epoch": 0.8796777546777547, "percentage": 4.4, "elapsed_time": "0:04:43", "remaining_time": "1:42:32", "throughput": 1077.95, "total_tokens": 305104} {"current_steps": 3390, "total_steps": 76960, "loss": 0.4255, "lr": 2.2017931392931394e-05, "epoch": 0.8809771309771309, "percentage": 4.4, "elapsed_time": "0:04:43", "remaining_time": "1:42:31", "throughput": 1078.06, "total_tokens": 305584} {"current_steps": 3395, "total_steps": 76960, "loss": 0.2312, "lr": 2.2050415800415804e-05, "epoch": 0.8822765072765073, "percentage": 4.41, "elapsed_time": "0:04:43", "remaining_time": "1:42:31", "throughput": 1078.12, "total_tokens": 306048} {"current_steps": 3400, "total_steps": 76960, "loss": 0.3106, "lr": 2.208290020790021e-05, "epoch": 0.8835758835758836, "percentage": 4.42, "elapsed_time": "0:04:44", "remaining_time": "1:42:30", "throughput": 1078.06, "total_tokens": 306480} {"current_steps": 3405, "total_steps": 76960, "loss": 0.2871, "lr": 2.2115384615384616e-05, "epoch": 0.8848752598752598, "percentage": 4.42, "elapsed_time": "0:04:44", "remaining_time": "1:42:30", "throughput": 1078.11, "total_tokens": 306944} {"current_steps": 3410, "total_steps": 76960, "loss": 0.2745, "lr": 2.2147869022869026e-05, "epoch": 0.8861746361746362, "percentage": 4.43, "elapsed_time": "0:04:45", "remaining_time": "1:42:29", "throughput": 1078.11, "total_tokens": 307392} {"current_steps": 3415, "total_steps": 76960, "loss": 0.3078, "lr": 2.2180353430353432e-05, "epoch": 0.8874740124740125, "percentage": 4.44, "elapsed_time": "0:04:45", "remaining_time": "1:42:29", "throughput": 1078.15, "total_tokens": 307856} {"current_steps": 3420, "total_steps": 76960, "loss": 0.2442, "lr": 2.221283783783784e-05, "epoch": 0.8887733887733887, "percentage": 4.44, "elapsed_time": "0:04:45", "remaining_time": "1:42:28", "throughput": 1078.09, "total_tokens": 308288} {"current_steps": 3425, "total_steps": 76960, "loss": 0.2251, "lr": 2.2245322245322248e-05, "epoch": 0.8900727650727651, "percentage": 4.45, "elapsed_time": "0:04:46", "remaining_time": "1:42:28", "throughput": 1077.98, "total_tokens": 308704} {"current_steps": 3430, "total_steps": 76960, "loss": 0.2622, "lr": 2.2277806652806654e-05, "epoch": 0.8913721413721414, "percentage": 4.46, "elapsed_time": "0:04:46", "remaining_time": "1:42:27", "throughput": 1078.04, "total_tokens": 309168} {"current_steps": 3435, "total_steps": 76960, "loss": 0.0923, "lr": 2.231029106029106e-05, "epoch": 0.8926715176715176, "percentage": 4.46, "elapsed_time": "0:04:47", "remaining_time": "1:42:27", "throughput": 1078.16, "total_tokens": 309648} {"current_steps": 3440, "total_steps": 76960, "loss": 0.2287, "lr": 2.2342775467775467e-05, "epoch": 0.893970893970894, "percentage": 4.47, "elapsed_time": "0:04:47", "remaining_time": "1:42:26", "throughput": 1078.28, "total_tokens": 310128} {"current_steps": 3445, "total_steps": 76960, "loss": 0.4678, "lr": 2.2375259875259877e-05, "epoch": 0.8952702702702703, "percentage": 4.48, "elapsed_time": "0:04:48", "remaining_time": "1:42:26", "throughput": 1078.29, "total_tokens": 310576} {"current_steps": 3450, "total_steps": 76960, "loss": 0.2791, "lr": 2.2407744282744283e-05, "epoch": 0.8965696465696466, "percentage": 4.48, "elapsed_time": "0:04:48", "remaining_time": "1:42:25", "throughput": 1078.35, "total_tokens": 311040} {"current_steps": 3455, "total_steps": 76960, "loss": 0.299, "lr": 2.244022869022869e-05, "epoch": 0.8978690228690228, "percentage": 4.49, "elapsed_time": "0:04:48", "remaining_time": "1:42:25", "throughput": 1078.36, "total_tokens": 311488} {"current_steps": 3460, "total_steps": 76960, "loss": 0.27, "lr": 2.24727130977131e-05, "epoch": 0.8991683991683992, "percentage": 4.5, "elapsed_time": "0:04:49", "remaining_time": "1:42:24", "throughput": 1078.37, "total_tokens": 311936} {"current_steps": 3465, "total_steps": 76960, "loss": 0.2766, "lr": 2.2505197505197505e-05, "epoch": 0.9004677754677755, "percentage": 4.5, "elapsed_time": "0:04:49", "remaining_time": "1:42:24", "throughput": 1078.31, "total_tokens": 312368} {"current_steps": 3470, "total_steps": 76960, "loss": 0.2977, "lr": 2.253768191268191e-05, "epoch": 0.9017671517671517, "percentage": 4.51, "elapsed_time": "0:04:50", "remaining_time": "1:42:23", "throughput": 1078.55, "total_tokens": 312880} {"current_steps": 3475, "total_steps": 76960, "loss": 0.2735, "lr": 2.257016632016632e-05, "epoch": 0.9030665280665281, "percentage": 4.52, "elapsed_time": "0:04:50", "remaining_time": "1:42:23", "throughput": 1078.61, "total_tokens": 313344} {"current_steps": 3480, "total_steps": 76960, "loss": 0.228, "lr": 2.2602650727650727e-05, "epoch": 0.9043659043659044, "percentage": 4.52, "elapsed_time": "0:04:50", "remaining_time": "1:42:22", "throughput": 1078.44, "total_tokens": 313744} {"current_steps": 3485, "total_steps": 76960, "loss": 0.3226, "lr": 2.2635135135135137e-05, "epoch": 0.9056652806652806, "percentage": 4.53, "elapsed_time": "0:04:51", "remaining_time": "1:42:22", "throughput": 1078.38, "total_tokens": 314176} {"current_steps": 3490, "total_steps": 76960, "loss": 0.2728, "lr": 2.2667619542619543e-05, "epoch": 0.906964656964657, "percentage": 4.53, "elapsed_time": "0:04:51", "remaining_time": "1:42:21", "throughput": 1078.39, "total_tokens": 314624} {"current_steps": 3495, "total_steps": 76960, "loss": 0.2262, "lr": 2.2700103950103953e-05, "epoch": 0.9082640332640333, "percentage": 4.54, "elapsed_time": "0:04:52", "remaining_time": "1:42:21", "throughput": 1078.44, "total_tokens": 315088} {"current_steps": 3500, "total_steps": 76960, "loss": 0.2946, "lr": 2.273258835758836e-05, "epoch": 0.9095634095634095, "percentage": 4.55, "elapsed_time": "0:04:52", "remaining_time": "1:42:20", "throughput": 1078.39, "total_tokens": 315520} {"current_steps": 3505, "total_steps": 76960, "loss": 0.2958, "lr": 2.276507276507277e-05, "epoch": 0.9108627858627859, "percentage": 4.55, "elapsed_time": "0:04:52", "remaining_time": "1:42:20", "throughput": 1078.34, "total_tokens": 315952} {"current_steps": 3510, "total_steps": 76960, "loss": 0.2548, "lr": 2.2797557172557175e-05, "epoch": 0.9121621621621622, "percentage": 4.56, "elapsed_time": "0:04:53", "remaining_time": "1:42:19", "throughput": 1078.28, "total_tokens": 316384} {"current_steps": 3515, "total_steps": 76960, "loss": 0.206, "lr": 2.283004158004158e-05, "epoch": 0.9134615384615384, "percentage": 4.57, "elapsed_time": "0:04:53", "remaining_time": "1:42:19", "throughput": 1078.28, "total_tokens": 316832} {"current_steps": 3520, "total_steps": 76960, "loss": 0.2743, "lr": 2.2862525987525988e-05, "epoch": 0.9147609147609148, "percentage": 4.57, "elapsed_time": "0:04:54", "remaining_time": "1:42:19", "throughput": 1078.28, "total_tokens": 317280} {"current_steps": 3525, "total_steps": 76960, "loss": 0.1572, "lr": 2.2895010395010397e-05, "epoch": 0.9160602910602911, "percentage": 4.58, "elapsed_time": "0:04:54", "remaining_time": "1:42:18", "throughput": 1078.28, "total_tokens": 317728} {"current_steps": 3530, "total_steps": 76960, "loss": 0.3265, "lr": 2.2927494802494803e-05, "epoch": 0.9173596673596673, "percentage": 4.59, "elapsed_time": "0:04:55", "remaining_time": "1:42:18", "throughput": 1078.33, "total_tokens": 318192} {"current_steps": 3535, "total_steps": 76960, "loss": 0.3673, "lr": 2.295997920997921e-05, "epoch": 0.9186590436590436, "percentage": 4.59, "elapsed_time": "0:04:55", "remaining_time": "1:42:17", "throughput": 1078.44, "total_tokens": 318672} {"current_steps": 3540, "total_steps": 76960, "loss": 0.2735, "lr": 2.299246361746362e-05, "epoch": 0.91995841995842, "percentage": 4.6, "elapsed_time": "0:04:55", "remaining_time": "1:42:17", "throughput": 1078.39, "total_tokens": 319104} {"current_steps": 3545, "total_steps": 76960, "loss": 0.2906, "lr": 2.3024948024948026e-05, "epoch": 0.9212577962577962, "percentage": 4.61, "elapsed_time": "0:04:56", "remaining_time": "1:42:16", "throughput": 1078.5, "total_tokens": 319584} {"current_steps": 3550, "total_steps": 76960, "loss": 0.2939, "lr": 2.3057432432432432e-05, "epoch": 0.9225571725571725, "percentage": 4.61, "elapsed_time": "0:04:56", "remaining_time": "1:42:16", "throughput": 1078.56, "total_tokens": 320048} {"current_steps": 3555, "total_steps": 76960, "loss": 0.3249, "lr": 2.308991683991684e-05, "epoch": 0.9238565488565489, "percentage": 4.62, "elapsed_time": "0:04:57", "remaining_time": "1:42:15", "throughput": 1078.66, "total_tokens": 320528} {"current_steps": 3560, "total_steps": 76960, "loss": 0.288, "lr": 2.3122401247401248e-05, "epoch": 0.9251559251559252, "percentage": 4.63, "elapsed_time": "0:04:57", "remaining_time": "1:42:15", "throughput": 1078.5, "total_tokens": 320928} {"current_steps": 3565, "total_steps": 76960, "loss": 0.2691, "lr": 2.3154885654885654e-05, "epoch": 0.9264553014553014, "percentage": 4.63, "elapsed_time": "0:04:57", "remaining_time": "1:42:14", "throughput": 1078.39, "total_tokens": 321344} {"current_steps": 3570, "total_steps": 76960, "loss": 0.3027, "lr": 2.3187370062370064e-05, "epoch": 0.9277546777546778, "percentage": 4.64, "elapsed_time": "0:04:58", "remaining_time": "1:42:14", "throughput": 1078.49, "total_tokens": 321824} {"current_steps": 3575, "total_steps": 76960, "loss": 0.2503, "lr": 2.321985446985447e-05, "epoch": 0.9290540540540541, "percentage": 4.65, "elapsed_time": "0:04:58", "remaining_time": "1:42:13", "throughput": 1078.43, "total_tokens": 322256} {"current_steps": 3580, "total_steps": 76960, "loss": 0.2139, "lr": 2.3252338877338876e-05, "epoch": 0.9303534303534303, "percentage": 4.65, "elapsed_time": "0:04:59", "remaining_time": "1:42:13", "throughput": 1078.32, "total_tokens": 322672} {"current_steps": 3585, "total_steps": 76960, "loss": 0.272, "lr": 2.3284823284823286e-05, "epoch": 0.9316528066528067, "percentage": 4.66, "elapsed_time": "0:04:59", "remaining_time": "1:42:13", "throughput": 1078.32, "total_tokens": 323120} {"current_steps": 3590, "total_steps": 76960, "loss": 0.2562, "lr": 2.3317307692307692e-05, "epoch": 0.932952182952183, "percentage": 4.66, "elapsed_time": "0:05:00", "remaining_time": "1:42:12", "throughput": 1078.43, "total_tokens": 323600} {"current_steps": 3595, "total_steps": 76960, "loss": 0.2211, "lr": 2.3349792099792102e-05, "epoch": 0.9342515592515592, "percentage": 4.67, "elapsed_time": "0:05:00", "remaining_time": "1:42:12", "throughput": 1078.42, "total_tokens": 324048} {"current_steps": 3600, "total_steps": 76960, "loss": 0.1482, "lr": 2.3382276507276508e-05, "epoch": 0.9355509355509356, "percentage": 4.68, "elapsed_time": "0:05:00", "remaining_time": "1:42:11", "throughput": 1078.47, "total_tokens": 324512} {"current_steps": 3605, "total_steps": 76960, "loss": 0.3235, "lr": 2.3414760914760918e-05, "epoch": 0.9368503118503119, "percentage": 4.68, "elapsed_time": "0:05:01", "remaining_time": "1:42:11", "throughput": 1078.69, "total_tokens": 325024} {"current_steps": 3610, "total_steps": 76960, "loss": 0.3255, "lr": 2.3447245322245324e-05, "epoch": 0.9381496881496881, "percentage": 4.69, "elapsed_time": "0:05:01", "remaining_time": "1:42:10", "throughput": 1078.63, "total_tokens": 325456} {"current_steps": 3615, "total_steps": 76960, "loss": 0.2684, "lr": 2.347972972972973e-05, "epoch": 0.9394490644490644, "percentage": 4.7, "elapsed_time": "0:05:02", "remaining_time": "1:42:10", "throughput": 1078.69, "total_tokens": 325920} {"current_steps": 3620, "total_steps": 76960, "loss": 0.2964, "lr": 2.351221413721414e-05, "epoch": 0.9407484407484408, "percentage": 4.7, "elapsed_time": "0:05:02", "remaining_time": "1:42:09", "throughput": 1078.63, "total_tokens": 326352} {"current_steps": 3625, "total_steps": 76960, "loss": 0.2189, "lr": 2.3544698544698546e-05, "epoch": 0.942047817047817, "percentage": 4.71, "elapsed_time": "0:05:02", "remaining_time": "1:42:09", "throughput": 1078.69, "total_tokens": 326816} {"current_steps": 3630, "total_steps": 76960, "loss": 0.2858, "lr": 2.3577182952182953e-05, "epoch": 0.9433471933471933, "percentage": 4.72, "elapsed_time": "0:05:03", "remaining_time": "1:42:08", "throughput": 1078.8, "total_tokens": 327296} {"current_steps": 3635, "total_steps": 76960, "loss": 0.3241, "lr": 2.3609667359667362e-05, "epoch": 0.9446465696465697, "percentage": 4.72, "elapsed_time": "0:05:03", "remaining_time": "1:42:08", "throughput": 1078.91, "total_tokens": 327776} {"current_steps": 3640, "total_steps": 76960, "loss": 0.1677, "lr": 2.364215176715177e-05, "epoch": 0.9459459459459459, "percentage": 4.73, "elapsed_time": "0:05:04", "remaining_time": "1:42:07", "throughput": 1078.91, "total_tokens": 328224} {"current_steps": 3645, "total_steps": 76960, "loss": 0.2443, "lr": 2.3674636174636175e-05, "epoch": 0.9472453222453222, "percentage": 4.74, "elapsed_time": "0:05:04", "remaining_time": "1:42:07", "throughput": 1078.86, "total_tokens": 328656} {"current_steps": 3650, "total_steps": 76960, "loss": 0.3226, "lr": 2.3707120582120584e-05, "epoch": 0.9485446985446986, "percentage": 4.74, "elapsed_time": "0:05:05", "remaining_time": "1:42:06", "throughput": 1078.86, "total_tokens": 329104} {"current_steps": 3655, "total_steps": 76960, "loss": 0.2662, "lr": 2.373960498960499e-05, "epoch": 0.9498440748440748, "percentage": 4.75, "elapsed_time": "0:05:05", "remaining_time": "1:42:06", "throughput": 1078.97, "total_tokens": 329584} {"current_steps": 3660, "total_steps": 76960, "loss": 0.2212, "lr": 2.3772089397089397e-05, "epoch": 0.9511434511434511, "percentage": 4.76, "elapsed_time": "0:05:05", "remaining_time": "1:42:05", "throughput": 1079.13, "total_tokens": 330080} {"current_steps": 3665, "total_steps": 76960, "loss": 0.2586, "lr": 2.3804573804573807e-05, "epoch": 0.9524428274428275, "percentage": 4.76, "elapsed_time": "0:05:06", "remaining_time": "1:42:05", "throughput": 1079.02, "total_tokens": 330496} {"current_steps": 3670, "total_steps": 76960, "loss": 0.243, "lr": 2.3837058212058213e-05, "epoch": 0.9537422037422038, "percentage": 4.77, "elapsed_time": "0:05:06", "remaining_time": "1:42:04", "throughput": 1079.02, "total_tokens": 330944} {"current_steps": 3675, "total_steps": 76960, "loss": 0.1934, "lr": 2.386954261954262e-05, "epoch": 0.95504158004158, "percentage": 4.78, "elapsed_time": "0:05:07", "remaining_time": "1:42:04", "throughput": 1079.18, "total_tokens": 331440} {"current_steps": 3680, "total_steps": 76960, "loss": 0.406, "lr": 2.3902027027027025e-05, "epoch": 0.9563409563409564, "percentage": 4.78, "elapsed_time": "0:05:07", "remaining_time": "1:42:03", "throughput": 1079.19, "total_tokens": 331888} {"current_steps": 3685, "total_steps": 76960, "loss": 0.1846, "lr": 2.3934511434511435e-05, "epoch": 0.9576403326403327, "percentage": 4.79, "elapsed_time": "0:05:07", "remaining_time": "1:42:03", "throughput": 1079.24, "total_tokens": 332352} {"current_steps": 3690, "total_steps": 76960, "loss": 0.2223, "lr": 2.396699584199584e-05, "epoch": 0.9589397089397089, "percentage": 4.79, "elapsed_time": "0:05:08", "remaining_time": "1:42:02", "throughput": 1079.14, "total_tokens": 332768} {"current_steps": 3695, "total_steps": 76960, "loss": 0.3355, "lr": 2.399948024948025e-05, "epoch": 0.9602390852390852, "percentage": 4.8, "elapsed_time": "0:05:08", "remaining_time": "1:42:02", "throughput": 1079.19, "total_tokens": 333232} {"current_steps": 3700, "total_steps": 76960, "loss": 0.2948, "lr": 2.403196465696466e-05, "epoch": 0.9615384615384616, "percentage": 4.81, "elapsed_time": "0:05:09", "remaining_time": "1:42:02", "throughput": 1079.19, "total_tokens": 333680} {"current_steps": 3705, "total_steps": 76960, "loss": 0.2973, "lr": 2.4064449064449067e-05, "epoch": 0.9628378378378378, "percentage": 4.81, "elapsed_time": "0:05:09", "remaining_time": "1:42:01", "throughput": 1079.23, "total_tokens": 334144} {"current_steps": 3710, "total_steps": 76960, "loss": 0.2871, "lr": 2.4096933471933473e-05, "epoch": 0.9641372141372141, "percentage": 4.82, "elapsed_time": "0:05:10", "remaining_time": "1:42:01", "throughput": 1079.23, "total_tokens": 334592} {"current_steps": 3715, "total_steps": 76960, "loss": 0.2912, "lr": 2.4129417879417883e-05, "epoch": 0.9654365904365905, "percentage": 4.83, "elapsed_time": "0:05:10", "remaining_time": "1:42:00", "throughput": 1079.12, "total_tokens": 335008} {"current_steps": 3720, "total_steps": 76960, "loss": 0.28, "lr": 2.416190228690229e-05, "epoch": 0.9667359667359667, "percentage": 4.83, "elapsed_time": "0:05:10", "remaining_time": "1:42:00", "throughput": 1079.13, "total_tokens": 335456} {"current_steps": 3725, "total_steps": 76960, "loss": 0.2782, "lr": 2.4194386694386695e-05, "epoch": 0.968035343035343, "percentage": 4.84, "elapsed_time": "0:05:11", "remaining_time": "1:41:59", "throughput": 1079.08, "total_tokens": 335888} {"current_steps": 3730, "total_steps": 76960, "loss": 0.2964, "lr": 2.4226871101871105e-05, "epoch": 0.9693347193347194, "percentage": 4.85, "elapsed_time": "0:05:11", "remaining_time": "1:41:59", "throughput": 1079.08, "total_tokens": 336336} {"current_steps": 3735, "total_steps": 76960, "loss": 0.2335, "lr": 2.425935550935551e-05, "epoch": 0.9706340956340956, "percentage": 4.85, "elapsed_time": "0:05:12", "remaining_time": "1:41:58", "throughput": 1079.08, "total_tokens": 336784} {"current_steps": 3740, "total_steps": 76960, "loss": 0.2201, "lr": 2.4291839916839917e-05, "epoch": 0.9719334719334719, "percentage": 4.86, "elapsed_time": "0:05:12", "remaining_time": "1:41:58", "throughput": 1079.19, "total_tokens": 337264} {"current_steps": 3745, "total_steps": 76960, "loss": 0.2689, "lr": 2.4324324324324327e-05, "epoch": 0.9732328482328483, "percentage": 4.87, "elapsed_time": "0:05:12", "remaining_time": "1:41:57", "throughput": 1079.08, "total_tokens": 337680} {"current_steps": 3750, "total_steps": 76960, "loss": 0.1906, "lr": 2.4356808731808733e-05, "epoch": 0.9745322245322245, "percentage": 4.87, "elapsed_time": "0:05:13", "remaining_time": "1:41:57", "throughput": 1079.03, "total_tokens": 338112} {"current_steps": 3755, "total_steps": 76960, "loss": 0.2836, "lr": 2.438929313929314e-05, "epoch": 0.9758316008316008, "percentage": 4.88, "elapsed_time": "0:05:13", "remaining_time": "1:41:56", "throughput": 1079.02, "total_tokens": 338560} {"current_steps": 3760, "total_steps": 76960, "loss": 0.2805, "lr": 2.4421777546777546e-05, "epoch": 0.9771309771309772, "percentage": 4.89, "elapsed_time": "0:05:14", "remaining_time": "1:41:56", "throughput": 1079.12, "total_tokens": 339040} {"current_steps": 3765, "total_steps": 76960, "loss": 0.2475, "lr": 2.4454261954261956e-05, "epoch": 0.9784303534303534, "percentage": 4.89, "elapsed_time": "0:05:14", "remaining_time": "1:41:56", "throughput": 1079.17, "total_tokens": 339504} {"current_steps": 3770, "total_steps": 76960, "loss": 0.2582, "lr": 2.4486746361746362e-05, "epoch": 0.9797297297297297, "percentage": 4.9, "elapsed_time": "0:05:15", "remaining_time": "1:41:55", "throughput": 1079.11, "total_tokens": 339936} {"current_steps": 3775, "total_steps": 76960, "loss": 0.2666, "lr": 2.4519230769230768e-05, "epoch": 0.981029106029106, "percentage": 4.91, "elapsed_time": "0:05:15", "remaining_time": "1:41:55", "throughput": 1078.99, "total_tokens": 340352} {"current_steps": 3780, "total_steps": 76960, "loss": 0.2573, "lr": 2.4551715176715178e-05, "epoch": 0.9823284823284824, "percentage": 4.91, "elapsed_time": "0:05:15", "remaining_time": "1:41:54", "throughput": 1079.09, "total_tokens": 340832} {"current_steps": 3785, "total_steps": 76960, "loss": 0.2612, "lr": 2.4584199584199584e-05, "epoch": 0.9836278586278586, "percentage": 4.92, "elapsed_time": "0:05:16", "remaining_time": "1:41:54", "throughput": 1079.14, "total_tokens": 341296} {"current_steps": 3790, "total_steps": 76960, "loss": 0.3082, "lr": 2.461668399168399e-05, "epoch": 0.9849272349272349, "percentage": 4.92, "elapsed_time": "0:05:16", "remaining_time": "1:41:53", "throughput": 1079.04, "total_tokens": 341712} {"current_steps": 3795, "total_steps": 76960, "loss": 0.2575, "lr": 2.46491683991684e-05, "epoch": 0.9862266112266113, "percentage": 4.93, "elapsed_time": "0:05:17", "remaining_time": "1:41:53", "throughput": 1078.99, "total_tokens": 342144} {"current_steps": 3800, "total_steps": 76960, "loss": 0.1976, "lr": 2.468165280665281e-05, "epoch": 0.9875259875259875, "percentage": 4.94, "elapsed_time": "0:05:17", "remaining_time": "1:41:52", "throughput": 1078.94, "total_tokens": 342576} {"current_steps": 3805, "total_steps": 76960, "loss": 0.2573, "lr": 2.4714137214137216e-05, "epoch": 0.9888253638253638, "percentage": 4.94, "elapsed_time": "0:05:17", "remaining_time": "1:41:52", "throughput": 1078.94, "total_tokens": 343024} {"current_steps": 3810, "total_steps": 76960, "loss": 0.1887, "lr": 2.4746621621621626e-05, "epoch": 0.9901247401247402, "percentage": 4.95, "elapsed_time": "0:05:18", "remaining_time": "1:41:52", "throughput": 1078.89, "total_tokens": 343456} {"current_steps": 3815, "total_steps": 76960, "loss": 0.3847, "lr": 2.4779106029106032e-05, "epoch": 0.9914241164241164, "percentage": 4.96, "elapsed_time": "0:05:18", "remaining_time": "1:41:51", "throughput": 1078.89, "total_tokens": 343904} {"current_steps": 3820, "total_steps": 76960, "loss": 0.2484, "lr": 2.4811590436590438e-05, "epoch": 0.9927234927234927, "percentage": 4.96, "elapsed_time": "0:05:19", "remaining_time": "1:41:51", "throughput": 1079.1, "total_tokens": 344416} {"current_steps": 3825, "total_steps": 76960, "loss": 0.2193, "lr": 2.4844074844074848e-05, "epoch": 0.9940228690228691, "percentage": 4.97, "elapsed_time": "0:05:19", "remaining_time": "1:41:50", "throughput": 1079.05, "total_tokens": 344848} {"current_steps": 3830, "total_steps": 76960, "loss": 0.1902, "lr": 2.4876559251559254e-05, "epoch": 0.9953222453222453, "percentage": 4.98, "elapsed_time": "0:05:19", "remaining_time": "1:41:50", "throughput": 1079.11, "total_tokens": 345312} {"current_steps": 3835, "total_steps": 76960, "loss": 0.266, "lr": 2.490904365904366e-05, "epoch": 0.9966216216216216, "percentage": 4.98, "elapsed_time": "0:05:20", "remaining_time": "1:41:49", "throughput": 1079.06, "total_tokens": 345744} {"current_steps": 3840, "total_steps": 76960, "loss": 0.0978, "lr": 2.4941528066528067e-05, "epoch": 0.997920997920998, "percentage": 4.99, "elapsed_time": "0:05:20", "remaining_time": "1:41:49", "throughput": 1079.02, "total_tokens": 346176} {"current_steps": 3845, "total_steps": 76960, "loss": 0.1268, "lr": 2.4974012474012476e-05, "epoch": 0.9992203742203742, "percentage": 5.0, "elapsed_time": "0:05:21", "remaining_time": "1:41:48", "throughput": 1079.2, "total_tokens": 346672} {"current_steps": 3848, "total_steps": 76960, "eval_loss": 0.28198137879371643, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:05:34", "remaining_time": "1:45:59", "throughput": 1036.4, "total_tokens": 346872} {"current_steps": 3850, "total_steps": 76960, "loss": 0.3316, "lr": 2.5006496881496882e-05, "epoch": 1.0005197505197505, "percentage": 5.0, "elapsed_time": "0:05:36", "remaining_time": "1:46:26", "throughput": 1031.94, "total_tokens": 347064} {"current_steps": 3855, "total_steps": 76960, "loss": 0.3127, "lr": 2.503898128898129e-05, "epoch": 1.0018191268191268, "percentage": 5.01, "elapsed_time": "0:05:36", "remaining_time": "1:46:26", "throughput": 1031.96, "total_tokens": 347512} {"current_steps": 3860, "total_steps": 76960, "loss": 0.2969, "lr": 2.5071465696465695e-05, "epoch": 1.003118503118503, "percentage": 5.02, "elapsed_time": "0:05:37", "remaining_time": "1:46:26", "throughput": 1031.8, "total_tokens": 347976} {"current_steps": 3865, "total_steps": 76960, "loss": 0.3167, "lr": 2.51039501039501e-05, "epoch": 1.0044178794178795, "percentage": 5.02, "elapsed_time": "0:05:37", "remaining_time": "1:46:26", "throughput": 1031.73, "total_tokens": 348424} {"current_steps": 3870, "total_steps": 76960, "loss": 0.2714, "lr": 2.5136434511434514e-05, "epoch": 1.0057172557172558, "percentage": 5.03, "elapsed_time": "0:05:38", "remaining_time": "1:46:26", "throughput": 1031.78, "total_tokens": 348888} {"current_steps": 3875, "total_steps": 76960, "loss": 0.2912, "lr": 2.516891891891892e-05, "epoch": 1.007016632016632, "percentage": 5.04, "elapsed_time": "0:05:38", "remaining_time": "1:46:26", "throughput": 1031.73, "total_tokens": 349336} {"current_steps": 3880, "total_steps": 76960, "loss": 0.2847, "lr": 2.5201403326403327e-05, "epoch": 1.0083160083160083, "percentage": 5.04, "elapsed_time": "0:05:39", "remaining_time": "1:46:25", "throughput": 1031.77, "total_tokens": 349784} {"current_steps": 3885, "total_steps": 76960, "loss": 0.24, "lr": 2.5233887733887733e-05, "epoch": 1.0096153846153846, "percentage": 5.05, "elapsed_time": "0:05:39", "remaining_time": "1:46:24", "throughput": 1031.77, "total_tokens": 350216} {"current_steps": 3890, "total_steps": 76960, "loss": 0.2767, "lr": 2.526637214137214e-05, "epoch": 1.0109147609147608, "percentage": 5.05, "elapsed_time": "0:05:39", "remaining_time": "1:46:24", "throughput": 1031.83, "total_tokens": 350696} {"current_steps": 3895, "total_steps": 76960, "loss": 0.3065, "lr": 2.529885654885655e-05, "epoch": 1.012214137214137, "percentage": 5.06, "elapsed_time": "0:05:40", "remaining_time": "1:46:23", "throughput": 1031.91, "total_tokens": 351160} {"current_steps": 3900, "total_steps": 76960, "loss": 0.3839, "lr": 2.533134095634096e-05, "epoch": 1.0135135135135136, "percentage": 5.07, "elapsed_time": "0:05:40", "remaining_time": "1:46:22", "throughput": 1031.95, "total_tokens": 351608} {"current_steps": 3905, "total_steps": 76960, "loss": 0.2553, "lr": 2.5363825363825365e-05, "epoch": 1.0148128898128899, "percentage": 5.07, "elapsed_time": "0:05:41", "remaining_time": "1:46:22", "throughput": 1032.0, "total_tokens": 352056} {"current_steps": 3910, "total_steps": 76960, "loss": 0.2986, "lr": 2.5396309771309775e-05, "epoch": 1.0161122661122661, "percentage": 5.08, "elapsed_time": "0:05:41", "remaining_time": "1:46:21", "throughput": 1032.04, "total_tokens": 352504} {"current_steps": 3915, "total_steps": 76960, "loss": 0.2913, "lr": 2.542879417879418e-05, "epoch": 1.0174116424116424, "percentage": 5.09, "elapsed_time": "0:05:41", "remaining_time": "1:46:20", "throughput": 1032.04, "total_tokens": 352936} {"current_steps": 3920, "total_steps": 76960, "loss": 0.3258, "lr": 2.5461278586278587e-05, "epoch": 1.0187110187110187, "percentage": 5.09, "elapsed_time": "0:05:42", "remaining_time": "1:46:19", "throughput": 1032.09, "total_tokens": 353384} {"current_steps": 3925, "total_steps": 76960, "loss": 0.2987, "lr": 2.5493762993762993e-05, "epoch": 1.020010395010395, "percentage": 5.1, "elapsed_time": "0:05:42", "remaining_time": "1:46:18", "throughput": 1032.24, "total_tokens": 353864} {"current_steps": 3930, "total_steps": 76960, "loss": 0.27, "lr": 2.5526247401247406e-05, "epoch": 1.0213097713097714, "percentage": 5.11, "elapsed_time": "0:05:43", "remaining_time": "1:46:18", "throughput": 1032.32, "total_tokens": 354328} {"current_steps": 3935, "total_steps": 76960, "loss": 0.2499, "lr": 2.5558731808731813e-05, "epoch": 1.0226091476091477, "percentage": 5.11, "elapsed_time": "0:05:43", "remaining_time": "1:46:17", "throughput": 1032.36, "total_tokens": 354776} {"current_steps": 3940, "total_steps": 76960, "loss": 0.2133, "lr": 2.559121621621622e-05, "epoch": 1.023908523908524, "percentage": 5.12, "elapsed_time": "0:05:44", "remaining_time": "1:46:16", "throughput": 1032.5, "total_tokens": 355256} {"current_steps": 3945, "total_steps": 76960, "loss": 0.292, "lr": 2.5623700623700625e-05, "epoch": 1.0252079002079002, "percentage": 5.13, "elapsed_time": "0:05:44", "remaining_time": "1:46:15", "throughput": 1032.5, "total_tokens": 355688} {"current_steps": 3950, "total_steps": 76960, "loss": 0.2222, "lr": 2.565618503118503e-05, "epoch": 1.0265072765072765, "percentage": 5.13, "elapsed_time": "0:05:44", "remaining_time": "1:46:15", "throughput": 1032.49, "total_tokens": 356120} {"current_steps": 3955, "total_steps": 76960, "loss": 0.2655, "lr": 2.5688669438669438e-05, "epoch": 1.0278066528066527, "percentage": 5.14, "elapsed_time": "0:05:45", "remaining_time": "1:46:14", "throughput": 1032.62, "total_tokens": 356600} {"current_steps": 3960, "total_steps": 76960, "loss": 0.2102, "lr": 2.5721153846153844e-05, "epoch": 1.0291060291060292, "percentage": 5.15, "elapsed_time": "0:05:45", "remaining_time": "1:46:13", "throughput": 1032.57, "total_tokens": 357016} {"current_steps": 3965, "total_steps": 76960, "loss": 0.2035, "lr": 2.5753638253638257e-05, "epoch": 1.0304054054054055, "percentage": 5.15, "elapsed_time": "0:05:46", "remaining_time": "1:46:13", "throughput": 1032.61, "total_tokens": 357464} {"current_steps": 3970, "total_steps": 76960, "loss": 0.3703, "lr": 2.5786122661122663e-05, "epoch": 1.0317047817047817, "percentage": 5.16, "elapsed_time": "0:05:46", "remaining_time": "1:46:12", "throughput": 1032.56, "total_tokens": 357880} {"current_steps": 3975, "total_steps": 76960, "loss": 0.2644, "lr": 2.581860706860707e-05, "epoch": 1.033004158004158, "percentage": 5.17, "elapsed_time": "0:05:47", "remaining_time": "1:46:11", "throughput": 1032.56, "total_tokens": 358312} {"current_steps": 3980, "total_steps": 76960, "loss": 0.2386, "lr": 2.5851091476091476e-05, "epoch": 1.0343035343035343, "percentage": 5.17, "elapsed_time": "0:05:47", "remaining_time": "1:46:10", "throughput": 1032.65, "total_tokens": 358776} {"current_steps": 3985, "total_steps": 76960, "loss": 0.2951, "lr": 2.5883575883575882e-05, "epoch": 1.0356029106029105, "percentage": 5.18, "elapsed_time": "0:05:47", "remaining_time": "1:46:10", "throughput": 1032.69, "total_tokens": 359224} {"current_steps": 3990, "total_steps": 76960, "loss": 0.2782, "lr": 2.591606029106029e-05, "epoch": 1.0369022869022868, "percentage": 5.18, "elapsed_time": "0:05:48", "remaining_time": "1:46:09", "throughput": 1032.78, "total_tokens": 359688} {"current_steps": 3995, "total_steps": 76960, "loss": 0.2713, "lr": 2.59485446985447e-05, "epoch": 1.0382016632016633, "percentage": 5.19, "elapsed_time": "0:05:48", "remaining_time": "1:46:08", "throughput": 1032.82, "total_tokens": 360136} {"current_steps": 4000, "total_steps": 76960, "loss": 0.2276, "lr": 2.5981029106029108e-05, "epoch": 1.0395010395010396, "percentage": 5.2, "elapsed_time": "0:05:49", "remaining_time": "1:46:07", "throughput": 1032.91, "total_tokens": 360600} {"current_steps": 4005, "total_steps": 76960, "loss": 0.3163, "lr": 2.6013513513513514e-05, "epoch": 1.0408004158004158, "percentage": 5.2, "elapsed_time": "0:05:49", "remaining_time": "1:46:07", "throughput": 1033.0, "total_tokens": 361064} {"current_steps": 4010, "total_steps": 76960, "loss": 0.193, "lr": 2.6045997920997924e-05, "epoch": 1.042099792099792, "percentage": 5.21, "elapsed_time": "0:05:49", "remaining_time": "1:46:06", "throughput": 1032.96, "total_tokens": 361480} {"current_steps": 4015, "total_steps": 76960, "loss": 0.2601, "lr": 2.607848232848233e-05, "epoch": 1.0433991683991684, "percentage": 5.22, "elapsed_time": "0:05:50", "remaining_time": "1:46:05", "throughput": 1033.05, "total_tokens": 361944} {"current_steps": 4020, "total_steps": 76960, "loss": 0.3448, "lr": 2.6110966735966736e-05, "epoch": 1.0446985446985446, "percentage": 5.22, "elapsed_time": "0:05:50", "remaining_time": "1:46:04", "throughput": 1033.15, "total_tokens": 362408} {"current_steps": 4025, "total_steps": 76960, "loss": 0.2211, "lr": 2.6143451143451142e-05, "epoch": 1.045997920997921, "percentage": 5.23, "elapsed_time": "0:05:51", "remaining_time": "1:46:03", "throughput": 1033.2, "total_tokens": 362856} {"current_steps": 4030, "total_steps": 76960, "loss": 0.2673, "lr": 2.6175935550935555e-05, "epoch": 1.0472972972972974, "percentage": 5.24, "elapsed_time": "0:05:51", "remaining_time": "1:46:02", "throughput": 1033.35, "total_tokens": 363336} {"current_steps": 4035, "total_steps": 76960, "loss": 0.2269, "lr": 2.6208419958419962e-05, "epoch": 1.0485966735966736, "percentage": 5.24, "elapsed_time": "0:05:52", "remaining_time": "1:46:02", "throughput": 1033.45, "total_tokens": 363800} {"current_steps": 4040, "total_steps": 76960, "loss": 0.2845, "lr": 2.6240904365904368e-05, "epoch": 1.04989604989605, "percentage": 5.25, "elapsed_time": "0:05:52", "remaining_time": "1:46:01", "throughput": 1033.45, "total_tokens": 364232} {"current_steps": 4045, "total_steps": 76960, "loss": 0.2148, "lr": 2.6273388773388774e-05, "epoch": 1.0511954261954262, "percentage": 5.26, "elapsed_time": "0:05:52", "remaining_time": "1:46:00", "throughput": 1033.59, "total_tokens": 364712} {"current_steps": 4050, "total_steps": 76960, "loss": 0.2147, "lr": 2.630587318087318e-05, "epoch": 1.0524948024948024, "percentage": 5.26, "elapsed_time": "0:05:53", "remaining_time": "1:45:59", "throughput": 1033.69, "total_tokens": 365176} {"current_steps": 4055, "total_steps": 76960, "loss": 0.1555, "lr": 2.6338357588357587e-05, "epoch": 1.0537941787941787, "percentage": 5.27, "elapsed_time": "0:05:53", "remaining_time": "1:45:59", "throughput": 1033.83, "total_tokens": 365656} {"current_steps": 4060, "total_steps": 76960, "loss": 0.3733, "lr": 2.6370841995842e-05, "epoch": 1.0550935550935552, "percentage": 5.28, "elapsed_time": "0:05:54", "remaining_time": "1:45:58", "throughput": 1033.97, "total_tokens": 366136} {"current_steps": 4065, "total_steps": 76960, "loss": 0.1949, "lr": 2.6403326403326406e-05, "epoch": 1.0563929313929314, "percentage": 5.28, "elapsed_time": "0:05:54", "remaining_time": "1:45:57", "throughput": 1034.07, "total_tokens": 366600} {"current_steps": 4070, "total_steps": 76960, "loss": 0.1996, "lr": 2.6435810810810812e-05, "epoch": 1.0576923076923077, "percentage": 5.29, "elapsed_time": "0:05:54", "remaining_time": "1:45:56", "throughput": 1034.16, "total_tokens": 367064} {"current_steps": 4075, "total_steps": 76960, "loss": 0.2949, "lr": 2.646829521829522e-05, "epoch": 1.058991683991684, "percentage": 5.29, "elapsed_time": "0:05:55", "remaining_time": "1:45:55", "throughput": 1034.26, "total_tokens": 367528} {"current_steps": 4080, "total_steps": 76960, "loss": 0.2706, "lr": 2.6500779625779625e-05, "epoch": 1.0602910602910602, "percentage": 5.3, "elapsed_time": "0:05:55", "remaining_time": "1:45:55", "throughput": 1034.26, "total_tokens": 367960} {"current_steps": 4085, "total_steps": 76960, "loss": 0.4016, "lr": 2.653326403326403e-05, "epoch": 1.0615904365904365, "percentage": 5.31, "elapsed_time": "0:05:56", "remaining_time": "1:45:54", "throughput": 1034.31, "total_tokens": 368408} {"current_steps": 4090, "total_steps": 76960, "loss": 0.296, "lr": 2.6565748440748444e-05, "epoch": 1.062889812889813, "percentage": 5.31, "elapsed_time": "0:05:56", "remaining_time": "1:45:53", "throughput": 1034.4, "total_tokens": 368872} {"current_steps": 4095, "total_steps": 76960, "loss": 0.3181, "lr": 2.659823284823285e-05, "epoch": 1.0641891891891893, "percentage": 5.32, "elapsed_time": "0:05:57", "remaining_time": "1:45:52", "throughput": 1034.35, "total_tokens": 369288} {"current_steps": 4100, "total_steps": 76960, "loss": 0.2979, "lr": 2.6630717255717257e-05, "epoch": 1.0654885654885655, "percentage": 5.33, "elapsed_time": "0:05:57", "remaining_time": "1:45:51", "throughput": 1034.4, "total_tokens": 369736} {"current_steps": 4105, "total_steps": 76960, "loss": 0.3449, "lr": 2.6663201663201663e-05, "epoch": 1.0667879417879418, "percentage": 5.33, "elapsed_time": "0:05:57", "remaining_time": "1:45:51", "throughput": 1034.52, "total_tokens": 370216} {"current_steps": 4110, "total_steps": 76960, "loss": 0.3188, "lr": 2.6695686070686073e-05, "epoch": 1.068087318087318, "percentage": 5.34, "elapsed_time": "0:05:58", "remaining_time": "1:45:50", "throughput": 1034.58, "total_tokens": 370664} {"current_steps": 4115, "total_steps": 76960, "loss": 0.2693, "lr": 2.672817047817048e-05, "epoch": 1.0693866943866943, "percentage": 5.35, "elapsed_time": "0:05:58", "remaining_time": "1:45:49", "throughput": 1034.63, "total_tokens": 371112} {"current_steps": 4120, "total_steps": 76960, "loss": 0.2364, "lr": 2.6760654885654885e-05, "epoch": 1.0706860706860706, "percentage": 5.35, "elapsed_time": "0:05:59", "remaining_time": "1:45:48", "throughput": 1034.67, "total_tokens": 371560} {"current_steps": 4125, "total_steps": 76960, "loss": 0.499, "lr": 2.6793139293139298e-05, "epoch": 1.071985446985447, "percentage": 5.36, "elapsed_time": "0:05:59", "remaining_time": "1:45:48", "throughput": 1034.81, "total_tokens": 372040} {"current_steps": 4130, "total_steps": 76960, "loss": 0.1734, "lr": 2.6825623700623705e-05, "epoch": 1.0732848232848233, "percentage": 5.37, "elapsed_time": "0:05:59", "remaining_time": "1:45:47", "throughput": 1034.89, "total_tokens": 372504} {"current_steps": 4135, "total_steps": 76960, "loss": 0.373, "lr": 2.685810810810811e-05, "epoch": 1.0745841995841996, "percentage": 5.37, "elapsed_time": "0:06:00", "remaining_time": "1:45:46", "throughput": 1034.88, "total_tokens": 372936} {"current_steps": 4140, "total_steps": 76960, "loss": 0.2816, "lr": 2.6890592515592517e-05, "epoch": 1.0758835758835759, "percentage": 5.38, "elapsed_time": "0:06:00", "remaining_time": "1:45:45", "throughput": 1035.15, "total_tokens": 373464} {"current_steps": 4145, "total_steps": 76960, "loss": 0.1593, "lr": 2.6923076923076923e-05, "epoch": 1.0771829521829521, "percentage": 5.39, "elapsed_time": "0:06:01", "remaining_time": "1:45:45", "throughput": 1035.2, "total_tokens": 373912} {"current_steps": 4150, "total_steps": 76960, "loss": 0.2522, "lr": 2.695556133056133e-05, "epoch": 1.0784823284823284, "percentage": 5.39, "elapsed_time": "0:06:01", "remaining_time": "1:45:44", "throughput": 1035.29, "total_tokens": 374376} {"current_steps": 4155, "total_steps": 76960, "loss": 0.1968, "lr": 2.6988045738045743e-05, "epoch": 1.0797817047817049, "percentage": 5.4, "elapsed_time": "0:06:02", "remaining_time": "1:45:43", "throughput": 1035.42, "total_tokens": 374856} {"current_steps": 4160, "total_steps": 76960, "loss": 0.2671, "lr": 2.702053014553015e-05, "epoch": 1.0810810810810811, "percentage": 5.41, "elapsed_time": "0:06:02", "remaining_time": "1:45:42", "throughput": 1035.42, "total_tokens": 375288} {"current_steps": 4165, "total_steps": 76960, "loss": 0.1427, "lr": 2.7053014553014555e-05, "epoch": 1.0823804573804574, "percentage": 5.41, "elapsed_time": "0:06:02", "remaining_time": "1:45:42", "throughput": 1035.46, "total_tokens": 375736} {"current_steps": 4170, "total_steps": 76960, "loss": 0.3121, "lr": 2.708549896049896e-05, "epoch": 1.0836798336798337, "percentage": 5.42, "elapsed_time": "0:06:03", "remaining_time": "1:45:41", "throughput": 1035.51, "total_tokens": 376184} {"current_steps": 4175, "total_steps": 76960, "loss": 0.335, "lr": 2.7117983367983368e-05, "epoch": 1.08497920997921, "percentage": 5.42, "elapsed_time": "0:06:03", "remaining_time": "1:45:40", "throughput": 1035.51, "total_tokens": 376616} {"current_steps": 4180, "total_steps": 76960, "loss": 0.2228, "lr": 2.7150467775467774e-05, "epoch": 1.0862785862785862, "percentage": 5.43, "elapsed_time": "0:06:04", "remaining_time": "1:45:39", "throughput": 1035.5, "total_tokens": 377048} {"current_steps": 4185, "total_steps": 76960, "loss": 0.3321, "lr": 2.718295218295218e-05, "epoch": 1.0875779625779627, "percentage": 5.44, "elapsed_time": "0:06:04", "remaining_time": "1:45:39", "throughput": 1035.5, "total_tokens": 377480} {"current_steps": 4190, "total_steps": 76960, "loss": 0.3094, "lr": 2.7215436590436593e-05, "epoch": 1.088877338877339, "percentage": 5.44, "elapsed_time": "0:06:04", "remaining_time": "1:45:38", "throughput": 1035.5, "total_tokens": 377912} {"current_steps": 4195, "total_steps": 76960, "loss": 0.288, "lr": 2.7247920997921e-05, "epoch": 1.0901767151767152, "percentage": 5.45, "elapsed_time": "0:06:05", "remaining_time": "1:45:37", "throughput": 1035.55, "total_tokens": 378360} {"current_steps": 4200, "total_steps": 76960, "loss": 0.302, "lr": 2.7280405405405406e-05, "epoch": 1.0914760914760915, "percentage": 5.46, "elapsed_time": "0:06:05", "remaining_time": "1:45:36", "throughput": 1035.5, "total_tokens": 378776} {"current_steps": 4205, "total_steps": 76960, "loss": 0.2419, "lr": 2.7312889812889812e-05, "epoch": 1.0927754677754677, "percentage": 5.46, "elapsed_time": "0:06:06", "remaining_time": "1:45:36", "throughput": 1035.5, "total_tokens": 379208} {"current_steps": 4210, "total_steps": 76960, "loss": 0.3265, "lr": 2.7345374220374222e-05, "epoch": 1.094074844074844, "percentage": 5.47, "elapsed_time": "0:06:06", "remaining_time": "1:45:35", "throughput": 1035.5, "total_tokens": 379640} {"current_steps": 4215, "total_steps": 76960, "loss": 0.258, "lr": 2.7377858627858628e-05, "epoch": 1.0953742203742203, "percentage": 5.48, "elapsed_time": "0:06:07", "remaining_time": "1:45:34", "throughput": 1035.59, "total_tokens": 380104} {"current_steps": 4220, "total_steps": 76960, "loss": 0.1928, "lr": 2.7410343035343038e-05, "epoch": 1.0966735966735968, "percentage": 5.48, "elapsed_time": "0:06:07", "remaining_time": "1:45:33", "throughput": 1035.68, "total_tokens": 380568} {"current_steps": 4225, "total_steps": 76960, "loss": 0.291, "lr": 2.7442827442827447e-05, "epoch": 1.097972972972973, "percentage": 5.49, "elapsed_time": "0:06:07", "remaining_time": "1:45:33", "throughput": 1035.72, "total_tokens": 381016} {"current_steps": 4230, "total_steps": 76960, "loss": 0.3303, "lr": 2.7475311850311854e-05, "epoch": 1.0992723492723493, "percentage": 5.5, "elapsed_time": "0:06:08", "remaining_time": "1:45:32", "throughput": 1035.81, "total_tokens": 381480} {"current_steps": 4235, "total_steps": 76960, "loss": 0.1827, "lr": 2.750779625779626e-05, "epoch": 1.1005717255717256, "percentage": 5.5, "elapsed_time": "0:06:08", "remaining_time": "1:45:31", "throughput": 1035.9, "total_tokens": 381944} {"current_steps": 4240, "total_steps": 76960, "loss": 0.2641, "lr": 2.7540280665280666e-05, "epoch": 1.1018711018711018, "percentage": 5.51, "elapsed_time": "0:06:09", "remaining_time": "1:45:30", "throughput": 1035.99, "total_tokens": 382408} {"current_steps": 4245, "total_steps": 76960, "loss": 0.2145, "lr": 2.7572765072765072e-05, "epoch": 1.103170478170478, "percentage": 5.52, "elapsed_time": "0:06:09", "remaining_time": "1:45:30", "throughput": 1036.08, "total_tokens": 382872} {"current_steps": 4250, "total_steps": 76960, "loss": 0.2747, "lr": 2.7605249480249485e-05, "epoch": 1.1044698544698546, "percentage": 5.52, "elapsed_time": "0:06:09", "remaining_time": "1:45:29", "throughput": 1036.12, "total_tokens": 383320} {"current_steps": 4255, "total_steps": 76960, "loss": 0.2187, "lr": 2.763773388773389e-05, "epoch": 1.1057692307692308, "percentage": 5.53, "elapsed_time": "0:06:10", "remaining_time": "1:45:28", "throughput": 1036.17, "total_tokens": 383768} {"current_steps": 4260, "total_steps": 76960, "loss": 0.2201, "lr": 2.7670218295218298e-05, "epoch": 1.107068607068607, "percentage": 5.54, "elapsed_time": "0:06:10", "remaining_time": "1:45:27", "throughput": 1036.3, "total_tokens": 384248} {"current_steps": 4265, "total_steps": 76960, "loss": 0.3144, "lr": 2.7702702702702704e-05, "epoch": 1.1083679833679834, "percentage": 5.54, "elapsed_time": "0:06:11", "remaining_time": "1:45:27", "throughput": 1036.25, "total_tokens": 384664} {"current_steps": 4270, "total_steps": 76960, "loss": 0.2599, "lr": 2.773518711018711e-05, "epoch": 1.1096673596673596, "percentage": 5.55, "elapsed_time": "0:06:11", "remaining_time": "1:45:26", "throughput": 1036.38, "total_tokens": 385144} {"current_steps": 4275, "total_steps": 76960, "loss": 0.3007, "lr": 2.7767671517671517e-05, "epoch": 1.110966735966736, "percentage": 5.55, "elapsed_time": "0:06:12", "remaining_time": "1:45:25", "throughput": 1036.38, "total_tokens": 385576} {"current_steps": 4280, "total_steps": 76960, "loss": 0.2986, "lr": 2.7800155925155923e-05, "epoch": 1.1122661122661124, "percentage": 5.56, "elapsed_time": "0:06:12", "remaining_time": "1:45:24", "throughput": 1036.38, "total_tokens": 386008} {"current_steps": 4285, "total_steps": 76960, "loss": 0.2878, "lr": 2.7832640332640336e-05, "epoch": 1.1135654885654886, "percentage": 5.57, "elapsed_time": "0:06:12", "remaining_time": "1:45:24", "throughput": 1036.47, "total_tokens": 386472} {"current_steps": 4290, "total_steps": 76960, "loss": 0.2769, "lr": 2.7865124740124742e-05, "epoch": 1.114864864864865, "percentage": 5.57, "elapsed_time": "0:06:13", "remaining_time": "1:45:23", "throughput": 1036.51, "total_tokens": 386920} {"current_steps": 4295, "total_steps": 76960, "loss": 0.2951, "lr": 2.789760914760915e-05, "epoch": 1.1161642411642412, "percentage": 5.58, "elapsed_time": "0:06:13", "remaining_time": "1:45:22", "throughput": 1036.54, "total_tokens": 387368} {"current_steps": 4300, "total_steps": 76960, "loss": 0.2477, "lr": 2.7930093555093555e-05, "epoch": 1.1174636174636174, "percentage": 5.59, "elapsed_time": "0:06:14", "remaining_time": "1:45:21", "throughput": 1036.54, "total_tokens": 387800} {"current_steps": 4305, "total_steps": 76960, "loss": 0.2643, "lr": 2.796257796257796e-05, "epoch": 1.1187629937629937, "percentage": 5.59, "elapsed_time": "0:06:14", "remaining_time": "1:45:21", "throughput": 1036.62, "total_tokens": 388264} {"current_steps": 4310, "total_steps": 76960, "loss": 0.2236, "lr": 2.799506237006237e-05, "epoch": 1.12006237006237, "percentage": 5.6, "elapsed_time": "0:06:14", "remaining_time": "1:45:20", "throughput": 1036.7, "total_tokens": 388728} {"current_steps": 4315, "total_steps": 76960, "loss": 0.2938, "lr": 2.802754677754678e-05, "epoch": 1.1213617463617465, "percentage": 5.61, "elapsed_time": "0:06:15", "remaining_time": "1:45:19", "throughput": 1036.64, "total_tokens": 389144} {"current_steps": 4320, "total_steps": 76960, "loss": 0.1694, "lr": 2.8060031185031187e-05, "epoch": 1.1226611226611227, "percentage": 5.61, "elapsed_time": "0:06:15", "remaining_time": "1:45:19", "throughput": 1036.68, "total_tokens": 389592} {"current_steps": 4325, "total_steps": 76960, "loss": 0.2792, "lr": 2.8092515592515596e-05, "epoch": 1.123960498960499, "percentage": 5.62, "elapsed_time": "0:06:16", "remaining_time": "1:45:18", "throughput": 1036.73, "total_tokens": 390040} {"current_steps": 4330, "total_steps": 76960, "loss": 0.3526, "lr": 2.8125000000000003e-05, "epoch": 1.1252598752598753, "percentage": 5.63, "elapsed_time": "0:06:16", "remaining_time": "1:45:17", "throughput": 1036.77, "total_tokens": 390488} {"current_steps": 4335, "total_steps": 76960, "loss": 0.2364, "lr": 2.815748440748441e-05, "epoch": 1.1265592515592515, "percentage": 5.63, "elapsed_time": "0:06:17", "remaining_time": "1:45:16", "throughput": 1036.8, "total_tokens": 390936} {"current_steps": 4340, "total_steps": 76960, "loss": 0.2852, "lr": 2.8189968814968815e-05, "epoch": 1.1278586278586278, "percentage": 5.64, "elapsed_time": "0:06:17", "remaining_time": "1:45:16", "throughput": 1036.8, "total_tokens": 391368} {"current_steps": 4345, "total_steps": 76960, "loss": 0.2592, "lr": 2.822245322245322e-05, "epoch": 1.129158004158004, "percentage": 5.65, "elapsed_time": "0:06:17", "remaining_time": "1:45:15", "throughput": 1036.8, "total_tokens": 391800} {"current_steps": 4350, "total_steps": 76960, "loss": 0.2695, "lr": 2.8254937629937634e-05, "epoch": 1.1304573804573805, "percentage": 5.65, "elapsed_time": "0:06:18", "remaining_time": "1:45:14", "throughput": 1036.79, "total_tokens": 392232} {"current_steps": 4355, "total_steps": 76960, "loss": 0.226, "lr": 2.828742203742204e-05, "epoch": 1.1317567567567568, "percentage": 5.66, "elapsed_time": "0:06:18", "remaining_time": "1:45:14", "throughput": 1036.79, "total_tokens": 392664} {"current_steps": 4360, "total_steps": 76960, "loss": 0.1616, "lr": 2.8319906444906447e-05, "epoch": 1.133056133056133, "percentage": 5.67, "elapsed_time": "0:06:19", "remaining_time": "1:45:13", "throughput": 1036.79, "total_tokens": 393096} {"current_steps": 4365, "total_steps": 76960, "loss": 0.2646, "lr": 2.8352390852390853e-05, "epoch": 1.1343555093555093, "percentage": 5.67, "elapsed_time": "0:06:19", "remaining_time": "1:45:12", "throughput": 1036.95, "total_tokens": 393592} {"current_steps": 4370, "total_steps": 76960, "loss": 0.3458, "lr": 2.838487525987526e-05, "epoch": 1.1356548856548856, "percentage": 5.68, "elapsed_time": "0:06:19", "remaining_time": "1:45:11", "throughput": 1037.16, "total_tokens": 394104} {"current_steps": 4375, "total_steps": 76960, "loss": 0.3494, "lr": 2.8417359667359666e-05, "epoch": 1.1369542619542619, "percentage": 5.68, "elapsed_time": "0:06:20", "remaining_time": "1:45:11", "throughput": 1037.2, "total_tokens": 394552} {"current_steps": 4380, "total_steps": 76960, "loss": 0.2906, "lr": 2.844984407484408e-05, "epoch": 1.1382536382536383, "percentage": 5.69, "elapsed_time": "0:06:20", "remaining_time": "1:45:10", "throughput": 1037.28, "total_tokens": 395016} {"current_steps": 4385, "total_steps": 76960, "loss": 0.2861, "lr": 2.8482328482328485e-05, "epoch": 1.1395530145530146, "percentage": 5.7, "elapsed_time": "0:06:21", "remaining_time": "1:45:09", "throughput": 1037.19, "total_tokens": 395416} {"current_steps": 4390, "total_steps": 76960, "loss": 0.2803, "lr": 2.851481288981289e-05, "epoch": 1.1408523908523909, "percentage": 5.7, "elapsed_time": "0:06:21", "remaining_time": "1:45:09", "throughput": 1037.23, "total_tokens": 395864} {"current_steps": 4395, "total_steps": 76960, "loss": 0.3196, "lr": 2.8547297297297298e-05, "epoch": 1.1421517671517671, "percentage": 5.71, "elapsed_time": "0:06:22", "remaining_time": "1:45:08", "throughput": 1037.27, "total_tokens": 396312} {"current_steps": 4400, "total_steps": 76960, "loss": 0.2432, "lr": 2.8579781704781704e-05, "epoch": 1.1434511434511434, "percentage": 5.72, "elapsed_time": "0:06:22", "remaining_time": "1:45:07", "throughput": 1037.27, "total_tokens": 396744} {"current_steps": 4405, "total_steps": 76960, "loss": 0.1879, "lr": 2.861226611226611e-05, "epoch": 1.1447505197505197, "percentage": 5.72, "elapsed_time": "0:06:22", "remaining_time": "1:45:06", "throughput": 1037.23, "total_tokens": 397160} {"current_steps": 4410, "total_steps": 76960, "loss": 0.3014, "lr": 2.864475051975052e-05, "epoch": 1.1460498960498962, "percentage": 5.73, "elapsed_time": "0:06:23", "remaining_time": "1:45:06", "throughput": 1037.27, "total_tokens": 397608} {"current_steps": 4415, "total_steps": 76960, "loss": 0.3056, "lr": 2.867723492723493e-05, "epoch": 1.1473492723492724, "percentage": 5.74, "elapsed_time": "0:06:23", "remaining_time": "1:45:05", "throughput": 1037.31, "total_tokens": 398056} {"current_steps": 4420, "total_steps": 76960, "loss": 0.2526, "lr": 2.8709719334719336e-05, "epoch": 1.1486486486486487, "percentage": 5.74, "elapsed_time": "0:06:24", "remaining_time": "1:45:04", "throughput": 1037.52, "total_tokens": 398568} {"current_steps": 4425, "total_steps": 76960, "loss": 0.2704, "lr": 2.8742203742203745e-05, "epoch": 1.149948024948025, "percentage": 5.75, "elapsed_time": "0:06:24", "remaining_time": "1:45:03", "throughput": 1037.68, "total_tokens": 399064} {"current_steps": 4430, "total_steps": 76960, "loss": 0.1857, "lr": 2.877468814968815e-05, "epoch": 1.1512474012474012, "percentage": 5.76, "elapsed_time": "0:06:24", "remaining_time": "1:45:03", "throughput": 1037.68, "total_tokens": 399496} {"current_steps": 4435, "total_steps": 76960, "loss": 0.2631, "lr": 2.8807172557172558e-05, "epoch": 1.1525467775467775, "percentage": 5.76, "elapsed_time": "0:06:25", "remaining_time": "1:45:02", "throughput": 1037.67, "total_tokens": 399928} {"current_steps": 4440, "total_steps": 76960, "loss": 0.439, "lr": 2.8839656964656964e-05, "epoch": 1.1538461538461537, "percentage": 5.77, "elapsed_time": "0:06:25", "remaining_time": "1:45:01", "throughput": 1037.71, "total_tokens": 400376} {"current_steps": 4445, "total_steps": 76960, "loss": 0.2331, "lr": 2.8872141372141377e-05, "epoch": 1.1551455301455302, "percentage": 5.78, "elapsed_time": "0:06:26", "remaining_time": "1:45:01", "throughput": 1037.83, "total_tokens": 400856} {"current_steps": 4450, "total_steps": 76960, "loss": 0.2763, "lr": 2.8904625779625784e-05, "epoch": 1.1564449064449065, "percentage": 5.78, "elapsed_time": "0:06:26", "remaining_time": "1:45:00", "throughput": 1038.04, "total_tokens": 401368} {"current_steps": 4455, "total_steps": 76960, "loss": 0.269, "lr": 2.893711018711019e-05, "epoch": 1.1577442827442828, "percentage": 5.79, "elapsed_time": "0:06:27", "remaining_time": "1:44:59", "throughput": 1038.08, "total_tokens": 401816} {"current_steps": 4460, "total_steps": 76960, "loss": 0.1462, "lr": 2.8969594594594596e-05, "epoch": 1.159043659043659, "percentage": 5.8, "elapsed_time": "0:06:27", "remaining_time": "1:44:58", "throughput": 1038.2, "total_tokens": 402296} {"current_steps": 4465, "total_steps": 76960, "loss": 0.2123, "lr": 2.9002079002079002e-05, "epoch": 1.1603430353430353, "percentage": 5.8, "elapsed_time": "0:06:27", "remaining_time": "1:44:58", "throughput": 1038.24, "total_tokens": 402744} {"current_steps": 4470, "total_steps": 76960, "loss": 0.2152, "lr": 2.903456340956341e-05, "epoch": 1.1616424116424116, "percentage": 5.81, "elapsed_time": "0:06:28", "remaining_time": "1:44:57", "throughput": 1038.27, "total_tokens": 403192} {"current_steps": 4475, "total_steps": 76960, "loss": 0.3885, "lr": 2.906704781704782e-05, "epoch": 1.1629417879417878, "percentage": 5.81, "elapsed_time": "0:06:28", "remaining_time": "1:44:56", "throughput": 1038.4, "total_tokens": 403672} {"current_steps": 4480, "total_steps": 76960, "loss": 0.2988, "lr": 2.9099532224532228e-05, "epoch": 1.1642411642411643, "percentage": 5.82, "elapsed_time": "0:06:29", "remaining_time": "1:44:56", "throughput": 1038.52, "total_tokens": 404152} {"current_steps": 4485, "total_steps": 76960, "loss": 0.2196, "lr": 2.9132016632016634e-05, "epoch": 1.1655405405405406, "percentage": 5.83, "elapsed_time": "0:06:29", "remaining_time": "1:44:55", "throughput": 1038.5, "total_tokens": 404584} {"current_steps": 4490, "total_steps": 76960, "loss": 0.2004, "lr": 2.916450103950104e-05, "epoch": 1.1668399168399168, "percentage": 5.83, "elapsed_time": "0:06:30", "remaining_time": "1:44:54", "throughput": 1038.6, "total_tokens": 405064} {"current_steps": 4495, "total_steps": 76960, "loss": 0.2267, "lr": 2.9196985446985447e-05, "epoch": 1.168139293139293, "percentage": 5.84, "elapsed_time": "0:06:30", "remaining_time": "1:44:54", "throughput": 1038.67, "total_tokens": 405528} {"current_steps": 4500, "total_steps": 76960, "loss": 0.336, "lr": 2.9229469854469853e-05, "epoch": 1.1694386694386694, "percentage": 5.85, "elapsed_time": "0:06:30", "remaining_time": "1:44:53", "throughput": 1038.71, "total_tokens": 405976} {"current_steps": 4505, "total_steps": 76960, "loss": 0.346, "lr": 2.926195426195426e-05, "epoch": 1.1707380457380459, "percentage": 5.85, "elapsed_time": "0:06:31", "remaining_time": "1:44:52", "throughput": 1038.71, "total_tokens": 406408} {"current_steps": 4510, "total_steps": 76960, "loss": 0.2644, "lr": 2.9294438669438672e-05, "epoch": 1.1720374220374221, "percentage": 5.86, "elapsed_time": "0:06:31", "remaining_time": "1:44:52", "throughput": 1038.7, "total_tokens": 406840} {"current_steps": 4515, "total_steps": 76960, "loss": 0.2422, "lr": 2.932692307692308e-05, "epoch": 1.1733367983367984, "percentage": 5.87, "elapsed_time": "0:06:32", "remaining_time": "1:44:51", "throughput": 1038.7, "total_tokens": 407272} {"current_steps": 4520, "total_steps": 76960, "loss": 0.3009, "lr": 2.9359407484407485e-05, "epoch": 1.1746361746361746, "percentage": 5.87, "elapsed_time": "0:06:32", "remaining_time": "1:44:50", "throughput": 1038.74, "total_tokens": 407720} {"current_steps": 4525, "total_steps": 76960, "loss": 0.1512, "lr": 2.9391891891891894e-05, "epoch": 1.175935550935551, "percentage": 5.88, "elapsed_time": "0:06:32", "remaining_time": "1:44:49", "throughput": 1038.74, "total_tokens": 408152} {"current_steps": 4530, "total_steps": 76960, "loss": 0.346, "lr": 2.94243762993763e-05, "epoch": 1.1772349272349272, "percentage": 5.89, "elapsed_time": "0:06:33", "remaining_time": "1:44:49", "throughput": 1038.78, "total_tokens": 408600} {"current_steps": 4535, "total_steps": 76960, "loss": 0.3058, "lr": 2.9456860706860707e-05, "epoch": 1.1785343035343034, "percentage": 5.89, "elapsed_time": "0:06:33", "remaining_time": "1:44:48", "throughput": 1038.82, "total_tokens": 409048} {"current_steps": 4540, "total_steps": 76960, "loss": 0.2708, "lr": 2.9489345114345117e-05, "epoch": 1.17983367983368, "percentage": 5.9, "elapsed_time": "0:06:34", "remaining_time": "1:44:47", "throughput": 1038.82, "total_tokens": 409480} {"current_steps": 4545, "total_steps": 76960, "loss": 0.2262, "lr": 2.9521829521829526e-05, "epoch": 1.1811330561330562, "percentage": 5.91, "elapsed_time": "0:06:34", "remaining_time": "1:44:47", "throughput": 1038.85, "total_tokens": 409928} {"current_steps": 4550, "total_steps": 76960, "loss": 0.3204, "lr": 2.9554313929313933e-05, "epoch": 1.1824324324324325, "percentage": 5.91, "elapsed_time": "0:06:35", "remaining_time": "1:44:46", "throughput": 1038.93, "total_tokens": 410392} {"current_steps": 4555, "total_steps": 76960, "loss": 0.2596, "lr": 2.958679833679834e-05, "epoch": 1.1837318087318087, "percentage": 5.92, "elapsed_time": "0:06:35", "remaining_time": "1:44:45", "throughput": 1038.97, "total_tokens": 410840} {"current_steps": 4560, "total_steps": 76960, "loss": 0.312, "lr": 2.9619282744282745e-05, "epoch": 1.185031185031185, "percentage": 5.93, "elapsed_time": "0:06:35", "remaining_time": "1:44:44", "throughput": 1039.01, "total_tokens": 411288} {"current_steps": 4565, "total_steps": 76960, "loss": 0.299, "lr": 2.965176715176715e-05, "epoch": 1.1863305613305613, "percentage": 5.93, "elapsed_time": "0:06:36", "remaining_time": "1:44:44", "throughput": 1039.05, "total_tokens": 411736} {"current_steps": 4570, "total_steps": 76960, "loss": 0.3002, "lr": 2.9684251559251558e-05, "epoch": 1.1876299376299375, "percentage": 5.94, "elapsed_time": "0:06:36", "remaining_time": "1:44:43", "throughput": 1039.08, "total_tokens": 412184} {"current_steps": 4575, "total_steps": 76960, "loss": 0.319, "lr": 2.971673596673597e-05, "epoch": 1.188929313929314, "percentage": 5.94, "elapsed_time": "0:06:37", "remaining_time": "1:44:42", "throughput": 1039.13, "total_tokens": 412632} {"current_steps": 4580, "total_steps": 76960, "loss": 0.2749, "lr": 2.9749220374220377e-05, "epoch": 1.1902286902286903, "percentage": 5.95, "elapsed_time": "0:06:37", "remaining_time": "1:44:42", "throughput": 1039.12, "total_tokens": 413064} {"current_steps": 4585, "total_steps": 76960, "loss": 0.2506, "lr": 2.9781704781704783e-05, "epoch": 1.1915280665280665, "percentage": 5.96, "elapsed_time": "0:06:37", "remaining_time": "1:44:41", "throughput": 1039.08, "total_tokens": 413480} {"current_steps": 4590, "total_steps": 76960, "loss": 0.2764, "lr": 2.981418918918919e-05, "epoch": 1.1928274428274428, "percentage": 5.96, "elapsed_time": "0:06:38", "remaining_time": "1:44:40", "throughput": 1039.2, "total_tokens": 413960} {"current_steps": 4595, "total_steps": 76960, "loss": 0.2359, "lr": 2.9846673596673596e-05, "epoch": 1.194126819126819, "percentage": 5.97, "elapsed_time": "0:06:38", "remaining_time": "1:44:39", "throughput": 1039.4, "total_tokens": 414472} {"current_steps": 4600, "total_steps": 76960, "loss": 0.3689, "lr": 2.9879158004158002e-05, "epoch": 1.1954261954261955, "percentage": 5.98, "elapsed_time": "0:06:39", "remaining_time": "1:44:39", "throughput": 1039.56, "total_tokens": 414968} {"current_steps": 4605, "total_steps": 76960, "loss": 0.2926, "lr": 2.9911642411642415e-05, "epoch": 1.1967255717255718, "percentage": 5.98, "elapsed_time": "0:06:39", "remaining_time": "1:44:38", "throughput": 1039.59, "total_tokens": 415416} {"current_steps": 4610, "total_steps": 76960, "loss": 0.2753, "lr": 2.994412681912682e-05, "epoch": 1.198024948024948, "percentage": 5.99, "elapsed_time": "0:06:40", "remaining_time": "1:44:37", "throughput": 1039.67, "total_tokens": 415880} {"current_steps": 4615, "total_steps": 76960, "loss": 0.2661, "lr": 2.9976611226611228e-05, "epoch": 1.1993243243243243, "percentage": 6.0, "elapsed_time": "0:06:40", "remaining_time": "1:44:37", "throughput": 1039.71, "total_tokens": 416328} {"current_steps": 4620, "total_steps": 76960, "loss": 0.269, "lr": 3.0009095634095634e-05, "epoch": 1.2006237006237006, "percentage": 6.0, "elapsed_time": "0:06:40", "remaining_time": "1:44:36", "throughput": 1039.66, "total_tokens": 416744} {"current_steps": 4625, "total_steps": 76960, "loss": 0.304, "lr": 3.0041580041580043e-05, "epoch": 1.2019230769230769, "percentage": 6.01, "elapsed_time": "0:06:41", "remaining_time": "1:44:35", "throughput": 1039.74, "total_tokens": 417208} {"current_steps": 4630, "total_steps": 76960, "loss": 0.2616, "lr": 3.007406444906445e-05, "epoch": 1.2032224532224531, "percentage": 6.02, "elapsed_time": "0:06:41", "remaining_time": "1:44:35", "throughput": 1039.74, "total_tokens": 417640} {"current_steps": 4635, "total_steps": 76960, "loss": 0.3582, "lr": 3.010654885654886e-05, "epoch": 1.2045218295218296, "percentage": 6.02, "elapsed_time": "0:06:42", "remaining_time": "1:44:34", "throughput": 1039.9, "total_tokens": 418136} {"current_steps": 4640, "total_steps": 76960, "loss": 0.2902, "lr": 3.0139033264033266e-05, "epoch": 1.2058212058212059, "percentage": 6.03, "elapsed_time": "0:06:42", "remaining_time": "1:44:33", "throughput": 1040.02, "total_tokens": 418616} {"current_steps": 4645, "total_steps": 76960, "loss": 0.2947, "lr": 3.0171517671517675e-05, "epoch": 1.2071205821205822, "percentage": 6.04, "elapsed_time": "0:06:42", "remaining_time": "1:44:32", "throughput": 1040.14, "total_tokens": 419096} {"current_steps": 4650, "total_steps": 76960, "loss": 0.3405, "lr": 3.020400207900208e-05, "epoch": 1.2084199584199584, "percentage": 6.04, "elapsed_time": "0:06:43", "remaining_time": "1:44:32", "throughput": 1040.17, "total_tokens": 419544} {"current_steps": 4655, "total_steps": 76960, "loss": 0.2953, "lr": 3.0236486486486488e-05, "epoch": 1.2097193347193347, "percentage": 6.05, "elapsed_time": "0:06:43", "remaining_time": "1:44:31", "throughput": 1040.15, "total_tokens": 419976} {"current_steps": 4660, "total_steps": 76960, "loss": 0.2286, "lr": 3.0268970893970894e-05, "epoch": 1.211018711018711, "percentage": 6.06, "elapsed_time": "0:06:44", "remaining_time": "1:44:31", "throughput": 1040.16, "total_tokens": 420424} {"current_steps": 4665, "total_steps": 76960, "loss": 0.2127, "lr": 3.03014553014553e-05, "epoch": 1.2123180873180872, "percentage": 6.06, "elapsed_time": "0:06:44", "remaining_time": "1:44:30", "throughput": 1040.17, "total_tokens": 420872} {"current_steps": 4670, "total_steps": 76960, "loss": 0.2222, "lr": 3.0333939708939713e-05, "epoch": 1.2136174636174637, "percentage": 6.07, "elapsed_time": "0:06:45", "remaining_time": "1:44:29", "throughput": 1040.23, "total_tokens": 421336} {"current_steps": 4675, "total_steps": 76960, "loss": 0.1869, "lr": 3.036642411642412e-05, "epoch": 1.21491683991684, "percentage": 6.07, "elapsed_time": "0:06:45", "remaining_time": "1:44:29", "throughput": 1040.29, "total_tokens": 421800} {"current_steps": 4680, "total_steps": 76960, "loss": 0.0567, "lr": 3.0398908523908526e-05, "epoch": 1.2162162162162162, "percentage": 6.08, "elapsed_time": "0:06:45", "remaining_time": "1:44:28", "throughput": 1040.2, "total_tokens": 422200} {"current_steps": 4685, "total_steps": 76960, "loss": 0.3446, "lr": 3.0431392931392932e-05, "epoch": 1.2175155925155925, "percentage": 6.09, "elapsed_time": "0:06:46", "remaining_time": "1:44:27", "throughput": 1040.11, "total_tokens": 422600} {"current_steps": 4690, "total_steps": 76960, "loss": 0.2948, "lr": 3.046387733887734e-05, "epoch": 1.2188149688149688, "percentage": 6.09, "elapsed_time": "0:06:46", "remaining_time": "1:44:27", "throughput": 1040.18, "total_tokens": 423064} {"current_steps": 4695, "total_steps": 76960, "loss": 0.3316, "lr": 3.0496361746361745e-05, "epoch": 1.220114345114345, "percentage": 6.1, "elapsed_time": "0:06:47", "remaining_time": "1:44:26", "throughput": 1040.26, "total_tokens": 423528} {"current_steps": 4700, "total_steps": 76960, "loss": 0.316, "lr": 3.052884615384616e-05, "epoch": 1.2214137214137215, "percentage": 6.11, "elapsed_time": "0:06:47", "remaining_time": "1:44:26", "throughput": 1040.31, "total_tokens": 423992} {"current_steps": 4705, "total_steps": 76960, "loss": 0.1964, "lr": 3.056133056133057e-05, "epoch": 1.2227130977130978, "percentage": 6.11, "elapsed_time": "0:06:47", "remaining_time": "1:44:25", "throughput": 1040.34, "total_tokens": 424440} {"current_steps": 4710, "total_steps": 76960, "loss": 0.2925, "lr": 3.059381496881497e-05, "epoch": 1.224012474012474, "percentage": 6.12, "elapsed_time": "0:06:48", "remaining_time": "1:44:24", "throughput": 1040.45, "total_tokens": 424920} {"current_steps": 4715, "total_steps": 76960, "loss": 0.2621, "lr": 3.062629937629938e-05, "epoch": 1.2253118503118503, "percentage": 6.13, "elapsed_time": "0:06:48", "remaining_time": "1:44:24", "throughput": 1040.44, "total_tokens": 425352} {"current_steps": 4720, "total_steps": 76960, "loss": 0.3405, "lr": 3.065878378378378e-05, "epoch": 1.2266112266112266, "percentage": 6.13, "elapsed_time": "0:06:49", "remaining_time": "1:44:23", "throughput": 1040.5, "total_tokens": 425816} {"current_steps": 4725, "total_steps": 76960, "loss": 0.2684, "lr": 3.069126819126819e-05, "epoch": 1.2279106029106028, "percentage": 6.14, "elapsed_time": "0:06:49", "remaining_time": "1:44:22", "throughput": 1040.61, "total_tokens": 426296} {"current_steps": 4730, "total_steps": 76960, "loss": 0.2846, "lr": 3.0723752598752595e-05, "epoch": 1.2292099792099793, "percentage": 6.15, "elapsed_time": "0:06:50", "remaining_time": "1:44:22", "throughput": 1040.52, "total_tokens": 426696} {"current_steps": 4735, "total_steps": 76960, "loss": 0.2675, "lr": 3.075623700623701e-05, "epoch": 1.2305093555093556, "percentage": 6.15, "elapsed_time": "0:06:50", "remaining_time": "1:44:21", "throughput": 1040.47, "total_tokens": 427112} {"current_steps": 4740, "total_steps": 76960, "loss": 0.2356, "lr": 3.0788721413721415e-05, "epoch": 1.2318087318087318, "percentage": 6.16, "elapsed_time": "0:06:50", "remaining_time": "1:44:20", "throughput": 1040.54, "total_tokens": 427576} {"current_steps": 4745, "total_steps": 76960, "loss": 0.2277, "lr": 3.0821205821205824e-05, "epoch": 1.2331081081081081, "percentage": 6.17, "elapsed_time": "0:06:51", "remaining_time": "1:44:20", "throughput": 1040.57, "total_tokens": 428024} {"current_steps": 4750, "total_steps": 76960, "loss": 0.2906, "lr": 3.085369022869023e-05, "epoch": 1.2344074844074844, "percentage": 6.17, "elapsed_time": "0:06:51", "remaining_time": "1:44:19", "throughput": 1040.68, "total_tokens": 428504} {"current_steps": 4755, "total_steps": 76960, "loss": 0.3357, "lr": 3.088617463617464e-05, "epoch": 1.2357068607068606, "percentage": 6.18, "elapsed_time": "0:06:52", "remaining_time": "1:44:18", "throughput": 1040.72, "total_tokens": 428952} {"current_steps": 4760, "total_steps": 76960, "loss": 0.322, "lr": 3.091865904365904e-05, "epoch": 1.237006237006237, "percentage": 6.19, "elapsed_time": "0:06:52", "remaining_time": "1:44:18", "throughput": 1040.67, "total_tokens": 429368} {"current_steps": 4765, "total_steps": 76960, "loss": 0.1969, "lr": 3.0951143451143456e-05, "epoch": 1.2383056133056134, "percentage": 6.19, "elapsed_time": "0:06:53", "remaining_time": "1:44:17", "throughput": 1040.79, "total_tokens": 429848} {"current_steps": 4770, "total_steps": 76960, "loss": 0.3236, "lr": 3.098362785862786e-05, "epoch": 1.2396049896049897, "percentage": 6.2, "elapsed_time": "0:06:53", "remaining_time": "1:44:16", "throughput": 1040.82, "total_tokens": 430296} {"current_steps": 4775, "total_steps": 76960, "loss": 0.2543, "lr": 3.101611226611227e-05, "epoch": 1.240904365904366, "percentage": 6.2, "elapsed_time": "0:06:53", "remaining_time": "1:44:16", "throughput": 1040.93, "total_tokens": 430776} {"current_steps": 4780, "total_steps": 76960, "loss": 0.2741, "lr": 3.104859667359667e-05, "epoch": 1.2422037422037422, "percentage": 6.21, "elapsed_time": "0:06:54", "remaining_time": "1:44:15", "throughput": 1040.97, "total_tokens": 431224} {"current_steps": 4785, "total_steps": 76960, "loss": 0.2727, "lr": 3.108108108108108e-05, "epoch": 1.2435031185031185, "percentage": 6.22, "elapsed_time": "0:06:54", "remaining_time": "1:44:14", "throughput": 1040.96, "total_tokens": 431656} {"current_steps": 4790, "total_steps": 76960, "loss": 0.2625, "lr": 3.111356548856549e-05, "epoch": 1.2448024948024947, "percentage": 6.22, "elapsed_time": "0:06:55", "remaining_time": "1:44:14", "throughput": 1040.92, "total_tokens": 432072} {"current_steps": 4795, "total_steps": 76960, "loss": 0.3266, "lr": 3.11460498960499e-05, "epoch": 1.246101871101871, "percentage": 6.23, "elapsed_time": "0:06:55", "remaining_time": "1:44:13", "throughput": 1040.99, "total_tokens": 432536} {"current_steps": 4800, "total_steps": 76960, "loss": 0.2068, "lr": 3.117853430353431e-05, "epoch": 1.2474012474012475, "percentage": 6.24, "elapsed_time": "0:06:55", "remaining_time": "1:44:12", "throughput": 1041.15, "total_tokens": 433032} {"current_steps": 4805, "total_steps": 76960, "loss": 0.3102, "lr": 3.121101871101871e-05, "epoch": 1.2487006237006237, "percentage": 6.24, "elapsed_time": "0:06:56", "remaining_time": "1:44:11", "throughput": 1041.22, "total_tokens": 433496} {"current_steps": 4810, "total_steps": 76960, "loss": 0.3067, "lr": 3.124350311850312e-05, "epoch": 1.25, "percentage": 6.25, "elapsed_time": "0:06:56", "remaining_time": "1:44:11", "throughput": 1041.22, "total_tokens": 433928} {"current_steps": 4815, "total_steps": 76960, "loss": 0.2743, "lr": 3.1275987525987526e-05, "epoch": 1.2512993762993763, "percentage": 6.26, "elapsed_time": "0:06:57", "remaining_time": "1:44:10", "throughput": 1041.25, "total_tokens": 434376} {"current_steps": 4820, "total_steps": 76960, "loss": 0.2535, "lr": 3.1308471933471935e-05, "epoch": 1.2525987525987525, "percentage": 6.26, "elapsed_time": "0:06:57", "remaining_time": "1:44:09", "throughput": 1041.23, "total_tokens": 434808} {"current_steps": 4825, "total_steps": 76960, "loss": 0.2825, "lr": 3.134095634095634e-05, "epoch": 1.253898128898129, "percentage": 6.27, "elapsed_time": "0:06:58", "remaining_time": "1:44:09", "throughput": 1041.26, "total_tokens": 435256} {"current_steps": 4830, "total_steps": 76960, "loss": 0.1504, "lr": 3.1373440748440755e-05, "epoch": 1.255197505197505, "percentage": 6.28, "elapsed_time": "0:06:58", "remaining_time": "1:44:08", "throughput": 1041.29, "total_tokens": 435704} {"current_steps": 4835, "total_steps": 76960, "loss": 0.2589, "lr": 3.140592515592516e-05, "epoch": 1.2564968814968815, "percentage": 6.28, "elapsed_time": "0:06:58", "remaining_time": "1:44:08", "throughput": 1041.33, "total_tokens": 436168} {"current_steps": 4840, "total_steps": 76960, "loss": 0.3343, "lr": 3.143840956340957e-05, "epoch": 1.2577962577962578, "percentage": 6.29, "elapsed_time": "0:06:59", "remaining_time": "1:44:07", "throughput": 1041.23, "total_tokens": 436568} {"current_steps": 4845, "total_steps": 76960, "loss": 0.2161, "lr": 3.147089397089397e-05, "epoch": 1.259095634095634, "percentage": 6.3, "elapsed_time": "0:06:59", "remaining_time": "1:44:07", "throughput": 1041.2, "total_tokens": 437000} {"current_steps": 4850, "total_steps": 76960, "loss": 0.2691, "lr": 3.150337837837838e-05, "epoch": 1.2603950103950103, "percentage": 6.3, "elapsed_time": "0:07:00", "remaining_time": "1:44:06", "throughput": 1041.15, "total_tokens": 437416} {"current_steps": 4855, "total_steps": 76960, "loss": 0.242, "lr": 3.153586278586278e-05, "epoch": 1.2616943866943866, "percentage": 6.31, "elapsed_time": "0:07:00", "remaining_time": "1:44:05", "throughput": 1041.19, "total_tokens": 437880} {"current_steps": 4860, "total_steps": 76960, "loss": 0.1751, "lr": 3.15683471933472e-05, "epoch": 1.262993762993763, "percentage": 6.31, "elapsed_time": "0:07:00", "remaining_time": "1:44:05", "throughput": 1041.21, "total_tokens": 438328} {"current_steps": 4865, "total_steps": 76960, "loss": 0.2486, "lr": 3.16008316008316e-05, "epoch": 1.2642931392931394, "percentage": 6.32, "elapsed_time": "0:07:01", "remaining_time": "1:44:04", "throughput": 1041.26, "total_tokens": 438792} {"current_steps": 4870, "total_steps": 76960, "loss": 0.3395, "lr": 3.163331600831601e-05, "epoch": 1.2655925155925156, "percentage": 6.33, "elapsed_time": "0:07:01", "remaining_time": "1:44:04", "throughput": 1041.23, "total_tokens": 439224} {"current_steps": 4875, "total_steps": 76960, "loss": 0.2673, "lr": 3.1665800415800414e-05, "epoch": 1.2668918918918919, "percentage": 6.33, "elapsed_time": "0:07:02", "remaining_time": "1:44:03", "throughput": 1041.21, "total_tokens": 439656} {"current_steps": 4880, "total_steps": 76960, "loss": 0.2595, "lr": 3.1698284823284824e-05, "epoch": 1.2681912681912682, "percentage": 6.34, "elapsed_time": "0:07:02", "remaining_time": "1:44:03", "throughput": 1041.16, "total_tokens": 440072} {"current_steps": 4885, "total_steps": 76960, "loss": 0.307, "lr": 3.1730769230769234e-05, "epoch": 1.2694906444906444, "percentage": 6.35, "elapsed_time": "0:07:03", "remaining_time": "1:44:02", "throughput": 1041.26, "total_tokens": 440552} {"current_steps": 4890, "total_steps": 76960, "loss": 0.2284, "lr": 3.1763253638253637e-05, "epoch": 1.2707900207900207, "percentage": 6.35, "elapsed_time": "0:07:03", "remaining_time": "1:44:01", "throughput": 1041.29, "total_tokens": 441000} {"current_steps": 4895, "total_steps": 76960, "loss": 0.2345, "lr": 3.1795738045738046e-05, "epoch": 1.2720893970893972, "percentage": 6.36, "elapsed_time": "0:07:03", "remaining_time": "1:44:01", "throughput": 1041.28, "total_tokens": 441432} {"current_steps": 4900, "total_steps": 76960, "loss": 0.2211, "lr": 3.1828222453222456e-05, "epoch": 1.2733887733887734, "percentage": 6.37, "elapsed_time": "0:07:04", "remaining_time": "1:44:00", "throughput": 1041.3, "total_tokens": 441880} {"current_steps": 4905, "total_steps": 76960, "loss": 0.1554, "lr": 3.1860706860706866e-05, "epoch": 1.2746881496881497, "percentage": 6.37, "elapsed_time": "0:07:04", "remaining_time": "1:43:59", "throughput": 1041.3, "total_tokens": 442312} {"current_steps": 4910, "total_steps": 76960, "loss": 0.2177, "lr": 3.189319126819127e-05, "epoch": 1.275987525987526, "percentage": 6.38, "elapsed_time": "0:07:05", "remaining_time": "1:43:59", "throughput": 1041.36, "total_tokens": 442776} {"current_steps": 4915, "total_steps": 76960, "loss": 0.1475, "lr": 3.192567567567568e-05, "epoch": 1.2772869022869022, "percentage": 6.39, "elapsed_time": "0:07:05", "remaining_time": "1:43:58", "throughput": 1041.35, "total_tokens": 443208} {"current_steps": 4920, "total_steps": 76960, "loss": 0.3021, "lr": 3.195816008316008e-05, "epoch": 1.2785862785862787, "percentage": 6.39, "elapsed_time": "0:07:06", "remaining_time": "1:43:57", "throughput": 1041.38, "total_tokens": 443656} {"current_steps": 4925, "total_steps": 76960, "loss": 0.1444, "lr": 3.19906444906445e-05, "epoch": 1.2798856548856548, "percentage": 6.4, "elapsed_time": "0:07:06", "remaining_time": "1:43:57", "throughput": 1041.33, "total_tokens": 444072} {"current_steps": 4930, "total_steps": 76960, "loss": 0.3297, "lr": 3.20231288981289e-05, "epoch": 1.2811850311850312, "percentage": 6.41, "elapsed_time": "0:07:06", "remaining_time": "1:43:56", "throughput": 1041.48, "total_tokens": 444568} {"current_steps": 4935, "total_steps": 76960, "loss": 0.3114, "lr": 3.205561330561331e-05, "epoch": 1.2824844074844075, "percentage": 6.41, "elapsed_time": "0:07:07", "remaining_time": "1:43:56", "throughput": 1041.51, "total_tokens": 445016} {"current_steps": 4940, "total_steps": 76960, "loss": 0.1781, "lr": 3.208809771309771e-05, "epoch": 1.2837837837837838, "percentage": 6.42, "elapsed_time": "0:07:07", "remaining_time": "1:43:55", "throughput": 1041.5, "total_tokens": 445448} {"current_steps": 4945, "total_steps": 76960, "loss": 0.2113, "lr": 3.212058212058212e-05, "epoch": 1.28508316008316, "percentage": 6.43, "elapsed_time": "0:07:08", "remaining_time": "1:43:54", "throughput": 1041.57, "total_tokens": 445912} {"current_steps": 4950, "total_steps": 76960, "loss": 0.2478, "lr": 3.2153066528066525e-05, "epoch": 1.2863825363825363, "percentage": 6.43, "elapsed_time": "0:07:08", "remaining_time": "1:43:54", "throughput": 1041.6, "total_tokens": 446360} {"current_steps": 4955, "total_steps": 76960, "loss": 0.2194, "lr": 3.2185550935550935e-05, "epoch": 1.2876819126819128, "percentage": 6.44, "elapsed_time": "0:07:08", "remaining_time": "1:43:53", "throughput": 1041.59, "total_tokens": 446792} {"current_steps": 4960, "total_steps": 76960, "loss": 0.2697, "lr": 3.2218035343035345e-05, "epoch": 1.288981288981289, "percentage": 6.44, "elapsed_time": "0:07:09", "remaining_time": "1:43:52", "throughput": 1041.63, "total_tokens": 447240} {"current_steps": 4965, "total_steps": 76960, "loss": 0.2385, "lr": 3.2250519750519754e-05, "epoch": 1.2902806652806653, "percentage": 6.45, "elapsed_time": "0:07:09", "remaining_time": "1:43:52", "throughput": 1041.66, "total_tokens": 447688} {"current_steps": 4970, "total_steps": 76960, "loss": 0.2569, "lr": 3.228300415800416e-05, "epoch": 1.2915800415800416, "percentage": 6.46, "elapsed_time": "0:07:10", "remaining_time": "1:43:51", "throughput": 1041.72, "total_tokens": 448152} {"current_steps": 4975, "total_steps": 76960, "loss": 0.2554, "lr": 3.231548856548857e-05, "epoch": 1.2928794178794178, "percentage": 6.46, "elapsed_time": "0:07:10", "remaining_time": "1:43:50", "throughput": 1041.83, "total_tokens": 448632} {"current_steps": 4980, "total_steps": 76960, "loss": 0.3469, "lr": 3.234797297297297e-05, "epoch": 1.2941787941787941, "percentage": 6.47, "elapsed_time": "0:07:11", "remaining_time": "1:43:50", "throughput": 1041.97, "total_tokens": 449128} {"current_steps": 4985, "total_steps": 76960, "loss": 0.2775, "lr": 3.238045738045738e-05, "epoch": 1.2954781704781704, "percentage": 6.48, "elapsed_time": "0:07:11", "remaining_time": "1:43:49", "throughput": 1042.04, "total_tokens": 449592} {"current_steps": 4990, "total_steps": 76960, "loss": 0.2509, "lr": 3.241294178794179e-05, "epoch": 1.2967775467775469, "percentage": 6.48, "elapsed_time": "0:07:11", "remaining_time": "1:43:48", "throughput": 1041.99, "total_tokens": 450008} {"current_steps": 4995, "total_steps": 76960, "loss": 0.3305, "lr": 3.24454261954262e-05, "epoch": 1.2980769230769231, "percentage": 6.49, "elapsed_time": "0:07:12", "remaining_time": "1:43:48", "throughput": 1042.05, "total_tokens": 450472} {"current_steps": 5000, "total_steps": 76960, "loss": 0.2676, "lr": 3.247791060291061e-05, "epoch": 1.2993762993762994, "percentage": 6.5, "elapsed_time": "0:07:12", "remaining_time": "1:43:47", "throughput": 1042.09, "total_tokens": 450920} {"current_steps": 5005, "total_steps": 76960, "loss": 0.1786, "lr": 3.251039501039501e-05, "epoch": 1.3006756756756757, "percentage": 6.5, "elapsed_time": "0:07:13", "remaining_time": "1:43:46", "throughput": 1042.15, "total_tokens": 451384} {"current_steps": 5010, "total_steps": 76960, "loss": 0.1618, "lr": 3.254287941787942e-05, "epoch": 1.301975051975052, "percentage": 6.51, "elapsed_time": "0:07:13", "remaining_time": "1:43:46", "throughput": 1042.1, "total_tokens": 451800} {"current_steps": 5015, "total_steps": 76960, "loss": 0.3312, "lr": 3.2575363825363824e-05, "epoch": 1.3032744282744284, "percentage": 6.52, "elapsed_time": "0:07:13", "remaining_time": "1:43:45", "throughput": 1042.16, "total_tokens": 452264} {"current_steps": 5020, "total_steps": 76960, "loss": 0.2566, "lr": 3.260784823284824e-05, "epoch": 1.3045738045738045, "percentage": 6.52, "elapsed_time": "0:07:14", "remaining_time": "1:43:45", "throughput": 1042.2, "total_tokens": 452712} {"current_steps": 5025, "total_steps": 76960, "loss": 0.2135, "lr": 3.264033264033264e-05, "epoch": 1.305873180873181, "percentage": 6.53, "elapsed_time": "0:07:14", "remaining_time": "1:43:44", "throughput": 1042.22, "total_tokens": 453160} {"current_steps": 5030, "total_steps": 76960, "loss": 0.2153, "lr": 3.267281704781705e-05, "epoch": 1.3071725571725572, "percentage": 6.54, "elapsed_time": "0:07:15", "remaining_time": "1:43:43", "throughput": 1042.18, "total_tokens": 453576} {"current_steps": 5035, "total_steps": 76960, "loss": 0.3808, "lr": 3.2705301455301456e-05, "epoch": 1.3084719334719335, "percentage": 6.54, "elapsed_time": "0:07:15", "remaining_time": "1:43:43", "throughput": 1042.2, "total_tokens": 454024} {"current_steps": 5040, "total_steps": 76960, "loss": 0.236, "lr": 3.2737785862785865e-05, "epoch": 1.3097713097713097, "percentage": 6.55, "elapsed_time": "0:07:16", "remaining_time": "1:43:42", "throughput": 1042.31, "total_tokens": 454504} {"current_steps": 5045, "total_steps": 76960, "loss": 0.2622, "lr": 3.277027027027027e-05, "epoch": 1.311070686070686, "percentage": 6.56, "elapsed_time": "0:07:16", "remaining_time": "1:43:41", "throughput": 1042.41, "total_tokens": 454984} {"current_steps": 5050, "total_steps": 76960, "loss": 0.2293, "lr": 3.280275467775468e-05, "epoch": 1.3123700623700625, "percentage": 6.56, "elapsed_time": "0:07:16", "remaining_time": "1:43:41", "throughput": 1042.47, "total_tokens": 455448} {"current_steps": 5055, "total_steps": 76960, "loss": 0.3113, "lr": 3.283523908523909e-05, "epoch": 1.3136694386694387, "percentage": 6.57, "elapsed_time": "0:07:17", "remaining_time": "1:43:40", "throughput": 1042.65, "total_tokens": 455960} {"current_steps": 5060, "total_steps": 76960, "loss": 0.1873, "lr": 3.28677234927235e-05, "epoch": 1.314968814968815, "percentage": 6.57, "elapsed_time": "0:07:17", "remaining_time": "1:43:39", "throughput": 1042.64, "total_tokens": 456392} {"current_steps": 5065, "total_steps": 76960, "loss": 0.2769, "lr": 3.29002079002079e-05, "epoch": 1.3162681912681913, "percentage": 6.58, "elapsed_time": "0:07:18", "remaining_time": "1:43:39", "throughput": 1042.79, "total_tokens": 456888} {"current_steps": 5070, "total_steps": 76960, "loss": 0.2108, "lr": 3.293269230769231e-05, "epoch": 1.3175675675675675, "percentage": 6.59, "elapsed_time": "0:07:18", "remaining_time": "1:43:38", "throughput": 1042.86, "total_tokens": 457352} {"current_steps": 5075, "total_steps": 76960, "loss": 0.2679, "lr": 3.296517671517671e-05, "epoch": 1.3188669438669438, "percentage": 6.59, "elapsed_time": "0:07:18", "remaining_time": "1:43:37", "throughput": 1043.03, "total_tokens": 457864} {"current_steps": 5080, "total_steps": 76960, "loss": 0.1111, "lr": 3.299766112266112e-05, "epoch": 1.32016632016632, "percentage": 6.6, "elapsed_time": "0:07:19", "remaining_time": "1:43:37", "throughput": 1043.02, "total_tokens": 458296} {"current_steps": 5085, "total_steps": 76960, "loss": 0.2773, "lr": 3.303014553014553e-05, "epoch": 1.3214656964656966, "percentage": 6.61, "elapsed_time": "0:07:19", "remaining_time": "1:43:36", "throughput": 1043.02, "total_tokens": 458728} {"current_steps": 5090, "total_steps": 76960, "loss": 0.3752, "lr": 3.306262993762994e-05, "epoch": 1.3227650727650728, "percentage": 6.61, "elapsed_time": "0:07:20", "remaining_time": "1:43:35", "throughput": 1043.12, "total_tokens": 459208} {"current_steps": 5095, "total_steps": 76960, "loss": 0.3144, "lr": 3.3095114345114344e-05, "epoch": 1.324064449064449, "percentage": 6.62, "elapsed_time": "0:07:20", "remaining_time": "1:43:35", "throughput": 1043.22, "total_tokens": 459688} {"current_steps": 5100, "total_steps": 76960, "loss": 0.1923, "lr": 3.3127598752598754e-05, "epoch": 1.3253638253638254, "percentage": 6.63, "elapsed_time": "0:07:21", "remaining_time": "1:43:34", "throughput": 1043.36, "total_tokens": 460184} {"current_steps": 5105, "total_steps": 76960, "loss": 0.2684, "lr": 3.3160083160083164e-05, "epoch": 1.3266632016632016, "percentage": 6.63, "elapsed_time": "0:07:21", "remaining_time": "1:43:34", "throughput": 1043.31, "total_tokens": 460600} {"current_steps": 5110, "total_steps": 76960, "loss": 0.2688, "lr": 3.3192567567567567e-05, "epoch": 1.3279625779625779, "percentage": 6.64, "elapsed_time": "0:07:21", "remaining_time": "1:43:33", "throughput": 1043.23, "total_tokens": 461000} {"current_steps": 5115, "total_steps": 76960, "loss": 0.2853, "lr": 3.3225051975051976e-05, "epoch": 1.3292619542619541, "percentage": 6.65, "elapsed_time": "0:07:22", "remaining_time": "1:43:32", "throughput": 1043.22, "total_tokens": 461432} {"current_steps": 5120, "total_steps": 76960, "loss": 0.2634, "lr": 3.3257536382536386e-05, "epoch": 1.3305613305613306, "percentage": 6.65, "elapsed_time": "0:07:22", "remaining_time": "1:43:32", "throughput": 1043.25, "total_tokens": 461880} {"current_steps": 5125, "total_steps": 76960, "loss": 0.2893, "lr": 3.3290020790020796e-05, "epoch": 1.331860706860707, "percentage": 6.66, "elapsed_time": "0:07:23", "remaining_time": "1:43:31", "throughput": 1043.28, "total_tokens": 462328} {"current_steps": 5130, "total_steps": 76960, "loss": 0.247, "lr": 3.33225051975052e-05, "epoch": 1.3331600831600832, "percentage": 6.67, "elapsed_time": "0:07:23", "remaining_time": "1:43:30", "throughput": 1043.23, "total_tokens": 462744} {"current_steps": 5135, "total_steps": 76960, "loss": 0.2029, "lr": 3.335498960498961e-05, "epoch": 1.3344594594594594, "percentage": 6.67, "elapsed_time": "0:07:23", "remaining_time": "1:43:30", "throughput": 1043.3, "total_tokens": 463208} {"current_steps": 5140, "total_steps": 76960, "loss": 0.2276, "lr": 3.338747401247401e-05, "epoch": 1.3357588357588357, "percentage": 6.68, "elapsed_time": "0:07:24", "remaining_time": "1:43:29", "throughput": 1043.3, "total_tokens": 463640} {"current_steps": 5145, "total_steps": 76960, "loss": 0.1598, "lr": 3.341995841995842e-05, "epoch": 1.3370582120582122, "percentage": 6.69, "elapsed_time": "0:07:24", "remaining_time": "1:43:28", "throughput": 1043.29, "total_tokens": 464072} {"current_steps": 5150, "total_steps": 76960, "loss": 0.2781, "lr": 3.345244282744283e-05, "epoch": 1.3383575883575882, "percentage": 6.69, "elapsed_time": "0:07:25", "remaining_time": "1:43:28", "throughput": 1043.32, "total_tokens": 464520} {"current_steps": 5155, "total_steps": 76960, "loss": 0.2288, "lr": 3.348492723492724e-05, "epoch": 1.3396569646569647, "percentage": 6.7, "elapsed_time": "0:07:25", "remaining_time": "1:43:27", "throughput": 1043.38, "total_tokens": 464984} {"current_steps": 5160, "total_steps": 76960, "loss": 0.3495, "lr": 3.351741164241164e-05, "epoch": 1.340956340956341, "percentage": 6.7, "elapsed_time": "0:07:26", "remaining_time": "1:43:26", "throughput": 1043.33, "total_tokens": 465400} {"current_steps": 5165, "total_steps": 76960, "loss": 0.2238, "lr": 3.354989604989605e-05, "epoch": 1.3422557172557172, "percentage": 6.71, "elapsed_time": "0:07:26", "remaining_time": "1:43:26", "throughput": 1043.39, "total_tokens": 465864} {"current_steps": 5170, "total_steps": 76960, "loss": 0.2678, "lr": 3.3582380457380455e-05, "epoch": 1.3435550935550935, "percentage": 6.72, "elapsed_time": "0:07:26", "remaining_time": "1:43:25", "throughput": 1043.38, "total_tokens": 466296} {"current_steps": 5175, "total_steps": 76960, "loss": 0.2248, "lr": 3.3614864864864865e-05, "epoch": 1.3448544698544698, "percentage": 6.72, "elapsed_time": "0:07:27", "remaining_time": "1:43:25", "throughput": 1043.41, "total_tokens": 466744} {"current_steps": 5180, "total_steps": 76960, "loss": 0.3252, "lr": 3.3647349272349275e-05, "epoch": 1.3461538461538463, "percentage": 6.73, "elapsed_time": "0:07:27", "remaining_time": "1:43:24", "throughput": 1043.4, "total_tokens": 467176} {"current_steps": 5185, "total_steps": 76960, "loss": 0.2235, "lr": 3.3679833679833684e-05, "epoch": 1.3474532224532225, "percentage": 6.74, "elapsed_time": "0:07:28", "remaining_time": "1:43:23", "throughput": 1043.43, "total_tokens": 467624} {"current_steps": 5190, "total_steps": 76960, "loss": 0.3018, "lr": 3.371231808731809e-05, "epoch": 1.3487525987525988, "percentage": 6.74, "elapsed_time": "0:07:28", "remaining_time": "1:43:23", "throughput": 1043.49, "total_tokens": 468088} {"current_steps": 5195, "total_steps": 76960, "loss": 0.291, "lr": 3.37448024948025e-05, "epoch": 1.350051975051975, "percentage": 6.75, "elapsed_time": "0:07:28", "remaining_time": "1:43:22", "throughput": 1043.59, "total_tokens": 468568} {"current_steps": 5200, "total_steps": 76960, "loss": 0.2589, "lr": 3.3777286902286906e-05, "epoch": 1.3513513513513513, "percentage": 6.76, "elapsed_time": "0:07:29", "remaining_time": "1:43:21", "throughput": 1043.61, "total_tokens": 469016} {"current_steps": 5205, "total_steps": 76960, "loss": 0.3073, "lr": 3.380977130977131e-05, "epoch": 1.3526507276507276, "percentage": 6.76, "elapsed_time": "0:07:29", "remaining_time": "1:43:21", "throughput": 1043.6, "total_tokens": 469448} {"current_steps": 5210, "total_steps": 76960, "loss": 0.2682, "lr": 3.384225571725572e-05, "epoch": 1.3539501039501038, "percentage": 6.77, "elapsed_time": "0:07:30", "remaining_time": "1:43:20", "throughput": 1043.63, "total_tokens": 469896} {"current_steps": 5215, "total_steps": 76960, "loss": 0.2244, "lr": 3.387474012474013e-05, "epoch": 1.3552494802494803, "percentage": 6.78, "elapsed_time": "0:07:30", "remaining_time": "1:43:20", "throughput": 1043.65, "total_tokens": 470344} {"current_steps": 5220, "total_steps": 76960, "loss": 0.2655, "lr": 3.390722453222454e-05, "epoch": 1.3565488565488566, "percentage": 6.78, "elapsed_time": "0:07:31", "remaining_time": "1:43:19", "throughput": 1043.64, "total_tokens": 470776} {"current_steps": 5225, "total_steps": 76960, "loss": 0.3456, "lr": 3.393970893970894e-05, "epoch": 1.3578482328482329, "percentage": 6.79, "elapsed_time": "0:07:31", "remaining_time": "1:43:18", "throughput": 1043.59, "total_tokens": 471192} {"current_steps": 5230, "total_steps": 76960, "loss": 0.3076, "lr": 3.397219334719335e-05, "epoch": 1.3591476091476091, "percentage": 6.8, "elapsed_time": "0:07:31", "remaining_time": "1:43:18", "throughput": 1043.58, "total_tokens": 471624} {"current_steps": 5235, "total_steps": 76960, "loss": 0.2427, "lr": 3.4004677754677754e-05, "epoch": 1.3604469854469854, "percentage": 6.8, "elapsed_time": "0:07:32", "remaining_time": "1:43:17", "throughput": 1043.68, "total_tokens": 472104} {"current_steps": 5240, "total_steps": 76960, "loss": 0.2646, "lr": 3.403716216216216e-05, "epoch": 1.3617463617463619, "percentage": 6.81, "elapsed_time": "0:07:32", "remaining_time": "1:43:17", "throughput": 1043.66, "total_tokens": 472536} {"current_steps": 5245, "total_steps": 76960, "loss": 0.2677, "lr": 3.406964656964657e-05, "epoch": 1.363045738045738, "percentage": 6.82, "elapsed_time": "0:07:33", "remaining_time": "1:43:16", "throughput": 1043.69, "total_tokens": 472984} {"current_steps": 5250, "total_steps": 76960, "loss": 0.2548, "lr": 3.410213097713098e-05, "epoch": 1.3643451143451144, "percentage": 6.82, "elapsed_time": "0:07:33", "remaining_time": "1:43:15", "throughput": 1043.68, "total_tokens": 473416} {"current_steps": 5255, "total_steps": 76960, "loss": 0.3413, "lr": 3.4134615384615386e-05, "epoch": 1.3656444906444907, "percentage": 6.83, "elapsed_time": "0:07:34", "remaining_time": "1:43:15", "throughput": 1043.67, "total_tokens": 473848} {"current_steps": 5260, "total_steps": 76960, "loss": 0.2464, "lr": 3.4167099792099795e-05, "epoch": 1.366943866943867, "percentage": 6.83, "elapsed_time": "0:07:34", "remaining_time": "1:43:14", "throughput": 1043.63, "total_tokens": 474264} {"current_steps": 5265, "total_steps": 76960, "loss": 0.2829, "lr": 3.41995841995842e-05, "epoch": 1.3682432432432432, "percentage": 6.84, "elapsed_time": "0:07:34", "remaining_time": "1:43:13", "throughput": 1043.58, "total_tokens": 474680} {"current_steps": 5270, "total_steps": 76960, "loss": 0.2774, "lr": 3.423206860706861e-05, "epoch": 1.3695426195426195, "percentage": 6.85, "elapsed_time": "0:07:35", "remaining_time": "1:43:13", "throughput": 1043.65, "total_tokens": 475144} {"current_steps": 5275, "total_steps": 76960, "loss": 0.2489, "lr": 3.426455301455301e-05, "epoch": 1.370841995841996, "percentage": 6.85, "elapsed_time": "0:07:35", "remaining_time": "1:43:12", "throughput": 1043.64, "total_tokens": 475576} {"current_steps": 5280, "total_steps": 76960, "loss": 0.2308, "lr": 3.429703742203743e-05, "epoch": 1.3721413721413722, "percentage": 6.86, "elapsed_time": "0:07:36", "remaining_time": "1:43:12", "throughput": 1043.66, "total_tokens": 476024} {"current_steps": 5285, "total_steps": 76960, "loss": 0.1734, "lr": 3.432952182952183e-05, "epoch": 1.3734407484407485, "percentage": 6.87, "elapsed_time": "0:07:36", "remaining_time": "1:43:11", "throughput": 1043.65, "total_tokens": 476456} {"current_steps": 5290, "total_steps": 76960, "loss": 0.2233, "lr": 3.436200623700624e-05, "epoch": 1.3747401247401247, "percentage": 6.87, "elapsed_time": "0:07:36", "remaining_time": "1:43:10", "throughput": 1043.72, "total_tokens": 476920} {"current_steps": 5295, "total_steps": 76960, "loss": 0.3744, "lr": 3.439449064449064e-05, "epoch": 1.376039501039501, "percentage": 6.88, "elapsed_time": "0:07:37", "remaining_time": "1:43:10", "throughput": 1043.75, "total_tokens": 477368} {"current_steps": 5300, "total_steps": 76960, "loss": 0.1502, "lr": 3.442697505197505e-05, "epoch": 1.3773388773388773, "percentage": 6.89, "elapsed_time": "0:07:37", "remaining_time": "1:43:09", "throughput": 1043.81, "total_tokens": 477832} {"current_steps": 5305, "total_steps": 76960, "loss": 0.1636, "lr": 3.445945945945946e-05, "epoch": 1.3786382536382535, "percentage": 6.89, "elapsed_time": "0:07:38", "remaining_time": "1:43:08", "throughput": 1043.8, "total_tokens": 478264} {"current_steps": 5310, "total_steps": 76960, "loss": 0.2825, "lr": 3.449194386694387e-05, "epoch": 1.37993762993763, "percentage": 6.9, "elapsed_time": "0:07:38", "remaining_time": "1:43:08", "throughput": 1043.79, "total_tokens": 478696} {"current_steps": 5315, "total_steps": 76960, "loss": 0.3361, "lr": 3.4524428274428274e-05, "epoch": 1.3812370062370063, "percentage": 6.91, "elapsed_time": "0:07:39", "remaining_time": "1:43:07", "throughput": 1043.78, "total_tokens": 479128} {"current_steps": 5320, "total_steps": 76960, "loss": 0.2026, "lr": 3.4556912681912684e-05, "epoch": 1.3825363825363826, "percentage": 6.91, "elapsed_time": "0:07:39", "remaining_time": "1:43:07", "throughput": 1043.84, "total_tokens": 479592} {"current_steps": 5325, "total_steps": 76960, "loss": 0.1351, "lr": 3.4589397089397094e-05, "epoch": 1.3838357588357588, "percentage": 6.92, "elapsed_time": "0:07:39", "remaining_time": "1:43:06", "throughput": 1043.87, "total_tokens": 480040} {"current_steps": 5330, "total_steps": 76960, "loss": 0.2492, "lr": 3.4621881496881496e-05, "epoch": 1.385135135135135, "percentage": 6.93, "elapsed_time": "0:07:40", "remaining_time": "1:43:05", "throughput": 1043.83, "total_tokens": 480456} {"current_steps": 5335, "total_steps": 76960, "loss": 0.241, "lr": 3.4654365904365906e-05, "epoch": 1.3864345114345114, "percentage": 6.93, "elapsed_time": "0:07:40", "remaining_time": "1:43:05", "throughput": 1043.85, "total_tokens": 480904} {"current_steps": 5340, "total_steps": 76960, "loss": 0.2753, "lr": 3.468685031185031e-05, "epoch": 1.3877338877338876, "percentage": 6.94, "elapsed_time": "0:07:41", "remaining_time": "1:43:04", "throughput": 1043.84, "total_tokens": 481336} {"current_steps": 5345, "total_steps": 76960, "loss": 0.2146, "lr": 3.4719334719334725e-05, "epoch": 1.389033264033264, "percentage": 6.95, "elapsed_time": "0:07:41", "remaining_time": "1:43:03", "throughput": 1043.87, "total_tokens": 481784} {"current_steps": 5350, "total_steps": 76960, "loss": 0.3346, "lr": 3.475181912681913e-05, "epoch": 1.3903326403326404, "percentage": 6.95, "elapsed_time": "0:07:41", "remaining_time": "1:43:03", "throughput": 1043.86, "total_tokens": 482216} {"current_steps": 5355, "total_steps": 76960, "loss": 0.2872, "lr": 3.478430353430354e-05, "epoch": 1.3916320166320166, "percentage": 6.96, "elapsed_time": "0:07:42", "remaining_time": "1:43:02", "throughput": 1043.89, "total_tokens": 482664} {"current_steps": 5360, "total_steps": 76960, "loss": 0.3192, "lr": 3.481678794178794e-05, "epoch": 1.392931392931393, "percentage": 6.96, "elapsed_time": "0:07:42", "remaining_time": "1:43:02", "throughput": 1043.88, "total_tokens": 483096} {"current_steps": 5365, "total_steps": 76960, "loss": 0.2142, "lr": 3.484927234927235e-05, "epoch": 1.3942307692307692, "percentage": 6.97, "elapsed_time": "0:07:43", "remaining_time": "1:43:01", "throughput": 1043.94, "total_tokens": 483560} {"current_steps": 5370, "total_steps": 76960, "loss": 0.2717, "lr": 3.488175675675675e-05, "epoch": 1.3955301455301456, "percentage": 6.98, "elapsed_time": "0:07:43", "remaining_time": "1:43:00", "throughput": 1043.93, "total_tokens": 483992} {"current_steps": 5375, "total_steps": 76960, "loss": 0.2969, "lr": 3.491424116424117e-05, "epoch": 1.3968295218295217, "percentage": 6.98, "elapsed_time": "0:07:44", "remaining_time": "1:43:00", "throughput": 1043.95, "total_tokens": 484440} {"current_steps": 5380, "total_steps": 76960, "loss": 0.3505, "lr": 3.494672557172557e-05, "epoch": 1.3981288981288982, "percentage": 6.99, "elapsed_time": "0:07:44", "remaining_time": "1:42:59", "throughput": 1043.98, "total_tokens": 484888} {"current_steps": 5385, "total_steps": 76960, "loss": 0.2441, "lr": 3.497920997920998e-05, "epoch": 1.3994282744282744, "percentage": 7.0, "elapsed_time": "0:07:44", "remaining_time": "1:42:58", "throughput": 1043.97, "total_tokens": 485320} {"current_steps": 5390, "total_steps": 76960, "loss": 0.2656, "lr": 3.5011694386694385e-05, "epoch": 1.4007276507276507, "percentage": 7.0, "elapsed_time": "0:07:45", "remaining_time": "1:42:58", "throughput": 1044.02, "total_tokens": 485784} {"current_steps": 5395, "total_steps": 76960, "loss": 0.267, "lr": 3.5044178794178795e-05, "epoch": 1.402027027027027, "percentage": 7.01, "elapsed_time": "0:07:45", "remaining_time": "1:42:57", "throughput": 1044.04, "total_tokens": 486232} {"current_steps": 5400, "total_steps": 76960, "loss": 0.2591, "lr": 3.5076663201663205e-05, "epoch": 1.4033264033264032, "percentage": 7.02, "elapsed_time": "0:07:46", "remaining_time": "1:42:57", "throughput": 1044.1, "total_tokens": 486696} {"current_steps": 5405, "total_steps": 76960, "loss": 0.3116, "lr": 3.5109147609147614e-05, "epoch": 1.4046257796257797, "percentage": 7.02, "elapsed_time": "0:07:46", "remaining_time": "1:42:56", "throughput": 1044.16, "total_tokens": 487160} {"current_steps": 5410, "total_steps": 76960, "loss": 0.3246, "lr": 3.514163201663202e-05, "epoch": 1.405925155925156, "percentage": 7.03, "elapsed_time": "0:07:46", "remaining_time": "1:42:55", "throughput": 1044.15, "total_tokens": 487592} {"current_steps": 5415, "total_steps": 76960, "loss": 0.2792, "lr": 3.517411642411643e-05, "epoch": 1.4072245322245323, "percentage": 7.04, "elapsed_time": "0:07:47", "remaining_time": "1:42:55", "throughput": 1044.14, "total_tokens": 488024} {"current_steps": 5420, "total_steps": 76960, "loss": 0.2985, "lr": 3.5206600831600836e-05, "epoch": 1.4085239085239085, "percentage": 7.04, "elapsed_time": "0:07:47", "remaining_time": "1:42:54", "throughput": 1044.2, "total_tokens": 488488} {"current_steps": 5425, "total_steps": 76960, "loss": 0.2858, "lr": 3.523908523908524e-05, "epoch": 1.4098232848232848, "percentage": 7.05, "elapsed_time": "0:07:48", "remaining_time": "1:42:54", "throughput": 1044.19, "total_tokens": 488920} {"current_steps": 5430, "total_steps": 76960, "loss": 0.2862, "lr": 3.527156964656965e-05, "epoch": 1.411122661122661, "percentage": 7.06, "elapsed_time": "0:07:48", "remaining_time": "1:42:53", "throughput": 1044.19, "total_tokens": 489352} {"current_steps": 5435, "total_steps": 76960, "loss": 0.2775, "lr": 3.530405405405405e-05, "epoch": 1.4124220374220373, "percentage": 7.06, "elapsed_time": "0:07:49", "remaining_time": "1:42:52", "throughput": 1044.25, "total_tokens": 489816} {"current_steps": 5440, "total_steps": 76960, "loss": 0.3098, "lr": 3.533653846153847e-05, "epoch": 1.4137214137214138, "percentage": 7.07, "elapsed_time": "0:07:49", "remaining_time": "1:42:52", "throughput": 1044.28, "total_tokens": 490264} {"current_steps": 5445, "total_steps": 76960, "loss": 0.271, "lr": 3.536902286902287e-05, "epoch": 1.41502079002079, "percentage": 7.08, "elapsed_time": "0:07:49", "remaining_time": "1:42:51", "throughput": 1044.34, "total_tokens": 490728} {"current_steps": 5450, "total_steps": 76960, "loss": 0.2188, "lr": 3.540150727650728e-05, "epoch": 1.4163201663201663, "percentage": 7.08, "elapsed_time": "0:07:50", "remaining_time": "1:42:51", "throughput": 1044.36, "total_tokens": 491176} {"current_steps": 5455, "total_steps": 76960, "loss": 0.2057, "lr": 3.5433991683991684e-05, "epoch": 1.4176195426195426, "percentage": 7.09, "elapsed_time": "0:07:50", "remaining_time": "1:42:50", "throughput": 1044.39, "total_tokens": 491624} {"current_steps": 5460, "total_steps": 76960, "loss": 0.2953, "lr": 3.546647609147609e-05, "epoch": 1.4189189189189189, "percentage": 7.09, "elapsed_time": "0:07:51", "remaining_time": "1:42:49", "throughput": 1044.55, "total_tokens": 492136} {"current_steps": 5465, "total_steps": 76960, "loss": 0.3739, "lr": 3.5498960498960496e-05, "epoch": 1.4202182952182953, "percentage": 7.1, "elapsed_time": "0:07:51", "remaining_time": "1:42:49", "throughput": 1044.61, "total_tokens": 492600} {"current_steps": 5470, "total_steps": 76960, "loss": 0.2624, "lr": 3.553144490644491e-05, "epoch": 1.4215176715176714, "percentage": 7.11, "elapsed_time": "0:07:51", "remaining_time": "1:42:48", "throughput": 1044.57, "total_tokens": 493016} {"current_steps": 5475, "total_steps": 76960, "loss": 0.3128, "lr": 3.5563929313929315e-05, "epoch": 1.4228170478170479, "percentage": 7.11, "elapsed_time": "0:07:52", "remaining_time": "1:42:47", "throughput": 1044.63, "total_tokens": 493480} {"current_steps": 5480, "total_steps": 76960, "loss": 0.1976, "lr": 3.5596413721413725e-05, "epoch": 1.4241164241164241, "percentage": 7.12, "elapsed_time": "0:07:52", "remaining_time": "1:42:47", "throughput": 1044.62, "total_tokens": 493912} {"current_steps": 5485, "total_steps": 76960, "loss": 0.2302, "lr": 3.562889812889813e-05, "epoch": 1.4254158004158004, "percentage": 7.13, "elapsed_time": "0:07:53", "remaining_time": "1:42:46", "throughput": 1044.61, "total_tokens": 494344} {"current_steps": 5490, "total_steps": 76960, "loss": 0.2221, "lr": 3.566138253638254e-05, "epoch": 1.4267151767151767, "percentage": 7.13, "elapsed_time": "0:07:53", "remaining_time": "1:42:46", "throughput": 1044.63, "total_tokens": 494792} {"current_steps": 5495, "total_steps": 76960, "loss": 0.1633, "lr": 3.569386694386694e-05, "epoch": 1.428014553014553, "percentage": 7.14, "elapsed_time": "0:07:54", "remaining_time": "1:42:45", "throughput": 1044.63, "total_tokens": 495224} {"current_steps": 5500, "total_steps": 76960, "loss": 0.2044, "lr": 3.572635135135135e-05, "epoch": 1.4293139293139294, "percentage": 7.15, "elapsed_time": "0:07:54", "remaining_time": "1:42:44", "throughput": 1044.75, "total_tokens": 495720} {"current_steps": 5505, "total_steps": 76960, "loss": 0.4463, "lr": 3.575883575883576e-05, "epoch": 1.4306133056133057, "percentage": 7.15, "elapsed_time": "0:07:54", "remaining_time": "1:42:44", "throughput": 1044.74, "total_tokens": 496152} {"current_steps": 5510, "total_steps": 76960, "loss": 0.2041, "lr": 3.579132016632017e-05, "epoch": 1.431912681912682, "percentage": 7.16, "elapsed_time": "0:07:55", "remaining_time": "1:42:43", "throughput": 1044.67, "total_tokens": 496552} {"current_steps": 5515, "total_steps": 76960, "loss": 0.2212, "lr": 3.582380457380458e-05, "epoch": 1.4332120582120582, "percentage": 7.17, "elapsed_time": "0:07:55", "remaining_time": "1:42:43", "throughput": 1044.62, "total_tokens": 496968} {"current_steps": 5520, "total_steps": 76960, "loss": 0.3021, "lr": 3.585628898128898e-05, "epoch": 1.4345114345114345, "percentage": 7.17, "elapsed_time": "0:07:56", "remaining_time": "1:42:42", "throughput": 1044.68, "total_tokens": 497432} {"current_steps": 5525, "total_steps": 76960, "loss": 0.2596, "lr": 3.588877338877339e-05, "epoch": 1.4358108108108107, "percentage": 7.18, "elapsed_time": "0:07:56", "remaining_time": "1:42:41", "throughput": 1044.74, "total_tokens": 497896} {"current_steps": 5530, "total_steps": 76960, "loss": 0.2292, "lr": 3.5921257796257795e-05, "epoch": 1.437110187110187, "percentage": 7.19, "elapsed_time": "0:07:56", "remaining_time": "1:42:41", "throughput": 1044.77, "total_tokens": 498344} {"current_steps": 5535, "total_steps": 76960, "loss": 0.1547, "lr": 3.595374220374221e-05, "epoch": 1.4384095634095635, "percentage": 7.19, "elapsed_time": "0:07:57", "remaining_time": "1:42:40", "throughput": 1044.75, "total_tokens": 498776} {"current_steps": 5540, "total_steps": 76960, "loss": 0.1075, "lr": 3.5986226611226614e-05, "epoch": 1.4397089397089398, "percentage": 7.2, "elapsed_time": "0:07:57", "remaining_time": "1:42:39", "throughput": 1044.81, "total_tokens": 499240} {"current_steps": 5545, "total_steps": 76960, "loss": 0.2388, "lr": 3.6018711018711024e-05, "epoch": 1.441008316008316, "percentage": 7.21, "elapsed_time": "0:07:58", "remaining_time": "1:42:39", "throughput": 1044.94, "total_tokens": 499736} {"current_steps": 5550, "total_steps": 76960, "loss": 0.4022, "lr": 3.6051195426195426e-05, "epoch": 1.4423076923076923, "percentage": 7.21, "elapsed_time": "0:07:58", "remaining_time": "1:42:38", "throughput": 1044.93, "total_tokens": 500168} {"current_steps": 5555, "total_steps": 76960, "loss": 0.3806, "lr": 3.6083679833679836e-05, "epoch": 1.4436070686070686, "percentage": 7.22, "elapsed_time": "0:07:59", "remaining_time": "1:42:38", "throughput": 1044.98, "total_tokens": 500632} {"current_steps": 5560, "total_steps": 76960, "loss": 0.3119, "lr": 3.611616424116424e-05, "epoch": 1.444906444906445, "percentage": 7.22, "elapsed_time": "0:07:59", "remaining_time": "1:42:37", "throughput": 1044.97, "total_tokens": 501064} {"current_steps": 5565, "total_steps": 76960, "loss": 0.2346, "lr": 3.6148648648648655e-05, "epoch": 1.446205821205821, "percentage": 7.23, "elapsed_time": "0:07:59", "remaining_time": "1:42:37", "throughput": 1044.96, "total_tokens": 501496} {"current_steps": 5570, "total_steps": 76960, "loss": 0.2611, "lr": 3.618113305613306e-05, "epoch": 1.4475051975051976, "percentage": 7.24, "elapsed_time": "0:08:00", "remaining_time": "1:42:36", "throughput": 1045.05, "total_tokens": 501976} {"current_steps": 5575, "total_steps": 76960, "loss": 0.2874, "lr": 3.621361746361747e-05, "epoch": 1.4488045738045738, "percentage": 7.24, "elapsed_time": "0:08:00", "remaining_time": "1:42:35", "throughput": 1045.0, "total_tokens": 502392} {"current_steps": 5580, "total_steps": 76960, "loss": 0.3838, "lr": 3.624610187110187e-05, "epoch": 1.45010395010395, "percentage": 7.25, "elapsed_time": "0:08:01", "remaining_time": "1:42:35", "throughput": 1044.99, "total_tokens": 502824} {"current_steps": 5585, "total_steps": 76960, "loss": 0.2304, "lr": 3.627858627858628e-05, "epoch": 1.4514033264033264, "percentage": 7.26, "elapsed_time": "0:08:01", "remaining_time": "1:42:34", "throughput": 1045.08, "total_tokens": 503304} {"current_steps": 5590, "total_steps": 76960, "loss": 0.2205, "lr": 3.631107068607068e-05, "epoch": 1.4527027027027026, "percentage": 7.26, "elapsed_time": "0:08:02", "remaining_time": "1:42:34", "throughput": 1045.04, "total_tokens": 503720} {"current_steps": 5595, "total_steps": 76960, "loss": 0.2235, "lr": 3.634355509355509e-05, "epoch": 1.4540020790020791, "percentage": 7.27, "elapsed_time": "0:08:02", "remaining_time": "1:42:33", "throughput": 1045.1, "total_tokens": 504184} {"current_steps": 5600, "total_steps": 76960, "loss": 0.1587, "lr": 3.63760395010395e-05, "epoch": 1.4553014553014554, "percentage": 7.28, "elapsed_time": "0:08:02", "remaining_time": "1:42:32", "throughput": 1045.19, "total_tokens": 504664} {"current_steps": 5605, "total_steps": 76960, "loss": 0.3989, "lr": 3.640852390852391e-05, "epoch": 1.4566008316008316, "percentage": 7.28, "elapsed_time": "0:08:03", "remaining_time": "1:42:32", "throughput": 1045.21, "total_tokens": 505112} {"current_steps": 5610, "total_steps": 76960, "loss": 0.2794, "lr": 3.6441008316008315e-05, "epoch": 1.457900207900208, "percentage": 7.29, "elapsed_time": "0:08:03", "remaining_time": "1:42:31", "throughput": 1045.23, "total_tokens": 505560} {"current_steps": 5615, "total_steps": 76960, "loss": 0.275, "lr": 3.6473492723492725e-05, "epoch": 1.4591995841995842, "percentage": 7.3, "elapsed_time": "0:08:04", "remaining_time": "1:42:31", "throughput": 1045.22, "total_tokens": 505992} {"current_steps": 5620, "total_steps": 76960, "loss": 0.2734, "lr": 3.6505977130977134e-05, "epoch": 1.4604989604989604, "percentage": 7.3, "elapsed_time": "0:08:04", "remaining_time": "1:42:30", "throughput": 1045.28, "total_tokens": 506456} {"current_steps": 5625, "total_steps": 76960, "loss": 0.2771, "lr": 3.653846153846154e-05, "epoch": 1.4617983367983367, "percentage": 7.31, "elapsed_time": "0:08:04", "remaining_time": "1:42:29", "throughput": 1045.24, "total_tokens": 506872} {"current_steps": 5630, "total_steps": 76960, "loss": 0.3451, "lr": 3.657094594594595e-05, "epoch": 1.4630977130977132, "percentage": 7.32, "elapsed_time": "0:08:05", "remaining_time": "1:42:29", "throughput": 1045.25, "total_tokens": 507320} {"current_steps": 5635, "total_steps": 76960, "loss": 0.3346, "lr": 3.660343035343036e-05, "epoch": 1.4643970893970895, "percentage": 7.32, "elapsed_time": "0:08:05", "remaining_time": "1:42:28", "throughput": 1045.41, "total_tokens": 507832} {"current_steps": 5640, "total_steps": 76960, "loss": 0.2429, "lr": 3.6635914760914766e-05, "epoch": 1.4656964656964657, "percentage": 7.33, "elapsed_time": "0:08:06", "remaining_time": "1:42:28", "throughput": 1045.46, "total_tokens": 508296} {"current_steps": 5645, "total_steps": 76960, "loss": 0.2855, "lr": 3.666839916839917e-05, "epoch": 1.466995841995842, "percentage": 7.33, "elapsed_time": "0:08:06", "remaining_time": "1:42:27", "throughput": 1045.52, "total_tokens": 508760} {"current_steps": 5650, "total_steps": 76960, "loss": 0.3005, "lr": 3.670088357588358e-05, "epoch": 1.4682952182952183, "percentage": 7.34, "elapsed_time": "0:08:07", "remaining_time": "1:42:26", "throughput": 1045.55, "total_tokens": 509208} {"current_steps": 5655, "total_steps": 76960, "loss": 0.2942, "lr": 3.673336798336798e-05, "epoch": 1.4695945945945945, "percentage": 7.35, "elapsed_time": "0:08:07", "remaining_time": "1:42:26", "throughput": 1045.53, "total_tokens": 509640} {"current_steps": 5660, "total_steps": 76960, "loss": 0.2358, "lr": 3.676585239085239e-05, "epoch": 1.4708939708939708, "percentage": 7.35, "elapsed_time": "0:08:07", "remaining_time": "1:42:25", "throughput": 1045.59, "total_tokens": 510104} {"current_steps": 5665, "total_steps": 76960, "loss": 0.2082, "lr": 3.67983367983368e-05, "epoch": 1.4721933471933473, "percentage": 7.36, "elapsed_time": "0:08:08", "remaining_time": "1:42:25", "throughput": 1045.54, "total_tokens": 510520} {"current_steps": 5670, "total_steps": 76960, "loss": 0.3282, "lr": 3.683082120582121e-05, "epoch": 1.4734927234927235, "percentage": 7.37, "elapsed_time": "0:08:08", "remaining_time": "1:42:24", "throughput": 1045.56, "total_tokens": 510968} {"current_steps": 5675, "total_steps": 76960, "loss": 0.2229, "lr": 3.6863305613305614e-05, "epoch": 1.4747920997920998, "percentage": 7.37, "elapsed_time": "0:08:09", "remaining_time": "1:42:23", "throughput": 1045.55, "total_tokens": 511400} {"current_steps": 5680, "total_steps": 76960, "loss": 0.1633, "lr": 3.689579002079002e-05, "epoch": 1.476091476091476, "percentage": 7.38, "elapsed_time": "0:08:09", "remaining_time": "1:42:23", "throughput": 1045.58, "total_tokens": 511848} {"current_steps": 5685, "total_steps": 76960, "loss": 0.2138, "lr": 3.6928274428274426e-05, "epoch": 1.4773908523908523, "percentage": 7.39, "elapsed_time": "0:08:09", "remaining_time": "1:42:22", "throughput": 1045.63, "total_tokens": 512312} {"current_steps": 5690, "total_steps": 76960, "loss": 0.3321, "lr": 3.6960758835758836e-05, "epoch": 1.4786902286902288, "percentage": 7.39, "elapsed_time": "0:08:10", "remaining_time": "1:42:22", "throughput": 1045.66, "total_tokens": 512760} {"current_steps": 5695, "total_steps": 76960, "loss": 0.3374, "lr": 3.6993243243243245e-05, "epoch": 1.4799896049896049, "percentage": 7.4, "elapsed_time": "0:08:10", "remaining_time": "1:42:21", "throughput": 1045.81, "total_tokens": 513272} {"current_steps": 5700, "total_steps": 76960, "loss": 0.2895, "lr": 3.7025727650727655e-05, "epoch": 1.4812889812889813, "percentage": 7.41, "elapsed_time": "0:08:11", "remaining_time": "1:42:20", "throughput": 1045.87, "total_tokens": 513736} {"current_steps": 5705, "total_steps": 76960, "loss": 0.2839, "lr": 3.705821205821206e-05, "epoch": 1.4825883575883576, "percentage": 7.41, "elapsed_time": "0:08:11", "remaining_time": "1:42:20", "throughput": 1045.86, "total_tokens": 514168} {"current_steps": 5710, "total_steps": 76960, "loss": 0.2762, "lr": 3.709069646569647e-05, "epoch": 1.4838877338877339, "percentage": 7.42, "elapsed_time": "0:08:12", "remaining_time": "1:42:19", "throughput": 1045.85, "total_tokens": 514600} {"current_steps": 5715, "total_steps": 76960, "loss": 0.2768, "lr": 3.712318087318088e-05, "epoch": 1.4851871101871101, "percentage": 7.43, "elapsed_time": "0:08:12", "remaining_time": "1:42:19", "throughput": 1046.0, "total_tokens": 515112} {"current_steps": 5720, "total_steps": 76960, "loss": 0.2751, "lr": 3.715566528066528e-05, "epoch": 1.4864864864864864, "percentage": 7.43, "elapsed_time": "0:08:12", "remaining_time": "1:42:18", "throughput": 1046.02, "total_tokens": 515560} {"current_steps": 5725, "total_steps": 76960, "loss": 0.1696, "lr": 3.718814968814969e-05, "epoch": 1.487785862785863, "percentage": 7.44, "elapsed_time": "0:08:13", "remaining_time": "1:42:17", "throughput": 1045.98, "total_tokens": 515976} {"current_steps": 5730, "total_steps": 76960, "loss": 0.3319, "lr": 3.72206340956341e-05, "epoch": 1.4890852390852392, "percentage": 7.45, "elapsed_time": "0:08:13", "remaining_time": "1:42:17", "throughput": 1046.16, "total_tokens": 516504} {"current_steps": 5735, "total_steps": 76960, "loss": 0.1943, "lr": 3.725311850311851e-05, "epoch": 1.4903846153846154, "percentage": 7.45, "elapsed_time": "0:08:14", "remaining_time": "1:42:16", "throughput": 1046.12, "total_tokens": 516920} {"current_steps": 5740, "total_steps": 76960, "loss": 0.3327, "lr": 3.728560291060291e-05, "epoch": 1.4916839916839917, "percentage": 7.46, "elapsed_time": "0:08:14", "remaining_time": "1:42:16", "throughput": 1046.11, "total_tokens": 517352} {"current_steps": 5745, "total_steps": 76960, "loss": 0.3304, "lr": 3.731808731808732e-05, "epoch": 1.492983367983368, "percentage": 7.46, "elapsed_time": "0:08:14", "remaining_time": "1:42:15", "throughput": 1046.16, "total_tokens": 517816} {"current_steps": 5750, "total_steps": 76960, "loss": 0.1735, "lr": 3.7350571725571725e-05, "epoch": 1.4942827442827442, "percentage": 7.47, "elapsed_time": "0:08:15", "remaining_time": "1:42:15", "throughput": 1046.24, "total_tokens": 518296} {"current_steps": 5755, "total_steps": 76960, "loss": 0.3286, "lr": 3.7383056133056134e-05, "epoch": 1.4955821205821205, "percentage": 7.48, "elapsed_time": "0:08:15", "remaining_time": "1:42:14", "throughput": 1046.26, "total_tokens": 518744} {"current_steps": 5760, "total_steps": 76960, "loss": 0.2308, "lr": 3.7415540540540544e-05, "epoch": 1.496881496881497, "percentage": 7.48, "elapsed_time": "0:08:16", "remaining_time": "1:42:13", "throughput": 1046.35, "total_tokens": 519224} {"current_steps": 5765, "total_steps": 76960, "loss": 0.281, "lr": 3.7448024948024953e-05, "epoch": 1.4981808731808732, "percentage": 7.49, "elapsed_time": "0:08:16", "remaining_time": "1:42:13", "throughput": 1046.37, "total_tokens": 519672} {"current_steps": 5770, "total_steps": 76960, "loss": 0.3025, "lr": 3.7480509355509356e-05, "epoch": 1.4994802494802495, "percentage": 7.5, "elapsed_time": "0:08:17", "remaining_time": "1:42:12", "throughput": 1046.39, "total_tokens": 520120} {"current_steps": 5775, "total_steps": 76960, "loss": 0.2471, "lr": 3.7512993762993766e-05, "epoch": 1.5007796257796258, "percentage": 7.5, "elapsed_time": "0:08:17", "remaining_time": "1:42:12", "throughput": 1046.37, "total_tokens": 520552} {"current_steps": 5780, "total_steps": 76960, "loss": 0.2577, "lr": 3.754547817047817e-05, "epoch": 1.502079002079002, "percentage": 7.51, "elapsed_time": "0:08:17", "remaining_time": "1:42:11", "throughput": 1046.36, "total_tokens": 520984} {"current_steps": 5785, "total_steps": 76960, "loss": 0.228, "lr": 3.757796257796258e-05, "epoch": 1.5033783783783785, "percentage": 7.52, "elapsed_time": "0:08:18", "remaining_time": "1:42:10", "throughput": 1046.42, "total_tokens": 521448} {"current_steps": 5790, "total_steps": 76960, "loss": 0.366, "lr": 3.761044698544699e-05, "epoch": 1.5046777546777546, "percentage": 7.52, "elapsed_time": "0:08:18", "remaining_time": "1:42:10", "throughput": 1046.44, "total_tokens": 521896} {"current_steps": 5795, "total_steps": 76960, "loss": 0.177, "lr": 3.76429313929314e-05, "epoch": 1.505977130977131, "percentage": 7.53, "elapsed_time": "0:08:19", "remaining_time": "1:42:09", "throughput": 1046.46, "total_tokens": 522344} {"current_steps": 5800, "total_steps": 76960, "loss": 0.2918, "lr": 3.76754158004158e-05, "epoch": 1.5072765072765073, "percentage": 7.54, "elapsed_time": "0:08:19", "remaining_time": "1:42:09", "throughput": 1046.42, "total_tokens": 522760} {"current_steps": 5805, "total_steps": 76960, "loss": 0.2278, "lr": 3.770790020790021e-05, "epoch": 1.5085758835758836, "percentage": 7.54, "elapsed_time": "0:08:19", "remaining_time": "1:42:08", "throughput": 1046.51, "total_tokens": 523240} {"current_steps": 5810, "total_steps": 76960, "loss": 0.1806, "lr": 3.774038461538461e-05, "epoch": 1.5098752598752598, "percentage": 7.55, "elapsed_time": "0:08:20", "remaining_time": "1:42:08", "throughput": 1046.53, "total_tokens": 523688} {"current_steps": 5815, "total_steps": 76960, "loss": 0.2258, "lr": 3.777286902286902e-05, "epoch": 1.511174636174636, "percentage": 7.56, "elapsed_time": "0:08:20", "remaining_time": "1:42:07", "throughput": 1046.64, "total_tokens": 524184} {"current_steps": 5820, "total_steps": 76960, "loss": 0.3478, "lr": 3.780535343035343e-05, "epoch": 1.5124740124740126, "percentage": 7.56, "elapsed_time": "0:08:21", "remaining_time": "1:42:06", "throughput": 1046.73, "total_tokens": 524664} {"current_steps": 5825, "total_steps": 76960, "loss": 0.3982, "lr": 3.783783783783784e-05, "epoch": 1.5137733887733886, "percentage": 7.57, "elapsed_time": "0:08:21", "remaining_time": "1:42:06", "throughput": 1046.85, "total_tokens": 525160} {"current_steps": 5830, "total_steps": 76960, "loss": 0.234, "lr": 3.7870322245322245e-05, "epoch": 1.5150727650727651, "percentage": 7.58, "elapsed_time": "0:08:22", "remaining_time": "1:42:05", "throughput": 1046.9, "total_tokens": 525624} {"current_steps": 5835, "total_steps": 76960, "loss": 0.2615, "lr": 3.7902806652806655e-05, "epoch": 1.5163721413721414, "percentage": 7.58, "elapsed_time": "0:08:22", "remaining_time": "1:42:05", "throughput": 1046.89, "total_tokens": 526056} {"current_steps": 5840, "total_steps": 76960, "loss": 0.2927, "lr": 3.7935291060291064e-05, "epoch": 1.5176715176715176, "percentage": 7.59, "elapsed_time": "0:08:22", "remaining_time": "1:42:04", "throughput": 1046.84, "total_tokens": 526472} {"current_steps": 5845, "total_steps": 76960, "loss": 0.2867, "lr": 3.796777546777547e-05, "epoch": 1.5189708939708941, "percentage": 7.59, "elapsed_time": "0:08:23", "remaining_time": "1:42:03", "throughput": 1046.87, "total_tokens": 526920} {"current_steps": 5850, "total_steps": 76960, "loss": 0.2623, "lr": 3.800025987525988e-05, "epoch": 1.5202702702702702, "percentage": 7.6, "elapsed_time": "0:08:23", "remaining_time": "1:42:03", "throughput": 1046.89, "total_tokens": 527368} {"current_steps": 5855, "total_steps": 76960, "loss": 0.1997, "lr": 3.8032744282744287e-05, "epoch": 1.5215696465696467, "percentage": 7.61, "elapsed_time": "0:08:24", "remaining_time": "1:42:02", "throughput": 1046.84, "total_tokens": 527784} {"current_steps": 5860, "total_steps": 76960, "loss": 0.2658, "lr": 3.8065228690228696e-05, "epoch": 1.5228690228690227, "percentage": 7.61, "elapsed_time": "0:08:24", "remaining_time": "1:42:02", "throughput": 1046.93, "total_tokens": 528264} {"current_steps": 5865, "total_steps": 76960, "loss": 0.3128, "lr": 3.80977130977131e-05, "epoch": 1.5241683991683992, "percentage": 7.62, "elapsed_time": "0:08:25", "remaining_time": "1:42:01", "throughput": 1046.91, "total_tokens": 528696} {"current_steps": 5870, "total_steps": 76960, "loss": 0.2169, "lr": 3.813019750519751e-05, "epoch": 1.5254677754677755, "percentage": 7.63, "elapsed_time": "0:08:25", "remaining_time": "1:42:01", "throughput": 1046.9, "total_tokens": 529128} {"current_steps": 5875, "total_steps": 76960, "loss": 0.3493, "lr": 3.816268191268191e-05, "epoch": 1.5267671517671517, "percentage": 7.63, "elapsed_time": "0:08:25", "remaining_time": "1:42:00", "throughput": 1046.92, "total_tokens": 529576} {"current_steps": 5880, "total_steps": 76960, "loss": 0.264, "lr": 3.819516632016632e-05, "epoch": 1.5280665280665282, "percentage": 7.64, "elapsed_time": "0:08:26", "remaining_time": "1:41:59", "throughput": 1046.95, "total_tokens": 530024} {"current_steps": 5885, "total_steps": 76960, "loss": 0.2942, "lr": 3.8227650727650724e-05, "epoch": 1.5293659043659042, "percentage": 7.65, "elapsed_time": "0:08:26", "remaining_time": "1:41:59", "throughput": 1047.0, "total_tokens": 530488} {"current_steps": 5890, "total_steps": 76960, "loss": 0.2711, "lr": 3.826013513513514e-05, "epoch": 1.5306652806652807, "percentage": 7.65, "elapsed_time": "0:08:27", "remaining_time": "1:41:58", "throughput": 1046.99, "total_tokens": 530920} {"current_steps": 5895, "total_steps": 76960, "loss": 0.2554, "lr": 3.8292619542619543e-05, "epoch": 1.531964656964657, "percentage": 7.66, "elapsed_time": "0:08:27", "remaining_time": "1:41:58", "throughput": 1046.98, "total_tokens": 531352} {"current_steps": 5900, "total_steps": 76960, "loss": 0.2967, "lr": 3.832510395010395e-05, "epoch": 1.5332640332640333, "percentage": 7.67, "elapsed_time": "0:08:27", "remaining_time": "1:41:57", "throughput": 1046.98, "total_tokens": 531784} {"current_steps": 5905, "total_steps": 76960, "loss": 0.2415, "lr": 3.8357588357588356e-05, "epoch": 1.5345634095634095, "percentage": 7.67, "elapsed_time": "0:08:28", "remaining_time": "1:41:56", "throughput": 1047.1, "total_tokens": 532280} {"current_steps": 5910, "total_steps": 76960, "loss": 0.2446, "lr": 3.8390072765072766e-05, "epoch": 1.5358627858627858, "percentage": 7.68, "elapsed_time": "0:08:28", "remaining_time": "1:41:56", "throughput": 1047.15, "total_tokens": 532744} {"current_steps": 5915, "total_steps": 76960, "loss": 0.2227, "lr": 3.8422557172557175e-05, "epoch": 1.5371621621621623, "percentage": 7.69, "elapsed_time": "0:08:29", "remaining_time": "1:41:55", "throughput": 1047.2, "total_tokens": 533208} {"current_steps": 5920, "total_steps": 76960, "loss": 0.2638, "lr": 3.8455041580041585e-05, "epoch": 1.5384615384615383, "percentage": 7.69, "elapsed_time": "0:08:29", "remaining_time": "1:41:55", "throughput": 1047.22, "total_tokens": 533656} {"current_steps": 5925, "total_steps": 76960, "loss": 0.3044, "lr": 3.848752598752599e-05, "epoch": 1.5397609147609148, "percentage": 7.7, "elapsed_time": "0:08:30", "remaining_time": "1:41:54", "throughput": 1047.24, "total_tokens": 534104} {"current_steps": 5930, "total_steps": 76960, "loss": 0.298, "lr": 3.85200103950104e-05, "epoch": 1.541060291060291, "percentage": 7.71, "elapsed_time": "0:08:30", "remaining_time": "1:41:53", "throughput": 1047.22, "total_tokens": 534536} {"current_steps": 5935, "total_steps": 76960, "loss": 0.2112, "lr": 3.855249480249481e-05, "epoch": 1.5423596673596673, "percentage": 7.71, "elapsed_time": "0:08:30", "remaining_time": "1:41:53", "throughput": 1047.27, "total_tokens": 535000} {"current_steps": 5940, "total_steps": 76960, "loss": 0.2796, "lr": 3.858497920997921e-05, "epoch": 1.5436590436590436, "percentage": 7.72, "elapsed_time": "0:08:31", "remaining_time": "1:41:52", "throughput": 1047.29, "total_tokens": 535448} {"current_steps": 5945, "total_steps": 76960, "loss": 0.2315, "lr": 3.861746361746362e-05, "epoch": 1.5449584199584199, "percentage": 7.72, "elapsed_time": "0:08:31", "remaining_time": "1:41:52", "throughput": 1047.37, "total_tokens": 535928} {"current_steps": 5950, "total_steps": 76960, "loss": 0.2575, "lr": 3.864994802494803e-05, "epoch": 1.5462577962577964, "percentage": 7.73, "elapsed_time": "0:08:32", "remaining_time": "1:41:51", "throughput": 1047.36, "total_tokens": 536360} {"current_steps": 5955, "total_steps": 76960, "loss": 0.3245, "lr": 3.868243243243244e-05, "epoch": 1.5475571725571724, "percentage": 7.74, "elapsed_time": "0:08:32", "remaining_time": "1:41:51", "throughput": 1047.28, "total_tokens": 536760} {"current_steps": 5960, "total_steps": 76960, "loss": 0.28, "lr": 3.871491683991684e-05, "epoch": 1.5488565488565489, "percentage": 7.74, "elapsed_time": "0:08:32", "remaining_time": "1:41:50", "throughput": 1047.24, "total_tokens": 537176} {"current_steps": 5965, "total_steps": 76960, "loss": 0.3386, "lr": 3.874740124740125e-05, "epoch": 1.5501559251559252, "percentage": 7.75, "elapsed_time": "0:08:33", "remaining_time": "1:41:49", "throughput": 1047.33, "total_tokens": 537656} {"current_steps": 5970, "total_steps": 76960, "loss": 0.2821, "lr": 3.8779885654885654e-05, "epoch": 1.5514553014553014, "percentage": 7.76, "elapsed_time": "0:08:33", "remaining_time": "1:41:49", "throughput": 1047.34, "total_tokens": 538104} {"current_steps": 5975, "total_steps": 76960, "loss": 0.2541, "lr": 3.8812370062370064e-05, "epoch": 1.552754677754678, "percentage": 7.76, "elapsed_time": "0:08:34", "remaining_time": "1:41:48", "throughput": 1047.42, "total_tokens": 538584} {"current_steps": 5980, "total_steps": 76960, "loss": 0.2535, "lr": 3.884485446985447e-05, "epoch": 1.554054054054054, "percentage": 7.77, "elapsed_time": "0:08:34", "remaining_time": "1:41:48", "throughput": 1047.51, "total_tokens": 539064} {"current_steps": 5985, "total_steps": 76960, "loss": 0.2164, "lr": 3.8877338877338883e-05, "epoch": 1.5553534303534304, "percentage": 7.78, "elapsed_time": "0:08:35", "remaining_time": "1:41:47", "throughput": 1047.47, "total_tokens": 539480} {"current_steps": 5990, "total_steps": 76960, "loss": 0.2182, "lr": 3.8909823284823286e-05, "epoch": 1.5566528066528067, "percentage": 7.78, "elapsed_time": "0:08:35", "remaining_time": "1:41:47", "throughput": 1047.45, "total_tokens": 539912} {"current_steps": 5995, "total_steps": 76960, "loss": 0.3255, "lr": 3.8942307692307696e-05, "epoch": 1.557952182952183, "percentage": 7.79, "elapsed_time": "0:08:35", "remaining_time": "1:41:46", "throughput": 1047.48, "total_tokens": 540360} {"current_steps": 6000, "total_steps": 76960, "loss": 0.273, "lr": 3.89747920997921e-05, "epoch": 1.5592515592515592, "percentage": 7.8, "elapsed_time": "0:08:36", "remaining_time": "1:41:45", "throughput": 1047.53, "total_tokens": 540824} {"current_steps": 6005, "total_steps": 76960, "loss": 0.3186, "lr": 3.900727650727651e-05, "epoch": 1.5605509355509355, "percentage": 7.8, "elapsed_time": "0:08:36", "remaining_time": "1:41:45", "throughput": 1047.64, "total_tokens": 541320} {"current_steps": 6010, "total_steps": 76960, "loss": 0.2186, "lr": 3.903976091476091e-05, "epoch": 1.561850311850312, "percentage": 7.81, "elapsed_time": "0:08:37", "remaining_time": "1:41:44", "throughput": 1047.66, "total_tokens": 541768} {"current_steps": 6015, "total_steps": 76960, "loss": 0.2006, "lr": 3.907224532224533e-05, "epoch": 1.563149688149688, "percentage": 7.82, "elapsed_time": "0:08:37", "remaining_time": "1:41:44", "throughput": 1047.74, "total_tokens": 542248} {"current_steps": 6020, "total_steps": 76960, "loss": 0.2073, "lr": 3.910472972972973e-05, "epoch": 1.5644490644490645, "percentage": 7.82, "elapsed_time": "0:08:37", "remaining_time": "1:41:43", "throughput": 1047.72, "total_tokens": 542680} {"current_steps": 6025, "total_steps": 76960, "loss": 0.1431, "lr": 3.913721413721414e-05, "epoch": 1.5657484407484408, "percentage": 7.83, "elapsed_time": "0:08:38", "remaining_time": "1:41:43", "throughput": 1047.71, "total_tokens": 543112} {"current_steps": 6030, "total_steps": 76960, "loss": 0.4523, "lr": 3.916969854469854e-05, "epoch": 1.567047817047817, "percentage": 7.84, "elapsed_time": "0:08:38", "remaining_time": "1:41:42", "throughput": 1047.76, "total_tokens": 543576} {"current_steps": 6035, "total_steps": 76960, "loss": 0.2679, "lr": 3.920218295218295e-05, "epoch": 1.5683471933471933, "percentage": 7.84, "elapsed_time": "0:08:39", "remaining_time": "1:41:41", "throughput": 1047.81, "total_tokens": 544040} {"current_steps": 6040, "total_steps": 76960, "loss": 0.232, "lr": 3.923466735966736e-05, "epoch": 1.5696465696465696, "percentage": 7.85, "elapsed_time": "0:08:39", "remaining_time": "1:41:41", "throughput": 1047.83, "total_tokens": 544488} {"current_steps": 6045, "total_steps": 76960, "loss": 0.3124, "lr": 3.9267151767151765e-05, "epoch": 1.570945945945946, "percentage": 7.85, "elapsed_time": "0:08:40", "remaining_time": "1:41:40", "throughput": 1047.78, "total_tokens": 544904} {"current_steps": 6050, "total_steps": 76960, "loss": 0.205, "lr": 3.929963617463618e-05, "epoch": 1.572245322245322, "percentage": 7.86, "elapsed_time": "0:08:40", "remaining_time": "1:41:40", "throughput": 1047.86, "total_tokens": 545384} {"current_steps": 6055, "total_steps": 76960, "loss": 0.2848, "lr": 3.9332120582120585e-05, "epoch": 1.5735446985446986, "percentage": 7.87, "elapsed_time": "0:08:40", "remaining_time": "1:41:39", "throughput": 1047.98, "total_tokens": 545880} {"current_steps": 6060, "total_steps": 76960, "loss": 0.1883, "lr": 3.9364604989604994e-05, "epoch": 1.5748440748440748, "percentage": 7.87, "elapsed_time": "0:08:41", "remaining_time": "1:41:39", "throughput": 1047.99, "total_tokens": 546328} {"current_steps": 6065, "total_steps": 76960, "loss": 0.2584, "lr": 3.93970893970894e-05, "epoch": 1.5761434511434511, "percentage": 7.88, "elapsed_time": "0:08:41", "remaining_time": "1:41:38", "throughput": 1048.04, "total_tokens": 546792} {"current_steps": 6070, "total_steps": 76960, "loss": 0.2689, "lr": 3.942957380457381e-05, "epoch": 1.5774428274428276, "percentage": 7.89, "elapsed_time": "0:08:42", "remaining_time": "1:41:37", "throughput": 1048.06, "total_tokens": 547240} {"current_steps": 6075, "total_steps": 76960, "loss": 0.1108, "lr": 3.946205821205821e-05, "epoch": 1.5787422037422036, "percentage": 7.89, "elapsed_time": "0:08:42", "remaining_time": "1:41:37", "throughput": 1048.08, "total_tokens": 547688} {"current_steps": 6080, "total_steps": 76960, "loss": 0.1893, "lr": 3.9494542619542626e-05, "epoch": 1.5800415800415801, "percentage": 7.9, "elapsed_time": "0:08:42", "remaining_time": "1:41:36", "throughput": 1048.07, "total_tokens": 548120} {"current_steps": 6085, "total_steps": 76960, "loss": 0.318, "lr": 3.952702702702703e-05, "epoch": 1.5813409563409564, "percentage": 7.91, "elapsed_time": "0:08:43", "remaining_time": "1:41:36", "throughput": 1048.12, "total_tokens": 548584} {"current_steps": 6090, "total_steps": 76960, "loss": 0.2628, "lr": 3.955951143451144e-05, "epoch": 1.5826403326403327, "percentage": 7.91, "elapsed_time": "0:08:43", "remaining_time": "1:41:35", "throughput": 1048.11, "total_tokens": 549016} {"current_steps": 6095, "total_steps": 76960, "loss": 0.3853, "lr": 3.959199584199584e-05, "epoch": 1.583939708939709, "percentage": 7.92, "elapsed_time": "0:08:44", "remaining_time": "1:41:35", "throughput": 1048.09, "total_tokens": 549448} {"current_steps": 6100, "total_steps": 76960, "loss": 0.2711, "lr": 3.962448024948025e-05, "epoch": 1.5852390852390852, "percentage": 7.93, "elapsed_time": "0:08:44", "remaining_time": "1:41:34", "throughput": 1048.17, "total_tokens": 549928} {"current_steps": 6105, "total_steps": 76960, "loss": 0.2834, "lr": 3.9656964656964654e-05, "epoch": 1.5865384615384617, "percentage": 7.93, "elapsed_time": "0:08:45", "remaining_time": "1:41:34", "throughput": 1048.25, "total_tokens": 550408} {"current_steps": 6110, "total_steps": 76960, "loss": 0.2721, "lr": 3.968944906444907e-05, "epoch": 1.5878378378378377, "percentage": 7.94, "elapsed_time": "0:08:45", "remaining_time": "1:41:33", "throughput": 1048.27, "total_tokens": 550856} {"current_steps": 6115, "total_steps": 76960, "loss": 0.2798, "lr": 3.9721933471933473e-05, "epoch": 1.5891372141372142, "percentage": 7.95, "elapsed_time": "0:08:45", "remaining_time": "1:41:32", "throughput": 1048.29, "total_tokens": 551304} {"current_steps": 6120, "total_steps": 76960, "loss": 0.2697, "lr": 3.975441787941788e-05, "epoch": 1.5904365904365905, "percentage": 7.95, "elapsed_time": "0:08:46", "remaining_time": "1:41:32", "throughput": 1048.34, "total_tokens": 551768} {"current_steps": 6125, "total_steps": 76960, "loss": 0.2599, "lr": 3.9786902286902286e-05, "epoch": 1.5917359667359667, "percentage": 7.96, "elapsed_time": "0:08:46", "remaining_time": "1:41:31", "throughput": 1048.35, "total_tokens": 552216} {"current_steps": 6130, "total_steps": 76960, "loss": 0.2794, "lr": 3.9819386694386696e-05, "epoch": 1.593035343035343, "percentage": 7.97, "elapsed_time": "0:08:47", "remaining_time": "1:41:31", "throughput": 1048.4, "total_tokens": 552680} {"current_steps": 6135, "total_steps": 76960, "loss": 0.2241, "lr": 3.9851871101871105e-05, "epoch": 1.5943347193347193, "percentage": 7.97, "elapsed_time": "0:08:47", "remaining_time": "1:41:30", "throughput": 1048.38, "total_tokens": 553112} {"current_steps": 6140, "total_steps": 76960, "loss": 0.1794, "lr": 3.988435550935551e-05, "epoch": 1.5956340956340958, "percentage": 7.98, "elapsed_time": "0:08:48", "remaining_time": "1:41:30", "throughput": 1048.34, "total_tokens": 553528} {"current_steps": 6145, "total_steps": 76960, "loss": 0.2787, "lr": 3.991683991683992e-05, "epoch": 1.5969334719334718, "percentage": 7.98, "elapsed_time": "0:08:48", "remaining_time": "1:41:29", "throughput": 1048.33, "total_tokens": 553960} {"current_steps": 6150, "total_steps": 76960, "loss": 0.251, "lr": 3.994932432432433e-05, "epoch": 1.5982328482328483, "percentage": 7.99, "elapsed_time": "0:08:48", "remaining_time": "1:41:28", "throughput": 1048.35, "total_tokens": 554408} {"current_steps": 6155, "total_steps": 76960, "loss": 0.2768, "lr": 3.998180873180874e-05, "epoch": 1.5995322245322245, "percentage": 8.0, "elapsed_time": "0:08:49", "remaining_time": "1:41:28", "throughput": 1048.37, "total_tokens": 554856} {"current_steps": 6160, "total_steps": 76960, "loss": 0.2538, "lr": 4.001429313929314e-05, "epoch": 1.6008316008316008, "percentage": 8.0, "elapsed_time": "0:08:49", "remaining_time": "1:41:27", "throughput": 1048.39, "total_tokens": 555304} {"current_steps": 6165, "total_steps": 76960, "loss": 0.2524, "lr": 4.004677754677755e-05, "epoch": 1.6021309771309773, "percentage": 8.01, "elapsed_time": "0:08:50", "remaining_time": "1:41:27", "throughput": 1048.5, "total_tokens": 555800} {"current_steps": 6170, "total_steps": 76960, "loss": 0.2173, "lr": 4.007926195426195e-05, "epoch": 1.6034303534303533, "percentage": 8.02, "elapsed_time": "0:08:50", "remaining_time": "1:41:26", "throughput": 1048.55, "total_tokens": 556264} {"current_steps": 6175, "total_steps": 76960, "loss": 0.3072, "lr": 4.011174636174637e-05, "epoch": 1.6047297297297298, "percentage": 8.02, "elapsed_time": "0:08:50", "remaining_time": "1:41:26", "throughput": 1048.51, "total_tokens": 556680} {"current_steps": 6180, "total_steps": 76960, "loss": 0.2583, "lr": 4.014423076923077e-05, "epoch": 1.6060291060291059, "percentage": 8.03, "elapsed_time": "0:08:51", "remaining_time": "1:41:25", "throughput": 1048.61, "total_tokens": 557176} {"current_steps": 6185, "total_steps": 76960, "loss": 0.1959, "lr": 4.017671517671518e-05, "epoch": 1.6073284823284824, "percentage": 8.04, "elapsed_time": "0:08:51", "remaining_time": "1:41:24", "throughput": 1048.72, "total_tokens": 557672} {"current_steps": 6190, "total_steps": 76960, "loss": 0.2515, "lr": 4.0209199584199584e-05, "epoch": 1.6086278586278586, "percentage": 8.04, "elapsed_time": "0:08:52", "remaining_time": "1:41:24", "throughput": 1048.77, "total_tokens": 558136} {"current_steps": 6195, "total_steps": 76960, "loss": 0.2582, "lr": 4.0241683991683994e-05, "epoch": 1.6099272349272349, "percentage": 8.05, "elapsed_time": "0:08:52", "remaining_time": "1:41:23", "throughput": 1048.76, "total_tokens": 558568} {"current_steps": 6200, "total_steps": 76960, "loss": 0.3152, "lr": 4.02741683991684e-05, "epoch": 1.6112266112266114, "percentage": 8.06, "elapsed_time": "0:08:53", "remaining_time": "1:41:23", "throughput": 1048.75, "total_tokens": 559000} {"current_steps": 6205, "total_steps": 76960, "loss": 0.2879, "lr": 4.0306652806652807e-05, "epoch": 1.6125259875259874, "percentage": 8.06, "elapsed_time": "0:08:53", "remaining_time": "1:41:22", "throughput": 1048.76, "total_tokens": 559448} {"current_steps": 6210, "total_steps": 76960, "loss": 0.2624, "lr": 4.0339137214137216e-05, "epoch": 1.613825363825364, "percentage": 8.07, "elapsed_time": "0:08:53", "remaining_time": "1:41:22", "throughput": 1048.84, "total_tokens": 559928} {"current_steps": 6215, "total_steps": 76960, "loss": 0.2488, "lr": 4.0371621621621626e-05, "epoch": 1.6151247401247402, "percentage": 8.08, "elapsed_time": "0:08:54", "remaining_time": "1:41:21", "throughput": 1048.83, "total_tokens": 560360} {"current_steps": 6220, "total_steps": 76960, "loss": 0.2236, "lr": 4.040410602910603e-05, "epoch": 1.6164241164241164, "percentage": 8.08, "elapsed_time": "0:08:54", "remaining_time": "1:41:21", "throughput": 1048.82, "total_tokens": 560792} {"current_steps": 6225, "total_steps": 76960, "loss": 0.2769, "lr": 4.043659043659044e-05, "epoch": 1.6177234927234927, "percentage": 8.09, "elapsed_time": "0:08:55", "remaining_time": "1:41:20", "throughput": 1048.83, "total_tokens": 561240} {"current_steps": 6230, "total_steps": 76960, "loss": 0.34, "lr": 4.046907484407484e-05, "epoch": 1.619022869022869, "percentage": 8.1, "elapsed_time": "0:08:55", "remaining_time": "1:41:19", "throughput": 1048.85, "total_tokens": 561688} {"current_steps": 6235, "total_steps": 76960, "loss": 0.2934, "lr": 4.050155925155925e-05, "epoch": 1.6203222453222454, "percentage": 8.1, "elapsed_time": "0:08:55", "remaining_time": "1:41:19", "throughput": 1048.84, "total_tokens": 562120} {"current_steps": 6240, "total_steps": 76960, "loss": 0.2094, "lr": 4.053404365904366e-05, "epoch": 1.6216216216216215, "percentage": 8.11, "elapsed_time": "0:08:56", "remaining_time": "1:41:18", "throughput": 1048.97, "total_tokens": 562632} {"current_steps": 6245, "total_steps": 76960, "loss": 0.2229, "lr": 4.056652806652807e-05, "epoch": 1.622920997920998, "percentage": 8.11, "elapsed_time": "0:08:56", "remaining_time": "1:41:18", "throughput": 1048.99, "total_tokens": 563080} {"current_steps": 6250, "total_steps": 76960, "loss": 0.2181, "lr": 4.059901247401248e-05, "epoch": 1.6242203742203742, "percentage": 8.12, "elapsed_time": "0:08:57", "remaining_time": "1:41:17", "throughput": 1048.95, "total_tokens": 563496} {"current_steps": 6255, "total_steps": 76960, "loss": 0.1637, "lr": 4.063149688149688e-05, "epoch": 1.6255197505197505, "percentage": 8.13, "elapsed_time": "0:08:57", "remaining_time": "1:41:17", "throughput": 1048.97, "total_tokens": 563944} {"current_steps": 6260, "total_steps": 76960, "loss": 0.2584, "lr": 4.066398128898129e-05, "epoch": 1.6268191268191268, "percentage": 8.13, "elapsed_time": "0:08:58", "remaining_time": "1:41:16", "throughput": 1048.99, "total_tokens": 564392} {"current_steps": 6265, "total_steps": 76960, "loss": 0.3802, "lr": 4.0696465696465695e-05, "epoch": 1.628118503118503, "percentage": 8.14, "elapsed_time": "0:08:58", "remaining_time": "1:41:15", "throughput": 1049.0, "total_tokens": 564840} {"current_steps": 6270, "total_steps": 76960, "loss": 0.289, "lr": 4.0728950103950105e-05, "epoch": 1.6294178794178795, "percentage": 8.15, "elapsed_time": "0:08:58", "remaining_time": "1:41:15", "throughput": 1049.08, "total_tokens": 565320} {"current_steps": 6275, "total_steps": 76960, "loss": 0.2228, "lr": 4.0761434511434515e-05, "epoch": 1.6307172557172556, "percentage": 8.15, "elapsed_time": "0:08:59", "remaining_time": "1:41:14", "throughput": 1049.13, "total_tokens": 565784} {"current_steps": 6280, "total_steps": 76960, "loss": 0.2924, "lr": 4.0793918918918924e-05, "epoch": 1.632016632016632, "percentage": 8.16, "elapsed_time": "0:08:59", "remaining_time": "1:41:14", "throughput": 1049.11, "total_tokens": 566216} {"current_steps": 6285, "total_steps": 76960, "loss": 0.2818, "lr": 4.082640332640333e-05, "epoch": 1.6333160083160083, "percentage": 8.17, "elapsed_time": "0:09:00", "remaining_time": "1:41:13", "throughput": 1049.13, "total_tokens": 566664} {"current_steps": 6290, "total_steps": 76960, "loss": 0.2255, "lr": 4.085888773388774e-05, "epoch": 1.6346153846153846, "percentage": 8.17, "elapsed_time": "0:09:00", "remaining_time": "1:41:13", "throughput": 1049.08, "total_tokens": 567080} {"current_steps": 6295, "total_steps": 76960, "loss": 0.1989, "lr": 4.089137214137214e-05, "epoch": 1.635914760914761, "percentage": 8.18, "elapsed_time": "0:09:00", "remaining_time": "1:41:12", "throughput": 1049.03, "total_tokens": 567496} {"current_steps": 6300, "total_steps": 76960, "loss": 0.2694, "lr": 4.092385654885655e-05, "epoch": 1.637214137214137, "percentage": 8.19, "elapsed_time": "0:09:01", "remaining_time": "1:41:12", "throughput": 1048.99, "total_tokens": 567912} {"current_steps": 6305, "total_steps": 76960, "loss": 0.303, "lr": 4.095634095634096e-05, "epoch": 1.6385135135135136, "percentage": 8.19, "elapsed_time": "0:09:01", "remaining_time": "1:41:11", "throughput": 1049.0, "total_tokens": 568360} {"current_steps": 6310, "total_steps": 76960, "loss": 0.3098, "lr": 4.098882536382537e-05, "epoch": 1.6398128898128899, "percentage": 8.2, "elapsed_time": "0:09:02", "remaining_time": "1:41:11", "throughput": 1048.99, "total_tokens": 568792} {"current_steps": 6315, "total_steps": 76960, "loss": 0.2614, "lr": 4.102130977130977e-05, "epoch": 1.6411122661122661, "percentage": 8.21, "elapsed_time": "0:09:02", "remaining_time": "1:41:10", "throughput": 1048.95, "total_tokens": 569208} {"current_steps": 6320, "total_steps": 76960, "loss": 0.2587, "lr": 4.105379417879418e-05, "epoch": 1.6424116424116424, "percentage": 8.21, "elapsed_time": "0:09:03", "remaining_time": "1:41:09", "throughput": 1048.97, "total_tokens": 569656} {"current_steps": 6325, "total_steps": 76960, "loss": 0.2597, "lr": 4.1086278586278584e-05, "epoch": 1.6437110187110187, "percentage": 8.22, "elapsed_time": "0:09:03", "remaining_time": "1:41:09", "throughput": 1048.95, "total_tokens": 570088} {"current_steps": 6330, "total_steps": 76960, "loss": 0.2461, "lr": 4.1118762993762994e-05, "epoch": 1.6450103950103951, "percentage": 8.23, "elapsed_time": "0:09:03", "remaining_time": "1:41:08", "throughput": 1048.97, "total_tokens": 570536} {"current_steps": 6335, "total_steps": 76960, "loss": 0.1996, "lr": 4.11512474012474e-05, "epoch": 1.6463097713097712, "percentage": 8.23, "elapsed_time": "0:09:04", "remaining_time": "1:41:08", "throughput": 1049.02, "total_tokens": 571000} {"current_steps": 6340, "total_steps": 76960, "loss": 0.2039, "lr": 4.118373180873181e-05, "epoch": 1.6476091476091477, "percentage": 8.24, "elapsed_time": "0:09:04", "remaining_time": "1:41:07", "throughput": 1049.13, "total_tokens": 571496} {"current_steps": 6345, "total_steps": 76960, "loss": 0.1572, "lr": 4.1216216216216216e-05, "epoch": 1.648908523908524, "percentage": 8.24, "elapsed_time": "0:09:05", "remaining_time": "1:41:07", "throughput": 1049.11, "total_tokens": 571928} {"current_steps": 6350, "total_steps": 76960, "loss": 0.1628, "lr": 4.1248700623700626e-05, "epoch": 1.6502079002079002, "percentage": 8.25, "elapsed_time": "0:09:05", "remaining_time": "1:41:06", "throughput": 1049.19, "total_tokens": 572408} {"current_steps": 6355, "total_steps": 76960, "loss": 0.1493, "lr": 4.1281185031185035e-05, "epoch": 1.6515072765072765, "percentage": 8.26, "elapsed_time": "0:09:05", "remaining_time": "1:41:06", "throughput": 1049.18, "total_tokens": 572840} {"current_steps": 6360, "total_steps": 76960, "loss": 0.441, "lr": 4.131366943866944e-05, "epoch": 1.6528066528066527, "percentage": 8.26, "elapsed_time": "0:09:06", "remaining_time": "1:41:05", "throughput": 1049.23, "total_tokens": 573304} {"current_steps": 6365, "total_steps": 76960, "loss": 0.3477, "lr": 4.134615384615385e-05, "epoch": 1.6541060291060292, "percentage": 8.27, "elapsed_time": "0:09:06", "remaining_time": "1:41:04", "throughput": 1049.22, "total_tokens": 573736} {"current_steps": 6370, "total_steps": 76960, "loss": 0.3636, "lr": 4.137863825363826e-05, "epoch": 1.6554054054054053, "percentage": 8.28, "elapsed_time": "0:09:07", "remaining_time": "1:41:04", "throughput": 1049.17, "total_tokens": 574152} {"current_steps": 6375, "total_steps": 76960, "loss": 0.3726, "lr": 4.141112266112267e-05, "epoch": 1.6567047817047817, "percentage": 8.28, "elapsed_time": "0:09:07", "remaining_time": "1:41:03", "throughput": 1049.22, "total_tokens": 574616} {"current_steps": 6380, "total_steps": 76960, "loss": 0.2792, "lr": 4.144360706860707e-05, "epoch": 1.658004158004158, "percentage": 8.29, "elapsed_time": "0:09:08", "remaining_time": "1:41:03", "throughput": 1049.23, "total_tokens": 575064} {"current_steps": 6385, "total_steps": 76960, "loss": 0.284, "lr": 4.147609147609148e-05, "epoch": 1.6593035343035343, "percentage": 8.3, "elapsed_time": "0:09:08", "remaining_time": "1:41:02", "throughput": 1049.24, "total_tokens": 575512} {"current_steps": 6390, "total_steps": 76960, "loss": 0.5268, "lr": 4.150857588357588e-05, "epoch": 1.6606029106029108, "percentage": 8.3, "elapsed_time": "0:09:08", "remaining_time": "1:41:02", "throughput": 1049.26, "total_tokens": 575960} {"current_steps": 6395, "total_steps": 76960, "loss": 0.5131, "lr": 4.154106029106029e-05, "epoch": 1.6619022869022868, "percentage": 8.31, "elapsed_time": "0:09:09", "remaining_time": "1:41:01", "throughput": 1049.25, "total_tokens": 576392} {"current_steps": 6400, "total_steps": 76960, "loss": 0.297, "lr": 4.15735446985447e-05, "epoch": 1.6632016632016633, "percentage": 8.32, "elapsed_time": "0:09:09", "remaining_time": "1:41:01", "throughput": 1049.26, "total_tokens": 576840} {"current_steps": 6405, "total_steps": 76960, "loss": 0.2625, "lr": 4.160602910602911e-05, "epoch": 1.6645010395010393, "percentage": 8.32, "elapsed_time": "0:09:10", "remaining_time": "1:41:00", "throughput": 1049.34, "total_tokens": 577320} {"current_steps": 6410, "total_steps": 76960, "loss": 0.3858, "lr": 4.1638513513513514e-05, "epoch": 1.6658004158004158, "percentage": 8.33, "elapsed_time": "0:09:10", "remaining_time": "1:40:59", "throughput": 1049.35, "total_tokens": 577768} {"current_steps": 6415, "total_steps": 76960, "loss": 0.665, "lr": 4.1670997920997924e-05, "epoch": 1.667099792099792, "percentage": 8.34, "elapsed_time": "0:09:11", "remaining_time": "1:40:59", "throughput": 1049.4, "total_tokens": 578232} {"current_steps": 6420, "total_steps": 76960, "loss": 0.4043, "lr": 4.170348232848233e-05, "epoch": 1.6683991683991684, "percentage": 8.34, "elapsed_time": "0:09:11", "remaining_time": "1:40:58", "throughput": 1049.39, "total_tokens": 578664} {"current_steps": 6425, "total_steps": 76960, "loss": 0.2675, "lr": 4.1735966735966736e-05, "epoch": 1.6696985446985448, "percentage": 8.35, "elapsed_time": "0:09:11", "remaining_time": "1:40:58", "throughput": 1049.5, "total_tokens": 579160} {"current_steps": 6430, "total_steps": 76960, "loss": 0.2689, "lr": 4.176845114345114e-05, "epoch": 1.6709979209979209, "percentage": 8.35, "elapsed_time": "0:09:12", "remaining_time": "1:40:57", "throughput": 1049.46, "total_tokens": 579576} {"current_steps": 6435, "total_steps": 76960, "loss": 0.2325, "lr": 4.1800935550935556e-05, "epoch": 1.6722972972972974, "percentage": 8.36, "elapsed_time": "0:09:12", "remaining_time": "1:40:57", "throughput": 1049.48, "total_tokens": 580024} {"current_steps": 6440, "total_steps": 76960, "loss": 0.2141, "lr": 4.183341995841996e-05, "epoch": 1.6735966735966736, "percentage": 8.37, "elapsed_time": "0:09:13", "remaining_time": "1:40:56", "throughput": 1049.56, "total_tokens": 580504} {"current_steps": 6445, "total_steps": 76960, "loss": 0.2221, "lr": 4.186590436590437e-05, "epoch": 1.67489604989605, "percentage": 8.37, "elapsed_time": "0:09:13", "remaining_time": "1:40:56", "throughput": 1049.54, "total_tokens": 580936} {"current_steps": 6450, "total_steps": 76960, "loss": 0.3093, "lr": 4.189838877338878e-05, "epoch": 1.6761954261954262, "percentage": 8.38, "elapsed_time": "0:09:13", "remaining_time": "1:40:55", "throughput": 1049.56, "total_tokens": 581384} {"current_steps": 6455, "total_steps": 76960, "loss": 0.2269, "lr": 4.193087318087318e-05, "epoch": 1.6774948024948024, "percentage": 8.39, "elapsed_time": "0:09:14", "remaining_time": "1:40:54", "throughput": 1049.54, "total_tokens": 581816} {"current_steps": 6460, "total_steps": 76960, "loss": 0.2137, "lr": 4.196335758835759e-05, "epoch": 1.678794178794179, "percentage": 8.39, "elapsed_time": "0:09:14", "remaining_time": "1:40:54", "throughput": 1049.59, "total_tokens": 582280} {"current_steps": 6465, "total_steps": 76960, "loss": 0.3475, "lr": 4.1995841995842e-05, "epoch": 1.680093555093555, "percentage": 8.4, "elapsed_time": "0:09:15", "remaining_time": "1:40:53", "throughput": 1049.55, "total_tokens": 582696} {"current_steps": 6470, "total_steps": 76960, "loss": 0.1379, "lr": 4.202832640332641e-05, "epoch": 1.6813929313929314, "percentage": 8.41, "elapsed_time": "0:09:15", "remaining_time": "1:40:53", "throughput": 1049.56, "total_tokens": 583144} {"current_steps": 6475, "total_steps": 76960, "loss": 0.3228, "lr": 4.206081081081081e-05, "epoch": 1.6826923076923077, "percentage": 8.41, "elapsed_time": "0:09:16", "remaining_time": "1:40:52", "throughput": 1049.61, "total_tokens": 583608} {"current_steps": 6480, "total_steps": 76960, "loss": 0.2558, "lr": 4.209329521829522e-05, "epoch": 1.683991683991684, "percentage": 8.42, "elapsed_time": "0:09:16", "remaining_time": "1:40:52", "throughput": 1049.68, "total_tokens": 584088} {"current_steps": 6485, "total_steps": 76960, "loss": 0.2461, "lr": 4.2125779625779625e-05, "epoch": 1.6852910602910602, "percentage": 8.43, "elapsed_time": "0:09:16", "remaining_time": "1:40:51", "throughput": 1049.76, "total_tokens": 584568} {"current_steps": 6490, "total_steps": 76960, "loss": 0.325, "lr": 4.2158264033264035e-05, "epoch": 1.6865904365904365, "percentage": 8.43, "elapsed_time": "0:09:17", "remaining_time": "1:40:51", "throughput": 1049.81, "total_tokens": 585032} {"current_steps": 6495, "total_steps": 76960, "loss": 0.267, "lr": 4.2190748440748445e-05, "epoch": 1.687889812889813, "percentage": 8.44, "elapsed_time": "0:09:17", "remaining_time": "1:40:50", "throughput": 1049.74, "total_tokens": 585432} {"current_steps": 6500, "total_steps": 76960, "loss": 0.2656, "lr": 4.2223232848232854e-05, "epoch": 1.689189189189189, "percentage": 8.45, "elapsed_time": "0:09:18", "remaining_time": "1:40:49", "throughput": 1049.73, "total_tokens": 585864} {"current_steps": 6505, "total_steps": 76960, "loss": 0.2717, "lr": 4.225571725571726e-05, "epoch": 1.6904885654885655, "percentage": 8.45, "elapsed_time": "0:09:18", "remaining_time": "1:40:49", "throughput": 1049.75, "total_tokens": 586312} {"current_steps": 6510, "total_steps": 76960, "loss": 0.2291, "lr": 4.228820166320167e-05, "epoch": 1.6917879417879418, "percentage": 8.46, "elapsed_time": "0:09:18", "remaining_time": "1:40:48", "throughput": 1049.8, "total_tokens": 586776} {"current_steps": 6515, "total_steps": 76960, "loss": 0.3184, "lr": 4.232068607068607e-05, "epoch": 1.693087318087318, "percentage": 8.47, "elapsed_time": "0:09:19", "remaining_time": "1:40:48", "throughput": 1049.85, "total_tokens": 587240} {"current_steps": 6520, "total_steps": 76960, "loss": 0.2161, "lr": 4.235317047817048e-05, "epoch": 1.6943866943866945, "percentage": 8.47, "elapsed_time": "0:09:19", "remaining_time": "1:40:47", "throughput": 1049.87, "total_tokens": 587688} {"current_steps": 6525, "total_steps": 76960, "loss": 0.2783, "lr": 4.238565488565488e-05, "epoch": 1.6956860706860706, "percentage": 8.48, "elapsed_time": "0:09:20", "remaining_time": "1:40:47", "throughput": 1049.83, "total_tokens": 588104} {"current_steps": 6530, "total_steps": 76960, "loss": 0.3159, "lr": 4.24181392931393e-05, "epoch": 1.696985446985447, "percentage": 8.48, "elapsed_time": "0:09:20", "remaining_time": "1:40:46", "throughput": 1049.9, "total_tokens": 588584} {"current_steps": 6535, "total_steps": 76960, "loss": 0.2799, "lr": 4.24506237006237e-05, "epoch": 1.6982848232848233, "percentage": 8.49, "elapsed_time": "0:09:21", "remaining_time": "1:40:45", "throughput": 1049.92, "total_tokens": 589032} {"current_steps": 6540, "total_steps": 76960, "loss": 0.2831, "lr": 4.248310810810811e-05, "epoch": 1.6995841995841996, "percentage": 8.5, "elapsed_time": "0:09:21", "remaining_time": "1:40:45", "throughput": 1049.88, "total_tokens": 589448} {"current_steps": 6545, "total_steps": 76960, "loss": 0.2408, "lr": 4.2515592515592514e-05, "epoch": 1.7008835758835759, "percentage": 8.5, "elapsed_time": "0:09:21", "remaining_time": "1:40:44", "throughput": 1049.93, "total_tokens": 589912} {"current_steps": 6550, "total_steps": 76960, "loss": 0.3145, "lr": 4.2548076923076924e-05, "epoch": 1.7021829521829521, "percentage": 8.51, "elapsed_time": "0:09:22", "remaining_time": "1:40:44", "throughput": 1049.97, "total_tokens": 590376} {"current_steps": 6555, "total_steps": 76960, "loss": 0.242, "lr": 4.258056133056133e-05, "epoch": 1.7034823284823286, "percentage": 8.52, "elapsed_time": "0:09:22", "remaining_time": "1:40:43", "throughput": 1049.96, "total_tokens": 590824} {"current_steps": 6560, "total_steps": 76960, "loss": 0.1913, "lr": 4.261304573804574e-05, "epoch": 1.7047817047817047, "percentage": 8.52, "elapsed_time": "0:09:23", "remaining_time": "1:40:43", "throughput": 1049.97, "total_tokens": 591272} {"current_steps": 6565, "total_steps": 76960, "loss": 0.2301, "lr": 4.264553014553015e-05, "epoch": 1.7060810810810811, "percentage": 8.53, "elapsed_time": "0:09:23", "remaining_time": "1:40:42", "throughput": 1050.03, "total_tokens": 591752} {"current_steps": 6570, "total_steps": 76960, "loss": 0.1563, "lr": 4.2678014553014555e-05, "epoch": 1.7073804573804574, "percentage": 8.54, "elapsed_time": "0:09:23", "remaining_time": "1:40:42", "throughput": 1049.99, "total_tokens": 592168} {"current_steps": 6575, "total_steps": 76960, "loss": 0.1394, "lr": 4.2710498960498965e-05, "epoch": 1.7086798336798337, "percentage": 8.54, "elapsed_time": "0:09:24", "remaining_time": "1:40:41", "throughput": 1050.06, "total_tokens": 592648} {"current_steps": 6580, "total_steps": 76960, "loss": 0.2536, "lr": 4.274298336798337e-05, "epoch": 1.70997920997921, "percentage": 8.55, "elapsed_time": "0:09:24", "remaining_time": "1:40:41", "throughput": 1050.08, "total_tokens": 593096} {"current_steps": 6585, "total_steps": 76960, "loss": 0.2829, "lr": 4.277546777546778e-05, "epoch": 1.7112785862785862, "percentage": 8.56, "elapsed_time": "0:09:25", "remaining_time": "1:40:40", "throughput": 1050.01, "total_tokens": 593496} {"current_steps": 6590, "total_steps": 76960, "loss": 0.3012, "lr": 4.280795218295218e-05, "epoch": 1.7125779625779627, "percentage": 8.56, "elapsed_time": "0:09:25", "remaining_time": "1:40:40", "throughput": 1049.99, "total_tokens": 593928} {"current_steps": 6595, "total_steps": 76960, "loss": 0.2869, "lr": 4.28404365904366e-05, "epoch": 1.7138773388773387, "percentage": 8.57, "elapsed_time": "0:09:26", "remaining_time": "1:40:39", "throughput": 1049.98, "total_tokens": 594360} {"current_steps": 6600, "total_steps": 76960, "loss": 0.2642, "lr": 4.2872920997921e-05, "epoch": 1.7151767151767152, "percentage": 8.58, "elapsed_time": "0:09:26", "remaining_time": "1:40:39", "throughput": 1049.94, "total_tokens": 594776} {"current_steps": 6605, "total_steps": 76960, "loss": 0.2519, "lr": 4.290540540540541e-05, "epoch": 1.7164760914760915, "percentage": 8.58, "elapsed_time": "0:09:26", "remaining_time": "1:40:38", "throughput": 1049.9, "total_tokens": 595192} {"current_steps": 6610, "total_steps": 76960, "loss": 0.2957, "lr": 4.293788981288981e-05, "epoch": 1.7177754677754677, "percentage": 8.59, "elapsed_time": "0:09:27", "remaining_time": "1:40:37", "throughput": 1049.89, "total_tokens": 595624} {"current_steps": 6615, "total_steps": 76960, "loss": 0.2801, "lr": 4.297037422037422e-05, "epoch": 1.7190748440748442, "percentage": 8.6, "elapsed_time": "0:09:27", "remaining_time": "1:40:37", "throughput": 1049.87, "total_tokens": 596056} {"current_steps": 6620, "total_steps": 76960, "loss": 0.2564, "lr": 4.3002858627858625e-05, "epoch": 1.7203742203742203, "percentage": 8.6, "elapsed_time": "0:09:28", "remaining_time": "1:40:36", "throughput": 1049.92, "total_tokens": 596520} {"current_steps": 6625, "total_steps": 76960, "loss": 0.2176, "lr": 4.303534303534304e-05, "epoch": 1.7216735966735968, "percentage": 8.61, "elapsed_time": "0:09:28", "remaining_time": "1:40:36", "throughput": 1049.94, "total_tokens": 596968} {"current_steps": 6630, "total_steps": 76960, "loss": 0.2715, "lr": 4.3067827442827444e-05, "epoch": 1.722972972972973, "percentage": 8.61, "elapsed_time": "0:09:28", "remaining_time": "1:40:35", "throughput": 1049.98, "total_tokens": 597432} {"current_steps": 6635, "total_steps": 76960, "loss": 0.266, "lr": 4.3100311850311854e-05, "epoch": 1.7242723492723493, "percentage": 8.62, "elapsed_time": "0:09:29", "remaining_time": "1:40:35", "throughput": 1050.03, "total_tokens": 597896} {"current_steps": 6640, "total_steps": 76960, "loss": 0.254, "lr": 4.313279625779626e-05, "epoch": 1.7255717255717256, "percentage": 8.63, "elapsed_time": "0:09:29", "remaining_time": "1:40:34", "throughput": 1050.04, "total_tokens": 598344} {"current_steps": 6645, "total_steps": 76960, "loss": 0.3156, "lr": 4.3165280665280666e-05, "epoch": 1.7268711018711018, "percentage": 8.63, "elapsed_time": "0:09:30", "remaining_time": "1:40:34", "throughput": 1050.06, "total_tokens": 598792} {"current_steps": 6650, "total_steps": 76960, "loss": 0.243, "lr": 4.3197765072765076e-05, "epoch": 1.7281704781704783, "percentage": 8.64, "elapsed_time": "0:09:30", "remaining_time": "1:40:33", "throughput": 1050.01, "total_tokens": 599208} {"current_steps": 6655, "total_steps": 76960, "loss": 0.2725, "lr": 4.3230249480249486e-05, "epoch": 1.7294698544698544, "percentage": 8.65, "elapsed_time": "0:09:31", "remaining_time": "1:40:33", "throughput": 1050.06, "total_tokens": 599672} {"current_steps": 6660, "total_steps": 76960, "loss": 0.2588, "lr": 4.326273388773389e-05, "epoch": 1.7307692307692308, "percentage": 8.65, "elapsed_time": "0:09:31", "remaining_time": "1:40:32", "throughput": 1050.08, "total_tokens": 600120} {"current_steps": 6665, "total_steps": 76960, "loss": 0.2464, "lr": 4.32952182952183e-05, "epoch": 1.732068607068607, "percentage": 8.66, "elapsed_time": "0:09:31", "remaining_time": "1:40:31", "throughput": 1050.09, "total_tokens": 600568} {"current_steps": 6670, "total_steps": 76960, "loss": 0.2872, "lr": 4.332770270270271e-05, "epoch": 1.7333679833679834, "percentage": 8.67, "elapsed_time": "0:09:32", "remaining_time": "1:40:31", "throughput": 1050.11, "total_tokens": 601016} {"current_steps": 6675, "total_steps": 76960, "loss": 0.2177, "lr": 4.336018711018711e-05, "epoch": 1.7346673596673596, "percentage": 8.67, "elapsed_time": "0:09:32", "remaining_time": "1:40:30", "throughput": 1050.18, "total_tokens": 601496} {"current_steps": 6680, "total_steps": 76960, "loss": 0.16, "lr": 4.339267151767152e-05, "epoch": 1.735966735966736, "percentage": 8.68, "elapsed_time": "0:09:33", "remaining_time": "1:40:30", "throughput": 1050.17, "total_tokens": 601928} {"current_steps": 6685, "total_steps": 76960, "loss": 0.2566, "lr": 4.342515592515592e-05, "epoch": 1.7372661122661124, "percentage": 8.69, "elapsed_time": "0:09:33", "remaining_time": "1:40:29", "throughput": 1050.19, "total_tokens": 602376} {"current_steps": 6690, "total_steps": 76960, "loss": 0.2159, "lr": 4.345764033264034e-05, "epoch": 1.7385654885654884, "percentage": 8.69, "elapsed_time": "0:09:34", "remaining_time": "1:40:29", "throughput": 1050.2, "total_tokens": 602824} {"current_steps": 6695, "total_steps": 76960, "loss": 0.2547, "lr": 4.349012474012474e-05, "epoch": 1.739864864864865, "percentage": 8.7, "elapsed_time": "0:09:34", "remaining_time": "1:40:28", "throughput": 1050.19, "total_tokens": 603256} {"current_steps": 6700, "total_steps": 76960, "loss": 0.313, "lr": 4.352260914760915e-05, "epoch": 1.7411642411642412, "percentage": 8.71, "elapsed_time": "0:09:34", "remaining_time": "1:40:28", "throughput": 1050.24, "total_tokens": 603720} {"current_steps": 6705, "total_steps": 76960, "loss": 0.2159, "lr": 4.3555093555093555e-05, "epoch": 1.7424636174636174, "percentage": 8.71, "elapsed_time": "0:09:35", "remaining_time": "1:40:27", "throughput": 1050.25, "total_tokens": 604168} {"current_steps": 6710, "total_steps": 76960, "loss": 0.1784, "lr": 4.3587577962577965e-05, "epoch": 1.743762993762994, "percentage": 8.72, "elapsed_time": "0:09:35", "remaining_time": "1:40:27", "throughput": 1050.24, "total_tokens": 604600} {"current_steps": 6715, "total_steps": 76960, "loss": 0.1672, "lr": 4.362006237006237e-05, "epoch": 1.74506237006237, "percentage": 8.73, "elapsed_time": "0:09:36", "remaining_time": "1:40:26", "throughput": 1050.26, "total_tokens": 605048} {"current_steps": 6720, "total_steps": 76960, "loss": 0.3436, "lr": 4.3652546777546784e-05, "epoch": 1.7463617463617465, "percentage": 8.73, "elapsed_time": "0:09:36", "remaining_time": "1:40:25", "throughput": 1050.3, "total_tokens": 605512} {"current_steps": 6725, "total_steps": 76960, "loss": 0.1596, "lr": 4.368503118503119e-05, "epoch": 1.7476611226611225, "percentage": 8.74, "elapsed_time": "0:09:36", "remaining_time": "1:40:25", "throughput": 1050.37, "total_tokens": 605992} {"current_steps": 6730, "total_steps": 76960, "loss": 0.2122, "lr": 4.37175155925156e-05, "epoch": 1.748960498960499, "percentage": 8.74, "elapsed_time": "0:09:37", "remaining_time": "1:40:24", "throughput": 1050.33, "total_tokens": 606408} {"current_steps": 6735, "total_steps": 76960, "loss": 0.2976, "lr": 4.375e-05, "epoch": 1.7502598752598753, "percentage": 8.75, "elapsed_time": "0:09:37", "remaining_time": "1:40:24", "throughput": 1050.4, "total_tokens": 606888} {"current_steps": 6740, "total_steps": 76960, "loss": 0.2298, "lr": 4.378248440748441e-05, "epoch": 1.7515592515592515, "percentage": 8.76, "elapsed_time": "0:09:38", "remaining_time": "1:40:23", "throughput": 1050.39, "total_tokens": 607320} {"current_steps": 6745, "total_steps": 76960, "loss": 0.1715, "lr": 4.381496881496881e-05, "epoch": 1.752858627858628, "percentage": 8.76, "elapsed_time": "0:09:38", "remaining_time": "1:40:23", "throughput": 1050.38, "total_tokens": 607752} {"current_steps": 6750, "total_steps": 76960, "loss": 0.2174, "lr": 4.384745322245322e-05, "epoch": 1.754158004158004, "percentage": 8.77, "elapsed_time": "0:09:39", "remaining_time": "1:40:22", "throughput": 1050.34, "total_tokens": 608168} {"current_steps": 6755, "total_steps": 76960, "loss": 0.2897, "lr": 4.387993762993763e-05, "epoch": 1.7554573804573805, "percentage": 8.78, "elapsed_time": "0:09:39", "remaining_time": "1:40:22", "throughput": 1050.33, "total_tokens": 608600} {"current_steps": 6760, "total_steps": 76960, "loss": 0.2663, "lr": 4.391242203742204e-05, "epoch": 1.7567567567567568, "percentage": 8.78, "elapsed_time": "0:09:39", "remaining_time": "1:40:21", "throughput": 1050.38, "total_tokens": 609064} {"current_steps": 6765, "total_steps": 76960, "loss": 0.3516, "lr": 4.394490644490645e-05, "epoch": 1.758056133056133, "percentage": 8.79, "elapsed_time": "0:09:40", "remaining_time": "1:40:21", "throughput": 1050.37, "total_tokens": 609496} {"current_steps": 6770, "total_steps": 76960, "loss": 0.2558, "lr": 4.3977390852390854e-05, "epoch": 1.7593555093555093, "percentage": 8.8, "elapsed_time": "0:09:40", "remaining_time": "1:40:20", "throughput": 1050.38, "total_tokens": 609944} {"current_steps": 6775, "total_steps": 76960, "loss": 0.2498, "lr": 4.400987525987526e-05, "epoch": 1.7606548856548856, "percentage": 8.8, "elapsed_time": "0:09:41", "remaining_time": "1:40:19", "throughput": 1050.45, "total_tokens": 610424} {"current_steps": 6780, "total_steps": 76960, "loss": 0.3431, "lr": 4.4042359667359666e-05, "epoch": 1.761954261954262, "percentage": 8.81, "elapsed_time": "0:09:41", "remaining_time": "1:40:19", "throughput": 1050.5, "total_tokens": 610888} {"current_steps": 6785, "total_steps": 76960, "loss": 0.2829, "lr": 4.407484407484408e-05, "epoch": 1.7632536382536381, "percentage": 8.82, "elapsed_time": "0:09:41", "remaining_time": "1:40:18", "throughput": 1050.46, "total_tokens": 611304} {"current_steps": 6790, "total_steps": 76960, "loss": 0.2072, "lr": 4.4107328482328485e-05, "epoch": 1.7645530145530146, "percentage": 8.82, "elapsed_time": "0:09:42", "remaining_time": "1:40:18", "throughput": 1050.44, "total_tokens": 611736} {"current_steps": 6795, "total_steps": 76960, "loss": 0.2461, "lr": 4.4139812889812895e-05, "epoch": 1.7658523908523909, "percentage": 8.83, "elapsed_time": "0:09:42", "remaining_time": "1:40:17", "throughput": 1050.49, "total_tokens": 612200} {"current_steps": 6800, "total_steps": 76960, "loss": 0.261, "lr": 4.41722972972973e-05, "epoch": 1.7671517671517671, "percentage": 8.84, "elapsed_time": "0:09:43", "remaining_time": "1:40:17", "throughput": 1050.5, "total_tokens": 612648} {"current_steps": 6805, "total_steps": 76960, "loss": 0.3425, "lr": 4.420478170478171e-05, "epoch": 1.7684511434511434, "percentage": 8.84, "elapsed_time": "0:09:43", "remaining_time": "1:40:16", "throughput": 1050.48, "total_tokens": 613080} {"current_steps": 6810, "total_steps": 76960, "loss": 0.1757, "lr": 4.423726611226611e-05, "epoch": 1.7697505197505197, "percentage": 8.85, "elapsed_time": "0:09:44", "remaining_time": "1:40:16", "throughput": 1050.41, "total_tokens": 613480} {"current_steps": 6815, "total_steps": 76960, "loss": 0.2254, "lr": 4.426975051975052e-05, "epoch": 1.7710498960498962, "percentage": 8.86, "elapsed_time": "0:09:44", "remaining_time": "1:40:15", "throughput": 1050.4, "total_tokens": 613912} {"current_steps": 6820, "total_steps": 76960, "loss": 0.1624, "lr": 4.430223492723493e-05, "epoch": 1.7723492723492722, "percentage": 8.86, "elapsed_time": "0:09:44", "remaining_time": "1:40:15", "throughput": 1050.39, "total_tokens": 614344} {"current_steps": 6825, "total_steps": 76960, "loss": 0.1704, "lr": 4.433471933471934e-05, "epoch": 1.7736486486486487, "percentage": 8.87, "elapsed_time": "0:09:45", "remaining_time": "1:40:14", "throughput": 1050.43, "total_tokens": 614808} {"current_steps": 6830, "total_steps": 76960, "loss": 0.2207, "lr": 4.436720374220374e-05, "epoch": 1.774948024948025, "percentage": 8.87, "elapsed_time": "0:09:45", "remaining_time": "1:40:14", "throughput": 1050.36, "total_tokens": 615208} {"current_steps": 6835, "total_steps": 76960, "loss": 0.3016, "lr": 4.439968814968815e-05, "epoch": 1.7762474012474012, "percentage": 8.88, "elapsed_time": "0:09:46", "remaining_time": "1:40:13", "throughput": 1050.37, "total_tokens": 615656} {"current_steps": 6840, "total_steps": 76960, "loss": 0.2815, "lr": 4.4432172557172555e-05, "epoch": 1.7775467775467777, "percentage": 8.89, "elapsed_time": "0:09:46", "remaining_time": "1:40:12", "throughput": 1050.36, "total_tokens": 616088} {"current_steps": 6845, "total_steps": 76960, "loss": 0.3066, "lr": 4.4464656964656965e-05, "epoch": 1.7788461538461537, "percentage": 8.89, "elapsed_time": "0:09:46", "remaining_time": "1:40:12", "throughput": 1050.35, "total_tokens": 616520} {"current_steps": 6850, "total_steps": 76960, "loss": 0.1796, "lr": 4.4497141372141374e-05, "epoch": 1.7801455301455302, "percentage": 8.9, "elapsed_time": "0:09:47", "remaining_time": "1:40:11", "throughput": 1050.37, "total_tokens": 616968} {"current_steps": 6855, "total_steps": 76960, "loss": 0.307, "lr": 4.4529625779625784e-05, "epoch": 1.7814449064449065, "percentage": 8.91, "elapsed_time": "0:09:47", "remaining_time": "1:40:11", "throughput": 1050.41, "total_tokens": 617432} {"current_steps": 6860, "total_steps": 76960, "loss": 0.325, "lr": 4.456211018711019e-05, "epoch": 1.7827442827442828, "percentage": 8.91, "elapsed_time": "0:09:48", "remaining_time": "1:40:10", "throughput": 1050.42, "total_tokens": 617880} {"current_steps": 6865, "total_steps": 76960, "loss": 0.2848, "lr": 4.4594594594594596e-05, "epoch": 1.784043659043659, "percentage": 8.92, "elapsed_time": "0:09:48", "remaining_time": "1:40:10", "throughput": 1050.55, "total_tokens": 618392} {"current_steps": 6870, "total_steps": 76960, "loss": 0.2816, "lr": 4.4627079002079006e-05, "epoch": 1.7853430353430353, "percentage": 8.93, "elapsed_time": "0:09:49", "remaining_time": "1:40:09", "throughput": 1050.59, "total_tokens": 618856} {"current_steps": 6875, "total_steps": 76960, "loss": 0.3671, "lr": 4.465956340956341e-05, "epoch": 1.7866424116424118, "percentage": 8.93, "elapsed_time": "0:09:49", "remaining_time": "1:40:09", "throughput": 1050.58, "total_tokens": 619288} {"current_steps": 6880, "total_steps": 76960, "loss": 0.272, "lr": 4.469204781704782e-05, "epoch": 1.7879417879417878, "percentage": 8.94, "elapsed_time": "0:09:49", "remaining_time": "1:40:08", "throughput": 1050.62, "total_tokens": 619752} {"current_steps": 6885, "total_steps": 76960, "loss": 0.2821, "lr": 4.472453222453223e-05, "epoch": 1.7892411642411643, "percentage": 8.95, "elapsed_time": "0:09:50", "remaining_time": "1:40:08", "throughput": 1050.58, "total_tokens": 620168} {"current_steps": 6890, "total_steps": 76960, "loss": 0.254, "lr": 4.475701663201664e-05, "epoch": 1.7905405405405406, "percentage": 8.95, "elapsed_time": "0:09:50", "remaining_time": "1:40:07", "throughput": 1050.6, "total_tokens": 620616} {"current_steps": 6895, "total_steps": 76960, "loss": 0.2268, "lr": 4.478950103950104e-05, "epoch": 1.7918399168399168, "percentage": 8.96, "elapsed_time": "0:09:51", "remaining_time": "1:40:07", "throughput": 1050.61, "total_tokens": 621064} {"current_steps": 6900, "total_steps": 76960, "loss": 0.2516, "lr": 4.482198544698545e-05, "epoch": 1.793139293139293, "percentage": 8.97, "elapsed_time": "0:09:51", "remaining_time": "1:40:06", "throughput": 1050.65, "total_tokens": 621528} {"current_steps": 6905, "total_steps": 76960, "loss": 0.4098, "lr": 4.485446985446985e-05, "epoch": 1.7944386694386694, "percentage": 8.97, "elapsed_time": "0:09:51", "remaining_time": "1:40:05", "throughput": 1050.7, "total_tokens": 621992} {"current_steps": 6910, "total_steps": 76960, "loss": 0.1987, "lr": 4.488695426195426e-05, "epoch": 1.7957380457380459, "percentage": 8.98, "elapsed_time": "0:09:52", "remaining_time": "1:40:05", "throughput": 1050.69, "total_tokens": 622424} {"current_steps": 6915, "total_steps": 76960, "loss": 0.2905, "lr": 4.491943866943867e-05, "epoch": 1.797037422037422, "percentage": 8.99, "elapsed_time": "0:09:52", "remaining_time": "1:40:04", "throughput": 1050.71, "total_tokens": 622872} {"current_steps": 6920, "total_steps": 76960, "loss": 0.2643, "lr": 4.495192307692308e-05, "epoch": 1.7983367983367984, "percentage": 8.99, "elapsed_time": "0:09:53", "remaining_time": "1:40:04", "throughput": 1050.75, "total_tokens": 623336} {"current_steps": 6925, "total_steps": 76960, "loss": 0.2684, "lr": 4.4984407484407485e-05, "epoch": 1.7996361746361746, "percentage": 9.0, "elapsed_time": "0:09:53", "remaining_time": "1:40:03", "throughput": 1050.82, "total_tokens": 623816} {"current_steps": 6930, "total_steps": 76960, "loss": 0.2235, "lr": 4.5016891891891895e-05, "epoch": 1.800935550935551, "percentage": 9.0, "elapsed_time": "0:09:54", "remaining_time": "1:40:03", "throughput": 1050.92, "total_tokens": 624312} {"current_steps": 6935, "total_steps": 76960, "loss": 0.1828, "lr": 4.50493762993763e-05, "epoch": 1.8022349272349274, "percentage": 9.01, "elapsed_time": "0:09:54", "remaining_time": "1:40:02", "throughput": 1050.94, "total_tokens": 624760} {"current_steps": 6940, "total_steps": 76960, "loss": 0.0461, "lr": 4.508186070686071e-05, "epoch": 1.8035343035343034, "percentage": 9.02, "elapsed_time": "0:09:54", "remaining_time": "1:40:02", "throughput": 1050.98, "total_tokens": 625224} {"current_steps": 6945, "total_steps": 76960, "loss": 0.498, "lr": 4.511434511434512e-05, "epoch": 1.80483367983368, "percentage": 9.02, "elapsed_time": "0:09:55", "remaining_time": "1:40:01", "throughput": 1050.97, "total_tokens": 625656} {"current_steps": 6950, "total_steps": 76960, "loss": 0.3447, "lr": 4.514682952182953e-05, "epoch": 1.806133056133056, "percentage": 9.03, "elapsed_time": "0:09:55", "remaining_time": "1:40:01", "throughput": 1050.98, "total_tokens": 626104} {"current_steps": 6955, "total_steps": 76960, "loss": 0.4269, "lr": 4.517931392931393e-05, "epoch": 1.8074324324324325, "percentage": 9.04, "elapsed_time": "0:09:56", "remaining_time": "1:40:00", "throughput": 1051.0, "total_tokens": 626552} {"current_steps": 6960, "total_steps": 76960, "loss": 0.3787, "lr": 4.521179833679834e-05, "epoch": 1.8087318087318087, "percentage": 9.04, "elapsed_time": "0:09:56", "remaining_time": "1:39:59", "throughput": 1050.98, "total_tokens": 626984} {"current_steps": 6965, "total_steps": 76960, "loss": 0.5512, "lr": 4.524428274428275e-05, "epoch": 1.810031185031185, "percentage": 9.05, "elapsed_time": "0:09:56", "remaining_time": "1:39:59", "throughput": 1050.97, "total_tokens": 627416} {"current_steps": 6970, "total_steps": 76960, "loss": 0.3317, "lr": 4.527676715176715e-05, "epoch": 1.8113305613305615, "percentage": 9.06, "elapsed_time": "0:09:57", "remaining_time": "1:39:58", "throughput": 1050.99, "total_tokens": 627864} {"current_steps": 6975, "total_steps": 76960, "loss": 0.5403, "lr": 4.530925155925156e-05, "epoch": 1.8126299376299375, "percentage": 9.06, "elapsed_time": "0:09:57", "remaining_time": "1:39:58", "throughput": 1051.03, "total_tokens": 628328} {"current_steps": 6980, "total_steps": 76960, "loss": 0.3437, "lr": 4.534173596673597e-05, "epoch": 1.813929313929314, "percentage": 9.07, "elapsed_time": "0:09:58", "remaining_time": "1:39:57", "throughput": 1051.04, "total_tokens": 628776} {"current_steps": 6985, "total_steps": 76960, "loss": 1.1302, "lr": 4.537422037422038e-05, "epoch": 1.8152286902286903, "percentage": 9.08, "elapsed_time": "0:09:58", "remaining_time": "1:39:57", "throughput": 1051.03, "total_tokens": 629208} {"current_steps": 6990, "total_steps": 76960, "loss": 0.277, "lr": 4.5406704781704784e-05, "epoch": 1.8165280665280665, "percentage": 9.08, "elapsed_time": "0:09:59", "remaining_time": "1:39:56", "throughput": 1051.06, "total_tokens": 629672} {"current_steps": 6995, "total_steps": 76960, "loss": 0.2799, "lr": 4.543918918918919e-05, "epoch": 1.8178274428274428, "percentage": 9.09, "elapsed_time": "0:09:59", "remaining_time": "1:39:56", "throughput": 1051.08, "total_tokens": 630120} {"current_steps": 7000, "total_steps": 76960, "loss": 0.2735, "lr": 4.5471673596673596e-05, "epoch": 1.819126819126819, "percentage": 9.1, "elapsed_time": "0:09:59", "remaining_time": "1:39:55", "throughput": 1051.12, "total_tokens": 630584} {"current_steps": 7005, "total_steps": 76960, "loss": 0.3188, "lr": 4.5504158004158006e-05, "epoch": 1.8204261954261955, "percentage": 9.1, "elapsed_time": "0:10:00", "remaining_time": "1:39:55", "throughput": 1051.13, "total_tokens": 631032} {"current_steps": 7010, "total_steps": 76960, "loss": 0.1845, "lr": 4.5536642411642415e-05, "epoch": 1.8217255717255716, "percentage": 9.11, "elapsed_time": "0:10:00", "remaining_time": "1:39:54", "throughput": 1051.13, "total_tokens": 631464} {"current_steps": 7015, "total_steps": 76960, "loss": 0.1565, "lr": 4.5569126819126825e-05, "epoch": 1.823024948024948, "percentage": 9.12, "elapsed_time": "0:10:01", "remaining_time": "1:39:54", "throughput": 1051.17, "total_tokens": 631928} {"current_steps": 7020, "total_steps": 76960, "loss": 0.4041, "lr": 4.560161122661123e-05, "epoch": 1.8243243243243243, "percentage": 9.12, "elapsed_time": "0:10:01", "remaining_time": "1:39:53", "throughput": 1051.24, "total_tokens": 632408} {"current_steps": 7025, "total_steps": 76960, "loss": 0.2856, "lr": 4.563409563409564e-05, "epoch": 1.8256237006237006, "percentage": 9.13, "elapsed_time": "0:10:01", "remaining_time": "1:39:52", "throughput": 1051.29, "total_tokens": 632872} {"current_steps": 7030, "total_steps": 76960, "loss": 0.5452, "lr": 4.566658004158004e-05, "epoch": 1.8269230769230769, "percentage": 9.13, "elapsed_time": "0:10:02", "remaining_time": "1:39:52", "throughput": 1051.33, "total_tokens": 633336} {"current_steps": 7035, "total_steps": 76960, "loss": 0.2883, "lr": 4.569906444906445e-05, "epoch": 1.8282224532224531, "percentage": 9.14, "elapsed_time": "0:10:02", "remaining_time": "1:39:51", "throughput": 1051.43, "total_tokens": 633832} {"current_steps": 7040, "total_steps": 76960, "loss": 0.2844, "lr": 4.573154885654886e-05, "epoch": 1.8295218295218296, "percentage": 9.15, "elapsed_time": "0:10:03", "remaining_time": "1:39:51", "throughput": 1051.5, "total_tokens": 634312} {"current_steps": 7045, "total_steps": 76960, "loss": 0.2918, "lr": 4.576403326403327e-05, "epoch": 1.8308212058212057, "percentage": 9.15, "elapsed_time": "0:10:03", "remaining_time": "1:39:50", "throughput": 1051.54, "total_tokens": 634776} {"current_steps": 7050, "total_steps": 76960, "loss": 0.3212, "lr": 4.579651767151767e-05, "epoch": 1.8321205821205822, "percentage": 9.16, "elapsed_time": "0:10:04", "remaining_time": "1:39:50", "throughput": 1051.6, "total_tokens": 635256} {"current_steps": 7055, "total_steps": 76960, "loss": 0.22, "lr": 4.582900207900208e-05, "epoch": 1.8334199584199584, "percentage": 9.17, "elapsed_time": "0:10:04", "remaining_time": "1:39:49", "throughput": 1051.67, "total_tokens": 635736} {"current_steps": 7060, "total_steps": 76960, "loss": 0.2571, "lr": 4.5861486486486485e-05, "epoch": 1.8347193347193347, "percentage": 9.17, "elapsed_time": "0:10:04", "remaining_time": "1:39:49", "throughput": 1051.69, "total_tokens": 636184} {"current_steps": 7065, "total_steps": 76960, "loss": 0.2779, "lr": 4.5893970893970894e-05, "epoch": 1.8360187110187112, "percentage": 9.18, "elapsed_time": "0:10:05", "remaining_time": "1:39:48", "throughput": 1051.7, "total_tokens": 636632} {"current_steps": 7070, "total_steps": 76960, "loss": 0.2578, "lr": 4.5926455301455304e-05, "epoch": 1.8373180873180872, "percentage": 9.19, "elapsed_time": "0:10:05", "remaining_time": "1:39:48", "throughput": 1051.69, "total_tokens": 637064} {"current_steps": 7075, "total_steps": 76960, "loss": 0.3023, "lr": 4.5958939708939714e-05, "epoch": 1.8386174636174637, "percentage": 9.19, "elapsed_time": "0:10:06", "remaining_time": "1:39:47", "throughput": 1051.7, "total_tokens": 637512} {"current_steps": 7080, "total_steps": 76960, "loss": 0.1988, "lr": 4.599142411642412e-05, "epoch": 1.83991683991684, "percentage": 9.2, "elapsed_time": "0:10:06", "remaining_time": "1:39:47", "throughput": 1051.71, "total_tokens": 637960} {"current_steps": 7085, "total_steps": 76960, "loss": 0.4236, "lr": 4.6023908523908526e-05, "epoch": 1.8412162162162162, "percentage": 9.21, "elapsed_time": "0:10:07", "remaining_time": "1:39:46", "throughput": 1051.67, "total_tokens": 638376} {"current_steps": 7090, "total_steps": 76960, "loss": 0.2842, "lr": 4.6056392931392936e-05, "epoch": 1.8425155925155925, "percentage": 9.21, "elapsed_time": "0:10:07", "remaining_time": "1:39:46", "throughput": 1051.63, "total_tokens": 638792} {"current_steps": 7095, "total_steps": 76960, "loss": 0.2842, "lr": 4.608887733887734e-05, "epoch": 1.8438149688149688, "percentage": 9.22, "elapsed_time": "0:10:07", "remaining_time": "1:39:45", "throughput": 1051.63, "total_tokens": 639224} {"current_steps": 7100, "total_steps": 76960, "loss": 0.2449, "lr": 4.612136174636175e-05, "epoch": 1.8451143451143452, "percentage": 9.23, "elapsed_time": "0:10:08", "remaining_time": "1:39:44", "throughput": 1051.58, "total_tokens": 639640} {"current_steps": 7105, "total_steps": 76960, "loss": 0.2079, "lr": 4.615384615384616e-05, "epoch": 1.8464137214137213, "percentage": 9.23, "elapsed_time": "0:10:08", "remaining_time": "1:39:44", "throughput": 1051.6, "total_tokens": 640088} {"current_steps": 7110, "total_steps": 76960, "loss": 0.3321, "lr": 4.618633056133057e-05, "epoch": 1.8477130977130978, "percentage": 9.24, "elapsed_time": "0:10:09", "remaining_time": "1:39:43", "throughput": 1051.62, "total_tokens": 640536} {"current_steps": 7115, "total_steps": 76960, "loss": 0.2169, "lr": 4.621881496881497e-05, "epoch": 1.849012474012474, "percentage": 9.25, "elapsed_time": "0:10:09", "remaining_time": "1:39:43", "throughput": 1051.62, "total_tokens": 640984} {"current_steps": 7120, "total_steps": 76960, "loss": 0.3788, "lr": 4.625129937629938e-05, "epoch": 1.8503118503118503, "percentage": 9.25, "elapsed_time": "0:10:09", "remaining_time": "1:39:42", "throughput": 1051.67, "total_tokens": 641464} {"current_steps": 7125, "total_steps": 76960, "loss": 0.3022, "lr": 4.628378378378378e-05, "epoch": 1.8516112266112266, "percentage": 9.26, "elapsed_time": "0:10:10", "remaining_time": "1:39:42", "throughput": 1051.71, "total_tokens": 641928} {"current_steps": 7130, "total_steps": 76960, "loss": 0.3147, "lr": 4.631626819126819e-05, "epoch": 1.8529106029106028, "percentage": 9.26, "elapsed_time": "0:10:10", "remaining_time": "1:39:41", "throughput": 1051.75, "total_tokens": 642392} {"current_steps": 7135, "total_steps": 76960, "loss": 0.2533, "lr": 4.6348752598752596e-05, "epoch": 1.8542099792099793, "percentage": 9.27, "elapsed_time": "0:10:11", "remaining_time": "1:39:41", "throughput": 1051.77, "total_tokens": 642840} {"current_steps": 7140, "total_steps": 76960, "loss": 0.2587, "lr": 4.638123700623701e-05, "epoch": 1.8555093555093554, "percentage": 9.28, "elapsed_time": "0:10:11", "remaining_time": "1:39:40", "throughput": 1051.78, "total_tokens": 643288} {"current_steps": 7145, "total_steps": 76960, "loss": 0.3129, "lr": 4.6413721413721415e-05, "epoch": 1.8568087318087318, "percentage": 9.28, "elapsed_time": "0:10:12", "remaining_time": "1:39:40", "throughput": 1051.79, "total_tokens": 643736} {"current_steps": 7150, "total_steps": 76960, "loss": 0.2092, "lr": 4.6446205821205825e-05, "epoch": 1.8581081081081081, "percentage": 9.29, "elapsed_time": "0:10:12", "remaining_time": "1:39:39", "throughput": 1051.8, "total_tokens": 644184} {"current_steps": 7155, "total_steps": 76960, "loss": 0.3758, "lr": 4.647869022869023e-05, "epoch": 1.8594074844074844, "percentage": 9.3, "elapsed_time": "0:10:12", "remaining_time": "1:39:39", "throughput": 1051.92, "total_tokens": 644696} {"current_steps": 7160, "total_steps": 76960, "loss": 0.2419, "lr": 4.651117463617464e-05, "epoch": 1.8607068607068609, "percentage": 9.3, "elapsed_time": "0:10:13", "remaining_time": "1:39:38", "throughput": 1051.94, "total_tokens": 645144} {"current_steps": 7165, "total_steps": 76960, "loss": 0.2827, "lr": 4.654365904365905e-05, "epoch": 1.862006237006237, "percentage": 9.31, "elapsed_time": "0:10:13", "remaining_time": "1:39:38", "throughput": 1051.97, "total_tokens": 645608} {"current_steps": 7170, "total_steps": 76960, "loss": 0.3201, "lr": 4.6576143451143457e-05, "epoch": 1.8633056133056134, "percentage": 9.32, "elapsed_time": "0:10:14", "remaining_time": "1:39:37", "throughput": 1052.09, "total_tokens": 646120} {"current_steps": 7175, "total_steps": 76960, "loss": 0.2567, "lr": 4.660862785862786e-05, "epoch": 1.8646049896049897, "percentage": 9.32, "elapsed_time": "0:10:14", "remaining_time": "1:39:37", "throughput": 1052.16, "total_tokens": 646600} {"current_steps": 7180, "total_steps": 76960, "loss": 0.2621, "lr": 4.664111226611227e-05, "epoch": 1.865904365904366, "percentage": 9.33, "elapsed_time": "0:10:14", "remaining_time": "1:39:36", "throughput": 1052.13, "total_tokens": 647032} {"current_steps": 7185, "total_steps": 76960, "loss": 0.307, "lr": 4.667359667359668e-05, "epoch": 1.8672037422037422, "percentage": 9.34, "elapsed_time": "0:10:15", "remaining_time": "1:39:36", "throughput": 1052.17, "total_tokens": 647496} {"current_steps": 7190, "total_steps": 76960, "loss": 0.283, "lr": 4.670608108108108e-05, "epoch": 1.8685031185031185, "percentage": 9.34, "elapsed_time": "0:10:15", "remaining_time": "1:39:35", "throughput": 1052.16, "total_tokens": 647928} {"current_steps": 7195, "total_steps": 76960, "loss": 0.2606, "lr": 4.673856548856549e-05, "epoch": 1.869802494802495, "percentage": 9.35, "elapsed_time": "0:10:16", "remaining_time": "1:39:35", "throughput": 1052.17, "total_tokens": 648376} {"current_steps": 7200, "total_steps": 76960, "loss": 0.2549, "lr": 4.67710498960499e-05, "epoch": 1.871101871101871, "percentage": 9.36, "elapsed_time": "0:10:16", "remaining_time": "1:39:34", "throughput": 1052.19, "total_tokens": 648824} {"current_steps": 7205, "total_steps": 76960, "loss": 0.2779, "lr": 4.680353430353431e-05, "epoch": 1.8724012474012475, "percentage": 9.36, "elapsed_time": "0:10:17", "remaining_time": "1:39:34", "throughput": 1052.15, "total_tokens": 649240} {"current_steps": 7210, "total_steps": 76960, "loss": 0.2287, "lr": 4.6836018711018713e-05, "epoch": 1.8737006237006237, "percentage": 9.37, "elapsed_time": "0:10:17", "remaining_time": "1:39:33", "throughput": 1052.11, "total_tokens": 649656} {"current_steps": 7215, "total_steps": 76960, "loss": 0.2018, "lr": 4.686850311850312e-05, "epoch": 1.875, "percentage": 9.38, "elapsed_time": "0:10:17", "remaining_time": "1:39:32", "throughput": 1052.1, "total_tokens": 650088} {"current_steps": 7220, "total_steps": 76960, "loss": 0.3872, "lr": 4.6900987525987526e-05, "epoch": 1.8762993762993763, "percentage": 9.38, "elapsed_time": "0:10:18", "remaining_time": "1:39:32", "throughput": 1052.11, "total_tokens": 650536} {"current_steps": 7225, "total_steps": 76960, "loss": 0.2158, "lr": 4.6933471933471936e-05, "epoch": 1.8775987525987525, "percentage": 9.39, "elapsed_time": "0:10:18", "remaining_time": "1:39:31", "throughput": 1052.07, "total_tokens": 650952} {"current_steps": 7230, "total_steps": 76960, "loss": 0.1841, "lr": 4.696595634095634e-05, "epoch": 1.878898128898129, "percentage": 9.39, "elapsed_time": "0:10:19", "remaining_time": "1:39:31", "throughput": 1052.12, "total_tokens": 651416} {"current_steps": 7235, "total_steps": 76960, "loss": 0.3088, "lr": 4.6998440748440755e-05, "epoch": 1.880197505197505, "percentage": 9.4, "elapsed_time": "0:10:19", "remaining_time": "1:39:30", "throughput": 1052.18, "total_tokens": 651896} {"current_steps": 7240, "total_steps": 76960, "loss": 0.3033, "lr": 4.703092515592516e-05, "epoch": 1.8814968814968815, "percentage": 9.41, "elapsed_time": "0:10:19", "remaining_time": "1:39:30", "throughput": 1052.12, "total_tokens": 652296} {"current_steps": 7245, "total_steps": 76960, "loss": 0.2799, "lr": 4.706340956340957e-05, "epoch": 1.8827962577962578, "percentage": 9.41, "elapsed_time": "0:10:20", "remaining_time": "1:39:29", "throughput": 1052.16, "total_tokens": 652760} {"current_steps": 7250, "total_steps": 76960, "loss": 0.2626, "lr": 4.709589397089397e-05, "epoch": 1.884095634095634, "percentage": 9.42, "elapsed_time": "0:10:20", "remaining_time": "1:39:29", "throughput": 1052.17, "total_tokens": 653208} {"current_steps": 7255, "total_steps": 76960, "loss": 0.2451, "lr": 4.712837837837838e-05, "epoch": 1.8853950103950103, "percentage": 9.43, "elapsed_time": "0:10:21", "remaining_time": "1:39:28", "throughput": 1052.26, "total_tokens": 653704} {"current_steps": 7260, "total_steps": 76960, "loss": 0.243, "lr": 4.716086278586278e-05, "epoch": 1.8866943866943866, "percentage": 9.43, "elapsed_time": "0:10:21", "remaining_time": "1:39:28", "throughput": 1052.3, "total_tokens": 654168} {"current_steps": 7265, "total_steps": 76960, "loss": 0.2637, "lr": 4.71933471933472e-05, "epoch": 1.887993762993763, "percentage": 9.44, "elapsed_time": "0:10:22", "remaining_time": "1:39:27", "throughput": 1052.39, "total_tokens": 654664} {"current_steps": 7270, "total_steps": 76960, "loss": 0.22, "lr": 4.72258316008316e-05, "epoch": 1.8892931392931391, "percentage": 9.45, "elapsed_time": "0:10:22", "remaining_time": "1:39:27", "throughput": 1052.38, "total_tokens": 655096} {"current_steps": 7275, "total_steps": 76960, "loss": 0.3186, "lr": 4.725831600831601e-05, "epoch": 1.8905925155925156, "percentage": 9.45, "elapsed_time": "0:10:22", "remaining_time": "1:39:26", "throughput": 1052.37, "total_tokens": 655528} {"current_steps": 7280, "total_steps": 76960, "loss": 0.1682, "lr": 4.7290800415800415e-05, "epoch": 1.8918918918918919, "percentage": 9.46, "elapsed_time": "0:10:23", "remaining_time": "1:39:26", "throughput": 1052.35, "total_tokens": 655960} {"current_steps": 7285, "total_steps": 76960, "loss": 0.2697, "lr": 4.7323284823284824e-05, "epoch": 1.8931912681912682, "percentage": 9.47, "elapsed_time": "0:10:23", "remaining_time": "1:39:25", "throughput": 1052.39, "total_tokens": 656424} {"current_steps": 7290, "total_steps": 76960, "loss": 0.2182, "lr": 4.7355769230769234e-05, "epoch": 1.8944906444906446, "percentage": 9.47, "elapsed_time": "0:10:24", "remaining_time": "1:39:25", "throughput": 1052.41, "total_tokens": 656872} {"current_steps": 7295, "total_steps": 76960, "loss": 0.3472, "lr": 4.738825363825364e-05, "epoch": 1.8957900207900207, "percentage": 9.48, "elapsed_time": "0:10:24", "remaining_time": "1:39:24", "throughput": 1052.45, "total_tokens": 657336} {"current_steps": 7300, "total_steps": 76960, "loss": 0.2438, "lr": 4.742073804573805e-05, "epoch": 1.8970893970893972, "percentage": 9.49, "elapsed_time": "0:10:24", "remaining_time": "1:39:24", "throughput": 1052.43, "total_tokens": 657768} {"current_steps": 7305, "total_steps": 76960, "loss": 0.254, "lr": 4.7453222453222456e-05, "epoch": 1.8983887733887734, "percentage": 9.49, "elapsed_time": "0:10:25", "remaining_time": "1:39:23", "throughput": 1052.4, "total_tokens": 658184} {"current_steps": 7310, "total_steps": 76960, "loss": 0.3168, "lr": 4.7485706860706866e-05, "epoch": 1.8996881496881497, "percentage": 9.5, "elapsed_time": "0:10:25", "remaining_time": "1:39:22", "throughput": 1052.41, "total_tokens": 658632} {"current_steps": 7315, "total_steps": 76960, "loss": 0.2549, "lr": 4.751819126819127e-05, "epoch": 1.900987525987526, "percentage": 9.5, "elapsed_time": "0:10:26", "remaining_time": "1:39:22", "throughput": 1052.37, "total_tokens": 659048} {"current_steps": 7320, "total_steps": 76960, "loss": 0.2119, "lr": 4.755067567567568e-05, "epoch": 1.9022869022869022, "percentage": 9.51, "elapsed_time": "0:10:26", "remaining_time": "1:39:21", "throughput": 1052.36, "total_tokens": 659480} {"current_steps": 7325, "total_steps": 76960, "loss": 0.179, "lr": 4.758316008316008e-05, "epoch": 1.9035862785862787, "percentage": 9.52, "elapsed_time": "0:10:27", "remaining_time": "1:39:21", "throughput": 1052.5, "total_tokens": 660008} {"current_steps": 7330, "total_steps": 76960, "loss": 0.0933, "lr": 4.76156444906445e-05, "epoch": 1.9048856548856548, "percentage": 9.52, "elapsed_time": "0:10:27", "remaining_time": "1:39:20", "throughput": 1052.46, "total_tokens": 660424} {"current_steps": 7335, "total_steps": 76960, "loss": 0.3896, "lr": 4.76481288981289e-05, "epoch": 1.9061850311850312, "percentage": 9.53, "elapsed_time": "0:10:27", "remaining_time": "1:39:20", "throughput": 1052.5, "total_tokens": 660888} {"current_steps": 7340, "total_steps": 76960, "loss": 0.3894, "lr": 4.768061330561331e-05, "epoch": 1.9074844074844075, "percentage": 9.54, "elapsed_time": "0:10:28", "remaining_time": "1:39:19", "throughput": 1052.54, "total_tokens": 661352} {"current_steps": 7345, "total_steps": 76960, "loss": 0.2741, "lr": 4.771309771309771e-05, "epoch": 1.9087837837837838, "percentage": 9.54, "elapsed_time": "0:10:28", "remaining_time": "1:39:19", "throughput": 1052.55, "total_tokens": 661800} {"current_steps": 7350, "total_steps": 76960, "loss": 0.3319, "lr": 4.774558212058212e-05, "epoch": 1.91008316008316, "percentage": 9.55, "elapsed_time": "0:10:29", "remaining_time": "1:39:18", "throughput": 1052.59, "total_tokens": 662264} {"current_steps": 7355, "total_steps": 76960, "loss": 0.3384, "lr": 4.7778066528066526e-05, "epoch": 1.9113825363825363, "percentage": 9.56, "elapsed_time": "0:10:29", "remaining_time": "1:39:18", "throughput": 1052.55, "total_tokens": 662680} {"current_steps": 7360, "total_steps": 76960, "loss": 0.3544, "lr": 4.7810550935550935e-05, "epoch": 1.9126819126819128, "percentage": 9.56, "elapsed_time": "0:10:30", "remaining_time": "1:39:17", "throughput": 1052.59, "total_tokens": 663144} {"current_steps": 7365, "total_steps": 76960, "loss": 0.2877, "lr": 4.7843035343035345e-05, "epoch": 1.9139812889812888, "percentage": 9.57, "elapsed_time": "0:10:30", "remaining_time": "1:39:17", "throughput": 1052.62, "total_tokens": 663608} {"current_steps": 7370, "total_steps": 76960, "loss": 0.1934, "lr": 4.7875519750519755e-05, "epoch": 1.9152806652806653, "percentage": 9.58, "elapsed_time": "0:10:30", "remaining_time": "1:39:16", "throughput": 1052.58, "total_tokens": 664024} {"current_steps": 7375, "total_steps": 76960, "loss": 0.0559, "lr": 4.790800415800416e-05, "epoch": 1.9165800415800416, "percentage": 9.58, "elapsed_time": "0:10:31", "remaining_time": "1:39:16", "throughput": 1052.62, "total_tokens": 664488} {"current_steps": 7380, "total_steps": 76960, "loss": 0.5102, "lr": 4.794048856548857e-05, "epoch": 1.9178794178794178, "percentage": 9.59, "elapsed_time": "0:10:31", "remaining_time": "1:39:15", "throughput": 1052.61, "total_tokens": 664920} {"current_steps": 7385, "total_steps": 76960, "loss": 0.6609, "lr": 4.797297297297298e-05, "epoch": 1.9191787941787943, "percentage": 9.6, "elapsed_time": "0:10:32", "remaining_time": "1:39:15", "throughput": 1052.62, "total_tokens": 665368} {"current_steps": 7390, "total_steps": 76960, "loss": 0.8141, "lr": 4.800545738045738e-05, "epoch": 1.9204781704781704, "percentage": 9.6, "elapsed_time": "0:10:32", "remaining_time": "1:39:14", "throughput": 1052.58, "total_tokens": 665784} {"current_steps": 7395, "total_steps": 76960, "loss": 0.1806, "lr": 4.803794178794179e-05, "epoch": 1.9217775467775469, "percentage": 9.61, "elapsed_time": "0:10:32", "remaining_time": "1:39:14", "throughput": 1052.67, "total_tokens": 666280} {"current_steps": 7400, "total_steps": 76960, "loss": 0.3647, "lr": 4.80704261954262e-05, "epoch": 1.9230769230769231, "percentage": 9.62, "elapsed_time": "0:10:33", "remaining_time": "1:39:13", "throughput": 1052.69, "total_tokens": 666728} {"current_steps": 7405, "total_steps": 76960, "loss": 0.6089, "lr": 4.810291060291061e-05, "epoch": 1.9243762993762994, "percentage": 9.62, "elapsed_time": "0:10:33", "remaining_time": "1:39:13", "throughput": 1052.67, "total_tokens": 667160} {"current_steps": 7410, "total_steps": 76960, "loss": 0.1884, "lr": 4.813539501039501e-05, "epoch": 1.9256756756756757, "percentage": 9.63, "elapsed_time": "0:10:34", "remaining_time": "1:39:12", "throughput": 1052.64, "total_tokens": 667576} {"current_steps": 7415, "total_steps": 76960, "loss": 0.3522, "lr": 4.816787941787942e-05, "epoch": 1.926975051975052, "percentage": 9.63, "elapsed_time": "0:10:34", "remaining_time": "1:39:12", "throughput": 1052.62, "total_tokens": 668008} {"current_steps": 7420, "total_steps": 76960, "loss": 0.215, "lr": 4.8200363825363824e-05, "epoch": 1.9282744282744284, "percentage": 9.64, "elapsed_time": "0:10:35", "remaining_time": "1:39:11", "throughput": 1052.69, "total_tokens": 668488} {"current_steps": 7425, "total_steps": 76960, "loss": 0.1805, "lr": 4.823284823284824e-05, "epoch": 1.9295738045738045, "percentage": 9.65, "elapsed_time": "0:10:35", "remaining_time": "1:39:10", "throughput": 1052.78, "total_tokens": 668984} {"current_steps": 7430, "total_steps": 76960, "loss": 0.4176, "lr": 4.8265332640332643e-05, "epoch": 1.930873180873181, "percentage": 9.65, "elapsed_time": "0:10:35", "remaining_time": "1:39:10", "throughput": 1052.82, "total_tokens": 669448} {"current_steps": 7435, "total_steps": 76960, "loss": 0.2619, "lr": 4.829781704781705e-05, "epoch": 1.9321725571725572, "percentage": 9.66, "elapsed_time": "0:10:36", "remaining_time": "1:39:09", "throughput": 1052.88, "total_tokens": 669928} {"current_steps": 7440, "total_steps": 76960, "loss": 0.348, "lr": 4.8330301455301456e-05, "epoch": 1.9334719334719335, "percentage": 9.67, "elapsed_time": "0:10:36", "remaining_time": "1:39:09", "throughput": 1052.84, "total_tokens": 670344} {"current_steps": 7445, "total_steps": 76960, "loss": 0.2874, "lr": 4.8362785862785866e-05, "epoch": 1.9347713097713097, "percentage": 9.67, "elapsed_time": "0:10:37", "remaining_time": "1:39:08", "throughput": 1052.86, "total_tokens": 670792} {"current_steps": 7450, "total_steps": 76960, "loss": 0.3101, "lr": 4.839527027027027e-05, "epoch": 1.936070686070686, "percentage": 9.68, "elapsed_time": "0:10:37", "remaining_time": "1:39:08", "throughput": 1052.95, "total_tokens": 671288} {"current_steps": 7455, "total_steps": 76960, "loss": 0.271, "lr": 4.842775467775468e-05, "epoch": 1.9373700623700625, "percentage": 9.69, "elapsed_time": "0:10:37", "remaining_time": "1:39:07", "throughput": 1052.96, "total_tokens": 671736} {"current_steps": 7460, "total_steps": 76960, "loss": 0.2681, "lr": 4.846023908523909e-05, "epoch": 1.9386694386694385, "percentage": 9.69, "elapsed_time": "0:10:38", "remaining_time": "1:39:07", "throughput": 1053.07, "total_tokens": 672248} {"current_steps": 7465, "total_steps": 76960, "loss": 0.2294, "lr": 4.84927234927235e-05, "epoch": 1.939968814968815, "percentage": 9.7, "elapsed_time": "0:10:38", "remaining_time": "1:39:06", "throughput": 1053.11, "total_tokens": 672712} {"current_steps": 7470, "total_steps": 76960, "loss": 0.2783, "lr": 4.85252079002079e-05, "epoch": 1.9412681912681913, "percentage": 9.71, "elapsed_time": "0:10:39", "remaining_time": "1:39:06", "throughput": 1053.15, "total_tokens": 673176} {"current_steps": 7475, "total_steps": 76960, "loss": 0.2226, "lr": 4.855769230769231e-05, "epoch": 1.9425675675675675, "percentage": 9.71, "elapsed_time": "0:10:39", "remaining_time": "1:39:05", "throughput": 1053.14, "total_tokens": 673608} {"current_steps": 7480, "total_steps": 76960, "loss": 0.2622, "lr": 4.859017671517671e-05, "epoch": 1.943866943866944, "percentage": 9.72, "elapsed_time": "0:10:40", "remaining_time": "1:39:05", "throughput": 1053.18, "total_tokens": 674072} {"current_steps": 7485, "total_steps": 76960, "loss": 0.1659, "lr": 4.862266112266112e-05, "epoch": 1.94516632016632, "percentage": 9.73, "elapsed_time": "0:10:40", "remaining_time": "1:39:04", "throughput": 1053.27, "total_tokens": 674568} {"current_steps": 7490, "total_steps": 76960, "loss": 0.2123, "lr": 4.865514553014553e-05, "epoch": 1.9464656964656966, "percentage": 9.73, "elapsed_time": "0:10:40", "remaining_time": "1:39:04", "throughput": 1053.28, "total_tokens": 675016} {"current_steps": 7495, "total_steps": 76960, "loss": 0.2615, "lr": 4.868762993762994e-05, "epoch": 1.9477650727650726, "percentage": 9.74, "elapsed_time": "0:10:41", "remaining_time": "1:39:03", "throughput": 1053.29, "total_tokens": 675464} {"current_steps": 7500, "total_steps": 76960, "loss": 0.3592, "lr": 4.872011434511435e-05, "epoch": 1.949064449064449, "percentage": 9.75, "elapsed_time": "0:10:41", "remaining_time": "1:39:03", "throughput": 1053.33, "total_tokens": 675928} {"current_steps": 7505, "total_steps": 76960, "loss": 0.2445, "lr": 4.8752598752598754e-05, "epoch": 1.9503638253638254, "percentage": 9.75, "elapsed_time": "0:10:42", "remaining_time": "1:39:02", "throughput": 1053.34, "total_tokens": 676376} {"current_steps": 7510, "total_steps": 76960, "loss": 0.2365, "lr": 4.8785083160083164e-05, "epoch": 1.9516632016632016, "percentage": 9.76, "elapsed_time": "0:10:42", "remaining_time": "1:39:01", "throughput": 1053.38, "total_tokens": 676840} {"current_steps": 7515, "total_steps": 76960, "loss": 0.2272, "lr": 4.881756756756757e-05, "epoch": 1.952962577962578, "percentage": 9.76, "elapsed_time": "0:10:42", "remaining_time": "1:39:01", "throughput": 1053.42, "total_tokens": 677304} {"current_steps": 7520, "total_steps": 76960, "loss": 0.1522, "lr": 4.8850051975051977e-05, "epoch": 1.9542619542619541, "percentage": 9.77, "elapsed_time": "0:10:43", "remaining_time": "1:39:00", "throughput": 1053.46, "total_tokens": 677768} {"current_steps": 7525, "total_steps": 76960, "loss": 0.1503, "lr": 4.8882536382536386e-05, "epoch": 1.9555613305613306, "percentage": 9.78, "elapsed_time": "0:10:43", "remaining_time": "1:39:00", "throughput": 1053.45, "total_tokens": 678200} {"current_steps": 7530, "total_steps": 76960, "loss": 0.3992, "lr": 4.8915020790020796e-05, "epoch": 1.956860706860707, "percentage": 9.78, "elapsed_time": "0:10:44", "remaining_time": "1:38:59", "throughput": 1053.48, "total_tokens": 678664} {"current_steps": 7535, "total_steps": 76960, "loss": 0.2919, "lr": 4.89475051975052e-05, "epoch": 1.9581600831600832, "percentage": 9.79, "elapsed_time": "0:10:44", "remaining_time": "1:38:59", "throughput": 1053.52, "total_tokens": 679128} {"current_steps": 7540, "total_steps": 76960, "loss": 0.2211, "lr": 4.897998960498961e-05, "epoch": 1.9594594594594594, "percentage": 9.8, "elapsed_time": "0:10:45", "remaining_time": "1:38:58", "throughput": 1053.5, "total_tokens": 679560} {"current_steps": 7545, "total_steps": 76960, "loss": 0.2162, "lr": 4.901247401247401e-05, "epoch": 1.9607588357588357, "percentage": 9.8, "elapsed_time": "0:10:45", "remaining_time": "1:38:58", "throughput": 1053.54, "total_tokens": 680024} {"current_steps": 7550, "total_steps": 76960, "loss": 0.2211, "lr": 4.904495841995842e-05, "epoch": 1.9620582120582122, "percentage": 9.81, "elapsed_time": "0:10:45", "remaining_time": "1:38:57", "throughput": 1053.52, "total_tokens": 680456} {"current_steps": 7555, "total_steps": 76960, "loss": 0.2075, "lr": 4.907744282744283e-05, "epoch": 1.9633575883575882, "percentage": 9.82, "elapsed_time": "0:10:46", "remaining_time": "1:38:57", "throughput": 1053.51, "total_tokens": 680888} {"current_steps": 7560, "total_steps": 76960, "loss": 0.3892, "lr": 4.910992723492724e-05, "epoch": 1.9646569646569647, "percentage": 9.82, "elapsed_time": "0:10:46", "remaining_time": "1:38:56", "throughput": 1053.55, "total_tokens": 681352} {"current_steps": 7565, "total_steps": 76960, "loss": 0.2773, "lr": 4.914241164241164e-05, "epoch": 1.965956340956341, "percentage": 9.83, "elapsed_time": "0:10:47", "remaining_time": "1:38:56", "throughput": 1053.56, "total_tokens": 681800} {"current_steps": 7570, "total_steps": 76960, "loss": 0.2491, "lr": 4.917489604989605e-05, "epoch": 1.9672557172557172, "percentage": 9.84, "elapsed_time": "0:10:47", "remaining_time": "1:38:55", "throughput": 1053.58, "total_tokens": 682248} {"current_steps": 7575, "total_steps": 76960, "loss": 0.287, "lr": 4.9207380457380456e-05, "epoch": 1.9685550935550935, "percentage": 9.84, "elapsed_time": "0:10:47", "remaining_time": "1:38:55", "throughput": 1053.6, "total_tokens": 682696} {"current_steps": 7580, "total_steps": 76960, "loss": 0.328, "lr": 4.9239864864864865e-05, "epoch": 1.9698544698544698, "percentage": 9.85, "elapsed_time": "0:10:48", "remaining_time": "1:38:54", "throughput": 1053.66, "total_tokens": 683176} {"current_steps": 7585, "total_steps": 76960, "loss": 0.2759, "lr": 4.9272349272349275e-05, "epoch": 1.9711538461538463, "percentage": 9.86, "elapsed_time": "0:10:48", "remaining_time": "1:38:54", "throughput": 1053.68, "total_tokens": 683624} {"current_steps": 7590, "total_steps": 76960, "loss": 0.2889, "lr": 4.9304833679833685e-05, "epoch": 1.9724532224532223, "percentage": 9.86, "elapsed_time": "0:10:49", "remaining_time": "1:38:53", "throughput": 1053.75, "total_tokens": 684104} {"current_steps": 7595, "total_steps": 76960, "loss": 0.2353, "lr": 4.933731808731809e-05, "epoch": 1.9737525987525988, "percentage": 9.87, "elapsed_time": "0:10:49", "remaining_time": "1:38:53", "throughput": 1053.77, "total_tokens": 684552} {"current_steps": 7600, "total_steps": 76960, "loss": 0.219, "lr": 4.93698024948025e-05, "epoch": 1.975051975051975, "percentage": 9.88, "elapsed_time": "0:10:50", "remaining_time": "1:38:52", "throughput": 1053.78, "total_tokens": 685000} {"current_steps": 7605, "total_steps": 76960, "loss": 0.1672, "lr": 4.940228690228691e-05, "epoch": 1.9763513513513513, "percentage": 9.88, "elapsed_time": "0:10:50", "remaining_time": "1:38:51", "throughput": 1053.79, "total_tokens": 685448} {"current_steps": 7610, "total_steps": 76960, "loss": 0.2905, "lr": 4.943477130977131e-05, "epoch": 1.9776507276507278, "percentage": 9.89, "elapsed_time": "0:10:50", "remaining_time": "1:38:51", "throughput": 1053.83, "total_tokens": 685912} {"current_steps": 7615, "total_steps": 76960, "loss": 0.2151, "lr": 4.946725571725572e-05, "epoch": 1.9789501039501038, "percentage": 9.89, "elapsed_time": "0:10:51", "remaining_time": "1:38:50", "throughput": 1053.87, "total_tokens": 686376} {"current_steps": 7620, "total_steps": 76960, "loss": 0.3295, "lr": 4.949974012474013e-05, "epoch": 1.9802494802494803, "percentage": 9.9, "elapsed_time": "0:10:51", "remaining_time": "1:38:50", "throughput": 1053.89, "total_tokens": 686824} {"current_steps": 7625, "total_steps": 76960, "loss": 0.3245, "lr": 4.953222453222454e-05, "epoch": 1.9815488565488566, "percentage": 9.91, "elapsed_time": "0:10:52", "remaining_time": "1:38:49", "throughput": 1053.95, "total_tokens": 687304} {"current_steps": 7630, "total_steps": 76960, "loss": 0.2638, "lr": 4.956470893970894e-05, "epoch": 1.9828482328482329, "percentage": 9.91, "elapsed_time": "0:10:52", "remaining_time": "1:38:49", "throughput": 1053.99, "total_tokens": 687768} {"current_steps": 7635, "total_steps": 76960, "loss": 0.2397, "lr": 4.959719334719335e-05, "epoch": 1.9841476091476091, "percentage": 9.92, "elapsed_time": "0:10:52", "remaining_time": "1:38:48", "throughput": 1053.98, "total_tokens": 688200} {"current_steps": 7640, "total_steps": 76960, "loss": 0.2337, "lr": 4.9629677754677754e-05, "epoch": 1.9854469854469854, "percentage": 9.93, "elapsed_time": "0:10:53", "remaining_time": "1:38:48", "throughput": 1054.09, "total_tokens": 688712} {"current_steps": 7645, "total_steps": 76960, "loss": 0.2193, "lr": 4.9662162162162164e-05, "epoch": 1.9867463617463619, "percentage": 9.93, "elapsed_time": "0:10:53", "remaining_time": "1:38:47", "throughput": 1054.13, "total_tokens": 689176} {"current_steps": 7650, "total_steps": 76960, "loss": 0.2671, "lr": 4.969464656964657e-05, "epoch": 1.988045738045738, "percentage": 9.94, "elapsed_time": "0:10:54", "remaining_time": "1:38:47", "throughput": 1054.17, "total_tokens": 689640} {"current_steps": 7655, "total_steps": 76960, "loss": 0.3715, "lr": 4.972713097713098e-05, "epoch": 1.9893451143451144, "percentage": 9.95, "elapsed_time": "0:10:54", "remaining_time": "1:38:46", "throughput": 1054.13, "total_tokens": 690056} {"current_steps": 7660, "total_steps": 76960, "loss": 0.1885, "lr": 4.9759615384615386e-05, "epoch": 1.9906444906444907, "percentage": 9.95, "elapsed_time": "0:10:55", "remaining_time": "1:38:46", "throughput": 1054.17, "total_tokens": 690520} {"current_steps": 7665, "total_steps": 76960, "loss": 0.1483, "lr": 4.9792099792099796e-05, "epoch": 1.991943866943867, "percentage": 9.96, "elapsed_time": "0:10:55", "remaining_time": "1:38:45", "throughput": 1054.23, "total_tokens": 691000} {"current_steps": 7670, "total_steps": 76960, "loss": 0.3273, "lr": 4.98245841995842e-05, "epoch": 1.9932432432432432, "percentage": 9.97, "elapsed_time": "0:10:55", "remaining_time": "1:38:45", "throughput": 1054.22, "total_tokens": 691432} {"current_steps": 7675, "total_steps": 76960, "loss": 0.2197, "lr": 4.985706860706861e-05, "epoch": 1.9945426195426195, "percentage": 9.97, "elapsed_time": "0:10:56", "remaining_time": "1:38:44", "throughput": 1054.23, "total_tokens": 691880} {"current_steps": 7680, "total_steps": 76960, "loss": 0.3314, "lr": 4.988955301455302e-05, "epoch": 1.995841995841996, "percentage": 9.98, "elapsed_time": "0:10:56", "remaining_time": "1:38:44", "throughput": 1054.22, "total_tokens": 692312} {"current_steps": 7685, "total_steps": 76960, "loss": 0.1706, "lr": 4.992203742203743e-05, "epoch": 1.997141372141372, "percentage": 9.99, "elapsed_time": "0:10:57", "remaining_time": "1:38:43", "throughput": 1054.26, "total_tokens": 692776} {"current_steps": 7690, "total_steps": 76960, "loss": 0.2496, "lr": 4.995452182952183e-05, "epoch": 1.9984407484407485, "percentage": 9.99, "elapsed_time": "0:10:57", "remaining_time": "1:38:42", "throughput": 1054.33, "total_tokens": 693256} {"current_steps": 7695, "total_steps": 76960, "loss": 0.3132, "lr": 4.998700623700624e-05, "epoch": 1.9997401247401247, "percentage": 10.0, "elapsed_time": "0:10:57", "remaining_time": "1:38:42", "throughput": 1054.36, "total_tokens": 693704} {"current_steps": 7696, "total_steps": 76960, "eval_loss": 0.24168933928012848, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:11:11", "remaining_time": "1:40:41", "throughput": 1033.51, "total_tokens": 693752} {"current_steps": 7700, "total_steps": 76960, "loss": 0.3253, "lr": 4.999999976856069e-05, "epoch": 2.001039501039501, "percentage": 10.01, "elapsed_time": "0:11:13", "remaining_time": "1:40:54", "throughput": 1031.22, "total_tokens": 694120} {"current_steps": 7705, "total_steps": 76960, "loss": 0.2705, "lr": 4.9999998354209355e-05, "epoch": 2.0023388773388775, "percentage": 10.01, "elapsed_time": "0:11:13", "remaining_time": "1:40:53", "throughput": 1031.21, "total_tokens": 694552} {"current_steps": 7710, "total_steps": 76960, "loss": 0.2336, "lr": 4.999999565408414e-05, "epoch": 2.0036382536382535, "percentage": 10.02, "elapsed_time": "0:11:13", "remaining_time": "1:40:53", "throughput": 1031.17, "total_tokens": 695000} {"current_steps": 7715, "total_steps": 76960, "loss": 0.2006, "lr": 4.999999166818521e-05, "epoch": 2.00493762993763, "percentage": 10.02, "elapsed_time": "0:11:14", "remaining_time": "1:40:53", "throughput": 1031.11, "total_tokens": 695400} {"current_steps": 7720, "total_steps": 76960, "loss": 0.3032, "lr": 4.999998639651274e-05, "epoch": 2.006237006237006, "percentage": 10.03, "elapsed_time": "0:11:14", "remaining_time": "1:40:52", "throughput": 1031.12, "total_tokens": 695848} {"current_steps": 7725, "total_steps": 76960, "loss": 0.2704, "lr": 4.999997983906703e-05, "epoch": 2.0075363825363826, "percentage": 10.04, "elapsed_time": "0:11:15", "remaining_time": "1:40:52", "throughput": 1031.14, "total_tokens": 696296} {"current_steps": 7730, "total_steps": 76960, "loss": 0.2609, "lr": 4.999997199584839e-05, "epoch": 2.008835758835759, "percentage": 10.04, "elapsed_time": "0:11:15", "remaining_time": "1:40:51", "throughput": 1031.16, "total_tokens": 696744} {"current_steps": 7735, "total_steps": 76960, "loss": 0.2254, "lr": 4.999996286685725e-05, "epoch": 2.010135135135135, "percentage": 10.05, "elapsed_time": "0:11:16", "remaining_time": "1:40:50", "throughput": 1031.18, "total_tokens": 697192} {"current_steps": 7740, "total_steps": 76960, "loss": 0.2215, "lr": 4.9999952452094055e-05, "epoch": 2.0114345114345116, "percentage": 10.06, "elapsed_time": "0:11:16", "remaining_time": "1:40:50", "throughput": 1031.2, "total_tokens": 697640} {"current_steps": 7745, "total_steps": 76960, "loss": 0.2143, "lr": 4.999994075155936e-05, "epoch": 2.0127338877338876, "percentage": 10.06, "elapsed_time": "0:11:16", "remaining_time": "1:40:49", "throughput": 1031.2, "total_tokens": 698072} {"current_steps": 7750, "total_steps": 76960, "loss": 0.3008, "lr": 4.999992776525375e-05, "epoch": 2.014033264033264, "percentage": 10.07, "elapsed_time": "0:11:17", "remaining_time": "1:40:49", "throughput": 1031.22, "total_tokens": 698520} {"current_steps": 7755, "total_steps": 76960, "loss": 0.2173, "lr": 4.999991349317791e-05, "epoch": 2.01533264033264, "percentage": 10.08, "elapsed_time": "0:11:17", "remaining_time": "1:40:48", "throughput": 1031.25, "total_tokens": 698968} {"current_steps": 7760, "total_steps": 76960, "loss": 0.2661, "lr": 4.9999897935332555e-05, "epoch": 2.0166320166320166, "percentage": 10.08, "elapsed_time": "0:11:18", "remaining_time": "1:40:47", "throughput": 1031.27, "total_tokens": 699416} {"current_steps": 7765, "total_steps": 76960, "loss": 0.2218, "lr": 4.9999881091718506e-05, "epoch": 2.017931392931393, "percentage": 10.09, "elapsed_time": "0:11:18", "remaining_time": "1:40:47", "throughput": 1031.33, "total_tokens": 699880} {"current_steps": 7770, "total_steps": 76960, "loss": 0.2493, "lr": 4.9999862962336606e-05, "epoch": 2.019230769230769, "percentage": 10.1, "elapsed_time": "0:11:19", "remaining_time": "1:40:46", "throughput": 1031.33, "total_tokens": 700312} {"current_steps": 7775, "total_steps": 76960, "loss": 0.2605, "lr": 4.999984354718781e-05, "epoch": 2.0205301455301456, "percentage": 10.1, "elapsed_time": "0:11:19", "remaining_time": "1:40:46", "throughput": 1031.33, "total_tokens": 700744} {"current_steps": 7780, "total_steps": 76960, "loss": 0.3015, "lr": 4.999982284627311e-05, "epoch": 2.0218295218295217, "percentage": 10.11, "elapsed_time": "0:11:19", "remaining_time": "1:40:45", "throughput": 1031.37, "total_tokens": 701208} {"current_steps": 7785, "total_steps": 76960, "loss": 0.2619, "lr": 4.999980085959356e-05, "epoch": 2.023128898128898, "percentage": 10.12, "elapsed_time": "0:11:20", "remaining_time": "1:40:44", "throughput": 1031.33, "total_tokens": 701608} {"current_steps": 7790, "total_steps": 76960, "loss": 0.2544, "lr": 4.9999777587150295e-05, "epoch": 2.024428274428274, "percentage": 10.12, "elapsed_time": "0:11:20", "remaining_time": "1:40:44", "throughput": 1031.44, "total_tokens": 702120} {"current_steps": 7795, "total_steps": 76960, "loss": 0.264, "lr": 4.999975302894452e-05, "epoch": 2.0257276507276507, "percentage": 10.13, "elapsed_time": "0:11:21", "remaining_time": "1:40:43", "throughput": 1031.46, "total_tokens": 702568} {"current_steps": 7800, "total_steps": 76960, "loss": 0.2507, "lr": 4.99997271849775e-05, "epoch": 2.027027027027027, "percentage": 10.14, "elapsed_time": "0:11:21", "remaining_time": "1:40:43", "throughput": 1031.51, "total_tokens": 703032} {"current_steps": 7805, "total_steps": 76960, "loss": 0.233, "lr": 4.9999700055250545e-05, "epoch": 2.0283264033264032, "percentage": 10.14, "elapsed_time": "0:11:21", "remaining_time": "1:40:42", "throughput": 1031.51, "total_tokens": 703464} {"current_steps": 7810, "total_steps": 76960, "loss": 0.3213, "lr": 4.9999671639765065e-05, "epoch": 2.0296257796257797, "percentage": 10.15, "elapsed_time": "0:11:22", "remaining_time": "1:40:41", "throughput": 1031.53, "total_tokens": 703912} {"current_steps": 7815, "total_steps": 76960, "loss": 0.2214, "lr": 4.999964193852252e-05, "epoch": 2.0309251559251558, "percentage": 10.15, "elapsed_time": "0:11:22", "remaining_time": "1:40:41", "throughput": 1031.55, "total_tokens": 704360} {"current_steps": 7820, "total_steps": 76960, "loss": 0.2578, "lr": 4.9999610951524445e-05, "epoch": 2.0322245322245323, "percentage": 10.16, "elapsed_time": "0:11:23", "remaining_time": "1:40:40", "throughput": 1031.55, "total_tokens": 704792} {"current_steps": 7825, "total_steps": 76960, "loss": 0.2617, "lr": 4.999957867877242e-05, "epoch": 2.0335239085239087, "percentage": 10.17, "elapsed_time": "0:11:23", "remaining_time": "1:40:40", "throughput": 1031.62, "total_tokens": 705272} {"current_steps": 7830, "total_steps": 76960, "loss": 0.2854, "lr": 4.9999545120268105e-05, "epoch": 2.034823284823285, "percentage": 10.17, "elapsed_time": "0:11:24", "remaining_time": "1:40:39", "throughput": 1031.6, "total_tokens": 705688} {"current_steps": 7835, "total_steps": 76960, "loss": 0.3052, "lr": 4.999951027601324e-05, "epoch": 2.0361226611226613, "percentage": 10.18, "elapsed_time": "0:11:24", "remaining_time": "1:40:38", "throughput": 1031.64, "total_tokens": 706152} {"current_steps": 7840, "total_steps": 76960, "loss": 0.3165, "lr": 4.99994741460096e-05, "epoch": 2.0374220374220373, "percentage": 10.19, "elapsed_time": "0:11:24", "remaining_time": "1:40:38", "throughput": 1031.74, "total_tokens": 706648} {"current_steps": 7845, "total_steps": 76960, "loss": 0.2882, "lr": 4.9999436730259053e-05, "epoch": 2.038721413721414, "percentage": 10.19, "elapsed_time": "0:11:25", "remaining_time": "1:40:37", "throughput": 1031.79, "total_tokens": 707112} {"current_steps": 7850, "total_steps": 76960, "loss": 0.2893, "lr": 4.999939802876352e-05, "epoch": 2.04002079002079, "percentage": 10.2, "elapsed_time": "0:11:25", "remaining_time": "1:40:37", "throughput": 1031.85, "total_tokens": 707592} {"current_steps": 7855, "total_steps": 76960, "loss": 0.2816, "lr": 4.9999358041525004e-05, "epoch": 2.0413201663201663, "percentage": 10.21, "elapsed_time": "0:11:26", "remaining_time": "1:40:36", "throughput": 1031.88, "total_tokens": 708040} {"current_steps": 7860, "total_steps": 76960, "loss": 0.2793, "lr": 4.999931676854554e-05, "epoch": 2.042619542619543, "percentage": 10.21, "elapsed_time": "0:11:26", "remaining_time": "1:40:36", "throughput": 1031.92, "total_tokens": 708504} {"current_steps": 7865, "total_steps": 76960, "loss": 0.2149, "lr": 4.999927420982726e-05, "epoch": 2.043918918918919, "percentage": 10.22, "elapsed_time": "0:11:27", "remaining_time": "1:40:35", "throughput": 1031.99, "total_tokens": 708984} {"current_steps": 7870, "total_steps": 76960, "loss": 0.2901, "lr": 4.999923036537236e-05, "epoch": 2.0452182952182953, "percentage": 10.23, "elapsed_time": "0:11:27", "remaining_time": "1:40:34", "throughput": 1032.04, "total_tokens": 709448} {"current_steps": 7875, "total_steps": 76960, "loss": 0.22, "lr": 4.999918523518309e-05, "epoch": 2.0465176715176714, "percentage": 10.23, "elapsed_time": "0:11:27", "remaining_time": "1:40:34", "throughput": 1032.13, "total_tokens": 709944} {"current_steps": 7880, "total_steps": 76960, "loss": 0.3173, "lr": 4.9999138819261764e-05, "epoch": 2.047817047817048, "percentage": 10.24, "elapsed_time": "0:11:28", "remaining_time": "1:40:33", "throughput": 1032.13, "total_tokens": 710376} {"current_steps": 7885, "total_steps": 76960, "loss": 0.2267, "lr": 4.999909111761078e-05, "epoch": 2.049116424116424, "percentage": 10.25, "elapsed_time": "0:11:28", "remaining_time": "1:40:33", "throughput": 1032.2, "total_tokens": 710856} {"current_steps": 7890, "total_steps": 76960, "loss": 0.251, "lr": 4.9999042130232585e-05, "epoch": 2.0504158004158004, "percentage": 10.25, "elapsed_time": "0:11:29", "remaining_time": "1:40:32", "throughput": 1032.23, "total_tokens": 711304} {"current_steps": 7895, "total_steps": 76960, "loss": 0.2325, "lr": 4.9998991857129704e-05, "epoch": 2.051715176715177, "percentage": 10.26, "elapsed_time": "0:11:29", "remaining_time": "1:40:31", "throughput": 1032.3, "total_tokens": 711784} {"current_steps": 7900, "total_steps": 76960, "loss": 0.1155, "lr": 4.999894029830472e-05, "epoch": 2.053014553014553, "percentage": 10.27, "elapsed_time": "0:11:29", "remaining_time": "1:40:31", "throughput": 1032.37, "total_tokens": 712264} {"current_steps": 7905, "total_steps": 76960, "loss": 0.2868, "lr": 4.999888745376028e-05, "epoch": 2.0543139293139294, "percentage": 10.27, "elapsed_time": "0:11:30", "remaining_time": "1:40:30", "throughput": 1032.41, "total_tokens": 712728} {"current_steps": 7910, "total_steps": 76960, "loss": 0.2141, "lr": 4.9998833323499104e-05, "epoch": 2.0556133056133055, "percentage": 10.28, "elapsed_time": "0:11:30", "remaining_time": "1:40:30", "throughput": 1032.46, "total_tokens": 713192} {"current_steps": 7915, "total_steps": 76960, "loss": 0.2864, "lr": 4.999877790752398e-05, "epoch": 2.056912681912682, "percentage": 10.28, "elapsed_time": "0:11:31", "remaining_time": "1:40:29", "throughput": 1032.51, "total_tokens": 713656} {"current_steps": 7920, "total_steps": 76960, "loss": 0.148, "lr": 4.999872120583775e-05, "epoch": 2.0582120582120584, "percentage": 10.29, "elapsed_time": "0:11:31", "remaining_time": "1:40:28", "throughput": 1032.51, "total_tokens": 714088} {"current_steps": 7925, "total_steps": 76960, "loss": 0.2181, "lr": 4.9998663218443344e-05, "epoch": 2.0595114345114345, "percentage": 10.3, "elapsed_time": "0:11:32", "remaining_time": "1:40:28", "throughput": 1032.48, "total_tokens": 714504} {"current_steps": 7930, "total_steps": 76960, "loss": 0.0836, "lr": 4.999860394534373e-05, "epoch": 2.060810810810811, "percentage": 10.3, "elapsed_time": "0:11:32", "remaining_time": "1:40:27", "throughput": 1032.57, "total_tokens": 715000} {"current_steps": 7935, "total_steps": 76960, "loss": 0.1456, "lr": 4.9998543386541964e-05, "epoch": 2.062110187110187, "percentage": 10.31, "elapsed_time": "0:11:32", "remaining_time": "1:40:27", "throughput": 1032.64, "total_tokens": 715480} {"current_steps": 7940, "total_steps": 76960, "loss": 0.4051, "lr": 4.9998481542041164e-05, "epoch": 2.0634095634095635, "percentage": 10.32, "elapsed_time": "0:11:33", "remaining_time": "1:40:26", "throughput": 1032.64, "total_tokens": 715912} {"current_steps": 7945, "total_steps": 76960, "loss": 0.2875, "lr": 4.99984184118445e-05, "epoch": 2.0647089397089395, "percentage": 10.32, "elapsed_time": "0:11:33", "remaining_time": "1:40:25", "throughput": 1032.66, "total_tokens": 716360} {"current_steps": 7950, "total_steps": 76960, "loss": 0.3367, "lr": 4.999835399595523e-05, "epoch": 2.066008316008316, "percentage": 10.33, "elapsed_time": "0:11:34", "remaining_time": "1:40:25", "throughput": 1032.73, "total_tokens": 716840} {"current_steps": 7955, "total_steps": 76960, "loss": 0.256, "lr": 4.999828829437666e-05, "epoch": 2.0673076923076925, "percentage": 10.34, "elapsed_time": "0:11:34", "remaining_time": "1:40:24", "throughput": 1032.73, "total_tokens": 717272} {"current_steps": 7960, "total_steps": 76960, "loss": 0.2473, "lr": 4.999822130711217e-05, "epoch": 2.0686070686070686, "percentage": 10.34, "elapsed_time": "0:11:34", "remaining_time": "1:40:24", "throughput": 1032.73, "total_tokens": 717704} {"current_steps": 7965, "total_steps": 76960, "loss": 0.2958, "lr": 4.99981530341652e-05, "epoch": 2.069906444906445, "percentage": 10.35, "elapsed_time": "0:11:35", "remaining_time": "1:40:23", "throughput": 1032.77, "total_tokens": 718168} {"current_steps": 7970, "total_steps": 76960, "loss": 0.2423, "lr": 4.999808347553927e-05, "epoch": 2.071205821205821, "percentage": 10.36, "elapsed_time": "0:11:35", "remaining_time": "1:40:22", "throughput": 1032.77, "total_tokens": 718600} {"current_steps": 7975, "total_steps": 76960, "loss": 0.3273, "lr": 4.999801263123796e-05, "epoch": 2.0725051975051976, "percentage": 10.36, "elapsed_time": "0:11:36", "remaining_time": "1:40:22", "throughput": 1032.84, "total_tokens": 719080} {"current_steps": 7980, "total_steps": 76960, "loss": 0.2272, "lr": 4.99979405012649e-05, "epoch": 2.0738045738045736, "percentage": 10.37, "elapsed_time": "0:11:36", "remaining_time": "1:40:21", "throughput": 1032.82, "total_tokens": 719496} {"current_steps": 7985, "total_steps": 76960, "loss": 0.2515, "lr": 4.9997867085623824e-05, "epoch": 2.07510395010395, "percentage": 10.38, "elapsed_time": "0:11:37", "remaining_time": "1:40:21", "throughput": 1032.86, "total_tokens": 719960} {"current_steps": 7990, "total_steps": 76960, "loss": 0.3196, "lr": 4.9997792384318475e-05, "epoch": 2.0764033264033266, "percentage": 10.38, "elapsed_time": "0:11:37", "remaining_time": "1:40:20", "throughput": 1032.89, "total_tokens": 720408} {"current_steps": 7995, "total_steps": 76960, "loss": 0.2823, "lr": 4.9997716397352725e-05, "epoch": 2.0777027027027026, "percentage": 10.39, "elapsed_time": "0:11:37", "remaining_time": "1:40:19", "throughput": 1032.91, "total_tokens": 720856} {"current_steps": 8000, "total_steps": 76960, "loss": 0.322, "lr": 4.9997639124730464e-05, "epoch": 2.079002079002079, "percentage": 10.4, "elapsed_time": "0:11:38", "remaining_time": "1:40:19", "throughput": 1032.91, "total_tokens": 721288} {"current_steps": 8005, "total_steps": 76960, "loss": 0.2745, "lr": 4.999756056645567e-05, "epoch": 2.080301455301455, "percentage": 10.4, "elapsed_time": "0:11:38", "remaining_time": "1:40:18", "throughput": 1032.93, "total_tokens": 721736} {"current_steps": 8010, "total_steps": 76960, "loss": 0.2846, "lr": 4.999748072253239e-05, "epoch": 2.0816008316008316, "percentage": 10.41, "elapsed_time": "0:11:39", "remaining_time": "1:40:18", "throughput": 1032.98, "total_tokens": 722200} {"current_steps": 8015, "total_steps": 76960, "loss": 0.2743, "lr": 4.999739959296471e-05, "epoch": 2.0829002079002077, "percentage": 10.41, "elapsed_time": "0:11:39", "remaining_time": "1:40:17", "throughput": 1032.98, "total_tokens": 722632} {"current_steps": 8020, "total_steps": 76960, "loss": 0.2262, "lr": 4.999731717775683e-05, "epoch": 2.084199584199584, "percentage": 10.42, "elapsed_time": "0:11:39", "remaining_time": "1:40:17", "throughput": 1032.95, "total_tokens": 723048} {"current_steps": 8025, "total_steps": 76960, "loss": 0.286, "lr": 4.9997233476912977e-05, "epoch": 2.0854989604989607, "percentage": 10.43, "elapsed_time": "0:11:40", "remaining_time": "1:40:16", "throughput": 1033.0, "total_tokens": 723512} {"current_steps": 8030, "total_steps": 76960, "loss": 0.2648, "lr": 4.999714849043745e-05, "epoch": 2.0867983367983367, "percentage": 10.43, "elapsed_time": "0:11:40", "remaining_time": "1:40:15", "throughput": 1033.02, "total_tokens": 723960} {"current_steps": 8035, "total_steps": 76960, "loss": 0.29, "lr": 4.9997062218334627e-05, "epoch": 2.088097713097713, "percentage": 10.44, "elapsed_time": "0:11:41", "remaining_time": "1:40:15", "throughput": 1033.03, "total_tokens": 724392} {"current_steps": 8040, "total_steps": 76960, "loss": 0.2637, "lr": 4.999697466060894e-05, "epoch": 2.0893970893970892, "percentage": 10.45, "elapsed_time": "0:11:41", "remaining_time": "1:40:14", "throughput": 1033.07, "total_tokens": 724856} {"current_steps": 8045, "total_steps": 76960, "loss": 0.3438, "lr": 4.9996885817264904e-05, "epoch": 2.0906964656964657, "percentage": 10.45, "elapsed_time": "0:11:42", "remaining_time": "1:40:14", "throughput": 1033.12, "total_tokens": 725320} {"current_steps": 8050, "total_steps": 76960, "loss": 0.2774, "lr": 4.999679568830707e-05, "epoch": 2.091995841995842, "percentage": 10.46, "elapsed_time": "0:11:42", "remaining_time": "1:40:13", "throughput": 1033.14, "total_tokens": 725768} {"current_steps": 8055, "total_steps": 76960, "loss": 0.2587, "lr": 4.999670427374009e-05, "epoch": 2.0932952182952183, "percentage": 10.47, "elapsed_time": "0:11:42", "remaining_time": "1:40:12", "throughput": 1033.17, "total_tokens": 726216} {"current_steps": 8060, "total_steps": 76960, "loss": 0.2907, "lr": 4.999661157356865e-05, "epoch": 2.0945945945945947, "percentage": 10.47, "elapsed_time": "0:11:43", "remaining_time": "1:40:12", "throughput": 1033.19, "total_tokens": 726664} {"current_steps": 8065, "total_steps": 76960, "loss": 0.1764, "lr": 4.999651758779754e-05, "epoch": 2.095893970893971, "percentage": 10.48, "elapsed_time": "0:11:43", "remaining_time": "1:40:11", "throughput": 1033.18, "total_tokens": 727096} {"current_steps": 8070, "total_steps": 76960, "loss": 0.2716, "lr": 4.999642231643157e-05, "epoch": 2.0971933471933473, "percentage": 10.49, "elapsed_time": "0:11:44", "remaining_time": "1:40:11", "throughput": 1033.21, "total_tokens": 727544} {"current_steps": 8075, "total_steps": 76960, "loss": 0.2598, "lr": 4.999632575947565e-05, "epoch": 2.0984927234927233, "percentage": 10.49, "elapsed_time": "0:11:44", "remaining_time": "1:40:10", "throughput": 1033.28, "total_tokens": 728024} {"current_steps": 8080, "total_steps": 76960, "loss": 0.2915, "lr": 4.999622791693475e-05, "epoch": 2.0997920997921, "percentage": 10.5, "elapsed_time": "0:11:44", "remaining_time": "1:40:09", "throughput": 1033.27, "total_tokens": 728456} {"current_steps": 8085, "total_steps": 76960, "loss": 0.3096, "lr": 4.999612878881389e-05, "epoch": 2.1010914760914763, "percentage": 10.51, "elapsed_time": "0:11:45", "remaining_time": "1:40:09", "throughput": 1033.31, "total_tokens": 728920} {"current_steps": 8090, "total_steps": 76960, "loss": 0.2515, "lr": 4.999602837511818e-05, "epoch": 2.1023908523908523, "percentage": 10.51, "elapsed_time": "0:11:45", "remaining_time": "1:40:08", "throughput": 1033.34, "total_tokens": 729368} {"current_steps": 8095, "total_steps": 76960, "loss": 0.261, "lr": 4.9995926675852784e-05, "epoch": 2.103690228690229, "percentage": 10.52, "elapsed_time": "0:11:46", "remaining_time": "1:40:08", "throughput": 1033.38, "total_tokens": 729832} {"current_steps": 8100, "total_steps": 76960, "loss": 0.3459, "lr": 4.9995823691022925e-05, "epoch": 2.104989604989605, "percentage": 10.52, "elapsed_time": "0:11:46", "remaining_time": "1:40:07", "throughput": 1033.42, "total_tokens": 730296} {"current_steps": 8105, "total_steps": 76960, "loss": 0.2285, "lr": 4.999571942063391e-05, "epoch": 2.1062889812889813, "percentage": 10.53, "elapsed_time": "0:11:47", "remaining_time": "1:40:07", "throughput": 1033.46, "total_tokens": 730760} {"current_steps": 8110, "total_steps": 76960, "loss": 0.2034, "lr": 4.999561386469109e-05, "epoch": 2.1075883575883574, "percentage": 10.54, "elapsed_time": "0:11:47", "remaining_time": "1:40:06", "throughput": 1033.51, "total_tokens": 731224} {"current_steps": 8115, "total_steps": 76960, "loss": 0.2444, "lr": 4.99955070231999e-05, "epoch": 2.108887733887734, "percentage": 10.54, "elapsed_time": "0:11:47", "remaining_time": "1:40:05", "throughput": 1033.55, "total_tokens": 731688} {"current_steps": 8120, "total_steps": 76960, "loss": 0.2494, "lr": 4.999539889616583e-05, "epoch": 2.1101871101871104, "percentage": 10.55, "elapsed_time": "0:11:48", "remaining_time": "1:40:05", "throughput": 1033.53, "total_tokens": 732104} {"current_steps": 8125, "total_steps": 76960, "loss": 0.2189, "lr": 4.9995289483594456e-05, "epoch": 2.1114864864864864, "percentage": 10.56, "elapsed_time": "0:11:48", "remaining_time": "1:40:04", "throughput": 1033.58, "total_tokens": 732568} {"current_steps": 8130, "total_steps": 76960, "loss": 0.3214, "lr": 4.9995178785491394e-05, "epoch": 2.112785862785863, "percentage": 10.56, "elapsed_time": "0:11:49", "remaining_time": "1:40:04", "throughput": 1033.7, "total_tokens": 733080} {"current_steps": 8135, "total_steps": 76960, "loss": 0.3081, "lr": 4.9995066801862326e-05, "epoch": 2.114085239085239, "percentage": 10.57, "elapsed_time": "0:11:49", "remaining_time": "1:40:03", "throughput": 1033.7, "total_tokens": 733512} {"current_steps": 8140, "total_steps": 76960, "loss": 0.2255, "lr": 4.999495353271303e-05, "epoch": 2.1153846153846154, "percentage": 10.58, "elapsed_time": "0:11:50", "remaining_time": "1:40:02", "throughput": 1033.73, "total_tokens": 733960} {"current_steps": 8145, "total_steps": 76960, "loss": 0.1927, "lr": 4.999483897804933e-05, "epoch": 2.116683991683992, "percentage": 10.58, "elapsed_time": "0:11:50", "remaining_time": "1:40:02", "throughput": 1033.78, "total_tokens": 734424} {"current_steps": 8150, "total_steps": 76960, "loss": 0.257, "lr": 4.99947231378771e-05, "epoch": 2.117983367983368, "percentage": 10.59, "elapsed_time": "0:11:50", "remaining_time": "1:40:01", "throughput": 1033.85, "total_tokens": 734904} {"current_steps": 8155, "total_steps": 76960, "loss": 0.2116, "lr": 4.999460601220232e-05, "epoch": 2.1192827442827444, "percentage": 10.6, "elapsed_time": "0:11:51", "remaining_time": "1:40:00", "throughput": 1033.9, "total_tokens": 735368} {"current_steps": 8160, "total_steps": 76960, "loss": 0.2743, "lr": 4.9994487601031006e-05, "epoch": 2.1205821205821205, "percentage": 10.6, "elapsed_time": "0:11:51", "remaining_time": "1:40:00", "throughput": 1033.95, "total_tokens": 735832} {"current_steps": 8165, "total_steps": 76960, "loss": 0.2126, "lr": 4.999436790436924e-05, "epoch": 2.121881496881497, "percentage": 10.61, "elapsed_time": "0:11:52", "remaining_time": "1:39:59", "throughput": 1033.95, "total_tokens": 736264} {"current_steps": 8170, "total_steps": 76960, "loss": 0.3183, "lr": 4.999424692222319e-05, "epoch": 2.123180873180873, "percentage": 10.62, "elapsed_time": "0:11:52", "remaining_time": "1:39:59", "throughput": 1033.99, "total_tokens": 736728} {"current_steps": 8175, "total_steps": 76960, "loss": 0.2199, "lr": 4.9994124654599064e-05, "epoch": 2.1244802494802495, "percentage": 10.62, "elapsed_time": "0:11:52", "remaining_time": "1:39:58", "throughput": 1033.99, "total_tokens": 737160} {"current_steps": 8180, "total_steps": 76960, "loss": 0.3564, "lr": 4.999400110150316e-05, "epoch": 2.125779625779626, "percentage": 10.63, "elapsed_time": "0:11:53", "remaining_time": "1:39:58", "throughput": 1034.06, "total_tokens": 737640} {"current_steps": 8185, "total_steps": 76960, "loss": 0.2239, "lr": 4.999387626294183e-05, "epoch": 2.127079002079002, "percentage": 10.64, "elapsed_time": "0:11:53", "remaining_time": "1:39:57", "throughput": 1034.11, "total_tokens": 738104} {"current_steps": 8190, "total_steps": 76960, "loss": 0.2325, "lr": 4.99937501389215e-05, "epoch": 2.1283783783783785, "percentage": 10.64, "elapsed_time": "0:11:54", "remaining_time": "1:39:56", "throughput": 1034.11, "total_tokens": 738536} {"current_steps": 8195, "total_steps": 76960, "loss": 0.2446, "lr": 4.9993622729448656e-05, "epoch": 2.1296777546777546, "percentage": 10.65, "elapsed_time": "0:11:54", "remaining_time": "1:39:56", "throughput": 1034.06, "total_tokens": 738936} {"current_steps": 8200, "total_steps": 76960, "loss": 0.2435, "lr": 4.9993494034529846e-05, "epoch": 2.130977130977131, "percentage": 10.65, "elapsed_time": "0:11:55", "remaining_time": "1:39:55", "throughput": 1034.2, "total_tokens": 739464} {"current_steps": 8205, "total_steps": 76960, "loss": 0.2161, "lr": 4.999336405417169e-05, "epoch": 2.132276507276507, "percentage": 10.66, "elapsed_time": "0:11:55", "remaining_time": "1:39:55", "throughput": 1034.2, "total_tokens": 739896} {"current_steps": 8210, "total_steps": 76960, "loss": 0.2146, "lr": 4.999323278838087e-05, "epoch": 2.1335758835758836, "percentage": 10.67, "elapsed_time": "0:11:55", "remaining_time": "1:39:54", "throughput": 1034.26, "total_tokens": 740376} {"current_steps": 8215, "total_steps": 76960, "loss": 0.2843, "lr": 4.9993100237164144e-05, "epoch": 2.13487525987526, "percentage": 10.67, "elapsed_time": "0:11:56", "remaining_time": "1:39:53", "throughput": 1034.33, "total_tokens": 740856} {"current_steps": 8220, "total_steps": 76960, "loss": 0.3624, "lr": 4.999296640052832e-05, "epoch": 2.136174636174636, "percentage": 10.68, "elapsed_time": "0:11:56", "remaining_time": "1:39:53", "throughput": 1034.38, "total_tokens": 741320} {"current_steps": 8225, "total_steps": 76960, "loss": 0.2201, "lr": 4.999283127848029e-05, "epoch": 2.1374740124740126, "percentage": 10.69, "elapsed_time": "0:11:57", "remaining_time": "1:39:52", "throughput": 1034.41, "total_tokens": 741768} {"current_steps": 8230, "total_steps": 76960, "loss": 0.2664, "lr": 4.9992694871027e-05, "epoch": 2.1387733887733886, "percentage": 10.69, "elapsed_time": "0:11:57", "remaining_time": "1:39:52", "throughput": 1034.43, "total_tokens": 742216} {"current_steps": 8235, "total_steps": 76960, "loss": 0.266, "lr": 4.999255717817547e-05, "epoch": 2.140072765072765, "percentage": 10.7, "elapsed_time": "0:11:57", "remaining_time": "1:39:51", "throughput": 1034.41, "total_tokens": 742632} {"current_steps": 8240, "total_steps": 76960, "loss": 0.2329, "lr": 4.999241819993277e-05, "epoch": 2.141372141372141, "percentage": 10.71, "elapsed_time": "0:11:58", "remaining_time": "1:39:50", "throughput": 1034.44, "total_tokens": 743080} {"current_steps": 8245, "total_steps": 76960, "loss": 0.3015, "lr": 4.999227793630606e-05, "epoch": 2.1426715176715176, "percentage": 10.71, "elapsed_time": "0:11:58", "remaining_time": "1:39:50", "throughput": 1034.51, "total_tokens": 743560} {"current_steps": 8250, "total_steps": 76960, "loss": 0.2581, "lr": 4.999213638730255e-05, "epoch": 2.143970893970894, "percentage": 10.72, "elapsed_time": "0:11:59", "remaining_time": "1:39:49", "throughput": 1034.53, "total_tokens": 744008} {"current_steps": 8255, "total_steps": 76960, "loss": 0.2576, "lr": 4.9991993552929514e-05, "epoch": 2.14527027027027, "percentage": 10.73, "elapsed_time": "0:11:59", "remaining_time": "1:39:49", "throughput": 1034.56, "total_tokens": 744456} {"current_steps": 8260, "total_steps": 76960, "loss": 0.2457, "lr": 4.999184943319432e-05, "epoch": 2.1465696465696467, "percentage": 10.73, "elapsed_time": "0:12:00", "remaining_time": "1:39:48", "throughput": 1034.55, "total_tokens": 744888} {"current_steps": 8265, "total_steps": 76960, "loss": 0.218, "lr": 4.9991704028104345e-05, "epoch": 2.1478690228690227, "percentage": 10.74, "elapsed_time": "0:12:00", "remaining_time": "1:39:47", "throughput": 1034.63, "total_tokens": 745384} {"current_steps": 8270, "total_steps": 76960, "loss": 0.3358, "lr": 4.9991557337667096e-05, "epoch": 2.149168399168399, "percentage": 10.75, "elapsed_time": "0:12:00", "remaining_time": "1:39:47", "throughput": 1034.62, "total_tokens": 745816} {"current_steps": 8275, "total_steps": 76960, "loss": 0.2913, "lr": 4.99914093618901e-05, "epoch": 2.1504677754677752, "percentage": 10.75, "elapsed_time": "0:12:01", "remaining_time": "1:39:46", "throughput": 1034.63, "total_tokens": 746264} {"current_steps": 8280, "total_steps": 76960, "loss": 0.2917, "lr": 4.999126010078098e-05, "epoch": 2.1517671517671517, "percentage": 10.76, "elapsed_time": "0:12:01", "remaining_time": "1:39:46", "throughput": 1034.57, "total_tokens": 746664} {"current_steps": 8285, "total_steps": 76960, "loss": 0.279, "lr": 4.99911095543474e-05, "epoch": 2.153066528066528, "percentage": 10.77, "elapsed_time": "0:12:02", "remaining_time": "1:39:45", "throughput": 1034.61, "total_tokens": 747128} {"current_steps": 8290, "total_steps": 76960, "loss": 0.2901, "lr": 4.999095772259712e-05, "epoch": 2.1543659043659042, "percentage": 10.77, "elapsed_time": "0:12:02", "remaining_time": "1:39:45", "throughput": 1034.66, "total_tokens": 747608} {"current_steps": 8295, "total_steps": 76960, "loss": 0.268, "lr": 4.999080460553793e-05, "epoch": 2.1556652806652807, "percentage": 10.78, "elapsed_time": "0:12:02", "remaining_time": "1:39:44", "throughput": 1034.66, "total_tokens": 748040} {"current_steps": 8300, "total_steps": 76960, "loss": 0.2531, "lr": 4.9990650203177724e-05, "epoch": 2.156964656964657, "percentage": 10.78, "elapsed_time": "0:12:03", "remaining_time": "1:39:44", "throughput": 1034.64, "total_tokens": 748456} {"current_steps": 8305, "total_steps": 76960, "loss": 0.2568, "lr": 4.999049451552443e-05, "epoch": 2.1582640332640333, "percentage": 10.79, "elapsed_time": "0:12:03", "remaining_time": "1:39:43", "throughput": 1034.66, "total_tokens": 748904} {"current_steps": 8310, "total_steps": 76960, "loss": 0.1674, "lr": 4.999033754258605e-05, "epoch": 2.1595634095634098, "percentage": 10.8, "elapsed_time": "0:12:04", "remaining_time": "1:39:43", "throughput": 1034.72, "total_tokens": 749384} {"current_steps": 8315, "total_steps": 76960, "loss": 0.2575, "lr": 4.9990179284370675e-05, "epoch": 2.160862785862786, "percentage": 10.8, "elapsed_time": "0:12:04", "remaining_time": "1:39:42", "throughput": 1034.77, "total_tokens": 749848} {"current_steps": 8320, "total_steps": 76960, "loss": 0.2577, "lr": 4.999001974088644e-05, "epoch": 2.1621621621621623, "percentage": 10.81, "elapsed_time": "0:12:05", "remaining_time": "1:39:41", "throughput": 1034.79, "total_tokens": 750296} {"current_steps": 8325, "total_steps": 76960, "loss": 0.2867, "lr": 4.998985891214153e-05, "epoch": 2.1634615384615383, "percentage": 10.82, "elapsed_time": "0:12:05", "remaining_time": "1:39:41", "throughput": 1034.8, "total_tokens": 750744} {"current_steps": 8330, "total_steps": 76960, "loss": 0.3342, "lr": 4.998969679814424e-05, "epoch": 2.164760914760915, "percentage": 10.82, "elapsed_time": "0:12:05", "remaining_time": "1:39:40", "throughput": 1034.87, "total_tokens": 751224} {"current_steps": 8335, "total_steps": 76960, "loss": 0.251, "lr": 4.99895333989029e-05, "epoch": 2.166060291060291, "percentage": 10.83, "elapsed_time": "0:12:06", "remaining_time": "1:39:40", "throughput": 1034.91, "total_tokens": 751688} {"current_steps": 8340, "total_steps": 76960, "loss": 0.2993, "lr": 4.998936871442591e-05, "epoch": 2.1673596673596673, "percentage": 10.84, "elapsed_time": "0:12:06", "remaining_time": "1:39:39", "throughput": 1034.96, "total_tokens": 752152} {"current_steps": 8345, "total_steps": 76960, "loss": 0.2766, "lr": 4.998920274472175e-05, "epoch": 2.168659043659044, "percentage": 10.84, "elapsed_time": "0:12:07", "remaining_time": "1:39:38", "throughput": 1035.02, "total_tokens": 752632} {"current_steps": 8350, "total_steps": 76960, "loss": 0.2558, "lr": 4.9989035489798944e-05, "epoch": 2.16995841995842, "percentage": 10.85, "elapsed_time": "0:12:07", "remaining_time": "1:39:38", "throughput": 1035.07, "total_tokens": 753096} {"current_steps": 8355, "total_steps": 76960, "loss": 0.2318, "lr": 4.9988866949666105e-05, "epoch": 2.1712577962577964, "percentage": 10.86, "elapsed_time": "0:12:08", "remaining_time": "1:39:37", "throughput": 1035.09, "total_tokens": 753544} {"current_steps": 8360, "total_steps": 76960, "loss": 0.2247, "lr": 4.99886971243319e-05, "epoch": 2.1725571725571724, "percentage": 10.86, "elapsed_time": "0:12:08", "remaining_time": "1:39:37", "throughput": 1035.11, "total_tokens": 753992} {"current_steps": 8365, "total_steps": 76960, "loss": 0.3085, "lr": 4.998852601380504e-05, "epoch": 2.173856548856549, "percentage": 10.87, "elapsed_time": "0:12:08", "remaining_time": "1:39:36", "throughput": 1035.15, "total_tokens": 754456} {"current_steps": 8370, "total_steps": 76960, "loss": 0.302, "lr": 4.998835361809436e-05, "epoch": 2.1751559251559254, "percentage": 10.88, "elapsed_time": "0:12:09", "remaining_time": "1:39:36", "throughput": 1035.2, "total_tokens": 754920} {"current_steps": 8375, "total_steps": 76960, "loss": 0.3243, "lr": 4.9988179937208704e-05, "epoch": 2.1764553014553014, "percentage": 10.88, "elapsed_time": "0:12:09", "remaining_time": "1:39:35", "throughput": 1035.19, "total_tokens": 755352} {"current_steps": 8380, "total_steps": 76960, "loss": 0.303, "lr": 4.998800497115701e-05, "epoch": 2.177754677754678, "percentage": 10.89, "elapsed_time": "0:12:10", "remaining_time": "1:39:34", "throughput": 1035.19, "total_tokens": 755784} {"current_steps": 8385, "total_steps": 76960, "loss": 0.2858, "lr": 4.9987828719948284e-05, "epoch": 2.179054054054054, "percentage": 10.9, "elapsed_time": "0:12:10", "remaining_time": "1:39:34", "throughput": 1035.21, "total_tokens": 756232} {"current_steps": 8390, "total_steps": 76960, "loss": 0.2843, "lr": 4.9987651183591574e-05, "epoch": 2.1803534303534304, "percentage": 10.9, "elapsed_time": "0:12:10", "remaining_time": "1:39:33", "throughput": 1035.28, "total_tokens": 756712} {"current_steps": 8395, "total_steps": 76960, "loss": 0.2742, "lr": 4.998747236209603e-05, "epoch": 2.1816528066528065, "percentage": 10.91, "elapsed_time": "0:12:11", "remaining_time": "1:39:33", "throughput": 1035.34, "total_tokens": 757192} {"current_steps": 8400, "total_steps": 76960, "loss": 0.2595, "lr": 4.998729225547085e-05, "epoch": 2.182952182952183, "percentage": 10.91, "elapsed_time": "0:12:11", "remaining_time": "1:39:32", "throughput": 1035.41, "total_tokens": 757672} {"current_steps": 8405, "total_steps": 76960, "loss": 0.2948, "lr": 4.998711086372527e-05, "epoch": 2.1842515592515594, "percentage": 10.92, "elapsed_time": "0:12:12", "remaining_time": "1:39:31", "throughput": 1035.48, "total_tokens": 758152} {"current_steps": 8410, "total_steps": 76960, "loss": 0.3009, "lr": 4.9986928186868645e-05, "epoch": 2.1855509355509355, "percentage": 10.93, "elapsed_time": "0:12:12", "remaining_time": "1:39:31", "throughput": 1035.5, "total_tokens": 758600} {"current_steps": 8415, "total_steps": 76960, "loss": 0.254, "lr": 4.998674422491036e-05, "epoch": 2.186850311850312, "percentage": 10.93, "elapsed_time": "0:12:13", "remaining_time": "1:39:30", "throughput": 1035.57, "total_tokens": 759080} {"current_steps": 8420, "total_steps": 76960, "loss": 0.2365, "lr": 4.998655897785989e-05, "epoch": 2.188149688149688, "percentage": 10.94, "elapsed_time": "0:12:13", "remaining_time": "1:39:30", "throughput": 1035.59, "total_tokens": 759528} {"current_steps": 8425, "total_steps": 76960, "loss": 0.2789, "lr": 4.998637244572674e-05, "epoch": 2.1894490644490645, "percentage": 10.95, "elapsed_time": "0:12:13", "remaining_time": "1:39:29", "throughput": 1035.61, "total_tokens": 759976} {"current_steps": 8430, "total_steps": 76960, "loss": 0.2497, "lr": 4.998618462852051e-05, "epoch": 2.1907484407484406, "percentage": 10.95, "elapsed_time": "0:12:14", "remaining_time": "1:39:29", "throughput": 1035.61, "total_tokens": 760408} {"current_steps": 8435, "total_steps": 76960, "loss": 0.2135, "lr": 4.9985995526250876e-05, "epoch": 2.192047817047817, "percentage": 10.96, "elapsed_time": "0:12:14", "remaining_time": "1:39:28", "throughput": 1035.63, "total_tokens": 760856} {"current_steps": 8440, "total_steps": 76960, "loss": 0.2942, "lr": 4.998580513892754e-05, "epoch": 2.1933471933471935, "percentage": 10.97, "elapsed_time": "0:12:15", "remaining_time": "1:39:27", "throughput": 1035.71, "total_tokens": 761352} {"current_steps": 8445, "total_steps": 76960, "loss": 0.227, "lr": 4.998561346656031e-05, "epoch": 2.1946465696465696, "percentage": 10.97, "elapsed_time": "0:12:15", "remaining_time": "1:39:27", "throughput": 1035.75, "total_tokens": 761816} {"current_steps": 8450, "total_steps": 76960, "loss": 0.2269, "lr": 4.998542050915904e-05, "epoch": 2.195945945945946, "percentage": 10.98, "elapsed_time": "0:12:15", "remaining_time": "1:39:26", "throughput": 1035.79, "total_tokens": 762280} {"current_steps": 8455, "total_steps": 76960, "loss": 0.1587, "lr": 4.9985226266733645e-05, "epoch": 2.197245322245322, "percentage": 10.99, "elapsed_time": "0:12:16", "remaining_time": "1:39:26", "throughput": 1035.77, "total_tokens": 762696} {"current_steps": 8460, "total_steps": 76960, "loss": 0.33, "lr": 4.9985030739294136e-05, "epoch": 2.1985446985446986, "percentage": 10.99, "elapsed_time": "0:12:16", "remaining_time": "1:39:25", "throughput": 1035.81, "total_tokens": 763160} {"current_steps": 8465, "total_steps": 76960, "loss": 0.2294, "lr": 4.998483392685055e-05, "epoch": 2.1998440748440746, "percentage": 11.0, "elapsed_time": "0:12:17", "remaining_time": "1:39:25", "throughput": 1035.87, "total_tokens": 763640} {"current_steps": 8470, "total_steps": 76960, "loss": 0.2586, "lr": 4.998463582941302e-05, "epoch": 2.201143451143451, "percentage": 11.01, "elapsed_time": "0:12:17", "remaining_time": "1:39:24", "throughput": 1035.89, "total_tokens": 764088} {"current_steps": 8475, "total_steps": 76960, "loss": 0.1808, "lr": 4.998443644699172e-05, "epoch": 2.2024428274428276, "percentage": 11.01, "elapsed_time": "0:12:18", "remaining_time": "1:39:23", "throughput": 1035.9, "total_tokens": 764536} {"current_steps": 8480, "total_steps": 76960, "loss": 0.288, "lr": 4.9984235779596925e-05, "epoch": 2.2037422037422036, "percentage": 11.02, "elapsed_time": "0:12:18", "remaining_time": "1:39:23", "throughput": 1035.92, "total_tokens": 764984} {"current_steps": 8485, "total_steps": 76960, "loss": 0.2898, "lr": 4.9984033827238944e-05, "epoch": 2.20504158004158, "percentage": 11.03, "elapsed_time": "0:12:18", "remaining_time": "1:39:22", "throughput": 1035.92, "total_tokens": 765416} {"current_steps": 8490, "total_steps": 76960, "loss": 0.2961, "lr": 4.998383058992817e-05, "epoch": 2.206340956340956, "percentage": 11.03, "elapsed_time": "0:12:19", "remaining_time": "1:39:22", "throughput": 1035.92, "total_tokens": 765848} {"current_steps": 8495, "total_steps": 76960, "loss": 0.2076, "lr": 4.998362606767504e-05, "epoch": 2.2076403326403327, "percentage": 11.04, "elapsed_time": "0:12:19", "remaining_time": "1:39:21", "throughput": 1035.96, "total_tokens": 766312} {"current_steps": 8500, "total_steps": 76960, "loss": 0.2628, "lr": 4.998342026049009e-05, "epoch": 2.208939708939709, "percentage": 11.04, "elapsed_time": "0:12:20", "remaining_time": "1:39:21", "throughput": 1035.98, "total_tokens": 766760} {"current_steps": 8505, "total_steps": 76960, "loss": 0.217, "lr": 4.998321316838389e-05, "epoch": 2.210239085239085, "percentage": 11.05, "elapsed_time": "0:12:20", "remaining_time": "1:39:20", "throughput": 1035.95, "total_tokens": 767176} {"current_steps": 8510, "total_steps": 76960, "loss": 0.2986, "lr": 4.9983004791367104e-05, "epoch": 2.2115384615384617, "percentage": 11.06, "elapsed_time": "0:12:20", "remaining_time": "1:39:19", "throughput": 1036.04, "total_tokens": 767672} {"current_steps": 8515, "total_steps": 76960, "loss": 0.2582, "lr": 4.9982795129450444e-05, "epoch": 2.2128378378378377, "percentage": 11.06, "elapsed_time": "0:12:21", "remaining_time": "1:39:19", "throughput": 1036.06, "total_tokens": 768120} {"current_steps": 8520, "total_steps": 76960, "loss": 0.2176, "lr": 4.998258418264469e-05, "epoch": 2.214137214137214, "percentage": 11.07, "elapsed_time": "0:12:21", "remaining_time": "1:39:18", "throughput": 1036.17, "total_tokens": 768632} {"current_steps": 8525, "total_steps": 76960, "loss": 0.2231, "lr": 4.99823719509607e-05, "epoch": 2.2154365904365902, "percentage": 11.08, "elapsed_time": "0:12:22", "remaining_time": "1:39:18", "throughput": 1036.25, "total_tokens": 769128} {"current_steps": 8530, "total_steps": 76960, "loss": 0.1989, "lr": 4.9982158434409374e-05, "epoch": 2.2167359667359667, "percentage": 11.08, "elapsed_time": "0:12:22", "remaining_time": "1:39:17", "throughput": 1036.32, "total_tokens": 769608} {"current_steps": 8535, "total_steps": 76960, "loss": 0.3446, "lr": 4.9981943633001715e-05, "epoch": 2.218035343035343, "percentage": 11.09, "elapsed_time": "0:12:23", "remaining_time": "1:39:17", "throughput": 1036.36, "total_tokens": 770072} {"current_steps": 8540, "total_steps": 76960, "loss": 0.2678, "lr": 4.998172754674876e-05, "epoch": 2.2193347193347193, "percentage": 11.1, "elapsed_time": "0:12:23", "remaining_time": "1:39:16", "throughput": 1036.34, "total_tokens": 770488} {"current_steps": 8545, "total_steps": 76960, "loss": 0.223, "lr": 4.9981510175661606e-05, "epoch": 2.2206340956340958, "percentage": 11.1, "elapsed_time": "0:12:23", "remaining_time": "1:39:15", "throughput": 1036.34, "total_tokens": 770920} {"current_steps": 8550, "total_steps": 76960, "loss": 0.2275, "lr": 4.998129151975146e-05, "epoch": 2.221933471933472, "percentage": 11.11, "elapsed_time": "0:12:24", "remaining_time": "1:39:15", "throughput": 1036.38, "total_tokens": 771384} {"current_steps": 8555, "total_steps": 76960, "loss": 0.174, "lr": 4.998107157902955e-05, "epoch": 2.2232328482328483, "percentage": 11.12, "elapsed_time": "0:12:24", "remaining_time": "1:39:14", "throughput": 1036.4, "total_tokens": 771832} {"current_steps": 8560, "total_steps": 76960, "loss": 0.2658, "lr": 4.998085035350719e-05, "epoch": 2.2245322245322248, "percentage": 11.12, "elapsed_time": "0:12:25", "remaining_time": "1:39:14", "throughput": 1036.4, "total_tokens": 772264} {"current_steps": 8565, "total_steps": 76960, "loss": 0.2568, "lr": 4.9980627843195774e-05, "epoch": 2.225831600831601, "percentage": 11.13, "elapsed_time": "0:12:25", "remaining_time": "1:39:13", "throughput": 1036.42, "total_tokens": 772712} {"current_steps": 8570, "total_steps": 76960, "loss": 0.2622, "lr": 4.998040404810672e-05, "epoch": 2.2271309771309773, "percentage": 11.14, "elapsed_time": "0:12:25", "remaining_time": "1:39:13", "throughput": 1036.44, "total_tokens": 773160} {"current_steps": 8575, "total_steps": 76960, "loss": 0.3098, "lr": 4.9980178968251554e-05, "epoch": 2.2284303534303533, "percentage": 11.14, "elapsed_time": "0:12:26", "remaining_time": "1:39:12", "throughput": 1036.39, "total_tokens": 773560} {"current_steps": 8580, "total_steps": 76960, "loss": 0.2944, "lr": 4.9979952603641846e-05, "epoch": 2.22972972972973, "percentage": 11.15, "elapsed_time": "0:12:26", "remaining_time": "1:39:11", "throughput": 1036.36, "total_tokens": 773976} {"current_steps": 8585, "total_steps": 76960, "loss": 0.2893, "lr": 4.9979724954289244e-05, "epoch": 2.231029106029106, "percentage": 11.16, "elapsed_time": "0:12:27", "remaining_time": "1:39:11", "throughput": 1036.41, "total_tokens": 774440} {"current_steps": 8590, "total_steps": 76960, "loss": 0.2748, "lr": 4.997949602020545e-05, "epoch": 2.2323284823284824, "percentage": 11.16, "elapsed_time": "0:12:27", "remaining_time": "1:39:10", "throughput": 1036.43, "total_tokens": 774888} {"current_steps": 8595, "total_steps": 76960, "loss": 0.2453, "lr": 4.997926580140225e-05, "epoch": 2.233627858627859, "percentage": 11.17, "elapsed_time": "0:12:28", "remaining_time": "1:39:10", "throughput": 1036.41, "total_tokens": 775304} {"current_steps": 8600, "total_steps": 76960, "loss": 0.3003, "lr": 4.997903429789147e-05, "epoch": 2.234927234927235, "percentage": 11.17, "elapsed_time": "0:12:28", "remaining_time": "1:39:09", "throughput": 1036.43, "total_tokens": 775752} {"current_steps": 8605, "total_steps": 76960, "loss": 0.2272, "lr": 4.997880150968502e-05, "epoch": 2.2362266112266114, "percentage": 11.18, "elapsed_time": "0:12:28", "remaining_time": "1:39:09", "throughput": 1036.41, "total_tokens": 776168} {"current_steps": 8610, "total_steps": 76960, "loss": 0.2956, "lr": 4.997856743679487e-05, "epoch": 2.2375259875259874, "percentage": 11.19, "elapsed_time": "0:12:29", "remaining_time": "1:39:08", "throughput": 1036.39, "total_tokens": 776584} {"current_steps": 8615, "total_steps": 76960, "loss": 0.2858, "lr": 4.997833207923308e-05, "epoch": 2.238825363825364, "percentage": 11.19, "elapsed_time": "0:12:29", "remaining_time": "1:39:07", "throughput": 1036.42, "total_tokens": 777048} {"current_steps": 8620, "total_steps": 76960, "loss": 0.3115, "lr": 4.997809543701173e-05, "epoch": 2.24012474012474, "percentage": 11.2, "elapsed_time": "0:12:30", "remaining_time": "1:39:07", "throughput": 1036.51, "total_tokens": 777544} {"current_steps": 8625, "total_steps": 76960, "loss": 0.2159, "lr": 4.9977857510143e-05, "epoch": 2.2414241164241164, "percentage": 11.21, "elapsed_time": "0:12:30", "remaining_time": "1:39:06", "throughput": 1036.48, "total_tokens": 777960} {"current_steps": 8630, "total_steps": 76960, "loss": 0.2799, "lr": 4.9977618298639114e-05, "epoch": 2.242723492723493, "percentage": 11.21, "elapsed_time": "0:12:30", "remaining_time": "1:39:06", "throughput": 1036.52, "total_tokens": 778424} {"current_steps": 8635, "total_steps": 76960, "loss": 0.173, "lr": 4.9977377802512405e-05, "epoch": 2.244022869022869, "percentage": 11.22, "elapsed_time": "0:12:31", "remaining_time": "1:39:05", "throughput": 1036.51, "total_tokens": 778856} {"current_steps": 8640, "total_steps": 76960, "loss": 0.3257, "lr": 4.997713602177521e-05, "epoch": 2.2453222453222454, "percentage": 11.23, "elapsed_time": "0:12:31", "remaining_time": "1:39:05", "throughput": 1036.5, "total_tokens": 779288} {"current_steps": 8645, "total_steps": 76960, "loss": 0.205, "lr": 4.997689295643998e-05, "epoch": 2.2466216216216215, "percentage": 11.23, "elapsed_time": "0:12:32", "remaining_time": "1:39:04", "throughput": 1036.53, "total_tokens": 779752} {"current_steps": 8650, "total_steps": 76960, "loss": 0.1579, "lr": 4.997664860651922e-05, "epoch": 2.247920997920998, "percentage": 11.24, "elapsed_time": "0:12:32", "remaining_time": "1:39:04", "throughput": 1036.52, "total_tokens": 780184} {"current_steps": 8655, "total_steps": 76960, "loss": 0.0809, "lr": 4.997640297202548e-05, "epoch": 2.249220374220374, "percentage": 11.25, "elapsed_time": "0:12:33", "remaining_time": "1:39:03", "throughput": 1036.48, "total_tokens": 780584} {"current_steps": 8660, "total_steps": 76960, "loss": 0.1595, "lr": 4.997615605297141e-05, "epoch": 2.2505197505197505, "percentage": 11.25, "elapsed_time": "0:12:33", "remaining_time": "1:39:02", "throughput": 1036.49, "total_tokens": 781032} {"current_steps": 8665, "total_steps": 76960, "loss": 0.1564, "lr": 4.997590784936971e-05, "epoch": 2.251819126819127, "percentage": 11.26, "elapsed_time": "0:12:33", "remaining_time": "1:39:02", "throughput": 1036.53, "total_tokens": 781496} {"current_steps": 8670, "total_steps": 76960, "loss": 0.6772, "lr": 4.997565836123313e-05, "epoch": 2.253118503118503, "percentage": 11.27, "elapsed_time": "0:12:34", "remaining_time": "1:39:01", "throughput": 1036.55, "total_tokens": 781944} {"current_steps": 8675, "total_steps": 76960, "loss": 0.3177, "lr": 4.9975407588574506e-05, "epoch": 2.2544178794178795, "percentage": 11.27, "elapsed_time": "0:12:34", "remaining_time": "1:39:01", "throughput": 1036.59, "total_tokens": 782408} {"current_steps": 8680, "total_steps": 76960, "loss": 0.3779, "lr": 4.9975155531406745e-05, "epoch": 2.2557172557172556, "percentage": 11.28, "elapsed_time": "0:12:35", "remaining_time": "1:39:00", "throughput": 1036.57, "total_tokens": 782824} {"current_steps": 8685, "total_steps": 76960, "loss": 0.2794, "lr": 4.9974902189742814e-05, "epoch": 2.257016632016632, "percentage": 11.29, "elapsed_time": "0:12:35", "remaining_time": "1:39:00", "throughput": 1036.55, "total_tokens": 783240} {"current_steps": 8690, "total_steps": 76960, "loss": 0.2593, "lr": 4.997464756359572e-05, "epoch": 2.258316008316008, "percentage": 11.29, "elapsed_time": "0:12:36", "remaining_time": "1:38:59", "throughput": 1036.55, "total_tokens": 783672} {"current_steps": 8695, "total_steps": 76960, "loss": 0.321, "lr": 4.997439165297858e-05, "epoch": 2.2596153846153846, "percentage": 11.3, "elapsed_time": "0:12:36", "remaining_time": "1:38:59", "throughput": 1036.61, "total_tokens": 784152} {"current_steps": 8700, "total_steps": 76960, "loss": 0.2794, "lr": 4.997413445790454e-05, "epoch": 2.260914760914761, "percentage": 11.3, "elapsed_time": "0:12:36", "remaining_time": "1:38:58", "throughput": 1036.67, "total_tokens": 784632} {"current_steps": 8705, "total_steps": 76960, "loss": 0.1955, "lr": 4.9973875978386843e-05, "epoch": 2.262214137214137, "percentage": 11.31, "elapsed_time": "0:12:37", "remaining_time": "1:38:57", "throughput": 1036.67, "total_tokens": 785064} {"current_steps": 8710, "total_steps": 76960, "loss": 0.4612, "lr": 4.997361621443877e-05, "epoch": 2.2635135135135136, "percentage": 11.32, "elapsed_time": "0:12:37", "remaining_time": "1:38:57", "throughput": 1036.68, "total_tokens": 785512} {"current_steps": 8715, "total_steps": 76960, "loss": 0.2838, "lr": 4.997335516607369e-05, "epoch": 2.2648128898128896, "percentage": 11.32, "elapsed_time": "0:12:38", "remaining_time": "1:38:56", "throughput": 1036.74, "total_tokens": 785992} {"current_steps": 8720, "total_steps": 76960, "loss": 0.2255, "lr": 4.997309283330503e-05, "epoch": 2.266112266112266, "percentage": 11.33, "elapsed_time": "0:12:38", "remaining_time": "1:38:56", "throughput": 1036.74, "total_tokens": 786424} {"current_steps": 8725, "total_steps": 76960, "loss": 0.1938, "lr": 4.997282921614627e-05, "epoch": 2.267411642411642, "percentage": 11.34, "elapsed_time": "0:12:38", "remaining_time": "1:38:55", "throughput": 1036.72, "total_tokens": 786840} {"current_steps": 8730, "total_steps": 76960, "loss": 0.4199, "lr": 4.997256431461098e-05, "epoch": 2.2687110187110187, "percentage": 11.34, "elapsed_time": "0:12:39", "remaining_time": "1:38:55", "throughput": 1036.78, "total_tokens": 787320} {"current_steps": 8735, "total_steps": 76960, "loss": 0.2813, "lr": 4.997229812871278e-05, "epoch": 2.270010395010395, "percentage": 11.35, "elapsed_time": "0:12:39", "remaining_time": "1:38:54", "throughput": 1036.78, "total_tokens": 787752} {"current_steps": 8740, "total_steps": 76960, "loss": 0.2709, "lr": 4.997203065846536e-05, "epoch": 2.271309771309771, "percentage": 11.36, "elapsed_time": "0:12:40", "remaining_time": "1:38:53", "throughput": 1036.8, "total_tokens": 788200} {"current_steps": 8745, "total_steps": 76960, "loss": 0.2654, "lr": 4.997176190388247e-05, "epoch": 2.2726091476091477, "percentage": 11.36, "elapsed_time": "0:12:40", "remaining_time": "1:38:53", "throughput": 1036.84, "total_tokens": 788664} {"current_steps": 8750, "total_steps": 76960, "loss": 0.2576, "lr": 4.9971491864977946e-05, "epoch": 2.2739085239085237, "percentage": 11.37, "elapsed_time": "0:12:41", "remaining_time": "1:38:52", "throughput": 1036.9, "total_tokens": 789144} {"current_steps": 8755, "total_steps": 76960, "loss": 0.2823, "lr": 4.997122054176566e-05, "epoch": 2.2752079002079, "percentage": 11.38, "elapsed_time": "0:12:41", "remaining_time": "1:38:52", "throughput": 1036.91, "total_tokens": 789592} {"current_steps": 8760, "total_steps": 76960, "loss": 0.2216, "lr": 4.997094793425958e-05, "epoch": 2.2765072765072767, "percentage": 11.38, "elapsed_time": "0:12:41", "remaining_time": "1:38:51", "throughput": 1036.93, "total_tokens": 790040} {"current_steps": 8765, "total_steps": 76960, "loss": 0.2146, "lr": 4.997067404247373e-05, "epoch": 2.2778066528066527, "percentage": 11.39, "elapsed_time": "0:12:42", "remaining_time": "1:38:51", "throughput": 1036.97, "total_tokens": 790504} {"current_steps": 8770, "total_steps": 76960, "loss": 0.1567, "lr": 4.997039886642218e-05, "epoch": 2.279106029106029, "percentage": 11.4, "elapsed_time": "0:12:42", "remaining_time": "1:38:50", "throughput": 1036.99, "total_tokens": 790952} {"current_steps": 8775, "total_steps": 76960, "loss": 0.151, "lr": 4.997012240611909e-05, "epoch": 2.2804054054054053, "percentage": 11.4, "elapsed_time": "0:12:43", "remaining_time": "1:38:50", "throughput": 1036.99, "total_tokens": 791384} {"current_steps": 8780, "total_steps": 76960, "loss": 0.2253, "lr": 4.996984466157868e-05, "epoch": 2.2817047817047817, "percentage": 11.41, "elapsed_time": "0:12:43", "remaining_time": "1:38:49", "throughput": 1037.05, "total_tokens": 791864} {"current_steps": 8785, "total_steps": 76960, "loss": 0.368, "lr": 4.996956563281524e-05, "epoch": 2.2830041580041582, "percentage": 11.42, "elapsed_time": "0:12:43", "remaining_time": "1:38:48", "throughput": 1037.09, "total_tokens": 792328} {"current_steps": 8790, "total_steps": 76960, "loss": 0.1462, "lr": 4.9969285319843105e-05, "epoch": 2.2843035343035343, "percentage": 11.42, "elapsed_time": "0:12:44", "remaining_time": "1:38:48", "throughput": 1037.13, "total_tokens": 792792} {"current_steps": 8795, "total_steps": 76960, "loss": 0.1499, "lr": 4.996900372267671e-05, "epoch": 2.2856029106029108, "percentage": 11.43, "elapsed_time": "0:12:44", "remaining_time": "1:38:47", "throughput": 1037.17, "total_tokens": 793256} {"current_steps": 8800, "total_steps": 76960, "loss": 0.2654, "lr": 4.996872084133053e-05, "epoch": 2.286902286902287, "percentage": 11.43, "elapsed_time": "0:12:45", "remaining_time": "1:38:47", "throughput": 1037.21, "total_tokens": 793720} {"current_steps": 8805, "total_steps": 76960, "loss": 0.2022, "lr": 4.996843667581911e-05, "epoch": 2.2882016632016633, "percentage": 11.44, "elapsed_time": "0:12:45", "remaining_time": "1:38:46", "throughput": 1037.2, "total_tokens": 794152} {"current_steps": 8810, "total_steps": 76960, "loss": 0.4079, "lr": 4.9968151226157065e-05, "epoch": 2.2895010395010393, "percentage": 11.45, "elapsed_time": "0:12:46", "remaining_time": "1:38:46", "throughput": 1037.2, "total_tokens": 794584} {"current_steps": 8815, "total_steps": 76960, "loss": 0.2238, "lr": 4.996786449235908e-05, "epoch": 2.290800415800416, "percentage": 11.45, "elapsed_time": "0:12:46", "remaining_time": "1:38:45", "throughput": 1037.21, "total_tokens": 795032} {"current_steps": 8820, "total_steps": 76960, "loss": 0.2615, "lr": 4.9967576474439905e-05, "epoch": 2.2920997920997923, "percentage": 11.46, "elapsed_time": "0:12:46", "remaining_time": "1:38:44", "throughput": 1037.23, "total_tokens": 795480} {"current_steps": 8825, "total_steps": 76960, "loss": 0.2935, "lr": 4.9967287172414345e-05, "epoch": 2.2933991683991684, "percentage": 11.47, "elapsed_time": "0:12:47", "remaining_time": "1:38:44", "throughput": 1037.25, "total_tokens": 795928} {"current_steps": 8830, "total_steps": 76960, "loss": 0.2265, "lr": 4.996699658629729e-05, "epoch": 2.294698544698545, "percentage": 11.47, "elapsed_time": "0:12:47", "remaining_time": "1:38:43", "throughput": 1037.23, "total_tokens": 796344} {"current_steps": 8835, "total_steps": 76960, "loss": 0.2736, "lr": 4.996670471610367e-05, "epoch": 2.295997920997921, "percentage": 11.48, "elapsed_time": "0:12:48", "remaining_time": "1:38:43", "throughput": 1037.27, "total_tokens": 796808} {"current_steps": 8840, "total_steps": 76960, "loss": 0.2757, "lr": 4.99664115618485e-05, "epoch": 2.2972972972972974, "percentage": 11.49, "elapsed_time": "0:12:48", "remaining_time": "1:38:42", "throughput": 1037.27, "total_tokens": 797240} {"current_steps": 8845, "total_steps": 76960, "loss": 0.282, "lr": 4.996611712354687e-05, "epoch": 2.2985966735966734, "percentage": 11.49, "elapsed_time": "0:12:49", "remaining_time": "1:38:42", "throughput": 1037.31, "total_tokens": 797704} {"current_steps": 8850, "total_steps": 76960, "loss": 0.2874, "lr": 4.996582140121392e-05, "epoch": 2.29989604989605, "percentage": 11.5, "elapsed_time": "0:12:49", "remaining_time": "1:38:41", "throughput": 1037.3, "total_tokens": 798136} {"current_steps": 8855, "total_steps": 76960, "loss": 0.261, "lr": 4.9965524394864846e-05, "epoch": 2.3011954261954264, "percentage": 11.51, "elapsed_time": "0:12:49", "remaining_time": "1:38:41", "throughput": 1037.32, "total_tokens": 798584} {"current_steps": 8860, "total_steps": 76960, "loss": 0.2474, "lr": 4.996522610451494e-05, "epoch": 2.3024948024948024, "percentage": 11.51, "elapsed_time": "0:12:50", "remaining_time": "1:38:40", "throughput": 1037.32, "total_tokens": 799016} {"current_steps": 8865, "total_steps": 76960, "loss": 0.2613, "lr": 4.996492653017952e-05, "epoch": 2.303794178794179, "percentage": 11.52, "elapsed_time": "0:12:50", "remaining_time": "1:38:39", "throughput": 1037.34, "total_tokens": 799464} {"current_steps": 8870, "total_steps": 76960, "loss": 0.3821, "lr": 4.996462567187402e-05, "epoch": 2.305093555093555, "percentage": 11.53, "elapsed_time": "0:12:51", "remaining_time": "1:38:39", "throughput": 1037.36, "total_tokens": 799912} {"current_steps": 8875, "total_steps": 76960, "loss": 0.2859, "lr": 4.9964323529613905e-05, "epoch": 2.3063929313929314, "percentage": 11.53, "elapsed_time": "0:12:51", "remaining_time": "1:38:38", "throughput": 1037.33, "total_tokens": 800328} {"current_steps": 8880, "total_steps": 76960, "loss": 0.2183, "lr": 4.9964020103414706e-05, "epoch": 2.3076923076923075, "percentage": 11.54, "elapsed_time": "0:12:51", "remaining_time": "1:38:38", "throughput": 1037.45, "total_tokens": 800856} {"current_steps": 8885, "total_steps": 76960, "loss": 0.2247, "lr": 4.996371539329203e-05, "epoch": 2.308991683991684, "percentage": 11.54, "elapsed_time": "0:12:52", "remaining_time": "1:38:37", "throughput": 1037.49, "total_tokens": 801320} {"current_steps": 8890, "total_steps": 76960, "loss": 0.289, "lr": 4.996340939926156e-05, "epoch": 2.3102910602910605, "percentage": 11.55, "elapsed_time": "0:12:52", "remaining_time": "1:38:37", "throughput": 1037.53, "total_tokens": 801784} {"current_steps": 8895, "total_steps": 76960, "loss": 0.2212, "lr": 4.996310212133902e-05, "epoch": 2.3115904365904365, "percentage": 11.56, "elapsed_time": "0:12:53", "remaining_time": "1:38:36", "throughput": 1037.58, "total_tokens": 802248} {"current_steps": 8900, "total_steps": 76960, "loss": 0.2175, "lr": 4.9962793559540224e-05, "epoch": 2.312889812889813, "percentage": 11.56, "elapsed_time": "0:12:53", "remaining_time": "1:38:35", "throughput": 1037.68, "total_tokens": 802760} {"current_steps": 8905, "total_steps": 76960, "loss": 0.3185, "lr": 4.996248371388103e-05, "epoch": 2.314189189189189, "percentage": 11.57, "elapsed_time": "0:12:54", "remaining_time": "1:38:35", "throughput": 1037.68, "total_tokens": 803192} {"current_steps": 8910, "total_steps": 76960, "loss": 0.2182, "lr": 4.9962172584377386e-05, "epoch": 2.3154885654885655, "percentage": 11.58, "elapsed_time": "0:12:54", "remaining_time": "1:38:34", "throughput": 1037.72, "total_tokens": 803656} {"current_steps": 8915, "total_steps": 76960, "loss": 0.1744, "lr": 4.9961860171045284e-05, "epoch": 2.3167879417879416, "percentage": 11.58, "elapsed_time": "0:12:54", "remaining_time": "1:38:34", "throughput": 1037.74, "total_tokens": 804104} {"current_steps": 8920, "total_steps": 76960, "loss": 0.3177, "lr": 4.99615464739008e-05, "epoch": 2.318087318087318, "percentage": 11.59, "elapsed_time": "0:12:55", "remaining_time": "1:38:33", "throughput": 1037.75, "total_tokens": 804552} {"current_steps": 8925, "total_steps": 76960, "loss": 0.2197, "lr": 4.996123149296007e-05, "epoch": 2.3193866943866945, "percentage": 11.6, "elapsed_time": "0:12:55", "remaining_time": "1:38:33", "throughput": 1037.77, "total_tokens": 805000} {"current_steps": 8930, "total_steps": 76960, "loss": 0.172, "lr": 4.9960915228239274e-05, "epoch": 2.3206860706860706, "percentage": 11.6, "elapsed_time": "0:12:56", "remaining_time": "1:38:32", "throughput": 1037.83, "total_tokens": 805480} {"current_steps": 8935, "total_steps": 76960, "loss": 0.2564, "lr": 4.99605976797547e-05, "epoch": 2.321985446985447, "percentage": 11.61, "elapsed_time": "0:12:56", "remaining_time": "1:38:32", "throughput": 1037.85, "total_tokens": 805928} {"current_steps": 8940, "total_steps": 76960, "loss": 0.3515, "lr": 4.996027884752267e-05, "epoch": 2.323284823284823, "percentage": 11.62, "elapsed_time": "0:12:56", "remaining_time": "1:38:31", "throughput": 1037.91, "total_tokens": 806408} {"current_steps": 8945, "total_steps": 76960, "loss": 0.2735, "lr": 4.995995873155958e-05, "epoch": 2.3245841995841996, "percentage": 11.62, "elapsed_time": "0:12:57", "remaining_time": "1:38:30", "throughput": 1037.91, "total_tokens": 806840} {"current_steps": 8950, "total_steps": 76960, "loss": 0.228, "lr": 4.99596373318819e-05, "epoch": 2.3258835758835756, "percentage": 11.63, "elapsed_time": "0:12:57", "remaining_time": "1:38:30", "throughput": 1037.93, "total_tokens": 807288} {"current_steps": 8955, "total_steps": 76960, "loss": 0.223, "lr": 4.995931464850616e-05, "epoch": 2.327182952182952, "percentage": 11.64, "elapsed_time": "0:12:58", "remaining_time": "1:38:29", "throughput": 1037.97, "total_tokens": 807752} {"current_steps": 8960, "total_steps": 76960, "loss": 0.2941, "lr": 4.995899068144895e-05, "epoch": 2.3284823284823286, "percentage": 11.64, "elapsed_time": "0:12:58", "remaining_time": "1:38:29", "throughput": 1037.92, "total_tokens": 808152} {"current_steps": 8965, "total_steps": 76960, "loss": 0.3187, "lr": 4.9958665430726924e-05, "epoch": 2.3297817047817047, "percentage": 11.65, "elapsed_time": "0:12:59", "remaining_time": "1:38:28", "throughput": 1037.92, "total_tokens": 808584} {"current_steps": 8970, "total_steps": 76960, "loss": 0.3338, "lr": 4.995833889635683e-05, "epoch": 2.331081081081081, "percentage": 11.66, "elapsed_time": "0:12:59", "remaining_time": "1:38:28", "throughput": 1037.94, "total_tokens": 809032} {"current_steps": 8975, "total_steps": 76960, "loss": 0.2674, "lr": 4.995801107835546e-05, "epoch": 2.3323804573804576, "percentage": 11.66, "elapsed_time": "0:12:59", "remaining_time": "1:38:27", "throughput": 1037.97, "total_tokens": 809496} {"current_steps": 8980, "total_steps": 76960, "loss": 0.2727, "lr": 4.995768197673966e-05, "epoch": 2.3336798336798337, "percentage": 11.67, "elapsed_time": "0:13:00", "remaining_time": "1:38:27", "throughput": 1037.97, "total_tokens": 809928} {"current_steps": 8985, "total_steps": 76960, "loss": 0.2473, "lr": 4.9957351591526356e-05, "epoch": 2.33497920997921, "percentage": 11.67, "elapsed_time": "0:13:00", "remaining_time": "1:38:26", "throughput": 1037.96, "total_tokens": 810360} {"current_steps": 8990, "total_steps": 76960, "loss": 0.2759, "lr": 4.995701992273255e-05, "epoch": 2.336278586278586, "percentage": 11.68, "elapsed_time": "0:13:01", "remaining_time": "1:38:25", "throughput": 1037.98, "total_tokens": 810808} {"current_steps": 8995, "total_steps": 76960, "loss": 0.302, "lr": 4.995668697037531e-05, "epoch": 2.3375779625779627, "percentage": 11.69, "elapsed_time": "0:13:01", "remaining_time": "1:38:25", "throughput": 1038.02, "total_tokens": 811272} {"current_steps": 9000, "total_steps": 76960, "loss": 0.259, "lr": 4.995635273447173e-05, "epoch": 2.3388773388773387, "percentage": 11.69, "elapsed_time": "0:13:01", "remaining_time": "1:38:24", "throughput": 1038.04, "total_tokens": 811720} {"current_steps": 9005, "total_steps": 76960, "loss": 0.2995, "lr": 4.995601721503902e-05, "epoch": 2.340176715176715, "percentage": 11.7, "elapsed_time": "0:13:02", "remaining_time": "1:38:24", "throughput": 1038.03, "total_tokens": 812152} {"current_steps": 9010, "total_steps": 76960, "loss": 0.303, "lr": 4.995568041209444e-05, "epoch": 2.3414760914760917, "percentage": 11.71, "elapsed_time": "0:13:02", "remaining_time": "1:38:23", "throughput": 1038.01, "total_tokens": 812568} {"current_steps": 9015, "total_steps": 76960, "loss": 0.2476, "lr": 4.9955342325655295e-05, "epoch": 2.3427754677754677, "percentage": 11.71, "elapsed_time": "0:13:03", "remaining_time": "1:38:23", "throughput": 1038.03, "total_tokens": 813016} {"current_steps": 9020, "total_steps": 76960, "loss": 0.2403, "lr": 4.995500295573899e-05, "epoch": 2.3440748440748442, "percentage": 11.72, "elapsed_time": "0:13:03", "remaining_time": "1:38:22", "throughput": 1038.0, "total_tokens": 813432} {"current_steps": 9025, "total_steps": 76960, "loss": 0.2581, "lr": 4.9954662302362973e-05, "epoch": 2.3453742203742203, "percentage": 11.73, "elapsed_time": "0:13:04", "remaining_time": "1:38:22", "throughput": 1038.0, "total_tokens": 813864} {"current_steps": 9030, "total_steps": 76960, "loss": 0.2509, "lr": 4.9954320365544765e-05, "epoch": 2.3466735966735968, "percentage": 11.73, "elapsed_time": "0:13:04", "remaining_time": "1:38:21", "throughput": 1037.98, "total_tokens": 814280} {"current_steps": 9035, "total_steps": 76960, "loss": 0.248, "lr": 4.995397714530194e-05, "epoch": 2.347972972972973, "percentage": 11.74, "elapsed_time": "0:13:04", "remaining_time": "1:38:20", "throughput": 1037.95, "total_tokens": 814696} {"current_steps": 9040, "total_steps": 76960, "loss": 0.2398, "lr": 4.9953632641652174e-05, "epoch": 2.3492723492723493, "percentage": 11.75, "elapsed_time": "0:13:05", "remaining_time": "1:38:20", "throughput": 1038.01, "total_tokens": 815176} {"current_steps": 9045, "total_steps": 76960, "loss": 0.2691, "lr": 4.995328685461317e-05, "epoch": 2.350571725571726, "percentage": 11.75, "elapsed_time": "0:13:05", "remaining_time": "1:38:19", "throughput": 1038.05, "total_tokens": 815640} {"current_steps": 9050, "total_steps": 76960, "loss": 0.1807, "lr": 4.995293978420271e-05, "epoch": 2.351871101871102, "percentage": 11.76, "elapsed_time": "0:13:06", "remaining_time": "1:38:19", "throughput": 1038.06, "total_tokens": 816088} {"current_steps": 9055, "total_steps": 76960, "loss": 0.2666, "lr": 4.9952591430438646e-05, "epoch": 2.3531704781704783, "percentage": 11.77, "elapsed_time": "0:13:06", "remaining_time": "1:38:18", "throughput": 1038.1, "total_tokens": 816552} {"current_steps": 9060, "total_steps": 76960, "loss": 0.2124, "lr": 4.9952241793338897e-05, "epoch": 2.3544698544698544, "percentage": 11.77, "elapsed_time": "0:13:06", "remaining_time": "1:38:18", "throughput": 1038.1, "total_tokens": 816984} {"current_steps": 9065, "total_steps": 76960, "loss": 0.2554, "lr": 4.995189087292145e-05, "epoch": 2.355769230769231, "percentage": 11.78, "elapsed_time": "0:13:07", "remaining_time": "1:38:17", "throughput": 1038.16, "total_tokens": 817464} {"current_steps": 9070, "total_steps": 76960, "loss": 0.2672, "lr": 4.995153866920434e-05, "epoch": 2.357068607068607, "percentage": 11.79, "elapsed_time": "0:13:07", "remaining_time": "1:38:17", "throughput": 1038.16, "total_tokens": 817896} {"current_steps": 9075, "total_steps": 76960, "loss": 0.3459, "lr": 4.9951185182205694e-05, "epoch": 2.3583679833679834, "percentage": 11.79, "elapsed_time": "0:13:08", "remaining_time": "1:38:16", "throughput": 1038.15, "total_tokens": 818328} {"current_steps": 9080, "total_steps": 76960, "loss": 0.2194, "lr": 4.9950830411943684e-05, "epoch": 2.35966735966736, "percentage": 11.8, "elapsed_time": "0:13:08", "remaining_time": "1:38:15", "throughput": 1038.17, "total_tokens": 818776} {"current_steps": 9085, "total_steps": 76960, "loss": 0.3325, "lr": 4.995047435843656e-05, "epoch": 2.360966735966736, "percentage": 11.8, "elapsed_time": "0:13:09", "remaining_time": "1:38:15", "throughput": 1038.17, "total_tokens": 819208} {"current_steps": 9090, "total_steps": 76960, "loss": 0.2692, "lr": 4.995011702170264e-05, "epoch": 2.3622661122661124, "percentage": 11.81, "elapsed_time": "0:13:09", "remaining_time": "1:38:14", "throughput": 1038.24, "total_tokens": 819704} {"current_steps": 9095, "total_steps": 76960, "loss": 0.2452, "lr": 4.994975840176028e-05, "epoch": 2.3635654885654884, "percentage": 11.82, "elapsed_time": "0:13:09", "remaining_time": "1:38:14", "throughput": 1038.29, "total_tokens": 820184} {"current_steps": 9100, "total_steps": 76960, "loss": 0.2296, "lr": 4.9949398498627955e-05, "epoch": 2.364864864864865, "percentage": 11.82, "elapsed_time": "0:13:10", "remaining_time": "1:38:13", "throughput": 1038.28, "total_tokens": 820616} {"current_steps": 9105, "total_steps": 76960, "loss": 0.175, "lr": 4.9949037312324155e-05, "epoch": 2.366164241164241, "percentage": 11.83, "elapsed_time": "0:13:10", "remaining_time": "1:38:13", "throughput": 1038.34, "total_tokens": 821096} {"current_steps": 9110, "total_steps": 76960, "loss": 0.3601, "lr": 4.994867484286746e-05, "epoch": 2.3674636174636174, "percentage": 11.84, "elapsed_time": "0:13:11", "remaining_time": "1:38:12", "throughput": 1038.38, "total_tokens": 821560} {"current_steps": 9115, "total_steps": 76960, "loss": 0.2517, "lr": 4.9948311090276515e-05, "epoch": 2.368762993762994, "percentage": 11.84, "elapsed_time": "0:13:11", "remaining_time": "1:38:12", "throughput": 1038.44, "total_tokens": 822040} {"current_steps": 9120, "total_steps": 76960, "loss": 0.2543, "lr": 4.994794605457002e-05, "epoch": 2.37006237006237, "percentage": 11.85, "elapsed_time": "0:13:12", "remaining_time": "1:38:11", "throughput": 1038.48, "total_tokens": 822504} {"current_steps": 9125, "total_steps": 76960, "loss": 0.2521, "lr": 4.994757973576676e-05, "epoch": 2.3713617463617465, "percentage": 11.86, "elapsed_time": "0:13:12", "remaining_time": "1:38:11", "throughput": 1038.52, "total_tokens": 822968} {"current_steps": 9130, "total_steps": 76960, "loss": 0.2208, "lr": 4.9947212133885566e-05, "epoch": 2.3726611226611225, "percentage": 11.86, "elapsed_time": "0:13:12", "remaining_time": "1:38:10", "throughput": 1038.54, "total_tokens": 823416} {"current_steps": 9135, "total_steps": 76960, "loss": 0.2258, "lr": 4.9946843248945353e-05, "epoch": 2.373960498960499, "percentage": 11.87, "elapsed_time": "0:13:13", "remaining_time": "1:38:09", "throughput": 1038.55, "total_tokens": 823864} {"current_steps": 9140, "total_steps": 76960, "loss": 0.3385, "lr": 4.994647308096509e-05, "epoch": 2.375259875259875, "percentage": 11.88, "elapsed_time": "0:13:13", "remaining_time": "1:38:09", "throughput": 1038.55, "total_tokens": 824296} {"current_steps": 9145, "total_steps": 76960, "loss": 0.2936, "lr": 4.9946101629963816e-05, "epoch": 2.3765592515592515, "percentage": 11.88, "elapsed_time": "0:13:14", "remaining_time": "1:38:08", "throughput": 1038.6, "total_tokens": 824776} {"current_steps": 9150, "total_steps": 76960, "loss": 0.2136, "lr": 4.994572889596063e-05, "epoch": 2.377858627858628, "percentage": 11.89, "elapsed_time": "0:13:14", "remaining_time": "1:38:08", "throughput": 1038.64, "total_tokens": 825240} {"current_steps": 9155, "total_steps": 76960, "loss": 0.1334, "lr": 4.99453548789747e-05, "epoch": 2.379158004158004, "percentage": 11.9, "elapsed_time": "0:13:14", "remaining_time": "1:38:07", "throughput": 1038.68, "total_tokens": 825704} {"current_steps": 9160, "total_steps": 76960, "loss": 0.3222, "lr": 4.994497957902528e-05, "epoch": 2.3804573804573805, "percentage": 11.9, "elapsed_time": "0:13:15", "remaining_time": "1:38:07", "throughput": 1038.65, "total_tokens": 826120} {"current_steps": 9165, "total_steps": 76960, "loss": 0.3754, "lr": 4.9944602996131646e-05, "epoch": 2.3817567567567566, "percentage": 11.91, "elapsed_time": "0:13:15", "remaining_time": "1:38:06", "throughput": 1038.65, "total_tokens": 826552} {"current_steps": 9170, "total_steps": 76960, "loss": 0.1713, "lr": 4.9944225130313183e-05, "epoch": 2.383056133056133, "percentage": 11.92, "elapsed_time": "0:13:16", "remaining_time": "1:38:06", "throughput": 1038.62, "total_tokens": 826968} {"current_steps": 9175, "total_steps": 76960, "loss": 0.2248, "lr": 4.994384598158932e-05, "epoch": 2.384355509355509, "percentage": 11.92, "elapsed_time": "0:13:16", "remaining_time": "1:38:05", "throughput": 1038.64, "total_tokens": 827416} {"current_steps": 9180, "total_steps": 76960, "loss": 0.2605, "lr": 4.994346554997956e-05, "epoch": 2.3856548856548856, "percentage": 11.93, "elapsed_time": "0:13:17", "remaining_time": "1:38:04", "throughput": 1038.64, "total_tokens": 827848} {"current_steps": 9185, "total_steps": 76960, "loss": 0.176, "lr": 4.9943083835503467e-05, "epoch": 2.386954261954262, "percentage": 11.93, "elapsed_time": "0:13:17", "remaining_time": "1:38:04", "throughput": 1038.66, "total_tokens": 828296} {"current_steps": 9190, "total_steps": 76960, "loss": 0.3197, "lr": 4.994270083818068e-05, "epoch": 2.388253638253638, "percentage": 11.94, "elapsed_time": "0:13:17", "remaining_time": "1:38:03", "throughput": 1038.68, "total_tokens": 828744} {"current_steps": 9195, "total_steps": 76960, "loss": 0.3576, "lr": 4.994231655803088e-05, "epoch": 2.3895530145530146, "percentage": 11.95, "elapsed_time": "0:13:18", "remaining_time": "1:38:03", "throughput": 1038.67, "total_tokens": 829176} {"current_steps": 9200, "total_steps": 76960, "loss": 0.2533, "lr": 4.994193099507384e-05, "epoch": 2.390852390852391, "percentage": 11.95, "elapsed_time": "0:13:18", "remaining_time": "1:38:02", "throughput": 1038.69, "total_tokens": 829624} {"current_steps": 9205, "total_steps": 76960, "loss": 0.2285, "lr": 4.99415441493294e-05, "epoch": 2.392151767151767, "percentage": 11.96, "elapsed_time": "0:13:19", "remaining_time": "1:38:02", "throughput": 1038.68, "total_tokens": 830056} {"current_steps": 9210, "total_steps": 76960, "loss": 0.2433, "lr": 4.9941156020817436e-05, "epoch": 2.3934511434511436, "percentage": 11.97, "elapsed_time": "0:13:19", "remaining_time": "1:38:01", "throughput": 1038.69, "total_tokens": 830504} {"current_steps": 9215, "total_steps": 76960, "loss": 0.173, "lr": 4.994076660955793e-05, "epoch": 2.3947505197505197, "percentage": 11.97, "elapsed_time": "0:13:20", "remaining_time": "1:38:01", "throughput": 1038.69, "total_tokens": 830952} {"current_steps": 9220, "total_steps": 76960, "loss": 0.3348, "lr": 4.9940375915570895e-05, "epoch": 2.396049896049896, "percentage": 11.98, "elapsed_time": "0:13:20", "remaining_time": "1:38:00", "throughput": 1038.68, "total_tokens": 831384} {"current_steps": 9225, "total_steps": 76960, "loss": 0.2683, "lr": 4.993998393887643e-05, "epoch": 2.397349272349272, "percentage": 11.99, "elapsed_time": "0:13:20", "remaining_time": "1:38:00", "throughput": 1038.7, "total_tokens": 831832} {"current_steps": 9230, "total_steps": 76960, "loss": 0.2612, "lr": 4.9939590679494694e-05, "epoch": 2.3986486486486487, "percentage": 11.99, "elapsed_time": "0:13:21", "remaining_time": "1:37:59", "throughput": 1038.69, "total_tokens": 832264} {"current_steps": 9235, "total_steps": 76960, "loss": 0.2613, "lr": 4.993919613744592e-05, "epoch": 2.399948024948025, "percentage": 12.0, "elapsed_time": "0:13:21", "remaining_time": "1:37:59", "throughput": 1038.71, "total_tokens": 832712} {"current_steps": 9240, "total_steps": 76960, "loss": 0.3107, "lr": 4.993880031275039e-05, "epoch": 2.401247401247401, "percentage": 12.01, "elapsed_time": "0:13:22", "remaining_time": "1:37:58", "throughput": 1038.75, "total_tokens": 833176} {"current_steps": 9245, "total_steps": 76960, "loss": 0.2641, "lr": 4.9938403205428466e-05, "epoch": 2.4025467775467777, "percentage": 12.01, "elapsed_time": "0:13:22", "remaining_time": "1:37:58", "throughput": 1038.74, "total_tokens": 833608} {"current_steps": 9250, "total_steps": 76960, "loss": 0.2319, "lr": 4.993800481550056e-05, "epoch": 2.4038461538461537, "percentage": 12.02, "elapsed_time": "0:13:22", "remaining_time": "1:37:57", "throughput": 1038.84, "total_tokens": 834120} {"current_steps": 9255, "total_steps": 76960, "loss": 0.2974, "lr": 4.993760514298718e-05, "epoch": 2.4051455301455302, "percentage": 12.03, "elapsed_time": "0:13:23", "remaining_time": "1:37:56", "throughput": 1038.86, "total_tokens": 834568} {"current_steps": 9260, "total_steps": 76960, "loss": 0.2236, "lr": 4.993720418790887e-05, "epoch": 2.4064449064449063, "percentage": 12.03, "elapsed_time": "0:13:23", "remaining_time": "1:37:56", "throughput": 1038.89, "total_tokens": 835032} {"current_steps": 9265, "total_steps": 76960, "loss": 0.367, "lr": 4.993680195028626e-05, "epoch": 2.4077442827442828, "percentage": 12.04, "elapsed_time": "0:13:24", "remaining_time": "1:37:55", "throughput": 1038.97, "total_tokens": 835528} {"current_steps": 9270, "total_steps": 76960, "loss": 0.3231, "lr": 4.993639843014003e-05, "epoch": 2.4090436590436592, "percentage": 12.05, "elapsed_time": "0:13:24", "remaining_time": "1:37:55", "throughput": 1039.01, "total_tokens": 835992} {"current_steps": 9275, "total_steps": 76960, "loss": 0.2633, "lr": 4.993599362749094e-05, "epoch": 2.4103430353430353, "percentage": 12.05, "elapsed_time": "0:13:25", "remaining_time": "1:37:54", "throughput": 1039.02, "total_tokens": 836440} {"current_steps": 9280, "total_steps": 76960, "loss": 0.2326, "lr": 4.99355875423598e-05, "epoch": 2.4116424116424118, "percentage": 12.06, "elapsed_time": "0:13:25", "remaining_time": "1:37:54", "throughput": 1039.06, "total_tokens": 836904} {"current_steps": 9285, "total_steps": 76960, "loss": 0.3023, "lr": 4.9935180174767496e-05, "epoch": 2.412941787941788, "percentage": 12.06, "elapsed_time": "0:13:25", "remaining_time": "1:37:53", "throughput": 1039.1, "total_tokens": 837368} {"current_steps": 9290, "total_steps": 76960, "loss": 0.2885, "lr": 4.993477152473499e-05, "epoch": 2.4142411642411643, "percentage": 12.07, "elapsed_time": "0:13:26", "remaining_time": "1:37:53", "throughput": 1039.11, "total_tokens": 837816} {"current_steps": 9295, "total_steps": 76960, "loss": 0.1986, "lr": 4.9934361592283297e-05, "epoch": 2.4155405405405403, "percentage": 12.08, "elapsed_time": "0:13:26", "remaining_time": "1:37:52", "throughput": 1039.15, "total_tokens": 838280} {"current_steps": 9300, "total_steps": 76960, "loss": 0.2593, "lr": 4.9933950377433494e-05, "epoch": 2.416839916839917, "percentage": 12.08, "elapsed_time": "0:13:27", "remaining_time": "1:37:51", "throughput": 1039.17, "total_tokens": 838728} {"current_steps": 9305, "total_steps": 76960, "loss": 0.304, "lr": 4.993353788020673e-05, "epoch": 2.4181392931392933, "percentage": 12.09, "elapsed_time": "0:13:27", "remaining_time": "1:37:51", "throughput": 1039.18, "total_tokens": 839176} {"current_steps": 9310, "total_steps": 76960, "loss": 0.2855, "lr": 4.993312410062422e-05, "epoch": 2.4194386694386694, "percentage": 12.1, "elapsed_time": "0:13:27", "remaining_time": "1:37:50", "throughput": 1039.22, "total_tokens": 839640} {"current_steps": 9315, "total_steps": 76960, "loss": 0.2801, "lr": 4.9932709038707246e-05, "epoch": 2.420738045738046, "percentage": 12.1, "elapsed_time": "0:13:28", "remaining_time": "1:37:50", "throughput": 1039.22, "total_tokens": 840072} {"current_steps": 9320, "total_steps": 76960, "loss": 0.2697, "lr": 4.9932292694477165e-05, "epoch": 2.422037422037422, "percentage": 12.11, "elapsed_time": "0:13:28", "remaining_time": "1:37:49", "throughput": 1039.23, "total_tokens": 840520} {"current_steps": 9325, "total_steps": 76960, "loss": 0.2651, "lr": 4.993187506795538e-05, "epoch": 2.4233367983367984, "percentage": 12.12, "elapsed_time": "0:13:29", "remaining_time": "1:37:49", "throughput": 1039.25, "total_tokens": 840968} {"current_steps": 9330, "total_steps": 76960, "loss": 0.3056, "lr": 4.993145615916337e-05, "epoch": 2.4246361746361744, "percentage": 12.12, "elapsed_time": "0:13:29", "remaining_time": "1:37:48", "throughput": 1039.33, "total_tokens": 841464} {"current_steps": 9335, "total_steps": 76960, "loss": 0.2921, "lr": 4.993103596812268e-05, "epoch": 2.425935550935551, "percentage": 12.13, "elapsed_time": "0:13:30", "remaining_time": "1:37:48", "throughput": 1039.3, "total_tokens": 841880} {"current_steps": 9340, "total_steps": 76960, "loss": 0.2868, "lr": 4.993061449485492e-05, "epoch": 2.4272349272349274, "percentage": 12.14, "elapsed_time": "0:13:30", "remaining_time": "1:37:47", "throughput": 1039.3, "total_tokens": 842312} {"current_steps": 9345, "total_steps": 76960, "loss": 0.2993, "lr": 4.9930191739381775e-05, "epoch": 2.4285343035343034, "percentage": 12.14, "elapsed_time": "0:13:30", "remaining_time": "1:37:47", "throughput": 1039.34, "total_tokens": 842776} {"current_steps": 9350, "total_steps": 76960, "loss": 0.2962, "lr": 4.992976770172498e-05, "epoch": 2.42983367983368, "percentage": 12.15, "elapsed_time": "0:13:31", "remaining_time": "1:37:46", "throughput": 1039.37, "total_tokens": 843240} {"current_steps": 9355, "total_steps": 76960, "loss": 0.2739, "lr": 4.9929342381906344e-05, "epoch": 2.431133056133056, "percentage": 12.16, "elapsed_time": "0:13:31", "remaining_time": "1:37:45", "throughput": 1039.39, "total_tokens": 843688} {"current_steps": 9360, "total_steps": 76960, "loss": 0.2141, "lr": 4.992891577994775e-05, "epoch": 2.4324324324324325, "percentage": 12.16, "elapsed_time": "0:13:32", "remaining_time": "1:37:45", "throughput": 1039.41, "total_tokens": 844136} {"current_steps": 9365, "total_steps": 76960, "loss": 0.2752, "lr": 4.9928487895871125e-05, "epoch": 2.4337318087318085, "percentage": 12.17, "elapsed_time": "0:13:32", "remaining_time": "1:37:44", "throughput": 1039.4, "total_tokens": 844568} {"current_steps": 9370, "total_steps": 76960, "loss": 0.3055, "lr": 4.9928058729698487e-05, "epoch": 2.435031185031185, "percentage": 12.18, "elapsed_time": "0:13:32", "remaining_time": "1:37:44", "throughput": 1039.38, "total_tokens": 844984} {"current_steps": 9375, "total_steps": 76960, "loss": 0.2621, "lr": 4.99276282814519e-05, "epoch": 2.4363305613305615, "percentage": 12.18, "elapsed_time": "0:13:33", "remaining_time": "1:37:43", "throughput": 1039.47, "total_tokens": 845496} {"current_steps": 9380, "total_steps": 76960, "loss": 0.1388, "lr": 4.99271965511535e-05, "epoch": 2.4376299376299375, "percentage": 12.19, "elapsed_time": "0:13:33", "remaining_time": "1:37:43", "throughput": 1039.47, "total_tokens": 845928} {"current_steps": 9385, "total_steps": 76960, "loss": 0.2544, "lr": 4.9926763538825505e-05, "epoch": 2.438929313929314, "percentage": 12.19, "elapsed_time": "0:13:34", "remaining_time": "1:37:42", "throughput": 1039.51, "total_tokens": 846392} {"current_steps": 9390, "total_steps": 76960, "loss": 0.1553, "lr": 4.9926329244490174e-05, "epoch": 2.44022869022869, "percentage": 12.2, "elapsed_time": "0:13:34", "remaining_time": "1:37:42", "throughput": 1039.5, "total_tokens": 846824} {"current_steps": 9395, "total_steps": 76960, "loss": 0.2848, "lr": 4.9925893668169855e-05, "epoch": 2.4415280665280665, "percentage": 12.21, "elapsed_time": "0:13:35", "remaining_time": "1:37:41", "throughput": 1039.52, "total_tokens": 847272} {"current_steps": 9400, "total_steps": 76960, "loss": 0.086, "lr": 4.9925456809886935e-05, "epoch": 2.442827442827443, "percentage": 12.21, "elapsed_time": "0:13:35", "remaining_time": "1:37:41", "throughput": 1039.58, "total_tokens": 847752} {"current_steps": 9405, "total_steps": 76960, "loss": 0.305, "lr": 4.9925018669663885e-05, "epoch": 2.444126819126819, "percentage": 12.22, "elapsed_time": "0:13:35", "remaining_time": "1:37:40", "throughput": 1039.57, "total_tokens": 848184} {"current_steps": 9410, "total_steps": 76960, "loss": 0.3236, "lr": 4.992457924752325e-05, "epoch": 2.4454261954261955, "percentage": 12.23, "elapsed_time": "0:13:36", "remaining_time": "1:37:39", "throughput": 1039.55, "total_tokens": 848600} {"current_steps": 9415, "total_steps": 76960, "loss": 0.2998, "lr": 4.992413854348762e-05, "epoch": 2.4467255717255716, "percentage": 12.23, "elapsed_time": "0:13:36", "remaining_time": "1:37:39", "throughput": 1039.54, "total_tokens": 849032} {"current_steps": 9420, "total_steps": 76960, "loss": 0.2335, "lr": 4.9923696557579665e-05, "epoch": 2.448024948024948, "percentage": 12.24, "elapsed_time": "0:13:37", "remaining_time": "1:37:38", "throughput": 1039.6, "total_tokens": 849512} {"current_steps": 9425, "total_steps": 76960, "loss": 0.2541, "lr": 4.9923253289822116e-05, "epoch": 2.4493243243243246, "percentage": 12.25, "elapsed_time": "0:13:37", "remaining_time": "1:37:38", "throughput": 1039.6, "total_tokens": 849944} {"current_steps": 9430, "total_steps": 76960, "loss": 0.224, "lr": 4.9922808740237764e-05, "epoch": 2.4506237006237006, "percentage": 12.25, "elapsed_time": "0:13:37", "remaining_time": "1:37:37", "throughput": 1039.65, "total_tokens": 850424} {"current_steps": 9435, "total_steps": 76960, "loss": 0.2186, "lr": 4.9922362908849484e-05, "epoch": 2.451923076923077, "percentage": 12.26, "elapsed_time": "0:13:38", "remaining_time": "1:37:37", "throughput": 1039.65, "total_tokens": 850856} {"current_steps": 9440, "total_steps": 76960, "loss": 0.266, "lr": 4.9921915795680194e-05, "epoch": 2.453222453222453, "percentage": 12.27, "elapsed_time": "0:13:38", "remaining_time": "1:37:36", "throughput": 1039.6, "total_tokens": 851256} {"current_steps": 9445, "total_steps": 76960, "loss": 0.3711, "lr": 4.99214674007529e-05, "epoch": 2.4545218295218296, "percentage": 12.27, "elapsed_time": "0:13:39", "remaining_time": "1:37:36", "throughput": 1039.68, "total_tokens": 851752} {"current_steps": 9450, "total_steps": 76960, "loss": 0.1962, "lr": 4.992101772409066e-05, "epoch": 2.4558212058212057, "percentage": 12.28, "elapsed_time": "0:13:39", "remaining_time": "1:37:35", "throughput": 1039.74, "total_tokens": 852232} {"current_steps": 9455, "total_steps": 76960, "loss": 0.1578, "lr": 4.99205667657166e-05, "epoch": 2.457120582120582, "percentage": 12.29, "elapsed_time": "0:13:40", "remaining_time": "1:37:35", "throughput": 1039.79, "total_tokens": 852712} {"current_steps": 9460, "total_steps": 76960, "loss": 0.2669, "lr": 4.992011452565392e-05, "epoch": 2.4584199584199586, "percentage": 12.29, "elapsed_time": "0:13:40", "remaining_time": "1:37:34", "throughput": 1039.81, "total_tokens": 853160} {"current_steps": 9465, "total_steps": 76960, "loss": 0.3487, "lr": 4.991966100392586e-05, "epoch": 2.4597193347193347, "percentage": 12.3, "elapsed_time": "0:13:40", "remaining_time": "1:37:33", "throughput": 1039.84, "total_tokens": 853624} {"current_steps": 9470, "total_steps": 76960, "loss": 0.3318, "lr": 4.991920620055576e-05, "epoch": 2.461018711018711, "percentage": 12.31, "elapsed_time": "0:13:41", "remaining_time": "1:37:33", "throughput": 1039.84, "total_tokens": 854056} {"current_steps": 9475, "total_steps": 76960, "loss": 0.3075, "lr": 4.991875011556702e-05, "epoch": 2.462318087318087, "percentage": 12.31, "elapsed_time": "0:13:41", "remaining_time": "1:37:32", "throughput": 1039.87, "total_tokens": 854520} {"current_steps": 9480, "total_steps": 76960, "loss": 0.2667, "lr": 4.9918292748983074e-05, "epoch": 2.4636174636174637, "percentage": 12.32, "elapsed_time": "0:13:42", "remaining_time": "1:37:32", "throughput": 1039.88, "total_tokens": 854968} {"current_steps": 9485, "total_steps": 76960, "loss": 0.2563, "lr": 4.991783410082745e-05, "epoch": 2.4649168399168397, "percentage": 12.32, "elapsed_time": "0:13:42", "remaining_time": "1:37:31", "throughput": 1039.88, "total_tokens": 855400} {"current_steps": 9490, "total_steps": 76960, "loss": 0.2133, "lr": 4.991737417112376e-05, "epoch": 2.4662162162162162, "percentage": 12.33, "elapsed_time": "0:13:43", "remaining_time": "1:37:31", "throughput": 1039.88, "total_tokens": 855832} {"current_steps": 9495, "total_steps": 76960, "loss": 0.3813, "lr": 4.991691295989563e-05, "epoch": 2.4675155925155927, "percentage": 12.34, "elapsed_time": "0:13:43", "remaining_time": "1:37:30", "throughput": 1039.87, "total_tokens": 856264} {"current_steps": 9500, "total_steps": 76960, "loss": 0.3198, "lr": 4.9916450467166804e-05, "epoch": 2.4688149688149688, "percentage": 12.34, "elapsed_time": "0:13:43", "remaining_time": "1:37:30", "throughput": 1039.88, "total_tokens": 856712} {"current_steps": 9505, "total_steps": 76960, "loss": 0.2508, "lr": 4.9915986692961045e-05, "epoch": 2.4701143451143452, "percentage": 12.35, "elapsed_time": "0:13:44", "remaining_time": "1:37:29", "throughput": 1039.9, "total_tokens": 857160} {"current_steps": 9510, "total_steps": 76960, "loss": 0.2651, "lr": 4.991552163730222e-05, "epoch": 2.4714137214137213, "percentage": 12.36, "elapsed_time": "0:13:44", "remaining_time": "1:37:29", "throughput": 1039.89, "total_tokens": 857592} {"current_steps": 9515, "total_steps": 76960, "loss": 0.2291, "lr": 4.9915055300214256e-05, "epoch": 2.4727130977130978, "percentage": 12.36, "elapsed_time": "0:13:45", "remaining_time": "1:37:28", "throughput": 1039.87, "total_tokens": 858008} {"current_steps": 9520, "total_steps": 76960, "loss": 0.2885, "lr": 4.991458768172111e-05, "epoch": 2.474012474012474, "percentage": 12.37, "elapsed_time": "0:13:45", "remaining_time": "1:37:28", "throughput": 1039.94, "total_tokens": 858504} {"current_steps": 9525, "total_steps": 76960, "loss": 0.287, "lr": 4.991411878184685e-05, "epoch": 2.4753118503118503, "percentage": 12.38, "elapsed_time": "0:13:45", "remaining_time": "1:37:27", "throughput": 1040.0, "total_tokens": 858984} {"current_steps": 9530, "total_steps": 76960, "loss": 0.1744, "lr": 4.991364860061559e-05, "epoch": 2.476611226611227, "percentage": 12.38, "elapsed_time": "0:13:46", "remaining_time": "1:37:26", "throughput": 1040.03, "total_tokens": 859448} {"current_steps": 9535, "total_steps": 76960, "loss": 0.2223, "lr": 4.9913177138051516e-05, "epoch": 2.477910602910603, "percentage": 12.39, "elapsed_time": "0:13:46", "remaining_time": "1:37:26", "throughput": 1040.07, "total_tokens": 859912} {"current_steps": 9540, "total_steps": 76960, "loss": 0.4293, "lr": 4.991270439417887e-05, "epoch": 2.4792099792099793, "percentage": 12.4, "elapsed_time": "0:13:47", "remaining_time": "1:37:25", "throughput": 1040.08, "total_tokens": 860360} {"current_steps": 9545, "total_steps": 76960, "loss": 0.3062, "lr": 4.991223036902197e-05, "epoch": 2.4805093555093554, "percentage": 12.4, "elapsed_time": "0:13:47", "remaining_time": "1:37:25", "throughput": 1040.12, "total_tokens": 860824} {"current_steps": 9550, "total_steps": 76960, "loss": 0.2934, "lr": 4.991175506260518e-05, "epoch": 2.481808731808732, "percentage": 12.41, "elapsed_time": "0:13:48", "remaining_time": "1:37:24", "throughput": 1040.11, "total_tokens": 861256} {"current_steps": 9555, "total_steps": 76960, "loss": 0.3002, "lr": 4.9911278474952974e-05, "epoch": 2.483108108108108, "percentage": 12.42, "elapsed_time": "0:13:48", "remaining_time": "1:37:24", "throughput": 1040.13, "total_tokens": 861704} {"current_steps": 9560, "total_steps": 76960, "loss": 0.2759, "lr": 4.9910800606089834e-05, "epoch": 2.4844074844074844, "percentage": 12.42, "elapsed_time": "0:13:48", "remaining_time": "1:37:23", "throughput": 1040.18, "total_tokens": 862184} {"current_steps": 9565, "total_steps": 76960, "loss": 0.2886, "lr": 4.9910321456040356e-05, "epoch": 2.485706860706861, "percentage": 12.43, "elapsed_time": "0:13:49", "remaining_time": "1:37:23", "throughput": 1040.18, "total_tokens": 862616} {"current_steps": 9570, "total_steps": 76960, "loss": 0.2061, "lr": 4.990984102482918e-05, "epoch": 2.487006237006237, "percentage": 12.44, "elapsed_time": "0:13:49", "remaining_time": "1:37:22", "throughput": 1040.16, "total_tokens": 863032} {"current_steps": 9575, "total_steps": 76960, "loss": 0.3516, "lr": 4.9909359312481006e-05, "epoch": 2.4883056133056134, "percentage": 12.44, "elapsed_time": "0:13:50", "remaining_time": "1:37:22", "throughput": 1040.19, "total_tokens": 863496} {"current_steps": 9580, "total_steps": 76960, "loss": 0.2583, "lr": 4.990887631902062e-05, "epoch": 2.4896049896049894, "percentage": 12.45, "elapsed_time": "0:13:50", "remaining_time": "1:37:21", "throughput": 1040.17, "total_tokens": 863912} {"current_steps": 9585, "total_steps": 76960, "loss": 0.2179, "lr": 4.9908392044472865e-05, "epoch": 2.490904365904366, "percentage": 12.45, "elapsed_time": "0:13:50", "remaining_time": "1:37:21", "throughput": 1040.14, "total_tokens": 864328} {"current_steps": 9590, "total_steps": 76960, "loss": 0.1813, "lr": 4.9907906488862626e-05, "epoch": 2.492203742203742, "percentage": 12.46, "elapsed_time": "0:13:51", "remaining_time": "1:37:20", "throughput": 1040.14, "total_tokens": 864760} {"current_steps": 9595, "total_steps": 76960, "loss": 0.2547, "lr": 4.99074196522149e-05, "epoch": 2.4935031185031185, "percentage": 12.47, "elapsed_time": "0:13:51", "remaining_time": "1:37:20", "throughput": 1040.13, "total_tokens": 865192} {"current_steps": 9600, "total_steps": 76960, "loss": 0.1397, "lr": 4.9906931534554714e-05, "epoch": 2.494802494802495, "percentage": 12.47, "elapsed_time": "0:13:52", "remaining_time": "1:37:19", "throughput": 1040.13, "total_tokens": 865624} {"current_steps": 9605, "total_steps": 76960, "loss": 0.288, "lr": 4.990644213590717e-05, "epoch": 2.496101871101871, "percentage": 12.48, "elapsed_time": "0:13:52", "remaining_time": "1:37:18", "throughput": 1040.16, "total_tokens": 866088} {"current_steps": 9610, "total_steps": 76960, "loss": 0.4961, "lr": 4.9905951456297454e-05, "epoch": 2.4974012474012475, "percentage": 12.49, "elapsed_time": "0:13:53", "remaining_time": "1:37:18", "throughput": 1040.18, "total_tokens": 866536} {"current_steps": 9615, "total_steps": 76960, "loss": 0.2608, "lr": 4.9905459495750786e-05, "epoch": 2.4987006237006235, "percentage": 12.49, "elapsed_time": "0:13:53", "remaining_time": "1:37:17", "throughput": 1040.18, "total_tokens": 866968} {"current_steps": 9620, "total_steps": 76960, "loss": 0.2469, "lr": 4.9904966254292475e-05, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:13:53", "remaining_time": "1:37:17", "throughput": 1040.19, "total_tokens": 867416} {"current_steps": 9625, "total_steps": 76960, "loss": 0.2555, "lr": 4.990447173194788e-05, "epoch": 2.501299376299376, "percentage": 12.51, "elapsed_time": "0:13:54", "remaining_time": "1:37:16", "throughput": 1040.23, "total_tokens": 867880} {"current_steps": 9630, "total_steps": 76960, "loss": 0.3563, "lr": 4.990397592874244e-05, "epoch": 2.5025987525987525, "percentage": 12.51, "elapsed_time": "0:13:54", "remaining_time": "1:37:16", "throughput": 1040.25, "total_tokens": 868328} {"current_steps": 9635, "total_steps": 76960, "loss": 0.2897, "lr": 4.990347884470167e-05, "epoch": 2.503898128898129, "percentage": 12.52, "elapsed_time": "0:13:55", "remaining_time": "1:37:15", "throughput": 1040.28, "total_tokens": 868792} {"current_steps": 9640, "total_steps": 76960, "loss": 0.2959, "lr": 4.99029804798511e-05, "epoch": 2.505197505197505, "percentage": 12.53, "elapsed_time": "0:13:55", "remaining_time": "1:37:15", "throughput": 1040.26, "total_tokens": 869208} {"current_steps": 9645, "total_steps": 76960, "loss": 0.2865, "lr": 4.99024808342164e-05, "epoch": 2.5064968814968815, "percentage": 12.53, "elapsed_time": "0:13:55", "remaining_time": "1:37:14", "throughput": 1040.31, "total_tokens": 869688} {"current_steps": 9650, "total_steps": 76960, "loss": 0.262, "lr": 4.990197990782325e-05, "epoch": 2.507796257796258, "percentage": 12.54, "elapsed_time": "0:13:56", "remaining_time": "1:37:14", "throughput": 1040.33, "total_tokens": 870136} {"current_steps": 9655, "total_steps": 76960, "loss": 0.2945, "lr": 4.990147770069741e-05, "epoch": 2.509095634095634, "percentage": 12.55, "elapsed_time": "0:13:56", "remaining_time": "1:37:13", "throughput": 1040.32, "total_tokens": 870568} {"current_steps": 9660, "total_steps": 76960, "loss": 0.2642, "lr": 4.990097421286471e-05, "epoch": 2.51039501039501, "percentage": 12.55, "elapsed_time": "0:13:57", "remaining_time": "1:37:12", "throughput": 1040.38, "total_tokens": 871048} {"current_steps": 9665, "total_steps": 76960, "loss": 0.2342, "lr": 4.990046944435105e-05, "epoch": 2.5116943866943866, "percentage": 12.56, "elapsed_time": "0:13:57", "remaining_time": "1:37:12", "throughput": 1040.41, "total_tokens": 871512} {"current_steps": 9670, "total_steps": 76960, "loss": 0.1835, "lr": 4.989996339518239e-05, "epoch": 2.512993762993763, "percentage": 12.56, "elapsed_time": "0:13:58", "remaining_time": "1:37:11", "throughput": 1040.43, "total_tokens": 871960} {"current_steps": 9675, "total_steps": 76960, "loss": 0.1569, "lr": 4.989945606538475e-05, "epoch": 2.514293139293139, "percentage": 12.57, "elapsed_time": "0:13:58", "remaining_time": "1:37:11", "throughput": 1040.48, "total_tokens": 872440} {"current_steps": 9680, "total_steps": 76960, "loss": 0.2839, "lr": 4.989894745498422e-05, "epoch": 2.5155925155925156, "percentage": 12.58, "elapsed_time": "0:13:58", "remaining_time": "1:37:10", "throughput": 1040.47, "total_tokens": 872872} {"current_steps": 9685, "total_steps": 76960, "loss": 0.2758, "lr": 4.989843756400698e-05, "epoch": 2.516891891891892, "percentage": 12.58, "elapsed_time": "0:13:59", "remaining_time": "1:37:10", "throughput": 1040.47, "total_tokens": 873304} {"current_steps": 9690, "total_steps": 76960, "loss": 0.319, "lr": 4.9897926392479235e-05, "epoch": 2.518191268191268, "percentage": 12.59, "elapsed_time": "0:13:59", "remaining_time": "1:37:09", "throughput": 1040.56, "total_tokens": 873816} {"current_steps": 9695, "total_steps": 76960, "loss": 0.27, "lr": 4.989741394042727e-05, "epoch": 2.5194906444906446, "percentage": 12.6, "elapsed_time": "0:14:00", "remaining_time": "1:37:09", "throughput": 1040.58, "total_tokens": 874264} {"current_steps": 9700, "total_steps": 76960, "loss": 0.2336, "lr": 4.9896900207877464e-05, "epoch": 2.5207900207900207, "percentage": 12.6, "elapsed_time": "0:14:00", "remaining_time": "1:37:08", "throughput": 1040.63, "total_tokens": 874744} {"current_steps": 9705, "total_steps": 76960, "loss": 0.288, "lr": 4.989638519485622e-05, "epoch": 2.522089397089397, "percentage": 12.61, "elapsed_time": "0:14:01", "remaining_time": "1:37:08", "throughput": 1040.6, "total_tokens": 875160} {"current_steps": 9710, "total_steps": 76960, "loss": 0.2235, "lr": 4.989586890139003e-05, "epoch": 2.523388773388773, "percentage": 12.62, "elapsed_time": "0:14:01", "remaining_time": "1:37:07", "throughput": 1040.58, "total_tokens": 875576} {"current_steps": 9715, "total_steps": 76960, "loss": 0.2813, "lr": 4.9895351327505454e-05, "epoch": 2.5246881496881497, "percentage": 12.62, "elapsed_time": "0:14:01", "remaining_time": "1:37:07", "throughput": 1040.58, "total_tokens": 876008} {"current_steps": 9720, "total_steps": 76960, "loss": 0.313, "lr": 4.98948324732291e-05, "epoch": 2.525987525987526, "percentage": 12.63, "elapsed_time": "0:14:02", "remaining_time": "1:37:06", "throughput": 1040.56, "total_tokens": 876424} {"current_steps": 9725, "total_steps": 76960, "loss": 0.2392, "lr": 4.989431233858766e-05, "epoch": 2.5272869022869022, "percentage": 12.64, "elapsed_time": "0:14:02", "remaining_time": "1:37:05", "throughput": 1040.59, "total_tokens": 876888} {"current_steps": 9730, "total_steps": 76960, "loss": 0.2303, "lr": 4.989379092360788e-05, "epoch": 2.5285862785862787, "percentage": 12.64, "elapsed_time": "0:14:03", "remaining_time": "1:37:05", "throughput": 1040.57, "total_tokens": 877304} {"current_steps": 9735, "total_steps": 76960, "loss": 0.153, "lr": 4.9893268228316584e-05, "epoch": 2.5298856548856548, "percentage": 12.65, "elapsed_time": "0:14:03", "remaining_time": "1:37:04", "throughput": 1040.59, "total_tokens": 877752} {"current_steps": 9740, "total_steps": 76960, "loss": 0.1578, "lr": 4.989274425274065e-05, "epoch": 2.5311850311850312, "percentage": 12.66, "elapsed_time": "0:14:03", "remaining_time": "1:37:04", "throughput": 1040.6, "total_tokens": 878200} {"current_steps": 9745, "total_steps": 76960, "loss": 0.3624, "lr": 4.989221899690704e-05, "epoch": 2.5324844074844073, "percentage": 12.66, "elapsed_time": "0:14:04", "remaining_time": "1:37:03", "throughput": 1040.6, "total_tokens": 878632} {"current_steps": 9750, "total_steps": 76960, "loss": 0.2814, "lr": 4.9891692460842736e-05, "epoch": 2.5337837837837838, "percentage": 12.67, "elapsed_time": "0:14:04", "remaining_time": "1:37:03", "throughput": 1040.63, "total_tokens": 879096} {"current_steps": 9755, "total_steps": 76960, "loss": 0.3956, "lr": 4.989116464457485e-05, "epoch": 2.5350831600831603, "percentage": 12.68, "elapsed_time": "0:14:05", "remaining_time": "1:37:02", "throughput": 1040.7, "total_tokens": 879592} {"current_steps": 9760, "total_steps": 76960, "loss": 0.1954, "lr": 4.989063554813051e-05, "epoch": 2.5363825363825363, "percentage": 12.68, "elapsed_time": "0:14:05", "remaining_time": "1:37:02", "throughput": 1040.7, "total_tokens": 880024} {"current_steps": 9765, "total_steps": 76960, "loss": 0.2277, "lr": 4.989010517153695e-05, "epoch": 2.537681912681913, "percentage": 12.69, "elapsed_time": "0:14:06", "remaining_time": "1:37:01", "throughput": 1040.66, "total_tokens": 880424} {"current_steps": 9770, "total_steps": 76960, "loss": 0.2275, "lr": 4.988957351482142e-05, "epoch": 2.538981288981289, "percentage": 12.69, "elapsed_time": "0:14:06", "remaining_time": "1:37:01", "throughput": 1040.67, "total_tokens": 880872} {"current_steps": 9775, "total_steps": 76960, "loss": 0.307, "lr": 4.9889040578011284e-05, "epoch": 2.5402806652806653, "percentage": 12.7, "elapsed_time": "0:14:06", "remaining_time": "1:37:00", "throughput": 1040.67, "total_tokens": 881304} {"current_steps": 9780, "total_steps": 76960, "loss": 0.259, "lr": 4.988850636113394e-05, "epoch": 2.5415800415800414, "percentage": 12.71, "elapsed_time": "0:14:07", "remaining_time": "1:37:00", "throughput": 1040.66, "total_tokens": 881736} {"current_steps": 9785, "total_steps": 76960, "loss": 0.3358, "lr": 4.988797086421686e-05, "epoch": 2.542879417879418, "percentage": 12.71, "elapsed_time": "0:14:07", "remaining_time": "1:36:59", "throughput": 1040.66, "total_tokens": 882168} {"current_steps": 9790, "total_steps": 76960, "loss": 0.2251, "lr": 4.988743408728759e-05, "epoch": 2.5441787941787943, "percentage": 12.72, "elapsed_time": "0:14:08", "remaining_time": "1:36:59", "throughput": 1040.67, "total_tokens": 882616} {"current_steps": 9795, "total_steps": 76960, "loss": 0.2983, "lr": 4.9886896030373755e-05, "epoch": 2.5454781704781704, "percentage": 12.73, "elapsed_time": "0:14:08", "remaining_time": "1:36:58", "throughput": 1040.69, "total_tokens": 883064} {"current_steps": 9800, "total_steps": 76960, "loss": 0.2554, "lr": 4.9886356693503e-05, "epoch": 2.546777546777547, "percentage": 12.73, "elapsed_time": "0:14:08", "remaining_time": "1:36:57", "throughput": 1040.68, "total_tokens": 883496} {"current_steps": 9805, "total_steps": 76960, "loss": 0.2097, "lr": 4.9885816076703075e-05, "epoch": 2.5480769230769234, "percentage": 12.74, "elapsed_time": "0:14:09", "remaining_time": "1:36:57", "throughput": 1040.7, "total_tokens": 883944} {"current_steps": 9810, "total_steps": 76960, "loss": 0.2235, "lr": 4.988527418000179e-05, "epoch": 2.5493762993762994, "percentage": 12.75, "elapsed_time": "0:14:09", "remaining_time": "1:36:56", "throughput": 1040.74, "total_tokens": 884408} {"current_steps": 9815, "total_steps": 76960, "loss": 0.2673, "lr": 4.988473100342701e-05, "epoch": 2.5506756756756754, "percentage": 12.75, "elapsed_time": "0:14:10", "remaining_time": "1:36:56", "throughput": 1040.75, "total_tokens": 884856} {"current_steps": 9820, "total_steps": 76960, "loss": 0.0867, "lr": 4.988418654700666e-05, "epoch": 2.551975051975052, "percentage": 12.76, "elapsed_time": "0:14:10", "remaining_time": "1:36:55", "throughput": 1040.78, "total_tokens": 885320} {"current_steps": 9825, "total_steps": 76960, "loss": 0.4661, "lr": 4.9883640810768764e-05, "epoch": 2.5532744282744284, "percentage": 12.77, "elapsed_time": "0:14:11", "remaining_time": "1:36:55", "throughput": 1040.82, "total_tokens": 885784} {"current_steps": 9830, "total_steps": 76960, "loss": 0.1595, "lr": 4.988309379474137e-05, "epoch": 2.5545738045738045, "percentage": 12.77, "elapsed_time": "0:14:11", "remaining_time": "1:36:54", "throughput": 1040.82, "total_tokens": 886216} {"current_steps": 9835, "total_steps": 76960, "loss": 0.167, "lr": 4.988254549895264e-05, "epoch": 2.555873180873181, "percentage": 12.78, "elapsed_time": "0:14:11", "remaining_time": "1:36:54", "throughput": 1040.79, "total_tokens": 886632} {"current_steps": 9840, "total_steps": 76960, "loss": 0.2054, "lr": 4.988199592343073e-05, "epoch": 2.5571725571725574, "percentage": 12.79, "elapsed_time": "0:14:12", "remaining_time": "1:36:53", "throughput": 1040.85, "total_tokens": 887112} {"current_steps": 9845, "total_steps": 76960, "loss": 0.2775, "lr": 4.988144506820395e-05, "epoch": 2.5584719334719335, "percentage": 12.79, "elapsed_time": "0:14:12", "remaining_time": "1:36:53", "throughput": 1040.88, "total_tokens": 887576} {"current_steps": 9850, "total_steps": 76960, "loss": 0.263, "lr": 4.9880892933300593e-05, "epoch": 2.5597713097713095, "percentage": 12.8, "elapsed_time": "0:14:13", "remaining_time": "1:36:52", "throughput": 1040.9, "total_tokens": 888024} {"current_steps": 9855, "total_steps": 76960, "loss": 0.2616, "lr": 4.988033951874908e-05, "epoch": 2.561070686070686, "percentage": 12.81, "elapsed_time": "0:14:13", "remaining_time": "1:36:52", "throughput": 1040.91, "total_tokens": 888472} {"current_steps": 9860, "total_steps": 76960, "loss": 0.2511, "lr": 4.9879784824577866e-05, "epoch": 2.5623700623700625, "percentage": 12.81, "elapsed_time": "0:14:13", "remaining_time": "1:36:51", "throughput": 1040.92, "total_tokens": 888920} {"current_steps": 9865, "total_steps": 76960, "loss": 0.3517, "lr": 4.9879228850815476e-05, "epoch": 2.5636694386694385, "percentage": 12.82, "elapsed_time": "0:14:14", "remaining_time": "1:36:51", "throughput": 1040.92, "total_tokens": 889352} {"current_steps": 9870, "total_steps": 76960, "loss": 0.2798, "lr": 4.987867159749051e-05, "epoch": 2.564968814968815, "percentage": 12.82, "elapsed_time": "0:14:14", "remaining_time": "1:36:50", "throughput": 1040.89, "total_tokens": 889768} {"current_steps": 9875, "total_steps": 76960, "loss": 0.2583, "lr": 4.987811306463163e-05, "epoch": 2.5662681912681915, "percentage": 12.83, "elapsed_time": "0:14:15", "remaining_time": "1:36:49", "throughput": 1040.9, "total_tokens": 890216} {"current_steps": 9880, "total_steps": 76960, "loss": 0.2611, "lr": 4.9877553252267564e-05, "epoch": 2.5675675675675675, "percentage": 12.84, "elapsed_time": "0:14:15", "remaining_time": "1:36:49", "throughput": 1040.93, "total_tokens": 890680} {"current_steps": 9885, "total_steps": 76960, "loss": 0.2232, "lr": 4.987699216042708e-05, "epoch": 2.568866943866944, "percentage": 12.84, "elapsed_time": "0:14:16", "remaining_time": "1:36:48", "throughput": 1040.99, "total_tokens": 891160} {"current_steps": 9890, "total_steps": 76960, "loss": 0.2226, "lr": 4.987642978913907e-05, "epoch": 2.57016632016632, "percentage": 12.85, "elapsed_time": "0:14:16", "remaining_time": "1:36:48", "throughput": 1041.02, "total_tokens": 891624} {"current_steps": 9895, "total_steps": 76960, "loss": 0.3802, "lr": 4.9875866138432426e-05, "epoch": 2.5714656964656966, "percentage": 12.86, "elapsed_time": "0:14:16", "remaining_time": "1:36:47", "throughput": 1041.04, "total_tokens": 892072} {"current_steps": 9900, "total_steps": 76960, "loss": 0.296, "lr": 4.987530120833616e-05, "epoch": 2.5727650727650726, "percentage": 12.86, "elapsed_time": "0:14:17", "remaining_time": "1:36:47", "throughput": 1041.07, "total_tokens": 892536} {"current_steps": 9905, "total_steps": 76960, "loss": 0.2547, "lr": 4.9874734998879316e-05, "epoch": 2.574064449064449, "percentage": 12.87, "elapsed_time": "0:14:17", "remaining_time": "1:36:46", "throughput": 1041.11, "total_tokens": 893000} {"current_steps": 9910, "total_steps": 76960, "loss": 0.2801, "lr": 4.987416751009102e-05, "epoch": 2.5753638253638256, "percentage": 12.88, "elapsed_time": "0:14:18", "remaining_time": "1:36:46", "throughput": 1041.1, "total_tokens": 893432} {"current_steps": 9915, "total_steps": 76960, "loss": 0.2649, "lr": 4.987359874200045e-05, "epoch": 2.5766632016632016, "percentage": 12.88, "elapsed_time": "0:14:18", "remaining_time": "1:36:45", "throughput": 1041.14, "total_tokens": 893896} {"current_steps": 9920, "total_steps": 76960, "loss": 0.2696, "lr": 4.987302869463687e-05, "epoch": 2.577962577962578, "percentage": 12.89, "elapsed_time": "0:14:18", "remaining_time": "1:36:45", "throughput": 1041.17, "total_tokens": 894360} {"current_steps": 9925, "total_steps": 76960, "loss": 0.2259, "lr": 4.987245736802959e-05, "epoch": 2.579261954261954, "percentage": 12.9, "elapsed_time": "0:14:19", "remaining_time": "1:36:44", "throughput": 1041.19, "total_tokens": 894808} {"current_steps": 9930, "total_steps": 76960, "loss": 0.279, "lr": 4.9871884762208e-05, "epoch": 2.5805613305613306, "percentage": 12.9, "elapsed_time": "0:14:19", "remaining_time": "1:36:44", "throughput": 1041.18, "total_tokens": 895240} {"current_steps": 9935, "total_steps": 76960, "loss": 0.2216, "lr": 4.9871310877201535e-05, "epoch": 2.5818607068607067, "percentage": 12.91, "elapsed_time": "0:14:20", "remaining_time": "1:36:43", "throughput": 1041.2, "total_tokens": 895688} {"current_steps": 9940, "total_steps": 76960, "loss": 0.1664, "lr": 4.987073571303973e-05, "epoch": 2.583160083160083, "percentage": 12.92, "elapsed_time": "0:14:20", "remaining_time": "1:36:42", "throughput": 1041.21, "total_tokens": 896136} {"current_steps": 9945, "total_steps": 76960, "loss": 0.2125, "lr": 4.987015926975216e-05, "epoch": 2.5844594594594597, "percentage": 12.92, "elapsed_time": "0:14:21", "remaining_time": "1:36:42", "throughput": 1041.25, "total_tokens": 896600} {"current_steps": 9950, "total_steps": 76960, "loss": 0.1934, "lr": 4.986958154736846e-05, "epoch": 2.5857588357588357, "percentage": 12.93, "elapsed_time": "0:14:21", "remaining_time": "1:36:41", "throughput": 1041.24, "total_tokens": 897032} {"current_steps": 9955, "total_steps": 76960, "loss": 0.3183, "lr": 4.986900254591835e-05, "epoch": 2.587058212058212, "percentage": 12.94, "elapsed_time": "0:14:21", "remaining_time": "1:36:41", "throughput": 1041.24, "total_tokens": 897464} {"current_steps": 9960, "total_steps": 76960, "loss": 0.3031, "lr": 4.986842226543162e-05, "epoch": 2.5883575883575882, "percentage": 12.94, "elapsed_time": "0:14:22", "remaining_time": "1:36:40", "throughput": 1041.25, "total_tokens": 897912} {"current_steps": 9965, "total_steps": 76960, "loss": 0.2717, "lr": 4.986784070593811e-05, "epoch": 2.5896569646569647, "percentage": 12.95, "elapsed_time": "0:14:22", "remaining_time": "1:36:40", "throughput": 1041.25, "total_tokens": 898344} {"current_steps": 9970, "total_steps": 76960, "loss": 0.2762, "lr": 4.986725786746771e-05, "epoch": 2.5909563409563408, "percentage": 12.95, "elapsed_time": "0:14:23", "remaining_time": "1:36:39", "throughput": 1041.25, "total_tokens": 898776} {"current_steps": 9975, "total_steps": 76960, "loss": 0.2519, "lr": 4.986667375005042e-05, "epoch": 2.5922557172557172, "percentage": 12.96, "elapsed_time": "0:14:23", "remaining_time": "1:36:39", "throughput": 1041.28, "total_tokens": 899240} {"current_steps": 9980, "total_steps": 76960, "loss": 0.3126, "lr": 4.986608835371627e-05, "epoch": 2.5935550935550937, "percentage": 12.97, "elapsed_time": "0:14:24", "remaining_time": "1:36:38", "throughput": 1041.37, "total_tokens": 899752} {"current_steps": 9985, "total_steps": 76960, "loss": 0.263, "lr": 4.9865501678495375e-05, "epoch": 2.5948544698544698, "percentage": 12.97, "elapsed_time": "0:14:24", "remaining_time": "1:36:38", "throughput": 1041.35, "total_tokens": 900168} {"current_steps": 9990, "total_steps": 76960, "loss": 0.2192, "lr": 4.98649137244179e-05, "epoch": 2.5961538461538463, "percentage": 12.98, "elapsed_time": "0:14:24", "remaining_time": "1:36:37", "throughput": 1041.4, "total_tokens": 900648} {"current_steps": 9995, "total_steps": 76960, "loss": 0.3107, "lr": 4.986432449151409e-05, "epoch": 2.5974532224532223, "percentage": 12.99, "elapsed_time": "0:14:25", "remaining_time": "1:36:37", "throughput": 1041.41, "total_tokens": 901096} {"current_steps": 10000, "total_steps": 76960, "loss": 0.2528, "lr": 4.9863733979814244e-05, "epoch": 2.598752598752599, "percentage": 12.99, "elapsed_time": "0:14:25", "remaining_time": "1:36:36", "throughput": 1041.37, "total_tokens": 901496} {"current_steps": 10005, "total_steps": 76960, "loss": 0.1313, "lr": 4.9863142189348735e-05, "epoch": 2.600051975051975, "percentage": 13.0, "elapsed_time": "0:14:26", "remaining_time": "1:36:36", "throughput": 1041.38, "total_tokens": 901944} {"current_steps": 10010, "total_steps": 76960, "loss": 0.3138, "lr": 4.9862549120148005e-05, "epoch": 2.6013513513513513, "percentage": 13.01, "elapsed_time": "0:14:26", "remaining_time": "1:36:35", "throughput": 1041.42, "total_tokens": 902408} {"current_steps": 10015, "total_steps": 76960, "loss": 0.2191, "lr": 4.9861954772242546e-05, "epoch": 2.602650727650728, "percentage": 13.01, "elapsed_time": "0:14:26", "remaining_time": "1:36:35", "throughput": 1041.43, "total_tokens": 902856} {"current_steps": 10020, "total_steps": 76960, "loss": 0.307, "lr": 4.986135914566294e-05, "epoch": 2.603950103950104, "percentage": 13.02, "elapsed_time": "0:14:27", "remaining_time": "1:36:34", "throughput": 1041.43, "total_tokens": 903288} {"current_steps": 10025, "total_steps": 76960, "loss": 0.2174, "lr": 4.986076224043981e-05, "epoch": 2.6052494802494803, "percentage": 13.03, "elapsed_time": "0:14:27", "remaining_time": "1:36:33", "throughput": 1041.42, "total_tokens": 903720} {"current_steps": 10030, "total_steps": 76960, "loss": 0.2434, "lr": 4.986016405660385e-05, "epoch": 2.606548856548857, "percentage": 13.03, "elapsed_time": "0:14:28", "remaining_time": "1:36:33", "throughput": 1041.42, "total_tokens": 904152} {"current_steps": 10035, "total_steps": 76960, "loss": 0.2953, "lr": 4.985956459418584e-05, "epoch": 2.607848232848233, "percentage": 13.04, "elapsed_time": "0:14:28", "remaining_time": "1:36:32", "throughput": 1041.45, "total_tokens": 904616} {"current_steps": 10040, "total_steps": 76960, "loss": 0.2348, "lr": 4.98589638532166e-05, "epoch": 2.609147609147609, "percentage": 13.05, "elapsed_time": "0:14:29", "remaining_time": "1:36:32", "throughput": 1041.49, "total_tokens": 905080} {"current_steps": 10045, "total_steps": 76960, "loss": 0.2485, "lr": 4.985836183372703e-05, "epoch": 2.6104469854469854, "percentage": 13.05, "elapsed_time": "0:14:29", "remaining_time": "1:36:31", "throughput": 1041.5, "total_tokens": 905528} {"current_steps": 10050, "total_steps": 76960, "loss": 0.2967, "lr": 4.98577585357481e-05, "epoch": 2.611746361746362, "percentage": 13.06, "elapsed_time": "0:14:29", "remaining_time": "1:36:31", "throughput": 1041.55, "total_tokens": 906008} {"current_steps": 10055, "total_steps": 76960, "loss": 0.2812, "lr": 4.985715395931083e-05, "epoch": 2.613045738045738, "percentage": 13.07, "elapsed_time": "0:14:30", "remaining_time": "1:36:30", "throughput": 1041.57, "total_tokens": 906456} {"current_steps": 10060, "total_steps": 76960, "loss": 0.1627, "lr": 4.98565481044463e-05, "epoch": 2.6143451143451144, "percentage": 13.07, "elapsed_time": "0:14:30", "remaining_time": "1:36:30", "throughput": 1041.54, "total_tokens": 906872} {"current_steps": 10065, "total_steps": 76960, "loss": 0.252, "lr": 4.98559409711857e-05, "epoch": 2.615644490644491, "percentage": 13.08, "elapsed_time": "0:14:31", "remaining_time": "1:36:29", "throughput": 1041.59, "total_tokens": 907352} {"current_steps": 10070, "total_steps": 76960, "loss": 0.2869, "lr": 4.9855332559560235e-05, "epoch": 2.616943866943867, "percentage": 13.08, "elapsed_time": "0:14:31", "remaining_time": "1:36:29", "throughput": 1041.61, "total_tokens": 907800} {"current_steps": 10075, "total_steps": 76960, "loss": 0.2655, "lr": 4.98547228696012e-05, "epoch": 2.618243243243243, "percentage": 13.09, "elapsed_time": "0:14:31", "remaining_time": "1:36:28", "throughput": 1041.62, "total_tokens": 908248} {"current_steps": 10080, "total_steps": 76960, "loss": 0.2569, "lr": 4.9854111901339954e-05, "epoch": 2.6195426195426195, "percentage": 13.1, "elapsed_time": "0:14:32", "remaining_time": "1:36:28", "throughput": 1041.68, "total_tokens": 908728} {"current_steps": 10085, "total_steps": 76960, "loss": 0.3517, "lr": 4.9853499654807924e-05, "epoch": 2.620841995841996, "percentage": 13.1, "elapsed_time": "0:14:32", "remaining_time": "1:36:27", "throughput": 1041.67, "total_tokens": 909160} {"current_steps": 10090, "total_steps": 76960, "loss": 0.2931, "lr": 4.9852886130036586e-05, "epoch": 2.622141372141372, "percentage": 13.11, "elapsed_time": "0:14:33", "remaining_time": "1:36:27", "throughput": 1041.65, "total_tokens": 909576} {"current_steps": 10095, "total_steps": 76960, "loss": 0.2835, "lr": 4.9852271327057504e-05, "epoch": 2.6234407484407485, "percentage": 13.12, "elapsed_time": "0:14:33", "remaining_time": "1:36:26", "throughput": 1041.69, "total_tokens": 910040} {"current_steps": 10100, "total_steps": 76960, "loss": 0.3092, "lr": 4.98516552459023e-05, "epoch": 2.624740124740125, "percentage": 13.12, "elapsed_time": "0:14:34", "remaining_time": "1:36:25", "throughput": 1041.71, "total_tokens": 910488} {"current_steps": 10105, "total_steps": 76960, "loss": 0.2823, "lr": 4.985103788660265e-05, "epoch": 2.626039501039501, "percentage": 13.13, "elapsed_time": "0:14:34", "remaining_time": "1:36:25", "throughput": 1041.76, "total_tokens": 910968} {"current_steps": 10110, "total_steps": 76960, "loss": 0.2907, "lr": 4.985041924919031e-05, "epoch": 2.6273388773388775, "percentage": 13.14, "elapsed_time": "0:14:34", "remaining_time": "1:36:24", "throughput": 1041.74, "total_tokens": 911384} {"current_steps": 10115, "total_steps": 76960, "loss": 0.2668, "lr": 4.9849799333697095e-05, "epoch": 2.6286382536382535, "percentage": 13.14, "elapsed_time": "0:14:35", "remaining_time": "1:36:24", "throughput": 1041.77, "total_tokens": 911848} {"current_steps": 10120, "total_steps": 76960, "loss": 0.2641, "lr": 4.984917814015489e-05, "epoch": 2.62993762993763, "percentage": 13.15, "elapsed_time": "0:14:35", "remaining_time": "1:36:23", "throughput": 1041.79, "total_tokens": 912296} {"current_steps": 10125, "total_steps": 76960, "loss": 0.2252, "lr": 4.984855566859565e-05, "epoch": 2.631237006237006, "percentage": 13.16, "elapsed_time": "0:14:36", "remaining_time": "1:36:23", "throughput": 1041.84, "total_tokens": 912776} {"current_steps": 10130, "total_steps": 76960, "loss": 0.2502, "lr": 4.984793191905138e-05, "epoch": 2.6325363825363826, "percentage": 13.16, "elapsed_time": "0:14:36", "remaining_time": "1:36:22", "throughput": 1041.86, "total_tokens": 913224} {"current_steps": 10135, "total_steps": 76960, "loss": 0.2887, "lr": 4.984730689155417e-05, "epoch": 2.633835758835759, "percentage": 13.17, "elapsed_time": "0:14:36", "remaining_time": "1:36:22", "throughput": 1041.91, "total_tokens": 913704} {"current_steps": 10140, "total_steps": 76960, "loss": 0.282, "lr": 4.984668058613615e-05, "epoch": 2.635135135135135, "percentage": 13.18, "elapsed_time": "0:14:37", "remaining_time": "1:36:21", "throughput": 1041.93, "total_tokens": 914152} {"current_steps": 10145, "total_steps": 76960, "loss": 0.2816, "lr": 4.984605300282954e-05, "epoch": 2.6364345114345116, "percentage": 13.18, "elapsed_time": "0:14:37", "remaining_time": "1:36:21", "throughput": 1041.93, "total_tokens": 914584} {"current_steps": 10150, "total_steps": 76960, "loss": 0.2451, "lr": 4.984542414166663e-05, "epoch": 2.6377338877338876, "percentage": 13.19, "elapsed_time": "0:14:38", "remaining_time": "1:36:20", "throughput": 1041.92, "total_tokens": 915016} {"current_steps": 10155, "total_steps": 76960, "loss": 0.2319, "lr": 4.984479400267974e-05, "epoch": 2.639033264033264, "percentage": 13.2, "elapsed_time": "0:14:38", "remaining_time": "1:36:20", "throughput": 1041.94, "total_tokens": 915464} {"current_steps": 10160, "total_steps": 76960, "loss": 0.2207, "lr": 4.984416258590129e-05, "epoch": 2.64033264033264, "percentage": 13.2, "elapsed_time": "0:14:39", "remaining_time": "1:36:19", "throughput": 1041.93, "total_tokens": 915896} {"current_steps": 10165, "total_steps": 76960, "loss": 0.265, "lr": 4.984352989136375e-05, "epoch": 2.6416320166320166, "percentage": 13.21, "elapsed_time": "0:14:39", "remaining_time": "1:36:19", "throughput": 1041.99, "total_tokens": 916392} {"current_steps": 10170, "total_steps": 76960, "loss": 0.2059, "lr": 4.984289591909967e-05, "epoch": 2.642931392931393, "percentage": 13.21, "elapsed_time": "0:14:39", "remaining_time": "1:36:18", "throughput": 1042.05, "total_tokens": 916888} {"current_steps": 10175, "total_steps": 76960, "loss": 0.1514, "lr": 4.984226066914165e-05, "epoch": 2.644230769230769, "percentage": 13.22, "elapsed_time": "0:14:40", "remaining_time": "1:36:18", "throughput": 1042.03, "total_tokens": 917320} {"current_steps": 10180, "total_steps": 76960, "loss": 0.3943, "lr": 4.984162414152236e-05, "epoch": 2.6455301455301456, "percentage": 13.23, "elapsed_time": "0:14:40", "remaining_time": "1:36:17", "throughput": 1042.04, "total_tokens": 917768} {"current_steps": 10185, "total_steps": 76960, "loss": 0.1096, "lr": 4.9840986336274534e-05, "epoch": 2.6468295218295217, "percentage": 13.23, "elapsed_time": "0:14:41", "remaining_time": "1:36:17", "throughput": 1042.07, "total_tokens": 918232} {"current_steps": 10190, "total_steps": 76960, "loss": 0.1697, "lr": 4.9840347253430984e-05, "epoch": 2.648128898128898, "percentage": 13.24, "elapsed_time": "0:14:41", "remaining_time": "1:36:16", "throughput": 1042.09, "total_tokens": 918680} {"current_steps": 10195, "total_steps": 76960, "loss": 0.2165, "lr": 4.983970689302457e-05, "epoch": 2.649428274428274, "percentage": 13.25, "elapsed_time": "0:14:41", "remaining_time": "1:36:16", "throughput": 1042.14, "total_tokens": 919160} {"current_steps": 10200, "total_steps": 76960, "loss": 0.3845, "lr": 4.9839065255088234e-05, "epoch": 2.6507276507276507, "percentage": 13.25, "elapsed_time": "0:14:42", "remaining_time": "1:36:15", "throughput": 1042.11, "total_tokens": 919576} {"current_steps": 10205, "total_steps": 76960, "loss": 0.21, "lr": 4.9838422339654974e-05, "epoch": 2.652027027027027, "percentage": 13.26, "elapsed_time": "0:14:42", "remaining_time": "1:36:14", "throughput": 1042.11, "total_tokens": 920008} {"current_steps": 10210, "total_steps": 76960, "loss": 0.255, "lr": 4.983777814675785e-05, "epoch": 2.6533264033264032, "percentage": 13.27, "elapsed_time": "0:14:43", "remaining_time": "1:36:14", "throughput": 1042.11, "total_tokens": 920440} {"current_steps": 10215, "total_steps": 76960, "loss": 0.2643, "lr": 4.983713267643e-05, "epoch": 2.6546257796257797, "percentage": 13.27, "elapsed_time": "0:14:43", "remaining_time": "1:36:13", "throughput": 1042.1, "total_tokens": 920872} {"current_steps": 10220, "total_steps": 76960, "loss": 0.2316, "lr": 4.983648592870462e-05, "epoch": 2.6559251559251558, "percentage": 13.28, "elapsed_time": "0:14:44", "remaining_time": "1:36:13", "throughput": 1042.08, "total_tokens": 921288} {"current_steps": 10225, "total_steps": 76960, "loss": 0.1878, "lr": 4.983583790361497e-05, "epoch": 2.6572245322245323, "percentage": 13.29, "elapsed_time": "0:14:44", "remaining_time": "1:36:12", "throughput": 1042.06, "total_tokens": 921704} {"current_steps": 10230, "total_steps": 76960, "loss": 0.2632, "lr": 4.9835188601194374e-05, "epoch": 2.6585239085239083, "percentage": 13.29, "elapsed_time": "0:14:44", "remaining_time": "1:36:12", "throughput": 1042.07, "total_tokens": 922152} {"current_steps": 10235, "total_steps": 76960, "loss": 0.2141, "lr": 4.983453802147624e-05, "epoch": 2.659823284823285, "percentage": 13.3, "elapsed_time": "0:14:45", "remaining_time": "1:36:11", "throughput": 1042.07, "total_tokens": 922600} {"current_steps": 10240, "total_steps": 76960, "loss": 0.2219, "lr": 4.9833886164494014e-05, "epoch": 2.6611226611226613, "percentage": 13.31, "elapsed_time": "0:14:45", "remaining_time": "1:36:11", "throughput": 1042.12, "total_tokens": 923080} {"current_steps": 10245, "total_steps": 76960, "loss": 0.3379, "lr": 4.983323303028124e-05, "epoch": 2.6624220374220373, "percentage": 13.31, "elapsed_time": "0:14:46", "remaining_time": "1:36:10", "throughput": 1042.12, "total_tokens": 923512} {"current_steps": 10250, "total_steps": 76960, "loss": 0.2169, "lr": 4.9832578618871485e-05, "epoch": 2.663721413721414, "percentage": 13.32, "elapsed_time": "0:14:46", "remaining_time": "1:36:10", "throughput": 1042.13, "total_tokens": 923960} {"current_steps": 10255, "total_steps": 76960, "loss": 0.2594, "lr": 4.983192293029843e-05, "epoch": 2.6650207900207903, "percentage": 13.33, "elapsed_time": "0:14:47", "remaining_time": "1:36:09", "throughput": 1042.15, "total_tokens": 924408} {"current_steps": 10260, "total_steps": 76960, "loss": 0.2115, "lr": 4.983126596459577e-05, "epoch": 2.6663201663201663, "percentage": 13.33, "elapsed_time": "0:14:47", "remaining_time": "1:36:09", "throughput": 1042.18, "total_tokens": 924872} {"current_steps": 10265, "total_steps": 76960, "loss": 0.2262, "lr": 4.983060772179732e-05, "epoch": 2.6676195426195424, "percentage": 13.34, "elapsed_time": "0:14:47", "remaining_time": "1:36:08", "throughput": 1042.14, "total_tokens": 925272} {"current_steps": 10270, "total_steps": 76960, "loss": 0.2605, "lr": 4.982994820193692e-05, "epoch": 2.668918918918919, "percentage": 13.34, "elapsed_time": "0:14:48", "remaining_time": "1:36:08", "throughput": 1042.13, "total_tokens": 925704} {"current_steps": 10275, "total_steps": 76960, "loss": 0.2187, "lr": 4.982928740504849e-05, "epoch": 2.6702182952182953, "percentage": 13.35, "elapsed_time": "0:14:48", "remaining_time": "1:36:07", "throughput": 1042.17, "total_tokens": 926168} {"current_steps": 10280, "total_steps": 76960, "loss": 0.2125, "lr": 4.9828625331166024e-05, "epoch": 2.6715176715176714, "percentage": 13.36, "elapsed_time": "0:14:49", "remaining_time": "1:36:07", "throughput": 1042.16, "total_tokens": 926600} {"current_steps": 10285, "total_steps": 76960, "loss": 0.2197, "lr": 4.982796198032357e-05, "epoch": 2.672817047817048, "percentage": 13.36, "elapsed_time": "0:14:49", "remaining_time": "1:36:06", "throughput": 1042.16, "total_tokens": 927032} {"current_steps": 10290, "total_steps": 76960, "loss": 0.2029, "lr": 4.982729735255523e-05, "epoch": 2.6741164241164244, "percentage": 13.37, "elapsed_time": "0:14:49", "remaining_time": "1:36:06", "throughput": 1042.19, "total_tokens": 927496} {"current_steps": 10295, "total_steps": 76960, "loss": 0.3218, "lr": 4.982663144789521e-05, "epoch": 2.6754158004158004, "percentage": 13.38, "elapsed_time": "0:14:50", "remaining_time": "1:36:05", "throughput": 1042.21, "total_tokens": 927944} {"current_steps": 10300, "total_steps": 76960, "loss": 0.3051, "lr": 4.982596426637774e-05, "epoch": 2.6767151767151764, "percentage": 13.38, "elapsed_time": "0:14:50", "remaining_time": "1:36:04", "throughput": 1042.22, "total_tokens": 928392} {"current_steps": 10305, "total_steps": 76960, "loss": 0.2296, "lr": 4.982529580803714e-05, "epoch": 2.678014553014553, "percentage": 13.39, "elapsed_time": "0:14:51", "remaining_time": "1:36:04", "throughput": 1042.31, "total_tokens": 928904} {"current_steps": 10310, "total_steps": 76960, "loss": 0.1824, "lr": 4.98246260729078e-05, "epoch": 2.6793139293139294, "percentage": 13.4, "elapsed_time": "0:14:51", "remaining_time": "1:36:03", "throughput": 1042.3, "total_tokens": 929336} {"current_steps": 10315, "total_steps": 76960, "loss": 0.3347, "lr": 4.982395506102415e-05, "epoch": 2.6806133056133055, "percentage": 13.4, "elapsed_time": "0:14:52", "remaining_time": "1:36:03", "throughput": 1042.34, "total_tokens": 929800} {"current_steps": 10320, "total_steps": 76960, "loss": 0.1855, "lr": 4.982328277242071e-05, "epoch": 2.681912681912682, "percentage": 13.41, "elapsed_time": "0:14:52", "remaining_time": "1:36:02", "throughput": 1042.35, "total_tokens": 930248} {"current_steps": 10325, "total_steps": 76960, "loss": 0.13, "lr": 4.9822609207132045e-05, "epoch": 2.6832120582120584, "percentage": 13.42, "elapsed_time": "0:14:52", "remaining_time": "1:36:02", "throughput": 1042.35, "total_tokens": 930680} {"current_steps": 10330, "total_steps": 76960, "loss": 0.1644, "lr": 4.9821934365192805e-05, "epoch": 2.6845114345114345, "percentage": 13.42, "elapsed_time": "0:14:53", "remaining_time": "1:36:01", "throughput": 1042.34, "total_tokens": 931112} {"current_steps": 10335, "total_steps": 76960, "loss": 0.2147, "lr": 4.98212582466377e-05, "epoch": 2.685810810810811, "percentage": 13.43, "elapsed_time": "0:14:53", "remaining_time": "1:36:01", "throughput": 1042.34, "total_tokens": 931544} {"current_steps": 10340, "total_steps": 76960, "loss": 0.1476, "lr": 4.98205808515015e-05, "epoch": 2.687110187110187, "percentage": 13.44, "elapsed_time": "0:14:54", "remaining_time": "1:36:00", "throughput": 1042.33, "total_tokens": 931976} {"current_steps": 10345, "total_steps": 76960, "loss": 0.137, "lr": 4.981990217981905e-05, "epoch": 2.6884095634095635, "percentage": 13.44, "elapsed_time": "0:14:54", "remaining_time": "1:36:00", "throughput": 1042.35, "total_tokens": 932424} {"current_steps": 10350, "total_steps": 76960, "loss": 0.2113, "lr": 4.9819222231625245e-05, "epoch": 2.6897089397089395, "percentage": 13.45, "elapsed_time": "0:14:54", "remaining_time": "1:35:59", "throughput": 1042.36, "total_tokens": 932872} {"current_steps": 10355, "total_steps": 76960, "loss": 0.3572, "lr": 4.981854100695506e-05, "epoch": 2.691008316008316, "percentage": 13.46, "elapsed_time": "0:14:55", "remaining_time": "1:35:59", "throughput": 1042.38, "total_tokens": 933320} {"current_steps": 10360, "total_steps": 76960, "loss": 0.3437, "lr": 4.981785850584353e-05, "epoch": 2.6923076923076925, "percentage": 13.46, "elapsed_time": "0:14:55", "remaining_time": "1:35:58", "throughput": 1042.37, "total_tokens": 933752} {"current_steps": 10365, "total_steps": 76960, "loss": 0.2157, "lr": 4.981717472832576e-05, "epoch": 2.6936070686070686, "percentage": 13.47, "elapsed_time": "0:14:56", "remaining_time": "1:35:58", "throughput": 1042.39, "total_tokens": 934200} {"current_steps": 10370, "total_steps": 76960, "loss": 0.2792, "lr": 4.9816489674436916e-05, "epoch": 2.694906444906445, "percentage": 13.47, "elapsed_time": "0:14:56", "remaining_time": "1:35:57", "throughput": 1042.38, "total_tokens": 934632} {"current_steps": 10375, "total_steps": 76960, "loss": 0.1876, "lr": 4.981580334421223e-05, "epoch": 2.696205821205821, "percentage": 13.48, "elapsed_time": "0:14:57", "remaining_time": "1:35:57", "throughput": 1042.38, "total_tokens": 935064} {"current_steps": 10380, "total_steps": 76960, "loss": 0.1731, "lr": 4.9815115737686995e-05, "epoch": 2.6975051975051976, "percentage": 13.49, "elapsed_time": "0:14:57", "remaining_time": "1:35:56", "throughput": 1042.38, "total_tokens": 935496} {"current_steps": 10385, "total_steps": 76960, "loss": 0.2087, "lr": 4.981442685489659e-05, "epoch": 2.6988045738045736, "percentage": 13.49, "elapsed_time": "0:14:57", "remaining_time": "1:35:56", "throughput": 1042.37, "total_tokens": 935928} {"current_steps": 10390, "total_steps": 76960, "loss": 0.2765, "lr": 4.981373669587642e-05, "epoch": 2.70010395010395, "percentage": 13.5, "elapsed_time": "0:14:58", "remaining_time": "1:35:55", "throughput": 1042.39, "total_tokens": 936376} {"current_steps": 10395, "total_steps": 76960, "loss": 0.2259, "lr": 4.981304526066202e-05, "epoch": 2.7014033264033266, "percentage": 13.51, "elapsed_time": "0:14:58", "remaining_time": "1:35:54", "throughput": 1042.4, "total_tokens": 936824} {"current_steps": 10400, "total_steps": 76960, "loss": 0.2077, "lr": 4.981235254928891e-05, "epoch": 2.7027027027027026, "percentage": 13.51, "elapsed_time": "0:14:59", "remaining_time": "1:35:54", "throughput": 1042.43, "total_tokens": 937288} {"current_steps": 10405, "total_steps": 76960, "loss": 0.3465, "lr": 4.981165856179274e-05, "epoch": 2.704002079002079, "percentage": 13.52, "elapsed_time": "0:14:59", "remaining_time": "1:35:53", "throughput": 1042.43, "total_tokens": 937720} {"current_steps": 10410, "total_steps": 76960, "loss": 0.2817, "lr": 4.981096329820919e-05, "epoch": 2.705301455301455, "percentage": 13.53, "elapsed_time": "0:14:59", "remaining_time": "1:35:53", "throughput": 1042.42, "total_tokens": 938152} {"current_steps": 10415, "total_steps": 76960, "loss": 0.2746, "lr": 4.981026675857403e-05, "epoch": 2.7066008316008316, "percentage": 13.53, "elapsed_time": "0:15:00", "remaining_time": "1:35:52", "throughput": 1042.43, "total_tokens": 938600} {"current_steps": 10420, "total_steps": 76960, "loss": 0.244, "lr": 4.980956894292308e-05, "epoch": 2.7079002079002077, "percentage": 13.54, "elapsed_time": "0:15:00", "remaining_time": "1:35:52", "throughput": 1042.48, "total_tokens": 939080} {"current_steps": 10425, "total_steps": 76960, "loss": 0.1774, "lr": 4.980886985129223e-05, "epoch": 2.709199584199584, "percentage": 13.55, "elapsed_time": "0:15:01", "remaining_time": "1:35:51", "throughput": 1042.49, "total_tokens": 939528} {"current_steps": 10430, "total_steps": 76960, "loss": 0.2756, "lr": 4.9808169483717427e-05, "epoch": 2.7104989604989607, "percentage": 13.55, "elapsed_time": "0:15:01", "remaining_time": "1:35:51", "throughput": 1042.49, "total_tokens": 939960} {"current_steps": 10435, "total_steps": 76960, "loss": 0.4027, "lr": 4.98074678402347e-05, "epoch": 2.7117983367983367, "percentage": 13.56, "elapsed_time": "0:15:02", "remaining_time": "1:35:50", "throughput": 1042.53, "total_tokens": 940440} {"current_steps": 10440, "total_steps": 76960, "loss": 0.2425, "lr": 4.980676492088013e-05, "epoch": 2.713097713097713, "percentage": 13.57, "elapsed_time": "0:15:02", "remaining_time": "1:35:50", "throughput": 1042.57, "total_tokens": 940904} {"current_steps": 10445, "total_steps": 76960, "loss": 0.2575, "lr": 4.980606072568988e-05, "epoch": 2.7143970893970892, "percentage": 13.57, "elapsed_time": "0:15:02", "remaining_time": "1:35:49", "throughput": 1042.56, "total_tokens": 941336} {"current_steps": 10450, "total_steps": 76960, "loss": 0.2054, "lr": 4.980535525470015e-05, "epoch": 2.7156964656964657, "percentage": 13.58, "elapsed_time": "0:15:03", "remaining_time": "1:35:49", "throughput": 1042.59, "total_tokens": 941800} {"current_steps": 10455, "total_steps": 76960, "loss": 0.2334, "lr": 4.980464850794724e-05, "epoch": 2.7169958419958418, "percentage": 13.58, "elapsed_time": "0:15:03", "remaining_time": "1:35:48", "throughput": 1042.61, "total_tokens": 942248} {"current_steps": 10460, "total_steps": 76960, "loss": 0.0117, "lr": 4.980394048546748e-05, "epoch": 2.7182952182952183, "percentage": 13.59, "elapsed_time": "0:15:04", "remaining_time": "1:35:48", "throughput": 1042.6, "total_tokens": 942680} {"current_steps": 10465, "total_steps": 76960, "loss": 0.2272, "lr": 4.9803231187297304e-05, "epoch": 2.7195945945945947, "percentage": 13.6, "elapsed_time": "0:15:04", "remaining_time": "1:35:47", "throughput": 1042.67, "total_tokens": 943176} {"current_steps": 10470, "total_steps": 76960, "loss": 0.3016, "lr": 4.980252061347318e-05, "epoch": 2.720893970893971, "percentage": 13.6, "elapsed_time": "0:15:04", "remaining_time": "1:35:47", "throughput": 1042.7, "total_tokens": 943640} {"current_steps": 10475, "total_steps": 76960, "loss": 0.664, "lr": 4.980180876403166e-05, "epoch": 2.7221933471933473, "percentage": 13.61, "elapsed_time": "0:15:05", "remaining_time": "1:35:46", "throughput": 1042.7, "total_tokens": 944072} {"current_steps": 10480, "total_steps": 76960, "loss": 0.5838, "lr": 4.9801095639009346e-05, "epoch": 2.7234927234927238, "percentage": 13.62, "elapsed_time": "0:15:05", "remaining_time": "1:35:46", "throughput": 1042.7, "total_tokens": 944504} {"current_steps": 10485, "total_steps": 76960, "loss": 0.3847, "lr": 4.980038123844292e-05, "epoch": 2.7247920997921, "percentage": 13.62, "elapsed_time": "0:15:06", "remaining_time": "1:35:45", "throughput": 1042.71, "total_tokens": 944952} {"current_steps": 10490, "total_steps": 76960, "loss": 0.2558, "lr": 4.979966556236912e-05, "epoch": 2.726091476091476, "percentage": 13.63, "elapsed_time": "0:15:06", "remaining_time": "1:35:45", "throughput": 1042.76, "total_tokens": 945432} {"current_steps": 10495, "total_steps": 76960, "loss": 0.2249, "lr": 4.9798948610824765e-05, "epoch": 2.7273908523908523, "percentage": 13.64, "elapsed_time": "0:15:07", "remaining_time": "1:35:44", "throughput": 1042.79, "total_tokens": 945896} {"current_steps": 10500, "total_steps": 76960, "loss": 0.3411, "lr": 4.9798230383846725e-05, "epoch": 2.728690228690229, "percentage": 13.64, "elapsed_time": "0:15:07", "remaining_time": "1:35:44", "throughput": 1042.82, "total_tokens": 946360} {"current_steps": 10505, "total_steps": 76960, "loss": 0.2611, "lr": 4.979751088147192e-05, "epoch": 2.729989604989605, "percentage": 13.65, "elapsed_time": "0:15:07", "remaining_time": "1:35:43", "throughput": 1042.8, "total_tokens": 946776} {"current_steps": 10510, "total_steps": 76960, "loss": 0.2902, "lr": 4.979679010373739e-05, "epoch": 2.7312889812889813, "percentage": 13.66, "elapsed_time": "0:15:08", "remaining_time": "1:35:43", "throughput": 1042.84, "total_tokens": 947256} {"current_steps": 10515, "total_steps": 76960, "loss": 0.2575, "lr": 4.979606805068017e-05, "epoch": 2.732588357588358, "percentage": 13.66, "elapsed_time": "0:15:08", "remaining_time": "1:35:42", "throughput": 1042.89, "total_tokens": 947736} {"current_steps": 10520, "total_steps": 76960, "loss": 0.3285, "lr": 4.979534472233742e-05, "epoch": 2.733887733887734, "percentage": 13.67, "elapsed_time": "0:15:09", "remaining_time": "1:35:41", "throughput": 1042.92, "total_tokens": 948200} {"current_steps": 10525, "total_steps": 76960, "loss": 0.2449, "lr": 4.9794620118746336e-05, "epoch": 2.73518711018711, "percentage": 13.68, "elapsed_time": "0:15:09", "remaining_time": "1:35:41", "throughput": 1042.92, "total_tokens": 948632} {"current_steps": 10530, "total_steps": 76960, "loss": 0.2382, "lr": 4.979389423994418e-05, "epoch": 2.7364864864864864, "percentage": 13.68, "elapsed_time": "0:15:10", "remaining_time": "1:35:40", "throughput": 1042.93, "total_tokens": 949080} {"current_steps": 10535, "total_steps": 76960, "loss": 0.2179, "lr": 4.979316708596829e-05, "epoch": 2.737785862785863, "percentage": 13.69, "elapsed_time": "0:15:10", "remaining_time": "1:35:40", "throughput": 1043.0, "total_tokens": 949576} {"current_steps": 10540, "total_steps": 76960, "loss": 0.2149, "lr": 4.9792438656856044e-05, "epoch": 2.739085239085239, "percentage": 13.7, "elapsed_time": "0:15:10", "remaining_time": "1:35:39", "throughput": 1043.01, "total_tokens": 950024} {"current_steps": 10545, "total_steps": 76960, "loss": 0.2224, "lr": 4.979170895264494e-05, "epoch": 2.7403846153846154, "percentage": 13.7, "elapsed_time": "0:15:11", "remaining_time": "1:35:39", "throughput": 1043.02, "total_tokens": 950472} {"current_steps": 10550, "total_steps": 76960, "loss": 0.421, "lr": 4.979097797337249e-05, "epoch": 2.741683991683992, "percentage": 13.71, "elapsed_time": "0:15:11", "remaining_time": "1:35:38", "throughput": 1043.04, "total_tokens": 950920} {"current_steps": 10555, "total_steps": 76960, "loss": 0.2164, "lr": 4.979024571907628e-05, "epoch": 2.742983367983368, "percentage": 13.71, "elapsed_time": "0:15:12", "remaining_time": "1:35:38", "throughput": 1043.07, "total_tokens": 951384} {"current_steps": 10560, "total_steps": 76960, "loss": 0.298, "lr": 4.978951218979398e-05, "epoch": 2.7442827442827444, "percentage": 13.72, "elapsed_time": "0:15:12", "remaining_time": "1:35:37", "throughput": 1043.08, "total_tokens": 951832} {"current_steps": 10565, "total_steps": 76960, "loss": 0.2284, "lr": 4.978877738556332e-05, "epoch": 2.7455821205821205, "percentage": 13.73, "elapsed_time": "0:15:12", "remaining_time": "1:35:37", "throughput": 1043.1, "total_tokens": 952280} {"current_steps": 10570, "total_steps": 76960, "loss": 0.2401, "lr": 4.9788041306422094e-05, "epoch": 2.746881496881497, "percentage": 13.73, "elapsed_time": "0:15:13", "remaining_time": "1:35:36", "throughput": 1043.11, "total_tokens": 952728} {"current_steps": 10575, "total_steps": 76960, "loss": 0.2692, "lr": 4.978730395240815e-05, "epoch": 2.748180873180873, "percentage": 13.74, "elapsed_time": "0:15:13", "remaining_time": "1:35:36", "throughput": 1043.12, "total_tokens": 953176} {"current_steps": 10580, "total_steps": 76960, "loss": 0.2027, "lr": 4.978656532355941e-05, "epoch": 2.7494802494802495, "percentage": 13.75, "elapsed_time": "0:15:14", "remaining_time": "1:35:35", "throughput": 1043.1, "total_tokens": 953592} {"current_steps": 10585, "total_steps": 76960, "loss": 0.2099, "lr": 4.978582541991386e-05, "epoch": 2.750779625779626, "percentage": 13.75, "elapsed_time": "0:15:14", "remaining_time": "1:35:35", "throughput": 1043.15, "total_tokens": 954072} {"current_steps": 10590, "total_steps": 76960, "loss": 0.1534, "lr": 4.978508424150957e-05, "epoch": 2.752079002079002, "percentage": 13.76, "elapsed_time": "0:15:15", "remaining_time": "1:35:34", "throughput": 1043.19, "total_tokens": 954552} {"current_steps": 10595, "total_steps": 76960, "loss": 0.3351, "lr": 4.9784341788384646e-05, "epoch": 2.7533783783783785, "percentage": 13.77, "elapsed_time": "0:15:15", "remaining_time": "1:35:34", "throughput": 1043.15, "total_tokens": 954952} {"current_steps": 10600, "total_steps": 76960, "loss": 0.2846, "lr": 4.978359806057727e-05, "epoch": 2.7546777546777546, "percentage": 13.77, "elapsed_time": "0:15:15", "remaining_time": "1:35:33", "throughput": 1043.18, "total_tokens": 955416} {"current_steps": 10605, "total_steps": 76960, "loss": 0.2572, "lr": 4.978285305812571e-05, "epoch": 2.755977130977131, "percentage": 13.78, "elapsed_time": "0:15:16", "remaining_time": "1:35:33", "throughput": 1043.21, "total_tokens": 955880} {"current_steps": 10610, "total_steps": 76960, "loss": 0.1848, "lr": 4.978210678106827e-05, "epoch": 2.757276507276507, "percentage": 13.79, "elapsed_time": "0:15:16", "remaining_time": "1:35:32", "throughput": 1043.22, "total_tokens": 956328} {"current_steps": 10615, "total_steps": 76960, "loss": 0.2212, "lr": 4.978135922944333e-05, "epoch": 2.7585758835758836, "percentage": 13.79, "elapsed_time": "0:15:17", "remaining_time": "1:35:32", "throughput": 1043.24, "total_tokens": 956792} {"current_steps": 10620, "total_steps": 76960, "loss": 0.4174, "lr": 4.9780610403289344e-05, "epoch": 2.75987525987526, "percentage": 13.8, "elapsed_time": "0:15:17", "remaining_time": "1:35:31", "throughput": 1043.2, "total_tokens": 957192} {"current_steps": 10625, "total_steps": 76960, "loss": 0.1998, "lr": 4.977986030264482e-05, "epoch": 2.761174636174636, "percentage": 13.81, "elapsed_time": "0:15:17", "remaining_time": "1:35:31", "throughput": 1043.22, "total_tokens": 957640} {"current_steps": 10630, "total_steps": 76960, "loss": 0.3082, "lr": 4.9779108927548336e-05, "epoch": 2.7624740124740126, "percentage": 13.81, "elapsed_time": "0:15:18", "remaining_time": "1:35:30", "throughput": 1043.21, "total_tokens": 958072} {"current_steps": 10635, "total_steps": 76960, "loss": 0.3381, "lr": 4.9778356278038535e-05, "epoch": 2.7637733887733886, "percentage": 13.82, "elapsed_time": "0:15:18", "remaining_time": "1:35:30", "throughput": 1043.25, "total_tokens": 958536} {"current_steps": 10640, "total_steps": 76960, "loss": 0.2985, "lr": 4.9777602354154126e-05, "epoch": 2.765072765072765, "percentage": 13.83, "elapsed_time": "0:15:19", "remaining_time": "1:35:29", "throughput": 1043.28, "total_tokens": 959000} {"current_steps": 10645, "total_steps": 76960, "loss": 0.3165, "lr": 4.9776847155933896e-05, "epoch": 2.766372141372141, "percentage": 13.83, "elapsed_time": "0:15:19", "remaining_time": "1:35:29", "throughput": 1043.29, "total_tokens": 959448} {"current_steps": 10650, "total_steps": 76960, "loss": 0.2761, "lr": 4.9776090683416674e-05, "epoch": 2.7676715176715176, "percentage": 13.84, "elapsed_time": "0:15:20", "remaining_time": "1:35:28", "throughput": 1043.27, "total_tokens": 959864} {"current_steps": 10655, "total_steps": 76960, "loss": 0.3023, "lr": 4.9775332936641374e-05, "epoch": 2.768970893970894, "percentage": 13.84, "elapsed_time": "0:15:20", "remaining_time": "1:35:28", "throughput": 1043.3, "total_tokens": 960328} {"current_steps": 10660, "total_steps": 76960, "loss": 0.2395, "lr": 4.9774573915646955e-05, "epoch": 2.77027027027027, "percentage": 13.85, "elapsed_time": "0:15:20", "remaining_time": "1:35:27", "throughput": 1043.29, "total_tokens": 960760} {"current_steps": 10665, "total_steps": 76960, "loss": 0.1832, "lr": 4.977381362047247e-05, "epoch": 2.7715696465696467, "percentage": 13.86, "elapsed_time": "0:15:21", "remaining_time": "1:35:26", "throughput": 1043.29, "total_tokens": 961192} {"current_steps": 10670, "total_steps": 76960, "loss": 0.2933, "lr": 4.9773052051157e-05, "epoch": 2.7728690228690227, "percentage": 13.86, "elapsed_time": "0:15:21", "remaining_time": "1:35:26", "throughput": 1043.26, "total_tokens": 961608} {"current_steps": 10675, "total_steps": 76960, "loss": 0.247, "lr": 4.977228920773974e-05, "epoch": 2.774168399168399, "percentage": 13.87, "elapsed_time": "0:15:22", "remaining_time": "1:35:25", "throughput": 1043.28, "total_tokens": 962056} {"current_steps": 10680, "total_steps": 76960, "loss": 0.2048, "lr": 4.9771525090259896e-05, "epoch": 2.7754677754677752, "percentage": 13.88, "elapsed_time": "0:15:22", "remaining_time": "1:35:25", "throughput": 1043.27, "total_tokens": 962488} {"current_steps": 10685, "total_steps": 76960, "loss": 0.2012, "lr": 4.9770759698756797e-05, "epoch": 2.7767671517671517, "percentage": 13.88, "elapsed_time": "0:15:22", "remaining_time": "1:35:24", "throughput": 1043.34, "total_tokens": 962984} {"current_steps": 10690, "total_steps": 76960, "loss": 0.2908, "lr": 4.976999303326978e-05, "epoch": 2.778066528066528, "percentage": 13.89, "elapsed_time": "0:15:23", "remaining_time": "1:35:24", "throughput": 1043.4, "total_tokens": 963480} {"current_steps": 10695, "total_steps": 76960, "loss": 0.296, "lr": 4.9769225093838294e-05, "epoch": 2.7793659043659042, "percentage": 13.9, "elapsed_time": "0:15:23", "remaining_time": "1:35:23", "throughput": 1043.41, "total_tokens": 963928} {"current_steps": 10700, "total_steps": 76960, "loss": 0.2533, "lr": 4.976845588050183e-05, "epoch": 2.7806652806652807, "percentage": 13.9, "elapsed_time": "0:15:24", "remaining_time": "1:35:23", "throughput": 1043.41, "total_tokens": 964360} {"current_steps": 10705, "total_steps": 76960, "loss": 0.2949, "lr": 4.976768539329994e-05, "epoch": 2.7819646569646572, "percentage": 13.91, "elapsed_time": "0:15:24", "remaining_time": "1:35:22", "throughput": 1043.4, "total_tokens": 964792} {"current_steps": 10710, "total_steps": 76960, "loss": 0.2749, "lr": 4.976691363227227e-05, "epoch": 2.7832640332640333, "percentage": 13.92, "elapsed_time": "0:15:25", "remaining_time": "1:35:22", "throughput": 1043.43, "total_tokens": 965256} {"current_steps": 10715, "total_steps": 76960, "loss": 0.3522, "lr": 4.97661405974585e-05, "epoch": 2.7845634095634093, "percentage": 13.92, "elapsed_time": "0:15:25", "remaining_time": "1:35:21", "throughput": 1043.46, "total_tokens": 965720} {"current_steps": 10720, "total_steps": 76960, "loss": 0.2569, "lr": 4.9765366288898384e-05, "epoch": 2.785862785862786, "percentage": 13.93, "elapsed_time": "0:15:25", "remaining_time": "1:35:21", "throughput": 1043.44, "total_tokens": 966136} {"current_steps": 10725, "total_steps": 76960, "loss": 0.2886, "lr": 4.9764590706631755e-05, "epoch": 2.7871621621621623, "percentage": 13.94, "elapsed_time": "0:15:26", "remaining_time": "1:35:20", "throughput": 1043.47, "total_tokens": 966600} {"current_steps": 10730, "total_steps": 76960, "loss": 0.1599, "lr": 4.9763813850698494e-05, "epoch": 2.7884615384615383, "percentage": 13.94, "elapsed_time": "0:15:26", "remaining_time": "1:35:20", "throughput": 1043.49, "total_tokens": 967048} {"current_steps": 10735, "total_steps": 76960, "loss": 0.3823, "lr": 4.9763035721138556e-05, "epoch": 2.789760914760915, "percentage": 13.95, "elapsed_time": "0:15:27", "remaining_time": "1:35:19", "throughput": 1043.48, "total_tokens": 967480} {"current_steps": 10740, "total_steps": 76960, "loss": 0.2271, "lr": 4.976225631799197e-05, "epoch": 2.7910602910602913, "percentage": 13.96, "elapsed_time": "0:15:27", "remaining_time": "1:35:19", "throughput": 1043.49, "total_tokens": 967928} {"current_steps": 10745, "total_steps": 76960, "loss": 0.2574, "lr": 4.9761475641298815e-05, "epoch": 2.7923596673596673, "percentage": 13.96, "elapsed_time": "0:15:28", "remaining_time": "1:35:18", "throughput": 1043.49, "total_tokens": 968360} {"current_steps": 10750, "total_steps": 76960, "loss": 0.1906, "lr": 4.9760693691099244e-05, "epoch": 2.7936590436590434, "percentage": 13.97, "elapsed_time": "0:15:28", "remaining_time": "1:35:18", "throughput": 1043.5, "total_tokens": 968808} {"current_steps": 10755, "total_steps": 76960, "loss": 0.3968, "lr": 4.975991046743347e-05, "epoch": 2.79495841995842, "percentage": 13.97, "elapsed_time": "0:15:28", "remaining_time": "1:35:17", "throughput": 1043.53, "total_tokens": 969272} {"current_steps": 10760, "total_steps": 76960, "loss": 0.2521, "lr": 4.975912597034177e-05, "epoch": 2.7962577962577964, "percentage": 13.98, "elapsed_time": "0:15:29", "remaining_time": "1:35:17", "throughput": 1043.56, "total_tokens": 969736} {"current_steps": 10765, "total_steps": 76960, "loss": 0.2168, "lr": 4.975834019986451e-05, "epoch": 2.7975571725571724, "percentage": 13.99, "elapsed_time": "0:15:29", "remaining_time": "1:35:16", "throughput": 1043.54, "total_tokens": 970152} {"current_steps": 10770, "total_steps": 76960, "loss": 0.2577, "lr": 4.975755315604208e-05, "epoch": 2.798856548856549, "percentage": 13.99, "elapsed_time": "0:15:30", "remaining_time": "1:35:16", "throughput": 1043.54, "total_tokens": 970584} {"current_steps": 10775, "total_steps": 76960, "loss": 0.2903, "lr": 4.9756764838914976e-05, "epoch": 2.8001559251559254, "percentage": 14.0, "elapsed_time": "0:15:30", "remaining_time": "1:35:15", "throughput": 1043.51, "total_tokens": 971000} {"current_steps": 10780, "total_steps": 76960, "loss": 0.2881, "lr": 4.975597524852374e-05, "epoch": 2.8014553014553014, "percentage": 14.01, "elapsed_time": "0:15:30", "remaining_time": "1:35:15", "throughput": 1043.48, "total_tokens": 971416} {"current_steps": 10785, "total_steps": 76960, "loss": 0.1648, "lr": 4.975518438490897e-05, "epoch": 2.802754677754678, "percentage": 14.01, "elapsed_time": "0:15:31", "remaining_time": "1:35:14", "throughput": 1043.5, "total_tokens": 971864} {"current_steps": 10790, "total_steps": 76960, "loss": 0.3211, "lr": 4.975439224811135e-05, "epoch": 2.804054054054054, "percentage": 14.02, "elapsed_time": "0:15:31", "remaining_time": "1:35:14", "throughput": 1043.49, "total_tokens": 972296} {"current_steps": 10795, "total_steps": 76960, "loss": 0.3028, "lr": 4.975359883817161e-05, "epoch": 2.8053534303534304, "percentage": 14.03, "elapsed_time": "0:15:32", "remaining_time": "1:35:13", "throughput": 1043.52, "total_tokens": 972760} {"current_steps": 10800, "total_steps": 76960, "loss": 0.2269, "lr": 4.9752804155130574e-05, "epoch": 2.8066528066528065, "percentage": 14.03, "elapsed_time": "0:15:32", "remaining_time": "1:35:13", "throughput": 1043.53, "total_tokens": 973208} {"current_steps": 10805, "total_steps": 76960, "loss": 0.2605, "lr": 4.97520081990291e-05, "epoch": 2.807952182952183, "percentage": 14.04, "elapsed_time": "0:15:33", "remaining_time": "1:35:12", "throughput": 1043.55, "total_tokens": 973656} {"current_steps": 10810, "total_steps": 76960, "loss": 0.2642, "lr": 4.9751210969908134e-05, "epoch": 2.8092515592515594, "percentage": 14.05, "elapsed_time": "0:15:33", "remaining_time": "1:35:12", "throughput": 1043.56, "total_tokens": 974104} {"current_steps": 10815, "total_steps": 76960, "loss": 0.2633, "lr": 4.975041246780866e-05, "epoch": 2.8105509355509355, "percentage": 14.05, "elapsed_time": "0:15:33", "remaining_time": "1:35:11", "throughput": 1043.61, "total_tokens": 974584} {"current_steps": 10820, "total_steps": 76960, "loss": 0.2263, "lr": 4.9749612692771776e-05, "epoch": 2.811850311850312, "percentage": 14.06, "elapsed_time": "0:15:34", "remaining_time": "1:35:11", "throughput": 1043.62, "total_tokens": 975032} {"current_steps": 10825, "total_steps": 76960, "loss": 0.2179, "lr": 4.9748811644838584e-05, "epoch": 2.813149688149688, "percentage": 14.07, "elapsed_time": "0:15:34", "remaining_time": "1:35:10", "throughput": 1043.61, "total_tokens": 975464} {"current_steps": 10830, "total_steps": 76960, "loss": 0.2629, "lr": 4.974800932405029e-05, "epoch": 2.8144490644490645, "percentage": 14.07, "elapsed_time": "0:15:35", "remaining_time": "1:35:10", "throughput": 1043.57, "total_tokens": 975864} {"current_steps": 10835, "total_steps": 76960, "loss": 0.256, "lr": 4.974720573044818e-05, "epoch": 2.8157484407484406, "percentage": 14.08, "elapsed_time": "0:15:35", "remaining_time": "1:35:09", "throughput": 1043.64, "total_tokens": 976360} {"current_steps": 10840, "total_steps": 76960, "loss": 0.2, "lr": 4.974640086407356e-05, "epoch": 2.817047817047817, "percentage": 14.09, "elapsed_time": "0:15:35", "remaining_time": "1:35:08", "throughput": 1043.63, "total_tokens": 976792} {"current_steps": 10845, "total_steps": 76960, "loss": 0.3297, "lr": 4.974559472496784e-05, "epoch": 2.8183471933471935, "percentage": 14.09, "elapsed_time": "0:15:36", "remaining_time": "1:35:08", "throughput": 1043.65, "total_tokens": 977240} {"current_steps": 10850, "total_steps": 76960, "loss": 0.3262, "lr": 4.974478731317246e-05, "epoch": 2.8196465696465696, "percentage": 14.1, "elapsed_time": "0:15:36", "remaining_time": "1:35:07", "throughput": 1043.68, "total_tokens": 977704} {"current_steps": 10855, "total_steps": 76960, "loss": 0.2158, "lr": 4.9743978628728965e-05, "epoch": 2.820945945945946, "percentage": 14.1, "elapsed_time": "0:15:37", "remaining_time": "1:35:07", "throughput": 1043.71, "total_tokens": 978168} {"current_steps": 10860, "total_steps": 76960, "loss": 0.1924, "lr": 4.974316867167894e-05, "epoch": 2.822245322245322, "percentage": 14.11, "elapsed_time": "0:15:37", "remaining_time": "1:35:06", "throughput": 1043.76, "total_tokens": 978648} {"current_steps": 10865, "total_steps": 76960, "loss": 0.2223, "lr": 4.9742357442064045e-05, "epoch": 2.8235446985446986, "percentage": 14.12, "elapsed_time": "0:15:38", "remaining_time": "1:35:06", "throughput": 1043.75, "total_tokens": 979080} {"current_steps": 10870, "total_steps": 76960, "loss": 0.2631, "lr": 4.9741544939926e-05, "epoch": 2.8248440748440746, "percentage": 14.12, "elapsed_time": "0:15:38", "remaining_time": "1:35:05", "throughput": 1043.75, "total_tokens": 979512} {"current_steps": 10875, "total_steps": 76960, "loss": 0.3197, "lr": 4.9740731165306585e-05, "epoch": 2.826143451143451, "percentage": 14.13, "elapsed_time": "0:15:38", "remaining_time": "1:35:05", "throughput": 1043.8, "total_tokens": 979992} {"current_steps": 10880, "total_steps": 76960, "loss": 0.2165, "lr": 4.973991611824767e-05, "epoch": 2.8274428274428276, "percentage": 14.14, "elapsed_time": "0:15:39", "remaining_time": "1:35:04", "throughput": 1043.79, "total_tokens": 980424} {"current_steps": 10885, "total_steps": 76960, "loss": 0.3029, "lr": 4.973909979879116e-05, "epoch": 2.8287422037422036, "percentage": 14.14, "elapsed_time": "0:15:39", "remaining_time": "1:35:04", "throughput": 1043.8, "total_tokens": 980872} {"current_steps": 10890, "total_steps": 76960, "loss": 0.2111, "lr": 4.973828220697905e-05, "epoch": 2.83004158004158, "percentage": 14.15, "elapsed_time": "0:15:40", "remaining_time": "1:35:03", "throughput": 1043.8, "total_tokens": 981304} {"current_steps": 10895, "total_steps": 76960, "loss": 0.2876, "lr": 4.973746334285337e-05, "epoch": 2.8313409563409566, "percentage": 14.16, "elapsed_time": "0:15:40", "remaining_time": "1:35:03", "throughput": 1043.79, "total_tokens": 981736} {"current_steps": 10900, "total_steps": 76960, "loss": 0.2648, "lr": 4.9736643206456256e-05, "epoch": 2.8326403326403327, "percentage": 14.16, "elapsed_time": "0:15:40", "remaining_time": "1:35:02", "throughput": 1043.82, "total_tokens": 982200} {"current_steps": 10905, "total_steps": 76960, "loss": 0.2996, "lr": 4.9735821797829884e-05, "epoch": 2.8339397089397087, "percentage": 14.17, "elapsed_time": "0:15:41", "remaining_time": "1:35:02", "throughput": 1043.85, "total_tokens": 982664} {"current_steps": 10910, "total_steps": 76960, "loss": 0.3081, "lr": 4.973499911701649e-05, "epoch": 2.835239085239085, "percentage": 14.18, "elapsed_time": "0:15:41", "remaining_time": "1:35:01", "throughput": 1043.81, "total_tokens": 983064} {"current_steps": 10915, "total_steps": 76960, "loss": 0.2811, "lr": 4.97341751640584e-05, "epoch": 2.8365384615384617, "percentage": 14.18, "elapsed_time": "0:15:42", "remaining_time": "1:35:01", "throughput": 1043.83, "total_tokens": 983512} {"current_steps": 10920, "total_steps": 76960, "loss": 0.2809, "lr": 4.973334993899798e-05, "epoch": 2.8378378378378377, "percentage": 14.19, "elapsed_time": "0:15:42", "remaining_time": "1:35:00", "throughput": 1043.82, "total_tokens": 983944} {"current_steps": 10925, "total_steps": 76960, "loss": 0.2263, "lr": 4.973252344187766e-05, "epoch": 2.839137214137214, "percentage": 14.2, "elapsed_time": "0:15:43", "remaining_time": "1:35:00", "throughput": 1043.87, "total_tokens": 984424} {"current_steps": 10930, "total_steps": 76960, "loss": 0.2271, "lr": 4.973169567273998e-05, "epoch": 2.8404365904365907, "percentage": 14.2, "elapsed_time": "0:15:43", "remaining_time": "1:34:59", "throughput": 1043.88, "total_tokens": 984872} {"current_steps": 10935, "total_steps": 76960, "loss": 0.2484, "lr": 4.9730866631627484e-05, "epoch": 2.8417359667359667, "percentage": 14.21, "elapsed_time": "0:15:43", "remaining_time": "1:34:59", "throughput": 1043.88, "total_tokens": 985304} {"current_steps": 10940, "total_steps": 76960, "loss": 0.3743, "lr": 4.973003631858282e-05, "epoch": 2.8430353430353428, "percentage": 14.22, "elapsed_time": "0:15:44", "remaining_time": "1:34:58", "throughput": 1043.85, "total_tokens": 985720} {"current_steps": 10945, "total_steps": 76960, "loss": 0.2719, "lr": 4.972920473364869e-05, "epoch": 2.8443347193347193, "percentage": 14.22, "elapsed_time": "0:15:44", "remaining_time": "1:34:58", "throughput": 1043.86, "total_tokens": 986168} {"current_steps": 10950, "total_steps": 76960, "loss": 0.2689, "lr": 4.972837187686788e-05, "epoch": 2.8456340956340958, "percentage": 14.23, "elapsed_time": "0:15:45", "remaining_time": "1:34:57", "throughput": 1043.88, "total_tokens": 986616} {"current_steps": 10955, "total_steps": 76960, "loss": 0.1664, "lr": 4.9727537748283206e-05, "epoch": 2.846933471933472, "percentage": 14.23, "elapsed_time": "0:15:45", "remaining_time": "1:34:57", "throughput": 1043.87, "total_tokens": 987048} {"current_steps": 10960, "total_steps": 76960, "loss": 0.215, "lr": 4.972670234793757e-05, "epoch": 2.8482328482328483, "percentage": 14.24, "elapsed_time": "0:15:45", "remaining_time": "1:34:56", "throughput": 1043.86, "total_tokens": 987480} {"current_steps": 10965, "total_steps": 76960, "loss": 0.155, "lr": 4.972586567587394e-05, "epoch": 2.8495322245322248, "percentage": 14.25, "elapsed_time": "0:15:46", "remaining_time": "1:34:56", "throughput": 1043.89, "total_tokens": 987944} {"current_steps": 10970, "total_steps": 76960, "loss": 0.1378, "lr": 4.972502773213534e-05, "epoch": 2.850831600831601, "percentage": 14.25, "elapsed_time": "0:15:46", "remaining_time": "1:34:55", "throughput": 1043.94, "total_tokens": 988424} {"current_steps": 10975, "total_steps": 76960, "loss": 0.306, "lr": 4.972418851676489e-05, "epoch": 2.8521309771309773, "percentage": 14.26, "elapsed_time": "0:15:47", "remaining_time": "1:34:55", "throughput": 1043.96, "total_tokens": 988888} {"current_steps": 10980, "total_steps": 76960, "loss": 0.346, "lr": 4.972334802980573e-05, "epoch": 2.8534303534303533, "percentage": 14.27, "elapsed_time": "0:15:47", "remaining_time": "1:34:54", "throughput": 1044.01, "total_tokens": 989368} {"current_steps": 10985, "total_steps": 76960, "loss": 0.3959, "lr": 4.972250627130108e-05, "epoch": 2.85472972972973, "percentage": 14.27, "elapsed_time": "0:15:48", "remaining_time": "1:34:54", "throughput": 1044.02, "total_tokens": 989816} {"current_steps": 10990, "total_steps": 76960, "loss": 0.2694, "lr": 4.9721663241294256e-05, "epoch": 2.856029106029106, "percentage": 14.28, "elapsed_time": "0:15:48", "remaining_time": "1:34:53", "throughput": 1044.07, "total_tokens": 990296} {"current_steps": 10995, "total_steps": 76960, "loss": 0.2753, "lr": 4.97208189398286e-05, "epoch": 2.8573284823284824, "percentage": 14.29, "elapsed_time": "0:15:48", "remaining_time": "1:34:53", "throughput": 1044.1, "total_tokens": 990760} {"current_steps": 11000, "total_steps": 76960, "loss": 0.2632, "lr": 4.9719973366947545e-05, "epoch": 2.858627858627859, "percentage": 14.29, "elapsed_time": "0:15:49", "remaining_time": "1:34:52", "throughput": 1044.11, "total_tokens": 991208} {"current_steps": 11005, "total_steps": 76960, "loss": 0.1757, "lr": 4.971912652269457e-05, "epoch": 2.859927234927235, "percentage": 14.3, "elapsed_time": "0:15:49", "remaining_time": "1:34:52", "throughput": 1044.16, "total_tokens": 991688} {"current_steps": 11010, "total_steps": 76960, "loss": 0.28, "lr": 4.971827840711323e-05, "epoch": 2.8612266112266114, "percentage": 14.31, "elapsed_time": "0:15:50", "remaining_time": "1:34:51", "throughput": 1044.15, "total_tokens": 992120} {"current_steps": 11015, "total_steps": 76960, "loss": 0.0825, "lr": 4.9717429020247156e-05, "epoch": 2.8625259875259874, "percentage": 14.31, "elapsed_time": "0:15:50", "remaining_time": "1:34:51", "throughput": 1044.16, "total_tokens": 992568} {"current_steps": 11020, "total_steps": 76960, "loss": 0.3019, "lr": 4.9716578362140016e-05, "epoch": 2.863825363825364, "percentage": 14.32, "elapsed_time": "0:15:51", "remaining_time": "1:34:50", "throughput": 1044.2, "total_tokens": 993032} {"current_steps": 11025, "total_steps": 76960, "loss": 0.3698, "lr": 4.971572643283557e-05, "epoch": 2.86512474012474, "percentage": 14.33, "elapsed_time": "0:15:51", "remaining_time": "1:34:49", "throughput": 1044.21, "total_tokens": 993480} {"current_steps": 11030, "total_steps": 76960, "loss": 0.2235, "lr": 4.9714873232377635e-05, "epoch": 2.8664241164241164, "percentage": 14.33, "elapsed_time": "0:15:51", "remaining_time": "1:34:49", "throughput": 1044.19, "total_tokens": 993896} {"current_steps": 11035, "total_steps": 76960, "loss": 0.3222, "lr": 4.971401876081009e-05, "epoch": 2.867723492723493, "percentage": 14.34, "elapsed_time": "0:15:52", "remaining_time": "1:34:48", "throughput": 1044.25, "total_tokens": 994392} {"current_steps": 11040, "total_steps": 76960, "loss": 0.2599, "lr": 4.9713163018176876e-05, "epoch": 2.869022869022869, "percentage": 14.35, "elapsed_time": "0:15:52", "remaining_time": "1:34:48", "throughput": 1044.3, "total_tokens": 994872} {"current_steps": 11045, "total_steps": 76960, "loss": 0.245, "lr": 4.971230600452201e-05, "epoch": 2.8703222453222454, "percentage": 14.35, "elapsed_time": "0:15:53", "remaining_time": "1:34:47", "throughput": 1044.27, "total_tokens": 995288} {"current_steps": 11050, "total_steps": 76960, "loss": 0.288, "lr": 4.971144771988957e-05, "epoch": 2.8716216216216215, "percentage": 14.36, "elapsed_time": "0:15:53", "remaining_time": "1:34:47", "throughput": 1044.29, "total_tokens": 995736} {"current_steps": 11055, "total_steps": 76960, "loss": 0.2882, "lr": 4.971058816432369e-05, "epoch": 2.872920997920998, "percentage": 14.36, "elapsed_time": "0:15:53", "remaining_time": "1:34:46", "throughput": 1044.28, "total_tokens": 996168} {"current_steps": 11060, "total_steps": 76960, "loss": 0.2422, "lr": 4.970972733786859e-05, "epoch": 2.874220374220374, "percentage": 14.37, "elapsed_time": "0:15:54", "remaining_time": "1:34:46", "throughput": 1044.26, "total_tokens": 996584} {"current_steps": 11065, "total_steps": 76960, "loss": 0.2291, "lr": 4.970886524056854e-05, "epoch": 2.8755197505197505, "percentage": 14.38, "elapsed_time": "0:15:54", "remaining_time": "1:34:45", "throughput": 1044.27, "total_tokens": 997032} {"current_steps": 11070, "total_steps": 76960, "loss": 0.3267, "lr": 4.970800187246787e-05, "epoch": 2.876819126819127, "percentage": 14.38, "elapsed_time": "0:15:55", "remaining_time": "1:34:45", "throughput": 1044.29, "total_tokens": 997480} {"current_steps": 11075, "total_steps": 76960, "loss": 0.2176, "lr": 4.9707137233610994e-05, "epoch": 2.878118503118503, "percentage": 14.39, "elapsed_time": "0:15:55", "remaining_time": "1:34:44", "throughput": 1044.31, "total_tokens": 997944} {"current_steps": 11080, "total_steps": 76960, "loss": 0.2515, "lr": 4.970627132404238e-05, "epoch": 2.8794178794178795, "percentage": 14.4, "elapsed_time": "0:15:56", "remaining_time": "1:34:44", "throughput": 1044.34, "total_tokens": 998408} {"current_steps": 11085, "total_steps": 76960, "loss": 0.2708, "lr": 4.9705404143806555e-05, "epoch": 2.8807172557172556, "percentage": 14.4, "elapsed_time": "0:15:56", "remaining_time": "1:34:43", "throughput": 1044.35, "total_tokens": 998856} {"current_steps": 11090, "total_steps": 76960, "loss": 0.2921, "lr": 4.970453569294812e-05, "epoch": 2.882016632016632, "percentage": 14.41, "elapsed_time": "0:15:56", "remaining_time": "1:34:43", "throughput": 1044.37, "total_tokens": 999304} {"current_steps": 11095, "total_steps": 76960, "loss": 0.2352, "lr": 4.970366597151175e-05, "epoch": 2.883316008316008, "percentage": 14.42, "elapsed_time": "0:15:57", "remaining_time": "1:34:42", "throughput": 1044.38, "total_tokens": 999752} {"current_steps": 11100, "total_steps": 76960, "loss": 0.2745, "lr": 4.970279497954216e-05, "epoch": 2.8846153846153846, "percentage": 14.42, "elapsed_time": "0:15:57", "remaining_time": "1:34:42", "throughput": 1044.37, "total_tokens": 1000184} {"current_steps": 11105, "total_steps": 76960, "loss": 0.242, "lr": 4.970192271708416e-05, "epoch": 2.885914760914761, "percentage": 14.43, "elapsed_time": "0:15:58", "remaining_time": "1:34:41", "throughput": 1044.38, "total_tokens": 1000632} {"current_steps": 11110, "total_steps": 76960, "loss": 0.3146, "lr": 4.9701049184182616e-05, "epoch": 2.887214137214137, "percentage": 14.44, "elapsed_time": "0:15:58", "remaining_time": "1:34:41", "throughput": 1044.4, "total_tokens": 1001080} {"current_steps": 11115, "total_steps": 76960, "loss": 0.2013, "lr": 4.970017438088243e-05, "epoch": 2.8885135135135136, "percentage": 14.44, "elapsed_time": "0:15:58", "remaining_time": "1:34:40", "throughput": 1044.41, "total_tokens": 1001528} {"current_steps": 11120, "total_steps": 76960, "loss": 0.2186, "lr": 4.9699298307228616e-05, "epoch": 2.88981288981289, "percentage": 14.45, "elapsed_time": "0:15:59", "remaining_time": "1:34:40", "throughput": 1044.42, "total_tokens": 1001976} {"current_steps": 11125, "total_steps": 76960, "loss": 0.1574, "lr": 4.969842096326622e-05, "epoch": 2.891112266112266, "percentage": 14.46, "elapsed_time": "0:15:59", "remaining_time": "1:34:39", "throughput": 1044.43, "total_tokens": 1002424} {"current_steps": 11130, "total_steps": 76960, "loss": 0.3257, "lr": 4.9697542349040375e-05, "epoch": 2.892411642411642, "percentage": 14.46, "elapsed_time": "0:16:00", "remaining_time": "1:34:39", "throughput": 1044.46, "total_tokens": 1002888} {"current_steps": 11135, "total_steps": 76960, "loss": 0.2828, "lr": 4.969666246459626e-05, "epoch": 2.8937110187110187, "percentage": 14.47, "elapsed_time": "0:16:00", "remaining_time": "1:34:38", "throughput": 1044.45, "total_tokens": 1003320} {"current_steps": 11140, "total_steps": 76960, "loss": 0.2648, "lr": 4.9695781309979135e-05, "epoch": 2.895010395010395, "percentage": 14.48, "elapsed_time": "0:16:01", "remaining_time": "1:34:38", "throughput": 1044.48, "total_tokens": 1003784} {"current_steps": 11145, "total_steps": 76960, "loss": 0.3482, "lr": 4.969489888523431e-05, "epoch": 2.896309771309771, "percentage": 14.48, "elapsed_time": "0:16:01", "remaining_time": "1:34:37", "throughput": 1044.54, "total_tokens": 1004280} {"current_steps": 11150, "total_steps": 76960, "loss": 0.2188, "lr": 4.9694015190407176e-05, "epoch": 2.8976091476091477, "percentage": 14.49, "elapsed_time": "0:16:01", "remaining_time": "1:34:37", "throughput": 1044.55, "total_tokens": 1004728} {"current_steps": 11155, "total_steps": 76960, "loss": 0.2792, "lr": 4.969313022554318e-05, "epoch": 2.898908523908524, "percentage": 14.49, "elapsed_time": "0:16:02", "remaining_time": "1:34:36", "throughput": 1044.58, "total_tokens": 1005192} {"current_steps": 11160, "total_steps": 76960, "loss": 0.2808, "lr": 4.9692243990687834e-05, "epoch": 2.9002079002079, "percentage": 14.5, "elapsed_time": "0:16:02", "remaining_time": "1:34:36", "throughput": 1044.56, "total_tokens": 1005608} {"current_steps": 11165, "total_steps": 76960, "loss": 0.2762, "lr": 4.969135648588672e-05, "epoch": 2.9015072765072762, "percentage": 14.51, "elapsed_time": "0:16:03", "remaining_time": "1:34:35", "throughput": 1044.59, "total_tokens": 1006072} {"current_steps": 11170, "total_steps": 76960, "loss": 0.1792, "lr": 4.969046771118549e-05, "epoch": 2.9028066528066527, "percentage": 14.51, "elapsed_time": "0:16:03", "remaining_time": "1:34:35", "throughput": 1044.57, "total_tokens": 1006488} {"current_steps": 11175, "total_steps": 76960, "loss": 0.2191, "lr": 4.968957766662985e-05, "epoch": 2.904106029106029, "percentage": 14.52, "elapsed_time": "0:16:03", "remaining_time": "1:34:34", "throughput": 1044.58, "total_tokens": 1006936} {"current_steps": 11180, "total_steps": 76960, "loss": 0.2622, "lr": 4.9688686352265566e-05, "epoch": 2.9054054054054053, "percentage": 14.53, "elapsed_time": "0:16:04", "remaining_time": "1:34:34", "throughput": 1044.54, "total_tokens": 1007336} {"current_steps": 11185, "total_steps": 76960, "loss": 0.2109, "lr": 4.968779376813849e-05, "epoch": 2.9067047817047817, "percentage": 14.53, "elapsed_time": "0:16:04", "remaining_time": "1:34:33", "throughput": 1044.55, "total_tokens": 1007784} {"current_steps": 11190, "total_steps": 76960, "loss": 0.3417, "lr": 4.968689991429453e-05, "epoch": 2.9080041580041582, "percentage": 14.54, "elapsed_time": "0:16:05", "remaining_time": "1:34:33", "throughput": 1044.6, "total_tokens": 1008264} {"current_steps": 11195, "total_steps": 76960, "loss": 0.3361, "lr": 4.968600479077964e-05, "epoch": 2.9093035343035343, "percentage": 14.55, "elapsed_time": "0:16:05", "remaining_time": "1:34:32", "throughput": 1044.63, "total_tokens": 1008728} {"current_steps": 11200, "total_steps": 76960, "loss": 0.2497, "lr": 4.968510839763989e-05, "epoch": 2.9106029106029108, "percentage": 14.55, "elapsed_time": "0:16:06", "remaining_time": "1:34:32", "throughput": 1044.66, "total_tokens": 1009192} {"current_steps": 11205, "total_steps": 76960, "loss": 0.3076, "lr": 4.968421073492135e-05, "epoch": 2.911902286902287, "percentage": 14.56, "elapsed_time": "0:16:06", "remaining_time": "1:34:31", "throughput": 1044.69, "total_tokens": 1009656} {"current_steps": 11210, "total_steps": 76960, "loss": 0.2438, "lr": 4.968331180267021e-05, "epoch": 2.9132016632016633, "percentage": 14.57, "elapsed_time": "0:16:06", "remaining_time": "1:34:31", "throughput": 1044.72, "total_tokens": 1010120} {"current_steps": 11215, "total_steps": 76960, "loss": 0.2743, "lr": 4.968241160093268e-05, "epoch": 2.9145010395010393, "percentage": 14.57, "elapsed_time": "0:16:07", "remaining_time": "1:34:30", "throughput": 1044.72, "total_tokens": 1010552} {"current_steps": 11220, "total_steps": 76960, "loss": 0.2776, "lr": 4.968151012975508e-05, "epoch": 2.915800415800416, "percentage": 14.58, "elapsed_time": "0:16:07", "remaining_time": "1:34:30", "throughput": 1044.75, "total_tokens": 1011016} {"current_steps": 11225, "total_steps": 76960, "loss": 0.2845, "lr": 4.968060738918376e-05, "epoch": 2.9170997920997923, "percentage": 14.59, "elapsed_time": "0:16:08", "remaining_time": "1:34:29", "throughput": 1044.73, "total_tokens": 1011432} {"current_steps": 11230, "total_steps": 76960, "loss": 0.2777, "lr": 4.967970337926516e-05, "epoch": 2.9183991683991684, "percentage": 14.59, "elapsed_time": "0:16:08", "remaining_time": "1:34:28", "throughput": 1044.71, "total_tokens": 1011848} {"current_steps": 11235, "total_steps": 76960, "loss": 0.2702, "lr": 4.9678798100045776e-05, "epoch": 2.919698544698545, "percentage": 14.6, "elapsed_time": "0:16:08", "remaining_time": "1:34:28", "throughput": 1044.68, "total_tokens": 1012264} {"current_steps": 11240, "total_steps": 76960, "loss": 0.2741, "lr": 4.967789155157215e-05, "epoch": 2.920997920997921, "percentage": 14.6, "elapsed_time": "0:16:09", "remaining_time": "1:34:27", "throughput": 1044.68, "total_tokens": 1012696} {"current_steps": 11245, "total_steps": 76960, "loss": 0.2535, "lr": 4.9676983733890913e-05, "epoch": 2.9222972972972974, "percentage": 14.61, "elapsed_time": "0:16:09", "remaining_time": "1:34:27", "throughput": 1044.69, "total_tokens": 1013144} {"current_steps": 11250, "total_steps": 76960, "loss": 0.3106, "lr": 4.9676074647048766e-05, "epoch": 2.9235966735966734, "percentage": 14.62, "elapsed_time": "0:16:10", "remaining_time": "1:34:26", "throughput": 1044.71, "total_tokens": 1013592} {"current_steps": 11255, "total_steps": 76960, "loss": 0.2338, "lr": 4.967516429109245e-05, "epoch": 2.92489604989605, "percentage": 14.62, "elapsed_time": "0:16:10", "remaining_time": "1:34:26", "throughput": 1044.72, "total_tokens": 1014040} {"current_steps": 11260, "total_steps": 76960, "loss": 0.2984, "lr": 4.96742526660688e-05, "epoch": 2.9261954261954264, "percentage": 14.63, "elapsed_time": "0:16:11", "remaining_time": "1:34:25", "throughput": 1044.76, "total_tokens": 1014520} {"current_steps": 11265, "total_steps": 76960, "loss": 0.2374, "lr": 4.967333977202469e-05, "epoch": 2.9274948024948024, "percentage": 14.64, "elapsed_time": "0:16:11", "remaining_time": "1:34:25", "throughput": 1044.77, "total_tokens": 1014968} {"current_steps": 11270, "total_steps": 76960, "loss": 0.2611, "lr": 4.9672425609007064e-05, "epoch": 2.928794178794179, "percentage": 14.64, "elapsed_time": "0:16:11", "remaining_time": "1:34:24", "throughput": 1044.78, "total_tokens": 1015416} {"current_steps": 11275, "total_steps": 76960, "loss": 0.2706, "lr": 4.967151017706296e-05, "epoch": 2.930093555093555, "percentage": 14.65, "elapsed_time": "0:16:12", "remaining_time": "1:34:24", "throughput": 1044.78, "total_tokens": 1015848} {"current_steps": 11280, "total_steps": 76960, "loss": 0.2536, "lr": 4.967059347623945e-05, "epoch": 2.9313929313929314, "percentage": 14.66, "elapsed_time": "0:16:12", "remaining_time": "1:34:23", "throughput": 1044.79, "total_tokens": 1016296} {"current_steps": 11285, "total_steps": 76960, "loss": 0.2597, "lr": 4.9669675506583675e-05, "epoch": 2.9326923076923075, "percentage": 14.66, "elapsed_time": "0:16:13", "remaining_time": "1:34:23", "throughput": 1044.8, "total_tokens": 1016744} {"current_steps": 11290, "total_steps": 76960, "loss": 0.281, "lr": 4.966875626814285e-05, "epoch": 2.933991683991684, "percentage": 14.67, "elapsed_time": "0:16:13", "remaining_time": "1:34:22", "throughput": 1044.79, "total_tokens": 1017176} {"current_steps": 11295, "total_steps": 76960, "loss": 0.214, "lr": 4.966783576096426e-05, "epoch": 2.9352910602910605, "percentage": 14.68, "elapsed_time": "0:16:13", "remaining_time": "1:34:22", "throughput": 1044.8, "total_tokens": 1017624} {"current_steps": 11300, "total_steps": 76960, "loss": 0.2971, "lr": 4.966691398509523e-05, "epoch": 2.9365904365904365, "percentage": 14.68, "elapsed_time": "0:16:14", "remaining_time": "1:34:21", "throughput": 1044.85, "total_tokens": 1018104} {"current_steps": 11305, "total_steps": 76960, "loss": 0.2176, "lr": 4.966599094058319e-05, "epoch": 2.937889812889813, "percentage": 14.69, "elapsed_time": "0:16:14", "remaining_time": "1:34:21", "throughput": 1044.84, "total_tokens": 1018536} {"current_steps": 11310, "total_steps": 76960, "loss": 0.2763, "lr": 4.96650666274756e-05, "epoch": 2.939189189189189, "percentage": 14.7, "elapsed_time": "0:16:15", "remaining_time": "1:34:20", "throughput": 1044.83, "total_tokens": 1018968} {"current_steps": 11315, "total_steps": 76960, "loss": 0.2218, "lr": 4.966414104581999e-05, "epoch": 2.9404885654885655, "percentage": 14.7, "elapsed_time": "0:16:15", "remaining_time": "1:34:20", "throughput": 1044.83, "total_tokens": 1019400} {"current_steps": 11320, "total_steps": 76960, "loss": 0.1346, "lr": 4.966321419566399e-05, "epoch": 2.9417879417879416, "percentage": 14.71, "elapsed_time": "0:16:16", "remaining_time": "1:34:19", "throughput": 1044.84, "total_tokens": 1019848} {"current_steps": 11325, "total_steps": 76960, "loss": 0.2575, "lr": 4.966228607705524e-05, "epoch": 2.943087318087318, "percentage": 14.72, "elapsed_time": "0:16:16", "remaining_time": "1:34:19", "throughput": 1044.85, "total_tokens": 1020296} {"current_steps": 11330, "total_steps": 76960, "loss": 0.3166, "lr": 4.9661356690041494e-05, "epoch": 2.9443866943866945, "percentage": 14.72, "elapsed_time": "0:16:16", "remaining_time": "1:34:18", "throughput": 1044.88, "total_tokens": 1020760} {"current_steps": 11335, "total_steps": 76960, "loss": 0.2559, "lr": 4.966042603467055e-05, "epoch": 2.9456860706860706, "percentage": 14.73, "elapsed_time": "0:16:17", "remaining_time": "1:34:18", "throughput": 1044.9, "total_tokens": 1021224} {"current_steps": 11340, "total_steps": 76960, "loss": 0.2534, "lr": 4.9659494110990256e-05, "epoch": 2.946985446985447, "percentage": 14.73, "elapsed_time": "0:16:17", "remaining_time": "1:34:17", "throughput": 1044.89, "total_tokens": 1021656} {"current_steps": 11345, "total_steps": 76960, "loss": 0.236, "lr": 4.965856091904855e-05, "epoch": 2.9482848232848236, "percentage": 14.74, "elapsed_time": "0:16:18", "remaining_time": "1:34:17", "throughput": 1044.89, "total_tokens": 1022088} {"current_steps": 11350, "total_steps": 76960, "loss": 0.1811, "lr": 4.9657626458893436e-05, "epoch": 2.9495841995841996, "percentage": 14.75, "elapsed_time": "0:16:18", "remaining_time": "1:34:16", "throughput": 1044.92, "total_tokens": 1022552} {"current_steps": 11355, "total_steps": 76960, "loss": 0.2209, "lr": 4.9656690730572965e-05, "epoch": 2.9508835758835756, "percentage": 14.75, "elapsed_time": "0:16:19", "remaining_time": "1:34:16", "throughput": 1044.96, "total_tokens": 1023032} {"current_steps": 11360, "total_steps": 76960, "loss": 0.2045, "lr": 4.965575373413527e-05, "epoch": 2.952182952182952, "percentage": 14.76, "elapsed_time": "0:16:19", "remaining_time": "1:34:15", "throughput": 1044.99, "total_tokens": 1023496} {"current_steps": 11365, "total_steps": 76960, "loss": 0.2124, "lr": 4.965481546962853e-05, "epoch": 2.9534823284823286, "percentage": 14.77, "elapsed_time": "0:16:19", "remaining_time": "1:34:15", "throughput": 1045.08, "total_tokens": 1024024} {"current_steps": 11370, "total_steps": 76960, "loss": 0.3944, "lr": 4.965387593710101e-05, "epoch": 2.9547817047817047, "percentage": 14.77, "elapsed_time": "0:16:20", "remaining_time": "1:34:14", "throughput": 1045.09, "total_tokens": 1024472} {"current_steps": 11375, "total_steps": 76960, "loss": 0.2717, "lr": 4.965293513660103e-05, "epoch": 2.956081081081081, "percentage": 14.78, "elapsed_time": "0:16:20", "remaining_time": "1:34:14", "throughput": 1045.1, "total_tokens": 1024920} {"current_steps": 11380, "total_steps": 76960, "loss": 0.2056, "lr": 4.965199306817697e-05, "epoch": 2.9573804573804576, "percentage": 14.79, "elapsed_time": "0:16:21", "remaining_time": "1:34:13", "throughput": 1045.08, "total_tokens": 1025336} {"current_steps": 11385, "total_steps": 76960, "loss": 0.2576, "lr": 4.9651049731877283e-05, "epoch": 2.9586798336798337, "percentage": 14.79, "elapsed_time": "0:16:21", "remaining_time": "1:34:13", "throughput": 1045.07, "total_tokens": 1025768} {"current_steps": 11390, "total_steps": 76960, "loss": 0.2801, "lr": 4.96501051277505e-05, "epoch": 2.9599792099792097, "percentage": 14.8, "elapsed_time": "0:16:21", "remaining_time": "1:34:12", "throughput": 1045.06, "total_tokens": 1026200} {"current_steps": 11395, "total_steps": 76960, "loss": 0.2576, "lr": 4.9649159255845184e-05, "epoch": 2.961278586278586, "percentage": 14.81, "elapsed_time": "0:16:22", "remaining_time": "1:34:12", "throughput": 1045.09, "total_tokens": 1026664} {"current_steps": 11400, "total_steps": 76960, "loss": 0.2916, "lr": 4.964821211620999e-05, "epoch": 2.9625779625779627, "percentage": 14.81, "elapsed_time": "0:16:22", "remaining_time": "1:34:11", "throughput": 1045.15, "total_tokens": 1027160} {"current_steps": 11405, "total_steps": 76960, "loss": 0.2779, "lr": 4.964726370889363e-05, "epoch": 2.9638773388773387, "percentage": 14.82, "elapsed_time": "0:16:23", "remaining_time": "1:34:11", "throughput": 1045.13, "total_tokens": 1027576} {"current_steps": 11410, "total_steps": 76960, "loss": 0.2515, "lr": 4.9646314033944884e-05, "epoch": 2.965176715176715, "percentage": 14.83, "elapsed_time": "0:16:23", "remaining_time": "1:34:10", "throughput": 1045.14, "total_tokens": 1028024} {"current_steps": 11415, "total_steps": 76960, "loss": 0.1818, "lr": 4.964536309141259e-05, "epoch": 2.9664760914760917, "percentage": 14.83, "elapsed_time": "0:16:24", "remaining_time": "1:34:10", "throughput": 1045.17, "total_tokens": 1028488} {"current_steps": 11420, "total_steps": 76960, "loss": 0.2718, "lr": 4.9644410881345665e-05, "epoch": 2.9677754677754677, "percentage": 14.84, "elapsed_time": "0:16:24", "remaining_time": "1:34:09", "throughput": 1045.24, "total_tokens": 1029000} {"current_steps": 11425, "total_steps": 76960, "loss": 0.2233, "lr": 4.964345740379307e-05, "epoch": 2.9690748440748442, "percentage": 14.85, "elapsed_time": "0:16:24", "remaining_time": "1:34:09", "throughput": 1045.27, "total_tokens": 1029464} {"current_steps": 11430, "total_steps": 76960, "loss": 0.3758, "lr": 4.9642502658803846e-05, "epoch": 2.9703742203742203, "percentage": 14.85, "elapsed_time": "0:16:25", "remaining_time": "1:34:08", "throughput": 1045.28, "total_tokens": 1029912} {"current_steps": 11435, "total_steps": 76960, "loss": 0.3498, "lr": 4.964154664642711e-05, "epoch": 2.9716735966735968, "percentage": 14.86, "elapsed_time": "0:16:25", "remaining_time": "1:34:08", "throughput": 1045.29, "total_tokens": 1030360} {"current_steps": 11440, "total_steps": 76960, "loss": 0.2866, "lr": 4.9640589366712e-05, "epoch": 2.972972972972973, "percentage": 14.86, "elapsed_time": "0:16:26", "remaining_time": "1:34:07", "throughput": 1045.31, "total_tokens": 1030808} {"current_steps": 11445, "total_steps": 76960, "loss": 0.3949, "lr": 4.963963081970778e-05, "epoch": 2.9742723492723493, "percentage": 14.87, "elapsed_time": "0:16:26", "remaining_time": "1:34:07", "throughput": 1045.33, "total_tokens": 1031272} {"current_steps": 11450, "total_steps": 76960, "loss": 0.358, "lr": 4.9638671005463746e-05, "epoch": 2.975571725571726, "percentage": 14.88, "elapsed_time": "0:16:26", "remaining_time": "1:34:06", "throughput": 1045.38, "total_tokens": 1031752} {"current_steps": 11455, "total_steps": 76960, "loss": 0.278, "lr": 4.9637709924029244e-05, "epoch": 2.976871101871102, "percentage": 14.88, "elapsed_time": "0:16:27", "remaining_time": "1:34:06", "throughput": 1045.37, "total_tokens": 1032184} {"current_steps": 11460, "total_steps": 76960, "loss": 0.34, "lr": 4.963674757545372e-05, "epoch": 2.9781704781704783, "percentage": 14.89, "elapsed_time": "0:16:27", "remaining_time": "1:34:05", "throughput": 1045.36, "total_tokens": 1032616} {"current_steps": 11465, "total_steps": 76960, "loss": 0.293, "lr": 4.9635783959786656e-05, "epoch": 2.9794698544698544, "percentage": 14.9, "elapsed_time": "0:16:28", "remaining_time": "1:34:05", "throughput": 1045.39, "total_tokens": 1033080} {"current_steps": 11470, "total_steps": 76960, "loss": 0.3192, "lr": 4.963481907707762e-05, "epoch": 2.980769230769231, "percentage": 14.9, "elapsed_time": "0:16:28", "remaining_time": "1:34:04", "throughput": 1045.43, "total_tokens": 1033560} {"current_steps": 11475, "total_steps": 76960, "loss": 0.2918, "lr": 4.963385292737624e-05, "epoch": 2.982068607068607, "percentage": 14.91, "elapsed_time": "0:16:29", "remaining_time": "1:34:04", "throughput": 1045.48, "total_tokens": 1034040} {"current_steps": 11480, "total_steps": 76960, "loss": 0.252, "lr": 4.96328855107322e-05, "epoch": 2.9833679833679834, "percentage": 14.92, "elapsed_time": "0:16:29", "remaining_time": "1:34:03", "throughput": 1045.48, "total_tokens": 1034488} {"current_steps": 11485, "total_steps": 76960, "loss": 0.2322, "lr": 4.963191682719525e-05, "epoch": 2.98466735966736, "percentage": 14.92, "elapsed_time": "0:16:29", "remaining_time": "1:34:03", "throughput": 1045.48, "total_tokens": 1034936} {"current_steps": 11490, "total_steps": 76960, "loss": 0.2238, "lr": 4.963094687681522e-05, "epoch": 2.985966735966736, "percentage": 14.93, "elapsed_time": "0:16:30", "remaining_time": "1:34:02", "throughput": 1045.49, "total_tokens": 1035384} {"current_steps": 11495, "total_steps": 76960, "loss": 0.4644, "lr": 4.9629975659641994e-05, "epoch": 2.9872661122661124, "percentage": 14.94, "elapsed_time": "0:16:30", "remaining_time": "1:34:02", "throughput": 1045.48, "total_tokens": 1035816} {"current_steps": 11500, "total_steps": 76960, "loss": 0.2535, "lr": 4.962900317572552e-05, "epoch": 2.9885654885654884, "percentage": 14.94, "elapsed_time": "0:16:31", "remaining_time": "1:34:01", "throughput": 1045.49, "total_tokens": 1036264} {"current_steps": 11505, "total_steps": 76960, "loss": 0.264, "lr": 4.962802942511581e-05, "epoch": 2.989864864864865, "percentage": 14.95, "elapsed_time": "0:16:31", "remaining_time": "1:34:01", "throughput": 1045.47, "total_tokens": 1036680} {"current_steps": 11510, "total_steps": 76960, "loss": 0.2842, "lr": 4.962705440786295e-05, "epoch": 2.991164241164241, "percentage": 14.96, "elapsed_time": "0:16:32", "remaining_time": "1:34:00", "throughput": 1045.44, "total_tokens": 1037096} {"current_steps": 11515, "total_steps": 76960, "loss": 0.2395, "lr": 4.96260781240171e-05, "epoch": 2.9924636174636174, "percentage": 14.96, "elapsed_time": "0:16:32", "remaining_time": "1:34:00", "throughput": 1045.47, "total_tokens": 1037560} {"current_steps": 11520, "total_steps": 76960, "loss": 0.2742, "lr": 4.962510057362844e-05, "epoch": 2.993762993762994, "percentage": 14.97, "elapsed_time": "0:16:32", "remaining_time": "1:33:59", "throughput": 1045.51, "total_tokens": 1038040} {"current_steps": 11525, "total_steps": 76960, "loss": 0.2721, "lr": 4.962412175674726e-05, "epoch": 2.99506237006237, "percentage": 14.98, "elapsed_time": "0:16:33", "remaining_time": "1:33:59", "throughput": 1045.51, "total_tokens": 1038472} {"current_steps": 11530, "total_steps": 76960, "loss": 0.2499, "lr": 4.962314167342391e-05, "epoch": 2.9963617463617465, "percentage": 14.98, "elapsed_time": "0:16:33", "remaining_time": "1:33:58", "throughput": 1045.57, "total_tokens": 1038968} {"current_steps": 11535, "total_steps": 76960, "loss": 0.1882, "lr": 4.96221603237088e-05, "epoch": 2.9976611226611225, "percentage": 14.99, "elapsed_time": "0:16:34", "remaining_time": "1:33:58", "throughput": 1045.54, "total_tokens": 1039384} {"current_steps": 11540, "total_steps": 76960, "loss": 0.2179, "lr": 4.962117770765238e-05, "epoch": 2.998960498960499, "percentage": 14.99, "elapsed_time": "0:16:34", "remaining_time": "1:33:57", "throughput": 1045.56, "total_tokens": 1039832} {"current_steps": 11544, "total_steps": 76960, "eval_loss": 0.24048779904842377, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:16:48", "remaining_time": "1:35:12", "throughput": 1031.75, "total_tokens": 1040128} {"current_steps": 11545, "total_steps": 76960, "loss": 0.2596, "lr": 4.962019382530521e-05, "epoch": 3.0002598752598755, "percentage": 15.0, "elapsed_time": "0:16:49", "remaining_time": "1:35:21", "throughput": 1030.24, "total_tokens": 1040224} {"current_steps": 11550, "total_steps": 76960, "loss": 0.245, "lr": 4.9619208676717874e-05, "epoch": 3.0015592515592515, "percentage": 15.01, "elapsed_time": "0:16:50", "remaining_time": "1:35:20", "throughput": 1030.3, "total_tokens": 1040720} {"current_steps": 11555, "total_steps": 76960, "loss": 0.3867, "lr": 4.961822226194104e-05, "epoch": 3.002858627858628, "percentage": 15.01, "elapsed_time": "0:16:50", "remaining_time": "1:35:20", "throughput": 1030.3, "total_tokens": 1041168} {"current_steps": 11560, "total_steps": 76960, "loss": 0.2219, "lr": 4.9617234581025465e-05, "epoch": 3.004158004158004, "percentage": 15.02, "elapsed_time": "0:16:50", "remaining_time": "1:35:19", "throughput": 1030.29, "total_tokens": 1041616} {"current_steps": 11565, "total_steps": 76960, "loss": 0.2821, "lr": 4.961624563402192e-05, "epoch": 3.0054573804573805, "percentage": 15.03, "elapsed_time": "0:16:51", "remaining_time": "1:35:19", "throughput": 1030.33, "total_tokens": 1042096} {"current_steps": 11570, "total_steps": 76960, "loss": 0.2927, "lr": 4.9615255420981266e-05, "epoch": 3.0067567567567566, "percentage": 15.03, "elapsed_time": "0:16:51", "remaining_time": "1:35:18", "throughput": 1030.44, "total_tokens": 1042640} {"current_steps": 11575, "total_steps": 76960, "loss": 0.2896, "lr": 4.961426394195445e-05, "epoch": 3.008056133056133, "percentage": 15.04, "elapsed_time": "0:16:52", "remaining_time": "1:35:18", "throughput": 1030.44, "total_tokens": 1043072} {"current_steps": 11580, "total_steps": 76960, "loss": 0.2831, "lr": 4.961327119699246e-05, "epoch": 3.0093555093555096, "percentage": 15.05, "elapsed_time": "0:16:52", "remaining_time": "1:35:17", "throughput": 1030.42, "total_tokens": 1043488} {"current_steps": 11585, "total_steps": 76960, "loss": 0.2749, "lr": 4.9612277186146335e-05, "epoch": 3.0106548856548856, "percentage": 15.05, "elapsed_time": "0:16:53", "remaining_time": "1:35:17", "throughput": 1030.43, "total_tokens": 1043936} {"current_steps": 11590, "total_steps": 76960, "loss": 0.2915, "lr": 4.961128190946723e-05, "epoch": 3.011954261954262, "percentage": 15.06, "elapsed_time": "0:16:53", "remaining_time": "1:35:16", "throughput": 1030.43, "total_tokens": 1044368} {"current_steps": 11595, "total_steps": 76960, "loss": 0.2813, "lr": 4.9610285367006305e-05, "epoch": 3.013253638253638, "percentage": 15.07, "elapsed_time": "0:16:53", "remaining_time": "1:35:15", "throughput": 1030.45, "total_tokens": 1044816} {"current_steps": 11600, "total_steps": 76960, "loss": 0.2509, "lr": 4.960928755881482e-05, "epoch": 3.0145530145530146, "percentage": 15.07, "elapsed_time": "0:16:54", "remaining_time": "1:35:15", "throughput": 1030.43, "total_tokens": 1045232} {"current_steps": 11605, "total_steps": 76960, "loss": 0.2475, "lr": 4.960828848494411e-05, "epoch": 3.0158523908523907, "percentage": 15.08, "elapsed_time": "0:16:54", "remaining_time": "1:35:14", "throughput": 1030.45, "total_tokens": 1045680} {"current_steps": 11610, "total_steps": 76960, "loss": 0.1622, "lr": 4.960728814544553e-05, "epoch": 3.017151767151767, "percentage": 15.09, "elapsed_time": "0:16:55", "remaining_time": "1:35:14", "throughput": 1030.45, "total_tokens": 1046112} {"current_steps": 11615, "total_steps": 76960, "loss": 0.3539, "lr": 4.960628654037055e-05, "epoch": 3.0184511434511436, "percentage": 15.09, "elapsed_time": "0:16:55", "remaining_time": "1:35:13", "throughput": 1030.43, "total_tokens": 1046528} {"current_steps": 11620, "total_steps": 76960, "loss": 0.216, "lr": 4.9605283669770674e-05, "epoch": 3.0197505197505197, "percentage": 15.1, "elapsed_time": "0:16:56", "remaining_time": "1:35:13", "throughput": 1030.44, "total_tokens": 1046976} {"current_steps": 11625, "total_steps": 76960, "loss": 0.2978, "lr": 4.960427953369749e-05, "epoch": 3.021049896049896, "percentage": 15.11, "elapsed_time": "0:16:56", "remaining_time": "1:35:12", "throughput": 1030.48, "total_tokens": 1047440} {"current_steps": 11630, "total_steps": 76960, "loss": 0.2633, "lr": 4.960327413220262e-05, "epoch": 3.022349272349272, "percentage": 15.11, "elapsed_time": "0:16:56", "remaining_time": "1:35:12", "throughput": 1030.49, "total_tokens": 1047888} {"current_steps": 11635, "total_steps": 76960, "loss": 0.287, "lr": 4.960226746533779e-05, "epoch": 3.0236486486486487, "percentage": 15.12, "elapsed_time": "0:16:57", "remaining_time": "1:35:11", "throughput": 1030.51, "total_tokens": 1048336} {"current_steps": 11640, "total_steps": 76960, "loss": 0.2448, "lr": 4.960125953315479e-05, "epoch": 3.024948024948025, "percentage": 15.12, "elapsed_time": "0:16:57", "remaining_time": "1:35:11", "throughput": 1030.54, "total_tokens": 1048800} {"current_steps": 11645, "total_steps": 76960, "loss": 0.3215, "lr": 4.9600250335705425e-05, "epoch": 3.026247401247401, "percentage": 15.13, "elapsed_time": "0:16:58", "remaining_time": "1:35:10", "throughput": 1030.59, "total_tokens": 1049280} {"current_steps": 11650, "total_steps": 76960, "loss": 0.2261, "lr": 4.959923987304161e-05, "epoch": 3.0275467775467777, "percentage": 15.14, "elapsed_time": "0:16:58", "remaining_time": "1:35:10", "throughput": 1030.6, "total_tokens": 1049728} {"current_steps": 11655, "total_steps": 76960, "loss": 0.2701, "lr": 4.9598228145215334e-05, "epoch": 3.0288461538461537, "percentage": 15.14, "elapsed_time": "0:16:58", "remaining_time": "1:35:09", "throughput": 1030.66, "total_tokens": 1050224} {"current_steps": 11660, "total_steps": 76960, "loss": 0.3203, "lr": 4.959721515227861e-05, "epoch": 3.0301455301455302, "percentage": 15.15, "elapsed_time": "0:16:59", "remaining_time": "1:35:08", "throughput": 1030.73, "total_tokens": 1050720} {"current_steps": 11665, "total_steps": 76960, "loss": 0.2889, "lr": 4.959620089428354e-05, "epoch": 3.0314449064449063, "percentage": 15.16, "elapsed_time": "0:16:59", "remaining_time": "1:35:08", "throughput": 1030.79, "total_tokens": 1051216} {"current_steps": 11670, "total_steps": 76960, "loss": 0.2499, "lr": 4.959518537128229e-05, "epoch": 3.0327442827442828, "percentage": 15.16, "elapsed_time": "0:17:00", "remaining_time": "1:35:07", "throughput": 1030.78, "total_tokens": 1051632} {"current_steps": 11675, "total_steps": 76960, "loss": 0.2906, "lr": 4.9594168583327094e-05, "epoch": 3.0340436590436592, "percentage": 15.17, "elapsed_time": "0:17:00", "remaining_time": "1:35:07", "throughput": 1030.77, "total_tokens": 1052064} {"current_steps": 11680, "total_steps": 76960, "loss": 0.2635, "lr": 4.959315053047024e-05, "epoch": 3.0353430353430353, "percentage": 15.18, "elapsed_time": "0:17:01", "remaining_time": "1:35:06", "throughput": 1030.79, "total_tokens": 1052512} {"current_steps": 11685, "total_steps": 76960, "loss": 0.231, "lr": 4.959213121276409e-05, "epoch": 3.0366424116424118, "percentage": 15.18, "elapsed_time": "0:17:01", "remaining_time": "1:35:06", "throughput": 1030.82, "total_tokens": 1052976} {"current_steps": 11690, "total_steps": 76960, "loss": 0.2749, "lr": 4.9591110630261076e-05, "epoch": 3.037941787941788, "percentage": 15.19, "elapsed_time": "0:17:01", "remaining_time": "1:35:05", "throughput": 1030.86, "total_tokens": 1053440} {"current_steps": 11695, "total_steps": 76960, "loss": 0.2611, "lr": 4.959008878301367e-05, "epoch": 3.0392411642411643, "percentage": 15.2, "elapsed_time": "0:17:02", "remaining_time": "1:35:05", "throughput": 1030.85, "total_tokens": 1053872} {"current_steps": 11700, "total_steps": 76960, "loss": 0.3249, "lr": 4.958906567107444e-05, "epoch": 3.0405405405405403, "percentage": 15.2, "elapsed_time": "0:17:02", "remaining_time": "1:35:04", "throughput": 1030.87, "total_tokens": 1054320} {"current_steps": 11705, "total_steps": 76960, "loss": 0.2394, "lr": 4.9588041294496e-05, "epoch": 3.041839916839917, "percentage": 15.21, "elapsed_time": "0:17:03", "remaining_time": "1:35:04", "throughput": 1030.87, "total_tokens": 1054752} {"current_steps": 11710, "total_steps": 76960, "loss": 0.2798, "lr": 4.958701565333104e-05, "epoch": 3.0431392931392933, "percentage": 15.22, "elapsed_time": "0:17:03", "remaining_time": "1:35:03", "throughput": 1030.86, "total_tokens": 1055184} {"current_steps": 11715, "total_steps": 76960, "loss": 0.2821, "lr": 4.9585988747632306e-05, "epoch": 3.0444386694386694, "percentage": 15.22, "elapsed_time": "0:17:04", "remaining_time": "1:35:03", "throughput": 1030.85, "total_tokens": 1055600} {"current_steps": 11720, "total_steps": 76960, "loss": 0.2264, "lr": 4.958496057745262e-05, "epoch": 3.045738045738046, "percentage": 15.23, "elapsed_time": "0:17:04", "remaining_time": "1:35:02", "throughput": 1030.88, "total_tokens": 1056064} {"current_steps": 11725, "total_steps": 76960, "loss": 0.2947, "lr": 4.9583931142844845e-05, "epoch": 3.047037422037422, "percentage": 15.24, "elapsed_time": "0:17:04", "remaining_time": "1:35:02", "throughput": 1030.91, "total_tokens": 1056528} {"current_steps": 11730, "total_steps": 76960, "loss": 0.2744, "lr": 4.958290044386194e-05, "epoch": 3.0483367983367984, "percentage": 15.24, "elapsed_time": "0:17:05", "remaining_time": "1:35:01", "throughput": 1030.95, "total_tokens": 1056992} {"current_steps": 11735, "total_steps": 76960, "loss": 0.2833, "lr": 4.958186848055691e-05, "epoch": 3.0496361746361744, "percentage": 15.25, "elapsed_time": "0:17:05", "remaining_time": "1:35:00", "throughput": 1030.96, "total_tokens": 1057440} {"current_steps": 11740, "total_steps": 76960, "loss": 0.2622, "lr": 4.9580835252982836e-05, "epoch": 3.050935550935551, "percentage": 15.25, "elapsed_time": "0:17:06", "remaining_time": "1:35:00", "throughput": 1030.95, "total_tokens": 1057856} {"current_steps": 11745, "total_steps": 76960, "loss": 0.3018, "lr": 4.957980076119285e-05, "epoch": 3.0522349272349274, "percentage": 15.26, "elapsed_time": "0:17:06", "remaining_time": "1:34:59", "throughput": 1030.96, "total_tokens": 1058304} {"current_steps": 11750, "total_steps": 76960, "loss": 0.2883, "lr": 4.9578765005240164e-05, "epoch": 3.0535343035343034, "percentage": 15.27, "elapsed_time": "0:17:06", "remaining_time": "1:34:59", "throughput": 1030.98, "total_tokens": 1058752} {"current_steps": 11755, "total_steps": 76960, "loss": 0.2998, "lr": 4.9577727985178036e-05, "epoch": 3.05483367983368, "percentage": 15.27, "elapsed_time": "0:17:07", "remaining_time": "1:34:58", "throughput": 1031.02, "total_tokens": 1059216} {"current_steps": 11760, "total_steps": 76960, "loss": 0.2821, "lr": 4.9576689701059815e-05, "epoch": 3.056133056133056, "percentage": 15.28, "elapsed_time": "0:17:07", "remaining_time": "1:34:58", "throughput": 1031.03, "total_tokens": 1059664} {"current_steps": 11765, "total_steps": 76960, "loss": 0.2998, "lr": 4.957565015293889e-05, "epoch": 3.0574324324324325, "percentage": 15.29, "elapsed_time": "0:17:08", "remaining_time": "1:34:57", "throughput": 1031.07, "total_tokens": 1060128} {"current_steps": 11770, "total_steps": 76960, "loss": 0.2817, "lr": 4.957460934086873e-05, "epoch": 3.058731808731809, "percentage": 15.29, "elapsed_time": "0:17:08", "remaining_time": "1:34:57", "throughput": 1031.12, "total_tokens": 1060608} {"current_steps": 11775, "total_steps": 76960, "loss": 0.27, "lr": 4.9573567264902865e-05, "epoch": 3.060031185031185, "percentage": 15.3, "elapsed_time": "0:17:09", "remaining_time": "1:34:56", "throughput": 1031.13, "total_tokens": 1061056} {"current_steps": 11780, "total_steps": 76960, "loss": 0.2112, "lr": 4.95725239250949e-05, "epoch": 3.0613305613305615, "percentage": 15.31, "elapsed_time": "0:17:09", "remaining_time": "1:34:55", "throughput": 1031.16, "total_tokens": 1061520} {"current_steps": 11785, "total_steps": 76960, "loss": 0.3359, "lr": 4.957147932149847e-05, "epoch": 3.0626299376299375, "percentage": 15.31, "elapsed_time": "0:17:09", "remaining_time": "1:34:55", "throughput": 1031.17, "total_tokens": 1061952} {"current_steps": 11790, "total_steps": 76960, "loss": 0.2239, "lr": 4.957043345416732e-05, "epoch": 3.063929313929314, "percentage": 15.32, "elapsed_time": "0:17:10", "remaining_time": "1:34:54", "throughput": 1031.17, "total_tokens": 1062384} {"current_steps": 11795, "total_steps": 76960, "loss": 0.279, "lr": 4.956938632315524e-05, "epoch": 3.06522869022869, "percentage": 15.33, "elapsed_time": "0:17:10", "remaining_time": "1:34:54", "throughput": 1031.18, "total_tokens": 1062832} {"current_steps": 11800, "total_steps": 76960, "loss": 0.1976, "lr": 4.956833792851608e-05, "epoch": 3.0665280665280665, "percentage": 15.33, "elapsed_time": "0:17:11", "remaining_time": "1:34:53", "throughput": 1031.17, "total_tokens": 1063248} {"current_steps": 11805, "total_steps": 76960, "loss": 0.2222, "lr": 4.956728827030376e-05, "epoch": 3.067827442827443, "percentage": 15.34, "elapsed_time": "0:17:11", "remaining_time": "1:34:53", "throughput": 1031.19, "total_tokens": 1063696} {"current_steps": 11810, "total_steps": 76960, "loss": 0.2091, "lr": 4.956623734857226e-05, "epoch": 3.069126819126819, "percentage": 15.35, "elapsed_time": "0:17:11", "remaining_time": "1:34:52", "throughput": 1031.17, "total_tokens": 1064112} {"current_steps": 11815, "total_steps": 76960, "loss": 0.1665, "lr": 4.956518516337564e-05, "epoch": 3.0704261954261955, "percentage": 15.35, "elapsed_time": "0:17:12", "remaining_time": "1:34:52", "throughput": 1031.24, "total_tokens": 1064608} {"current_steps": 11820, "total_steps": 76960, "loss": 0.2096, "lr": 4.9564131714768e-05, "epoch": 3.0717255717255716, "percentage": 15.36, "elapsed_time": "0:17:12", "remaining_time": "1:34:51", "throughput": 1031.28, "total_tokens": 1065088} {"current_steps": 11825, "total_steps": 76960, "loss": 0.3691, "lr": 4.956307700280354e-05, "epoch": 3.073024948024948, "percentage": 15.37, "elapsed_time": "0:17:13", "remaining_time": "1:34:51", "throughput": 1031.29, "total_tokens": 1065520} {"current_steps": 11830, "total_steps": 76960, "loss": 0.3175, "lr": 4.9562021027536494e-05, "epoch": 3.074324324324324, "percentage": 15.37, "elapsed_time": "0:17:13", "remaining_time": "1:34:50", "throughput": 1031.27, "total_tokens": 1065936} {"current_steps": 11835, "total_steps": 76960, "loss": 0.337, "lr": 4.956096378902117e-05, "epoch": 3.0756237006237006, "percentage": 15.38, "elapsed_time": "0:17:14", "remaining_time": "1:34:50", "throughput": 1031.32, "total_tokens": 1066416} {"current_steps": 11840, "total_steps": 76960, "loss": 0.2031, "lr": 4.955990528731195e-05, "epoch": 3.076923076923077, "percentage": 15.38, "elapsed_time": "0:17:14", "remaining_time": "1:34:49", "throughput": 1031.33, "total_tokens": 1066864} {"current_steps": 11845, "total_steps": 76960, "loss": 0.224, "lr": 4.955884552246326e-05, "epoch": 3.078222453222453, "percentage": 15.39, "elapsed_time": "0:17:14", "remaining_time": "1:34:48", "throughput": 1031.4, "total_tokens": 1067360} {"current_steps": 11850, "total_steps": 76960, "loss": 0.2693, "lr": 4.955778449452962e-05, "epoch": 3.0795218295218296, "percentage": 15.4, "elapsed_time": "0:17:15", "remaining_time": "1:34:48", "throughput": 1031.41, "total_tokens": 1067808} {"current_steps": 11855, "total_steps": 76960, "loss": 0.3121, "lr": 4.9556722203565585e-05, "epoch": 3.0808212058212057, "percentage": 15.4, "elapsed_time": "0:17:15", "remaining_time": "1:34:47", "throughput": 1031.46, "total_tokens": 1068288} {"current_steps": 11860, "total_steps": 76960, "loss": 0.2525, "lr": 4.955565864962581e-05, "epoch": 3.082120582120582, "percentage": 15.41, "elapsed_time": "0:17:16", "remaining_time": "1:34:47", "throughput": 1031.48, "total_tokens": 1068736} {"current_steps": 11865, "total_steps": 76960, "loss": 0.2628, "lr": 4.955459383276497e-05, "epoch": 3.0834199584199586, "percentage": 15.42, "elapsed_time": "0:17:16", "remaining_time": "1:34:46", "throughput": 1031.47, "total_tokens": 1069152} {"current_steps": 11870, "total_steps": 76960, "loss": 0.2639, "lr": 4.955352775303786e-05, "epoch": 3.0847193347193347, "percentage": 15.42, "elapsed_time": "0:17:16", "remaining_time": "1:34:46", "throughput": 1031.48, "total_tokens": 1069600} {"current_steps": 11875, "total_steps": 76960, "loss": 0.1707, "lr": 4.955246041049927e-05, "epoch": 3.086018711018711, "percentage": 15.43, "elapsed_time": "0:17:17", "remaining_time": "1:34:45", "throughput": 1031.53, "total_tokens": 1070080} {"current_steps": 11880, "total_steps": 76960, "loss": 0.2763, "lr": 4.9551391805204126e-05, "epoch": 3.087318087318087, "percentage": 15.44, "elapsed_time": "0:17:17", "remaining_time": "1:34:45", "throughput": 1031.53, "total_tokens": 1070528} {"current_steps": 11885, "total_steps": 76960, "loss": 0.3068, "lr": 4.955032193720739e-05, "epoch": 3.0886174636174637, "percentage": 15.44, "elapsed_time": "0:17:18", "remaining_time": "1:34:44", "throughput": 1031.59, "total_tokens": 1071024} {"current_steps": 11890, "total_steps": 76960, "loss": 0.2181, "lr": 4.954925080656405e-05, "epoch": 3.0899168399168397, "percentage": 15.45, "elapsed_time": "0:17:18", "remaining_time": "1:34:44", "throughput": 1031.6, "total_tokens": 1071472} {"current_steps": 11895, "total_steps": 76960, "loss": 0.273, "lr": 4.9548178413329236e-05, "epoch": 3.0912162162162162, "percentage": 15.46, "elapsed_time": "0:17:19", "remaining_time": "1:34:43", "throughput": 1031.64, "total_tokens": 1071952} {"current_steps": 11900, "total_steps": 76960, "loss": 0.2976, "lr": 4.954710475755808e-05, "epoch": 3.0925155925155927, "percentage": 15.46, "elapsed_time": "0:17:19", "remaining_time": "1:34:43", "throughput": 1031.64, "total_tokens": 1072384} {"current_steps": 11905, "total_steps": 76960, "loss": 0.2194, "lr": 4.954602983930581e-05, "epoch": 3.0938149688149688, "percentage": 15.47, "elapsed_time": "0:17:19", "remaining_time": "1:34:42", "throughput": 1031.69, "total_tokens": 1072864} {"current_steps": 11910, "total_steps": 76960, "loss": 0.2571, "lr": 4.95449536586277e-05, "epoch": 3.0951143451143452, "percentage": 15.48, "elapsed_time": "0:17:20", "remaining_time": "1:34:42", "throughput": 1031.69, "total_tokens": 1073296} {"current_steps": 11915, "total_steps": 76960, "loss": 0.258, "lr": 4.954387621557911e-05, "epoch": 3.0964137214137213, "percentage": 15.48, "elapsed_time": "0:17:20", "remaining_time": "1:34:41", "throughput": 1031.67, "total_tokens": 1073712} {"current_steps": 11920, "total_steps": 76960, "loss": 0.3063, "lr": 4.954279751021545e-05, "epoch": 3.0977130977130978, "percentage": 15.49, "elapsed_time": "0:17:21", "remaining_time": "1:34:41", "throughput": 1031.68, "total_tokens": 1074160} {"current_steps": 11925, "total_steps": 76960, "loss": 0.2918, "lr": 4.954171754259219e-05, "epoch": 3.099012474012474, "percentage": 15.5, "elapsed_time": "0:17:21", "remaining_time": "1:34:40", "throughput": 1031.68, "total_tokens": 1074592} {"current_steps": 11930, "total_steps": 76960, "loss": 0.2601, "lr": 4.9540636312764886e-05, "epoch": 3.1003118503118503, "percentage": 15.5, "elapsed_time": "0:17:22", "remaining_time": "1:34:39", "throughput": 1031.68, "total_tokens": 1075024} {"current_steps": 11935, "total_steps": 76960, "loss": 0.2839, "lr": 4.953955382078915e-05, "epoch": 3.101611226611227, "percentage": 15.51, "elapsed_time": "0:17:22", "remaining_time": "1:34:39", "throughput": 1031.68, "total_tokens": 1075456} {"current_steps": 11940, "total_steps": 76960, "loss": 0.1875, "lr": 4.953847006672064e-05, "epoch": 3.102910602910603, "percentage": 15.51, "elapsed_time": "0:17:22", "remaining_time": "1:34:38", "throughput": 1031.73, "total_tokens": 1075936} {"current_steps": 11945, "total_steps": 76960, "loss": 0.2263, "lr": 4.95373850506151e-05, "epoch": 3.1042099792099793, "percentage": 15.52, "elapsed_time": "0:17:23", "remaining_time": "1:34:38", "throughput": 1031.74, "total_tokens": 1076384} {"current_steps": 11950, "total_steps": 76960, "loss": 0.3752, "lr": 4.953629877252835e-05, "epoch": 3.1055093555093554, "percentage": 15.53, "elapsed_time": "0:17:23", "remaining_time": "1:34:37", "throughput": 1031.79, "total_tokens": 1076864} {"current_steps": 11955, "total_steps": 76960, "loss": 0.2563, "lr": 4.953521123251624e-05, "epoch": 3.106808731808732, "percentage": 15.53, "elapsed_time": "0:17:24", "remaining_time": "1:34:37", "throughput": 1031.8, "total_tokens": 1077312} {"current_steps": 11960, "total_steps": 76960, "loss": 0.1846, "lr": 4.95341224306347e-05, "epoch": 3.108108108108108, "percentage": 15.54, "elapsed_time": "0:17:24", "remaining_time": "1:34:36", "throughput": 1031.8, "total_tokens": 1077744} {"current_steps": 11965, "total_steps": 76960, "loss": 0.1793, "lr": 4.9533032366939744e-05, "epoch": 3.1094074844074844, "percentage": 15.55, "elapsed_time": "0:17:24", "remaining_time": "1:34:36", "throughput": 1031.83, "total_tokens": 1078208} {"current_steps": 11970, "total_steps": 76960, "loss": 0.3446, "lr": 4.9531941041487414e-05, "epoch": 3.110706860706861, "percentage": 15.55, "elapsed_time": "0:17:25", "remaining_time": "1:34:35", "throughput": 1031.86, "total_tokens": 1078672} {"current_steps": 11975, "total_steps": 76960, "loss": 0.177, "lr": 4.9530848454333865e-05, "epoch": 3.112006237006237, "percentage": 15.56, "elapsed_time": "0:17:25", "remaining_time": "1:34:35", "throughput": 1031.88, "total_tokens": 1079120} {"current_steps": 11980, "total_steps": 76960, "loss": 0.2742, "lr": 4.952975460553527e-05, "epoch": 3.1133056133056134, "percentage": 15.57, "elapsed_time": "0:17:26", "remaining_time": "1:34:34", "throughput": 1031.9, "total_tokens": 1079568} {"current_steps": 11985, "total_steps": 76960, "loss": 0.2461, "lr": 4.95286594951479e-05, "epoch": 3.1146049896049894, "percentage": 15.57, "elapsed_time": "0:17:26", "remaining_time": "1:34:34", "throughput": 1031.93, "total_tokens": 1080032} {"current_steps": 11990, "total_steps": 76960, "loss": 0.3015, "lr": 4.952756312322806e-05, "epoch": 3.115904365904366, "percentage": 15.58, "elapsed_time": "0:17:27", "remaining_time": "1:34:33", "throughput": 1031.94, "total_tokens": 1080480} {"current_steps": 11995, "total_steps": 76960, "loss": 0.2163, "lr": 4.952646548983215e-05, "epoch": 3.1172037422037424, "percentage": 15.59, "elapsed_time": "0:17:27", "remaining_time": "1:34:33", "throughput": 1032.0, "total_tokens": 1080976} {"current_steps": 12000, "total_steps": 76960, "loss": 0.3264, "lr": 4.952536659501662e-05, "epoch": 3.1185031185031185, "percentage": 15.59, "elapsed_time": "0:17:27", "remaining_time": "1:34:32", "throughput": 1032.02, "total_tokens": 1081424} {"current_steps": 12005, "total_steps": 76960, "loss": 0.2274, "lr": 4.952426643883799e-05, "epoch": 3.119802494802495, "percentage": 15.6, "elapsed_time": "0:17:28", "remaining_time": "1:34:31", "throughput": 1032.0, "total_tokens": 1081840} {"current_steps": 12010, "total_steps": 76960, "loss": 0.2252, "lr": 4.952316502135284e-05, "epoch": 3.121101871101871, "percentage": 15.61, "elapsed_time": "0:17:28", "remaining_time": "1:34:31", "throughput": 1032.02, "total_tokens": 1082288} {"current_steps": 12015, "total_steps": 76960, "loss": 0.2311, "lr": 4.952206234261781e-05, "epoch": 3.1224012474012475, "percentage": 15.61, "elapsed_time": "0:17:29", "remaining_time": "1:34:30", "throughput": 1032.01, "total_tokens": 1082720} {"current_steps": 12020, "total_steps": 76960, "loss": 0.2653, "lr": 4.952095840268962e-05, "epoch": 3.1237006237006235, "percentage": 15.62, "elapsed_time": "0:17:29", "remaining_time": "1:34:30", "throughput": 1032.02, "total_tokens": 1083152} {"current_steps": 12025, "total_steps": 76960, "loss": 0.1061, "lr": 4.9519853201625044e-05, "epoch": 3.125, "percentage": 15.62, "elapsed_time": "0:17:29", "remaining_time": "1:34:29", "throughput": 1032.0, "total_tokens": 1083568} {"current_steps": 12030, "total_steps": 76960, "loss": 0.3622, "lr": 4.951874673948093e-05, "epoch": 3.1262993762993765, "percentage": 15.63, "elapsed_time": "0:17:30", "remaining_time": "1:34:29", "throughput": 1032.03, "total_tokens": 1084032} {"current_steps": 12035, "total_steps": 76960, "loss": 0.2539, "lr": 4.951763901631417e-05, "epoch": 3.1275987525987525, "percentage": 15.64, "elapsed_time": "0:17:30", "remaining_time": "1:34:28", "throughput": 1032.04, "total_tokens": 1084480} {"current_steps": 12040, "total_steps": 76960, "loss": 0.2532, "lr": 4.9516530032181744e-05, "epoch": 3.128898128898129, "percentage": 15.64, "elapsed_time": "0:17:31", "remaining_time": "1:34:28", "throughput": 1032.07, "total_tokens": 1084944} {"current_steps": 12045, "total_steps": 76960, "loss": 0.3106, "lr": 4.951541978714069e-05, "epoch": 3.130197505197505, "percentage": 15.65, "elapsed_time": "0:17:31", "remaining_time": "1:34:27", "throughput": 1032.1, "total_tokens": 1085408} {"current_steps": 12050, "total_steps": 76960, "loss": 0.198, "lr": 4.951430828124811e-05, "epoch": 3.1314968814968815, "percentage": 15.66, "elapsed_time": "0:17:32", "remaining_time": "1:34:27", "throughput": 1032.1, "total_tokens": 1085840} {"current_steps": 12055, "total_steps": 76960, "loss": 0.2507, "lr": 4.9513195514561164e-05, "epoch": 3.1327962577962576, "percentage": 15.66, "elapsed_time": "0:17:32", "remaining_time": "1:34:26", "throughput": 1032.15, "total_tokens": 1086320} {"current_steps": 12060, "total_steps": 76960, "loss": 0.2208, "lr": 4.951208148713708e-05, "epoch": 3.134095634095634, "percentage": 15.67, "elapsed_time": "0:17:32", "remaining_time": "1:34:26", "throughput": 1032.14, "total_tokens": 1086736} {"current_steps": 12065, "total_steps": 76960, "loss": 0.2691, "lr": 4.9510966199033174e-05, "epoch": 3.1353950103950106, "percentage": 15.68, "elapsed_time": "0:17:33", "remaining_time": "1:34:25", "throughput": 1032.15, "total_tokens": 1087184} {"current_steps": 12070, "total_steps": 76960, "loss": 0.2182, "lr": 4.950984965030678e-05, "epoch": 3.1366943866943866, "percentage": 15.68, "elapsed_time": "0:17:33", "remaining_time": "1:34:25", "throughput": 1032.17, "total_tokens": 1087632} {"current_steps": 12075, "total_steps": 76960, "loss": 0.3108, "lr": 4.9508731841015334e-05, "epoch": 3.137993762993763, "percentage": 15.69, "elapsed_time": "0:17:34", "remaining_time": "1:34:24", "throughput": 1032.19, "total_tokens": 1088080} {"current_steps": 12080, "total_steps": 76960, "loss": 0.2195, "lr": 4.950761277121633e-05, "epoch": 3.139293139293139, "percentage": 15.7, "elapsed_time": "0:17:34", "remaining_time": "1:34:23", "throughput": 1032.22, "total_tokens": 1088544} {"current_steps": 12085, "total_steps": 76960, "loss": 0.3117, "lr": 4.950649244096731e-05, "epoch": 3.1405925155925156, "percentage": 15.7, "elapsed_time": "0:17:34", "remaining_time": "1:34:23", "throughput": 1032.23, "total_tokens": 1088992} {"current_steps": 12090, "total_steps": 76960, "loss": 0.2135, "lr": 4.950537085032591e-05, "epoch": 3.141891891891892, "percentage": 15.71, "elapsed_time": "0:17:35", "remaining_time": "1:34:22", "throughput": 1032.24, "total_tokens": 1089440} {"current_steps": 12095, "total_steps": 76960, "loss": 0.3415, "lr": 4.9504247999349815e-05, "epoch": 3.143191268191268, "percentage": 15.72, "elapsed_time": "0:17:35", "remaining_time": "1:34:22", "throughput": 1032.31, "total_tokens": 1089936} {"current_steps": 12100, "total_steps": 76960, "loss": 0.2541, "lr": 4.950312388809676e-05, "epoch": 3.1444906444906446, "percentage": 15.72, "elapsed_time": "0:17:36", "remaining_time": "1:34:21", "throughput": 1032.29, "total_tokens": 1090352} {"current_steps": 12105, "total_steps": 76960, "loss": 0.2398, "lr": 4.950199851662456e-05, "epoch": 3.1457900207900207, "percentage": 15.73, "elapsed_time": "0:17:36", "remaining_time": "1:34:21", "throughput": 1032.27, "total_tokens": 1090768} {"current_steps": 12110, "total_steps": 76960, "loss": 0.2649, "lr": 4.950087188499111e-05, "epoch": 3.147089397089397, "percentage": 15.74, "elapsed_time": "0:17:37", "remaining_time": "1:34:20", "throughput": 1032.3, "total_tokens": 1091232} {"current_steps": 12115, "total_steps": 76960, "loss": 0.34, "lr": 4.9499743993254335e-05, "epoch": 3.148388773388773, "percentage": 15.74, "elapsed_time": "0:17:37", "remaining_time": "1:34:20", "throughput": 1032.35, "total_tokens": 1091712} {"current_steps": 12120, "total_steps": 76960, "loss": 0.2665, "lr": 4.949861484147225e-05, "epoch": 3.1496881496881497, "percentage": 15.75, "elapsed_time": "0:17:37", "remaining_time": "1:34:19", "throughput": 1032.35, "total_tokens": 1092144} {"current_steps": 12125, "total_steps": 76960, "loss": 0.2237, "lr": 4.949748442970293e-05, "epoch": 3.150987525987526, "percentage": 15.75, "elapsed_time": "0:17:38", "remaining_time": "1:34:19", "throughput": 1032.35, "total_tokens": 1092576} {"current_steps": 12130, "total_steps": 76960, "loss": 0.2199, "lr": 4.9496352758004524e-05, "epoch": 3.1522869022869022, "percentage": 15.76, "elapsed_time": "0:17:38", "remaining_time": "1:34:18", "throughput": 1032.36, "total_tokens": 1093024} {"current_steps": 12135, "total_steps": 76960, "loss": 0.3749, "lr": 4.949521982643522e-05, "epoch": 3.1535862785862787, "percentage": 15.77, "elapsed_time": "0:17:39", "remaining_time": "1:34:18", "throughput": 1032.38, "total_tokens": 1093472} {"current_steps": 12140, "total_steps": 76960, "loss": 0.225, "lr": 4.9494085635053286e-05, "epoch": 3.1548856548856548, "percentage": 15.77, "elapsed_time": "0:17:39", "remaining_time": "1:34:17", "throughput": 1032.39, "total_tokens": 1093920} {"current_steps": 12145, "total_steps": 76960, "loss": 0.2171, "lr": 4.949295018391706e-05, "epoch": 3.1561850311850312, "percentage": 15.78, "elapsed_time": "0:17:40", "remaining_time": "1:34:17", "throughput": 1032.42, "total_tokens": 1094384} {"current_steps": 12150, "total_steps": 76960, "loss": 0.3481, "lr": 4.949181347308494e-05, "epoch": 3.1574844074844073, "percentage": 15.79, "elapsed_time": "0:17:40", "remaining_time": "1:34:16", "throughput": 1032.41, "total_tokens": 1094800} {"current_steps": 12155, "total_steps": 76960, "loss": 0.1983, "lr": 4.949067550261539e-05, "epoch": 3.1587837837837838, "percentage": 15.79, "elapsed_time": "0:17:40", "remaining_time": "1:34:15", "throughput": 1032.44, "total_tokens": 1095264} {"current_steps": 12160, "total_steps": 76960, "loss": 0.1829, "lr": 4.948953627256693e-05, "epoch": 3.1600831600831603, "percentage": 15.8, "elapsed_time": "0:17:41", "remaining_time": "1:34:15", "throughput": 1032.44, "total_tokens": 1095696} {"current_steps": 12165, "total_steps": 76960, "loss": 0.2632, "lr": 4.948839578299815e-05, "epoch": 3.1613825363825363, "percentage": 15.81, "elapsed_time": "0:17:41", "remaining_time": "1:34:14", "throughput": 1032.44, "total_tokens": 1096128} {"current_steps": 12170, "total_steps": 76960, "loss": 0.2015, "lr": 4.948725403396771e-05, "epoch": 3.162681912681913, "percentage": 15.81, "elapsed_time": "0:17:42", "remaining_time": "1:34:14", "throughput": 1032.48, "total_tokens": 1096608} {"current_steps": 12175, "total_steps": 76960, "loss": 0.3182, "lr": 4.948611102553434e-05, "epoch": 3.163981288981289, "percentage": 15.82, "elapsed_time": "0:17:42", "remaining_time": "1:34:13", "throughput": 1032.53, "total_tokens": 1097088} {"current_steps": 12180, "total_steps": 76960, "loss": 0.1136, "lr": 4.948496675775681e-05, "epoch": 3.1652806652806653, "percentage": 15.83, "elapsed_time": "0:17:42", "remaining_time": "1:34:13", "throughput": 1032.54, "total_tokens": 1097536} {"current_steps": 12185, "total_steps": 76960, "loss": 0.2725, "lr": 4.948382123069399e-05, "epoch": 3.1665800415800414, "percentage": 15.83, "elapsed_time": "0:17:43", "remaining_time": "1:34:12", "throughput": 1032.57, "total_tokens": 1098000} {"current_steps": 12190, "total_steps": 76960, "loss": 0.3244, "lr": 4.9482674444404776e-05, "epoch": 3.167879417879418, "percentage": 15.84, "elapsed_time": "0:17:43", "remaining_time": "1:34:12", "throughput": 1032.61, "total_tokens": 1098480} {"current_steps": 12195, "total_steps": 76960, "loss": 0.1589, "lr": 4.948152639894816e-05, "epoch": 3.1691787941787943, "percentage": 15.85, "elapsed_time": "0:17:44", "remaining_time": "1:34:11", "throughput": 1032.63, "total_tokens": 1098928} {"current_steps": 12200, "total_steps": 76960, "loss": 0.221, "lr": 4.948037709438319e-05, "epoch": 3.1704781704781704, "percentage": 15.85, "elapsed_time": "0:17:44", "remaining_time": "1:34:11", "throughput": 1032.63, "total_tokens": 1099360} {"current_steps": 12205, "total_steps": 76960, "loss": 0.2684, "lr": 4.947922653076896e-05, "epoch": 3.171777546777547, "percentage": 15.86, "elapsed_time": "0:17:45", "remaining_time": "1:34:10", "throughput": 1032.64, "total_tokens": 1099808} {"current_steps": 12210, "total_steps": 76960, "loss": 0.1676, "lr": 4.947807470816466e-05, "epoch": 3.173076923076923, "percentage": 15.87, "elapsed_time": "0:17:45", "remaining_time": "1:34:10", "throughput": 1032.65, "total_tokens": 1100256} {"current_steps": 12215, "total_steps": 76960, "loss": 0.3083, "lr": 4.9476921626629524e-05, "epoch": 3.1743762993762994, "percentage": 15.87, "elapsed_time": "0:17:45", "remaining_time": "1:34:09", "throughput": 1032.67, "total_tokens": 1100704} {"current_steps": 12220, "total_steps": 76960, "loss": 0.2369, "lr": 4.9475767286222856e-05, "epoch": 3.175675675675676, "percentage": 15.88, "elapsed_time": "0:17:46", "remaining_time": "1:34:09", "throughput": 1032.71, "total_tokens": 1101184} {"current_steps": 12225, "total_steps": 76960, "loss": 0.203, "lr": 4.947461168700402e-05, "epoch": 3.176975051975052, "percentage": 15.88, "elapsed_time": "0:17:46", "remaining_time": "1:34:08", "throughput": 1032.77, "total_tokens": 1101680} {"current_steps": 12230, "total_steps": 76960, "loss": 0.1814, "lr": 4.947345482903246e-05, "epoch": 3.1782744282744284, "percentage": 15.89, "elapsed_time": "0:17:47", "remaining_time": "1:34:08", "throughput": 1032.77, "total_tokens": 1102112} {"current_steps": 12235, "total_steps": 76960, "loss": 0.3002, "lr": 4.947229671236767e-05, "epoch": 3.1795738045738045, "percentage": 15.9, "elapsed_time": "0:17:47", "remaining_time": "1:34:07", "throughput": 1032.77, "total_tokens": 1102544} {"current_steps": 12240, "total_steps": 76960, "loss": 0.3675, "lr": 4.9471137337069215e-05, "epoch": 3.180873180873181, "percentage": 15.9, "elapsed_time": "0:17:47", "remaining_time": "1:34:07", "throughput": 1032.76, "total_tokens": 1102960} {"current_steps": 12245, "total_steps": 76960, "loss": 0.2034, "lr": 4.946997670319671e-05, "epoch": 3.182172557172557, "percentage": 15.91, "elapsed_time": "0:17:48", "remaining_time": "1:34:06", "throughput": 1032.76, "total_tokens": 1103408} {"current_steps": 12250, "total_steps": 76960, "loss": 0.2874, "lr": 4.946881481080987e-05, "epoch": 3.1834719334719335, "percentage": 15.92, "elapsed_time": "0:17:48", "remaining_time": "1:34:05", "throughput": 1032.78, "total_tokens": 1103856} {"current_steps": 12255, "total_steps": 76960, "loss": 0.2433, "lr": 4.946765165996843e-05, "epoch": 3.18477130977131, "percentage": 15.92, "elapsed_time": "0:17:49", "remaining_time": "1:34:05", "throughput": 1032.8, "total_tokens": 1104304} {"current_steps": 12260, "total_steps": 76960, "loss": 0.2963, "lr": 4.946648725073222e-05, "epoch": 3.186070686070686, "percentage": 15.93, "elapsed_time": "0:17:49", "remaining_time": "1:34:04", "throughput": 1032.81, "total_tokens": 1104752} {"current_steps": 12265, "total_steps": 76960, "loss": 0.2649, "lr": 4.946532158316113e-05, "epoch": 3.1873700623700625, "percentage": 15.94, "elapsed_time": "0:17:50", "remaining_time": "1:34:04", "throughput": 1032.8, "total_tokens": 1105168} {"current_steps": 12270, "total_steps": 76960, "loss": 0.3, "lr": 4.946415465731511e-05, "epoch": 3.1886694386694385, "percentage": 15.94, "elapsed_time": "0:17:50", "remaining_time": "1:34:03", "throughput": 1032.81, "total_tokens": 1105616} {"current_steps": 12275, "total_steps": 76960, "loss": 0.3209, "lr": 4.9462986473254166e-05, "epoch": 3.189968814968815, "percentage": 15.95, "elapsed_time": "0:17:50", "remaining_time": "1:34:03", "throughput": 1032.83, "total_tokens": 1106064} {"current_steps": 12280, "total_steps": 76960, "loss": 0.2817, "lr": 4.9461817031038405e-05, "epoch": 3.1912681912681915, "percentage": 15.96, "elapsed_time": "0:17:51", "remaining_time": "1:34:02", "throughput": 1032.81, "total_tokens": 1106480} {"current_steps": 12285, "total_steps": 76960, "loss": 0.2849, "lr": 4.946064633072795e-05, "epoch": 3.1925675675675675, "percentage": 15.96, "elapsed_time": "0:17:51", "remaining_time": "1:34:02", "throughput": 1032.83, "total_tokens": 1106928} {"current_steps": 12290, "total_steps": 76960, "loss": 0.2619, "lr": 4.945947437238301e-05, "epoch": 3.193866943866944, "percentage": 15.97, "elapsed_time": "0:17:52", "remaining_time": "1:34:01", "throughput": 1032.84, "total_tokens": 1107376} {"current_steps": 12295, "total_steps": 76960, "loss": 0.2467, "lr": 4.945830115606388e-05, "epoch": 3.19516632016632, "percentage": 15.98, "elapsed_time": "0:17:52", "remaining_time": "1:34:01", "throughput": 1032.87, "total_tokens": 1107840} {"current_steps": 12300, "total_steps": 76960, "loss": 0.2259, "lr": 4.9457126681830876e-05, "epoch": 3.1964656964656966, "percentage": 15.98, "elapsed_time": "0:17:53", "remaining_time": "1:34:00", "throughput": 1032.88, "total_tokens": 1108288} {"current_steps": 12305, "total_steps": 76960, "loss": 0.1654, "lr": 4.945595094974442e-05, "epoch": 3.1977650727650726, "percentage": 15.99, "elapsed_time": "0:17:53", "remaining_time": "1:34:00", "throughput": 1032.87, "total_tokens": 1108704} {"current_steps": 12310, "total_steps": 76960, "loss": 0.2525, "lr": 4.945477395986497e-05, "epoch": 3.199064449064449, "percentage": 16.0, "elapsed_time": "0:17:53", "remaining_time": "1:33:59", "throughput": 1032.9, "total_tokens": 1109168} {"current_steps": 12315, "total_steps": 76960, "loss": 0.4178, "lr": 4.945359571225307e-05, "epoch": 3.2003638253638256, "percentage": 16.0, "elapsed_time": "0:17:54", "remaining_time": "1:33:59", "throughput": 1032.94, "total_tokens": 1109648} {"current_steps": 12320, "total_steps": 76960, "loss": 0.2151, "lr": 4.94524162069693e-05, "epoch": 3.2016632016632016, "percentage": 16.01, "elapsed_time": "0:17:54", "remaining_time": "1:33:58", "throughput": 1032.94, "total_tokens": 1110080} {"current_steps": 12325, "total_steps": 76960, "loss": 0.3601, "lr": 4.945123544407434e-05, "epoch": 3.202962577962578, "percentage": 16.01, "elapsed_time": "0:17:55", "remaining_time": "1:33:58", "throughput": 1033.0, "total_tokens": 1110576} {"current_steps": 12330, "total_steps": 76960, "loss": 0.2431, "lr": 4.945005342362892e-05, "epoch": 3.204261954261954, "percentage": 16.02, "elapsed_time": "0:17:55", "remaining_time": "1:33:57", "throughput": 1033.02, "total_tokens": 1111024} {"current_steps": 12335, "total_steps": 76960, "loss": 0.2618, "lr": 4.944887014569381e-05, "epoch": 3.2055613305613306, "percentage": 16.03, "elapsed_time": "0:17:55", "remaining_time": "1:33:56", "throughput": 1033.02, "total_tokens": 1111456} {"current_steps": 12340, "total_steps": 76960, "loss": 0.2778, "lr": 4.9447685610329905e-05, "epoch": 3.2068607068607067, "percentage": 16.03, "elapsed_time": "0:17:56", "remaining_time": "1:33:56", "throughput": 1033.03, "total_tokens": 1111904} {"current_steps": 12345, "total_steps": 76960, "loss": 0.2903, "lr": 4.944649981759809e-05, "epoch": 3.208160083160083, "percentage": 16.04, "elapsed_time": "0:17:56", "remaining_time": "1:33:55", "throughput": 1033.05, "total_tokens": 1112352} {"current_steps": 12350, "total_steps": 76960, "loss": 0.2778, "lr": 4.944531276755937e-05, "epoch": 3.2094594594594597, "percentage": 16.05, "elapsed_time": "0:17:57", "remaining_time": "1:33:55", "throughput": 1033.04, "total_tokens": 1112784} {"current_steps": 12355, "total_steps": 76960, "loss": 0.2479, "lr": 4.9444124460274785e-05, "epoch": 3.2107588357588357, "percentage": 16.05, "elapsed_time": "0:17:57", "remaining_time": "1:33:54", "throughput": 1033.06, "total_tokens": 1113232} {"current_steps": 12360, "total_steps": 76960, "loss": 0.1933, "lr": 4.944293489580547e-05, "epoch": 3.212058212058212, "percentage": 16.06, "elapsed_time": "0:17:58", "remaining_time": "1:33:54", "throughput": 1033.09, "total_tokens": 1113696} {"current_steps": 12365, "total_steps": 76960, "loss": 0.1646, "lr": 4.944174407421258e-05, "epoch": 3.2133575883575882, "percentage": 16.07, "elapsed_time": "0:17:58", "remaining_time": "1:33:53", "throughput": 1033.15, "total_tokens": 1114192} {"current_steps": 12370, "total_steps": 76960, "loss": 0.411, "lr": 4.9440551995557384e-05, "epoch": 3.2146569646569647, "percentage": 16.07, "elapsed_time": "0:17:58", "remaining_time": "1:33:53", "throughput": 1033.15, "total_tokens": 1114624} {"current_steps": 12375, "total_steps": 76960, "loss": 0.1486, "lr": 4.943935865990118e-05, "epoch": 3.2159563409563408, "percentage": 16.08, "elapsed_time": "0:17:59", "remaining_time": "1:33:52", "throughput": 1033.19, "total_tokens": 1115104} {"current_steps": 12380, "total_steps": 76960, "loss": 0.141, "lr": 4.943816406730534e-05, "epoch": 3.2172557172557172, "percentage": 16.09, "elapsed_time": "0:17:59", "remaining_time": "1:33:52", "throughput": 1033.19, "total_tokens": 1115536} {"current_steps": 12385, "total_steps": 76960, "loss": 0.4694, "lr": 4.94369682178313e-05, "epoch": 3.2185550935550937, "percentage": 16.09, "elapsed_time": "0:18:00", "remaining_time": "1:33:51", "throughput": 1033.22, "total_tokens": 1116000} {"current_steps": 12390, "total_steps": 76960, "loss": 0.2719, "lr": 4.943577111154058e-05, "epoch": 3.2198544698544698, "percentage": 16.1, "elapsed_time": "0:18:00", "remaining_time": "1:33:51", "throughput": 1033.21, "total_tokens": 1116432} {"current_steps": 12395, "total_steps": 76960, "loss": 0.249, "lr": 4.943457274849473e-05, "epoch": 3.2211538461538463, "percentage": 16.11, "elapsed_time": "0:18:00", "remaining_time": "1:33:50", "throughput": 1033.27, "total_tokens": 1116928} {"current_steps": 12400, "total_steps": 76960, "loss": 0.2198, "lr": 4.94333731287554e-05, "epoch": 3.2224532224532223, "percentage": 16.11, "elapsed_time": "0:18:01", "remaining_time": "1:33:50", "throughput": 1033.26, "total_tokens": 1117360} {"current_steps": 12405, "total_steps": 76960, "loss": 0.2095, "lr": 4.9432172252384276e-05, "epoch": 3.223752598752599, "percentage": 16.12, "elapsed_time": "0:18:01", "remaining_time": "1:33:49", "throughput": 1033.25, "total_tokens": 1117792} {"current_steps": 12410, "total_steps": 76960, "loss": 0.2117, "lr": 4.9430970119443124e-05, "epoch": 3.225051975051975, "percentage": 16.13, "elapsed_time": "0:18:02", "remaining_time": "1:33:49", "throughput": 1033.24, "total_tokens": 1118224} {"current_steps": 12415, "total_steps": 76960, "loss": 0.4231, "lr": 4.9429766729993776e-05, "epoch": 3.2263513513513513, "percentage": 16.13, "elapsed_time": "0:18:02", "remaining_time": "1:33:48", "throughput": 1033.24, "total_tokens": 1118656} {"current_steps": 12420, "total_steps": 76960, "loss": 0.331, "lr": 4.9428562084098106e-05, "epoch": 3.227650727650728, "percentage": 16.14, "elapsed_time": "0:18:03", "remaining_time": "1:33:48", "throughput": 1033.23, "total_tokens": 1119088} {"current_steps": 12425, "total_steps": 76960, "loss": 0.2649, "lr": 4.942735618181808e-05, "epoch": 3.228950103950104, "percentage": 16.14, "elapsed_time": "0:18:03", "remaining_time": "1:33:47", "throughput": 1033.22, "total_tokens": 1119504} {"current_steps": 12430, "total_steps": 76960, "loss": 0.2598, "lr": 4.942614902321574e-05, "epoch": 3.2302494802494803, "percentage": 16.15, "elapsed_time": "0:18:03", "remaining_time": "1:33:47", "throughput": 1033.23, "total_tokens": 1119952} {"current_steps": 12435, "total_steps": 76960, "loss": 0.2929, "lr": 4.9424940608353135e-05, "epoch": 3.2315488565488564, "percentage": 16.16, "elapsed_time": "0:18:04", "remaining_time": "1:33:46", "throughput": 1033.27, "total_tokens": 1120432} {"current_steps": 12440, "total_steps": 76960, "loss": 0.2093, "lr": 4.9423730937292434e-05, "epoch": 3.232848232848233, "percentage": 16.16, "elapsed_time": "0:18:04", "remaining_time": "1:33:46", "throughput": 1033.32, "total_tokens": 1120912} {"current_steps": 12445, "total_steps": 76960, "loss": 0.2933, "lr": 4.942252001009585e-05, "epoch": 3.2341476091476093, "percentage": 16.17, "elapsed_time": "0:18:05", "remaining_time": "1:33:45", "throughput": 1033.33, "total_tokens": 1121360} {"current_steps": 12450, "total_steps": 76960, "loss": 0.1792, "lr": 4.942130782682566e-05, "epoch": 3.2354469854469854, "percentage": 16.18, "elapsed_time": "0:18:05", "remaining_time": "1:33:45", "throughput": 1033.33, "total_tokens": 1121792} {"current_steps": 12455, "total_steps": 76960, "loss": 0.2629, "lr": 4.942009438754421e-05, "epoch": 3.236746361746362, "percentage": 16.18, "elapsed_time": "0:18:06", "remaining_time": "1:33:44", "throughput": 1033.34, "total_tokens": 1122240} {"current_steps": 12460, "total_steps": 76960, "loss": 0.2835, "lr": 4.9418879692313914e-05, "epoch": 3.238045738045738, "percentage": 16.19, "elapsed_time": "0:18:06", "remaining_time": "1:33:44", "throughput": 1033.34, "total_tokens": 1122672} {"current_steps": 12465, "total_steps": 76960, "loss": 0.2552, "lr": 4.9417663741197236e-05, "epoch": 3.2393451143451144, "percentage": 16.2, "elapsed_time": "0:18:06", "remaining_time": "1:33:43", "throughput": 1033.34, "total_tokens": 1123104} {"current_steps": 12470, "total_steps": 76960, "loss": 0.2582, "lr": 4.941644653425671e-05, "epoch": 3.2406444906444904, "percentage": 16.2, "elapsed_time": "0:18:07", "remaining_time": "1:33:42", "throughput": 1033.34, "total_tokens": 1123536} {"current_steps": 12475, "total_steps": 76960, "loss": 0.2672, "lr": 4.941522807155495e-05, "epoch": 3.241943866943867, "percentage": 16.21, "elapsed_time": "0:18:07", "remaining_time": "1:33:42", "throughput": 1033.34, "total_tokens": 1123968} {"current_steps": 12480, "total_steps": 76960, "loss": 0.2194, "lr": 4.941400835315461e-05, "epoch": 3.2432432432432434, "percentage": 16.22, "elapsed_time": "0:18:08", "remaining_time": "1:33:41", "throughput": 1033.34, "total_tokens": 1124400} {"current_steps": 12485, "total_steps": 76960, "loss": 0.2547, "lr": 4.941278737911843e-05, "epoch": 3.2445426195426195, "percentage": 16.22, "elapsed_time": "0:18:08", "remaining_time": "1:33:41", "throughput": 1033.37, "total_tokens": 1124864} {"current_steps": 12490, "total_steps": 76960, "loss": 0.2123, "lr": 4.941156514950921e-05, "epoch": 3.245841995841996, "percentage": 16.23, "elapsed_time": "0:18:08", "remaining_time": "1:33:40", "throughput": 1033.36, "total_tokens": 1125280} {"current_steps": 12495, "total_steps": 76960, "loss": 0.1734, "lr": 4.9410341664389803e-05, "epoch": 3.247141372141372, "percentage": 16.24, "elapsed_time": "0:18:09", "remaining_time": "1:33:40", "throughput": 1033.33, "total_tokens": 1125680} {"current_steps": 12500, "total_steps": 76960, "loss": 0.2191, "lr": 4.940911692382313e-05, "epoch": 3.2484407484407485, "percentage": 16.24, "elapsed_time": "0:18:09", "remaining_time": "1:33:39", "throughput": 1033.36, "total_tokens": 1126144} {"current_steps": 12505, "total_steps": 76960, "loss": 0.3229, "lr": 4.9407890927872184e-05, "epoch": 3.249740124740125, "percentage": 16.25, "elapsed_time": "0:18:10", "remaining_time": "1:33:39", "throughput": 1033.39, "total_tokens": 1126608} {"current_steps": 12510, "total_steps": 76960, "loss": 0.3141, "lr": 4.9406663676600026e-05, "epoch": 3.251039501039501, "percentage": 16.26, "elapsed_time": "0:18:10", "remaining_time": "1:33:38", "throughput": 1033.4, "total_tokens": 1127056} {"current_steps": 12515, "total_steps": 76960, "loss": 0.2475, "lr": 4.940543517006977e-05, "epoch": 3.2523388773388775, "percentage": 16.26, "elapsed_time": "0:18:11", "remaining_time": "1:33:38", "throughput": 1033.43, "total_tokens": 1127520} {"current_steps": 12520, "total_steps": 76960, "loss": 0.2232, "lr": 4.94042054083446e-05, "epoch": 3.2536382536382535, "percentage": 16.27, "elapsed_time": "0:18:11", "remaining_time": "1:33:37", "throughput": 1033.41, "total_tokens": 1127936} {"current_steps": 12525, "total_steps": 76960, "loss": 0.2137, "lr": 4.940297439148776e-05, "epoch": 3.25493762993763, "percentage": 16.27, "elapsed_time": "0:18:11", "remaining_time": "1:33:37", "throughput": 1033.43, "total_tokens": 1128384} {"current_steps": 12530, "total_steps": 76960, "loss": 0.279, "lr": 4.940174211956256e-05, "epoch": 3.256237006237006, "percentage": 16.28, "elapsed_time": "0:18:12", "remaining_time": "1:33:36", "throughput": 1033.44, "total_tokens": 1128832} {"current_steps": 12535, "total_steps": 76960, "loss": 0.1855, "lr": 4.94005085926324e-05, "epoch": 3.2575363825363826, "percentage": 16.29, "elapsed_time": "0:18:12", "remaining_time": "1:33:36", "throughput": 1033.44, "total_tokens": 1129264} {"current_steps": 12540, "total_steps": 76960, "loss": 0.1097, "lr": 4.9399273810760685e-05, "epoch": 3.258835758835759, "percentage": 16.29, "elapsed_time": "0:18:13", "remaining_time": "1:33:35", "throughput": 1033.43, "total_tokens": 1129680} {"current_steps": 12545, "total_steps": 76960, "loss": 0.2216, "lr": 4.939803777401095e-05, "epoch": 3.260135135135135, "percentage": 16.3, "elapsed_time": "0:18:13", "remaining_time": "1:33:35", "throughput": 1033.44, "total_tokens": 1130128} {"current_steps": 12550, "total_steps": 76960, "loss": 0.3092, "lr": 4.9396800482446746e-05, "epoch": 3.2614345114345116, "percentage": 16.31, "elapsed_time": "0:18:13", "remaining_time": "1:33:34", "throughput": 1033.41, "total_tokens": 1130528} {"current_steps": 12555, "total_steps": 76960, "loss": 0.2081, "lr": 4.939556193613173e-05, "epoch": 3.2627338877338876, "percentage": 16.31, "elapsed_time": "0:18:14", "remaining_time": "1:33:34", "throughput": 1033.43, "total_tokens": 1130992} {"current_steps": 12560, "total_steps": 76960, "loss": 0.2816, "lr": 4.939432213512958e-05, "epoch": 3.264033264033264, "percentage": 16.32, "elapsed_time": "0:18:14", "remaining_time": "1:33:33", "throughput": 1033.46, "total_tokens": 1131456} {"current_steps": 12565, "total_steps": 76960, "loss": 0.2272, "lr": 4.939308107950407e-05, "epoch": 3.26533264033264, "percentage": 16.33, "elapsed_time": "0:18:15", "remaining_time": "1:33:33", "throughput": 1033.49, "total_tokens": 1131920} {"current_steps": 12570, "total_steps": 76960, "loss": 0.2185, "lr": 4.939183876931903e-05, "epoch": 3.2666320166320166, "percentage": 16.33, "elapsed_time": "0:18:15", "remaining_time": "1:33:32", "throughput": 1033.49, "total_tokens": 1132352} {"current_steps": 12575, "total_steps": 76960, "loss": 0.2239, "lr": 4.939059520463835e-05, "epoch": 3.267931392931393, "percentage": 16.34, "elapsed_time": "0:18:16", "remaining_time": "1:33:32", "throughput": 1033.52, "total_tokens": 1132816} {"current_steps": 12580, "total_steps": 76960, "loss": 0.2423, "lr": 4.938935038552599e-05, "epoch": 3.269230769230769, "percentage": 16.35, "elapsed_time": "0:18:16", "remaining_time": "1:33:31", "throughput": 1033.53, "total_tokens": 1133264} {"current_steps": 12585, "total_steps": 76960, "loss": 0.1666, "lr": 4.938810431204597e-05, "epoch": 3.2705301455301456, "percentage": 16.35, "elapsed_time": "0:18:16", "remaining_time": "1:33:30", "throughput": 1033.56, "total_tokens": 1133728} {"current_steps": 12590, "total_steps": 76960, "loss": 0.2217, "lr": 4.9386856984262374e-05, "epoch": 3.2718295218295217, "percentage": 16.36, "elapsed_time": "0:18:17", "remaining_time": "1:33:30", "throughput": 1033.54, "total_tokens": 1134144} {"current_steps": 12595, "total_steps": 76960, "loss": 0.213, "lr": 4.9385608402239364e-05, "epoch": 3.273128898128898, "percentage": 16.37, "elapsed_time": "0:18:17", "remaining_time": "1:33:29", "throughput": 1033.53, "total_tokens": 1134560} {"current_steps": 12600, "total_steps": 76960, "loss": 0.2548, "lr": 4.9384358566041144e-05, "epoch": 3.274428274428274, "percentage": 16.37, "elapsed_time": "0:18:18", "remaining_time": "1:33:29", "throughput": 1033.56, "total_tokens": 1135024} {"current_steps": 12605, "total_steps": 76960, "loss": 0.3305, "lr": 4.938310747573201e-05, "epoch": 3.2757276507276507, "percentage": 16.38, "elapsed_time": "0:18:18", "remaining_time": "1:33:28", "throughput": 1033.56, "total_tokens": 1135456} {"current_steps": 12610, "total_steps": 76960, "loss": 0.3608, "lr": 4.938185513137627e-05, "epoch": 3.277027027027027, "percentage": 16.39, "elapsed_time": "0:18:19", "remaining_time": "1:33:28", "throughput": 1033.57, "total_tokens": 1135904} {"current_steps": 12615, "total_steps": 76960, "loss": 0.1612, "lr": 4.9380601533038385e-05, "epoch": 3.2783264033264032, "percentage": 16.39, "elapsed_time": "0:18:19", "remaining_time": "1:33:27", "throughput": 1033.59, "total_tokens": 1136352} {"current_steps": 12620, "total_steps": 76960, "loss": 0.2531, "lr": 4.937934668078279e-05, "epoch": 3.2796257796257797, "percentage": 16.4, "elapsed_time": "0:18:19", "remaining_time": "1:33:27", "throughput": 1033.59, "total_tokens": 1136784} {"current_steps": 12625, "total_steps": 76960, "loss": 0.2637, "lr": 4.937809057467404e-05, "epoch": 3.2809251559251558, "percentage": 16.4, "elapsed_time": "0:18:20", "remaining_time": "1:33:26", "throughput": 1033.62, "total_tokens": 1137248} {"current_steps": 12630, "total_steps": 76960, "loss": 0.2122, "lr": 4.937683321477673e-05, "epoch": 3.2822245322245323, "percentage": 16.41, "elapsed_time": "0:18:20", "remaining_time": "1:33:26", "throughput": 1033.66, "total_tokens": 1137728} {"current_steps": 12635, "total_steps": 76960, "loss": 0.2474, "lr": 4.9375574601155536e-05, "epoch": 3.2835239085239083, "percentage": 16.42, "elapsed_time": "0:18:21", "remaining_time": "1:33:25", "throughput": 1033.72, "total_tokens": 1138224} {"current_steps": 12640, "total_steps": 76960, "loss": 0.3617, "lr": 4.9374314733875184e-05, "epoch": 3.284823284823285, "percentage": 16.42, "elapsed_time": "0:18:21", "remaining_time": "1:33:25", "throughput": 1033.72, "total_tokens": 1138656} {"current_steps": 12645, "total_steps": 76960, "loss": 0.236, "lr": 4.937305361300046e-05, "epoch": 3.2861226611226613, "percentage": 16.43, "elapsed_time": "0:18:21", "remaining_time": "1:33:24", "throughput": 1033.69, "total_tokens": 1139056} {"current_steps": 12650, "total_steps": 76960, "loss": 0.2654, "lr": 4.937179123859625e-05, "epoch": 3.2874220374220373, "percentage": 16.44, "elapsed_time": "0:18:22", "remaining_time": "1:33:24", "throughput": 1033.72, "total_tokens": 1139520} {"current_steps": 12655, "total_steps": 76960, "loss": 0.2074, "lr": 4.937052761072746e-05, "epoch": 3.288721413721414, "percentage": 16.44, "elapsed_time": "0:18:22", "remaining_time": "1:33:23", "throughput": 1033.74, "total_tokens": 1139984} {"current_steps": 12660, "total_steps": 76960, "loss": 0.1612, "lr": 4.936926272945908e-05, "epoch": 3.29002079002079, "percentage": 16.45, "elapsed_time": "0:18:23", "remaining_time": "1:33:23", "throughput": 1033.76, "total_tokens": 1140432} {"current_steps": 12665, "total_steps": 76960, "loss": 0.3134, "lr": 4.936799659485617e-05, "epoch": 3.2913201663201663, "percentage": 16.46, "elapsed_time": "0:18:23", "remaining_time": "1:33:22", "throughput": 1033.79, "total_tokens": 1140896} {"current_steps": 12670, "total_steps": 76960, "loss": 0.2347, "lr": 4.936672920698385e-05, "epoch": 3.2926195426195424, "percentage": 16.46, "elapsed_time": "0:18:24", "remaining_time": "1:33:22", "throughput": 1033.82, "total_tokens": 1141360} {"current_steps": 12675, "total_steps": 76960, "loss": 0.3462, "lr": 4.93654605659073e-05, "epoch": 3.293918918918919, "percentage": 16.47, "elapsed_time": "0:18:24", "remaining_time": "1:33:21", "throughput": 1033.84, "total_tokens": 1141824} {"current_steps": 12680, "total_steps": 76960, "loss": 0.2922, "lr": 4.936419067169177e-05, "epoch": 3.2952182952182953, "percentage": 16.48, "elapsed_time": "0:18:24", "remaining_time": "1:33:20", "throughput": 1033.86, "total_tokens": 1142272} {"current_steps": 12685, "total_steps": 76960, "loss": 0.1798, "lr": 4.936291952440256e-05, "epoch": 3.2965176715176714, "percentage": 16.48, "elapsed_time": "0:18:25", "remaining_time": "1:33:20", "throughput": 1033.9, "total_tokens": 1142752} {"current_steps": 12690, "total_steps": 76960, "loss": 0.2254, "lr": 4.936164712410506e-05, "epoch": 3.297817047817048, "percentage": 16.49, "elapsed_time": "0:18:25", "remaining_time": "1:33:19", "throughput": 1033.92, "total_tokens": 1143200} {"current_steps": 12695, "total_steps": 76960, "loss": 0.323, "lr": 4.936037347086471e-05, "epoch": 3.2991164241164244, "percentage": 16.5, "elapsed_time": "0:18:26", "remaining_time": "1:33:19", "throughput": 1033.9, "total_tokens": 1143616} {"current_steps": 12700, "total_steps": 76960, "loss": 0.3001, "lr": 4.9359098564747e-05, "epoch": 3.3004158004158004, "percentage": 16.5, "elapsed_time": "0:18:26", "remaining_time": "1:33:18", "throughput": 1033.91, "total_tokens": 1144064} {"current_steps": 12705, "total_steps": 76960, "loss": 0.2635, "lr": 4.935782240581752e-05, "epoch": 3.301715176715177, "percentage": 16.51, "elapsed_time": "0:18:26", "remaining_time": "1:33:18", "throughput": 1033.95, "total_tokens": 1144544} {"current_steps": 12710, "total_steps": 76960, "loss": 0.2558, "lr": 4.93565449941419e-05, "epoch": 3.303014553014553, "percentage": 16.52, "elapsed_time": "0:18:27", "remaining_time": "1:33:17", "throughput": 1033.95, "total_tokens": 1144976} {"current_steps": 12715, "total_steps": 76960, "loss": 0.2564, "lr": 4.935526632978582e-05, "epoch": 3.3043139293139294, "percentage": 16.52, "elapsed_time": "0:18:27", "remaining_time": "1:33:17", "throughput": 1033.97, "total_tokens": 1145424} {"current_steps": 12720, "total_steps": 76960, "loss": 0.2352, "lr": 4.935398641281507e-05, "epoch": 3.3056133056133055, "percentage": 16.53, "elapsed_time": "0:18:28", "remaining_time": "1:33:16", "throughput": 1033.95, "total_tokens": 1145840} {"current_steps": 12725, "total_steps": 76960, "loss": 0.2236, "lr": 4.935270524329546e-05, "epoch": 3.306912681912682, "percentage": 16.53, "elapsed_time": "0:18:28", "remaining_time": "1:33:16", "throughput": 1033.93, "total_tokens": 1146256} {"current_steps": 12730, "total_steps": 76960, "loss": 0.3255, "lr": 4.935142282129288e-05, "epoch": 3.3082120582120584, "percentage": 16.54, "elapsed_time": "0:18:29", "remaining_time": "1:33:15", "throughput": 1033.95, "total_tokens": 1146704} {"current_steps": 12735, "total_steps": 76960, "loss": 0.3522, "lr": 4.93501391468733e-05, "epoch": 3.3095114345114345, "percentage": 16.55, "elapsed_time": "0:18:29", "remaining_time": "1:33:15", "throughput": 1033.98, "total_tokens": 1147168} {"current_steps": 12740, "total_steps": 76960, "loss": 0.2614, "lr": 4.934885422010272e-05, "epoch": 3.310810810810811, "percentage": 16.55, "elapsed_time": "0:18:29", "remaining_time": "1:33:14", "throughput": 1033.99, "total_tokens": 1147616} {"current_steps": 12745, "total_steps": 76960, "loss": 0.2327, "lr": 4.934756804104725e-05, "epoch": 3.312110187110187, "percentage": 16.56, "elapsed_time": "0:18:30", "remaining_time": "1:33:14", "throughput": 1034.02, "total_tokens": 1148080} {"current_steps": 12750, "total_steps": 76960, "loss": 0.2288, "lr": 4.934628060977302e-05, "epoch": 3.3134095634095635, "percentage": 16.57, "elapsed_time": "0:18:30", "remaining_time": "1:33:13", "throughput": 1034.01, "total_tokens": 1148512} {"current_steps": 12755, "total_steps": 76960, "loss": 0.2454, "lr": 4.934499192634626e-05, "epoch": 3.3147089397089395, "percentage": 16.57, "elapsed_time": "0:18:31", "remaining_time": "1:33:13", "throughput": 1034.04, "total_tokens": 1148976} {"current_steps": 12760, "total_steps": 76960, "loss": 0.2604, "lr": 4.9343701990833225e-05, "epoch": 3.316008316008316, "percentage": 16.58, "elapsed_time": "0:18:31", "remaining_time": "1:33:12", "throughput": 1034.02, "total_tokens": 1149392} {"current_steps": 12765, "total_steps": 76960, "loss": 0.2836, "lr": 4.934241080330028e-05, "epoch": 3.3173076923076925, "percentage": 16.59, "elapsed_time": "0:18:31", "remaining_time": "1:33:12", "throughput": 1034.05, "total_tokens": 1149856} {"current_steps": 12770, "total_steps": 76960, "loss": 0.213, "lr": 4.934111836381383e-05, "epoch": 3.3186070686070686, "percentage": 16.59, "elapsed_time": "0:18:32", "remaining_time": "1:33:11", "throughput": 1034.03, "total_tokens": 1150272} {"current_steps": 12775, "total_steps": 76960, "loss": 0.1728, "lr": 4.9339824672440325e-05, "epoch": 3.319906444906445, "percentage": 16.6, "elapsed_time": "0:18:32", "remaining_time": "1:33:11", "throughput": 1034.05, "total_tokens": 1150720} {"current_steps": 12780, "total_steps": 76960, "loss": 0.2089, "lr": 4.933852972924633e-05, "epoch": 3.321205821205821, "percentage": 16.61, "elapsed_time": "0:18:33", "remaining_time": "1:33:10", "throughput": 1034.06, "total_tokens": 1151168} {"current_steps": 12785, "total_steps": 76960, "loss": 0.3719, "lr": 4.9337233534298425e-05, "epoch": 3.3225051975051976, "percentage": 16.61, "elapsed_time": "0:18:33", "remaining_time": "1:33:10", "throughput": 1034.07, "total_tokens": 1151616} {"current_steps": 12790, "total_steps": 76960, "loss": 0.2012, "lr": 4.933593608766328e-05, "epoch": 3.3238045738045736, "percentage": 16.62, "elapsed_time": "0:18:34", "remaining_time": "1:33:09", "throughput": 1034.07, "total_tokens": 1152048} {"current_steps": 12795, "total_steps": 76960, "loss": 0.1234, "lr": 4.9334637389407624e-05, "epoch": 3.32510395010395, "percentage": 16.63, "elapsed_time": "0:18:34", "remaining_time": "1:33:09", "throughput": 1034.11, "total_tokens": 1152528} {"current_steps": 12800, "total_steps": 76960, "loss": 0.2634, "lr": 4.9333337439598247e-05, "epoch": 3.3264033264033266, "percentage": 16.63, "elapsed_time": "0:18:34", "remaining_time": "1:33:08", "throughput": 1034.1, "total_tokens": 1152944} {"current_steps": 12805, "total_steps": 76960, "loss": 0.3545, "lr": 4.933203623830201e-05, "epoch": 3.3277027027027026, "percentage": 16.64, "elapsed_time": "0:18:35", "remaining_time": "1:33:08", "throughput": 1034.13, "total_tokens": 1153408} {"current_steps": 12810, "total_steps": 76960, "loss": 0.2128, "lr": 4.9330733785585845e-05, "epoch": 3.329002079002079, "percentage": 16.65, "elapsed_time": "0:18:35", "remaining_time": "1:33:07", "throughput": 1034.13, "total_tokens": 1153840} {"current_steps": 12815, "total_steps": 76960, "loss": 0.2948, "lr": 4.932943008151673e-05, "epoch": 3.330301455301455, "percentage": 16.65, "elapsed_time": "0:18:36", "remaining_time": "1:33:07", "throughput": 1034.15, "total_tokens": 1154304} {"current_steps": 12820, "total_steps": 76960, "loss": 0.2805, "lr": 4.93281251261617e-05, "epoch": 3.3316008316008316, "percentage": 16.66, "elapsed_time": "0:18:36", "remaining_time": "1:33:06", "throughput": 1034.12, "total_tokens": 1154704} {"current_steps": 12825, "total_steps": 76960, "loss": 0.2463, "lr": 4.932681891958789e-05, "epoch": 3.3329002079002077, "percentage": 16.66, "elapsed_time": "0:18:37", "remaining_time": "1:33:05", "throughput": 1034.13, "total_tokens": 1155152} {"current_steps": 12830, "total_steps": 76960, "loss": 0.2982, "lr": 4.9325511461862486e-05, "epoch": 3.334199584199584, "percentage": 16.67, "elapsed_time": "0:18:37", "remaining_time": "1:33:05", "throughput": 1034.13, "total_tokens": 1155584} {"current_steps": 12835, "total_steps": 76960, "loss": 0.2918, "lr": 4.932420275305271e-05, "epoch": 3.3354989604989607, "percentage": 16.68, "elapsed_time": "0:18:37", "remaining_time": "1:33:04", "throughput": 1034.18, "total_tokens": 1156064} {"current_steps": 12840, "total_steps": 76960, "loss": 0.2639, "lr": 4.932289279322588e-05, "epoch": 3.3367983367983367, "percentage": 16.68, "elapsed_time": "0:18:38", "remaining_time": "1:33:04", "throughput": 1034.23, "total_tokens": 1156560} {"current_steps": 12845, "total_steps": 76960, "loss": 0.237, "lr": 4.9321581582449365e-05, "epoch": 3.338097713097713, "percentage": 16.69, "elapsed_time": "0:18:38", "remaining_time": "1:33:03", "throughput": 1034.26, "total_tokens": 1157024} {"current_steps": 12850, "total_steps": 76960, "loss": 0.2862, "lr": 4.9320269120790616e-05, "epoch": 3.3393970893970892, "percentage": 16.7, "elapsed_time": "0:18:39", "remaining_time": "1:33:03", "throughput": 1034.29, "total_tokens": 1157488} {"current_steps": 12855, "total_steps": 76960, "loss": 0.2704, "lr": 4.9318955408317115e-05, "epoch": 3.3406964656964657, "percentage": 16.7, "elapsed_time": "0:18:39", "remaining_time": "1:33:02", "throughput": 1034.32, "total_tokens": 1157952} {"current_steps": 12860, "total_steps": 76960, "loss": 0.2816, "lr": 4.931764044509643e-05, "epoch": 3.3419958419958418, "percentage": 16.71, "elapsed_time": "0:18:39", "remaining_time": "1:33:02", "throughput": 1034.33, "total_tokens": 1158400} {"current_steps": 12865, "total_steps": 76960, "loss": 0.2153, "lr": 4.931632423119621e-05, "epoch": 3.3432952182952183, "percentage": 16.72, "elapsed_time": "0:18:40", "remaining_time": "1:33:01", "throughput": 1034.35, "total_tokens": 1158848} {"current_steps": 12870, "total_steps": 76960, "loss": 0.2172, "lr": 4.9315006766684135e-05, "epoch": 3.3445945945945947, "percentage": 16.72, "elapsed_time": "0:18:40", "remaining_time": "1:33:01", "throughput": 1034.35, "total_tokens": 1159280} {"current_steps": 12875, "total_steps": 76960, "loss": 0.2194, "lr": 4.931368805162796e-05, "epoch": 3.345893970893971, "percentage": 16.73, "elapsed_time": "0:18:41", "remaining_time": "1:33:00", "throughput": 1034.36, "total_tokens": 1159728} {"current_steps": 12880, "total_steps": 76960, "loss": 0.1555, "lr": 4.931236808609552e-05, "epoch": 3.3471933471933473, "percentage": 16.74, "elapsed_time": "0:18:41", "remaining_time": "1:33:00", "throughput": 1034.34, "total_tokens": 1160144} {"current_steps": 12885, "total_steps": 76960, "loss": 0.3162, "lr": 4.931104687015468e-05, "epoch": 3.3484927234927233, "percentage": 16.74, "elapsed_time": "0:18:42", "remaining_time": "1:32:59", "throughput": 1034.39, "total_tokens": 1160624} {"current_steps": 12890, "total_steps": 76960, "loss": 0.2111, "lr": 4.930972440387341e-05, "epoch": 3.3497920997921, "percentage": 16.75, "elapsed_time": "0:18:42", "remaining_time": "1:32:59", "throughput": 1034.39, "total_tokens": 1161056} {"current_steps": 12895, "total_steps": 76960, "loss": 0.3191, "lr": 4.930840068731973e-05, "epoch": 3.3510914760914763, "percentage": 16.76, "elapsed_time": "0:18:42", "remaining_time": "1:32:58", "throughput": 1034.43, "total_tokens": 1161536} {"current_steps": 12900, "total_steps": 76960, "loss": 0.2724, "lr": 4.9307075720561705e-05, "epoch": 3.3523908523908523, "percentage": 16.76, "elapsed_time": "0:18:43", "remaining_time": "1:32:58", "throughput": 1034.45, "total_tokens": 1162000} {"current_steps": 12905, "total_steps": 76960, "loss": 0.227, "lr": 4.930574950366749e-05, "epoch": 3.353690228690229, "percentage": 16.77, "elapsed_time": "0:18:43", "remaining_time": "1:32:57", "throughput": 1034.45, "total_tokens": 1162432} {"current_steps": 12910, "total_steps": 76960, "loss": 0.2509, "lr": 4.930442203670529e-05, "epoch": 3.354989604989605, "percentage": 16.77, "elapsed_time": "0:18:44", "remaining_time": "1:32:57", "throughput": 1034.49, "total_tokens": 1162912} {"current_steps": 12915, "total_steps": 76960, "loss": 0.2569, "lr": 4.9303093319743364e-05, "epoch": 3.3562889812889813, "percentage": 16.78, "elapsed_time": "0:18:44", "remaining_time": "1:32:56", "throughput": 1034.49, "total_tokens": 1163344} {"current_steps": 12920, "total_steps": 76960, "loss": 0.3177, "lr": 4.9301763352850075e-05, "epoch": 3.357588357588358, "percentage": 16.79, "elapsed_time": "0:18:44", "remaining_time": "1:32:56", "throughput": 1034.5, "total_tokens": 1163792} {"current_steps": 12925, "total_steps": 76960, "loss": 0.2537, "lr": 4.930043213609381e-05, "epoch": 3.358887733887734, "percentage": 16.79, "elapsed_time": "0:18:45", "remaining_time": "1:32:55", "throughput": 1034.5, "total_tokens": 1164224} {"current_steps": 12930, "total_steps": 76960, "loss": 0.2313, "lr": 4.9299099669543035e-05, "epoch": 3.3601871101871104, "percentage": 16.8, "elapsed_time": "0:18:45", "remaining_time": "1:32:55", "throughput": 1034.48, "total_tokens": 1164640} {"current_steps": 12935, "total_steps": 76960, "loss": 0.2896, "lr": 4.9297765953266287e-05, "epoch": 3.3614864864864864, "percentage": 16.81, "elapsed_time": "0:18:46", "remaining_time": "1:32:54", "throughput": 1034.51, "total_tokens": 1165104} {"current_steps": 12940, "total_steps": 76960, "loss": 0.1805, "lr": 4.929643098733215e-05, "epoch": 3.362785862785863, "percentage": 16.81, "elapsed_time": "0:18:46", "remaining_time": "1:32:54", "throughput": 1034.54, "total_tokens": 1165568} {"current_steps": 12945, "total_steps": 76960, "loss": 0.246, "lr": 4.9295094771809285e-05, "epoch": 3.364085239085239, "percentage": 16.82, "elapsed_time": "0:18:47", "remaining_time": "1:32:53", "throughput": 1034.54, "total_tokens": 1166000} {"current_steps": 12950, "total_steps": 76960, "loss": 0.333, "lr": 4.929375730676642e-05, "epoch": 3.3653846153846154, "percentage": 16.83, "elapsed_time": "0:18:47", "remaining_time": "1:32:53", "throughput": 1034.53, "total_tokens": 1166432} {"current_steps": 12955, "total_steps": 76960, "loss": 0.2042, "lr": 4.9292418592272344e-05, "epoch": 3.366683991683992, "percentage": 16.83, "elapsed_time": "0:18:47", "remaining_time": "1:32:52", "throughput": 1034.53, "total_tokens": 1166864} {"current_steps": 12960, "total_steps": 76960, "loss": 0.2737, "lr": 4.92910786283959e-05, "epoch": 3.367983367983368, "percentage": 16.84, "elapsed_time": "0:18:48", "remaining_time": "1:32:52", "throughput": 1034.56, "total_tokens": 1167328} {"current_steps": 12965, "total_steps": 76960, "loss": 0.3122, "lr": 4.928973741520601e-05, "epoch": 3.3692827442827444, "percentage": 16.85, "elapsed_time": "0:18:48", "remaining_time": "1:32:51", "throughput": 1034.56, "total_tokens": 1167760} {"current_steps": 12970, "total_steps": 76960, "loss": 0.2614, "lr": 4.9288394952771645e-05, "epoch": 3.3705821205821205, "percentage": 16.85, "elapsed_time": "0:18:49", "remaining_time": "1:32:50", "throughput": 1034.56, "total_tokens": 1168192} {"current_steps": 12975, "total_steps": 76960, "loss": 0.2319, "lr": 4.9287051241161865e-05, "epoch": 3.371881496881497, "percentage": 16.86, "elapsed_time": "0:18:49", "remaining_time": "1:32:50", "throughput": 1034.6, "total_tokens": 1168672} {"current_steps": 12980, "total_steps": 76960, "loss": 0.2582, "lr": 4.9285706280445756e-05, "epoch": 3.373180873180873, "percentage": 16.87, "elapsed_time": "0:18:50", "remaining_time": "1:32:49", "throughput": 1034.58, "total_tokens": 1169088} {"current_steps": 12985, "total_steps": 76960, "loss": 0.2299, "lr": 4.928436007069251e-05, "epoch": 3.3744802494802495, "percentage": 16.87, "elapsed_time": "0:18:50", "remaining_time": "1:32:49", "throughput": 1034.6, "total_tokens": 1169536} {"current_steps": 12990, "total_steps": 76960, "loss": 4.2041, "lr": 4.9283012611971365e-05, "epoch": 3.375779625779626, "percentage": 16.88, "elapsed_time": "0:18:50", "remaining_time": "1:32:48", "throughput": 1034.62, "total_tokens": 1170000} {"current_steps": 12995, "total_steps": 76960, "loss": 0.3513, "lr": 4.9281663904351604e-05, "epoch": 3.377079002079002, "percentage": 16.89, "elapsed_time": "0:18:51", "remaining_time": "1:32:48", "throughput": 1034.61, "total_tokens": 1170416} {"current_steps": 13000, "total_steps": 76960, "loss": 0.3522, "lr": 4.928031394790261e-05, "epoch": 3.3783783783783785, "percentage": 16.89, "elapsed_time": "0:18:51", "remaining_time": "1:32:47", "throughput": 1034.59, "total_tokens": 1170832} {"current_steps": 13005, "total_steps": 76960, "loss": 0.2465, "lr": 4.92789627426938e-05, "epoch": 3.3796777546777546, "percentage": 16.9, "elapsed_time": "0:18:52", "remaining_time": "1:32:47", "throughput": 1034.61, "total_tokens": 1171280} {"current_steps": 13010, "total_steps": 76960, "loss": 0.1622, "lr": 4.9277610288794675e-05, "epoch": 3.380977130977131, "percentage": 16.9, "elapsed_time": "0:18:52", "remaining_time": "1:32:46", "throughput": 1034.6, "total_tokens": 1171712} {"current_steps": 13015, "total_steps": 76960, "loss": 0.4014, "lr": 4.92762565862748e-05, "epoch": 3.382276507276507, "percentage": 16.91, "elapsed_time": "0:18:52", "remaining_time": "1:32:46", "throughput": 1034.62, "total_tokens": 1172160} {"current_steps": 13020, "total_steps": 76960, "loss": 0.3128, "lr": 4.927490163520377e-05, "epoch": 3.3835758835758836, "percentage": 16.92, "elapsed_time": "0:18:53", "remaining_time": "1:32:45", "throughput": 1034.66, "total_tokens": 1172640} {"current_steps": 13025, "total_steps": 76960, "loss": 0.5311, "lr": 4.92735454356513e-05, "epoch": 3.38487525987526, "percentage": 16.92, "elapsed_time": "0:18:53", "remaining_time": "1:32:45", "throughput": 1034.66, "total_tokens": 1173072} {"current_steps": 13030, "total_steps": 76960, "loss": 0.2446, "lr": 4.9272187987687136e-05, "epoch": 3.386174636174636, "percentage": 16.93, "elapsed_time": "0:18:54", "remaining_time": "1:32:44", "throughput": 1034.69, "total_tokens": 1173536} {"current_steps": 13035, "total_steps": 76960, "loss": 0.226, "lr": 4.9270829291381084e-05, "epoch": 3.3874740124740126, "percentage": 16.94, "elapsed_time": "0:18:54", "remaining_time": "1:32:44", "throughput": 1034.71, "total_tokens": 1174000} {"current_steps": 13040, "total_steps": 76960, "loss": 0.208, "lr": 4.926946934680302e-05, "epoch": 3.3887733887733886, "percentage": 16.94, "elapsed_time": "0:18:55", "remaining_time": "1:32:43", "throughput": 1034.71, "total_tokens": 1174432} {"current_steps": 13045, "total_steps": 76960, "loss": 0.2775, "lr": 4.92681081540229e-05, "epoch": 3.390072765072765, "percentage": 16.95, "elapsed_time": "0:18:55", "remaining_time": "1:32:43", "throughput": 1034.74, "total_tokens": 1174896} {"current_steps": 13050, "total_steps": 76960, "loss": 0.2728, "lr": 4.926674571311072e-05, "epoch": 3.391372141372141, "percentage": 16.96, "elapsed_time": "0:18:55", "remaining_time": "1:32:42", "throughput": 1034.79, "total_tokens": 1175392} {"current_steps": 13055, "total_steps": 76960, "loss": 0.2178, "lr": 4.926538202413656e-05, "epoch": 3.3926715176715176, "percentage": 16.96, "elapsed_time": "0:18:56", "remaining_time": "1:32:42", "throughput": 1034.81, "total_tokens": 1175840} {"current_steps": 13060, "total_steps": 76960, "loss": 0.1601, "lr": 4.926401708717055e-05, "epoch": 3.393970893970894, "percentage": 16.97, "elapsed_time": "0:18:56", "remaining_time": "1:32:41", "throughput": 1034.81, "total_tokens": 1176272} {"current_steps": 13065, "total_steps": 76960, "loss": 0.2726, "lr": 4.926265090228289e-05, "epoch": 3.39527027027027, "percentage": 16.98, "elapsed_time": "0:18:57", "remaining_time": "1:32:41", "throughput": 1034.81, "total_tokens": 1176704} {"current_steps": 13070, "total_steps": 76960, "loss": 0.1971, "lr": 4.926128346954385e-05, "epoch": 3.3965696465696467, "percentage": 16.98, "elapsed_time": "0:18:57", "remaining_time": "1:32:40", "throughput": 1034.83, "total_tokens": 1177168} {"current_steps": 13075, "total_steps": 76960, "loss": 0.25, "lr": 4.9259914789023764e-05, "epoch": 3.3978690228690227, "percentage": 16.99, "elapsed_time": "0:18:57", "remaining_time": "1:32:40", "throughput": 1034.85, "total_tokens": 1177616} {"current_steps": 13080, "total_steps": 76960, "loss": 0.2627, "lr": 4.925854486079301e-05, "epoch": 3.399168399168399, "percentage": 17.0, "elapsed_time": "0:18:58", "remaining_time": "1:32:39", "throughput": 1034.9, "total_tokens": 1178112} {"current_steps": 13085, "total_steps": 76960, "loss": 0.266, "lr": 4.925717368492204e-05, "epoch": 3.4004677754677752, "percentage": 17.0, "elapsed_time": "0:18:58", "remaining_time": "1:32:39", "throughput": 1034.9, "total_tokens": 1178544} {"current_steps": 13090, "total_steps": 76960, "loss": 0.2463, "lr": 4.92558012614814e-05, "epoch": 3.4017671517671517, "percentage": 17.01, "elapsed_time": "0:18:59", "remaining_time": "1:32:38", "throughput": 1034.93, "total_tokens": 1179008} {"current_steps": 13095, "total_steps": 76960, "loss": 0.3055, "lr": 4.9254427590541655e-05, "epoch": 3.403066528066528, "percentage": 17.02, "elapsed_time": "0:18:59", "remaining_time": "1:32:38", "throughput": 1034.95, "total_tokens": 1179472} {"current_steps": 13100, "total_steps": 76960, "loss": 0.2524, "lr": 4.925305267217346e-05, "epoch": 3.4043659043659042, "percentage": 17.02, "elapsed_time": "0:19:00", "remaining_time": "1:32:37", "throughput": 1034.99, "total_tokens": 1179952} {"current_steps": 13105, "total_steps": 76960, "loss": 0.2389, "lr": 4.925167650644752e-05, "epoch": 3.4056652806652807, "percentage": 17.03, "elapsed_time": "0:19:00", "remaining_time": "1:32:37", "throughput": 1035.08, "total_tokens": 1180480} {"current_steps": 13110, "total_steps": 76960, "loss": 0.1831, "lr": 4.925029909343463e-05, "epoch": 3.406964656964657, "percentage": 17.03, "elapsed_time": "0:19:00", "remaining_time": "1:32:36", "throughput": 1035.08, "total_tokens": 1180928} {"current_steps": 13115, "total_steps": 76960, "loss": 0.3422, "lr": 4.924892043320561e-05, "epoch": 3.4082640332640333, "percentage": 17.04, "elapsed_time": "0:19:01", "remaining_time": "1:32:36", "throughput": 1035.11, "total_tokens": 1181392} {"current_steps": 13120, "total_steps": 76960, "loss": 0.2201, "lr": 4.9247540525831394e-05, "epoch": 3.4095634095634098, "percentage": 17.05, "elapsed_time": "0:19:01", "remaining_time": "1:32:35", "throughput": 1035.12, "total_tokens": 1181840} {"current_steps": 13125, "total_steps": 76960, "loss": 0.26, "lr": 4.924615937138293e-05, "epoch": 3.410862785862786, "percentage": 17.05, "elapsed_time": "0:19:02", "remaining_time": "1:32:35", "throughput": 1035.15, "total_tokens": 1182304} {"current_steps": 13130, "total_steps": 76960, "loss": 0.2561, "lr": 4.9244776969931256e-05, "epoch": 3.4121621621621623, "percentage": 17.06, "elapsed_time": "0:19:02", "remaining_time": "1:32:34", "throughput": 1035.19, "total_tokens": 1182784} {"current_steps": 13135, "total_steps": 76960, "loss": 0.3454, "lr": 4.9243393321547474e-05, "epoch": 3.4134615384615383, "percentage": 17.07, "elapsed_time": "0:19:02", "remaining_time": "1:32:33", "throughput": 1035.23, "total_tokens": 1183264} {"current_steps": 13140, "total_steps": 76960, "loss": 0.2362, "lr": 4.924200842630275e-05, "epoch": 3.414760914760915, "percentage": 17.07, "elapsed_time": "0:19:03", "remaining_time": "1:32:33", "throughput": 1035.26, "total_tokens": 1183728} {"current_steps": 13145, "total_steps": 76960, "loss": 0.2934, "lr": 4.9240622284268287e-05, "epoch": 3.4160602910602913, "percentage": 17.08, "elapsed_time": "0:19:03", "remaining_time": "1:32:32", "throughput": 1035.27, "total_tokens": 1184176} {"current_steps": 13150, "total_steps": 76960, "loss": 0.2527, "lr": 4.9239234895515406e-05, "epoch": 3.4173596673596673, "percentage": 17.09, "elapsed_time": "0:19:04", "remaining_time": "1:32:32", "throughput": 1035.28, "total_tokens": 1184624} {"current_steps": 13155, "total_steps": 76960, "loss": 0.2113, "lr": 4.923784626011545e-05, "epoch": 3.418659043659044, "percentage": 17.09, "elapsed_time": "0:19:04", "remaining_time": "1:32:31", "throughput": 1035.28, "total_tokens": 1185056} {"current_steps": 13160, "total_steps": 76960, "loss": 0.1748, "lr": 4.9236456378139836e-05, "epoch": 3.41995841995842, "percentage": 17.1, "elapsed_time": "0:19:05", "remaining_time": "1:32:31", "throughput": 1035.27, "total_tokens": 1185472} {"current_steps": 13165, "total_steps": 76960, "loss": 0.2067, "lr": 4.923506524966005e-05, "epoch": 3.4212577962577964, "percentage": 17.11, "elapsed_time": "0:19:05", "remaining_time": "1:32:30", "throughput": 1035.25, "total_tokens": 1185888} {"current_steps": 13170, "total_steps": 76960, "loss": 0.4042, "lr": 4.923367287474764e-05, "epoch": 3.4225571725571724, "percentage": 17.11, "elapsed_time": "0:19:05", "remaining_time": "1:32:30", "throughput": 1035.28, "total_tokens": 1186352} {"current_steps": 13175, "total_steps": 76960, "loss": 0.2504, "lr": 4.9232279253474205e-05, "epoch": 3.423856548856549, "percentage": 17.12, "elapsed_time": "0:19:06", "remaining_time": "1:32:29", "throughput": 1035.27, "total_tokens": 1186784} {"current_steps": 13180, "total_steps": 76960, "loss": 0.3515, "lr": 4.9230884385911436e-05, "epoch": 3.4251559251559254, "percentage": 17.13, "elapsed_time": "0:19:06", "remaining_time": "1:32:29", "throughput": 1035.3, "total_tokens": 1187248} {"current_steps": 13185, "total_steps": 76960, "loss": 0.3831, "lr": 4.9229488272131067e-05, "epoch": 3.4264553014553014, "percentage": 17.13, "elapsed_time": "0:19:07", "remaining_time": "1:32:28", "throughput": 1035.33, "total_tokens": 1187712} {"current_steps": 13190, "total_steps": 76960, "loss": 0.2877, "lr": 4.922809091220489e-05, "epoch": 3.427754677754678, "percentage": 17.14, "elapsed_time": "0:19:07", "remaining_time": "1:32:28", "throughput": 1035.37, "total_tokens": 1188192} {"current_steps": 13195, "total_steps": 76960, "loss": 0.2158, "lr": 4.9226692306204795e-05, "epoch": 3.429054054054054, "percentage": 17.15, "elapsed_time": "0:19:08", "remaining_time": "1:32:27", "throughput": 1035.38, "total_tokens": 1188640} {"current_steps": 13200, "total_steps": 76960, "loss": 0.4155, "lr": 4.92252924542027e-05, "epoch": 3.4303534303534304, "percentage": 17.15, "elapsed_time": "0:19:08", "remaining_time": "1:32:27", "throughput": 1035.38, "total_tokens": 1189072} {"current_steps": 13205, "total_steps": 76960, "loss": 0.4508, "lr": 4.92238913562706e-05, "epoch": 3.4316528066528065, "percentage": 17.16, "elapsed_time": "0:19:08", "remaining_time": "1:32:26", "throughput": 1035.38, "total_tokens": 1189504} {"current_steps": 13210, "total_steps": 76960, "loss": 0.448, "lr": 4.922248901248056e-05, "epoch": 3.432952182952183, "percentage": 17.16, "elapsed_time": "0:19:09", "remaining_time": "1:32:26", "throughput": 1035.41, "total_tokens": 1189968} {"current_steps": 13215, "total_steps": 76960, "loss": 0.3266, "lr": 4.92210854229047e-05, "epoch": 3.4342515592515594, "percentage": 17.17, "elapsed_time": "0:19:09", "remaining_time": "1:32:25", "throughput": 1035.45, "total_tokens": 1190448} {"current_steps": 13220, "total_steps": 76960, "loss": 0.2409, "lr": 4.921968058761521e-05, "epoch": 3.4355509355509355, "percentage": 17.18, "elapsed_time": "0:19:10", "remaining_time": "1:32:25", "throughput": 1035.48, "total_tokens": 1190912} {"current_steps": 13225, "total_steps": 76960, "loss": 0.3289, "lr": 4.921827450668434e-05, "epoch": 3.436850311850312, "percentage": 17.18, "elapsed_time": "0:19:10", "remaining_time": "1:32:24", "throughput": 1035.45, "total_tokens": 1191312} {"current_steps": 13230, "total_steps": 76960, "loss": 0.2078, "lr": 4.92168671801844e-05, "epoch": 3.438149688149688, "percentage": 17.19, "elapsed_time": "0:19:10", "remaining_time": "1:32:24", "throughput": 1035.47, "total_tokens": 1191776} {"current_steps": 13235, "total_steps": 76960, "loss": 0.2127, "lr": 4.921545860818779e-05, "epoch": 3.4394490644490645, "percentage": 17.2, "elapsed_time": "0:19:11", "remaining_time": "1:32:23", "throughput": 1035.48, "total_tokens": 1192224} {"current_steps": 13240, "total_steps": 76960, "loss": 0.2168, "lr": 4.921404879076693e-05, "epoch": 3.4407484407484406, "percentage": 17.2, "elapsed_time": "0:19:11", "remaining_time": "1:32:23", "throughput": 1035.5, "total_tokens": 1192672} {"current_steps": 13245, "total_steps": 76960, "loss": 0.3331, "lr": 4.921263772799435e-05, "epoch": 3.442047817047817, "percentage": 17.21, "elapsed_time": "0:19:12", "remaining_time": "1:32:22", "throughput": 1035.54, "total_tokens": 1193152} {"current_steps": 13250, "total_steps": 76960, "loss": 0.2115, "lr": 4.921122541994261e-05, "epoch": 3.4433471933471935, "percentage": 17.22, "elapsed_time": "0:19:12", "remaining_time": "1:32:22", "throughput": 1035.55, "total_tokens": 1193600} {"current_steps": 13255, "total_steps": 76960, "loss": 0.3222, "lr": 4.920981186668435e-05, "epoch": 3.4446465696465696, "percentage": 17.22, "elapsed_time": "0:19:13", "remaining_time": "1:32:21", "throughput": 1035.56, "total_tokens": 1194048} {"current_steps": 13260, "total_steps": 76960, "loss": 0.2255, "lr": 4.920839706829226e-05, "epoch": 3.445945945945946, "percentage": 17.23, "elapsed_time": "0:19:13", "remaining_time": "1:32:21", "throughput": 1035.59, "total_tokens": 1194512} {"current_steps": 13265, "total_steps": 76960, "loss": 0.2063, "lr": 4.920698102483912e-05, "epoch": 3.447245322245322, "percentage": 17.24, "elapsed_time": "0:19:13", "remaining_time": "1:32:20", "throughput": 1035.59, "total_tokens": 1194944} {"current_steps": 13270, "total_steps": 76960, "loss": 0.3014, "lr": 4.920556373639775e-05, "epoch": 3.4485446985446986, "percentage": 17.24, "elapsed_time": "0:19:14", "remaining_time": "1:32:20", "throughput": 1035.61, "total_tokens": 1195408} {"current_steps": 13275, "total_steps": 76960, "loss": 0.3674, "lr": 4.920414520304105e-05, "epoch": 3.4498440748440746, "percentage": 17.25, "elapsed_time": "0:19:14", "remaining_time": "1:32:19", "throughput": 1035.61, "total_tokens": 1195840} {"current_steps": 13280, "total_steps": 76960, "loss": 0.2356, "lr": 4.920272542484197e-05, "epoch": 3.451143451143451, "percentage": 17.26, "elapsed_time": "0:19:15", "remaining_time": "1:32:19", "throughput": 1035.61, "total_tokens": 1196272} {"current_steps": 13285, "total_steps": 76960, "loss": 0.2744, "lr": 4.920130440187352e-05, "epoch": 3.4524428274428276, "percentage": 17.26, "elapsed_time": "0:19:15", "remaining_time": "1:32:18", "throughput": 1035.6, "total_tokens": 1196704} {"current_steps": 13290, "total_steps": 76960, "loss": 0.2563, "lr": 4.919988213420881e-05, "epoch": 3.4537422037422036, "percentage": 17.27, "elapsed_time": "0:19:15", "remaining_time": "1:32:18", "throughput": 1035.63, "total_tokens": 1197168} {"current_steps": 13295, "total_steps": 76960, "loss": 0.1817, "lr": 4.919845862192096e-05, "epoch": 3.45504158004158, "percentage": 17.28, "elapsed_time": "0:19:16", "remaining_time": "1:32:17", "throughput": 1035.64, "total_tokens": 1197616} {"current_steps": 13300, "total_steps": 76960, "loss": 0.1697, "lr": 4.9197033865083206e-05, "epoch": 3.456340956340956, "percentage": 17.28, "elapsed_time": "0:19:16", "remaining_time": "1:32:17", "throughput": 1035.65, "total_tokens": 1198064} {"current_steps": 13305, "total_steps": 76960, "loss": 0.2221, "lr": 4.919560786376882e-05, "epoch": 3.4576403326403327, "percentage": 17.29, "elapsed_time": "0:19:17", "remaining_time": "1:32:16", "throughput": 1035.65, "total_tokens": 1198496} {"current_steps": 13310, "total_steps": 76960, "loss": 0.2221, "lr": 4.919418061805113e-05, "epoch": 3.4589397089397087, "percentage": 17.29, "elapsed_time": "0:19:17", "remaining_time": "1:32:16", "throughput": 1035.65, "total_tokens": 1198928} {"current_steps": 13315, "total_steps": 76960, "loss": 0.2283, "lr": 4.9192752128003554e-05, "epoch": 3.460239085239085, "percentage": 17.3, "elapsed_time": "0:19:18", "remaining_time": "1:32:15", "throughput": 1035.66, "total_tokens": 1199376} {"current_steps": 13320, "total_steps": 76960, "loss": 0.4857, "lr": 4.9191322393699557e-05, "epoch": 3.4615384615384617, "percentage": 17.31, "elapsed_time": "0:19:18", "remaining_time": "1:32:15", "throughput": 1035.68, "total_tokens": 1199824} {"current_steps": 13325, "total_steps": 76960, "loss": 0.3225, "lr": 4.918989141521267e-05, "epoch": 3.4628378378378377, "percentage": 17.31, "elapsed_time": "0:19:18", "remaining_time": "1:32:14", "throughput": 1035.7, "total_tokens": 1200288} {"current_steps": 13330, "total_steps": 76960, "loss": 0.2513, "lr": 4.9188459192616484e-05, "epoch": 3.464137214137214, "percentage": 17.32, "elapsed_time": "0:19:19", "remaining_time": "1:32:13", "throughput": 1035.72, "total_tokens": 1200736} {"current_steps": 13335, "total_steps": 76960, "loss": 0.2495, "lr": 4.918702572598467e-05, "epoch": 3.4654365904365902, "percentage": 17.33, "elapsed_time": "0:19:19", "remaining_time": "1:32:13", "throughput": 1035.69, "total_tokens": 1201136} {"current_steps": 13340, "total_steps": 76960, "loss": 0.2289, "lr": 4.9185591015390955e-05, "epoch": 3.4667359667359667, "percentage": 17.33, "elapsed_time": "0:19:20", "remaining_time": "1:32:12", "throughput": 1035.7, "total_tokens": 1201584} {"current_steps": 13345, "total_steps": 76960, "loss": 0.1586, "lr": 4.918415506090911e-05, "epoch": 3.468035343035343, "percentage": 17.34, "elapsed_time": "0:19:20", "remaining_time": "1:32:12", "throughput": 1035.7, "total_tokens": 1202016} {"current_steps": 13350, "total_steps": 76960, "loss": 0.2854, "lr": 4.9182717862613e-05, "epoch": 3.4693347193347193, "percentage": 17.35, "elapsed_time": "0:19:21", "remaining_time": "1:32:11", "throughput": 1035.73, "total_tokens": 1202480} {"current_steps": 13355, "total_steps": 76960, "loss": 0.2787, "lr": 4.918127942057654e-05, "epoch": 3.4706340956340958, "percentage": 17.35, "elapsed_time": "0:19:21", "remaining_time": "1:32:11", "throughput": 1035.73, "total_tokens": 1202912} {"current_steps": 13360, "total_steps": 76960, "loss": 0.3391, "lr": 4.917983973487371e-05, "epoch": 3.471933471933472, "percentage": 17.36, "elapsed_time": "0:19:21", "remaining_time": "1:32:10", "throughput": 1035.74, "total_tokens": 1203360} {"current_steps": 13365, "total_steps": 76960, "loss": 0.3033, "lr": 4.917839880557855e-05, "epoch": 3.4732328482328483, "percentage": 17.37, "elapsed_time": "0:19:22", "remaining_time": "1:32:10", "throughput": 1035.75, "total_tokens": 1203808} {"current_steps": 13370, "total_steps": 76960, "loss": 0.2704, "lr": 4.917695663276518e-05, "epoch": 3.4745322245322248, "percentage": 17.37, "elapsed_time": "0:19:22", "remaining_time": "1:32:09", "throughput": 1035.75, "total_tokens": 1204240} {"current_steps": 13375, "total_steps": 76960, "loss": 0.235, "lr": 4.917551321650776e-05, "epoch": 3.475831600831601, "percentage": 17.38, "elapsed_time": "0:19:23", "remaining_time": "1:32:09", "throughput": 1035.72, "total_tokens": 1204640} {"current_steps": 13380, "total_steps": 76960, "loss": 0.3419, "lr": 4.917406855688054e-05, "epoch": 3.4771309771309773, "percentage": 17.39, "elapsed_time": "0:19:23", "remaining_time": "1:32:08", "throughput": 1035.71, "total_tokens": 1205056} {"current_steps": 13385, "total_steps": 76960, "loss": 0.1732, "lr": 4.917262265395781e-05, "epoch": 3.4784303534303533, "percentage": 17.39, "elapsed_time": "0:19:23", "remaining_time": "1:32:08", "throughput": 1035.72, "total_tokens": 1205504} {"current_steps": 13390, "total_steps": 76960, "loss": 0.3043, "lr": 4.9171175507813924e-05, "epoch": 3.47972972972973, "percentage": 17.4, "elapsed_time": "0:19:24", "remaining_time": "1:32:07", "throughput": 1035.72, "total_tokens": 1205936} {"current_steps": 13395, "total_steps": 76960, "loss": 0.3398, "lr": 4.916972711852333e-05, "epoch": 3.481029106029106, "percentage": 17.41, "elapsed_time": "0:19:24", "remaining_time": "1:32:07", "throughput": 1035.72, "total_tokens": 1206368} {"current_steps": 13400, "total_steps": 76960, "loss": 0.2656, "lr": 4.916827748616052e-05, "epoch": 3.4823284823284824, "percentage": 17.41, "elapsed_time": "0:19:25", "remaining_time": "1:32:06", "throughput": 1035.73, "total_tokens": 1206816} {"current_steps": 13405, "total_steps": 76960, "loss": 0.278, "lr": 4.9166826610800035e-05, "epoch": 3.483627858627859, "percentage": 17.42, "elapsed_time": "0:19:25", "remaining_time": "1:32:06", "throughput": 1035.73, "total_tokens": 1207248} {"current_steps": 13410, "total_steps": 76960, "loss": 0.2535, "lr": 4.916537449251649e-05, "epoch": 3.484927234927235, "percentage": 17.42, "elapsed_time": "0:19:26", "remaining_time": "1:32:05", "throughput": 1035.75, "total_tokens": 1207712} {"current_steps": 13415, "total_steps": 76960, "loss": 0.2956, "lr": 4.916392113138459e-05, "epoch": 3.4862266112266114, "percentage": 17.43, "elapsed_time": "0:19:26", "remaining_time": "1:32:05", "throughput": 1035.78, "total_tokens": 1208176} {"current_steps": 13420, "total_steps": 76960, "loss": 0.3278, "lr": 4.916246652747908e-05, "epoch": 3.4875259875259874, "percentage": 17.44, "elapsed_time": "0:19:26", "remaining_time": "1:32:04", "throughput": 1035.84, "total_tokens": 1208672} {"current_steps": 13425, "total_steps": 76960, "loss": 0.2833, "lr": 4.916101068087476e-05, "epoch": 3.488825363825364, "percentage": 17.44, "elapsed_time": "0:19:27", "remaining_time": "1:32:04", "throughput": 1035.83, "total_tokens": 1209104} {"current_steps": 13430, "total_steps": 76960, "loss": 0.2997, "lr": 4.915955359164651e-05, "epoch": 3.49012474012474, "percentage": 17.45, "elapsed_time": "0:19:27", "remaining_time": "1:32:03", "throughput": 1035.82, "total_tokens": 1209520} {"current_steps": 13435, "total_steps": 76960, "loss": 0.2878, "lr": 4.9158095259869274e-05, "epoch": 3.4914241164241164, "percentage": 17.46, "elapsed_time": "0:19:28", "remaining_time": "1:32:03", "throughput": 1035.83, "total_tokens": 1209968} {"current_steps": 13440, "total_steps": 76960, "loss": 0.2346, "lr": 4.9156635685618045e-05, "epoch": 3.492723492723493, "percentage": 17.46, "elapsed_time": "0:19:28", "remaining_time": "1:32:02", "throughput": 1035.83, "total_tokens": 1210400} {"current_steps": 13445, "total_steps": 76960, "loss": 0.3044, "lr": 4.9155174868967904e-05, "epoch": 3.494022869022869, "percentage": 17.47, "elapsed_time": "0:19:28", "remaining_time": "1:32:02", "throughput": 1035.87, "total_tokens": 1210880} {"current_steps": 13450, "total_steps": 76960, "loss": 0.2593, "lr": 4.915371280999397e-05, "epoch": 3.4953222453222454, "percentage": 17.48, "elapsed_time": "0:19:29", "remaining_time": "1:32:01", "throughput": 1035.88, "total_tokens": 1211328} {"current_steps": 13455, "total_steps": 76960, "loss": 0.1707, "lr": 4.9152249508771445e-05, "epoch": 3.4966216216216215, "percentage": 17.48, "elapsed_time": "0:19:29", "remaining_time": "1:32:01", "throughput": 1035.9, "total_tokens": 1211792} {"current_steps": 13460, "total_steps": 76960, "loss": 0.214, "lr": 4.9150784965375586e-05, "epoch": 3.497920997920998, "percentage": 17.49, "elapsed_time": "0:19:30", "remaining_time": "1:32:00", "throughput": 1035.92, "total_tokens": 1212240} {"current_steps": 13465, "total_steps": 76960, "loss": 0.2216, "lr": 4.9149319179881716e-05, "epoch": 3.499220374220374, "percentage": 17.5, "elapsed_time": "0:19:30", "remaining_time": "1:32:00", "throughput": 1035.95, "total_tokens": 1212720} {"current_steps": 13470, "total_steps": 76960, "loss": 0.2127, "lr": 4.914785215236522e-05, "epoch": 3.5005197505197505, "percentage": 17.5, "elapsed_time": "0:19:31", "remaining_time": "1:31:59", "throughput": 1035.96, "total_tokens": 1213168} {"current_steps": 13475, "total_steps": 76960, "loss": 0.1907, "lr": 4.9146383882901555e-05, "epoch": 3.501819126819127, "percentage": 17.51, "elapsed_time": "0:19:31", "remaining_time": "1:31:59", "throughput": 1035.96, "total_tokens": 1213600} {"current_steps": 13480, "total_steps": 76960, "loss": 0.3714, "lr": 4.914491437156623e-05, "epoch": 3.503118503118503, "percentage": 17.52, "elapsed_time": "0:19:31", "remaining_time": "1:31:58", "throughput": 1035.96, "total_tokens": 1214032} {"current_steps": 13485, "total_steps": 76960, "loss": 0.249, "lr": 4.914344361843482e-05, "epoch": 3.5044178794178795, "percentage": 17.52, "elapsed_time": "0:19:32", "remaining_time": "1:31:58", "throughput": 1035.94, "total_tokens": 1214448} {"current_steps": 13490, "total_steps": 76960, "loss": 0.2561, "lr": 4.914197162358297e-05, "epoch": 3.5057172557172556, "percentage": 17.53, "elapsed_time": "0:19:32", "remaining_time": "1:31:57", "throughput": 1035.97, "total_tokens": 1214912} {"current_steps": 13495, "total_steps": 76960, "loss": 0.1908, "lr": 4.9140498387086396e-05, "epoch": 3.507016632016632, "percentage": 17.54, "elapsed_time": "0:19:33", "remaining_time": "1:31:57", "throughput": 1036.01, "total_tokens": 1215392} {"current_steps": 13500, "total_steps": 76960, "loss": 0.2895, "lr": 4.913902390902085e-05, "epoch": 3.508316008316008, "percentage": 17.54, "elapsed_time": "0:19:33", "remaining_time": "1:31:56", "throughput": 1036.02, "total_tokens": 1215840} {"current_steps": 13505, "total_steps": 76960, "loss": 0.1327, "lr": 4.913754818946219e-05, "epoch": 3.5096153846153846, "percentage": 17.55, "elapsed_time": "0:19:33", "remaining_time": "1:31:56", "throughput": 1036.05, "total_tokens": 1216304} {"current_steps": 13510, "total_steps": 76960, "loss": 0.2677, "lr": 4.913607122848628e-05, "epoch": 3.510914760914761, "percentage": 17.55, "elapsed_time": "0:19:34", "remaining_time": "1:31:55", "throughput": 1036.07, "total_tokens": 1216768} {"current_steps": 13515, "total_steps": 76960, "loss": 0.2627, "lr": 4.913459302616912e-05, "epoch": 3.512214137214137, "percentage": 17.56, "elapsed_time": "0:19:34", "remaining_time": "1:31:55", "throughput": 1036.08, "total_tokens": 1217216} {"current_steps": 13520, "total_steps": 76960, "loss": 0.319, "lr": 4.91331135825867e-05, "epoch": 3.5135135135135136, "percentage": 17.57, "elapsed_time": "0:19:35", "remaining_time": "1:31:54", "throughput": 1036.1, "total_tokens": 1217664} {"current_steps": 13525, "total_steps": 76960, "loss": 0.2131, "lr": 4.913163289781514e-05, "epoch": 3.51481288981289, "percentage": 17.57, "elapsed_time": "0:19:35", "remaining_time": "1:31:54", "throughput": 1036.1, "total_tokens": 1218096} {"current_steps": 13530, "total_steps": 76960, "loss": 0.2961, "lr": 4.913015097193057e-05, "epoch": 3.516112266112266, "percentage": 17.58, "elapsed_time": "0:19:36", "remaining_time": "1:31:53", "throughput": 1036.12, "total_tokens": 1218560} {"current_steps": 13535, "total_steps": 76960, "loss": 0.3445, "lr": 4.912866780500921e-05, "epoch": 3.517411642411642, "percentage": 17.59, "elapsed_time": "0:19:36", "remaining_time": "1:31:53", "throughput": 1036.18, "total_tokens": 1219056} {"current_steps": 13540, "total_steps": 76960, "loss": 0.2884, "lr": 4.912718339712735e-05, "epoch": 3.5187110187110187, "percentage": 17.59, "elapsed_time": "0:19:36", "remaining_time": "1:31:52", "throughput": 1036.19, "total_tokens": 1219504} {"current_steps": 13545, "total_steps": 76960, "loss": 0.2987, "lr": 4.9125697748361335e-05, "epoch": 3.520010395010395, "percentage": 17.6, "elapsed_time": "0:19:37", "remaining_time": "1:31:52", "throughput": 1036.2, "total_tokens": 1219952} {"current_steps": 13550, "total_steps": 76960, "loss": 0.2859, "lr": 4.912421085878757e-05, "epoch": 3.521309771309771, "percentage": 17.61, "elapsed_time": "0:19:37", "remaining_time": "1:31:51", "throughput": 1036.24, "total_tokens": 1220432} {"current_steps": 13555, "total_steps": 76960, "loss": 0.2734, "lr": 4.912272272848252e-05, "epoch": 3.5226091476091477, "percentage": 17.61, "elapsed_time": "0:19:38", "remaining_time": "1:31:50", "throughput": 1036.26, "total_tokens": 1220880} {"current_steps": 13560, "total_steps": 76960, "loss": 0.2789, "lr": 4.9121233357522724e-05, "epoch": 3.523908523908524, "percentage": 17.62, "elapsed_time": "0:19:38", "remaining_time": "1:31:50", "throughput": 1036.25, "total_tokens": 1221312} {"current_steps": 13565, "total_steps": 76960, "loss": 0.2089, "lr": 4.911974274598479e-05, "epoch": 3.5252079002079, "percentage": 17.63, "elapsed_time": "0:19:39", "remaining_time": "1:31:49", "throughput": 1036.29, "total_tokens": 1221792} {"current_steps": 13570, "total_steps": 76960, "loss": 0.2451, "lr": 4.911825089394537e-05, "epoch": 3.5265072765072762, "percentage": 17.63, "elapsed_time": "0:19:39", "remaining_time": "1:31:49", "throughput": 1036.31, "total_tokens": 1222256} {"current_steps": 13575, "total_steps": 76960, "loss": 0.2568, "lr": 4.911675780148121e-05, "epoch": 3.5278066528066527, "percentage": 17.64, "elapsed_time": "0:19:39", "remaining_time": "1:31:49", "throughput": 1036.32, "total_tokens": 1222704} {"current_steps": 13580, "total_steps": 76960, "loss": 0.3118, "lr": 4.911526346866907e-05, "epoch": 3.529106029106029, "percentage": 17.65, "elapsed_time": "0:19:40", "remaining_time": "1:31:48", "throughput": 1036.32, "total_tokens": 1223152} {"current_steps": 13585, "total_steps": 76960, "loss": 0.2557, "lr": 4.911376789558584e-05, "epoch": 3.5304054054054053, "percentage": 17.65, "elapsed_time": "0:19:40", "remaining_time": "1:31:48", "throughput": 1036.39, "total_tokens": 1223664} {"current_steps": 13590, "total_steps": 76960, "loss": 0.1857, "lr": 4.9112271082308415e-05, "epoch": 3.5317047817047817, "percentage": 17.66, "elapsed_time": "0:19:41", "remaining_time": "1:31:47", "throughput": 1036.41, "total_tokens": 1224128} {"current_steps": 13595, "total_steps": 76960, "loss": 0.2217, "lr": 4.9110773028913785e-05, "epoch": 3.5330041580041582, "percentage": 17.67, "elapsed_time": "0:19:41", "remaining_time": "1:31:47", "throughput": 1036.43, "total_tokens": 1224592} {"current_steps": 13600, "total_steps": 76960, "loss": 0.3474, "lr": 4.9109273735479e-05, "epoch": 3.5343035343035343, "percentage": 17.67, "elapsed_time": "0:19:41", "remaining_time": "1:31:46", "throughput": 1036.44, "total_tokens": 1225040} {"current_steps": 13605, "total_steps": 76960, "loss": 0.3618, "lr": 4.910777320208117e-05, "epoch": 3.5356029106029108, "percentage": 17.68, "elapsed_time": "0:19:42", "remaining_time": "1:31:46", "throughput": 1036.45, "total_tokens": 1225488} {"current_steps": 13610, "total_steps": 76960, "loss": 0.2365, "lr": 4.9106271428797455e-05, "epoch": 3.536902286902287, "percentage": 17.68, "elapsed_time": "0:19:42", "remaining_time": "1:31:45", "throughput": 1036.49, "total_tokens": 1225968} {"current_steps": 13615, "total_steps": 76960, "loss": 0.2946, "lr": 4.9104768415705106e-05, "epoch": 3.5382016632016633, "percentage": 17.69, "elapsed_time": "0:19:43", "remaining_time": "1:31:45", "throughput": 1036.5, "total_tokens": 1226416} {"current_steps": 13620, "total_steps": 76960, "loss": 0.2642, "lr": 4.910326416288142e-05, "epoch": 3.5395010395010393, "percentage": 17.7, "elapsed_time": "0:19:43", "remaining_time": "1:31:44", "throughput": 1036.51, "total_tokens": 1226864} {"current_steps": 13625, "total_steps": 76960, "loss": 0.2865, "lr": 4.910175867040377e-05, "epoch": 3.540800415800416, "percentage": 17.7, "elapsed_time": "0:19:44", "remaining_time": "1:31:44", "throughput": 1036.53, "total_tokens": 1227312} {"current_steps": 13630, "total_steps": 76960, "loss": 0.2652, "lr": 4.910025193834957e-05, "epoch": 3.5420997920997923, "percentage": 17.71, "elapsed_time": "0:19:44", "remaining_time": "1:31:43", "throughput": 1036.52, "total_tokens": 1227744} {"current_steps": 13635, "total_steps": 76960, "loss": 0.2404, "lr": 4.909874396679633e-05, "epoch": 3.5433991683991684, "percentage": 17.72, "elapsed_time": "0:19:44", "remaining_time": "1:31:43", "throughput": 1036.53, "total_tokens": 1228192} {"current_steps": 13640, "total_steps": 76960, "loss": 0.2294, "lr": 4.9097234755821595e-05, "epoch": 3.544698544698545, "percentage": 17.72, "elapsed_time": "0:19:45", "remaining_time": "1:31:42", "throughput": 1036.56, "total_tokens": 1228656} {"current_steps": 13645, "total_steps": 76960, "loss": 0.2089, "lr": 4.909572430550299e-05, "epoch": 3.545997920997921, "percentage": 17.73, "elapsed_time": "0:19:45", "remaining_time": "1:31:42", "throughput": 1036.54, "total_tokens": 1229072} {"current_steps": 13650, "total_steps": 76960, "loss": 0.2558, "lr": 4.9094212615918186e-05, "epoch": 3.5472972972972974, "percentage": 17.74, "elapsed_time": "0:19:46", "remaining_time": "1:31:41", "throughput": 1036.57, "total_tokens": 1229536} {"current_steps": 13655, "total_steps": 76960, "loss": 0.0825, "lr": 4.909269968714495e-05, "epoch": 3.5485966735966734, "percentage": 17.74, "elapsed_time": "0:19:46", "remaining_time": "1:31:41", "throughput": 1036.58, "total_tokens": 1229984} {"current_steps": 13660, "total_steps": 76960, "loss": 0.2266, "lr": 4.909118551926108e-05, "epoch": 3.54989604989605, "percentage": 17.75, "elapsed_time": "0:19:46", "remaining_time": "1:31:40", "throughput": 1036.59, "total_tokens": 1230432} {"current_steps": 13665, "total_steps": 76960, "loss": 0.3154, "lr": 4.9089670112344456e-05, "epoch": 3.5511954261954264, "percentage": 17.76, "elapsed_time": "0:19:47", "remaining_time": "1:31:39", "throughput": 1036.62, "total_tokens": 1230896} {"current_steps": 13670, "total_steps": 76960, "loss": 0.208, "lr": 4.908815346647302e-05, "epoch": 3.5524948024948024, "percentage": 17.76, "elapsed_time": "0:19:47", "remaining_time": "1:31:39", "throughput": 1036.67, "total_tokens": 1231392} {"current_steps": 13675, "total_steps": 76960, "loss": 0.4175, "lr": 4.9086635581724774e-05, "epoch": 3.553794178794179, "percentage": 17.77, "elapsed_time": "0:19:48", "remaining_time": "1:31:38", "throughput": 1036.67, "total_tokens": 1231824} {"current_steps": 13680, "total_steps": 76960, "loss": 0.2726, "lr": 4.908511645817777e-05, "epoch": 3.555093555093555, "percentage": 17.78, "elapsed_time": "0:19:48", "remaining_time": "1:31:38", "throughput": 1036.67, "total_tokens": 1232256} {"current_steps": 13685, "total_steps": 76960, "loss": 0.2594, "lr": 4.908359609591016e-05, "epoch": 3.5563929313929314, "percentage": 17.78, "elapsed_time": "0:19:49", "remaining_time": "1:31:37", "throughput": 1036.67, "total_tokens": 1232688} {"current_steps": 13690, "total_steps": 76960, "loss": 0.2494, "lr": 4.9082074495000116e-05, "epoch": 3.5576923076923075, "percentage": 17.79, "elapsed_time": "0:19:49", "remaining_time": "1:31:37", "throughput": 1036.65, "total_tokens": 1233104} {"current_steps": 13695, "total_steps": 76960, "loss": 0.2099, "lr": 4.908055165552592e-05, "epoch": 3.558991683991684, "percentage": 17.79, "elapsed_time": "0:19:49", "remaining_time": "1:31:36", "throughput": 1036.68, "total_tokens": 1233568} {"current_steps": 13700, "total_steps": 76960, "loss": 0.2569, "lr": 4.907902757756587e-05, "epoch": 3.5602910602910605, "percentage": 17.8, "elapsed_time": "0:19:50", "remaining_time": "1:31:36", "throughput": 1036.7, "total_tokens": 1234032} {"current_steps": 13705, "total_steps": 76960, "loss": 0.3075, "lr": 4.907750226119837e-05, "epoch": 3.5615904365904365, "percentage": 17.81, "elapsed_time": "0:19:50", "remaining_time": "1:31:35", "throughput": 1036.73, "total_tokens": 1234496} {"current_steps": 13710, "total_steps": 76960, "loss": 0.2287, "lr": 4.907597570650185e-05, "epoch": 3.562889812889813, "percentage": 17.81, "elapsed_time": "0:19:51", "remaining_time": "1:31:35", "throughput": 1036.76, "total_tokens": 1234960} {"current_steps": 13715, "total_steps": 76960, "loss": 0.315, "lr": 4.907444791355483e-05, "epoch": 3.564189189189189, "percentage": 17.82, "elapsed_time": "0:19:51", "remaining_time": "1:31:34", "throughput": 1036.75, "total_tokens": 1235392} {"current_steps": 13720, "total_steps": 76960, "loss": 0.2337, "lr": 4.9072918882435894e-05, "epoch": 3.5654885654885655, "percentage": 17.83, "elapsed_time": "0:19:52", "remaining_time": "1:31:34", "throughput": 1036.77, "total_tokens": 1235840} {"current_steps": 13725, "total_steps": 76960, "loss": 0.2363, "lr": 4.907138861322367e-05, "epoch": 3.5667879417879416, "percentage": 17.83, "elapsed_time": "0:19:52", "remaining_time": "1:31:33", "throughput": 1036.77, "total_tokens": 1236272} {"current_steps": 13730, "total_steps": 76960, "loss": 0.3853, "lr": 4.906985710599686e-05, "epoch": 3.568087318087318, "percentage": 17.84, "elapsed_time": "0:19:52", "remaining_time": "1:31:33", "throughput": 1036.82, "total_tokens": 1236768} {"current_steps": 13735, "total_steps": 76960, "loss": 0.2609, "lr": 4.9068324360834245e-05, "epoch": 3.5693866943866945, "percentage": 17.85, "elapsed_time": "0:19:53", "remaining_time": "1:31:32", "throughput": 1036.82, "total_tokens": 1237200} {"current_steps": 13740, "total_steps": 76960, "loss": 0.2115, "lr": 4.9066790377814643e-05, "epoch": 3.5706860706860706, "percentage": 17.85, "elapsed_time": "0:19:53", "remaining_time": "1:31:32", "throughput": 1036.84, "total_tokens": 1237664} {"current_steps": 13745, "total_steps": 76960, "loss": 0.2237, "lr": 4.906525515701695e-05, "epoch": 3.571985446985447, "percentage": 17.86, "elapsed_time": "0:19:54", "remaining_time": "1:31:31", "throughput": 1036.84, "total_tokens": 1238096} {"current_steps": 13750, "total_steps": 76960, "loss": 0.2204, "lr": 4.906371869852013e-05, "epoch": 3.5732848232848236, "percentage": 17.87, "elapsed_time": "0:19:54", "remaining_time": "1:31:31", "throughput": 1036.85, "total_tokens": 1238544} {"current_steps": 13755, "total_steps": 76960, "loss": 0.3671, "lr": 4.906218100240321e-05, "epoch": 3.5745841995841996, "percentage": 17.87, "elapsed_time": "0:19:54", "remaining_time": "1:31:30", "throughput": 1036.87, "total_tokens": 1238992} {"current_steps": 13760, "total_steps": 76960, "loss": 0.2222, "lr": 4.906064206874525e-05, "epoch": 3.5758835758835756, "percentage": 17.88, "elapsed_time": "0:19:55", "remaining_time": "1:31:30", "throughput": 1036.88, "total_tokens": 1239440} {"current_steps": 13765, "total_steps": 76960, "loss": 0.2567, "lr": 4.905910189762542e-05, "epoch": 3.577182952182952, "percentage": 17.89, "elapsed_time": "0:19:55", "remaining_time": "1:31:29", "throughput": 1036.9, "total_tokens": 1239904} {"current_steps": 13770, "total_steps": 76960, "loss": 0.2192, "lr": 4.905756048912293e-05, "epoch": 3.5784823284823286, "percentage": 17.89, "elapsed_time": "0:19:56", "remaining_time": "1:31:29", "throughput": 1036.92, "total_tokens": 1240368} {"current_steps": 13775, "total_steps": 76960, "loss": 0.3535, "lr": 4.905601784331705e-05, "epoch": 3.5797817047817047, "percentage": 17.9, "elapsed_time": "0:19:56", "remaining_time": "1:31:28", "throughput": 1036.95, "total_tokens": 1240848} {"current_steps": 13780, "total_steps": 76960, "loss": 0.2353, "lr": 4.9054473960287116e-05, "epoch": 3.581081081081081, "percentage": 17.91, "elapsed_time": "0:19:57", "remaining_time": "1:31:28", "throughput": 1036.94, "total_tokens": 1241280} {"current_steps": 13785, "total_steps": 76960, "loss": 0.2707, "lr": 4.9052928840112555e-05, "epoch": 3.5823804573804576, "percentage": 17.91, "elapsed_time": "0:19:57", "remaining_time": "1:31:27", "throughput": 1036.97, "total_tokens": 1241744} {"current_steps": 13790, "total_steps": 76960, "loss": 0.2697, "lr": 4.90513824828728e-05, "epoch": 3.5836798336798337, "percentage": 17.92, "elapsed_time": "0:19:57", "remaining_time": "1:31:27", "throughput": 1036.98, "total_tokens": 1242192} {"current_steps": 13795, "total_steps": 76960, "loss": 0.2887, "lr": 4.904983488864741e-05, "epoch": 3.5849792099792097, "percentage": 17.92, "elapsed_time": "0:19:58", "remaining_time": "1:31:26", "throughput": 1037.0, "total_tokens": 1242656} {"current_steps": 13800, "total_steps": 76960, "loss": 0.2431, "lr": 4.904828605751597e-05, "epoch": 3.586278586278586, "percentage": 17.93, "elapsed_time": "0:19:58", "remaining_time": "1:31:26", "throughput": 1037.05, "total_tokens": 1243152} {"current_steps": 13805, "total_steps": 76960, "loss": 0.198, "lr": 4.904673598955813e-05, "epoch": 3.5875779625779627, "percentage": 17.94, "elapsed_time": "0:19:59", "remaining_time": "1:31:25", "throughput": 1037.05, "total_tokens": 1243584} {"current_steps": 13810, "total_steps": 76960, "loss": 0.2623, "lr": 4.904518468485362e-05, "epoch": 3.5888773388773387, "percentage": 17.94, "elapsed_time": "0:19:59", "remaining_time": "1:31:25", "throughput": 1037.09, "total_tokens": 1244064} {"current_steps": 13815, "total_steps": 76960, "loss": 0.1562, "lr": 4.904363214348222e-05, "epoch": 3.590176715176715, "percentage": 17.95, "elapsed_time": "0:19:59", "remaining_time": "1:31:24", "throughput": 1037.12, "total_tokens": 1244528} {"current_steps": 13820, "total_steps": 76960, "loss": 0.1446, "lr": 4.904207836552378e-05, "epoch": 3.5914760914760917, "percentage": 17.96, "elapsed_time": "0:20:00", "remaining_time": "1:31:24", "throughput": 1037.11, "total_tokens": 1244960} {"current_steps": 13825, "total_steps": 76960, "loss": 0.2184, "lr": 4.904052335105822e-05, "epoch": 3.5927754677754677, "percentage": 17.96, "elapsed_time": "0:20:00", "remaining_time": "1:31:23", "throughput": 1037.14, "total_tokens": 1245424} {"current_steps": 13830, "total_steps": 76960, "loss": 0.2832, "lr": 4.903896710016551e-05, "epoch": 3.5940748440748442, "percentage": 17.97, "elapsed_time": "0:20:01", "remaining_time": "1:31:23", "throughput": 1037.17, "total_tokens": 1245904} {"current_steps": 13835, "total_steps": 76960, "loss": 0.2186, "lr": 4.9037409612925675e-05, "epoch": 3.5953742203742203, "percentage": 17.98, "elapsed_time": "0:20:01", "remaining_time": "1:31:22", "throughput": 1037.17, "total_tokens": 1246336} {"current_steps": 13840, "total_steps": 76960, "loss": 0.3229, "lr": 4.903585088941885e-05, "epoch": 3.5966735966735968, "percentage": 17.98, "elapsed_time": "0:20:02", "remaining_time": "1:31:22", "throughput": 1037.16, "total_tokens": 1246752} {"current_steps": 13845, "total_steps": 76960, "loss": 0.1163, "lr": 4.9034290929725174e-05, "epoch": 3.597972972972973, "percentage": 17.99, "elapsed_time": "0:20:02", "remaining_time": "1:31:21", "throughput": 1037.16, "total_tokens": 1247184} {"current_steps": 13850, "total_steps": 76960, "loss": 0.3011, "lr": 4.9032729733924885e-05, "epoch": 3.5992723492723493, "percentage": 18.0, "elapsed_time": "0:20:02", "remaining_time": "1:31:21", "throughput": 1037.18, "total_tokens": 1247648} {"current_steps": 13855, "total_steps": 76960, "loss": 0.2684, "lr": 4.9031167302098294e-05, "epoch": 3.600571725571726, "percentage": 18.0, "elapsed_time": "0:20:03", "remaining_time": "1:31:20", "throughput": 1037.15, "total_tokens": 1248048} {"current_steps": 13860, "total_steps": 76960, "loss": 0.2104, "lr": 4.9029603634325726e-05, "epoch": 3.601871101871102, "percentage": 18.01, "elapsed_time": "0:20:03", "remaining_time": "1:31:20", "throughput": 1037.18, "total_tokens": 1248512} {"current_steps": 13865, "total_steps": 76960, "loss": 0.2077, "lr": 4.902803873068763e-05, "epoch": 3.6031704781704783, "percentage": 18.02, "elapsed_time": "0:20:04", "remaining_time": "1:31:19", "throughput": 1037.2, "total_tokens": 1248976} {"current_steps": 13870, "total_steps": 76960, "loss": 0.1976, "lr": 4.902647259126447e-05, "epoch": 3.6044698544698544, "percentage": 18.02, "elapsed_time": "0:20:04", "remaining_time": "1:31:19", "throughput": 1037.19, "total_tokens": 1249392} {"current_steps": 13875, "total_steps": 76960, "loss": 0.2141, "lr": 4.902490521613681e-05, "epoch": 3.605769230769231, "percentage": 18.03, "elapsed_time": "0:20:05", "remaining_time": "1:31:18", "throughput": 1037.21, "total_tokens": 1249856} {"current_steps": 13880, "total_steps": 76960, "loss": 0.2737, "lr": 4.902333660538525e-05, "epoch": 3.607068607068607, "percentage": 18.04, "elapsed_time": "0:20:05", "remaining_time": "1:31:18", "throughput": 1037.22, "total_tokens": 1250304} {"current_steps": 13885, "total_steps": 76960, "loss": 0.1539, "lr": 4.902176675909047e-05, "epoch": 3.6083679833679834, "percentage": 18.04, "elapsed_time": "0:20:05", "remaining_time": "1:31:17", "throughput": 1037.25, "total_tokens": 1250768} {"current_steps": 13890, "total_steps": 76960, "loss": 0.268, "lr": 4.902019567733321e-05, "epoch": 3.60966735966736, "percentage": 18.05, "elapsed_time": "0:20:06", "remaining_time": "1:31:17", "throughput": 1037.29, "total_tokens": 1251248} {"current_steps": 13895, "total_steps": 76960, "loss": 0.2134, "lr": 4.9018623360194284e-05, "epoch": 3.610966735966736, "percentage": 18.05, "elapsed_time": "0:20:06", "remaining_time": "1:31:16", "throughput": 1037.31, "total_tokens": 1251712} {"current_steps": 13900, "total_steps": 76960, "loss": 0.266, "lr": 4.9017049807754534e-05, "epoch": 3.6122661122661124, "percentage": 18.06, "elapsed_time": "0:20:07", "remaining_time": "1:31:16", "throughput": 1037.34, "total_tokens": 1252176} {"current_steps": 13905, "total_steps": 76960, "loss": 0.2729, "lr": 4.90154750200949e-05, "epoch": 3.6135654885654884, "percentage": 18.07, "elapsed_time": "0:20:07", "remaining_time": "1:31:15", "throughput": 1037.36, "total_tokens": 1252640} {"current_steps": 13910, "total_steps": 76960, "loss": 0.2179, "lr": 4.901389899729638e-05, "epoch": 3.614864864864865, "percentage": 18.07, "elapsed_time": "0:20:07", "remaining_time": "1:31:15", "throughput": 1037.37, "total_tokens": 1253088} {"current_steps": 13915, "total_steps": 76960, "loss": 0.2434, "lr": 4.901232173944001e-05, "epoch": 3.616164241164241, "percentage": 18.08, "elapsed_time": "0:20:08", "remaining_time": "1:31:14", "throughput": 1037.39, "total_tokens": 1253536} {"current_steps": 13920, "total_steps": 76960, "loss": 0.3, "lr": 4.901074324660695e-05, "epoch": 3.6174636174636174, "percentage": 18.09, "elapsed_time": "0:20:08", "remaining_time": "1:31:14", "throughput": 1037.41, "total_tokens": 1254000} {"current_steps": 13925, "total_steps": 76960, "loss": 0.1413, "lr": 4.900916351887834e-05, "epoch": 3.618762993762994, "percentage": 18.09, "elapsed_time": "0:20:09", "remaining_time": "1:31:13", "throughput": 1037.41, "total_tokens": 1254432} {"current_steps": 13930, "total_steps": 76960, "loss": 0.1808, "lr": 4.9007582556335454e-05, "epoch": 3.62006237006237, "percentage": 18.1, "elapsed_time": "0:20:09", "remaining_time": "1:31:13", "throughput": 1037.41, "total_tokens": 1254864} {"current_steps": 13935, "total_steps": 76960, "loss": 0.2197, "lr": 4.900600035905959e-05, "epoch": 3.6213617463617465, "percentage": 18.11, "elapsed_time": "0:20:10", "remaining_time": "1:31:12", "throughput": 1037.42, "total_tokens": 1255312} {"current_steps": 13940, "total_steps": 76960, "loss": 0.3891, "lr": 4.900441692713213e-05, "epoch": 3.6226611226611225, "percentage": 18.11, "elapsed_time": "0:20:10", "remaining_time": "1:31:12", "throughput": 1037.4, "total_tokens": 1255728} {"current_steps": 13945, "total_steps": 76960, "loss": 0.212, "lr": 4.90028322606345e-05, "epoch": 3.623960498960499, "percentage": 18.12, "elapsed_time": "0:20:10", "remaining_time": "1:31:11", "throughput": 1037.37, "total_tokens": 1256128} {"current_steps": 13950, "total_steps": 76960, "loss": 0.2202, "lr": 4.9001246359648224e-05, "epoch": 3.625259875259875, "percentage": 18.13, "elapsed_time": "0:20:11", "remaining_time": "1:31:11", "throughput": 1037.42, "total_tokens": 1256624} {"current_steps": 13955, "total_steps": 76960, "loss": 0.2542, "lr": 4.899965922425483e-05, "epoch": 3.6265592515592515, "percentage": 18.13, "elapsed_time": "0:20:11", "remaining_time": "1:31:10", "throughput": 1037.45, "total_tokens": 1257088} {"current_steps": 13960, "total_steps": 76960, "loss": 0.25, "lr": 4.8998070854535984e-05, "epoch": 3.627858627858628, "percentage": 18.14, "elapsed_time": "0:20:12", "remaining_time": "1:31:10", "throughput": 1037.45, "total_tokens": 1257520} {"current_steps": 13965, "total_steps": 76960, "loss": 0.225, "lr": 4.899648125057336e-05, "epoch": 3.629158004158004, "percentage": 18.15, "elapsed_time": "0:20:12", "remaining_time": "1:31:09", "throughput": 1037.46, "total_tokens": 1257968} {"current_steps": 13970, "total_steps": 76960, "loss": 0.2957, "lr": 4.89948904124487e-05, "epoch": 3.6304573804573805, "percentage": 18.15, "elapsed_time": "0:20:12", "remaining_time": "1:31:09", "throughput": 1037.44, "total_tokens": 1258384} {"current_steps": 13975, "total_steps": 76960, "loss": 0.3458, "lr": 4.899329834024384e-05, "epoch": 3.631756756756757, "percentage": 18.16, "elapsed_time": "0:20:13", "remaining_time": "1:31:08", "throughput": 1037.51, "total_tokens": 1258896} {"current_steps": 13980, "total_steps": 76960, "loss": 0.2385, "lr": 4.899170503404066e-05, "epoch": 3.633056133056133, "percentage": 18.17, "elapsed_time": "0:20:13", "remaining_time": "1:31:08", "throughput": 1037.54, "total_tokens": 1259376} {"current_steps": 13985, "total_steps": 76960, "loss": 0.2403, "lr": 4.8990110493921105e-05, "epoch": 3.634355509355509, "percentage": 18.17, "elapsed_time": "0:20:14", "remaining_time": "1:31:07", "throughput": 1037.51, "total_tokens": 1259776} {"current_steps": 13990, "total_steps": 76960, "loss": 0.2606, "lr": 4.8988514719967175e-05, "epoch": 3.6356548856548856, "percentage": 18.18, "elapsed_time": "0:20:14", "remaining_time": "1:31:07", "throughput": 1037.54, "total_tokens": 1260240} {"current_steps": 13995, "total_steps": 76960, "loss": 0.2878, "lr": 4.898691771226095e-05, "epoch": 3.636954261954262, "percentage": 18.18, "elapsed_time": "0:20:15", "remaining_time": "1:31:06", "throughput": 1037.56, "total_tokens": 1260704} {"current_steps": 14000, "total_steps": 76960, "loss": 0.255, "lr": 4.898531947088457e-05, "epoch": 3.638253638253638, "percentage": 18.19, "elapsed_time": "0:20:15", "remaining_time": "1:31:06", "throughput": 1037.57, "total_tokens": 1261152} {"current_steps": 14005, "total_steps": 76960, "loss": 0.2674, "lr": 4.898371999592022e-05, "epoch": 3.6395530145530146, "percentage": 18.2, "elapsed_time": "0:20:15", "remaining_time": "1:31:05", "throughput": 1037.56, "total_tokens": 1261568} {"current_steps": 14010, "total_steps": 76960, "loss": 0.2637, "lr": 4.898211928745017e-05, "epoch": 3.640852390852391, "percentage": 18.2, "elapsed_time": "0:20:16", "remaining_time": "1:31:05", "throughput": 1037.57, "total_tokens": 1262016} {"current_steps": 14015, "total_steps": 76960, "loss": 0.261, "lr": 4.898051734555676e-05, "epoch": 3.642151767151767, "percentage": 18.21, "elapsed_time": "0:20:16", "remaining_time": "1:31:04", "throughput": 1037.57, "total_tokens": 1262448} {"current_steps": 14020, "total_steps": 76960, "loss": 0.2563, "lr": 4.897891417032235e-05, "epoch": 3.643451143451143, "percentage": 18.22, "elapsed_time": "0:20:17", "remaining_time": "1:31:04", "throughput": 1037.58, "total_tokens": 1262896} {"current_steps": 14025, "total_steps": 76960, "loss": 0.3047, "lr": 4.8977309761829416e-05, "epoch": 3.6447505197505197, "percentage": 18.22, "elapsed_time": "0:20:17", "remaining_time": "1:31:03", "throughput": 1037.59, "total_tokens": 1263344} {"current_steps": 14030, "total_steps": 76960, "loss": 0.2768, "lr": 4.8975704120160464e-05, "epoch": 3.646049896049896, "percentage": 18.23, "elapsed_time": "0:20:17", "remaining_time": "1:31:03", "throughput": 1037.61, "total_tokens": 1263808} {"current_steps": 14035, "total_steps": 76960, "loss": 0.3009, "lr": 4.897409724539808e-05, "epoch": 3.647349272349272, "percentage": 18.24, "elapsed_time": "0:20:18", "remaining_time": "1:31:02", "throughput": 1037.64, "total_tokens": 1264272} {"current_steps": 14040, "total_steps": 76960, "loss": 0.2785, "lr": 4.89724891376249e-05, "epoch": 3.6486486486486487, "percentage": 18.24, "elapsed_time": "0:20:18", "remaining_time": "1:31:02", "throughput": 1037.64, "total_tokens": 1264704} {"current_steps": 14045, "total_steps": 76960, "loss": 0.2757, "lr": 4.8970879796923635e-05, "epoch": 3.649948024948025, "percentage": 18.25, "elapsed_time": "0:20:19", "remaining_time": "1:31:01", "throughput": 1037.65, "total_tokens": 1265152} {"current_steps": 14050, "total_steps": 76960, "loss": 0.2998, "lr": 4.8969269223377056e-05, "epoch": 3.651247401247401, "percentage": 18.26, "elapsed_time": "0:20:19", "remaining_time": "1:31:01", "throughput": 1037.65, "total_tokens": 1265584} {"current_steps": 14055, "total_steps": 76960, "loss": 0.2918, "lr": 4.896765741706799e-05, "epoch": 3.6525467775467777, "percentage": 18.26, "elapsed_time": "0:20:20", "remaining_time": "1:31:00", "throughput": 1037.69, "total_tokens": 1266064} {"current_steps": 14060, "total_steps": 76960, "loss": 0.2697, "lr": 4.896604437807935e-05, "epoch": 3.6538461538461537, "percentage": 18.27, "elapsed_time": "0:20:20", "remaining_time": "1:31:00", "throughput": 1037.71, "total_tokens": 1266528} {"current_steps": 14065, "total_steps": 76960, "loss": 0.261, "lr": 4.8964430106494075e-05, "epoch": 3.6551455301455302, "percentage": 18.28, "elapsed_time": "0:20:20", "remaining_time": "1:30:59", "throughput": 1037.72, "total_tokens": 1266976} {"current_steps": 14070, "total_steps": 76960, "loss": 0.1993, "lr": 4.89628146023952e-05, "epoch": 3.6564449064449063, "percentage": 18.28, "elapsed_time": "0:20:21", "remaining_time": "1:30:59", "throughput": 1037.71, "total_tokens": 1267392} {"current_steps": 14075, "total_steps": 76960, "loss": 0.1772, "lr": 4.896119786586581e-05, "epoch": 3.6577442827442828, "percentage": 18.29, "elapsed_time": "0:20:21", "remaining_time": "1:30:58", "throughput": 1037.75, "total_tokens": 1267872} {"current_steps": 14080, "total_steps": 76960, "loss": 0.2081, "lr": 4.8959579896989054e-05, "epoch": 3.6590436590436592, "percentage": 18.3, "elapsed_time": "0:20:22", "remaining_time": "1:30:58", "throughput": 1037.72, "total_tokens": 1268272} {"current_steps": 14085, "total_steps": 76960, "loss": 0.257, "lr": 4.895796069584815e-05, "epoch": 3.6603430353430353, "percentage": 18.3, "elapsed_time": "0:20:22", "remaining_time": "1:30:57", "throughput": 1037.72, "total_tokens": 1268704} {"current_steps": 14090, "total_steps": 76960, "loss": 0.3519, "lr": 4.895634026252637e-05, "epoch": 3.6616424116424118, "percentage": 18.31, "elapsed_time": "0:20:23", "remaining_time": "1:30:57", "throughput": 1037.73, "total_tokens": 1269152} {"current_steps": 14095, "total_steps": 76960, "loss": 0.0979, "lr": 4.895471859710705e-05, "epoch": 3.662941787941788, "percentage": 18.31, "elapsed_time": "0:20:23", "remaining_time": "1:30:56", "throughput": 1037.72, "total_tokens": 1269568} {"current_steps": 14100, "total_steps": 76960, "loss": 0.3616, "lr": 4.895309569967361e-05, "epoch": 3.6642411642411643, "percentage": 18.32, "elapsed_time": "0:20:23", "remaining_time": "1:30:56", "throughput": 1037.72, "total_tokens": 1270000} {"current_steps": 14105, "total_steps": 76960, "loss": 0.3003, "lr": 4.895147157030951e-05, "epoch": 3.6655405405405403, "percentage": 18.33, "elapsed_time": "0:20:24", "remaining_time": "1:30:55", "throughput": 1037.76, "total_tokens": 1270480} {"current_steps": 14110, "total_steps": 76960, "loss": 0.3299, "lr": 4.894984620909827e-05, "epoch": 3.666839916839917, "percentage": 18.33, "elapsed_time": "0:20:24", "remaining_time": "1:30:55", "throughput": 1037.75, "total_tokens": 1270912} {"current_steps": 14115, "total_steps": 76960, "loss": 0.311, "lr": 4.894821961612349e-05, "epoch": 3.6681392931392933, "percentage": 18.34, "elapsed_time": "0:20:25", "remaining_time": "1:30:54", "throughput": 1037.75, "total_tokens": 1271344} {"current_steps": 14120, "total_steps": 76960, "loss": 0.2614, "lr": 4.894659179146883e-05, "epoch": 3.6694386694386694, "percentage": 18.35, "elapsed_time": "0:20:25", "remaining_time": "1:30:54", "throughput": 1037.76, "total_tokens": 1271792} {"current_steps": 14125, "total_steps": 76960, "loss": 0.2805, "lr": 4.894496273521802e-05, "epoch": 3.670738045738046, "percentage": 18.35, "elapsed_time": "0:20:25", "remaining_time": "1:30:53", "throughput": 1037.79, "total_tokens": 1272256} {"current_steps": 14130, "total_steps": 76960, "loss": 0.2462, "lr": 4.894333244745483e-05, "epoch": 3.672037422037422, "percentage": 18.36, "elapsed_time": "0:20:26", "remaining_time": "1:30:53", "throughput": 1037.8, "total_tokens": 1272704} {"current_steps": 14135, "total_steps": 76960, "loss": 0.1998, "lr": 4.89417009282631e-05, "epoch": 3.6733367983367984, "percentage": 18.37, "elapsed_time": "0:20:26", "remaining_time": "1:30:52", "throughput": 1037.82, "total_tokens": 1273168} {"current_steps": 14140, "total_steps": 76960, "loss": 0.2609, "lr": 4.894006817772676e-05, "epoch": 3.6746361746361744, "percentage": 18.37, "elapsed_time": "0:20:27", "remaining_time": "1:30:52", "throughput": 1037.84, "total_tokens": 1273616} {"current_steps": 14145, "total_steps": 76960, "loss": 0.2152, "lr": 4.893843419592977e-05, "epoch": 3.675935550935551, "percentage": 18.38, "elapsed_time": "0:20:27", "remaining_time": "1:30:51", "throughput": 1037.86, "total_tokens": 1274080} {"current_steps": 14150, "total_steps": 76960, "loss": 0.1492, "lr": 4.893679898295618e-05, "epoch": 3.6772349272349274, "percentage": 18.39, "elapsed_time": "0:20:28", "remaining_time": "1:30:51", "throughput": 1037.9, "total_tokens": 1274560} {"current_steps": 14155, "total_steps": 76960, "loss": 0.2657, "lr": 4.893516253889008e-05, "epoch": 3.6785343035343034, "percentage": 18.39, "elapsed_time": "0:20:28", "remaining_time": "1:30:50", "throughput": 1037.91, "total_tokens": 1275008} {"current_steps": 14160, "total_steps": 76960, "loss": 0.4315, "lr": 4.893352486381564e-05, "epoch": 3.67983367983368, "percentage": 18.4, "elapsed_time": "0:20:28", "remaining_time": "1:30:50", "throughput": 1037.92, "total_tokens": 1275456} {"current_steps": 14165, "total_steps": 76960, "loss": 0.1851, "lr": 4.893188595781708e-05, "epoch": 3.681133056133056, "percentage": 18.41, "elapsed_time": "0:20:29", "remaining_time": "1:30:49", "throughput": 1037.94, "total_tokens": 1275920} {"current_steps": 14170, "total_steps": 76960, "loss": 0.2571, "lr": 4.893024582097869e-05, "epoch": 3.6824324324324325, "percentage": 18.41, "elapsed_time": "0:20:29", "remaining_time": "1:30:49", "throughput": 1037.99, "total_tokens": 1276416} {"current_steps": 14175, "total_steps": 76960, "loss": 0.1822, "lr": 4.892860445338484e-05, "epoch": 3.6837318087318085, "percentage": 18.42, "elapsed_time": "0:20:30", "remaining_time": "1:30:48", "throughput": 1038.03, "total_tokens": 1276896} {"current_steps": 14180, "total_steps": 76960, "loss": 0.1652, "lr": 4.892696185511993e-05, "epoch": 3.685031185031185, "percentage": 18.43, "elapsed_time": "0:20:30", "remaining_time": "1:30:48", "throughput": 1038.03, "total_tokens": 1277328} {"current_steps": 14185, "total_steps": 76960, "loss": 0.1478, "lr": 4.892531802626844e-05, "epoch": 3.6863305613305615, "percentage": 18.43, "elapsed_time": "0:20:30", "remaining_time": "1:30:47", "throughput": 1038.02, "total_tokens": 1277760} {"current_steps": 14190, "total_steps": 76960, "loss": 0.2886, "lr": 4.892367296691493e-05, "epoch": 3.6876299376299375, "percentage": 18.44, "elapsed_time": "0:20:31", "remaining_time": "1:30:47", "throughput": 1038.07, "total_tokens": 1278256} {"current_steps": 14195, "total_steps": 76960, "loss": 0.145, "lr": 4.8922026677144e-05, "epoch": 3.688929313929314, "percentage": 18.44, "elapsed_time": "0:20:31", "remaining_time": "1:30:46", "throughput": 1038.09, "total_tokens": 1278704} {"current_steps": 14200, "total_steps": 76960, "loss": 0.401, "lr": 4.8920379157040304e-05, "epoch": 3.6902286902286905, "percentage": 18.45, "elapsed_time": "0:20:32", "remaining_time": "1:30:46", "throughput": 1038.11, "total_tokens": 1279168} {"current_steps": 14205, "total_steps": 76960, "loss": 0.2242, "lr": 4.89187304066886e-05, "epoch": 3.6915280665280665, "percentage": 18.46, "elapsed_time": "0:20:32", "remaining_time": "1:30:45", "throughput": 1038.16, "total_tokens": 1279664} {"current_steps": 14210, "total_steps": 76960, "loss": 0.1213, "lr": 4.891708042617366e-05, "epoch": 3.6928274428274426, "percentage": 18.46, "elapsed_time": "0:20:33", "remaining_time": "1:30:45", "throughput": 1038.16, "total_tokens": 1280096} {"current_steps": 14215, "total_steps": 76960, "loss": 0.3006, "lr": 4.891542921558036e-05, "epoch": 3.694126819126819, "percentage": 18.47, "elapsed_time": "0:20:33", "remaining_time": "1:30:44", "throughput": 1038.17, "total_tokens": 1280544} {"current_steps": 14220, "total_steps": 76960, "loss": 0.3111, "lr": 4.891377677499363e-05, "epoch": 3.6954261954261955, "percentage": 18.48, "elapsed_time": "0:20:33", "remaining_time": "1:30:43", "throughput": 1038.17, "total_tokens": 1280976} {"current_steps": 14225, "total_steps": 76960, "loss": 0.3079, "lr": 4.891212310449844e-05, "epoch": 3.6967255717255716, "percentage": 18.48, "elapsed_time": "0:20:34", "remaining_time": "1:30:43", "throughput": 1038.18, "total_tokens": 1281424} {"current_steps": 14230, "total_steps": 76960, "loss": 0.2598, "lr": 4.891046820417985e-05, "epoch": 3.698024948024948, "percentage": 18.49, "elapsed_time": "0:20:34", "remaining_time": "1:30:42", "throughput": 1038.19, "total_tokens": 1281872} {"current_steps": 14235, "total_steps": 76960, "loss": 0.26, "lr": 4.890881207412298e-05, "epoch": 3.6993243243243246, "percentage": 18.5, "elapsed_time": "0:20:35", "remaining_time": "1:30:42", "throughput": 1038.19, "total_tokens": 1282304} {"current_steps": 14240, "total_steps": 76960, "loss": 0.256, "lr": 4.8907154714412984e-05, "epoch": 3.7006237006237006, "percentage": 18.5, "elapsed_time": "0:20:35", "remaining_time": "1:30:41", "throughput": 1038.2, "total_tokens": 1282752} {"current_steps": 14245, "total_steps": 76960, "loss": 0.2264, "lr": 4.890549612513512e-05, "epoch": 3.7019230769230766, "percentage": 18.51, "elapsed_time": "0:20:35", "remaining_time": "1:30:41", "throughput": 1038.25, "total_tokens": 1283248} {"current_steps": 14250, "total_steps": 76960, "loss": 0.2792, "lr": 4.890383630637468e-05, "epoch": 3.703222453222453, "percentage": 18.52, "elapsed_time": "0:20:36", "remaining_time": "1:30:40", "throughput": 1038.28, "total_tokens": 1283712} {"current_steps": 14255, "total_steps": 76960, "loss": 0.2505, "lr": 4.890217525821704e-05, "epoch": 3.7045218295218296, "percentage": 18.52, "elapsed_time": "0:20:36", "remaining_time": "1:30:40", "throughput": 1038.32, "total_tokens": 1284192} {"current_steps": 14260, "total_steps": 76960, "loss": 0.284, "lr": 4.890051298074762e-05, "epoch": 3.7058212058212057, "percentage": 18.53, "elapsed_time": "0:20:37", "remaining_time": "1:30:39", "throughput": 1038.38, "total_tokens": 1284704} {"current_steps": 14265, "total_steps": 76960, "loss": 0.279, "lr": 4.8898849474051924e-05, "epoch": 3.707120582120582, "percentage": 18.54, "elapsed_time": "0:20:37", "remaining_time": "1:30:39", "throughput": 1038.4, "total_tokens": 1285168} {"current_steps": 14270, "total_steps": 76960, "loss": 0.2901, "lr": 4.88971847382155e-05, "epoch": 3.7084199584199586, "percentage": 18.54, "elapsed_time": "0:20:38", "remaining_time": "1:30:38", "throughput": 1038.4, "total_tokens": 1285600} {"current_steps": 14275, "total_steps": 76960, "loss": 0.2596, "lr": 4.889551877332396e-05, "epoch": 3.7097193347193347, "percentage": 18.55, "elapsed_time": "0:20:38", "remaining_time": "1:30:38", "throughput": 1038.43, "total_tokens": 1286064} {"current_steps": 14280, "total_steps": 76960, "loss": 0.2005, "lr": 4.8893851579462993e-05, "epoch": 3.711018711018711, "percentage": 18.56, "elapsed_time": "0:20:38", "remaining_time": "1:30:37", "throughput": 1038.41, "total_tokens": 1286480} {"current_steps": 14285, "total_steps": 76960, "loss": 0.229, "lr": 4.8892183156718354e-05, "epoch": 3.712318087318087, "percentage": 18.56, "elapsed_time": "0:20:39", "remaining_time": "1:30:37", "throughput": 1038.44, "total_tokens": 1286944} {"current_steps": 14290, "total_steps": 76960, "loss": 0.2166, "lr": 4.889051350517584e-05, "epoch": 3.7136174636174637, "percentage": 18.57, "elapsed_time": "0:20:39", "remaining_time": "1:30:36", "throughput": 1038.46, "total_tokens": 1287408} {"current_steps": 14295, "total_steps": 76960, "loss": 0.2084, "lr": 4.888884262492132e-05, "epoch": 3.7149168399168397, "percentage": 18.57, "elapsed_time": "0:20:40", "remaining_time": "1:30:36", "throughput": 1038.45, "total_tokens": 1287824} {"current_steps": 14300, "total_steps": 76960, "loss": 0.2186, "lr": 4.888717051604074e-05, "epoch": 3.7162162162162162, "percentage": 18.58, "elapsed_time": "0:20:40", "remaining_time": "1:30:35", "throughput": 1038.46, "total_tokens": 1288272} {"current_steps": 14305, "total_steps": 76960, "loss": 0.3226, "lr": 4.8885497178620095e-05, "epoch": 3.7175155925155927, "percentage": 18.59, "elapsed_time": "0:20:40", "remaining_time": "1:30:35", "throughput": 1038.47, "total_tokens": 1288720} {"current_steps": 14310, "total_steps": 76960, "loss": 0.3052, "lr": 4.888382261274544e-05, "epoch": 3.7188149688149688, "percentage": 18.59, "elapsed_time": "0:20:41", "remaining_time": "1:30:34", "throughput": 1038.47, "total_tokens": 1289152} {"current_steps": 14315, "total_steps": 76960, "loss": 0.2547, "lr": 4.88821468185029e-05, "epoch": 3.7201143451143452, "percentage": 18.6, "elapsed_time": "0:20:41", "remaining_time": "1:30:34", "throughput": 1038.48, "total_tokens": 1289600} {"current_steps": 14320, "total_steps": 76960, "loss": 0.2293, "lr": 4.8880469795978676e-05, "epoch": 3.7214137214137213, "percentage": 18.61, "elapsed_time": "0:20:42", "remaining_time": "1:30:33", "throughput": 1038.48, "total_tokens": 1290032} {"current_steps": 14325, "total_steps": 76960, "loss": 0.3141, "lr": 4.887879154525901e-05, "epoch": 3.7227130977130978, "percentage": 18.61, "elapsed_time": "0:20:42", "remaining_time": "1:30:33", "throughput": 1038.53, "total_tokens": 1290528} {"current_steps": 14330, "total_steps": 76960, "loss": 0.2549, "lr": 4.887711206643021e-05, "epoch": 3.724012474012474, "percentage": 18.62, "elapsed_time": "0:20:43", "remaining_time": "1:30:32", "throughput": 1038.53, "total_tokens": 1290960} {"current_steps": 14335, "total_steps": 76960, "loss": 0.2645, "lr": 4.887543135957865e-05, "epoch": 3.7253118503118503, "percentage": 18.63, "elapsed_time": "0:20:43", "remaining_time": "1:30:32", "throughput": 1038.51, "total_tokens": 1291376} {"current_steps": 14340, "total_steps": 76960, "loss": 0.258, "lr": 4.887374942479079e-05, "epoch": 3.726611226611227, "percentage": 18.63, "elapsed_time": "0:20:43", "remaining_time": "1:30:31", "throughput": 1038.51, "total_tokens": 1291808} {"current_steps": 14345, "total_steps": 76960, "loss": 0.2256, "lr": 4.887206626215312e-05, "epoch": 3.727910602910603, "percentage": 18.64, "elapsed_time": "0:20:44", "remaining_time": "1:30:31", "throughput": 1038.56, "total_tokens": 1292304} {"current_steps": 14350, "total_steps": 76960, "loss": 0.2168, "lr": 4.887038187175221e-05, "epoch": 3.7292099792099793, "percentage": 18.65, "elapsed_time": "0:20:44", "remaining_time": "1:30:30", "throughput": 1038.58, "total_tokens": 1292768} {"current_steps": 14355, "total_steps": 76960, "loss": 0.362, "lr": 4.886869625367468e-05, "epoch": 3.7305093555093554, "percentage": 18.65, "elapsed_time": "0:20:45", "remaining_time": "1:30:30", "throughput": 1038.62, "total_tokens": 1293248} {"current_steps": 14360, "total_steps": 76960, "loss": 0.2563, "lr": 4.886700940800725e-05, "epoch": 3.731808731808732, "percentage": 18.66, "elapsed_time": "0:20:45", "remaining_time": "1:30:29", "throughput": 1038.65, "total_tokens": 1293728} {"current_steps": 14365, "total_steps": 76960, "loss": 0.3208, "lr": 4.886532133483664e-05, "epoch": 3.733108108108108, "percentage": 18.67, "elapsed_time": "0:20:45", "remaining_time": "1:30:29", "throughput": 1038.67, "total_tokens": 1294176} {"current_steps": 14370, "total_steps": 76960, "loss": 0.1995, "lr": 4.8863632034249694e-05, "epoch": 3.7344074844074844, "percentage": 18.67, "elapsed_time": "0:20:46", "remaining_time": "1:30:28", "throughput": 1038.68, "total_tokens": 1294624} {"current_steps": 14375, "total_steps": 76960, "loss": 0.156, "lr": 4.886194150633328e-05, "epoch": 3.735706860706861, "percentage": 18.68, "elapsed_time": "0:20:46", "remaining_time": "1:30:28", "throughput": 1038.69, "total_tokens": 1295072} {"current_steps": 14380, "total_steps": 76960, "loss": 0.1664, "lr": 4.886024975117437e-05, "epoch": 3.737006237006237, "percentage": 18.69, "elapsed_time": "0:20:47", "remaining_time": "1:30:27", "throughput": 1038.69, "total_tokens": 1295504} {"current_steps": 14385, "total_steps": 76960, "loss": 0.2708, "lr": 4.8858556768859944e-05, "epoch": 3.7383056133056134, "percentage": 18.69, "elapsed_time": "0:20:47", "remaining_time": "1:30:27", "throughput": 1038.73, "total_tokens": 1295984} {"current_steps": 14390, "total_steps": 76960, "loss": 0.3828, "lr": 4.885686255947708e-05, "epoch": 3.73960498960499, "percentage": 18.7, "elapsed_time": "0:20:48", "remaining_time": "1:30:26", "throughput": 1038.75, "total_tokens": 1296448} {"current_steps": 14395, "total_steps": 76960, "loss": 0.2143, "lr": 4.8855167123112914e-05, "epoch": 3.740904365904366, "percentage": 18.7, "elapsed_time": "0:20:48", "remaining_time": "1:30:26", "throughput": 1038.76, "total_tokens": 1296896} {"current_steps": 14400, "total_steps": 76960, "loss": 0.2567, "lr": 4.885347045985465e-05, "epoch": 3.742203742203742, "percentage": 18.71, "elapsed_time": "0:20:48", "remaining_time": "1:30:25", "throughput": 1038.76, "total_tokens": 1297328} {"current_steps": 14405, "total_steps": 76960, "loss": 0.1734, "lr": 4.8851772569789545e-05, "epoch": 3.7435031185031185, "percentage": 18.72, "elapsed_time": "0:20:49", "remaining_time": "1:30:25", "throughput": 1038.75, "total_tokens": 1297744} {"current_steps": 14410, "total_steps": 76960, "loss": 0.1175, "lr": 4.885007345300492e-05, "epoch": 3.744802494802495, "percentage": 18.72, "elapsed_time": "0:20:49", "remaining_time": "1:30:24", "throughput": 1038.73, "total_tokens": 1298160} {"current_steps": 14415, "total_steps": 76960, "loss": 0.3417, "lr": 4.884837310958817e-05, "epoch": 3.746101871101871, "percentage": 18.73, "elapsed_time": "0:20:50", "remaining_time": "1:30:24", "throughput": 1038.73, "total_tokens": 1298592} {"current_steps": 14420, "total_steps": 76960, "loss": 0.2112, "lr": 4.8846671539626735e-05, "epoch": 3.7474012474012475, "percentage": 18.74, "elapsed_time": "0:20:50", "remaining_time": "1:30:23", "throughput": 1038.74, "total_tokens": 1299040} {"current_steps": 14425, "total_steps": 76960, "loss": 0.2165, "lr": 4.8844968743208144e-05, "epoch": 3.748700623700624, "percentage": 18.74, "elapsed_time": "0:20:51", "remaining_time": "1:30:23", "throughput": 1038.78, "total_tokens": 1299520} {"current_steps": 14430, "total_steps": 76960, "loss": 0.3505, "lr": 4.884326472041995e-05, "epoch": 3.75, "percentage": 18.75, "elapsed_time": "0:20:51", "remaining_time": "1:30:22", "throughput": 1038.82, "total_tokens": 1300000} {"current_steps": 14435, "total_steps": 76960, "loss": 0.2722, "lr": 4.884155947134982e-05, "epoch": 3.751299376299376, "percentage": 18.76, "elapsed_time": "0:20:51", "remaining_time": "1:30:22", "throughput": 1038.84, "total_tokens": 1300464} {"current_steps": 14440, "total_steps": 76960, "loss": 0.1739, "lr": 4.883985299608543e-05, "epoch": 3.7525987525987525, "percentage": 18.76, "elapsed_time": "0:20:52", "remaining_time": "1:30:21", "throughput": 1038.82, "total_tokens": 1300880} {"current_steps": 14445, "total_steps": 76960, "loss": 0.299, "lr": 4.883814529471457e-05, "epoch": 3.753898128898129, "percentage": 18.77, "elapsed_time": "0:20:52", "remaining_time": "1:30:21", "throughput": 1038.82, "total_tokens": 1301312} {"current_steps": 14450, "total_steps": 76960, "loss": 0.3433, "lr": 4.8836436367325044e-05, "epoch": 3.755197505197505, "percentage": 18.78, "elapsed_time": "0:20:53", "remaining_time": "1:30:20", "throughput": 1038.82, "total_tokens": 1301744} {"current_steps": 14455, "total_steps": 76960, "loss": 0.3457, "lr": 4.8834726214004764e-05, "epoch": 3.7564968814968815, "percentage": 18.78, "elapsed_time": "0:20:53", "remaining_time": "1:30:20", "throughput": 1038.83, "total_tokens": 1302192} {"current_steps": 14460, "total_steps": 76960, "loss": 0.2664, "lr": 4.883301483484167e-05, "epoch": 3.757796257796258, "percentage": 18.79, "elapsed_time": "0:20:53", "remaining_time": "1:30:19", "throughput": 1038.86, "total_tokens": 1302656} {"current_steps": 14465, "total_steps": 76960, "loss": 0.2772, "lr": 4.88313022299238e-05, "epoch": 3.759095634095634, "percentage": 18.8, "elapsed_time": "0:20:54", "remaining_time": "1:30:19", "throughput": 1038.84, "total_tokens": 1303072} {"current_steps": 14470, "total_steps": 76960, "loss": 0.2806, "lr": 4.882958839933921e-05, "epoch": 3.76039501039501, "percentage": 18.8, "elapsed_time": "0:20:54", "remaining_time": "1:30:18", "throughput": 1038.85, "total_tokens": 1303520} {"current_steps": 14475, "total_steps": 76960, "loss": 0.2233, "lr": 4.882787334317607e-05, "epoch": 3.7616943866943866, "percentage": 18.81, "elapsed_time": "0:20:55", "remaining_time": "1:30:18", "throughput": 1038.85, "total_tokens": 1303952} {"current_steps": 14480, "total_steps": 76960, "loss": 0.2674, "lr": 4.882615706152256e-05, "epoch": 3.762993762993763, "percentage": 18.81, "elapsed_time": "0:20:55", "remaining_time": "1:30:17", "throughput": 1038.86, "total_tokens": 1304400} {"current_steps": 14485, "total_steps": 76960, "loss": 0.347, "lr": 4.8824439554466974e-05, "epoch": 3.764293139293139, "percentage": 18.82, "elapsed_time": "0:20:56", "remaining_time": "1:30:17", "throughput": 1038.87, "total_tokens": 1304848} {"current_steps": 14490, "total_steps": 76960, "loss": 0.2409, "lr": 4.882272082209762e-05, "epoch": 3.7655925155925156, "percentage": 18.83, "elapsed_time": "0:20:56", "remaining_time": "1:30:16", "throughput": 1038.91, "total_tokens": 1305328} {"current_steps": 14495, "total_steps": 76960, "loss": 0.3304, "lr": 4.882100086450292e-05, "epoch": 3.766891891891892, "percentage": 18.83, "elapsed_time": "0:20:56", "remaining_time": "1:30:16", "throughput": 1038.9, "total_tokens": 1305744} {"current_steps": 14500, "total_steps": 76960, "loss": 0.203, "lr": 4.881927968177132e-05, "epoch": 3.768191268191268, "percentage": 18.84, "elapsed_time": "0:20:57", "remaining_time": "1:30:15", "throughput": 1038.92, "total_tokens": 1306208} {"current_steps": 14505, "total_steps": 76960, "loss": 0.1948, "lr": 4.881755727399134e-05, "epoch": 3.7694906444906446, "percentage": 18.85, "elapsed_time": "0:20:57", "remaining_time": "1:30:15", "throughput": 1038.93, "total_tokens": 1306656} {"current_steps": 14510, "total_steps": 76960, "loss": 0.1752, "lr": 4.881583364125157e-05, "epoch": 3.7707900207900207, "percentage": 18.85, "elapsed_time": "0:20:58", "remaining_time": "1:30:14", "throughput": 1038.94, "total_tokens": 1307104} {"current_steps": 14515, "total_steps": 76960, "loss": 0.2727, "lr": 4.8814108783640655e-05, "epoch": 3.772089397089397, "percentage": 18.86, "elapsed_time": "0:20:58", "remaining_time": "1:30:14", "throughput": 1038.97, "total_tokens": 1307568} {"current_steps": 14520, "total_steps": 76960, "loss": 0.3152, "lr": 4.881238270124731e-05, "epoch": 3.773388773388773, "percentage": 18.87, "elapsed_time": "0:20:58", "remaining_time": "1:30:13", "throughput": 1038.99, "total_tokens": 1308032} {"current_steps": 14525, "total_steps": 76960, "loss": 0.387, "lr": 4.881065539416031e-05, "epoch": 3.7746881496881497, "percentage": 18.87, "elapsed_time": "0:20:59", "remaining_time": "1:30:13", "throughput": 1039.01, "total_tokens": 1308496} {"current_steps": 14530, "total_steps": 76960, "loss": 0.2625, "lr": 4.880892686246849e-05, "epoch": 3.775987525987526, "percentage": 18.88, "elapsed_time": "0:20:59", "remaining_time": "1:30:12", "throughput": 1039.01, "total_tokens": 1308928} {"current_steps": 14535, "total_steps": 76960, "loss": 0.2716, "lr": 4.880719710626074e-05, "epoch": 3.7772869022869022, "percentage": 18.89, "elapsed_time": "0:21:00", "remaining_time": "1:30:12", "throughput": 1039.03, "total_tokens": 1309392} {"current_steps": 14540, "total_steps": 76960, "loss": 0.2752, "lr": 4.880546612562603e-05, "epoch": 3.7785862785862787, "percentage": 18.89, "elapsed_time": "0:21:00", "remaining_time": "1:30:11", "throughput": 1039.03, "total_tokens": 1309824} {"current_steps": 14545, "total_steps": 76960, "loss": 0.2197, "lr": 4.88037339206534e-05, "epoch": 3.7798856548856548, "percentage": 18.9, "elapsed_time": "0:21:01", "remaining_time": "1:30:11", "throughput": 1039.05, "total_tokens": 1310288} {"current_steps": 14550, "total_steps": 76960, "loss": 0.2613, "lr": 4.880200049143191e-05, "epoch": 3.7811850311850312, "percentage": 18.91, "elapsed_time": "0:21:01", "remaining_time": "1:30:10", "throughput": 1039.07, "total_tokens": 1310752} {"current_steps": 14555, "total_steps": 76960, "loss": 0.2521, "lr": 4.880026583805074e-05, "epoch": 3.7824844074844073, "percentage": 18.91, "elapsed_time": "0:21:01", "remaining_time": "1:30:10", "throughput": 1039.07, "total_tokens": 1311184} {"current_steps": 14560, "total_steps": 76960, "loss": 0.2974, "lr": 4.8798529960599096e-05, "epoch": 3.7837837837837838, "percentage": 18.92, "elapsed_time": "0:21:02", "remaining_time": "1:30:09", "throughput": 1039.07, "total_tokens": 1311616} {"current_steps": 14565, "total_steps": 76960, "loss": 0.2249, "lr": 4.879679285916625e-05, "epoch": 3.7850831600831603, "percentage": 18.93, "elapsed_time": "0:21:02", "remaining_time": "1:30:09", "throughput": 1039.09, "total_tokens": 1312080} {"current_steps": 14570, "total_steps": 76960, "loss": 0.2963, "lr": 4.879505453384154e-05, "epoch": 3.7863825363825363, "percentage": 18.93, "elapsed_time": "0:21:03", "remaining_time": "1:30:08", "throughput": 1039.09, "total_tokens": 1312512} {"current_steps": 14575, "total_steps": 76960, "loss": 0.2941, "lr": 4.879331498471439e-05, "epoch": 3.787681912681913, "percentage": 18.94, "elapsed_time": "0:21:03", "remaining_time": "1:30:08", "throughput": 1039.09, "total_tokens": 1312944} {"current_steps": 14580, "total_steps": 76960, "loss": 0.3193, "lr": 4.8791574211874244e-05, "epoch": 3.788981288981289, "percentage": 18.94, "elapsed_time": "0:21:03", "remaining_time": "1:30:07", "throughput": 1039.09, "total_tokens": 1313376} {"current_steps": 14585, "total_steps": 76960, "loss": 0.2697, "lr": 4.878983221541064e-05, "epoch": 3.7902806652806653, "percentage": 18.95, "elapsed_time": "0:21:04", "remaining_time": "1:30:07", "throughput": 1039.1, "total_tokens": 1313824} {"current_steps": 14590, "total_steps": 76960, "loss": 0.2473, "lr": 4.878808899541317e-05, "epoch": 3.7915800415800414, "percentage": 18.96, "elapsed_time": "0:21:04", "remaining_time": "1:30:06", "throughput": 1039.09, "total_tokens": 1314256} {"current_steps": 14595, "total_steps": 76960, "loss": 0.2822, "lr": 4.87863445519715e-05, "epoch": 3.792879417879418, "percentage": 18.96, "elapsed_time": "0:21:05", "remaining_time": "1:30:06", "throughput": 1039.1, "total_tokens": 1314704} {"current_steps": 14600, "total_steps": 76960, "loss": 0.2652, "lr": 4.8784598885175324e-05, "epoch": 3.7941787941787943, "percentage": 18.97, "elapsed_time": "0:21:05", "remaining_time": "1:30:05", "throughput": 1039.1, "total_tokens": 1315136} {"current_steps": 14605, "total_steps": 76960, "loss": 0.2204, "lr": 4.8782851995114455e-05, "epoch": 3.7954781704781704, "percentage": 18.98, "elapsed_time": "0:21:06", "remaining_time": "1:30:05", "throughput": 1039.13, "total_tokens": 1315600} {"current_steps": 14610, "total_steps": 76960, "loss": 0.1691, "lr": 4.878110388187871e-05, "epoch": 3.796777546777547, "percentage": 18.98, "elapsed_time": "0:21:06", "remaining_time": "1:30:04", "throughput": 1039.15, "total_tokens": 1316064} {"current_steps": 14615, "total_steps": 76960, "loss": 0.2125, "lr": 4.8779354545558e-05, "epoch": 3.7980769230769234, "percentage": 18.99, "elapsed_time": "0:21:06", "remaining_time": "1:30:04", "throughput": 1039.15, "total_tokens": 1316496} {"current_steps": 14620, "total_steps": 76960, "loss": 0.244, "lr": 4.877760398624232e-05, "epoch": 3.7993762993762994, "percentage": 19.0, "elapsed_time": "0:21:07", "remaining_time": "1:30:03", "throughput": 1039.16, "total_tokens": 1316944} {"current_steps": 14625, "total_steps": 76960, "loss": 0.2768, "lr": 4.8775852204021665e-05, "epoch": 3.8006756756756754, "percentage": 19.0, "elapsed_time": "0:21:07", "remaining_time": "1:30:03", "throughput": 1039.15, "total_tokens": 1317360} {"current_steps": 14630, "total_steps": 76960, "loss": 0.3197, "lr": 4.8774099198986154e-05, "epoch": 3.801975051975052, "percentage": 19.01, "elapsed_time": "0:21:08", "remaining_time": "1:30:02", "throughput": 1039.13, "total_tokens": 1317776} {"current_steps": 14635, "total_steps": 76960, "loss": 0.2667, "lr": 4.877234497122595e-05, "epoch": 3.8032744282744284, "percentage": 19.02, "elapsed_time": "0:21:08", "remaining_time": "1:30:02", "throughput": 1039.13, "total_tokens": 1318208} {"current_steps": 14640, "total_steps": 76960, "loss": 0.2852, "lr": 4.877058952083126e-05, "epoch": 3.8045738045738045, "percentage": 19.02, "elapsed_time": "0:21:08", "remaining_time": "1:30:01", "throughput": 1039.15, "total_tokens": 1318672} {"current_steps": 14645, "total_steps": 76960, "loss": 0.2864, "lr": 4.8768832847892375e-05, "epoch": 3.805873180873181, "percentage": 19.03, "elapsed_time": "0:21:09", "remaining_time": "1:30:01", "throughput": 1039.15, "total_tokens": 1319104} {"current_steps": 14650, "total_steps": 76960, "loss": 0.2465, "lr": 4.876707495249965e-05, "epoch": 3.8071725571725574, "percentage": 19.04, "elapsed_time": "0:21:09", "remaining_time": "1:30:00", "throughput": 1039.16, "total_tokens": 1319552} {"current_steps": 14655, "total_steps": 76960, "loss": 0.2304, "lr": 4.876531583474349e-05, "epoch": 3.8084719334719335, "percentage": 19.04, "elapsed_time": "0:21:10", "remaining_time": "1:30:00", "throughput": 1039.19, "total_tokens": 1320016} {"current_steps": 14660, "total_steps": 76960, "loss": 0.2775, "lr": 4.8763555494714355e-05, "epoch": 3.8097713097713095, "percentage": 19.05, "elapsed_time": "0:21:10", "remaining_time": "1:29:59", "throughput": 1039.22, "total_tokens": 1320480} {"current_steps": 14665, "total_steps": 76960, "loss": 0.2464, "lr": 4.876179393250279e-05, "epoch": 3.811070686070686, "percentage": 19.06, "elapsed_time": "0:21:11", "remaining_time": "1:29:59", "throughput": 1039.24, "total_tokens": 1320944} {"current_steps": 14670, "total_steps": 76960, "loss": 0.3052, "lr": 4.8760031148199404e-05, "epoch": 3.8123700623700625, "percentage": 19.06, "elapsed_time": "0:21:11", "remaining_time": "1:29:58", "throughput": 1039.27, "total_tokens": 1321424} {"current_steps": 14675, "total_steps": 76960, "loss": 0.268, "lr": 4.8758267141894844e-05, "epoch": 3.8136694386694385, "percentage": 19.07, "elapsed_time": "0:21:11", "remaining_time": "1:29:58", "throughput": 1039.27, "total_tokens": 1321856} {"current_steps": 14680, "total_steps": 76960, "loss": 0.2546, "lr": 4.875650191367984e-05, "epoch": 3.814968814968815, "percentage": 19.07, "elapsed_time": "0:21:12", "remaining_time": "1:29:57", "throughput": 1039.26, "total_tokens": 1322272} {"current_steps": 14685, "total_steps": 76960, "loss": 0.198, "lr": 4.875473546364519e-05, "epoch": 3.8162681912681915, "percentage": 19.08, "elapsed_time": "0:21:12", "remaining_time": "1:29:57", "throughput": 1039.28, "total_tokens": 1322736} {"current_steps": 14690, "total_steps": 76960, "loss": 0.1887, "lr": 4.875296779188173e-05, "epoch": 3.8175675675675675, "percentage": 19.09, "elapsed_time": "0:21:13", "remaining_time": "1:29:56", "throughput": 1039.3, "total_tokens": 1323200} {"current_steps": 14695, "total_steps": 76960, "loss": 0.3513, "lr": 4.8751198898480376e-05, "epoch": 3.818866943866944, "percentage": 19.09, "elapsed_time": "0:21:13", "remaining_time": "1:29:56", "throughput": 1039.31, "total_tokens": 1323648} {"current_steps": 14700, "total_steps": 76960, "loss": 0.2187, "lr": 4.87494287835321e-05, "epoch": 3.82016632016632, "percentage": 19.1, "elapsed_time": "0:21:13", "remaining_time": "1:29:55", "throughput": 1039.34, "total_tokens": 1324112} {"current_steps": 14705, "total_steps": 76960, "loss": 0.3052, "lr": 4.874765744712796e-05, "epoch": 3.8214656964656966, "percentage": 19.11, "elapsed_time": "0:21:14", "remaining_time": "1:29:55", "throughput": 1039.36, "total_tokens": 1324576} {"current_steps": 14710, "total_steps": 76960, "loss": 0.3032, "lr": 4.874588488935903e-05, "epoch": 3.8227650727650726, "percentage": 19.11, "elapsed_time": "0:21:14", "remaining_time": "1:29:54", "throughput": 1039.38, "total_tokens": 1325040} {"current_steps": 14715, "total_steps": 76960, "loss": 0.2635, "lr": 4.874411111031649e-05, "epoch": 3.824064449064449, "percentage": 19.12, "elapsed_time": "0:21:15", "remaining_time": "1:29:54", "throughput": 1039.38, "total_tokens": 1325472} {"current_steps": 14720, "total_steps": 76960, "loss": 0.2846, "lr": 4.874233611009157e-05, "epoch": 3.8253638253638256, "percentage": 19.13, "elapsed_time": "0:21:15", "remaining_time": "1:29:53", "throughput": 1039.39, "total_tokens": 1325920} {"current_steps": 14725, "total_steps": 76960, "loss": 0.2737, "lr": 4.874055988877556e-05, "epoch": 3.8266632016632016, "percentage": 19.13, "elapsed_time": "0:21:16", "remaining_time": "1:29:53", "throughput": 1039.4, "total_tokens": 1326368} {"current_steps": 14730, "total_steps": 76960, "loss": 0.2823, "lr": 4.87387824464598e-05, "epoch": 3.827962577962578, "percentage": 19.14, "elapsed_time": "0:21:16", "remaining_time": "1:29:52", "throughput": 1039.45, "total_tokens": 1326864} {"current_steps": 14735, "total_steps": 76960, "loss": 0.2613, "lr": 4.873700378323571e-05, "epoch": 3.829261954261954, "percentage": 19.15, "elapsed_time": "0:21:16", "remaining_time": "1:29:52", "throughput": 1039.45, "total_tokens": 1327296} {"current_steps": 14740, "total_steps": 76960, "loss": 0.2391, "lr": 4.873522389919478e-05, "epoch": 3.8305613305613306, "percentage": 19.15, "elapsed_time": "0:21:17", "remaining_time": "1:29:51", "throughput": 1039.48, "total_tokens": 1327776} {"current_steps": 14745, "total_steps": 76960, "loss": 0.2588, "lr": 4.8733442794428533e-05, "epoch": 3.8318607068607067, "percentage": 19.16, "elapsed_time": "0:21:17", "remaining_time": "1:29:51", "throughput": 1039.48, "total_tokens": 1328208} {"current_steps": 14750, "total_steps": 76960, "loss": 0.3393, "lr": 4.873166046902859e-05, "epoch": 3.833160083160083, "percentage": 19.17, "elapsed_time": "0:21:18", "remaining_time": "1:29:50", "throughput": 1039.49, "total_tokens": 1328656} {"current_steps": 14755, "total_steps": 76960, "loss": 0.2298, "lr": 4.872987692308661e-05, "epoch": 3.8344594594594597, "percentage": 19.17, "elapsed_time": "0:21:18", "remaining_time": "1:29:50", "throughput": 1039.48, "total_tokens": 1329072} {"current_steps": 14760, "total_steps": 76960, "loss": 0.2597, "lr": 4.872809215669432e-05, "epoch": 3.8357588357588357, "percentage": 19.18, "elapsed_time": "0:21:19", "remaining_time": "1:29:49", "throughput": 1039.49, "total_tokens": 1329520} {"current_steps": 14765, "total_steps": 76960, "loss": 0.2601, "lr": 4.872630616994352e-05, "epoch": 3.837058212058212, "percentage": 19.19, "elapsed_time": "0:21:19", "remaining_time": "1:29:49", "throughput": 1039.5, "total_tokens": 1329968} {"current_steps": 14770, "total_steps": 76960, "loss": 0.3156, "lr": 4.8724518962926055e-05, "epoch": 3.8383575883575882, "percentage": 19.19, "elapsed_time": "0:21:19", "remaining_time": "1:29:48", "throughput": 1039.55, "total_tokens": 1330464} {"current_steps": 14775, "total_steps": 76960, "loss": 0.2482, "lr": 4.8722730535733854e-05, "epoch": 3.8396569646569647, "percentage": 19.2, "elapsed_time": "0:21:20", "remaining_time": "1:29:48", "throughput": 1039.54, "total_tokens": 1330896} {"current_steps": 14780, "total_steps": 76960, "loss": 0.2642, "lr": 4.872094088845889e-05, "epoch": 3.8409563409563408, "percentage": 19.2, "elapsed_time": "0:21:20", "remaining_time": "1:29:47", "throughput": 1039.59, "total_tokens": 1331392} {"current_steps": 14785, "total_steps": 76960, "loss": 0.2835, "lr": 4.871915002119321e-05, "epoch": 3.8422557172557172, "percentage": 19.21, "elapsed_time": "0:21:21", "remaining_time": "1:29:47", "throughput": 1039.58, "total_tokens": 1331808} {"current_steps": 14790, "total_steps": 76960, "loss": 0.3025, "lr": 4.871735793402891e-05, "epoch": 3.8435550935550937, "percentage": 19.22, "elapsed_time": "0:21:21", "remaining_time": "1:29:46", "throughput": 1039.57, "total_tokens": 1332240} {"current_steps": 14795, "total_steps": 76960, "loss": 0.3084, "lr": 4.8715564627058165e-05, "epoch": 3.8448544698544698, "percentage": 19.22, "elapsed_time": "0:21:21", "remaining_time": "1:29:46", "throughput": 1039.58, "total_tokens": 1332688} {"current_steps": 14800, "total_steps": 76960, "loss": 0.283, "lr": 4.8713770100373213e-05, "epoch": 3.8461538461538463, "percentage": 19.23, "elapsed_time": "0:21:22", "remaining_time": "1:29:45", "throughput": 1039.59, "total_tokens": 1333136} {"current_steps": 14805, "total_steps": 76960, "loss": 0.2852, "lr": 4.8711974354066344e-05, "epoch": 3.8474532224532223, "percentage": 19.24, "elapsed_time": "0:21:22", "remaining_time": "1:29:45", "throughput": 1039.58, "total_tokens": 1333552} {"current_steps": 14810, "total_steps": 76960, "loss": 0.2639, "lr": 4.871017738822992e-05, "epoch": 3.848752598752599, "percentage": 19.24, "elapsed_time": "0:21:23", "remaining_time": "1:29:44", "throughput": 1039.6, "total_tokens": 1334016} {"current_steps": 14815, "total_steps": 76960, "loss": 0.2199, "lr": 4.870837920295634e-05, "epoch": 3.850051975051975, "percentage": 19.25, "elapsed_time": "0:21:23", "remaining_time": "1:29:44", "throughput": 1039.64, "total_tokens": 1334496} {"current_steps": 14820, "total_steps": 76960, "loss": 0.2235, "lr": 4.8706579798338116e-05, "epoch": 3.8513513513513513, "percentage": 19.26, "elapsed_time": "0:21:24", "remaining_time": "1:29:43", "throughput": 1039.65, "total_tokens": 1334944} {"current_steps": 14825, "total_steps": 76960, "loss": 0.287, "lr": 4.870477917446777e-05, "epoch": 3.852650727650728, "percentage": 19.26, "elapsed_time": "0:21:24", "remaining_time": "1:29:43", "throughput": 1039.66, "total_tokens": 1335392} {"current_steps": 14830, "total_steps": 76960, "loss": 0.2493, "lr": 4.870297733143793e-05, "epoch": 3.853950103950104, "percentage": 19.27, "elapsed_time": "0:21:24", "remaining_time": "1:29:42", "throughput": 1039.66, "total_tokens": 1335824} {"current_steps": 14835, "total_steps": 76960, "loss": 0.3001, "lr": 4.870117426934124e-05, "epoch": 3.8552494802494803, "percentage": 19.28, "elapsed_time": "0:21:25", "remaining_time": "1:29:42", "throughput": 1039.67, "total_tokens": 1336272} {"current_steps": 14840, "total_steps": 76960, "loss": 0.246, "lr": 4.869936998827045e-05, "epoch": 3.856548856548857, "percentage": 19.28, "elapsed_time": "0:21:25", "remaining_time": "1:29:41", "throughput": 1039.69, "total_tokens": 1336736} {"current_steps": 14845, "total_steps": 76960, "loss": 0.2694, "lr": 4.869756448831836e-05, "epoch": 3.857848232848233, "percentage": 19.29, "elapsed_time": "0:21:26", "remaining_time": "1:29:41", "throughput": 1039.73, "total_tokens": 1337216} {"current_steps": 14850, "total_steps": 76960, "loss": 0.2893, "lr": 4.869575776957782e-05, "epoch": 3.859147609147609, "percentage": 19.3, "elapsed_time": "0:21:26", "remaining_time": "1:29:40", "throughput": 1039.74, "total_tokens": 1337664} {"current_steps": 14855, "total_steps": 76960, "loss": 0.2696, "lr": 4.869394983214175e-05, "epoch": 3.8604469854469854, "percentage": 19.3, "elapsed_time": "0:21:26", "remaining_time": "1:29:40", "throughput": 1039.72, "total_tokens": 1338080} {"current_steps": 14860, "total_steps": 76960, "loss": 0.3017, "lr": 4.8692140676103146e-05, "epoch": 3.861746361746362, "percentage": 19.31, "elapsed_time": "0:21:27", "remaining_time": "1:29:39", "throughput": 1039.72, "total_tokens": 1338512} {"current_steps": 14865, "total_steps": 76960, "loss": 0.2808, "lr": 4.8690330301555045e-05, "epoch": 3.863045738045738, "percentage": 19.32, "elapsed_time": "0:21:27", "remaining_time": "1:29:39", "throughput": 1039.7, "total_tokens": 1338928} {"current_steps": 14870, "total_steps": 76960, "loss": 0.2953, "lr": 4.8688518708590544e-05, "epoch": 3.8643451143451144, "percentage": 19.32, "elapsed_time": "0:21:28", "remaining_time": "1:29:38", "throughput": 1039.71, "total_tokens": 1339376} {"current_steps": 14875, "total_steps": 76960, "loss": 0.3172, "lr": 4.8686705897302845e-05, "epoch": 3.865644490644491, "percentage": 19.33, "elapsed_time": "0:21:28", "remaining_time": "1:29:38", "throughput": 1039.7, "total_tokens": 1339792} {"current_steps": 14880, "total_steps": 76960, "loss": 0.2586, "lr": 4.868489186778516e-05, "epoch": 3.866943866943867, "percentage": 19.33, "elapsed_time": "0:21:29", "remaining_time": "1:29:37", "throughput": 1039.71, "total_tokens": 1340240} {"current_steps": 14885, "total_steps": 76960, "loss": 0.2949, "lr": 4.8683076620130794e-05, "epoch": 3.868243243243243, "percentage": 19.34, "elapsed_time": "0:21:29", "remaining_time": "1:29:37", "throughput": 1039.73, "total_tokens": 1340704} {"current_steps": 14890, "total_steps": 76960, "loss": 0.2847, "lr": 4.86812601544331e-05, "epoch": 3.8695426195426195, "percentage": 19.35, "elapsed_time": "0:21:29", "remaining_time": "1:29:36", "throughput": 1039.74, "total_tokens": 1341152} {"current_steps": 14895, "total_steps": 76960, "loss": 0.3298, "lr": 4.867944247078551e-05, "epoch": 3.870841995841996, "percentage": 19.35, "elapsed_time": "0:21:30", "remaining_time": "1:29:36", "throughput": 1039.74, "total_tokens": 1341584} {"current_steps": 14900, "total_steps": 76960, "loss": 0.2955, "lr": 4.8677623569281505e-05, "epoch": 3.872141372141372, "percentage": 19.36, "elapsed_time": "0:21:30", "remaining_time": "1:29:36", "throughput": 1039.76, "total_tokens": 1342048} {"current_steps": 14905, "total_steps": 76960, "loss": 0.3004, "lr": 4.867580345001463e-05, "epoch": 3.8734407484407485, "percentage": 19.37, "elapsed_time": "0:21:31", "remaining_time": "1:29:35", "throughput": 1039.78, "total_tokens": 1342512} {"current_steps": 14910, "total_steps": 76960, "loss": 0.281, "lr": 4.867398211307851e-05, "epoch": 3.874740124740125, "percentage": 19.37, "elapsed_time": "0:21:31", "remaining_time": "1:29:35", "throughput": 1039.82, "total_tokens": 1342992} {"current_steps": 14915, "total_steps": 76960, "loss": 0.2658, "lr": 4.8672159558566796e-05, "epoch": 3.876039501039501, "percentage": 19.38, "elapsed_time": "0:21:31", "remaining_time": "1:29:34", "throughput": 1039.83, "total_tokens": 1343440} {"current_steps": 14920, "total_steps": 76960, "loss": 0.2907, "lr": 4.8670335786573236e-05, "epoch": 3.8773388773388775, "percentage": 19.39, "elapsed_time": "0:21:32", "remaining_time": "1:29:34", "throughput": 1039.85, "total_tokens": 1343904} {"current_steps": 14925, "total_steps": 76960, "loss": 0.2858, "lr": 4.866851079719162e-05, "epoch": 3.8786382536382535, "percentage": 19.39, "elapsed_time": "0:21:32", "remaining_time": "1:29:33", "throughput": 1039.89, "total_tokens": 1344384} {"current_steps": 14930, "total_steps": 76960, "loss": 0.2279, "lr": 4.866668459051583e-05, "epoch": 3.87993762993763, "percentage": 19.4, "elapsed_time": "0:21:33", "remaining_time": "1:29:33", "throughput": 1039.87, "total_tokens": 1344800} {"current_steps": 14935, "total_steps": 76960, "loss": 0.279, "lr": 4.8664857166639764e-05, "epoch": 3.881237006237006, "percentage": 19.41, "elapsed_time": "0:21:33", "remaining_time": "1:29:32", "throughput": 1039.88, "total_tokens": 1345248} {"current_steps": 14940, "total_steps": 76960, "loss": 0.1546, "lr": 4.866302852565743e-05, "epoch": 3.8825363825363826, "percentage": 19.41, "elapsed_time": "0:21:34", "remaining_time": "1:29:32", "throughput": 1039.89, "total_tokens": 1345696} {"current_steps": 14945, "total_steps": 76960, "loss": 0.2327, "lr": 4.8661198667662854e-05, "epoch": 3.883835758835759, "percentage": 19.42, "elapsed_time": "0:21:34", "remaining_time": "1:29:31", "throughput": 1039.9, "total_tokens": 1346144} {"current_steps": 14950, "total_steps": 76960, "loss": 0.2246, "lr": 4.865936759275017e-05, "epoch": 3.885135135135135, "percentage": 19.43, "elapsed_time": "0:21:34", "remaining_time": "1:29:31", "throughput": 1039.92, "total_tokens": 1346608} {"current_steps": 14955, "total_steps": 76960, "loss": 0.1547, "lr": 4.8657535301013536e-05, "epoch": 3.8864345114345116, "percentage": 19.43, "elapsed_time": "0:21:35", "remaining_time": "1:29:30", "throughput": 1039.96, "total_tokens": 1347088} {"current_steps": 14960, "total_steps": 76960, "loss": 0.2937, "lr": 4.865570179254719e-05, "epoch": 3.8877338877338876, "percentage": 19.44, "elapsed_time": "0:21:35", "remaining_time": "1:29:30", "throughput": 1039.99, "total_tokens": 1347568} {"current_steps": 14965, "total_steps": 76960, "loss": 0.1543, "lr": 4.865386706744544e-05, "epoch": 3.889033264033264, "percentage": 19.45, "elapsed_time": "0:21:36", "remaining_time": "1:29:29", "throughput": 1040.01, "total_tokens": 1348032} {"current_steps": 14970, "total_steps": 76960, "loss": 0.3336, "lr": 4.865203112580265e-05, "epoch": 3.89033264033264, "percentage": 19.45, "elapsed_time": "0:21:36", "remaining_time": "1:29:29", "throughput": 1040.04, "total_tokens": 1348496} {"current_steps": 14975, "total_steps": 76960, "loss": 0.2925, "lr": 4.865019396771322e-05, "epoch": 3.8916320166320166, "percentage": 19.46, "elapsed_time": "0:21:37", "remaining_time": "1:29:28", "throughput": 1040.06, "total_tokens": 1348960} {"current_steps": 14980, "total_steps": 76960, "loss": 0.3069, "lr": 4.8648355593271665e-05, "epoch": 3.892931392931393, "percentage": 19.46, "elapsed_time": "0:21:37", "remaining_time": "1:29:28", "throughput": 1040.11, "total_tokens": 1349456} {"current_steps": 14985, "total_steps": 76960, "loss": 0.2873, "lr": 4.864651600257252e-05, "epoch": 3.894230769230769, "percentage": 19.47, "elapsed_time": "0:21:37", "remaining_time": "1:29:27", "throughput": 1040.17, "total_tokens": 1349968} {"current_steps": 14990, "total_steps": 76960, "loss": 0.2335, "lr": 4.86446751957104e-05, "epoch": 3.8955301455301456, "percentage": 19.48, "elapsed_time": "0:21:38", "remaining_time": "1:29:27", "throughput": 1040.16, "total_tokens": 1350400} {"current_steps": 14995, "total_steps": 76960, "loss": 0.2385, "lr": 4.864283317277998e-05, "epoch": 3.8968295218295217, "percentage": 19.48, "elapsed_time": "0:21:38", "remaining_time": "1:29:26", "throughput": 1040.19, "total_tokens": 1350864} {"current_steps": 15000, "total_steps": 76960, "loss": 0.2556, "lr": 4.8640989933876e-05, "epoch": 3.898128898128898, "percentage": 19.49, "elapsed_time": "0:21:39", "remaining_time": "1:29:26", "throughput": 1040.19, "total_tokens": 1351296} {"current_steps": 15005, "total_steps": 76960, "loss": 0.3135, "lr": 4.863914547909325e-05, "epoch": 3.899428274428274, "percentage": 19.5, "elapsed_time": "0:21:39", "remaining_time": "1:29:25", "throughput": 1040.18, "total_tokens": 1351728} {"current_steps": 15010, "total_steps": 76960, "loss": 0.2605, "lr": 4.8637299808526606e-05, "epoch": 3.9007276507276507, "percentage": 19.5, "elapsed_time": "0:21:39", "remaining_time": "1:29:25", "throughput": 1040.17, "total_tokens": 1352144} {"current_steps": 15015, "total_steps": 76960, "loss": 0.2252, "lr": 4.8635452922270975e-05, "epoch": 3.902027027027027, "percentage": 19.51, "elapsed_time": "0:21:40", "remaining_time": "1:29:24", "throughput": 1040.17, "total_tokens": 1352576} {"current_steps": 15020, "total_steps": 76960, "loss": 0.2953, "lr": 4.863360482042135e-05, "epoch": 3.9033264033264032, "percentage": 19.52, "elapsed_time": "0:21:40", "remaining_time": "1:29:24", "throughput": 1040.19, "total_tokens": 1353040} {"current_steps": 15025, "total_steps": 76960, "loss": 0.2771, "lr": 4.86317555030728e-05, "epoch": 3.9046257796257797, "percentage": 19.52, "elapsed_time": "0:21:41", "remaining_time": "1:29:23", "throughput": 1040.2, "total_tokens": 1353488} {"current_steps": 15030, "total_steps": 76960, "loss": 0.2109, "lr": 4.862990497032042e-05, "epoch": 3.9059251559251558, "percentage": 19.53, "elapsed_time": "0:21:41", "remaining_time": "1:29:23", "throughput": 1040.23, "total_tokens": 1353952} {"current_steps": 15035, "total_steps": 76960, "loss": 0.2649, "lr": 4.862805322225937e-05, "epoch": 3.9072245322245323, "percentage": 19.54, "elapsed_time": "0:21:42", "remaining_time": "1:29:22", "throughput": 1040.21, "total_tokens": 1354368} {"current_steps": 15040, "total_steps": 76960, "loss": 0.1926, "lr": 4.862620025898492e-05, "epoch": 3.9085239085239083, "percentage": 19.54, "elapsed_time": "0:21:42", "remaining_time": "1:29:22", "throughput": 1040.21, "total_tokens": 1354800} {"current_steps": 15045, "total_steps": 76960, "loss": 0.1691, "lr": 4.862434608059234e-05, "epoch": 3.909823284823285, "percentage": 19.55, "elapsed_time": "0:21:42", "remaining_time": "1:29:21", "throughput": 1040.21, "total_tokens": 1355232} {"current_steps": 15050, "total_steps": 76960, "loss": 0.2257, "lr": 4.862249068717702e-05, "epoch": 3.9111226611226613, "percentage": 19.56, "elapsed_time": "0:21:43", "remaining_time": "1:29:21", "throughput": 1040.22, "total_tokens": 1355680} {"current_steps": 15055, "total_steps": 76960, "loss": 0.2668, "lr": 4.862063407883436e-05, "epoch": 3.9124220374220373, "percentage": 19.56, "elapsed_time": "0:21:43", "remaining_time": "1:29:20", "throughput": 1040.21, "total_tokens": 1356112} {"current_steps": 15060, "total_steps": 76960, "loss": 0.2514, "lr": 4.861877625565986e-05, "epoch": 3.913721413721414, "percentage": 19.57, "elapsed_time": "0:21:44", "remaining_time": "1:29:20", "throughput": 1040.24, "total_tokens": 1356576} {"current_steps": 15065, "total_steps": 76960, "loss": 0.2186, "lr": 4.861691721774906e-05, "epoch": 3.9150207900207903, "percentage": 19.58, "elapsed_time": "0:21:44", "remaining_time": "1:29:19", "throughput": 1040.25, "total_tokens": 1357024} {"current_steps": 15070, "total_steps": 76960, "loss": 0.2168, "lr": 4.861505696519759e-05, "epoch": 3.9163201663201663, "percentage": 19.58, "elapsed_time": "0:21:44", "remaining_time": "1:29:19", "throughput": 1040.22, "total_tokens": 1357424} {"current_steps": 15075, "total_steps": 76960, "loss": 0.3942, "lr": 4.86131954981011e-05, "epoch": 3.9176195426195424, "percentage": 19.59, "elapsed_time": "0:21:45", "remaining_time": "1:29:18", "throughput": 1040.23, "total_tokens": 1357872} {"current_steps": 15080, "total_steps": 76960, "loss": 0.2014, "lr": 4.8611332816555354e-05, "epoch": 3.918918918918919, "percentage": 19.59, "elapsed_time": "0:21:45", "remaining_time": "1:29:18", "throughput": 1040.23, "total_tokens": 1358320} {"current_steps": 15085, "total_steps": 76960, "loss": 0.2625, "lr": 4.860946892065614e-05, "epoch": 3.9202182952182953, "percentage": 19.6, "elapsed_time": "0:21:46", "remaining_time": "1:29:17", "throughput": 1040.23, "total_tokens": 1358752} {"current_steps": 15090, "total_steps": 76960, "loss": 0.2488, "lr": 4.8607603810499305e-05, "epoch": 3.9215176715176714, "percentage": 19.61, "elapsed_time": "0:21:46", "remaining_time": "1:29:17", "throughput": 1040.24, "total_tokens": 1359200} {"current_steps": 15095, "total_steps": 76960, "loss": 0.226, "lr": 4.8605737486180793e-05, "epoch": 3.922817047817048, "percentage": 19.61, "elapsed_time": "0:21:47", "remaining_time": "1:29:16", "throughput": 1040.23, "total_tokens": 1359616} {"current_steps": 15100, "total_steps": 76960, "loss": 0.1743, "lr": 4.860386994779659e-05, "epoch": 3.9241164241164244, "percentage": 19.62, "elapsed_time": "0:21:47", "remaining_time": "1:29:16", "throughput": 1040.25, "total_tokens": 1360080} {"current_steps": 15105, "total_steps": 76960, "loss": 0.2803, "lr": 4.8602001195442725e-05, "epoch": 3.9254158004158004, "percentage": 19.63, "elapsed_time": "0:21:47", "remaining_time": "1:29:15", "throughput": 1040.3, "total_tokens": 1360576} {"current_steps": 15110, "total_steps": 76960, "loss": 0.2237, "lr": 4.8600131229215336e-05, "epoch": 3.9267151767151764, "percentage": 19.63, "elapsed_time": "0:21:48", "remaining_time": "1:29:15", "throughput": 1040.31, "total_tokens": 1361024} {"current_steps": 15115, "total_steps": 76960, "loss": 0.2866, "lr": 4.859826004921058e-05, "epoch": 3.928014553014553, "percentage": 19.64, "elapsed_time": "0:21:48", "remaining_time": "1:29:14", "throughput": 1040.36, "total_tokens": 1361520} {"current_steps": 15120, "total_steps": 76960, "loss": 0.2157, "lr": 4.85963876555247e-05, "epoch": 3.9293139293139294, "percentage": 19.65, "elapsed_time": "0:21:49", "remaining_time": "1:29:14", "throughput": 1040.34, "total_tokens": 1361936} {"current_steps": 15125, "total_steps": 76960, "loss": 0.2909, "lr": 4.859451404825399e-05, "epoch": 3.9306133056133055, "percentage": 19.65, "elapsed_time": "0:21:49", "remaining_time": "1:29:13", "throughput": 1040.36, "total_tokens": 1362400} {"current_steps": 15130, "total_steps": 76960, "loss": 0.1724, "lr": 4.859263922749482e-05, "epoch": 3.931912681912682, "percentage": 19.66, "elapsed_time": "0:21:49", "remaining_time": "1:29:13", "throughput": 1040.4, "total_tokens": 1362880} {"current_steps": 15135, "total_steps": 76960, "loss": 0.2659, "lr": 4.859076319334361e-05, "epoch": 3.9332120582120584, "percentage": 19.67, "elapsed_time": "0:21:50", "remaining_time": "1:29:12", "throughput": 1040.41, "total_tokens": 1363328} {"current_steps": 15140, "total_steps": 76960, "loss": 0.2618, "lr": 4.858888594589685e-05, "epoch": 3.9345114345114345, "percentage": 19.67, "elapsed_time": "0:21:50", "remaining_time": "1:29:12", "throughput": 1040.41, "total_tokens": 1363760} {"current_steps": 15145, "total_steps": 76960, "loss": 0.3639, "lr": 4.8587007485251074e-05, "epoch": 3.935810810810811, "percentage": 19.68, "elapsed_time": "0:21:51", "remaining_time": "1:29:11", "throughput": 1040.43, "total_tokens": 1364224} {"current_steps": 15150, "total_steps": 76960, "loss": 0.2567, "lr": 4.858512781150291e-05, "epoch": 3.937110187110187, "percentage": 19.69, "elapsed_time": "0:21:51", "remaining_time": "1:29:11", "throughput": 1040.41, "total_tokens": 1364640} {"current_steps": 15155, "total_steps": 76960, "loss": 0.3109, "lr": 4.858324692474902e-05, "epoch": 3.9384095634095635, "percentage": 19.69, "elapsed_time": "0:21:52", "remaining_time": "1:29:10", "throughput": 1040.41, "total_tokens": 1365072} {"current_steps": 15160, "total_steps": 76960, "loss": 0.2611, "lr": 4.8581364825086144e-05, "epoch": 3.9397089397089395, "percentage": 19.7, "elapsed_time": "0:21:52", "remaining_time": "1:29:10", "throughput": 1040.4, "total_tokens": 1365488} {"current_steps": 15165, "total_steps": 76960, "loss": 0.2307, "lr": 4.857948151261108e-05, "epoch": 3.941008316008316, "percentage": 19.71, "elapsed_time": "0:21:52", "remaining_time": "1:29:09", "throughput": 1040.44, "total_tokens": 1365984} {"current_steps": 15170, "total_steps": 76960, "loss": 0.2063, "lr": 4.857759698742069e-05, "epoch": 3.9423076923076925, "percentage": 19.71, "elapsed_time": "0:21:53", "remaining_time": "1:29:09", "throughput": 1040.47, "total_tokens": 1366448} {"current_steps": 15175, "total_steps": 76960, "loss": 0.225, "lr": 4.85757112496119e-05, "epoch": 3.9436070686070686, "percentage": 19.72, "elapsed_time": "0:21:53", "remaining_time": "1:29:08", "throughput": 1040.5, "total_tokens": 1366928} {"current_steps": 15180, "total_steps": 76960, "loss": 0.2087, "lr": 4.857382429928169e-05, "epoch": 3.944906444906445, "percentage": 19.72, "elapsed_time": "0:21:54", "remaining_time": "1:29:08", "throughput": 1040.5, "total_tokens": 1367360} {"current_steps": 15185, "total_steps": 76960, "loss": 0.411, "lr": 4.857193613652711e-05, "epoch": 3.946205821205821, "percentage": 19.73, "elapsed_time": "0:21:54", "remaining_time": "1:29:07", "throughput": 1040.51, "total_tokens": 1367808} {"current_steps": 15190, "total_steps": 76960, "loss": 0.3174, "lr": 4.8570046761445265e-05, "epoch": 3.9475051975051976, "percentage": 19.74, "elapsed_time": "0:21:54", "remaining_time": "1:29:07", "throughput": 1040.52, "total_tokens": 1368256} {"current_steps": 15195, "total_steps": 76960, "loss": 0.2677, "lr": 4.8568156174133325e-05, "epoch": 3.9488045738045736, "percentage": 19.74, "elapsed_time": "0:21:55", "remaining_time": "1:29:06", "throughput": 1040.51, "total_tokens": 1368688} {"current_steps": 15200, "total_steps": 76960, "loss": 0.339, "lr": 4.856626437468854e-05, "epoch": 3.95010395010395, "percentage": 19.75, "elapsed_time": "0:21:55", "remaining_time": "1:29:06", "throughput": 1040.54, "total_tokens": 1369152} {"current_steps": 15205, "total_steps": 76960, "loss": 0.2572, "lr": 4.856437136320821e-05, "epoch": 3.9514033264033266, "percentage": 19.76, "elapsed_time": "0:21:56", "remaining_time": "1:29:05", "throughput": 1040.53, "total_tokens": 1369584} {"current_steps": 15210, "total_steps": 76960, "loss": 0.2681, "lr": 4.856247713978966e-05, "epoch": 3.9527027027027026, "percentage": 19.76, "elapsed_time": "0:21:56", "remaining_time": "1:29:05", "throughput": 1040.53, "total_tokens": 1370016} {"current_steps": 15215, "total_steps": 76960, "loss": 0.3142, "lr": 4.8560581704530345e-05, "epoch": 3.954002079002079, "percentage": 19.77, "elapsed_time": "0:21:57", "remaining_time": "1:29:04", "throughput": 1040.55, "total_tokens": 1370480} {"current_steps": 15220, "total_steps": 76960, "loss": 0.2523, "lr": 4.855868505752774e-05, "epoch": 3.955301455301455, "percentage": 19.78, "elapsed_time": "0:21:57", "remaining_time": "1:29:04", "throughput": 1040.59, "total_tokens": 1370960} {"current_steps": 15225, "total_steps": 76960, "loss": 0.3128, "lr": 4.8556787198879386e-05, "epoch": 3.9566008316008316, "percentage": 19.78, "elapsed_time": "0:21:57", "remaining_time": "1:29:03", "throughput": 1040.59, "total_tokens": 1371392} {"current_steps": 15230, "total_steps": 76960, "loss": 0.2674, "lr": 4.85548881286829e-05, "epoch": 3.9579002079002077, "percentage": 19.79, "elapsed_time": "0:21:58", "remaining_time": "1:29:03", "throughput": 1040.61, "total_tokens": 1371856} {"current_steps": 15235, "total_steps": 76960, "loss": 0.2398, "lr": 4.8552987847035934e-05, "epoch": 3.959199584199584, "percentage": 19.8, "elapsed_time": "0:21:58", "remaining_time": "1:29:02", "throughput": 1040.64, "total_tokens": 1372336} {"current_steps": 15240, "total_steps": 76960, "loss": 0.2866, "lr": 4.855108635403624e-05, "epoch": 3.9604989604989607, "percentage": 19.8, "elapsed_time": "0:21:59", "remaining_time": "1:29:02", "throughput": 1040.67, "total_tokens": 1372800} {"current_steps": 15245, "total_steps": 76960, "loss": 0.3484, "lr": 4.8549183649781626e-05, "epoch": 3.9617983367983367, "percentage": 19.81, "elapsed_time": "0:21:59", "remaining_time": "1:29:01", "throughput": 1040.68, "total_tokens": 1373248} {"current_steps": 15250, "total_steps": 76960, "loss": 0.1702, "lr": 4.854727973436992e-05, "epoch": 3.963097713097713, "percentage": 19.82, "elapsed_time": "0:21:59", "remaining_time": "1:29:01", "throughput": 1040.69, "total_tokens": 1373696} {"current_steps": 15255, "total_steps": 76960, "loss": 0.2908, "lr": 4.854537460789906e-05, "epoch": 3.9643970893970892, "percentage": 19.82, "elapsed_time": "0:22:00", "remaining_time": "1:29:00", "throughput": 1040.69, "total_tokens": 1374144} {"current_steps": 15260, "total_steps": 76960, "loss": 0.2555, "lr": 4.854346827046702e-05, "epoch": 3.9656964656964657, "percentage": 19.83, "elapsed_time": "0:22:00", "remaining_time": "1:29:00", "throughput": 1040.7, "total_tokens": 1374592} {"current_steps": 15265, "total_steps": 76960, "loss": 0.2867, "lr": 4.8541560722171855e-05, "epoch": 3.9669958419958418, "percentage": 19.83, "elapsed_time": "0:22:01", "remaining_time": "1:28:59", "throughput": 1040.72, "total_tokens": 1375056} {"current_steps": 15270, "total_steps": 76960, "loss": 0.3049, "lr": 4.8539651963111655e-05, "epoch": 3.9682952182952183, "percentage": 19.84, "elapsed_time": "0:22:01", "remaining_time": "1:28:59", "throughput": 1040.72, "total_tokens": 1375488} {"current_steps": 15275, "total_steps": 76960, "loss": 0.237, "lr": 4.853774199338461e-05, "epoch": 3.9695945945945947, "percentage": 19.85, "elapsed_time": "0:22:02", "remaining_time": "1:28:58", "throughput": 1040.76, "total_tokens": 1375968} {"current_steps": 15280, "total_steps": 76960, "loss": 0.3063, "lr": 4.8535830813088934e-05, "epoch": 3.970893970893971, "percentage": 19.85, "elapsed_time": "0:22:02", "remaining_time": "1:28:58", "throughput": 1040.78, "total_tokens": 1376432} {"current_steps": 15285, "total_steps": 76960, "loss": 0.2415, "lr": 4.853391842232293e-05, "epoch": 3.9721933471933473, "percentage": 19.86, "elapsed_time": "0:22:02", "remaining_time": "1:28:57", "throughput": 1040.78, "total_tokens": 1376864} {"current_steps": 15290, "total_steps": 76960, "loss": 0.2266, "lr": 4.853200482118495e-05, "epoch": 3.9734927234927238, "percentage": 19.87, "elapsed_time": "0:22:03", "remaining_time": "1:28:57", "throughput": 1040.79, "total_tokens": 1377312} {"current_steps": 15295, "total_steps": 76960, "loss": 0.2189, "lr": 4.853009000977342e-05, "epoch": 3.9747920997921, "percentage": 19.87, "elapsed_time": "0:22:03", "remaining_time": "1:28:56", "throughput": 1040.8, "total_tokens": 1377760} {"current_steps": 15300, "total_steps": 76960, "loss": 0.1538, "lr": 4.852817398818682e-05, "epoch": 3.976091476091476, "percentage": 19.88, "elapsed_time": "0:22:04", "remaining_time": "1:28:56", "throughput": 1040.83, "total_tokens": 1378240} {"current_steps": 15305, "total_steps": 76960, "loss": 0.2128, "lr": 4.852625675652368e-05, "epoch": 3.9773908523908523, "percentage": 19.89, "elapsed_time": "0:22:04", "remaining_time": "1:28:56", "throughput": 1040.87, "total_tokens": 1378720} {"current_steps": 15310, "total_steps": 76960, "loss": 0.4285, "lr": 4.852433831488261e-05, "epoch": 3.978690228690229, "percentage": 19.89, "elapsed_time": "0:22:05", "remaining_time": "1:28:55", "throughput": 1040.87, "total_tokens": 1379168} {"current_steps": 15315, "total_steps": 76960, "loss": 0.2885, "lr": 4.852241866336229e-05, "epoch": 3.979989604989605, "percentage": 19.9, "elapsed_time": "0:22:05", "remaining_time": "1:28:55", "throughput": 1040.9, "total_tokens": 1379632} {"current_steps": 15320, "total_steps": 76960, "loss": 0.2255, "lr": 4.8520497802061436e-05, "epoch": 3.9812889812889813, "percentage": 19.91, "elapsed_time": "0:22:05", "remaining_time": "1:28:54", "throughput": 1040.88, "total_tokens": 1380048} {"current_steps": 15325, "total_steps": 76960, "loss": 0.266, "lr": 4.8518575731078844e-05, "epoch": 3.982588357588358, "percentage": 19.91, "elapsed_time": "0:22:06", "remaining_time": "1:28:54", "throughput": 1040.9, "total_tokens": 1380512} {"current_steps": 15330, "total_steps": 76960, "loss": 0.3224, "lr": 4.851665245051337e-05, "epoch": 3.983887733887734, "percentage": 19.92, "elapsed_time": "0:22:06", "remaining_time": "1:28:53", "throughput": 1040.91, "total_tokens": 1380960} {"current_steps": 15335, "total_steps": 76960, "loss": 0.3266, "lr": 4.8514727960463926e-05, "epoch": 3.98518711018711, "percentage": 19.93, "elapsed_time": "0:22:07", "remaining_time": "1:28:53", "throughput": 1040.95, "total_tokens": 1381440} {"current_steps": 15340, "total_steps": 76960, "loss": 0.2828, "lr": 4.8512802261029486e-05, "epoch": 3.9864864864864864, "percentage": 19.93, "elapsed_time": "0:22:07", "remaining_time": "1:28:52", "throughput": 1040.97, "total_tokens": 1381904} {"current_steps": 15345, "total_steps": 76960, "loss": 0.2969, "lr": 4.8510875352309106e-05, "epoch": 3.987785862785863, "percentage": 19.94, "elapsed_time": "0:22:07", "remaining_time": "1:28:52", "throughput": 1041.02, "total_tokens": 1382400} {"current_steps": 15350, "total_steps": 76960, "loss": 0.2503, "lr": 4.8508947234401875e-05, "epoch": 3.989085239085239, "percentage": 19.95, "elapsed_time": "0:22:08", "remaining_time": "1:28:51", "throughput": 1041.01, "total_tokens": 1382832} {"current_steps": 15355, "total_steps": 76960, "loss": 0.2689, "lr": 4.850701790740696e-05, "epoch": 3.9903846153846154, "percentage": 19.95, "elapsed_time": "0:22:08", "remaining_time": "1:28:51", "throughput": 1041.05, "total_tokens": 1383312} {"current_steps": 15360, "total_steps": 76960, "loss": 0.2155, "lr": 4.85050873714236e-05, "epoch": 3.991683991683992, "percentage": 19.96, "elapsed_time": "0:22:09", "remaining_time": "1:28:50", "throughput": 1041.06, "total_tokens": 1383760} {"current_steps": 15365, "total_steps": 76960, "loss": 0.1709, "lr": 4.850315562655107e-05, "epoch": 3.992983367983368, "percentage": 19.96, "elapsed_time": "0:22:09", "remaining_time": "1:28:50", "throughput": 1041.05, "total_tokens": 1384192} {"current_steps": 15370, "total_steps": 76960, "loss": 0.2844, "lr": 4.850122267288872e-05, "epoch": 3.9942827442827444, "percentage": 19.97, "elapsed_time": "0:22:10", "remaining_time": "1:28:49", "throughput": 1041.09, "total_tokens": 1384672} {"current_steps": 15375, "total_steps": 76960, "loss": 0.2892, "lr": 4.8499288510535975e-05, "epoch": 3.9955821205821205, "percentage": 19.98, "elapsed_time": "0:22:10", "remaining_time": "1:28:49", "throughput": 1041.12, "total_tokens": 1385152} {"current_steps": 15380, "total_steps": 76960, "loss": 0.2602, "lr": 4.849735313959231e-05, "epoch": 3.996881496881497, "percentage": 19.98, "elapsed_time": "0:22:10", "remaining_time": "1:28:48", "throughput": 1041.16, "total_tokens": 1385632} {"current_steps": 15385, "total_steps": 76960, "loss": 0.2136, "lr": 4.849541656015726e-05, "epoch": 3.998180873180873, "percentage": 19.99, "elapsed_time": "0:22:11", "remaining_time": "1:28:48", "throughput": 1041.18, "total_tokens": 1386096} {"current_steps": 15390, "total_steps": 76960, "loss": 0.2649, "lr": 4.8493478772330414e-05, "epoch": 3.9994802494802495, "percentage": 20.0, "elapsed_time": "0:22:11", "remaining_time": "1:28:47", "throughput": 1041.2, "total_tokens": 1386544} {"current_steps": 15392, "total_steps": 76960, "eval_loss": 0.2411372810602188, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:22:25", "remaining_time": "1:29:40", "throughput": 1030.9, "total_tokens": 1386696} {"current_steps": 15395, "total_steps": 76960, "loss": 0.2266, "lr": 4.8491539776211453e-05, "epoch": 4.000779625779626, "percentage": 20.0, "elapsed_time": "0:22:26", "remaining_time": "1:29:46", "throughput": 1029.77, "total_tokens": 1386968} {"current_steps": 15400, "total_steps": 76960, "loss": 0.1759, "lr": 4.848959957190009e-05, "epoch": 4.002079002079002, "percentage": 20.01, "elapsed_time": "0:22:27", "remaining_time": "1:29:45", "throughput": 1029.78, "total_tokens": 1387416} {"current_steps": 15405, "total_steps": 76960, "loss": 0.3191, "lr": 4.848765815949611e-05, "epoch": 4.003378378378378, "percentage": 20.02, "elapsed_time": "0:22:27", "remaining_time": "1:29:45", "throughput": 1029.74, "total_tokens": 1387832} {"current_steps": 15410, "total_steps": 76960, "loss": 0.2108, "lr": 4.8485715539099374e-05, "epoch": 4.004677754677755, "percentage": 20.02, "elapsed_time": "0:22:28", "remaining_time": "1:29:44", "throughput": 1029.75, "total_tokens": 1388280} {"current_steps": 15415, "total_steps": 76960, "loss": 0.2174, "lr": 4.848377171080978e-05, "epoch": 4.005977130977131, "percentage": 20.03, "elapsed_time": "0:22:28", "remaining_time": "1:29:44", "throughput": 1029.8, "total_tokens": 1388792} {"current_steps": 15420, "total_steps": 76960, "loss": 0.1705, "lr": 4.848182667472731e-05, "epoch": 4.007276507276507, "percentage": 20.04, "elapsed_time": "0:22:29", "remaining_time": "1:29:43", "throughput": 1029.8, "total_tokens": 1389224} {"current_steps": 15425, "total_steps": 76960, "loss": 0.2668, "lr": 4.8479880430951995e-05, "epoch": 4.008575883575884, "percentage": 20.04, "elapsed_time": "0:22:29", "remaining_time": "1:29:43", "throughput": 1029.82, "total_tokens": 1389688} {"current_steps": 15430, "total_steps": 76960, "loss": 0.2078, "lr": 4.847793297958393e-05, "epoch": 4.00987525987526, "percentage": 20.05, "elapsed_time": "0:22:29", "remaining_time": "1:29:42", "throughput": 1029.82, "total_tokens": 1390120} {"current_steps": 15435, "total_steps": 76960, "loss": 0.2596, "lr": 4.847598432072327e-05, "epoch": 4.011174636174636, "percentage": 20.06, "elapsed_time": "0:22:30", "remaining_time": "1:29:42", "throughput": 1029.85, "total_tokens": 1390600} {"current_steps": 15440, "total_steps": 76960, "loss": 0.3094, "lr": 4.847403445447025e-05, "epoch": 4.012474012474012, "percentage": 20.06, "elapsed_time": "0:22:30", "remaining_time": "1:29:41", "throughput": 1029.86, "total_tokens": 1391048} {"current_steps": 15445, "total_steps": 76960, "loss": 0.209, "lr": 4.847208338092515e-05, "epoch": 4.013773388773389, "percentage": 20.07, "elapsed_time": "0:22:31", "remaining_time": "1:29:41", "throughput": 1029.87, "total_tokens": 1391496} {"current_steps": 15450, "total_steps": 76960, "loss": 0.2632, "lr": 4.84701311001883e-05, "epoch": 4.015072765072765, "percentage": 20.08, "elapsed_time": "0:22:31", "remaining_time": "1:29:40", "throughput": 1029.91, "total_tokens": 1391976} {"current_steps": 15455, "total_steps": 76960, "loss": 0.2181, "lr": 4.8468177612360126e-05, "epoch": 4.016372141372141, "percentage": 20.08, "elapsed_time": "0:22:31", "remaining_time": "1:29:40", "throughput": 1029.91, "total_tokens": 1392408} {"current_steps": 15460, "total_steps": 76960, "loss": 0.3022, "lr": 4.8466222917541095e-05, "epoch": 4.017671517671518, "percentage": 20.09, "elapsed_time": "0:22:32", "remaining_time": "1:29:39", "throughput": 1029.91, "total_tokens": 1392840} {"current_steps": 15465, "total_steps": 76960, "loss": 0.228, "lr": 4.846426701583173e-05, "epoch": 4.018970893970894, "percentage": 20.09, "elapsed_time": "0:22:32", "remaining_time": "1:29:39", "throughput": 1029.91, "total_tokens": 1393272} {"current_steps": 15470, "total_steps": 76960, "loss": 0.193, "lr": 4.846230990733263e-05, "epoch": 4.02027027027027, "percentage": 20.1, "elapsed_time": "0:22:33", "remaining_time": "1:29:38", "throughput": 1029.93, "total_tokens": 1393736} {"current_steps": 15475, "total_steps": 76960, "loss": 0.1615, "lr": 4.846035159214446e-05, "epoch": 4.021569646569646, "percentage": 20.11, "elapsed_time": "0:22:33", "remaining_time": "1:29:38", "throughput": 1029.92, "total_tokens": 1394152} {"current_steps": 15480, "total_steps": 76960, "loss": 0.2707, "lr": 4.845839207036792e-05, "epoch": 4.022869022869023, "percentage": 20.11, "elapsed_time": "0:22:34", "remaining_time": "1:29:37", "throughput": 1029.94, "total_tokens": 1394616} {"current_steps": 15485, "total_steps": 76960, "loss": 0.3604, "lr": 4.845643134210379e-05, "epoch": 4.024168399168399, "percentage": 20.12, "elapsed_time": "0:22:34", "remaining_time": "1:29:37", "throughput": 1029.92, "total_tokens": 1395032} {"current_steps": 15490, "total_steps": 76960, "loss": 0.2635, "lr": 4.845446940745294e-05, "epoch": 4.025467775467775, "percentage": 20.13, "elapsed_time": "0:22:34", "remaining_time": "1:29:36", "throughput": 1029.93, "total_tokens": 1395480} {"current_steps": 15495, "total_steps": 76960, "loss": 0.2547, "lr": 4.845250626651625e-05, "epoch": 4.026767151767152, "percentage": 20.13, "elapsed_time": "0:22:35", "remaining_time": "1:29:36", "throughput": 1029.94, "total_tokens": 1395928} {"current_steps": 15500, "total_steps": 76960, "loss": 0.3138, "lr": 4.8450541919394686e-05, "epoch": 4.028066528066528, "percentage": 20.14, "elapsed_time": "0:22:35", "remaining_time": "1:29:35", "throughput": 1029.95, "total_tokens": 1396376} {"current_steps": 15505, "total_steps": 76960, "loss": 0.2875, "lr": 4.844857636618928e-05, "epoch": 4.029365904365904, "percentage": 20.15, "elapsed_time": "0:22:36", "remaining_time": "1:29:35", "throughput": 1029.95, "total_tokens": 1396808} {"current_steps": 15510, "total_steps": 76960, "loss": 0.2644, "lr": 4.844660960700113e-05, "epoch": 4.03066528066528, "percentage": 20.15, "elapsed_time": "0:22:36", "remaining_time": "1:29:34", "throughput": 1029.97, "total_tokens": 1397272} {"current_steps": 15515, "total_steps": 76960, "loss": 0.1868, "lr": 4.844464164193138e-05, "epoch": 4.031964656964657, "percentage": 20.16, "elapsed_time": "0:22:37", "remaining_time": "1:29:34", "throughput": 1029.99, "total_tokens": 1397736} {"current_steps": 15520, "total_steps": 76960, "loss": 0.225, "lr": 4.844267247108125e-05, "epoch": 4.033264033264033, "percentage": 20.17, "elapsed_time": "0:22:37", "remaining_time": "1:29:33", "throughput": 1030.02, "total_tokens": 1398200} {"current_steps": 15525, "total_steps": 76960, "loss": 0.2154, "lr": 4.8440702094552015e-05, "epoch": 4.034563409563409, "percentage": 20.17, "elapsed_time": "0:22:37", "remaining_time": "1:29:33", "throughput": 1030.03, "total_tokens": 1398648} {"current_steps": 15530, "total_steps": 76960, "loss": 0.3091, "lr": 4.843873051244501e-05, "epoch": 4.035862785862786, "percentage": 20.18, "elapsed_time": "0:22:38", "remaining_time": "1:29:32", "throughput": 1030.05, "total_tokens": 1399112} {"current_steps": 15535, "total_steps": 76960, "loss": 0.2114, "lr": 4.8436757724861624e-05, "epoch": 4.037162162162162, "percentage": 20.19, "elapsed_time": "0:22:38", "remaining_time": "1:29:32", "throughput": 1030.06, "total_tokens": 1399560} {"current_steps": 15540, "total_steps": 76960, "loss": 0.2097, "lr": 4.843478373190334e-05, "epoch": 4.038461538461538, "percentage": 20.19, "elapsed_time": "0:22:39", "remaining_time": "1:29:31", "throughput": 1030.08, "total_tokens": 1400008} {"current_steps": 15545, "total_steps": 76960, "loss": 0.2964, "lr": 4.843280853367168e-05, "epoch": 4.039760914760914, "percentage": 20.2, "elapsed_time": "0:22:39", "remaining_time": "1:29:31", "throughput": 1030.12, "total_tokens": 1400504} {"current_steps": 15550, "total_steps": 76960, "loss": 0.2687, "lr": 4.843083213026823e-05, "epoch": 4.041060291060291, "percentage": 20.21, "elapsed_time": "0:22:39", "remaining_time": "1:29:30", "throughput": 1030.09, "total_tokens": 1400904} {"current_steps": 15555, "total_steps": 76960, "loss": 0.3143, "lr": 4.842885452179462e-05, "epoch": 4.042359667359667, "percentage": 20.21, "elapsed_time": "0:22:40", "remaining_time": "1:29:30", "throughput": 1030.11, "total_tokens": 1401352} {"current_steps": 15560, "total_steps": 76960, "loss": 0.2365, "lr": 4.842687570835258e-05, "epoch": 4.043659043659043, "percentage": 20.22, "elapsed_time": "0:22:40", "remaining_time": "1:29:29", "throughput": 1030.11, "total_tokens": 1401784} {"current_steps": 15565, "total_steps": 76960, "loss": 0.335, "lr": 4.842489569004388e-05, "epoch": 4.04495841995842, "percentage": 20.22, "elapsed_time": "0:22:41", "remaining_time": "1:29:29", "throughput": 1030.17, "total_tokens": 1402296} {"current_steps": 15570, "total_steps": 76960, "loss": 0.2776, "lr": 4.842291446697034e-05, "epoch": 4.046257796257796, "percentage": 20.23, "elapsed_time": "0:22:41", "remaining_time": "1:29:28", "throughput": 1030.21, "total_tokens": 1402792} {"current_steps": 15575, "total_steps": 76960, "loss": 0.2872, "lr": 4.842093203923387e-05, "epoch": 4.047557172557172, "percentage": 20.24, "elapsed_time": "0:22:42", "remaining_time": "1:29:28", "throughput": 1030.24, "total_tokens": 1403256} {"current_steps": 15580, "total_steps": 76960, "loss": 0.2751, "lr": 4.841894840693642e-05, "epoch": 4.048856548856548, "percentage": 20.24, "elapsed_time": "0:22:42", "remaining_time": "1:29:27", "throughput": 1030.24, "total_tokens": 1403688} {"current_steps": 15585, "total_steps": 76960, "loss": 0.2572, "lr": 4.8416963570180025e-05, "epoch": 4.050155925155925, "percentage": 20.25, "elapsed_time": "0:22:42", "remaining_time": "1:29:27", "throughput": 1030.26, "total_tokens": 1404152} {"current_steps": 15590, "total_steps": 76960, "loss": 0.2601, "lr": 4.8414977529066754e-05, "epoch": 4.051455301455301, "percentage": 20.26, "elapsed_time": "0:22:43", "remaining_time": "1:29:26", "throughput": 1030.3, "total_tokens": 1404632} {"current_steps": 15595, "total_steps": 76960, "loss": 0.236, "lr": 4.841299028369874e-05, "epoch": 4.0527546777546775, "percentage": 20.26, "elapsed_time": "0:22:43", "remaining_time": "1:29:26", "throughput": 1030.31, "total_tokens": 1405080} {"current_steps": 15600, "total_steps": 76960, "loss": 0.2177, "lr": 4.841100183417822e-05, "epoch": 4.054054054054054, "percentage": 20.27, "elapsed_time": "0:22:44", "remaining_time": "1:29:25", "throughput": 1030.31, "total_tokens": 1405512} {"current_steps": 15605, "total_steps": 76960, "loss": 0.2646, "lr": 4.840901218060744e-05, "epoch": 4.05535343035343, "percentage": 20.28, "elapsed_time": "0:22:44", "remaining_time": "1:29:25", "throughput": 1030.3, "total_tokens": 1405928} {"current_steps": 15610, "total_steps": 76960, "loss": 0.262, "lr": 4.840702132308873e-05, "epoch": 4.0566528066528065, "percentage": 20.28, "elapsed_time": "0:22:45", "remaining_time": "1:29:24", "throughput": 1030.31, "total_tokens": 1406376} {"current_steps": 15615, "total_steps": 76960, "loss": 0.3513, "lr": 4.840502926172449e-05, "epoch": 4.0579521829521825, "percentage": 20.29, "elapsed_time": "0:22:45", "remaining_time": "1:29:24", "throughput": 1030.33, "total_tokens": 1406840} {"current_steps": 15620, "total_steps": 76960, "loss": 0.2388, "lr": 4.840303599661716e-05, "epoch": 4.0592515592515594, "percentage": 20.3, "elapsed_time": "0:22:45", "remaining_time": "1:29:23", "throughput": 1030.31, "total_tokens": 1407240} {"current_steps": 15625, "total_steps": 76960, "loss": 0.1908, "lr": 4.840104152786927e-05, "epoch": 4.0605509355509355, "percentage": 20.3, "elapsed_time": "0:22:46", "remaining_time": "1:29:23", "throughput": 1030.31, "total_tokens": 1407672} {"current_steps": 15630, "total_steps": 76960, "loss": 0.2943, "lr": 4.8399045855583404e-05, "epoch": 4.0618503118503115, "percentage": 20.31, "elapsed_time": "0:22:46", "remaining_time": "1:29:22", "throughput": 1030.36, "total_tokens": 1408168} {"current_steps": 15635, "total_steps": 76960, "loss": 0.2485, "lr": 4.8397048979862176e-05, "epoch": 4.0631496881496885, "percentage": 20.32, "elapsed_time": "0:22:47", "remaining_time": "1:29:22", "throughput": 1030.36, "total_tokens": 1408600} {"current_steps": 15640, "total_steps": 76960, "loss": 0.2212, "lr": 4.83950509008083e-05, "epoch": 4.0644490644490645, "percentage": 20.32, "elapsed_time": "0:22:47", "remaining_time": "1:29:21", "throughput": 1030.38, "total_tokens": 1409064} {"current_steps": 15645, "total_steps": 76960, "loss": 0.2535, "lr": 4.8393051618524554e-05, "epoch": 4.0657484407484406, "percentage": 20.33, "elapsed_time": "0:22:47", "remaining_time": "1:29:21", "throughput": 1030.39, "total_tokens": 1409512} {"current_steps": 15650, "total_steps": 76960, "loss": 0.3013, "lr": 4.839105113311373e-05, "epoch": 4.0670478170478175, "percentage": 20.34, "elapsed_time": "0:22:48", "remaining_time": "1:29:20", "throughput": 1030.42, "total_tokens": 1409976} {"current_steps": 15655, "total_steps": 76960, "loss": 0.2487, "lr": 4.8389049444678746e-05, "epoch": 4.0683471933471935, "percentage": 20.34, "elapsed_time": "0:22:48", "remaining_time": "1:29:20", "throughput": 1030.43, "total_tokens": 1410424} {"current_steps": 15660, "total_steps": 76960, "loss": 0.308, "lr": 4.838704655332254e-05, "epoch": 4.06964656964657, "percentage": 20.35, "elapsed_time": "0:22:49", "remaining_time": "1:29:19", "throughput": 1030.43, "total_tokens": 1410856} {"current_steps": 15665, "total_steps": 76960, "loss": 0.3029, "lr": 4.838504245914812e-05, "epoch": 4.070945945945946, "percentage": 20.35, "elapsed_time": "0:22:49", "remaining_time": "1:29:19", "throughput": 1030.45, "total_tokens": 1411320} {"current_steps": 15670, "total_steps": 76960, "loss": 0.2025, "lr": 4.838303716225856e-05, "epoch": 4.0722453222453225, "percentage": 20.36, "elapsed_time": "0:22:50", "remaining_time": "1:29:18", "throughput": 1030.44, "total_tokens": 1411752} {"current_steps": 15675, "total_steps": 76960, "loss": 0.2566, "lr": 4.8381030662756984e-05, "epoch": 4.073544698544699, "percentage": 20.37, "elapsed_time": "0:22:50", "remaining_time": "1:29:18", "throughput": 1030.44, "total_tokens": 1412184} {"current_steps": 15680, "total_steps": 76960, "loss": 0.3038, "lr": 4.837902296074661e-05, "epoch": 4.074844074844075, "percentage": 20.37, "elapsed_time": "0:22:50", "remaining_time": "1:29:17", "throughput": 1030.46, "total_tokens": 1412648} {"current_steps": 15685, "total_steps": 76960, "loss": 0.2559, "lr": 4.8377014056330686e-05, "epoch": 4.076143451143452, "percentage": 20.38, "elapsed_time": "0:22:51", "remaining_time": "1:29:17", "throughput": 1030.47, "total_tokens": 1413096} {"current_steps": 15690, "total_steps": 76960, "loss": 0.3019, "lr": 4.8375003949612525e-05, "epoch": 4.077442827442828, "percentage": 20.39, "elapsed_time": "0:22:51", "remaining_time": "1:29:16", "throughput": 1030.48, "total_tokens": 1413544} {"current_steps": 15695, "total_steps": 76960, "loss": 0.2597, "lr": 4.8372992640695515e-05, "epoch": 4.078742203742204, "percentage": 20.39, "elapsed_time": "0:22:52", "remaining_time": "1:29:16", "throughput": 1030.52, "total_tokens": 1414024} {"current_steps": 15700, "total_steps": 76960, "loss": 0.262, "lr": 4.8370980129683096e-05, "epoch": 4.08004158004158, "percentage": 20.4, "elapsed_time": "0:22:52", "remaining_time": "1:29:15", "throughput": 1030.56, "total_tokens": 1414520} {"current_steps": 15705, "total_steps": 76960, "loss": 0.2862, "lr": 4.836896641667878e-05, "epoch": 4.081340956340957, "percentage": 20.41, "elapsed_time": "0:22:52", "remaining_time": "1:29:15", "throughput": 1030.63, "total_tokens": 1415048} {"current_steps": 15710, "total_steps": 76960, "loss": 0.2446, "lr": 4.836695150178613e-05, "epoch": 4.082640332640333, "percentage": 20.41, "elapsed_time": "0:22:53", "remaining_time": "1:29:14", "throughput": 1030.65, "total_tokens": 1415512} {"current_steps": 15715, "total_steps": 76960, "loss": 0.2533, "lr": 4.8364935385108765e-05, "epoch": 4.083939708939709, "percentage": 20.42, "elapsed_time": "0:22:53", "remaining_time": "1:29:14", "throughput": 1030.64, "total_tokens": 1415928} {"current_steps": 15720, "total_steps": 76960, "loss": 0.2507, "lr": 4.83629180667504e-05, "epoch": 4.085239085239086, "percentage": 20.43, "elapsed_time": "0:22:54", "remaining_time": "1:29:13", "throughput": 1030.63, "total_tokens": 1416344} {"current_steps": 15725, "total_steps": 76960, "loss": 0.2704, "lr": 4.836089954681477e-05, "epoch": 4.086538461538462, "percentage": 20.43, "elapsed_time": "0:22:54", "remaining_time": "1:29:13", "throughput": 1030.64, "total_tokens": 1416792} {"current_steps": 15730, "total_steps": 76960, "loss": 0.2582, "lr": 4.835887982540569e-05, "epoch": 4.087837837837838, "percentage": 20.44, "elapsed_time": "0:22:55", "remaining_time": "1:29:12", "throughput": 1030.63, "total_tokens": 1417208} {"current_steps": 15735, "total_steps": 76960, "loss": 0.2903, "lr": 4.8356858902627036e-05, "epoch": 4.089137214137214, "percentage": 20.45, "elapsed_time": "0:22:55", "remaining_time": "1:29:12", "throughput": 1030.63, "total_tokens": 1417640} {"current_steps": 15740, "total_steps": 76960, "loss": 0.2117, "lr": 4.8354836778582756e-05, "epoch": 4.090436590436591, "percentage": 20.45, "elapsed_time": "0:22:55", "remaining_time": "1:29:11", "throughput": 1030.63, "total_tokens": 1418072} {"current_steps": 15745, "total_steps": 76960, "loss": 0.2805, "lr": 4.8352813453376836e-05, "epoch": 4.091735966735967, "percentage": 20.46, "elapsed_time": "0:22:56", "remaining_time": "1:29:11", "throughput": 1030.64, "total_tokens": 1418520} {"current_steps": 15750, "total_steps": 76960, "loss": 0.2598, "lr": 4.835078892711336e-05, "epoch": 4.093035343035343, "percentage": 20.47, "elapsed_time": "0:22:56", "remaining_time": "1:29:10", "throughput": 1030.67, "total_tokens": 1418984} {"current_steps": 15755, "total_steps": 76960, "loss": 0.1994, "lr": 4.834876319989642e-05, "epoch": 4.09433471933472, "percentage": 20.47, "elapsed_time": "0:22:57", "remaining_time": "1:29:10", "throughput": 1030.65, "total_tokens": 1419400} {"current_steps": 15760, "total_steps": 76960, "loss": 0.3949, "lr": 4.8346736271830214e-05, "epoch": 4.095634095634096, "percentage": 20.48, "elapsed_time": "0:22:57", "remaining_time": "1:29:09", "throughput": 1030.68, "total_tokens": 1419864} {"current_steps": 15765, "total_steps": 76960, "loss": 0.2946, "lr": 4.8344708143019e-05, "epoch": 4.096933471933472, "percentage": 20.48, "elapsed_time": "0:22:58", "remaining_time": "1:29:09", "throughput": 1030.67, "total_tokens": 1420280} {"current_steps": 15770, "total_steps": 76960, "loss": 0.2615, "lr": 4.8342678813567076e-05, "epoch": 4.098232848232848, "percentage": 20.49, "elapsed_time": "0:22:58", "remaining_time": "1:29:08", "throughput": 1030.69, "total_tokens": 1420744} {"current_steps": 15775, "total_steps": 76960, "loss": 0.2325, "lr": 4.834064828357882e-05, "epoch": 4.099532224532225, "percentage": 20.5, "elapsed_time": "0:22:58", "remaining_time": "1:29:08", "throughput": 1030.72, "total_tokens": 1421208} {"current_steps": 15780, "total_steps": 76960, "loss": 0.2113, "lr": 4.8338616553158656e-05, "epoch": 4.100831600831601, "percentage": 20.5, "elapsed_time": "0:22:59", "remaining_time": "1:29:07", "throughput": 1030.76, "total_tokens": 1421688} {"current_steps": 15785, "total_steps": 76960, "loss": 0.314, "lr": 4.833658362241108e-05, "epoch": 4.102130977130977, "percentage": 20.51, "elapsed_time": "0:22:59", "remaining_time": "1:29:06", "throughput": 1030.76, "total_tokens": 1422120} {"current_steps": 15790, "total_steps": 76960, "loss": 0.2156, "lr": 4.833454949144065e-05, "epoch": 4.103430353430354, "percentage": 20.52, "elapsed_time": "0:23:00", "remaining_time": "1:29:06", "throughput": 1030.74, "total_tokens": 1422536} {"current_steps": 15795, "total_steps": 76960, "loss": 0.1103, "lr": 4.833251416035198e-05, "epoch": 4.10472972972973, "percentage": 20.52, "elapsed_time": "0:23:00", "remaining_time": "1:29:05", "throughput": 1030.79, "total_tokens": 1423032} {"current_steps": 15800, "total_steps": 76960, "loss": 0.3645, "lr": 4.833047762924975e-05, "epoch": 4.106029106029106, "percentage": 20.53, "elapsed_time": "0:23:00", "remaining_time": "1:29:05", "throughput": 1030.79, "total_tokens": 1423464} {"current_steps": 15805, "total_steps": 76960, "loss": 0.2135, "lr": 4.83284398982387e-05, "epoch": 4.107328482328482, "percentage": 20.54, "elapsed_time": "0:23:01", "remaining_time": "1:29:04", "throughput": 1030.78, "total_tokens": 1423880} {"current_steps": 15810, "total_steps": 76960, "loss": 0.2145, "lr": 4.8326400967423636e-05, "epoch": 4.108627858627859, "percentage": 20.54, "elapsed_time": "0:23:01", "remaining_time": "1:29:04", "throughput": 1030.8, "total_tokens": 1424344} {"current_steps": 15815, "total_steps": 76960, "loss": 0.25, "lr": 4.8324360836909425e-05, "epoch": 4.109927234927235, "percentage": 20.55, "elapsed_time": "0:23:02", "remaining_time": "1:29:03", "throughput": 1030.85, "total_tokens": 1424840} {"current_steps": 15820, "total_steps": 76960, "loss": 0.2603, "lr": 4.832231950680097e-05, "epoch": 4.111226611226611, "percentage": 20.56, "elapsed_time": "0:23:02", "remaining_time": "1:29:03", "throughput": 1030.84, "total_tokens": 1425256} {"current_steps": 15825, "total_steps": 76960, "loss": 0.3562, "lr": 4.83202769772033e-05, "epoch": 4.112525987525988, "percentage": 20.56, "elapsed_time": "0:23:03", "remaining_time": "1:29:02", "throughput": 1030.86, "total_tokens": 1425720} {"current_steps": 15830, "total_steps": 76960, "loss": 0.2374, "lr": 4.8318233248221424e-05, "epoch": 4.113825363825364, "percentage": 20.57, "elapsed_time": "0:23:03", "remaining_time": "1:29:02", "throughput": 1030.86, "total_tokens": 1426152} {"current_steps": 15835, "total_steps": 76960, "loss": 0.2436, "lr": 4.831618831996048e-05, "epoch": 4.11512474012474, "percentage": 20.58, "elapsed_time": "0:23:03", "remaining_time": "1:29:01", "throughput": 1030.91, "total_tokens": 1426648} {"current_steps": 15840, "total_steps": 76960, "loss": 0.2493, "lr": 4.8314142192525615e-05, "epoch": 4.116424116424117, "percentage": 20.58, "elapsed_time": "0:23:04", "remaining_time": "1:29:01", "throughput": 1030.88, "total_tokens": 1427048} {"current_steps": 15845, "total_steps": 76960, "loss": 0.25, "lr": 4.8312094866022096e-05, "epoch": 4.117723492723493, "percentage": 20.59, "elapsed_time": "0:23:04", "remaining_time": "1:29:00", "throughput": 1030.91, "total_tokens": 1427512} {"current_steps": 15850, "total_steps": 76960, "loss": 0.2869, "lr": 4.8310046340555196e-05, "epoch": 4.119022869022869, "percentage": 20.6, "elapsed_time": "0:23:05", "remaining_time": "1:29:00", "throughput": 1030.92, "total_tokens": 1427960} {"current_steps": 15855, "total_steps": 76960, "loss": 0.2976, "lr": 4.830799661623027e-05, "epoch": 4.120322245322245, "percentage": 20.6, "elapsed_time": "0:23:05", "remaining_time": "1:28:59", "throughput": 1030.92, "total_tokens": 1428392} {"current_steps": 15860, "total_steps": 76960, "loss": 0.2308, "lr": 4.8305945693152754e-05, "epoch": 4.121621621621622, "percentage": 20.61, "elapsed_time": "0:23:05", "remaining_time": "1:28:59", "throughput": 1030.93, "total_tokens": 1428840} {"current_steps": 15865, "total_steps": 76960, "loss": 0.2313, "lr": 4.8303893571428116e-05, "epoch": 4.122920997920998, "percentage": 20.61, "elapsed_time": "0:23:06", "remaining_time": "1:28:58", "throughput": 1030.92, "total_tokens": 1429256} {"current_steps": 15870, "total_steps": 76960, "loss": 0.2644, "lr": 4.83018402511619e-05, "epoch": 4.124220374220374, "percentage": 20.62, "elapsed_time": "0:23:06", "remaining_time": "1:28:58", "throughput": 1030.94, "total_tokens": 1429720} {"current_steps": 15875, "total_steps": 76960, "loss": 0.2649, "lr": 4.829978573245972e-05, "epoch": 4.12551975051975, "percentage": 20.63, "elapsed_time": "0:23:07", "remaining_time": "1:28:57", "throughput": 1030.94, "total_tokens": 1430152} {"current_steps": 15880, "total_steps": 76960, "loss": 0.1724, "lr": 4.8297730015427233e-05, "epoch": 4.126819126819127, "percentage": 20.63, "elapsed_time": "0:23:07", "remaining_time": "1:28:57", "throughput": 1030.97, "total_tokens": 1430616} {"current_steps": 15885, "total_steps": 76960, "loss": 0.1832, "lr": 4.829567310017017e-05, "epoch": 4.128118503118503, "percentage": 20.64, "elapsed_time": "0:23:08", "remaining_time": "1:28:56", "throughput": 1030.95, "total_tokens": 1431032} {"current_steps": 15890, "total_steps": 76960, "loss": 0.3162, "lr": 4.829361498679432e-05, "epoch": 4.129417879417879, "percentage": 20.65, "elapsed_time": "0:23:08", "remaining_time": "1:28:56", "throughput": 1031.0, "total_tokens": 1431528} {"current_steps": 15895, "total_steps": 76960, "loss": 0.3221, "lr": 4.8291555675405526e-05, "epoch": 4.130717255717256, "percentage": 20.65, "elapsed_time": "0:23:08", "remaining_time": "1:28:55", "throughput": 1031.02, "total_tokens": 1431976} {"current_steps": 15900, "total_steps": 76960, "loss": 0.2058, "lr": 4.828949516610971e-05, "epoch": 4.132016632016632, "percentage": 20.66, "elapsed_time": "0:23:09", "remaining_time": "1:28:55", "throughput": 1031.03, "total_tokens": 1432424} {"current_steps": 15905, "total_steps": 76960, "loss": 0.2906, "lr": 4.8287433459012844e-05, "epoch": 4.133316008316008, "percentage": 20.67, "elapsed_time": "0:23:09", "remaining_time": "1:28:54", "throughput": 1031.05, "total_tokens": 1432888} {"current_steps": 15910, "total_steps": 76960, "loss": 0.3194, "lr": 4.828537055422096e-05, "epoch": 4.134615384615385, "percentage": 20.67, "elapsed_time": "0:23:10", "remaining_time": "1:28:54", "throughput": 1031.08, "total_tokens": 1433352} {"current_steps": 15915, "total_steps": 76960, "loss": 0.2257, "lr": 4.828330645184016e-05, "epoch": 4.135914760914761, "percentage": 20.68, "elapsed_time": "0:23:10", "remaining_time": "1:28:53", "throughput": 1031.06, "total_tokens": 1433768} {"current_steps": 15920, "total_steps": 76960, "loss": 0.2755, "lr": 4.8281241151976596e-05, "epoch": 4.137214137214137, "percentage": 20.69, "elapsed_time": "0:23:10", "remaining_time": "1:28:53", "throughput": 1031.05, "total_tokens": 1434184} {"current_steps": 15925, "total_steps": 76960, "loss": 0.2646, "lr": 4.82791746547365e-05, "epoch": 4.138513513513513, "percentage": 20.69, "elapsed_time": "0:23:11", "remaining_time": "1:28:52", "throughput": 1031.05, "total_tokens": 1434616} {"current_steps": 15930, "total_steps": 76960, "loss": 0.2559, "lr": 4.8277106960226136e-05, "epoch": 4.13981288981289, "percentage": 20.7, "elapsed_time": "0:23:11", "remaining_time": "1:28:52", "throughput": 1031.07, "total_tokens": 1435080} {"current_steps": 15935, "total_steps": 76960, "loss": 0.2021, "lr": 4.8275038068551866e-05, "epoch": 4.141112266112266, "percentage": 20.71, "elapsed_time": "0:23:12", "remaining_time": "1:28:51", "throughput": 1031.08, "total_tokens": 1435512} {"current_steps": 15940, "total_steps": 76960, "loss": 0.2775, "lr": 4.827296797982008e-05, "epoch": 4.142411642411642, "percentage": 20.71, "elapsed_time": "0:23:12", "remaining_time": "1:28:51", "throughput": 1031.12, "total_tokens": 1436008} {"current_steps": 15945, "total_steps": 76960, "loss": 0.275, "lr": 4.827089669413726e-05, "epoch": 4.143711018711019, "percentage": 20.72, "elapsed_time": "0:23:13", "remaining_time": "1:28:50", "throughput": 1031.12, "total_tokens": 1436440} {"current_steps": 15950, "total_steps": 76960, "loss": 0.2081, "lr": 4.826882421160992e-05, "epoch": 4.145010395010395, "percentage": 20.73, "elapsed_time": "0:23:13", "remaining_time": "1:28:50", "throughput": 1031.14, "total_tokens": 1436904} {"current_steps": 15955, "total_steps": 76960, "loss": 0.2574, "lr": 4.826675053234466e-05, "epoch": 4.146309771309771, "percentage": 20.73, "elapsed_time": "0:23:13", "remaining_time": "1:28:49", "throughput": 1031.16, "total_tokens": 1437352} {"current_steps": 15960, "total_steps": 76960, "loss": 0.2592, "lr": 4.8264675656448126e-05, "epoch": 4.147609147609147, "percentage": 20.74, "elapsed_time": "0:23:14", "remaining_time": "1:28:49", "throughput": 1031.17, "total_tokens": 1437800} {"current_steps": 15965, "total_steps": 76960, "loss": 0.2635, "lr": 4.826259958402703e-05, "epoch": 4.148908523908524, "percentage": 20.74, "elapsed_time": "0:23:14", "remaining_time": "1:28:48", "throughput": 1031.2, "total_tokens": 1438280} {"current_steps": 15970, "total_steps": 76960, "loss": 0.2325, "lr": 4.826052231518815e-05, "epoch": 4.1502079002079, "percentage": 20.75, "elapsed_time": "0:23:15", "remaining_time": "1:28:48", "throughput": 1031.23, "total_tokens": 1438744} {"current_steps": 15975, "total_steps": 76960, "loss": 0.2438, "lr": 4.825844385003832e-05, "epoch": 4.151507276507276, "percentage": 20.76, "elapsed_time": "0:23:15", "remaining_time": "1:28:47", "throughput": 1031.24, "total_tokens": 1439192} {"current_steps": 15980, "total_steps": 76960, "loss": 0.2931, "lr": 4.825636418868443e-05, "epoch": 4.152806652806653, "percentage": 20.76, "elapsed_time": "0:23:16", "remaining_time": "1:28:47", "throughput": 1031.25, "total_tokens": 1439640} {"current_steps": 15985, "total_steps": 76960, "loss": 0.2803, "lr": 4.8254283331233464e-05, "epoch": 4.154106029106029, "percentage": 20.77, "elapsed_time": "0:23:16", "remaining_time": "1:28:46", "throughput": 1031.27, "total_tokens": 1440104} {"current_steps": 15990, "total_steps": 76960, "loss": 0.2601, "lr": 4.8252201277792405e-05, "epoch": 4.155405405405405, "percentage": 20.78, "elapsed_time": "0:23:16", "remaining_time": "1:28:46", "throughput": 1031.29, "total_tokens": 1440568} {"current_steps": 15995, "total_steps": 76960, "loss": 0.2078, "lr": 4.8250118028468374e-05, "epoch": 4.156704781704781, "percentage": 20.78, "elapsed_time": "0:23:17", "remaining_time": "1:28:45", "throughput": 1031.33, "total_tokens": 1441048} {"current_steps": 16000, "total_steps": 76960, "loss": 0.2263, "lr": 4.824803358336848e-05, "epoch": 4.158004158004158, "percentage": 20.79, "elapsed_time": "0:23:17", "remaining_time": "1:28:45", "throughput": 1031.34, "total_tokens": 1441496} {"current_steps": 16005, "total_steps": 76960, "loss": 0.1919, "lr": 4.8245947942599955e-05, "epoch": 4.159303534303534, "percentage": 20.8, "elapsed_time": "0:23:18", "remaining_time": "1:28:44", "throughput": 1031.35, "total_tokens": 1441944} {"current_steps": 16010, "total_steps": 76960, "loss": 0.1493, "lr": 4.824386110627005e-05, "epoch": 4.16060291060291, "percentage": 20.8, "elapsed_time": "0:23:18", "remaining_time": "1:28:44", "throughput": 1031.38, "total_tokens": 1442424} {"current_steps": 16015, "total_steps": 76960, "loss": 0.2194, "lr": 4.8241773074486094e-05, "epoch": 4.161902286902287, "percentage": 20.81, "elapsed_time": "0:23:18", "remaining_time": "1:28:43", "throughput": 1031.4, "total_tokens": 1442872} {"current_steps": 16020, "total_steps": 76960, "loss": 0.2015, "lr": 4.8239683847355475e-05, "epoch": 4.163201663201663, "percentage": 20.82, "elapsed_time": "0:23:19", "remaining_time": "1:28:43", "throughput": 1031.43, "total_tokens": 1443352} {"current_steps": 16025, "total_steps": 76960, "loss": 0.3222, "lr": 4.8237593424985664e-05, "epoch": 4.164501039501039, "percentage": 20.82, "elapsed_time": "0:23:19", "remaining_time": "1:28:42", "throughput": 1031.43, "total_tokens": 1443784} {"current_steps": 16030, "total_steps": 76960, "loss": 0.1935, "lr": 4.8235501807484144e-05, "epoch": 4.165800415800415, "percentage": 20.83, "elapsed_time": "0:23:20", "remaining_time": "1:28:42", "throughput": 1031.44, "total_tokens": 1444232} {"current_steps": 16035, "total_steps": 76960, "loss": 0.2373, "lr": 4.82334089949585e-05, "epoch": 4.167099792099792, "percentage": 20.84, "elapsed_time": "0:23:20", "remaining_time": "1:28:41", "throughput": 1031.42, "total_tokens": 1444632} {"current_steps": 16040, "total_steps": 76960, "loss": 0.3738, "lr": 4.823131498751638e-05, "epoch": 4.168399168399168, "percentage": 20.84, "elapsed_time": "0:23:21", "remaining_time": "1:28:41", "throughput": 1031.46, "total_tokens": 1445128} {"current_steps": 16045, "total_steps": 76960, "loss": 0.223, "lr": 4.8229219785265476e-05, "epoch": 4.169698544698544, "percentage": 20.85, "elapsed_time": "0:23:21", "remaining_time": "1:28:40", "throughput": 1031.45, "total_tokens": 1445544} {"current_steps": 16050, "total_steps": 76960, "loss": 0.2646, "lr": 4.8227123388313534e-05, "epoch": 4.170997920997921, "percentage": 20.85, "elapsed_time": "0:23:21", "remaining_time": "1:28:40", "throughput": 1031.5, "total_tokens": 1446040} {"current_steps": 16055, "total_steps": 76960, "loss": 0.3062, "lr": 4.822502579676839e-05, "epoch": 4.172297297297297, "percentage": 20.86, "elapsed_time": "0:23:22", "remaining_time": "1:28:39", "throughput": 1031.5, "total_tokens": 1446472} {"current_steps": 16060, "total_steps": 76960, "loss": 0.2725, "lr": 4.82229270107379e-05, "epoch": 4.173596673596673, "percentage": 20.87, "elapsed_time": "0:23:22", "remaining_time": "1:28:39", "throughput": 1031.52, "total_tokens": 1446936} {"current_steps": 16065, "total_steps": 76960, "loss": 0.2555, "lr": 4.822082703033003e-05, "epoch": 4.17489604989605, "percentage": 20.87, "elapsed_time": "0:23:23", "remaining_time": "1:28:38", "throughput": 1031.51, "total_tokens": 1447352} {"current_steps": 16070, "total_steps": 76960, "loss": 0.238, "lr": 4.821872585565278e-05, "epoch": 4.176195426195426, "percentage": 20.88, "elapsed_time": "0:23:23", "remaining_time": "1:28:38", "throughput": 1031.52, "total_tokens": 1447800} {"current_steps": 16075, "total_steps": 76960, "loss": 0.3193, "lr": 4.821662348681421e-05, "epoch": 4.177494802494802, "percentage": 20.89, "elapsed_time": "0:23:23", "remaining_time": "1:28:37", "throughput": 1031.54, "total_tokens": 1448264} {"current_steps": 16080, "total_steps": 76960, "loss": 0.1954, "lr": 4.821451992392245e-05, "epoch": 4.1787941787941785, "percentage": 20.89, "elapsed_time": "0:23:24", "remaining_time": "1:28:37", "throughput": 1031.55, "total_tokens": 1448712} {"current_steps": 16085, "total_steps": 76960, "loss": 0.177, "lr": 4.821241516708568e-05, "epoch": 4.180093555093555, "percentage": 20.9, "elapsed_time": "0:23:24", "remaining_time": "1:28:36", "throughput": 1031.56, "total_tokens": 1449160} {"current_steps": 16090, "total_steps": 76960, "loss": 0.1811, "lr": 4.821030921641216e-05, "epoch": 4.1813929313929314, "percentage": 20.91, "elapsed_time": "0:23:25", "remaining_time": "1:28:36", "throughput": 1031.59, "total_tokens": 1449624} {"current_steps": 16095, "total_steps": 76960, "loss": 0.1482, "lr": 4.8208202072010204e-05, "epoch": 4.1826923076923075, "percentage": 20.91, "elapsed_time": "0:23:25", "remaining_time": "1:28:35", "throughput": 1031.61, "total_tokens": 1450088} {"current_steps": 16100, "total_steps": 76960, "loss": 0.25, "lr": 4.820609373398818e-05, "epoch": 4.183991683991684, "percentage": 20.92, "elapsed_time": "0:23:26", "remaining_time": "1:28:35", "throughput": 1031.63, "total_tokens": 1450552} {"current_steps": 16105, "total_steps": 76960, "loss": 0.1416, "lr": 4.820398420245451e-05, "epoch": 4.1852910602910605, "percentage": 20.93, "elapsed_time": "0:23:26", "remaining_time": "1:28:34", "throughput": 1031.62, "total_tokens": 1450968} {"current_steps": 16110, "total_steps": 76960, "loss": 0.2694, "lr": 4.820187347751771e-05, "epoch": 4.1865904365904365, "percentage": 20.93, "elapsed_time": "0:23:26", "remaining_time": "1:28:34", "throughput": 1031.62, "total_tokens": 1451400} {"current_steps": 16115, "total_steps": 76960, "loss": 0.392, "lr": 4.819976155928631e-05, "epoch": 4.1878898128898125, "percentage": 20.94, "elapsed_time": "0:23:27", "remaining_time": "1:28:33", "throughput": 1031.6, "total_tokens": 1451800} {"current_steps": 16120, "total_steps": 76960, "loss": 0.2821, "lr": 4.819764844786896e-05, "epoch": 4.1891891891891895, "percentage": 20.95, "elapsed_time": "0:23:27", "remaining_time": "1:28:33", "throughput": 1031.59, "total_tokens": 1452216} {"current_steps": 16125, "total_steps": 76960, "loss": 0.267, "lr": 4.819553414337432e-05, "epoch": 4.1904885654885655, "percentage": 20.95, "elapsed_time": "0:23:28", "remaining_time": "1:28:32", "throughput": 1031.6, "total_tokens": 1452664} {"current_steps": 16130, "total_steps": 76960, "loss": 0.2633, "lr": 4.819341864591113e-05, "epoch": 4.191787941787942, "percentage": 20.96, "elapsed_time": "0:23:28", "remaining_time": "1:28:32", "throughput": 1031.68, "total_tokens": 1453208} {"current_steps": 16135, "total_steps": 76960, "loss": 0.2535, "lr": 4.81913019555882e-05, "epoch": 4.1930873180873185, "percentage": 20.97, "elapsed_time": "0:23:29", "remaining_time": "1:28:31", "throughput": 1031.68, "total_tokens": 1453640} {"current_steps": 16140, "total_steps": 76960, "loss": 0.2688, "lr": 4.818918407251439e-05, "epoch": 4.1943866943866945, "percentage": 20.97, "elapsed_time": "0:23:29", "remaining_time": "1:28:31", "throughput": 1031.71, "total_tokens": 1454120} {"current_steps": 16145, "total_steps": 76960, "loss": 0.2854, "lr": 4.818706499679862e-05, "epoch": 4.195686070686071, "percentage": 20.98, "elapsed_time": "0:23:29", "remaining_time": "1:28:30", "throughput": 1031.71, "total_tokens": 1454552} {"current_steps": 16150, "total_steps": 76960, "loss": 0.215, "lr": 4.818494472854988e-05, "epoch": 4.196985446985447, "percentage": 20.98, "elapsed_time": "0:23:30", "remaining_time": "1:28:30", "throughput": 1031.77, "total_tokens": 1455064} {"current_steps": 16155, "total_steps": 76960, "loss": 0.2585, "lr": 4.818282326787722e-05, "epoch": 4.1982848232848236, "percentage": 20.99, "elapsed_time": "0:23:30", "remaining_time": "1:28:29", "throughput": 1031.77, "total_tokens": 1455496} {"current_steps": 16160, "total_steps": 76960, "loss": 0.2334, "lr": 4.818070061488975e-05, "epoch": 4.1995841995842, "percentage": 21.0, "elapsed_time": "0:23:31", "remaining_time": "1:28:29", "throughput": 1031.78, "total_tokens": 1455944} {"current_steps": 16165, "total_steps": 76960, "loss": 0.2588, "lr": 4.817857676969663e-05, "epoch": 4.200883575883576, "percentage": 21.0, "elapsed_time": "0:23:31", "remaining_time": "1:28:28", "throughput": 1031.78, "total_tokens": 1456376} {"current_steps": 16170, "total_steps": 76960, "loss": 0.3519, "lr": 4.8176451732407104e-05, "epoch": 4.202182952182953, "percentage": 21.01, "elapsed_time": "0:23:31", "remaining_time": "1:28:28", "throughput": 1031.78, "total_tokens": 1456824} {"current_steps": 16175, "total_steps": 76960, "loss": 0.137, "lr": 4.8174325503130454e-05, "epoch": 4.203482328482329, "percentage": 21.02, "elapsed_time": "0:23:32", "remaining_time": "1:28:27", "throughput": 1031.78, "total_tokens": 1457256} {"current_steps": 16180, "total_steps": 76960, "loss": 0.2462, "lr": 4.8172198081976046e-05, "epoch": 4.204781704781705, "percentage": 21.02, "elapsed_time": "0:23:32", "remaining_time": "1:28:27", "throughput": 1031.79, "total_tokens": 1457720} {"current_steps": 16185, "total_steps": 76960, "loss": 0.3069, "lr": 4.817006946905328e-05, "epoch": 4.206081081081081, "percentage": 21.03, "elapsed_time": "0:23:33", "remaining_time": "1:28:26", "throughput": 1031.79, "total_tokens": 1458152} {"current_steps": 16190, "total_steps": 76960, "loss": 0.1763, "lr": 4.816793966447165e-05, "epoch": 4.207380457380458, "percentage": 21.04, "elapsed_time": "0:23:33", "remaining_time": "1:28:26", "throughput": 1031.83, "total_tokens": 1458632} {"current_steps": 16195, "total_steps": 76960, "loss": 0.2152, "lr": 4.8165808668340675e-05, "epoch": 4.208679833679834, "percentage": 21.04, "elapsed_time": "0:23:34", "remaining_time": "1:28:25", "throughput": 1031.83, "total_tokens": 1459064} {"current_steps": 16200, "total_steps": 76960, "loss": 0.3434, "lr": 4.8163676480769974e-05, "epoch": 4.20997920997921, "percentage": 21.05, "elapsed_time": "0:23:34", "remaining_time": "1:28:25", "throughput": 1031.85, "total_tokens": 1459528} {"current_steps": 16205, "total_steps": 76960, "loss": 0.2571, "lr": 4.816154310186919e-05, "epoch": 4.211278586278587, "percentage": 21.06, "elapsed_time": "0:23:34", "remaining_time": "1:28:24", "throughput": 1031.84, "total_tokens": 1459944} {"current_steps": 16210, "total_steps": 76960, "loss": 0.2659, "lr": 4.8159408531748054e-05, "epoch": 4.212577962577963, "percentage": 21.06, "elapsed_time": "0:23:35", "remaining_time": "1:28:24", "throughput": 1031.86, "total_tokens": 1460408} {"current_steps": 16215, "total_steps": 76960, "loss": 0.1577, "lr": 4.815727277051634e-05, "epoch": 4.213877338877339, "percentage": 21.07, "elapsed_time": "0:23:35", "remaining_time": "1:28:23", "throughput": 1031.86, "total_tokens": 1460840} {"current_steps": 16220, "total_steps": 76960, "loss": 0.268, "lr": 4.81551358182839e-05, "epoch": 4.215176715176715, "percentage": 21.08, "elapsed_time": "0:23:36", "remaining_time": "1:28:23", "throughput": 1031.88, "total_tokens": 1461304} {"current_steps": 16225, "total_steps": 76960, "loss": 0.1525, "lr": 4.815299767516065e-05, "epoch": 4.216476091476092, "percentage": 21.08, "elapsed_time": "0:23:36", "remaining_time": "1:28:22", "throughput": 1031.91, "total_tokens": 1461768} {"current_steps": 16230, "total_steps": 76960, "loss": 0.2449, "lr": 4.8150858341256535e-05, "epoch": 4.217775467775468, "percentage": 21.09, "elapsed_time": "0:23:36", "remaining_time": "1:28:22", "throughput": 1031.92, "total_tokens": 1462216} {"current_steps": 16235, "total_steps": 76960, "loss": 0.4635, "lr": 4.81487178166816e-05, "epoch": 4.219074844074844, "percentage": 21.1, "elapsed_time": "0:23:37", "remaining_time": "1:28:21", "throughput": 1031.94, "total_tokens": 1462680} {"current_steps": 16240, "total_steps": 76960, "loss": 0.1286, "lr": 4.814657610154593e-05, "epoch": 4.220374220374221, "percentage": 21.1, "elapsed_time": "0:23:37", "remaining_time": "1:28:21", "throughput": 1031.98, "total_tokens": 1463160} {"current_steps": 16245, "total_steps": 76960, "loss": 0.1832, "lr": 4.8144433195959666e-05, "epoch": 4.221673596673597, "percentage": 21.11, "elapsed_time": "0:23:38", "remaining_time": "1:28:20", "throughput": 1031.98, "total_tokens": 1463592} {"current_steps": 16250, "total_steps": 76960, "loss": 0.1193, "lr": 4.814228910003303e-05, "epoch": 4.222972972972973, "percentage": 21.11, "elapsed_time": "0:23:38", "remaining_time": "1:28:20", "throughput": 1032.02, "total_tokens": 1464088} {"current_steps": 16255, "total_steps": 76960, "loss": 0.0903, "lr": 4.814014381387629e-05, "epoch": 4.224272349272349, "percentage": 21.12, "elapsed_time": "0:23:39", "remaining_time": "1:28:19", "throughput": 1032.01, "total_tokens": 1464504} {"current_steps": 16260, "total_steps": 76960, "loss": 0.2891, "lr": 4.8137997337599785e-05, "epoch": 4.225571725571726, "percentage": 21.13, "elapsed_time": "0:23:39", "remaining_time": "1:28:19", "throughput": 1032.0, "total_tokens": 1464920} {"current_steps": 16265, "total_steps": 76960, "loss": 0.2822, "lr": 4.8135849671313904e-05, "epoch": 4.226871101871102, "percentage": 21.13, "elapsed_time": "0:23:39", "remaining_time": "1:28:18", "throughput": 1032.01, "total_tokens": 1465368} {"current_steps": 16270, "total_steps": 76960, "loss": 0.1408, "lr": 4.813370081512911e-05, "epoch": 4.228170478170478, "percentage": 21.14, "elapsed_time": "0:23:40", "remaining_time": "1:28:18", "throughput": 1032.01, "total_tokens": 1465800} {"current_steps": 16275, "total_steps": 76960, "loss": 0.4113, "lr": 4.8131550769155906e-05, "epoch": 4.229469854469855, "percentage": 21.15, "elapsed_time": "0:23:40", "remaining_time": "1:28:17", "throughput": 1032.03, "total_tokens": 1466248} {"current_steps": 16280, "total_steps": 76960, "loss": 0.2152, "lr": 4.812939953350489e-05, "epoch": 4.230769230769231, "percentage": 21.15, "elapsed_time": "0:23:41", "remaining_time": "1:28:17", "throughput": 1032.03, "total_tokens": 1466680} {"current_steps": 16285, "total_steps": 76960, "loss": 0.346, "lr": 4.81272471082867e-05, "epoch": 4.232068607068607, "percentage": 21.16, "elapsed_time": "0:23:41", "remaining_time": "1:28:16", "throughput": 1032.04, "total_tokens": 1467128} {"current_steps": 16290, "total_steps": 76960, "loss": 0.2316, "lr": 4.8125093493612026e-05, "epoch": 4.233367983367984, "percentage": 21.17, "elapsed_time": "0:23:42", "remaining_time": "1:28:16", "throughput": 1032.04, "total_tokens": 1467560} {"current_steps": 16295, "total_steps": 76960, "loss": 0.2263, "lr": 4.8122938689591644e-05, "epoch": 4.23466735966736, "percentage": 21.17, "elapsed_time": "0:23:42", "remaining_time": "1:28:15", "throughput": 1032.05, "total_tokens": 1468008} {"current_steps": 16300, "total_steps": 76960, "loss": 0.2596, "lr": 4.8120782696336366e-05, "epoch": 4.235966735966736, "percentage": 21.18, "elapsed_time": "0:23:42", "remaining_time": "1:28:15", "throughput": 1032.07, "total_tokens": 1468472} {"current_steps": 16305, "total_steps": 76960, "loss": 0.2977, "lr": 4.8118625513957074e-05, "epoch": 4.237266112266112, "percentage": 21.19, "elapsed_time": "0:23:43", "remaining_time": "1:28:14", "throughput": 1032.08, "total_tokens": 1468920} {"current_steps": 16310, "total_steps": 76960, "loss": 0.1464, "lr": 4.811646714256473e-05, "epoch": 4.238565488565489, "percentage": 21.19, "elapsed_time": "0:23:43", "remaining_time": "1:28:14", "throughput": 1032.08, "total_tokens": 1469352} {"current_steps": 16315, "total_steps": 76960, "loss": 0.1635, "lr": 4.811430758227032e-05, "epoch": 4.239864864864865, "percentage": 21.2, "elapsed_time": "0:23:44", "remaining_time": "1:28:13", "throughput": 1032.13, "total_tokens": 1469848} {"current_steps": 16320, "total_steps": 76960, "loss": 0.2499, "lr": 4.8112146833184937e-05, "epoch": 4.241164241164241, "percentage": 21.21, "elapsed_time": "0:23:44", "remaining_time": "1:28:13", "throughput": 1032.14, "total_tokens": 1470296} {"current_steps": 16325, "total_steps": 76960, "loss": 0.3066, "lr": 4.810998489541969e-05, "epoch": 4.242463617463618, "percentage": 21.21, "elapsed_time": "0:23:44", "remaining_time": "1:28:12", "throughput": 1032.14, "total_tokens": 1470728} {"current_steps": 16330, "total_steps": 76960, "loss": 0.2513, "lr": 4.8107821769085775e-05, "epoch": 4.243762993762994, "percentage": 21.22, "elapsed_time": "0:23:45", "remaining_time": "1:28:12", "throughput": 1032.14, "total_tokens": 1471160} {"current_steps": 16335, "total_steps": 76960, "loss": 0.3589, "lr": 4.810565745429445e-05, "epoch": 4.24506237006237, "percentage": 21.23, "elapsed_time": "0:23:45", "remaining_time": "1:28:11", "throughput": 1032.15, "total_tokens": 1471608} {"current_steps": 16340, "total_steps": 76960, "loss": 0.2653, "lr": 4.810349195115702e-05, "epoch": 4.246361746361746, "percentage": 21.23, "elapsed_time": "0:23:46", "remaining_time": "1:28:11", "throughput": 1032.15, "total_tokens": 1472040} {"current_steps": 16345, "total_steps": 76960, "loss": 0.3084, "lr": 4.810132525978487e-05, "epoch": 4.247661122661123, "percentage": 21.24, "elapsed_time": "0:23:46", "remaining_time": "1:28:10", "throughput": 1032.16, "total_tokens": 1472488} {"current_steps": 16350, "total_steps": 76960, "loss": 0.2791, "lr": 4.809915738028942e-05, "epoch": 4.248960498960499, "percentage": 21.24, "elapsed_time": "0:23:47", "remaining_time": "1:28:10", "throughput": 1032.18, "total_tokens": 1472952} {"current_steps": 16355, "total_steps": 76960, "loss": 0.2768, "lr": 4.8096988312782174e-05, "epoch": 4.250259875259875, "percentage": 21.25, "elapsed_time": "0:23:47", "remaining_time": "1:28:09", "throughput": 1032.21, "total_tokens": 1473416} {"current_steps": 16360, "total_steps": 76960, "loss": 0.2583, "lr": 4.8094818057374686e-05, "epoch": 4.251559251559252, "percentage": 21.26, "elapsed_time": "0:23:47", "remaining_time": "1:28:09", "throughput": 1032.21, "total_tokens": 1473848} {"current_steps": 16365, "total_steps": 76960, "loss": 0.2759, "lr": 4.809264661417858e-05, "epoch": 4.252858627858628, "percentage": 21.26, "elapsed_time": "0:23:48", "remaining_time": "1:28:08", "throughput": 1032.22, "total_tokens": 1474296} {"current_steps": 16370, "total_steps": 76960, "loss": 0.2504, "lr": 4.8090473983305535e-05, "epoch": 4.254158004158004, "percentage": 21.27, "elapsed_time": "0:23:48", "remaining_time": "1:28:08", "throughput": 1032.25, "total_tokens": 1474776} {"current_steps": 16375, "total_steps": 76960, "loss": 0.2638, "lr": 4.8088300164867284e-05, "epoch": 4.25545738045738, "percentage": 21.28, "elapsed_time": "0:23:49", "remaining_time": "1:28:07", "throughput": 1032.29, "total_tokens": 1475256} {"current_steps": 16380, "total_steps": 76960, "loss": 0.2954, "lr": 4.808612515897564e-05, "epoch": 4.256756756756757, "percentage": 21.28, "elapsed_time": "0:23:49", "remaining_time": "1:28:06", "throughput": 1032.33, "total_tokens": 1475752} {"current_steps": 16385, "total_steps": 76960, "loss": 0.2122, "lr": 4.808394896574245e-05, "epoch": 4.258056133056133, "percentage": 21.29, "elapsed_time": "0:23:49", "remaining_time": "1:28:06", "throughput": 1032.33, "total_tokens": 1476184} {"current_steps": 16390, "total_steps": 76960, "loss": 0.1931, "lr": 4.808177158527965e-05, "epoch": 4.259355509355509, "percentage": 21.3, "elapsed_time": "0:23:50", "remaining_time": "1:28:05", "throughput": 1032.33, "total_tokens": 1476616} {"current_steps": 16395, "total_steps": 76960, "loss": 0.217, "lr": 4.807959301769923e-05, "epoch": 4.260654885654886, "percentage": 21.3, "elapsed_time": "0:23:50", "remaining_time": "1:28:05", "throughput": 1032.33, "total_tokens": 1477048} {"current_steps": 16400, "total_steps": 76960, "loss": 0.2701, "lr": 4.807741326311321e-05, "epoch": 4.261954261954262, "percentage": 21.31, "elapsed_time": "0:23:51", "remaining_time": "1:28:04", "throughput": 1032.33, "total_tokens": 1477480} {"current_steps": 16405, "total_steps": 76960, "loss": 0.1513, "lr": 4.8075232321633736e-05, "epoch": 4.263253638253638, "percentage": 21.32, "elapsed_time": "0:23:51", "remaining_time": "1:28:04", "throughput": 1032.33, "total_tokens": 1477912} {"current_steps": 16410, "total_steps": 76960, "loss": 0.2749, "lr": 4.8073050193372935e-05, "epoch": 4.264553014553014, "percentage": 21.32, "elapsed_time": "0:23:52", "remaining_time": "1:28:03", "throughput": 1032.33, "total_tokens": 1478344} {"current_steps": 16415, "total_steps": 76960, "loss": 0.2395, "lr": 4.8070866878443065e-05, "epoch": 4.265852390852391, "percentage": 21.33, "elapsed_time": "0:23:52", "remaining_time": "1:28:03", "throughput": 1032.37, "total_tokens": 1478824} {"current_steps": 16420, "total_steps": 76960, "loss": 0.2645, "lr": 4.806868237695641e-05, "epoch": 4.267151767151767, "percentage": 21.34, "elapsed_time": "0:23:52", "remaining_time": "1:28:02", "throughput": 1032.38, "total_tokens": 1479272} {"current_steps": 16425, "total_steps": 76960, "loss": 0.2175, "lr": 4.806649668902531e-05, "epoch": 4.268451143451143, "percentage": 21.34, "elapsed_time": "0:23:53", "remaining_time": "1:28:02", "throughput": 1032.39, "total_tokens": 1479720} {"current_steps": 16430, "total_steps": 76960, "loss": 0.2538, "lr": 4.8064309814762176e-05, "epoch": 4.26975051975052, "percentage": 21.35, "elapsed_time": "0:23:53", "remaining_time": "1:28:01", "throughput": 1032.38, "total_tokens": 1480136} {"current_steps": 16435, "total_steps": 76960, "loss": 0.2884, "lr": 4.80621217542795e-05, "epoch": 4.271049896049896, "percentage": 21.36, "elapsed_time": "0:23:54", "remaining_time": "1:28:01", "throughput": 1032.37, "total_tokens": 1480552} {"current_steps": 16440, "total_steps": 76960, "loss": 0.2576, "lr": 4.805993250768981e-05, "epoch": 4.272349272349272, "percentage": 21.36, "elapsed_time": "0:23:54", "remaining_time": "1:28:00", "throughput": 1032.41, "total_tokens": 1481032} {"current_steps": 16445, "total_steps": 76960, "loss": 0.1529, "lr": 4.805774207510568e-05, "epoch": 4.273648648648648, "percentage": 21.37, "elapsed_time": "0:23:54", "remaining_time": "1:28:00", "throughput": 1032.41, "total_tokens": 1481464} {"current_steps": 16450, "total_steps": 76960, "loss": 0.3222, "lr": 4.8055550456639796e-05, "epoch": 4.274948024948025, "percentage": 21.37, "elapsed_time": "0:23:55", "remaining_time": "1:27:59", "throughput": 1032.43, "total_tokens": 1481928} {"current_steps": 16455, "total_steps": 76960, "loss": 0.3122, "lr": 4.805335765240486e-05, "epoch": 4.276247401247401, "percentage": 21.38, "elapsed_time": "0:23:55", "remaining_time": "1:27:59", "throughput": 1032.43, "total_tokens": 1482360} {"current_steps": 16460, "total_steps": 76960, "loss": 0.2232, "lr": 4.805116366251364e-05, "epoch": 4.277546777546777, "percentage": 21.39, "elapsed_time": "0:23:56", "remaining_time": "1:27:58", "throughput": 1032.44, "total_tokens": 1482808} {"current_steps": 16465, "total_steps": 76960, "loss": 0.2631, "lr": 4.8048968487079e-05, "epoch": 4.278846153846154, "percentage": 21.39, "elapsed_time": "0:23:56", "remaining_time": "1:27:58", "throughput": 1032.45, "total_tokens": 1483256} {"current_steps": 16470, "total_steps": 76960, "loss": 0.298, "lr": 4.804677212621382e-05, "epoch": 4.28014553014553, "percentage": 21.4, "elapsed_time": "0:23:57", "remaining_time": "1:27:57", "throughput": 1032.48, "total_tokens": 1483736} {"current_steps": 16475, "total_steps": 76960, "loss": 0.2273, "lr": 4.8044574580031065e-05, "epoch": 4.281444906444906, "percentage": 21.41, "elapsed_time": "0:23:57", "remaining_time": "1:27:57", "throughput": 1032.47, "total_tokens": 1484152} {"current_steps": 16480, "total_steps": 76960, "loss": 0.2506, "lr": 4.8042375848643764e-05, "epoch": 4.282744282744282, "percentage": 21.41, "elapsed_time": "0:23:57", "remaining_time": "1:27:56", "throughput": 1032.49, "total_tokens": 1484616} {"current_steps": 16485, "total_steps": 76960, "loss": 0.3266, "lr": 4.804017593216499e-05, "epoch": 4.284043659043659, "percentage": 21.42, "elapsed_time": "0:23:58", "remaining_time": "1:27:56", "throughput": 1032.49, "total_tokens": 1485048} {"current_steps": 16490, "total_steps": 76960, "loss": 0.2705, "lr": 4.80379748307079e-05, "epoch": 4.285343035343035, "percentage": 21.43, "elapsed_time": "0:23:58", "remaining_time": "1:27:55", "throughput": 1032.51, "total_tokens": 1485496} {"current_steps": 16495, "total_steps": 76960, "loss": 0.2513, "lr": 4.8035772544385685e-05, "epoch": 4.286642411642411, "percentage": 21.43, "elapsed_time": "0:23:59", "remaining_time": "1:27:55", "throughput": 1032.48, "total_tokens": 1485896} {"current_steps": 16500, "total_steps": 76960, "loss": 0.2363, "lr": 4.803356907331161e-05, "epoch": 4.287941787941788, "percentage": 21.44, "elapsed_time": "0:23:59", "remaining_time": "1:27:54", "throughput": 1032.49, "total_tokens": 1486344} {"current_steps": 16505, "total_steps": 76960, "loss": 0.256, "lr": 4.803136441759902e-05, "epoch": 4.289241164241164, "percentage": 21.45, "elapsed_time": "0:23:59", "remaining_time": "1:27:54", "throughput": 1032.48, "total_tokens": 1486760} {"current_steps": 16510, "total_steps": 76960, "loss": 0.2269, "lr": 4.8029158577361275e-05, "epoch": 4.29054054054054, "percentage": 21.45, "elapsed_time": "0:24:00", "remaining_time": "1:27:53", "throughput": 1032.51, "total_tokens": 1487240} {"current_steps": 16515, "total_steps": 76960, "loss": 0.223, "lr": 4.802695155271185e-05, "epoch": 4.291839916839917, "percentage": 21.46, "elapsed_time": "0:24:00", "remaining_time": "1:27:53", "throughput": 1032.52, "total_tokens": 1487688} {"current_steps": 16520, "total_steps": 76960, "loss": 0.2447, "lr": 4.802474334376425e-05, "epoch": 4.293139293139293, "percentage": 21.47, "elapsed_time": "0:24:01", "remaining_time": "1:27:52", "throughput": 1032.54, "total_tokens": 1488136} {"current_steps": 16525, "total_steps": 76960, "loss": 0.2683, "lr": 4.802253395063203e-05, "epoch": 4.294438669438669, "percentage": 21.47, "elapsed_time": "0:24:01", "remaining_time": "1:27:52", "throughput": 1032.54, "total_tokens": 1488568} {"current_steps": 16530, "total_steps": 76960, "loss": 0.2709, "lr": 4.802032337342882e-05, "epoch": 4.295738045738045, "percentage": 21.48, "elapsed_time": "0:24:02", "remaining_time": "1:27:51", "throughput": 1032.55, "total_tokens": 1489016} {"current_steps": 16535, "total_steps": 76960, "loss": 0.3348, "lr": 4.801811161226834e-05, "epoch": 4.297037422037422, "percentage": 21.49, "elapsed_time": "0:24:02", "remaining_time": "1:27:51", "throughput": 1032.58, "total_tokens": 1489496} {"current_steps": 16540, "total_steps": 76960, "loss": 0.3023, "lr": 4.8015898667264316e-05, "epoch": 4.298336798336798, "percentage": 21.49, "elapsed_time": "0:24:02", "remaining_time": "1:27:50", "throughput": 1032.58, "total_tokens": 1489928} {"current_steps": 16545, "total_steps": 76960, "loss": 0.2082, "lr": 4.8013684538530565e-05, "epoch": 4.299636174636174, "percentage": 21.5, "elapsed_time": "0:24:03", "remaining_time": "1:27:50", "throughput": 1032.57, "total_tokens": 1490344} {"current_steps": 16550, "total_steps": 76960, "loss": 0.3049, "lr": 4.801146922618098e-05, "epoch": 4.3009355509355505, "percentage": 21.5, "elapsed_time": "0:24:03", "remaining_time": "1:27:49", "throughput": 1032.58, "total_tokens": 1490792} {"current_steps": 16555, "total_steps": 76960, "loss": 0.264, "lr": 4.8009252730329476e-05, "epoch": 4.302234927234927, "percentage": 21.51, "elapsed_time": "0:24:04", "remaining_time": "1:27:49", "throughput": 1032.62, "total_tokens": 1491272} {"current_steps": 16560, "total_steps": 76960, "loss": 0.3043, "lr": 4.800703505109006e-05, "epoch": 4.303534303534303, "percentage": 21.52, "elapsed_time": "0:24:04", "remaining_time": "1:27:48", "throughput": 1032.6, "total_tokens": 1491688} {"current_steps": 16565, "total_steps": 76960, "loss": 0.2937, "lr": 4.8004816188576783e-05, "epoch": 4.3048336798336795, "percentage": 21.52, "elapsed_time": "0:24:05", "remaining_time": "1:27:48", "throughput": 1032.6, "total_tokens": 1492120} {"current_steps": 16570, "total_steps": 76960, "loss": 0.2601, "lr": 4.800259614290378e-05, "epoch": 4.306133056133056, "percentage": 21.53, "elapsed_time": "0:24:05", "remaining_time": "1:27:47", "throughput": 1032.6, "total_tokens": 1492552} {"current_steps": 16575, "total_steps": 76960, "loss": 0.2988, "lr": 4.800037491418521e-05, "epoch": 4.3074324324324325, "percentage": 21.54, "elapsed_time": "0:24:05", "remaining_time": "1:27:47", "throughput": 1032.6, "total_tokens": 1492984} {"current_steps": 16580, "total_steps": 76960, "loss": 0.2754, "lr": 4.7998152502535316e-05, "epoch": 4.3087318087318085, "percentage": 21.54, "elapsed_time": "0:24:06", "remaining_time": "1:27:46", "throughput": 1032.6, "total_tokens": 1493416} {"current_steps": 16585, "total_steps": 76960, "loss": 0.2717, "lr": 4.79959289080684e-05, "epoch": 4.310031185031185, "percentage": 21.55, "elapsed_time": "0:24:06", "remaining_time": "1:27:46", "throughput": 1032.64, "total_tokens": 1493896} {"current_steps": 16590, "total_steps": 76960, "loss": 0.248, "lr": 4.799370413089884e-05, "epoch": 4.3113305613305615, "percentage": 21.56, "elapsed_time": "0:24:07", "remaining_time": "1:27:45", "throughput": 1032.66, "total_tokens": 1494360} {"current_steps": 16595, "total_steps": 76960, "loss": 0.2854, "lr": 4.799147817114104e-05, "epoch": 4.3126299376299375, "percentage": 21.56, "elapsed_time": "0:24:07", "remaining_time": "1:27:45", "throughput": 1032.68, "total_tokens": 1494824} {"current_steps": 16600, "total_steps": 76960, "loss": 0.1874, "lr": 4.7989251028909476e-05, "epoch": 4.313929313929314, "percentage": 21.57, "elapsed_time": "0:24:07", "remaining_time": "1:27:44", "throughput": 1032.7, "total_tokens": 1495288} {"current_steps": 16605, "total_steps": 76960, "loss": 0.2628, "lr": 4.798702270431872e-05, "epoch": 4.3152286902286905, "percentage": 21.58, "elapsed_time": "0:24:08", "remaining_time": "1:27:44", "throughput": 1032.73, "total_tokens": 1495752} {"current_steps": 16610, "total_steps": 76960, "loss": 0.1734, "lr": 4.7984793197483356e-05, "epoch": 4.3165280665280665, "percentage": 21.58, "elapsed_time": "0:24:08", "remaining_time": "1:27:43", "throughput": 1032.72, "total_tokens": 1496168} {"current_steps": 16615, "total_steps": 76960, "loss": 0.278, "lr": 4.798256250851805e-05, "epoch": 4.317827442827443, "percentage": 21.59, "elapsed_time": "0:24:09", "remaining_time": "1:27:43", "throughput": 1032.76, "total_tokens": 1496664} {"current_steps": 16620, "total_steps": 76960, "loss": 0.4004, "lr": 4.798033063753754e-05, "epoch": 4.3191268191268195, "percentage": 21.6, "elapsed_time": "0:24:09", "remaining_time": "1:27:42", "throughput": 1032.77, "total_tokens": 1497112} {"current_steps": 16625, "total_steps": 76960, "loss": 0.3004, "lr": 4.79780975846566e-05, "epoch": 4.3204261954261955, "percentage": 21.6, "elapsed_time": "0:24:10", "remaining_time": "1:27:42", "throughput": 1032.76, "total_tokens": 1497528} {"current_steps": 16630, "total_steps": 76960, "loss": 0.2323, "lr": 4.797586334999009e-05, "epoch": 4.321725571725572, "percentage": 21.61, "elapsed_time": "0:24:10", "remaining_time": "1:27:41", "throughput": 1032.8, "total_tokens": 1498008} {"current_steps": 16635, "total_steps": 76960, "loss": 0.1866, "lr": 4.797362793365291e-05, "epoch": 4.323024948024948, "percentage": 21.62, "elapsed_time": "0:24:10", "remaining_time": "1:27:41", "throughput": 1032.8, "total_tokens": 1498440} {"current_steps": 16640, "total_steps": 76960, "loss": 0.2902, "lr": 4.797139133576004e-05, "epoch": 4.324324324324325, "percentage": 21.62, "elapsed_time": "0:24:11", "remaining_time": "1:27:40", "throughput": 1032.83, "total_tokens": 1498920} {"current_steps": 16645, "total_steps": 76960, "loss": 0.2177, "lr": 4.79691535564265e-05, "epoch": 4.325623700623701, "percentage": 21.63, "elapsed_time": "0:24:11", "remaining_time": "1:27:40", "throughput": 1032.85, "total_tokens": 1499384} {"current_steps": 16650, "total_steps": 76960, "loss": 0.1674, "lr": 4.796691459576739e-05, "epoch": 4.326923076923077, "percentage": 21.63, "elapsed_time": "0:24:12", "remaining_time": "1:27:39", "throughput": 1032.85, "total_tokens": 1499816} {"current_steps": 16655, "total_steps": 76960, "loss": 0.2763, "lr": 4.796467445389784e-05, "epoch": 4.328222453222454, "percentage": 21.64, "elapsed_time": "0:24:12", "remaining_time": "1:27:39", "throughput": 1032.88, "total_tokens": 1500296} {"current_steps": 16660, "total_steps": 76960, "loss": 0.3459, "lr": 4.7962433130933096e-05, "epoch": 4.32952182952183, "percentage": 21.65, "elapsed_time": "0:24:12", "remaining_time": "1:27:38", "throughput": 1032.9, "total_tokens": 1500744} {"current_steps": 16665, "total_steps": 76960, "loss": 0.3002, "lr": 4.7960190626988405e-05, "epoch": 4.330821205821206, "percentage": 21.65, "elapsed_time": "0:24:13", "remaining_time": "1:27:38", "throughput": 1032.92, "total_tokens": 1501208} {"current_steps": 16670, "total_steps": 76960, "loss": 0.2605, "lr": 4.795794694217911e-05, "epoch": 4.332120582120582, "percentage": 21.66, "elapsed_time": "0:24:13", "remaining_time": "1:27:37", "throughput": 1032.94, "total_tokens": 1501672} {"current_steps": 16675, "total_steps": 76960, "loss": 0.2328, "lr": 4.795570207662061e-05, "epoch": 4.333419958419959, "percentage": 21.67, "elapsed_time": "0:24:14", "remaining_time": "1:27:37", "throughput": 1032.96, "total_tokens": 1502136} {"current_steps": 16680, "total_steps": 76960, "loss": 0.2943, "lr": 4.795345603042836e-05, "epoch": 4.334719334719335, "percentage": 21.67, "elapsed_time": "0:24:14", "remaining_time": "1:27:36", "throughput": 1032.96, "total_tokens": 1502568} {"current_steps": 16685, "total_steps": 76960, "loss": 0.276, "lr": 4.7951208803717876e-05, "epoch": 4.336018711018711, "percentage": 21.68, "elapsed_time": "0:24:15", "remaining_time": "1:27:36", "throughput": 1032.95, "total_tokens": 1502984} {"current_steps": 16690, "total_steps": 76960, "loss": 0.3066, "lr": 4.794896039660472e-05, "epoch": 4.337318087318088, "percentage": 21.69, "elapsed_time": "0:24:15", "remaining_time": "1:27:35", "throughput": 1032.94, "total_tokens": 1503400} {"current_steps": 16695, "total_steps": 76960, "loss": 0.263, "lr": 4.794671080920455e-05, "epoch": 4.338617463617464, "percentage": 21.69, "elapsed_time": "0:24:15", "remaining_time": "1:27:35", "throughput": 1032.95, "total_tokens": 1503848} {"current_steps": 16700, "total_steps": 76960, "loss": 0.2885, "lr": 4.794446004163306e-05, "epoch": 4.33991683991684, "percentage": 21.7, "elapsed_time": "0:24:16", "remaining_time": "1:27:34", "throughput": 1032.97, "total_tokens": 1504312} {"current_steps": 16705, "total_steps": 76960, "loss": 0.2926, "lr": 4.7942208094006e-05, "epoch": 4.341216216216216, "percentage": 21.71, "elapsed_time": "0:24:16", "remaining_time": "1:27:34", "throughput": 1032.96, "total_tokens": 1504728} {"current_steps": 16710, "total_steps": 76960, "loss": 0.3248, "lr": 4.7939954966439195e-05, "epoch": 4.342515592515593, "percentage": 21.71, "elapsed_time": "0:24:17", "remaining_time": "1:27:33", "throughput": 1032.97, "total_tokens": 1505176} {"current_steps": 16715, "total_steps": 76960, "loss": 0.2785, "lr": 4.7937700659048527e-05, "epoch": 4.343814968814969, "percentage": 21.72, "elapsed_time": "0:24:17", "remaining_time": "1:27:33", "throughput": 1033.0, "total_tokens": 1505656} {"current_steps": 16720, "total_steps": 76960, "loss": 0.2842, "lr": 4.7935445171949936e-05, "epoch": 4.345114345114345, "percentage": 21.73, "elapsed_time": "0:24:17", "remaining_time": "1:27:32", "throughput": 1033.02, "total_tokens": 1506120} {"current_steps": 16725, "total_steps": 76960, "loss": 0.2426, "lr": 4.793318850525943e-05, "epoch": 4.346413721413722, "percentage": 21.73, "elapsed_time": "0:24:18", "remaining_time": "1:27:32", "throughput": 1033.05, "total_tokens": 1506584} {"current_steps": 16730, "total_steps": 76960, "loss": 0.2059, "lr": 4.7930930659093054e-05, "epoch": 4.347713097713098, "percentage": 21.74, "elapsed_time": "0:24:18", "remaining_time": "1:27:31", "throughput": 1033.02, "total_tokens": 1506984} {"current_steps": 16735, "total_steps": 76960, "loss": 0.2564, "lr": 4.792867163356696e-05, "epoch": 4.349012474012474, "percentage": 21.75, "elapsed_time": "0:24:19", "remaining_time": "1:27:31", "throughput": 1033.06, "total_tokens": 1507464} {"current_steps": 16740, "total_steps": 76960, "loss": 0.2851, "lr": 4.79264114287973e-05, "epoch": 4.350311850311851, "percentage": 21.75, "elapsed_time": "0:24:19", "remaining_time": "1:27:30", "throughput": 1033.07, "total_tokens": 1507912} {"current_steps": 16745, "total_steps": 76960, "loss": 0.3157, "lr": 4.792415004490034e-05, "epoch": 4.351611226611227, "percentage": 21.76, "elapsed_time": "0:24:20", "remaining_time": "1:27:30", "throughput": 1033.07, "total_tokens": 1508344} {"current_steps": 16750, "total_steps": 76960, "loss": 0.1439, "lr": 4.792188748199237e-05, "epoch": 4.352910602910603, "percentage": 21.76, "elapsed_time": "0:24:20", "remaining_time": "1:27:29", "throughput": 1033.07, "total_tokens": 1508776} {"current_steps": 16755, "total_steps": 76960, "loss": 0.295, "lr": 4.7919623740189774e-05, "epoch": 4.354209979209979, "percentage": 21.77, "elapsed_time": "0:24:20", "remaining_time": "1:27:29", "throughput": 1033.08, "total_tokens": 1509224} {"current_steps": 16760, "total_steps": 76960, "loss": 0.2876, "lr": 4.791735881960896e-05, "epoch": 4.355509355509356, "percentage": 21.78, "elapsed_time": "0:24:21", "remaining_time": "1:27:28", "throughput": 1033.1, "total_tokens": 1509688} {"current_steps": 16765, "total_steps": 76960, "loss": 0.2446, "lr": 4.791509272036643e-05, "epoch": 4.356808731808732, "percentage": 21.78, "elapsed_time": "0:24:21", "remaining_time": "1:27:28", "throughput": 1033.1, "total_tokens": 1510120} {"current_steps": 16770, "total_steps": 76960, "loss": 0.2726, "lr": 4.791282544257872e-05, "epoch": 4.358108108108108, "percentage": 21.79, "elapsed_time": "0:24:22", "remaining_time": "1:27:27", "throughput": 1033.11, "total_tokens": 1510568} {"current_steps": 16775, "total_steps": 76960, "loss": 0.2305, "lr": 4.7910556986362455e-05, "epoch": 4.359407484407485, "percentage": 21.8, "elapsed_time": "0:24:22", "remaining_time": "1:27:27", "throughput": 1033.09, "total_tokens": 1510968} {"current_steps": 16780, "total_steps": 76960, "loss": 0.2611, "lr": 4.790828735183428e-05, "epoch": 4.360706860706861, "percentage": 21.8, "elapsed_time": "0:24:22", "remaining_time": "1:27:26", "throughput": 1033.13, "total_tokens": 1511464} {"current_steps": 16785, "total_steps": 76960, "loss": 0.2601, "lr": 4.790601653911094e-05, "epoch": 4.362006237006237, "percentage": 21.81, "elapsed_time": "0:24:23", "remaining_time": "1:27:26", "throughput": 1033.15, "total_tokens": 1511912} {"current_steps": 16790, "total_steps": 76960, "loss": 0.1362, "lr": 4.790374454830923e-05, "epoch": 4.363305613305613, "percentage": 21.82, "elapsed_time": "0:24:23", "remaining_time": "1:27:25", "throughput": 1033.15, "total_tokens": 1512344} {"current_steps": 16795, "total_steps": 76960, "loss": 0.305, "lr": 4.790147137954598e-05, "epoch": 4.36460498960499, "percentage": 21.82, "elapsed_time": "0:24:24", "remaining_time": "1:27:25", "throughput": 1033.16, "total_tokens": 1512792} {"current_steps": 16800, "total_steps": 76960, "loss": 0.1521, "lr": 4.7899197032938125e-05, "epoch": 4.365904365904366, "percentage": 21.83, "elapsed_time": "0:24:24", "remaining_time": "1:27:24", "throughput": 1033.17, "total_tokens": 1513240} {"current_steps": 16805, "total_steps": 76960, "loss": 0.4078, "lr": 4.7896921508602623e-05, "epoch": 4.367203742203742, "percentage": 21.84, "elapsed_time": "0:24:25", "remaining_time": "1:27:24", "throughput": 1033.2, "total_tokens": 1513720} {"current_steps": 16810, "total_steps": 76960, "loss": 0.2071, "lr": 4.7894644806656493e-05, "epoch": 4.368503118503119, "percentage": 21.84, "elapsed_time": "0:24:25", "remaining_time": "1:27:23", "throughput": 1033.22, "total_tokens": 1514184} {"current_steps": 16815, "total_steps": 76960, "loss": 0.2314, "lr": 4.789236692721686e-05, "epoch": 4.369802494802495, "percentage": 21.85, "elapsed_time": "0:24:25", "remaining_time": "1:27:23", "throughput": 1033.23, "total_tokens": 1514632} {"current_steps": 16820, "total_steps": 76960, "loss": 0.1856, "lr": 4.789008787040086e-05, "epoch": 4.371101871101871, "percentage": 21.86, "elapsed_time": "0:24:26", "remaining_time": "1:27:22", "throughput": 1033.25, "total_tokens": 1515096} {"current_steps": 16825, "total_steps": 76960, "loss": 0.2142, "lr": 4.788780763632571e-05, "epoch": 4.372401247401247, "percentage": 21.86, "elapsed_time": "0:24:26", "remaining_time": "1:27:22", "throughput": 1033.27, "total_tokens": 1515544} {"current_steps": 16830, "total_steps": 76960, "loss": 0.2977, "lr": 4.788552622510868e-05, "epoch": 4.373700623700624, "percentage": 21.87, "elapsed_time": "0:24:27", "remaining_time": "1:27:21", "throughput": 1033.28, "total_tokens": 1515992} {"current_steps": 16835, "total_steps": 76960, "loss": 0.2992, "lr": 4.788324363686711e-05, "epoch": 4.375, "percentage": 21.88, "elapsed_time": "0:24:27", "remaining_time": "1:27:21", "throughput": 1033.3, "total_tokens": 1516456} {"current_steps": 16840, "total_steps": 76960, "loss": 0.1776, "lr": 4.788095987171839e-05, "epoch": 4.376299376299376, "percentage": 21.88, "elapsed_time": "0:24:28", "remaining_time": "1:27:20", "throughput": 1033.3, "total_tokens": 1516888} {"current_steps": 16845, "total_steps": 76960, "loss": 0.1678, "lr": 4.787867492977999e-05, "epoch": 4.377598752598753, "percentage": 21.89, "elapsed_time": "0:24:28", "remaining_time": "1:27:20", "throughput": 1033.31, "total_tokens": 1517336} {"current_steps": 16850, "total_steps": 76960, "loss": 0.3, "lr": 4.7876388811169405e-05, "epoch": 4.378898128898129, "percentage": 21.89, "elapsed_time": "0:24:28", "remaining_time": "1:27:19", "throughput": 1033.33, "total_tokens": 1517800} {"current_steps": 16855, "total_steps": 76960, "loss": 0.3107, "lr": 4.787410151600423e-05, "epoch": 4.380197505197505, "percentage": 21.9, "elapsed_time": "0:24:29", "remaining_time": "1:27:19", "throughput": 1033.35, "total_tokens": 1518264} {"current_steps": 16860, "total_steps": 76960, "loss": 0.2787, "lr": 4.78718130444021e-05, "epoch": 4.381496881496881, "percentage": 21.91, "elapsed_time": "0:24:29", "remaining_time": "1:27:18", "throughput": 1033.4, "total_tokens": 1518776} {"current_steps": 16865, "total_steps": 76960, "loss": 0.2945, "lr": 4.786952339648071e-05, "epoch": 4.382796257796258, "percentage": 21.91, "elapsed_time": "0:24:30", "remaining_time": "1:27:18", "throughput": 1033.42, "total_tokens": 1519240} {"current_steps": 16870, "total_steps": 76960, "loss": 0.2334, "lr": 4.786723257235781e-05, "epoch": 4.384095634095634, "percentage": 21.92, "elapsed_time": "0:24:30", "remaining_time": "1:27:17", "throughput": 1033.44, "total_tokens": 1519704} {"current_steps": 16875, "total_steps": 76960, "loss": 0.2259, "lr": 4.786494057215124e-05, "epoch": 4.38539501039501, "percentage": 21.93, "elapsed_time": "0:24:30", "remaining_time": "1:27:17", "throughput": 1033.45, "total_tokens": 1520152} {"current_steps": 16880, "total_steps": 76960, "loss": 0.1402, "lr": 4.786264739597886e-05, "epoch": 4.386694386694387, "percentage": 21.93, "elapsed_time": "0:24:31", "remaining_time": "1:27:16", "throughput": 1033.45, "total_tokens": 1520584} {"current_steps": 16885, "total_steps": 76960, "loss": 0.3021, "lr": 4.786035304395862e-05, "epoch": 4.387993762993763, "percentage": 21.94, "elapsed_time": "0:24:31", "remaining_time": "1:27:16", "throughput": 1033.46, "total_tokens": 1521032} {"current_steps": 16890, "total_steps": 76960, "loss": 0.3755, "lr": 4.785805751620852e-05, "epoch": 4.389293139293139, "percentage": 21.95, "elapsed_time": "0:24:32", "remaining_time": "1:27:15", "throughput": 1033.49, "total_tokens": 1521496} {"current_steps": 16895, "total_steps": 76960, "loss": 0.2244, "lr": 4.785576081284663e-05, "epoch": 4.390592515592515, "percentage": 21.95, "elapsed_time": "0:24:32", "remaining_time": "1:27:15", "throughput": 1033.46, "total_tokens": 1521896} {"current_steps": 16900, "total_steps": 76960, "loss": 0.1832, "lr": 4.7853462933991045e-05, "epoch": 4.391891891891892, "percentage": 21.96, "elapsed_time": "0:24:33", "remaining_time": "1:27:14", "throughput": 1033.47, "total_tokens": 1522344} {"current_steps": 16905, "total_steps": 76960, "loss": 0.3454, "lr": 4.7851163879759975e-05, "epoch": 4.393191268191268, "percentage": 21.97, "elapsed_time": "0:24:33", "remaining_time": "1:27:14", "throughput": 1033.51, "total_tokens": 1522840} {"current_steps": 16910, "total_steps": 76960, "loss": 0.3308, "lr": 4.7848863650271646e-05, "epoch": 4.394490644490644, "percentage": 21.97, "elapsed_time": "0:24:33", "remaining_time": "1:27:13", "throughput": 1033.5, "total_tokens": 1523256} {"current_steps": 16915, "total_steps": 76960, "loss": 0.2017, "lr": 4.784656224564438e-05, "epoch": 4.395790020790021, "percentage": 21.98, "elapsed_time": "0:24:34", "remaining_time": "1:27:13", "throughput": 1033.52, "total_tokens": 1523720} {"current_steps": 16920, "total_steps": 76960, "loss": 0.1961, "lr": 4.784425966599651e-05, "epoch": 4.397089397089397, "percentage": 21.99, "elapsed_time": "0:24:34", "remaining_time": "1:27:13", "throughput": 1033.53, "total_tokens": 1524168} {"current_steps": 16925, "total_steps": 76960, "loss": 0.4031, "lr": 4.7841955911446487e-05, "epoch": 4.398388773388773, "percentage": 21.99, "elapsed_time": "0:24:35", "remaining_time": "1:27:12", "throughput": 1033.56, "total_tokens": 1524648} {"current_steps": 16930, "total_steps": 76960, "loss": 0.1663, "lr": 4.783965098211278e-05, "epoch": 4.399688149688149, "percentage": 22.0, "elapsed_time": "0:24:35", "remaining_time": "1:27:12", "throughput": 1033.56, "total_tokens": 1525080} {"current_steps": 16935, "total_steps": 76960, "loss": 0.2312, "lr": 4.7837344878113944e-05, "epoch": 4.400987525987526, "percentage": 22.0, "elapsed_time": "0:24:35", "remaining_time": "1:27:11", "throughput": 1033.57, "total_tokens": 1525528} {"current_steps": 16940, "total_steps": 76960, "loss": 0.3788, "lr": 4.783503759956858e-05, "epoch": 4.402286902286902, "percentage": 22.01, "elapsed_time": "0:24:36", "remaining_time": "1:27:11", "throughput": 1033.59, "total_tokens": 1525992} {"current_steps": 16945, "total_steps": 76960, "loss": 0.2554, "lr": 4.783272914659535e-05, "epoch": 4.403586278586278, "percentage": 22.02, "elapsed_time": "0:24:36", "remaining_time": "1:27:10", "throughput": 1033.59, "total_tokens": 1526424} {"current_steps": 16950, "total_steps": 76960, "loss": 0.2329, "lr": 4.783041951931297e-05, "epoch": 4.404885654885655, "percentage": 22.02, "elapsed_time": "0:24:37", "remaining_time": "1:27:10", "throughput": 1033.6, "total_tokens": 1526872} {"current_steps": 16955, "total_steps": 76960, "loss": 0.3028, "lr": 4.7828108717840256e-05, "epoch": 4.406185031185031, "percentage": 22.03, "elapsed_time": "0:24:37", "remaining_time": "1:27:09", "throughput": 1033.61, "total_tokens": 1527320} {"current_steps": 16960, "total_steps": 76960, "loss": 0.2255, "lr": 4.782579674229604e-05, "epoch": 4.407484407484407, "percentage": 22.04, "elapsed_time": "0:24:38", "remaining_time": "1:27:09", "throughput": 1033.62, "total_tokens": 1527768} {"current_steps": 16965, "total_steps": 76960, "loss": 0.2279, "lr": 4.782348359279922e-05, "epoch": 4.408783783783784, "percentage": 22.04, "elapsed_time": "0:24:38", "remaining_time": "1:27:08", "throughput": 1033.63, "total_tokens": 1528216} {"current_steps": 16970, "total_steps": 76960, "loss": 0.2151, "lr": 4.782116926946877e-05, "epoch": 4.41008316008316, "percentage": 22.05, "elapsed_time": "0:24:38", "remaining_time": "1:27:08", "throughput": 1033.64, "total_tokens": 1528664} {"current_steps": 16975, "total_steps": 76960, "loss": 0.3549, "lr": 4.781885377242372e-05, "epoch": 4.411382536382536, "percentage": 22.06, "elapsed_time": "0:24:39", "remaining_time": "1:27:07", "throughput": 1033.64, "total_tokens": 1529096} {"current_steps": 16980, "total_steps": 76960, "loss": 0.1826, "lr": 4.781653710178315e-05, "epoch": 4.412681912681912, "percentage": 22.06, "elapsed_time": "0:24:39", "remaining_time": "1:27:07", "throughput": 1033.64, "total_tokens": 1529528} {"current_steps": 16985, "total_steps": 76960, "loss": 0.2603, "lr": 4.781421925766623e-05, "epoch": 4.413981288981289, "percentage": 22.07, "elapsed_time": "0:24:40", "remaining_time": "1:27:06", "throughput": 1033.63, "total_tokens": 1529944} {"current_steps": 16990, "total_steps": 76960, "loss": 0.2443, "lr": 4.781190024019214e-05, "epoch": 4.415280665280665, "percentage": 22.08, "elapsed_time": "0:24:40", "remaining_time": "1:27:06", "throughput": 1033.63, "total_tokens": 1530376} {"current_steps": 16995, "total_steps": 76960, "loss": 0.2345, "lr": 4.7809580049480164e-05, "epoch": 4.416580041580041, "percentage": 22.08, "elapsed_time": "0:24:41", "remaining_time": "1:27:05", "throughput": 1033.65, "total_tokens": 1530840} {"current_steps": 17000, "total_steps": 76960, "loss": 0.2494, "lr": 4.7807258685649634e-05, "epoch": 4.417879417879418, "percentage": 22.09, "elapsed_time": "0:24:41", "remaining_time": "1:27:05", "throughput": 1033.67, "total_tokens": 1531304} {"current_steps": 17005, "total_steps": 76960, "loss": 0.3262, "lr": 4.780493614881995e-05, "epoch": 4.419178794178794, "percentage": 22.1, "elapsed_time": "0:24:41", "remaining_time": "1:27:04", "throughput": 1033.69, "total_tokens": 1531768} {"current_steps": 17010, "total_steps": 76960, "loss": 0.1914, "lr": 4.780261243911053e-05, "epoch": 4.42047817047817, "percentage": 22.1, "elapsed_time": "0:24:42", "remaining_time": "1:27:04", "throughput": 1033.69, "total_tokens": 1532200} {"current_steps": 17015, "total_steps": 76960, "loss": 0.2386, "lr": 4.780028755664091e-05, "epoch": 4.421777546777546, "percentage": 22.11, "elapsed_time": "0:24:42", "remaining_time": "1:27:03", "throughput": 1033.72, "total_tokens": 1532664} {"current_steps": 17020, "total_steps": 76960, "loss": 0.2606, "lr": 4.779796150153065e-05, "epoch": 4.423076923076923, "percentage": 22.12, "elapsed_time": "0:24:43", "remaining_time": "1:27:03", "throughput": 1033.75, "total_tokens": 1533144} {"current_steps": 17025, "total_steps": 76960, "loss": 0.2409, "lr": 4.77956342738994e-05, "epoch": 4.424376299376299, "percentage": 22.12, "elapsed_time": "0:24:43", "remaining_time": "1:27:02", "throughput": 1033.77, "total_tokens": 1533608} {"current_steps": 17030, "total_steps": 76960, "loss": 0.3651, "lr": 4.7793305873866825e-05, "epoch": 4.425675675675675, "percentage": 22.13, "elapsed_time": "0:24:43", "remaining_time": "1:27:02", "throughput": 1033.74, "total_tokens": 1534008} {"current_steps": 17035, "total_steps": 76960, "loss": 0.2284, "lr": 4.779097630155269e-05, "epoch": 4.426975051975052, "percentage": 22.13, "elapsed_time": "0:24:44", "remaining_time": "1:27:01", "throughput": 1033.79, "total_tokens": 1534504} {"current_steps": 17040, "total_steps": 76960, "loss": 0.2212, "lr": 4.778864555707681e-05, "epoch": 4.428274428274428, "percentage": 22.14, "elapsed_time": "0:24:44", "remaining_time": "1:27:01", "throughput": 1033.79, "total_tokens": 1534936} {"current_steps": 17045, "total_steps": 76960, "loss": 0.2878, "lr": 4.778631364055906e-05, "epoch": 4.4295738045738045, "percentage": 22.15, "elapsed_time": "0:24:45", "remaining_time": "1:27:00", "throughput": 1033.81, "total_tokens": 1535400} {"current_steps": 17050, "total_steps": 76960, "loss": 0.2427, "lr": 4.778398055211936e-05, "epoch": 4.4308731808731805, "percentage": 22.15, "elapsed_time": "0:24:45", "remaining_time": "1:27:00", "throughput": 1033.85, "total_tokens": 1535896} {"current_steps": 17055, "total_steps": 76960, "loss": 0.3627, "lr": 4.778164629187771e-05, "epoch": 4.432172557172557, "percentage": 22.16, "elapsed_time": "0:24:46", "remaining_time": "1:26:59", "throughput": 1033.87, "total_tokens": 1536360} {"current_steps": 17060, "total_steps": 76960, "loss": 0.2855, "lr": 4.777931085995416e-05, "epoch": 4.4334719334719335, "percentage": 22.17, "elapsed_time": "0:24:46", "remaining_time": "1:26:59", "throughput": 1033.88, "total_tokens": 1536808} {"current_steps": 17065, "total_steps": 76960, "loss": 0.289, "lr": 4.777697425646883e-05, "epoch": 4.4347713097713095, "percentage": 22.17, "elapsed_time": "0:24:46", "remaining_time": "1:26:58", "throughput": 1033.9, "total_tokens": 1537272} {"current_steps": 17070, "total_steps": 76960, "loss": 0.2882, "lr": 4.7774636481541897e-05, "epoch": 4.436070686070686, "percentage": 22.18, "elapsed_time": "0:24:47", "remaining_time": "1:26:58", "throughput": 1033.93, "total_tokens": 1537752} {"current_steps": 17075, "total_steps": 76960, "loss": 0.28, "lr": 4.777229753529357e-05, "epoch": 4.4373700623700625, "percentage": 22.19, "elapsed_time": "0:24:47", "remaining_time": "1:26:57", "throughput": 1033.93, "total_tokens": 1538184} {"current_steps": 17080, "total_steps": 76960, "loss": 0.2581, "lr": 4.776995741784418e-05, "epoch": 4.4386694386694385, "percentage": 22.19, "elapsed_time": "0:24:48", "remaining_time": "1:26:57", "throughput": 1033.95, "total_tokens": 1538648} {"current_steps": 17085, "total_steps": 76960, "loss": 0.2059, "lr": 4.776761612931405e-05, "epoch": 4.439968814968815, "percentage": 22.2, "elapsed_time": "0:24:48", "remaining_time": "1:26:56", "throughput": 1033.97, "total_tokens": 1539096} {"current_steps": 17090, "total_steps": 76960, "loss": 0.3009, "lr": 4.776527366982362e-05, "epoch": 4.4412681912681915, "percentage": 22.21, "elapsed_time": "0:24:48", "remaining_time": "1:26:56", "throughput": 1033.97, "total_tokens": 1539544} {"current_steps": 17095, "total_steps": 76960, "loss": 0.1644, "lr": 4.776293003949335e-05, "epoch": 4.4425675675675675, "percentage": 22.21, "elapsed_time": "0:24:49", "remaining_time": "1:26:55", "throughput": 1034.01, "total_tokens": 1540024} {"current_steps": 17100, "total_steps": 76960, "loss": 0.3835, "lr": 4.776058523844377e-05, "epoch": 4.443866943866944, "percentage": 22.22, "elapsed_time": "0:24:49", "remaining_time": "1:26:55", "throughput": 1034.03, "total_tokens": 1540488} {"current_steps": 17105, "total_steps": 76960, "loss": 0.3003, "lr": 4.775823926679548e-05, "epoch": 4.4451663201663205, "percentage": 22.23, "elapsed_time": "0:24:50", "remaining_time": "1:26:54", "throughput": 1034.04, "total_tokens": 1540936} {"current_steps": 17110, "total_steps": 76960, "loss": 0.2657, "lr": 4.775589212466915e-05, "epoch": 4.446465696465697, "percentage": 22.23, "elapsed_time": "0:24:50", "remaining_time": "1:26:54", "throughput": 1034.04, "total_tokens": 1541368} {"current_steps": 17115, "total_steps": 76960, "loss": 0.2183, "lr": 4.775354381218548e-05, "epoch": 4.447765072765073, "percentage": 22.24, "elapsed_time": "0:24:51", "remaining_time": "1:26:53", "throughput": 1034.03, "total_tokens": 1541784} {"current_steps": 17120, "total_steps": 76960, "loss": 0.2446, "lr": 4.775119432946525e-05, "epoch": 4.4490644490644495, "percentage": 22.25, "elapsed_time": "0:24:51", "remaining_time": "1:26:53", "throughput": 1034.03, "total_tokens": 1542216} {"current_steps": 17125, "total_steps": 76960, "loss": 0.1847, "lr": 4.7748843676629295e-05, "epoch": 4.450363825363826, "percentage": 22.25, "elapsed_time": "0:24:51", "remaining_time": "1:26:52", "throughput": 1034.04, "total_tokens": 1542664} {"current_steps": 17130, "total_steps": 76960, "loss": 0.2812, "lr": 4.7746491853798514e-05, "epoch": 4.451663201663202, "percentage": 22.26, "elapsed_time": "0:24:52", "remaining_time": "1:26:52", "throughput": 1034.05, "total_tokens": 1543112} {"current_steps": 17135, "total_steps": 76960, "loss": 0.22, "lr": 4.774413886109386e-05, "epoch": 4.452962577962578, "percentage": 22.26, "elapsed_time": "0:24:52", "remaining_time": "1:26:51", "throughput": 1034.07, "total_tokens": 1543576} {"current_steps": 17140, "total_steps": 76960, "loss": 0.1136, "lr": 4.774178469863636e-05, "epoch": 4.454261954261955, "percentage": 22.27, "elapsed_time": "0:24:53", "remaining_time": "1:26:51", "throughput": 1034.08, "total_tokens": 1544024} {"current_steps": 17145, "total_steps": 76960, "loss": 0.2181, "lr": 4.7739429366547076e-05, "epoch": 4.455561330561331, "percentage": 22.28, "elapsed_time": "0:24:53", "remaining_time": "1:26:50", "throughput": 1034.1, "total_tokens": 1544488} {"current_steps": 17150, "total_steps": 76960, "loss": 0.3454, "lr": 4.773707286494715e-05, "epoch": 4.456860706860707, "percentage": 22.28, "elapsed_time": "0:24:53", "remaining_time": "1:26:50", "throughput": 1034.14, "total_tokens": 1544984} {"current_steps": 17155, "total_steps": 76960, "loss": 0.2137, "lr": 4.773471519395778e-05, "epoch": 4.458160083160083, "percentage": 22.29, "elapsed_time": "0:24:54", "remaining_time": "1:26:49", "throughput": 1034.15, "total_tokens": 1545432} {"current_steps": 17160, "total_steps": 76960, "loss": 0.2703, "lr": 4.7732356353700234e-05, "epoch": 4.45945945945946, "percentage": 22.3, "elapsed_time": "0:24:54", "remaining_time": "1:26:49", "throughput": 1034.18, "total_tokens": 1545912} {"current_steps": 17165, "total_steps": 76960, "loss": 0.27, "lr": 4.7729996344295814e-05, "epoch": 4.460758835758836, "percentage": 22.3, "elapsed_time": "0:24:55", "remaining_time": "1:26:48", "throughput": 1034.17, "total_tokens": 1546328} {"current_steps": 17170, "total_steps": 76960, "loss": 0.2105, "lr": 4.77276351658659e-05, "epoch": 4.462058212058212, "percentage": 22.31, "elapsed_time": "0:24:55", "remaining_time": "1:26:48", "throughput": 1034.18, "total_tokens": 1546776} {"current_steps": 17175, "total_steps": 76960, "loss": 0.2205, "lr": 4.7725272818531934e-05, "epoch": 4.463357588357589, "percentage": 22.32, "elapsed_time": "0:24:56", "remaining_time": "1:26:47", "throughput": 1034.21, "total_tokens": 1547256} {"current_steps": 17180, "total_steps": 76960, "loss": 0.218, "lr": 4.772290930241542e-05, "epoch": 4.464656964656965, "percentage": 22.32, "elapsed_time": "0:24:56", "remaining_time": "1:26:47", "throughput": 1034.23, "total_tokens": 1547720} {"current_steps": 17185, "total_steps": 76960, "loss": 0.3562, "lr": 4.77205446176379e-05, "epoch": 4.465956340956341, "percentage": 22.33, "elapsed_time": "0:24:56", "remaining_time": "1:26:46", "throughput": 1034.28, "total_tokens": 1548216} {"current_steps": 17190, "total_steps": 76960, "loss": 0.2623, "lr": 4.7718178764321006e-05, "epoch": 4.467255717255718, "percentage": 22.34, "elapsed_time": "0:24:57", "remaining_time": "1:26:46", "throughput": 1034.29, "total_tokens": 1548664} {"current_steps": 17195, "total_steps": 76960, "loss": 0.3693, "lr": 4.7715811742586404e-05, "epoch": 4.468555093555094, "percentage": 22.34, "elapsed_time": "0:24:57", "remaining_time": "1:26:45", "throughput": 1034.3, "total_tokens": 1549112} {"current_steps": 17200, "total_steps": 76960, "loss": 0.27, "lr": 4.7713443552555845e-05, "epoch": 4.46985446985447, "percentage": 22.35, "elapsed_time": "0:24:58", "remaining_time": "1:26:45", "throughput": 1034.28, "total_tokens": 1549528} {"current_steps": 17205, "total_steps": 76960, "loss": 0.2462, "lr": 4.771107419435112e-05, "epoch": 4.471153846153846, "percentage": 22.36, "elapsed_time": "0:24:58", "remaining_time": "1:26:44", "throughput": 1034.28, "total_tokens": 1549960} {"current_steps": 17210, "total_steps": 76960, "loss": 0.2771, "lr": 4.770870366809409e-05, "epoch": 4.472453222453223, "percentage": 22.36, "elapsed_time": "0:24:59", "remaining_time": "1:26:44", "throughput": 1034.29, "total_tokens": 1550408} {"current_steps": 17215, "total_steps": 76960, "loss": 0.2096, "lr": 4.7706331973906664e-05, "epoch": 4.473752598752599, "percentage": 22.37, "elapsed_time": "0:24:59", "remaining_time": "1:26:43", "throughput": 1034.29, "total_tokens": 1550840} {"current_steps": 17220, "total_steps": 76960, "loss": 0.2241, "lr": 4.770395911191084e-05, "epoch": 4.475051975051975, "percentage": 22.38, "elapsed_time": "0:24:59", "remaining_time": "1:26:43", "throughput": 1034.29, "total_tokens": 1551272} {"current_steps": 17225, "total_steps": 76960, "loss": 0.2623, "lr": 4.7701585082228634e-05, "epoch": 4.476351351351352, "percentage": 22.38, "elapsed_time": "0:25:00", "remaining_time": "1:26:42", "throughput": 1034.3, "total_tokens": 1551736} {"current_steps": 17230, "total_steps": 76960, "loss": 0.3304, "lr": 4.769920988498216e-05, "epoch": 4.477650727650728, "percentage": 22.39, "elapsed_time": "0:25:00", "remaining_time": "1:26:42", "throughput": 1034.32, "total_tokens": 1552200} {"current_steps": 17235, "total_steps": 76960, "loss": 0.376, "lr": 4.769683352029357e-05, "epoch": 4.478950103950104, "percentage": 22.39, "elapsed_time": "0:25:01", "remaining_time": "1:26:41", "throughput": 1034.32, "total_tokens": 1552632} {"current_steps": 17240, "total_steps": 76960, "loss": 0.2187, "lr": 4.769445598828509e-05, "epoch": 4.48024948024948, "percentage": 22.4, "elapsed_time": "0:25:01", "remaining_time": "1:26:41", "throughput": 1034.33, "total_tokens": 1553080} {"current_steps": 17245, "total_steps": 76960, "loss": 0.2591, "lr": 4.7692077289078996e-05, "epoch": 4.481548856548857, "percentage": 22.41, "elapsed_time": "0:25:01", "remaining_time": "1:26:40", "throughput": 1034.32, "total_tokens": 1553496} {"current_steps": 17250, "total_steps": 76960, "loss": 0.2318, "lr": 4.768969742279762e-05, "epoch": 4.482848232848233, "percentage": 22.41, "elapsed_time": "0:25:02", "remaining_time": "1:26:40", "throughput": 1034.33, "total_tokens": 1553944} {"current_steps": 17255, "total_steps": 76960, "loss": 0.2168, "lr": 4.7687316389563365e-05, "epoch": 4.484147609147609, "percentage": 22.42, "elapsed_time": "0:25:02", "remaining_time": "1:26:39", "throughput": 1034.33, "total_tokens": 1554376} {"current_steps": 17260, "total_steps": 76960, "loss": 0.2628, "lr": 4.7684934189498686e-05, "epoch": 4.485446985446986, "percentage": 22.43, "elapsed_time": "0:25:03", "remaining_time": "1:26:39", "throughput": 1034.32, "total_tokens": 1554792} {"current_steps": 17265, "total_steps": 76960, "loss": 0.2717, "lr": 4.768255082272611e-05, "epoch": 4.486746361746362, "percentage": 22.43, "elapsed_time": "0:25:03", "remaining_time": "1:26:38", "throughput": 1034.33, "total_tokens": 1555240} {"current_steps": 17270, "total_steps": 76960, "loss": 0.3214, "lr": 4.768016628936821e-05, "epoch": 4.488045738045738, "percentage": 22.44, "elapsed_time": "0:25:04", "remaining_time": "1:26:38", "throughput": 1034.36, "total_tokens": 1555720} {"current_steps": 17275, "total_steps": 76960, "loss": 0.2537, "lr": 4.7677780589547635e-05, "epoch": 4.489345114345114, "percentage": 22.45, "elapsed_time": "0:25:04", "remaining_time": "1:26:37", "throughput": 1034.36, "total_tokens": 1556152} {"current_steps": 17280, "total_steps": 76960, "loss": 0.2727, "lr": 4.7675393723387064e-05, "epoch": 4.490644490644491, "percentage": 22.45, "elapsed_time": "0:25:04", "remaining_time": "1:26:37", "throughput": 1034.4, "total_tokens": 1556632} {"current_steps": 17285, "total_steps": 76960, "loss": 0.2048, "lr": 4.767300569100928e-05, "epoch": 4.491943866943867, "percentage": 22.46, "elapsed_time": "0:25:05", "remaining_time": "1:26:36", "throughput": 1034.41, "total_tokens": 1557080} {"current_steps": 17290, "total_steps": 76960, "loss": 0.2156, "lr": 4.7670616492537076e-05, "epoch": 4.493243243243243, "percentage": 22.47, "elapsed_time": "0:25:05", "remaining_time": "1:26:36", "throughput": 1034.43, "total_tokens": 1557544} {"current_steps": 17295, "total_steps": 76960, "loss": 0.1632, "lr": 4.7668226128093354e-05, "epoch": 4.49454261954262, "percentage": 22.47, "elapsed_time": "0:25:06", "remaining_time": "1:26:35", "throughput": 1034.44, "total_tokens": 1557992} {"current_steps": 17300, "total_steps": 76960, "loss": 0.2174, "lr": 4.766583459780104e-05, "epoch": 4.495841995841996, "percentage": 22.48, "elapsed_time": "0:25:06", "remaining_time": "1:26:35", "throughput": 1034.47, "total_tokens": 1558472} {"current_steps": 17305, "total_steps": 76960, "loss": 0.2176, "lr": 4.766344190178313e-05, "epoch": 4.497141372141372, "percentage": 22.49, "elapsed_time": "0:25:06", "remaining_time": "1:26:34", "throughput": 1034.48, "total_tokens": 1558920} {"current_steps": 17310, "total_steps": 76960, "loss": 0.2162, "lr": 4.766104804016269e-05, "epoch": 4.498440748440748, "percentage": 22.49, "elapsed_time": "0:25:07", "remaining_time": "1:26:34", "throughput": 1034.47, "total_tokens": 1559336} {"current_steps": 17315, "total_steps": 76960, "loss": 0.2774, "lr": 4.765865301306284e-05, "epoch": 4.499740124740125, "percentage": 22.5, "elapsed_time": "0:25:07", "remaining_time": "1:26:33", "throughput": 1034.5, "total_tokens": 1559816} {"current_steps": 17320, "total_steps": 76960, "loss": 0.3013, "lr": 4.7656256820606745e-05, "epoch": 4.501039501039501, "percentage": 22.51, "elapsed_time": "0:25:08", "remaining_time": "1:26:33", "throughput": 1034.52, "total_tokens": 1560280} {"current_steps": 17325, "total_steps": 76960, "loss": 0.3216, "lr": 4.765385946291767e-05, "epoch": 4.502338877338877, "percentage": 22.51, "elapsed_time": "0:25:08", "remaining_time": "1:26:32", "throughput": 1034.58, "total_tokens": 1560792} {"current_steps": 17330, "total_steps": 76960, "loss": 0.2871, "lr": 4.7651460940118887e-05, "epoch": 4.503638253638254, "percentage": 22.52, "elapsed_time": "0:25:09", "remaining_time": "1:26:32", "throughput": 1034.59, "total_tokens": 1561240} {"current_steps": 17335, "total_steps": 76960, "loss": 0.2922, "lr": 4.764906125233377e-05, "epoch": 4.50493762993763, "percentage": 22.52, "elapsed_time": "0:25:09", "remaining_time": "1:26:31", "throughput": 1034.61, "total_tokens": 1561704} {"current_steps": 17340, "total_steps": 76960, "loss": 0.2946, "lr": 4.764666039968572e-05, "epoch": 4.506237006237006, "percentage": 22.53, "elapsed_time": "0:25:09", "remaining_time": "1:26:31", "throughput": 1034.61, "total_tokens": 1562136} {"current_steps": 17345, "total_steps": 76960, "loss": 0.271, "lr": 4.764425838229824e-05, "epoch": 4.507536382536383, "percentage": 22.54, "elapsed_time": "0:25:10", "remaining_time": "1:26:30", "throughput": 1034.6, "total_tokens": 1562552} {"current_steps": 17350, "total_steps": 76960, "loss": 0.3003, "lr": 4.7641855200294844e-05, "epoch": 4.508835758835759, "percentage": 22.54, "elapsed_time": "0:25:10", "remaining_time": "1:26:30", "throughput": 1034.61, "total_tokens": 1563000} {"current_steps": 17355, "total_steps": 76960, "loss": 0.2605, "lr": 4.763945085379915e-05, "epoch": 4.510135135135135, "percentage": 22.55, "elapsed_time": "0:25:11", "remaining_time": "1:26:29", "throughput": 1034.62, "total_tokens": 1563448} {"current_steps": 17360, "total_steps": 76960, "loss": 0.2516, "lr": 4.7637045342934795e-05, "epoch": 4.511434511434511, "percentage": 22.56, "elapsed_time": "0:25:11", "remaining_time": "1:26:29", "throughput": 1034.61, "total_tokens": 1563864} {"current_steps": 17365, "total_steps": 76960, "loss": 0.3071, "lr": 4.763463866782551e-05, "epoch": 4.512733887733888, "percentage": 22.56, "elapsed_time": "0:25:11", "remaining_time": "1:26:28", "throughput": 1034.64, "total_tokens": 1564344} {"current_steps": 17370, "total_steps": 76960, "loss": 0.2447, "lr": 4.763223082859508e-05, "epoch": 4.514033264033264, "percentage": 22.57, "elapsed_time": "0:25:12", "remaining_time": "1:26:28", "throughput": 1034.63, "total_tokens": 1564776} {"current_steps": 17375, "total_steps": 76960, "loss": 0.2385, "lr": 4.7629821825367335e-05, "epoch": 4.51533264033264, "percentage": 22.58, "elapsed_time": "0:25:12", "remaining_time": "1:26:28", "throughput": 1034.62, "total_tokens": 1565208} {"current_steps": 17380, "total_steps": 76960, "loss": 0.2792, "lr": 4.762741165826616e-05, "epoch": 4.516632016632016, "percentage": 22.58, "elapsed_time": "0:25:13", "remaining_time": "1:26:27", "throughput": 1034.63, "total_tokens": 1565656} {"current_steps": 17385, "total_steps": 76960, "loss": 0.2082, "lr": 4.762500032741553e-05, "epoch": 4.517931392931393, "percentage": 22.59, "elapsed_time": "0:25:13", "remaining_time": "1:26:27", "throughput": 1034.63, "total_tokens": 1566104} {"current_steps": 17390, "total_steps": 76960, "loss": 0.326, "lr": 4.7622587832939456e-05, "epoch": 4.519230769230769, "percentage": 22.6, "elapsed_time": "0:25:14", "remaining_time": "1:26:26", "throughput": 1034.64, "total_tokens": 1566552} {"current_steps": 17395, "total_steps": 76960, "loss": 0.2485, "lr": 4.7620174174962005e-05, "epoch": 4.520530145530145, "percentage": 22.6, "elapsed_time": "0:25:14", "remaining_time": "1:26:26", "throughput": 1034.66, "total_tokens": 1567016} {"current_steps": 17400, "total_steps": 76960, "loss": 0.3134, "lr": 4.7617759353607325e-05, "epoch": 4.521829521829522, "percentage": 22.61, "elapsed_time": "0:25:14", "remaining_time": "1:26:25", "throughput": 1034.66, "total_tokens": 1567448} {"current_steps": 17405, "total_steps": 76960, "loss": 0.3008, "lr": 4.761534336899962e-05, "epoch": 4.523128898128898, "percentage": 22.62, "elapsed_time": "0:25:15", "remaining_time": "1:26:25", "throughput": 1034.67, "total_tokens": 1567896} {"current_steps": 17410, "total_steps": 76960, "loss": 0.2618, "lr": 4.761292622126313e-05, "epoch": 4.524428274428274, "percentage": 22.62, "elapsed_time": "0:25:15", "remaining_time": "1:26:24", "throughput": 1034.73, "total_tokens": 1568424} {"current_steps": 17415, "total_steps": 76960, "loss": 0.2573, "lr": 4.761050791052217e-05, "epoch": 4.525727650727651, "percentage": 22.63, "elapsed_time": "0:25:16", "remaining_time": "1:26:24", "throughput": 1034.73, "total_tokens": 1568856} {"current_steps": 17420, "total_steps": 76960, "loss": 0.2289, "lr": 4.7608088436901135e-05, "epoch": 4.527027027027027, "percentage": 22.64, "elapsed_time": "0:25:16", "remaining_time": "1:26:23", "throughput": 1034.75, "total_tokens": 1569320} {"current_steps": 17425, "total_steps": 76960, "loss": 0.1755, "lr": 4.760566780052445e-05, "epoch": 4.528326403326403, "percentage": 22.64, "elapsed_time": "0:25:17", "remaining_time": "1:26:23", "throughput": 1034.73, "total_tokens": 1569720} {"current_steps": 17430, "total_steps": 76960, "loss": 0.2966, "lr": 4.760324600151661e-05, "epoch": 4.529625779625779, "percentage": 22.65, "elapsed_time": "0:25:17", "remaining_time": "1:26:22", "throughput": 1034.73, "total_tokens": 1570152} {"current_steps": 17435, "total_steps": 76960, "loss": 0.3764, "lr": 4.7600823040002164e-05, "epoch": 4.530925155925156, "percentage": 22.65, "elapsed_time": "0:25:17", "remaining_time": "1:26:22", "throughput": 1034.73, "total_tokens": 1570584} {"current_steps": 17440, "total_steps": 76960, "loss": 0.354, "lr": 4.7598398916105736e-05, "epoch": 4.532224532224532, "percentage": 22.66, "elapsed_time": "0:25:18", "remaining_time": "1:26:21", "throughput": 1034.75, "total_tokens": 1571048} {"current_steps": 17445, "total_steps": 76960, "loss": 0.1997, "lr": 4.7595973629952e-05, "epoch": 4.533523908523908, "percentage": 22.67, "elapsed_time": "0:25:18", "remaining_time": "1:26:21", "throughput": 1034.74, "total_tokens": 1571480} {"current_steps": 17450, "total_steps": 76960, "loss": 0.3092, "lr": 4.759354718166569e-05, "epoch": 4.534823284823284, "percentage": 22.67, "elapsed_time": "0:25:19", "remaining_time": "1:26:20", "throughput": 1034.75, "total_tokens": 1571912} {"current_steps": 17455, "total_steps": 76960, "loss": 0.2126, "lr": 4.75911195713716e-05, "epoch": 4.536122661122661, "percentage": 22.68, "elapsed_time": "0:25:19", "remaining_time": "1:26:20", "throughput": 1034.76, "total_tokens": 1572360} {"current_steps": 17460, "total_steps": 76960, "loss": 0.2504, "lr": 4.7588690799194586e-05, "epoch": 4.537422037422037, "percentage": 22.69, "elapsed_time": "0:25:19", "remaining_time": "1:26:19", "throughput": 1034.76, "total_tokens": 1572792} {"current_steps": 17465, "total_steps": 76960, "loss": 0.2504, "lr": 4.758626086525956e-05, "epoch": 4.538721413721413, "percentage": 22.69, "elapsed_time": "0:25:20", "remaining_time": "1:26:19", "throughput": 1034.76, "total_tokens": 1573240} {"current_steps": 17470, "total_steps": 76960, "loss": 0.3045, "lr": 4.7583829769691496e-05, "epoch": 4.54002079002079, "percentage": 22.7, "elapsed_time": "0:25:20", "remaining_time": "1:26:18", "throughput": 1034.76, "total_tokens": 1573672} {"current_steps": 17475, "total_steps": 76960, "loss": 0.2203, "lr": 4.7581397512615425e-05, "epoch": 4.541320166320166, "percentage": 22.71, "elapsed_time": "0:25:21", "remaining_time": "1:26:18", "throughput": 1034.76, "total_tokens": 1574104} {"current_steps": 17480, "total_steps": 76960, "loss": 0.2581, "lr": 4.7578964094156455e-05, "epoch": 4.542619542619542, "percentage": 22.71, "elapsed_time": "0:25:21", "remaining_time": "1:26:17", "throughput": 1034.78, "total_tokens": 1574568} {"current_steps": 17485, "total_steps": 76960, "loss": 0.2203, "lr": 4.7576529514439715e-05, "epoch": 4.543918918918919, "percentage": 22.72, "elapsed_time": "0:25:22", "remaining_time": "1:26:17", "throughput": 1034.77, "total_tokens": 1574984} {"current_steps": 17490, "total_steps": 76960, "loss": 0.2229, "lr": 4.757409377359043e-05, "epoch": 4.545218295218295, "percentage": 22.73, "elapsed_time": "0:25:22", "remaining_time": "1:26:16", "throughput": 1034.76, "total_tokens": 1575400} {"current_steps": 17495, "total_steps": 76960, "loss": 0.2694, "lr": 4.757165687173388e-05, "epoch": 4.546517671517671, "percentage": 22.73, "elapsed_time": "0:25:22", "remaining_time": "1:26:16", "throughput": 1034.76, "total_tokens": 1575832} {"current_steps": 17500, "total_steps": 76960, "loss": 0.324, "lr": 4.756921880899539e-05, "epoch": 4.547817047817047, "percentage": 22.74, "elapsed_time": "0:25:23", "remaining_time": "1:26:15", "throughput": 1034.78, "total_tokens": 1576296} {"current_steps": 17505, "total_steps": 76960, "loss": 0.279, "lr": 4.7566779585500347e-05, "epoch": 4.549116424116424, "percentage": 22.75, "elapsed_time": "0:25:23", "remaining_time": "1:26:15", "throughput": 1034.79, "total_tokens": 1576744} {"current_steps": 17510, "total_steps": 76960, "loss": 0.1626, "lr": 4.756433920137421e-05, "epoch": 4.5504158004158, "percentage": 22.75, "elapsed_time": "0:25:24", "remaining_time": "1:26:14", "throughput": 1034.8, "total_tokens": 1577192} {"current_steps": 17515, "total_steps": 76960, "loss": 0.3062, "lr": 4.756189765674249e-05, "epoch": 4.5517151767151764, "percentage": 22.76, "elapsed_time": "0:25:24", "remaining_time": "1:26:14", "throughput": 1034.81, "total_tokens": 1577640} {"current_steps": 17520, "total_steps": 76960, "loss": 0.2831, "lr": 4.755945495173075e-05, "epoch": 4.553014553014553, "percentage": 22.77, "elapsed_time": "0:25:24", "remaining_time": "1:26:13", "throughput": 1034.81, "total_tokens": 1578072} {"current_steps": 17525, "total_steps": 76960, "loss": 0.1907, "lr": 4.755701108646463e-05, "epoch": 4.554313929313929, "percentage": 22.77, "elapsed_time": "0:25:25", "remaining_time": "1:26:13", "throughput": 1034.83, "total_tokens": 1578536} {"current_steps": 17530, "total_steps": 76960, "loss": 0.2813, "lr": 4.7554566061069816e-05, "epoch": 4.5556133056133055, "percentage": 22.78, "elapsed_time": "0:25:25", "remaining_time": "1:26:12", "throughput": 1034.83, "total_tokens": 1578968} {"current_steps": 17535, "total_steps": 76960, "loss": 0.2226, "lr": 4.755211987567206e-05, "epoch": 4.5569126819126815, "percentage": 22.78, "elapsed_time": "0:25:26", "remaining_time": "1:26:12", "throughput": 1034.83, "total_tokens": 1579400} {"current_steps": 17540, "total_steps": 76960, "loss": 0.1769, "lr": 4.754967253039717e-05, "epoch": 4.558212058212058, "percentage": 22.79, "elapsed_time": "0:25:26", "remaining_time": "1:26:11", "throughput": 1034.82, "total_tokens": 1579816} {"current_steps": 17545, "total_steps": 76960, "loss": 0.2194, "lr": 4.754722402537102e-05, "epoch": 4.5595114345114345, "percentage": 22.8, "elapsed_time": "0:25:27", "remaining_time": "1:26:11", "throughput": 1034.83, "total_tokens": 1580264} {"current_steps": 17550, "total_steps": 76960, "loss": 0.4212, "lr": 4.7544774360719526e-05, "epoch": 4.5608108108108105, "percentage": 22.8, "elapsed_time": "0:25:27", "remaining_time": "1:26:10", "throughput": 1034.85, "total_tokens": 1580728} {"current_steps": 17555, "total_steps": 76960, "loss": 0.2158, "lr": 4.754232353656869e-05, "epoch": 4.5621101871101875, "percentage": 22.81, "elapsed_time": "0:25:27", "remaining_time": "1:26:10", "throughput": 1034.83, "total_tokens": 1581128} {"current_steps": 17560, "total_steps": 76960, "loss": 0.2818, "lr": 4.753987155304456e-05, "epoch": 4.5634095634095635, "percentage": 22.82, "elapsed_time": "0:25:28", "remaining_time": "1:26:09", "throughput": 1034.81, "total_tokens": 1581544} {"current_steps": 17565, "total_steps": 76960, "loss": 0.2637, "lr": 4.753741841027323e-05, "epoch": 4.5647089397089395, "percentage": 22.82, "elapsed_time": "0:25:28", "remaining_time": "1:26:09", "throughput": 1034.8, "total_tokens": 1581960} {"current_steps": 17570, "total_steps": 76960, "loss": 0.2775, "lr": 4.753496410838088e-05, "epoch": 4.5660083160083165, "percentage": 22.83, "elapsed_time": "0:25:29", "remaining_time": "1:26:08", "throughput": 1034.82, "total_tokens": 1582424} {"current_steps": 17575, "total_steps": 76960, "loss": 0.2526, "lr": 4.753250864749373e-05, "epoch": 4.5673076923076925, "percentage": 22.84, "elapsed_time": "0:25:29", "remaining_time": "1:26:08", "throughput": 1034.84, "total_tokens": 1582888} {"current_steps": 17580, "total_steps": 76960, "loss": 0.2311, "lr": 4.753005202773808e-05, "epoch": 4.5686070686070686, "percentage": 22.84, "elapsed_time": "0:25:30", "remaining_time": "1:26:07", "throughput": 1034.87, "total_tokens": 1583368} {"current_steps": 17585, "total_steps": 76960, "loss": 0.1545, "lr": 4.7527594249240264e-05, "epoch": 4.569906444906445, "percentage": 22.85, "elapsed_time": "0:25:30", "remaining_time": "1:26:07", "throughput": 1034.89, "total_tokens": 1583832} {"current_steps": 17590, "total_steps": 76960, "loss": 0.3523, "lr": 4.752513531212669e-05, "epoch": 4.5712058212058215, "percentage": 22.86, "elapsed_time": "0:25:30", "remaining_time": "1:26:06", "throughput": 1034.91, "total_tokens": 1584296} {"current_steps": 17595, "total_steps": 76960, "loss": 0.3238, "lr": 4.7522675216523824e-05, "epoch": 4.572505197505198, "percentage": 22.86, "elapsed_time": "0:25:31", "remaining_time": "1:26:06", "throughput": 1034.91, "total_tokens": 1584728} {"current_steps": 17600, "total_steps": 76960, "loss": 0.2598, "lr": 4.7520213962558194e-05, "epoch": 4.573804573804574, "percentage": 22.87, "elapsed_time": "0:25:31", "remaining_time": "1:26:05", "throughput": 1034.93, "total_tokens": 1585192} {"current_steps": 17605, "total_steps": 76960, "loss": 0.332, "lr": 4.751775155035637e-05, "epoch": 4.57510395010395, "percentage": 22.88, "elapsed_time": "0:25:32", "remaining_time": "1:26:05", "throughput": 1034.94, "total_tokens": 1585640} {"current_steps": 17610, "total_steps": 76960, "loss": 0.2502, "lr": 4.751528798004502e-05, "epoch": 4.576403326403327, "percentage": 22.88, "elapsed_time": "0:25:32", "remaining_time": "1:26:04", "throughput": 1034.94, "total_tokens": 1586072} {"current_steps": 17615, "total_steps": 76960, "loss": 0.2166, "lr": 4.7512823251750836e-05, "epoch": 4.577702702702703, "percentage": 22.89, "elapsed_time": "0:25:32", "remaining_time": "1:26:04", "throughput": 1034.98, "total_tokens": 1586568} {"current_steps": 17620, "total_steps": 76960, "loss": 0.248, "lr": 4.7510357365600576e-05, "epoch": 4.579002079002079, "percentage": 22.9, "elapsed_time": "0:25:33", "remaining_time": "1:26:04", "throughput": 1035.0, "total_tokens": 1587032} {"current_steps": 17625, "total_steps": 76960, "loss": 0.1873, "lr": 4.750789032172107e-05, "epoch": 4.580301455301456, "percentage": 22.9, "elapsed_time": "0:25:33", "remaining_time": "1:26:03", "throughput": 1035.02, "total_tokens": 1587496} {"current_steps": 17630, "total_steps": 76960, "loss": 0.2635, "lr": 4.750542212023921e-05, "epoch": 4.581600831600832, "percentage": 22.91, "elapsed_time": "0:25:34", "remaining_time": "1:26:03", "throughput": 1035.02, "total_tokens": 1587928} {"current_steps": 17635, "total_steps": 76960, "loss": 0.3153, "lr": 4.750295276128191e-05, "epoch": 4.582900207900208, "percentage": 22.91, "elapsed_time": "0:25:34", "remaining_time": "1:26:02", "throughput": 1035.05, "total_tokens": 1588408} {"current_steps": 17640, "total_steps": 76960, "loss": 0.1187, "lr": 4.7500482244976193e-05, "epoch": 4.584199584199585, "percentage": 22.92, "elapsed_time": "0:25:35", "remaining_time": "1:26:02", "throughput": 1035.05, "total_tokens": 1588840} {"current_steps": 17645, "total_steps": 76960, "loss": 0.3031, "lr": 4.7498010571449117e-05, "epoch": 4.585498960498961, "percentage": 22.93, "elapsed_time": "0:25:35", "remaining_time": "1:26:01", "throughput": 1035.05, "total_tokens": 1589272} {"current_steps": 17650, "total_steps": 76960, "loss": 0.1147, "lr": 4.74955377408278e-05, "epoch": 4.586798336798337, "percentage": 22.93, "elapsed_time": "0:25:35", "remaining_time": "1:26:01", "throughput": 1035.04, "total_tokens": 1589688} {"current_steps": 17655, "total_steps": 76960, "loss": 0.3048, "lr": 4.749306375323943e-05, "epoch": 4.588097713097713, "percentage": 22.94, "elapsed_time": "0:25:36", "remaining_time": "1:26:00", "throughput": 1035.04, "total_tokens": 1590120} {"current_steps": 17660, "total_steps": 76960, "loss": 0.2489, "lr": 4.749058860881123e-05, "epoch": 4.58939708939709, "percentage": 22.95, "elapsed_time": "0:25:36", "remaining_time": "1:26:00", "throughput": 1035.06, "total_tokens": 1590584} {"current_steps": 17665, "total_steps": 76960, "loss": 0.2094, "lr": 4.748811230767051e-05, "epoch": 4.590696465696466, "percentage": 22.95, "elapsed_time": "0:25:37", "remaining_time": "1:25:59", "throughput": 1035.08, "total_tokens": 1591048} {"current_steps": 17670, "total_steps": 76960, "loss": 0.3648, "lr": 4.748563484994463e-05, "epoch": 4.591995841995842, "percentage": 22.96, "elapsed_time": "0:25:37", "remaining_time": "1:25:59", "throughput": 1035.09, "total_tokens": 1591496} {"current_steps": 17675, "total_steps": 76960, "loss": 0.3129, "lr": 4.748315623576101e-05, "epoch": 4.593295218295218, "percentage": 22.97, "elapsed_time": "0:25:37", "remaining_time": "1:25:58", "throughput": 1035.13, "total_tokens": 1591992} {"current_steps": 17680, "total_steps": 76960, "loss": 0.2694, "lr": 4.748067646524711e-05, "epoch": 4.594594594594595, "percentage": 22.97, "elapsed_time": "0:25:38", "remaining_time": "1:25:58", "throughput": 1035.15, "total_tokens": 1592456} {"current_steps": 17685, "total_steps": 76960, "loss": 0.3127, "lr": 4.747819553853049e-05, "epoch": 4.595893970893971, "percentage": 22.98, "elapsed_time": "0:25:38", "remaining_time": "1:25:57", "throughput": 1035.16, "total_tokens": 1592904} {"current_steps": 17690, "total_steps": 76960, "loss": 0.2568, "lr": 4.7475713455738724e-05, "epoch": 4.597193347193347, "percentage": 22.99, "elapsed_time": "0:25:39", "remaining_time": "1:25:57", "throughput": 1035.15, "total_tokens": 1593320} {"current_steps": 17695, "total_steps": 76960, "loss": 0.2816, "lr": 4.747323021699949e-05, "epoch": 4.598492723492724, "percentage": 22.99, "elapsed_time": "0:25:39", "remaining_time": "1:25:56", "throughput": 1035.17, "total_tokens": 1593784} {"current_steps": 17700, "total_steps": 76960, "loss": 0.2626, "lr": 4.7470745822440487e-05, "epoch": 4.5997920997921, "percentage": 23.0, "elapsed_time": "0:25:40", "remaining_time": "1:25:56", "throughput": 1035.18, "total_tokens": 1594232} {"current_steps": 17705, "total_steps": 76960, "loss": 0.2886, "lr": 4.74682602721895e-05, "epoch": 4.601091476091476, "percentage": 23.01, "elapsed_time": "0:25:40", "remaining_time": "1:25:55", "throughput": 1035.19, "total_tokens": 1594680} {"current_steps": 17710, "total_steps": 76960, "loss": 0.239, "lr": 4.746577356637436e-05, "epoch": 4.602390852390853, "percentage": 23.01, "elapsed_time": "0:25:40", "remaining_time": "1:25:55", "throughput": 1035.18, "total_tokens": 1595096} {"current_steps": 17715, "total_steps": 76960, "loss": 0.2036, "lr": 4.746328570512296e-05, "epoch": 4.603690228690229, "percentage": 23.02, "elapsed_time": "0:25:41", "remaining_time": "1:25:54", "throughput": 1035.16, "total_tokens": 1595512} {"current_steps": 17720, "total_steps": 76960, "loss": 0.2529, "lr": 4.746079668856325e-05, "epoch": 4.604989604989605, "percentage": 23.02, "elapsed_time": "0:25:41", "remaining_time": "1:25:54", "throughput": 1035.17, "total_tokens": 1595960} {"current_steps": 17725, "total_steps": 76960, "loss": 0.2168, "lr": 4.745830651682325e-05, "epoch": 4.606288981288982, "percentage": 23.03, "elapsed_time": "0:25:42", "remaining_time": "1:25:53", "throughput": 1035.17, "total_tokens": 1596392} {"current_steps": 17730, "total_steps": 76960, "loss": 0.203, "lr": 4.745581519003102e-05, "epoch": 4.607588357588358, "percentage": 23.04, "elapsed_time": "0:25:42", "remaining_time": "1:25:53", "throughput": 1035.2, "total_tokens": 1596872} {"current_steps": 17735, "total_steps": 76960, "loss": 0.1605, "lr": 4.74533227083147e-05, "epoch": 4.608887733887734, "percentage": 23.04, "elapsed_time": "0:25:42", "remaining_time": "1:25:52", "throughput": 1035.21, "total_tokens": 1597320} {"current_steps": 17740, "total_steps": 76960, "loss": 0.2889, "lr": 4.7450829071802484e-05, "epoch": 4.61018711018711, "percentage": 23.05, "elapsed_time": "0:25:43", "remaining_time": "1:25:52", "throughput": 1035.22, "total_tokens": 1597768} {"current_steps": 17745, "total_steps": 76960, "loss": 0.1463, "lr": 4.744833428062262e-05, "epoch": 4.611486486486487, "percentage": 23.06, "elapsed_time": "0:25:43", "remaining_time": "1:25:51", "throughput": 1035.21, "total_tokens": 1598184} {"current_steps": 17750, "total_steps": 76960, "loss": 0.2147, "lr": 4.74458383349034e-05, "epoch": 4.612785862785863, "percentage": 23.06, "elapsed_time": "0:25:44", "remaining_time": "1:25:51", "throughput": 1035.21, "total_tokens": 1598616} {"current_steps": 17755, "total_steps": 76960, "loss": 0.4283, "lr": 4.744334123477322e-05, "epoch": 4.614085239085239, "percentage": 23.07, "elapsed_time": "0:25:44", "remaining_time": "1:25:50", "throughput": 1035.2, "total_tokens": 1599032} {"current_steps": 17760, "total_steps": 76960, "loss": 0.1265, "lr": 4.7440842980360503e-05, "epoch": 4.615384615384615, "percentage": 23.08, "elapsed_time": "0:25:45", "remaining_time": "1:25:50", "throughput": 1035.2, "total_tokens": 1599464} {"current_steps": 17765, "total_steps": 76960, "loss": 0.2603, "lr": 4.743834357179372e-05, "epoch": 4.616683991683992, "percentage": 23.08, "elapsed_time": "0:25:45", "remaining_time": "1:25:49", "throughput": 1035.18, "total_tokens": 1599880} {"current_steps": 17770, "total_steps": 76960, "loss": 0.3138, "lr": 4.743584300920142e-05, "epoch": 4.617983367983368, "percentage": 23.09, "elapsed_time": "0:25:45", "remaining_time": "1:25:49", "throughput": 1035.2, "total_tokens": 1600344} {"current_steps": 17775, "total_steps": 76960, "loss": 0.2189, "lr": 4.743334129271223e-05, "epoch": 4.619282744282744, "percentage": 23.1, "elapsed_time": "0:25:46", "remaining_time": "1:25:48", "throughput": 1035.21, "total_tokens": 1600792} {"current_steps": 17780, "total_steps": 76960, "loss": 0.2568, "lr": 4.74308384224548e-05, "epoch": 4.620582120582121, "percentage": 23.1, "elapsed_time": "0:25:46", "remaining_time": "1:25:48", "throughput": 1035.21, "total_tokens": 1601224} {"current_steps": 17785, "total_steps": 76960, "loss": 0.2415, "lr": 4.7428334398557856e-05, "epoch": 4.621881496881497, "percentage": 23.11, "elapsed_time": "0:25:47", "remaining_time": "1:25:47", "throughput": 1035.25, "total_tokens": 1601720} {"current_steps": 17790, "total_steps": 76960, "loss": 0.2481, "lr": 4.742582922115019e-05, "epoch": 4.623180873180873, "percentage": 23.12, "elapsed_time": "0:25:47", "remaining_time": "1:25:47", "throughput": 1035.25, "total_tokens": 1602152} {"current_steps": 17795, "total_steps": 76960, "loss": 0.2195, "lr": 4.7423322890360625e-05, "epoch": 4.62448024948025, "percentage": 23.12, "elapsed_time": "0:25:48", "remaining_time": "1:25:46", "throughput": 1035.26, "total_tokens": 1602600} {"current_steps": 17800, "total_steps": 76960, "loss": 0.1746, "lr": 4.7420815406318086e-05, "epoch": 4.625779625779626, "percentage": 23.13, "elapsed_time": "0:25:48", "remaining_time": "1:25:46", "throughput": 1035.26, "total_tokens": 1603032} {"current_steps": 17805, "total_steps": 76960, "loss": 0.1122, "lr": 4.741830676915153e-05, "epoch": 4.627079002079002, "percentage": 23.14, "elapsed_time": "0:25:48", "remaining_time": "1:25:45", "throughput": 1035.26, "total_tokens": 1603464} {"current_steps": 17810, "total_steps": 76960, "loss": 0.2558, "lr": 4.741579697898998e-05, "epoch": 4.628378378378378, "percentage": 23.14, "elapsed_time": "0:25:49", "remaining_time": "1:25:45", "throughput": 1035.28, "total_tokens": 1603928} {"current_steps": 17815, "total_steps": 76960, "loss": 0.2511, "lr": 4.741328603596251e-05, "epoch": 4.629677754677755, "percentage": 23.15, "elapsed_time": "0:25:49", "remaining_time": "1:25:44", "throughput": 1035.27, "total_tokens": 1604344} {"current_steps": 17820, "total_steps": 76960, "loss": 0.1483, "lr": 4.741077394019826e-05, "epoch": 4.630977130977131, "percentage": 23.15, "elapsed_time": "0:25:50", "remaining_time": "1:25:44", "throughput": 1035.24, "total_tokens": 1604744} {"current_steps": 17825, "total_steps": 76960, "loss": 0.1385, "lr": 4.740826069182645e-05, "epoch": 4.632276507276507, "percentage": 23.16, "elapsed_time": "0:25:50", "remaining_time": "1:25:43", "throughput": 1035.26, "total_tokens": 1605208} {"current_steps": 17830, "total_steps": 76960, "loss": 0.2708, "lr": 4.74057462909763e-05, "epoch": 4.633575883575883, "percentage": 23.17, "elapsed_time": "0:25:50", "remaining_time": "1:25:43", "throughput": 1035.27, "total_tokens": 1605656} {"current_steps": 17835, "total_steps": 76960, "loss": 0.3964, "lr": 4.740323073777716e-05, "epoch": 4.63487525987526, "percentage": 23.17, "elapsed_time": "0:25:51", "remaining_time": "1:25:42", "throughput": 1035.28, "total_tokens": 1606104} {"current_steps": 17840, "total_steps": 76960, "loss": 0.2662, "lr": 4.740071403235839e-05, "epoch": 4.636174636174636, "percentage": 23.18, "elapsed_time": "0:25:51", "remaining_time": "1:25:42", "throughput": 1035.27, "total_tokens": 1606536} {"current_steps": 17845, "total_steps": 76960, "loss": 0.2651, "lr": 4.739819617484945e-05, "epoch": 4.637474012474012, "percentage": 23.19, "elapsed_time": "0:25:52", "remaining_time": "1:25:42", "throughput": 1035.3, "total_tokens": 1607000} {"current_steps": 17850, "total_steps": 76960, "loss": 0.1373, "lr": 4.739567716537981e-05, "epoch": 4.638773388773389, "percentage": 23.19, "elapsed_time": "0:25:52", "remaining_time": "1:25:41", "throughput": 1035.29, "total_tokens": 1607432} {"current_steps": 17855, "total_steps": 76960, "loss": 0.1696, "lr": 4.7393157004079034e-05, "epoch": 4.640072765072765, "percentage": 23.2, "elapsed_time": "0:25:53", "remaining_time": "1:25:41", "throughput": 1035.31, "total_tokens": 1607896} {"current_steps": 17860, "total_steps": 76960, "loss": 0.2606, "lr": 4.7390635691076735e-05, "epoch": 4.641372141372141, "percentage": 23.21, "elapsed_time": "0:25:53", "remaining_time": "1:25:40", "throughput": 1035.34, "total_tokens": 1608376} {"current_steps": 17865, "total_steps": 76960, "loss": 0.2574, "lr": 4.73881132265026e-05, "epoch": 4.642671517671518, "percentage": 23.21, "elapsed_time": "0:25:53", "remaining_time": "1:25:40", "throughput": 1035.35, "total_tokens": 1608824} {"current_steps": 17870, "total_steps": 76960, "loss": 0.2687, "lr": 4.738558961048634e-05, "epoch": 4.643970893970894, "percentage": 23.22, "elapsed_time": "0:25:54", "remaining_time": "1:25:39", "throughput": 1035.39, "total_tokens": 1609320} {"current_steps": 17875, "total_steps": 76960, "loss": 0.148, "lr": 4.7383064843157757e-05, "epoch": 4.64527027027027, "percentage": 23.23, "elapsed_time": "0:25:54", "remaining_time": "1:25:39", "throughput": 1035.41, "total_tokens": 1609784} {"current_steps": 17880, "total_steps": 76960, "loss": 0.3869, "lr": 4.7380538924646714e-05, "epoch": 4.646569646569646, "percentage": 23.23, "elapsed_time": "0:25:55", "remaining_time": "1:25:38", "throughput": 1035.42, "total_tokens": 1610232} {"current_steps": 17885, "total_steps": 76960, "loss": 0.1823, "lr": 4.737801185508309e-05, "epoch": 4.647869022869023, "percentage": 23.24, "elapsed_time": "0:25:55", "remaining_time": "1:25:38", "throughput": 1035.41, "total_tokens": 1610648} {"current_steps": 17890, "total_steps": 76960, "loss": 0.3228, "lr": 4.7375483634596895e-05, "epoch": 4.649168399168399, "percentage": 23.25, "elapsed_time": "0:25:55", "remaining_time": "1:25:37", "throughput": 1035.42, "total_tokens": 1611096} {"current_steps": 17895, "total_steps": 76960, "loss": 0.2299, "lr": 4.7372954263318124e-05, "epoch": 4.650467775467775, "percentage": 23.25, "elapsed_time": "0:25:56", "remaining_time": "1:25:37", "throughput": 1035.44, "total_tokens": 1611560} {"current_steps": 17900, "total_steps": 76960, "loss": 0.2727, "lr": 4.737042374137689e-05, "epoch": 4.651767151767151, "percentage": 23.26, "elapsed_time": "0:25:56", "remaining_time": "1:25:36", "throughput": 1035.42, "total_tokens": 1611960} {"current_steps": 17905, "total_steps": 76960, "loss": 0.2781, "lr": 4.736789206890332e-05, "epoch": 4.653066528066528, "percentage": 23.27, "elapsed_time": "0:25:57", "remaining_time": "1:25:36", "throughput": 1035.4, "total_tokens": 1612360} {"current_steps": 17910, "total_steps": 76960, "loss": 0.2543, "lr": 4.736535924602763e-05, "epoch": 4.654365904365904, "percentage": 23.27, "elapsed_time": "0:25:57", "remaining_time": "1:25:35", "throughput": 1035.41, "total_tokens": 1612808} {"current_steps": 17915, "total_steps": 76960, "loss": 0.2606, "lr": 4.736282527288008e-05, "epoch": 4.65566528066528, "percentage": 23.28, "elapsed_time": "0:25:58", "remaining_time": "1:25:35", "throughput": 1035.41, "total_tokens": 1613240} {"current_steps": 17920, "total_steps": 76960, "loss": 0.2292, "lr": 4.736029014959101e-05, "epoch": 4.656964656964657, "percentage": 23.28, "elapsed_time": "0:25:58", "remaining_time": "1:25:34", "throughput": 1035.45, "total_tokens": 1613736} {"current_steps": 17925, "total_steps": 76960, "loss": 0.289, "lr": 4.735775387629079e-05, "epoch": 4.658264033264033, "percentage": 23.29, "elapsed_time": "0:25:58", "remaining_time": "1:25:34", "throughput": 1035.47, "total_tokens": 1614200} {"current_steps": 17930, "total_steps": 76960, "loss": 0.1775, "lr": 4.735521645310986e-05, "epoch": 4.659563409563409, "percentage": 23.3, "elapsed_time": "0:25:59", "remaining_time": "1:25:33", "throughput": 1035.48, "total_tokens": 1614648} {"current_steps": 17935, "total_steps": 76960, "loss": 0.2503, "lr": 4.735267788017874e-05, "epoch": 4.660862785862786, "percentage": 23.3, "elapsed_time": "0:25:59", "remaining_time": "1:25:33", "throughput": 1035.47, "total_tokens": 1615080} {"current_steps": 17940, "total_steps": 76960, "loss": 0.2104, "lr": 4.735013815762796e-05, "epoch": 4.662162162162162, "percentage": 23.31, "elapsed_time": "0:26:00", "remaining_time": "1:25:32", "throughput": 1035.46, "total_tokens": 1615512} {"current_steps": 17945, "total_steps": 76960, "loss": 0.3016, "lr": 4.734759728558819e-05, "epoch": 4.663461538461538, "percentage": 23.32, "elapsed_time": "0:26:00", "remaining_time": "1:25:32", "throughput": 1035.45, "total_tokens": 1615944} {"current_steps": 17950, "total_steps": 76960, "loss": 0.37, "lr": 4.734505526419005e-05, "epoch": 4.664760914760915, "percentage": 23.32, "elapsed_time": "0:26:01", "remaining_time": "1:25:31", "throughput": 1035.46, "total_tokens": 1616392} {"current_steps": 17955, "total_steps": 76960, "loss": 0.2228, "lr": 4.734251209356432e-05, "epoch": 4.666060291060291, "percentage": 23.33, "elapsed_time": "0:26:01", "remaining_time": "1:25:31", "throughput": 1035.46, "total_tokens": 1616824} {"current_steps": 17960, "total_steps": 76960, "loss": 0.2181, "lr": 4.7339967773841786e-05, "epoch": 4.667359667359667, "percentage": 23.34, "elapsed_time": "0:26:01", "remaining_time": "1:25:30", "throughput": 1035.47, "total_tokens": 1617272} {"current_steps": 17965, "total_steps": 76960, "loss": 0.2071, "lr": 4.73374223051533e-05, "epoch": 4.668659043659043, "percentage": 23.34, "elapsed_time": "0:26:02", "remaining_time": "1:25:30", "throughput": 1035.49, "total_tokens": 1617736} {"current_steps": 17970, "total_steps": 76960, "loss": 0.352, "lr": 4.733487568762979e-05, "epoch": 4.66995841995842, "percentage": 23.35, "elapsed_time": "0:26:02", "remaining_time": "1:25:29", "throughput": 1035.49, "total_tokens": 1618184} {"current_steps": 17975, "total_steps": 76960, "loss": 0.2316, "lr": 4.733232792140221e-05, "epoch": 4.671257796257796, "percentage": 23.36, "elapsed_time": "0:26:03", "remaining_time": "1:25:29", "throughput": 1035.49, "total_tokens": 1618616} {"current_steps": 17980, "total_steps": 76960, "loss": 0.2126, "lr": 4.732977900660162e-05, "epoch": 4.672557172557172, "percentage": 23.36, "elapsed_time": "0:26:03", "remaining_time": "1:25:28", "throughput": 1035.5, "total_tokens": 1619064} {"current_steps": 17985, "total_steps": 76960, "loss": 0.2726, "lr": 4.732722894335909e-05, "epoch": 4.673856548856548, "percentage": 23.37, "elapsed_time": "0:26:03", "remaining_time": "1:25:28", "throughput": 1035.52, "total_tokens": 1619528} {"current_steps": 17990, "total_steps": 76960, "loss": 0.2334, "lr": 4.732467773180579e-05, "epoch": 4.675155925155925, "percentage": 23.38, "elapsed_time": "0:26:04", "remaining_time": "1:25:27", "throughput": 1035.53, "total_tokens": 1619976} {"current_steps": 17995, "total_steps": 76960, "loss": 0.2226, "lr": 4.7322125372072924e-05, "epoch": 4.676455301455301, "percentage": 23.38, "elapsed_time": "0:26:04", "remaining_time": "1:25:27", "throughput": 1035.55, "total_tokens": 1620440} {"current_steps": 18000, "total_steps": 76960, "loss": 0.2635, "lr": 4.731957186429176e-05, "epoch": 4.6777546777546775, "percentage": 23.39, "elapsed_time": "0:26:05", "remaining_time": "1:25:27", "throughput": 1035.59, "total_tokens": 1620936} {"current_steps": 18005, "total_steps": 76960, "loss": 0.2142, "lr": 4.731701720859362e-05, "epoch": 4.679054054054054, "percentage": 23.4, "elapsed_time": "0:26:05", "remaining_time": "1:25:26", "throughput": 1035.62, "total_tokens": 1621416} {"current_steps": 18010, "total_steps": 76960, "loss": 0.0947, "lr": 4.731446140510991e-05, "epoch": 4.68035343035343, "percentage": 23.4, "elapsed_time": "0:26:06", "remaining_time": "1:25:26", "throughput": 1035.63, "total_tokens": 1621864} {"current_steps": 18015, "total_steps": 76960, "loss": 0.3913, "lr": 4.731190445397207e-05, "epoch": 4.6816528066528065, "percentage": 23.41, "elapsed_time": "0:26:06", "remaining_time": "1:25:25", "throughput": 1035.66, "total_tokens": 1622344} {"current_steps": 18020, "total_steps": 76960, "loss": 0.212, "lr": 4.730934635531161e-05, "epoch": 4.682952182952183, "percentage": 23.41, "elapsed_time": "0:26:06", "remaining_time": "1:25:25", "throughput": 1035.68, "total_tokens": 1622808} {"current_steps": 18025, "total_steps": 76960, "loss": 0.2517, "lr": 4.7306787109260085e-05, "epoch": 4.6842515592515594, "percentage": 23.42, "elapsed_time": "0:26:07", "remaining_time": "1:25:24", "throughput": 1035.68, "total_tokens": 1623240} {"current_steps": 18030, "total_steps": 76960, "loss": 0.2451, "lr": 4.730422671594913e-05, "epoch": 4.6855509355509355, "percentage": 23.43, "elapsed_time": "0:26:07", "remaining_time": "1:25:24", "throughput": 1035.7, "total_tokens": 1623704} {"current_steps": 18035, "total_steps": 76960, "loss": 0.3156, "lr": 4.7301665175510416e-05, "epoch": 4.6868503118503115, "percentage": 23.43, "elapsed_time": "0:26:08", "remaining_time": "1:25:23", "throughput": 1035.74, "total_tokens": 1624200} {"current_steps": 18040, "total_steps": 76960, "loss": 0.3067, "lr": 4.72991024880757e-05, "epoch": 4.6881496881496885, "percentage": 23.44, "elapsed_time": "0:26:08", "remaining_time": "1:25:23", "throughput": 1035.75, "total_tokens": 1624648} {"current_steps": 18045, "total_steps": 76960, "loss": 0.3005, "lr": 4.729653865377678e-05, "epoch": 4.6894490644490645, "percentage": 23.45, "elapsed_time": "0:26:08", "remaining_time": "1:25:22", "throughput": 1035.74, "total_tokens": 1625080} {"current_steps": 18050, "total_steps": 76960, "loss": 0.28, "lr": 4.729397367274551e-05, "epoch": 4.6907484407484406, "percentage": 23.45, "elapsed_time": "0:26:09", "remaining_time": "1:25:22", "throughput": 1035.78, "total_tokens": 1625560} {"current_steps": 18055, "total_steps": 76960, "loss": 0.2982, "lr": 4.729140754511381e-05, "epoch": 4.692047817047817, "percentage": 23.46, "elapsed_time": "0:26:09", "remaining_time": "1:25:21", "throughput": 1035.77, "total_tokens": 1625992} {"current_steps": 18060, "total_steps": 76960, "loss": 0.2994, "lr": 4.728884027101367e-05, "epoch": 4.6933471933471935, "percentage": 23.47, "elapsed_time": "0:26:10", "remaining_time": "1:25:21", "throughput": 1035.79, "total_tokens": 1626456} {"current_steps": 18065, "total_steps": 76960, "loss": 0.2412, "lr": 4.7286271850577105e-05, "epoch": 4.69464656964657, "percentage": 23.47, "elapsed_time": "0:26:10", "remaining_time": "1:25:20", "throughput": 1035.81, "total_tokens": 1626920} {"current_steps": 18070, "total_steps": 76960, "loss": 0.2193, "lr": 4.728370228393624e-05, "epoch": 4.695945945945946, "percentage": 23.48, "elapsed_time": "0:26:11", "remaining_time": "1:25:20", "throughput": 1035.85, "total_tokens": 1627416} {"current_steps": 18075, "total_steps": 76960, "loss": 0.2073, "lr": 4.7281131571223206e-05, "epoch": 4.6972453222453225, "percentage": 23.49, "elapsed_time": "0:26:11", "remaining_time": "1:25:19", "throughput": 1035.84, "total_tokens": 1627832} {"current_steps": 18080, "total_steps": 76960, "loss": 0.2203, "lr": 4.727855971257023e-05, "epoch": 4.698544698544699, "percentage": 23.49, "elapsed_time": "0:26:11", "remaining_time": "1:25:19", "throughput": 1035.84, "total_tokens": 1628264} {"current_steps": 18085, "total_steps": 76960, "loss": 0.3302, "lr": 4.727598670810958e-05, "epoch": 4.699844074844075, "percentage": 23.5, "elapsed_time": "0:26:12", "remaining_time": "1:25:18", "throughput": 1035.86, "total_tokens": 1628728} {"current_steps": 18090, "total_steps": 76960, "loss": 0.1687, "lr": 4.727341255797358e-05, "epoch": 4.701143451143452, "percentage": 23.51, "elapsed_time": "0:26:12", "remaining_time": "1:25:18", "throughput": 1035.87, "total_tokens": 1629176} {"current_steps": 18095, "total_steps": 76960, "loss": 0.167, "lr": 4.7270837262294644e-05, "epoch": 4.702442827442828, "percentage": 23.51, "elapsed_time": "0:26:13", "remaining_time": "1:25:17", "throughput": 1035.89, "total_tokens": 1629640} {"current_steps": 18100, "total_steps": 76960, "loss": 0.2527, "lr": 4.7268260821205205e-05, "epoch": 4.703742203742204, "percentage": 23.52, "elapsed_time": "0:26:13", "remaining_time": "1:25:17", "throughput": 1035.91, "total_tokens": 1630104} {"current_steps": 18105, "total_steps": 76960, "loss": 0.359, "lr": 4.7265683234837774e-05, "epoch": 4.70504158004158, "percentage": 23.53, "elapsed_time": "0:26:14", "remaining_time": "1:25:16", "throughput": 1035.94, "total_tokens": 1630584} {"current_steps": 18110, "total_steps": 76960, "loss": 0.2101, "lr": 4.726310450332493e-05, "epoch": 4.706340956340957, "percentage": 23.53, "elapsed_time": "0:26:14", "remaining_time": "1:25:16", "throughput": 1035.97, "total_tokens": 1631064} {"current_steps": 18115, "total_steps": 76960, "loss": 0.2084, "lr": 4.726052462679928e-05, "epoch": 4.707640332640333, "percentage": 23.54, "elapsed_time": "0:26:14", "remaining_time": "1:25:15", "throughput": 1036.0, "total_tokens": 1631544} {"current_steps": 18120, "total_steps": 76960, "loss": 0.2082, "lr": 4.725794360539352e-05, "epoch": 4.708939708939709, "percentage": 23.54, "elapsed_time": "0:26:15", "remaining_time": "1:25:15", "throughput": 1036.02, "total_tokens": 1632024} {"current_steps": 18125, "total_steps": 76960, "loss": 0.2751, "lr": 4.7255361439240395e-05, "epoch": 4.710239085239085, "percentage": 23.55, "elapsed_time": "0:26:15", "remaining_time": "1:25:14", "throughput": 1036.03, "total_tokens": 1632472} {"current_steps": 18130, "total_steps": 76960, "loss": 0.2773, "lr": 4.725277812847271e-05, "epoch": 4.711538461538462, "percentage": 23.56, "elapsed_time": "0:26:16", "remaining_time": "1:25:14", "throughput": 1036.06, "total_tokens": 1632952} {"current_steps": 18135, "total_steps": 76960, "loss": 0.2591, "lr": 4.725019367322332e-05, "epoch": 4.712837837837838, "percentage": 23.56, "elapsed_time": "0:26:16", "remaining_time": "1:25:13", "throughput": 1036.06, "total_tokens": 1633384} {"current_steps": 18140, "total_steps": 76960, "loss": 0.2338, "lr": 4.7247608073625154e-05, "epoch": 4.714137214137214, "percentage": 23.57, "elapsed_time": "0:26:16", "remaining_time": "1:25:13", "throughput": 1036.09, "total_tokens": 1633864} {"current_steps": 18145, "total_steps": 76960, "loss": 0.2657, "lr": 4.724502132981119e-05, "epoch": 4.715436590436591, "percentage": 23.58, "elapsed_time": "0:26:17", "remaining_time": "1:25:12", "throughput": 1036.11, "total_tokens": 1634328} {"current_steps": 18150, "total_steps": 76960, "loss": 0.2563, "lr": 4.724243344191446e-05, "epoch": 4.716735966735967, "percentage": 23.58, "elapsed_time": "0:26:17", "remaining_time": "1:25:12", "throughput": 1036.11, "total_tokens": 1634760} {"current_steps": 18155, "total_steps": 76960, "loss": 0.3037, "lr": 4.7239844410068065e-05, "epoch": 4.718035343035343, "percentage": 23.59, "elapsed_time": "0:26:18", "remaining_time": "1:25:11", "throughput": 1036.14, "total_tokens": 1635240} {"current_steps": 18160, "total_steps": 76960, "loss": 0.19, "lr": 4.7237254234405164e-05, "epoch": 4.71933471933472, "percentage": 23.6, "elapsed_time": "0:26:18", "remaining_time": "1:25:11", "throughput": 1036.15, "total_tokens": 1635704} {"current_steps": 18165, "total_steps": 76960, "loss": 0.2546, "lr": 4.723466291505897e-05, "epoch": 4.720634095634096, "percentage": 23.6, "elapsed_time": "0:26:19", "remaining_time": "1:25:10", "throughput": 1036.16, "total_tokens": 1636152} {"current_steps": 18170, "total_steps": 76960, "loss": 0.2673, "lr": 4.7232070452162765e-05, "epoch": 4.721933471933472, "percentage": 23.61, "elapsed_time": "0:26:19", "remaining_time": "1:25:10", "throughput": 1036.16, "total_tokens": 1636584} {"current_steps": 18175, "total_steps": 76960, "loss": 0.2174, "lr": 4.722947684584987e-05, "epoch": 4.723232848232849, "percentage": 23.62, "elapsed_time": "0:26:19", "remaining_time": "1:25:09", "throughput": 1036.18, "total_tokens": 1637048} {"current_steps": 18180, "total_steps": 76960, "loss": 0.2613, "lr": 4.722688209625368e-05, "epoch": 4.724532224532225, "percentage": 23.62, "elapsed_time": "0:26:20", "remaining_time": "1:25:09", "throughput": 1036.23, "total_tokens": 1637560} {"current_steps": 18185, "total_steps": 76960, "loss": 0.3344, "lr": 4.722428620350765e-05, "epoch": 4.725831600831601, "percentage": 23.63, "elapsed_time": "0:26:20", "remaining_time": "1:25:08", "throughput": 1036.22, "total_tokens": 1637976} {"current_steps": 18190, "total_steps": 76960, "loss": 0.2479, "lr": 4.7221689167745286e-05, "epoch": 4.727130977130977, "percentage": 23.64, "elapsed_time": "0:26:21", "remaining_time": "1:25:08", "throughput": 1036.22, "total_tokens": 1638408} {"current_steps": 18195, "total_steps": 76960, "loss": 0.2506, "lr": 4.7219090989100155e-05, "epoch": 4.728430353430354, "percentage": 23.64, "elapsed_time": "0:26:21", "remaining_time": "1:25:08", "throughput": 1036.22, "total_tokens": 1638840} {"current_steps": 18200, "total_steps": 76960, "loss": 0.2984, "lr": 4.721649166770589e-05, "epoch": 4.72972972972973, "percentage": 23.65, "elapsed_time": "0:26:21", "remaining_time": "1:25:07", "throughput": 1036.22, "total_tokens": 1639272} {"current_steps": 18205, "total_steps": 76960, "loss": 0.2102, "lr": 4.7213891203696164e-05, "epoch": 4.731029106029106, "percentage": 23.66, "elapsed_time": "0:26:22", "remaining_time": "1:25:07", "throughput": 1036.25, "total_tokens": 1639752} {"current_steps": 18210, "total_steps": 76960, "loss": 0.2509, "lr": 4.7211289597204736e-05, "epoch": 4.732328482328482, "percentage": 23.66, "elapsed_time": "0:26:22", "remaining_time": "1:25:06", "throughput": 1036.27, "total_tokens": 1640216} {"current_steps": 18215, "total_steps": 76960, "loss": 0.185, "lr": 4.7208686848365394e-05, "epoch": 4.733627858627859, "percentage": 23.67, "elapsed_time": "0:26:23", "remaining_time": "1:25:06", "throughput": 1036.28, "total_tokens": 1640680} {"current_steps": 18220, "total_steps": 76960, "loss": 0.2586, "lr": 4.7206082957312015e-05, "epoch": 4.734927234927235, "percentage": 23.67, "elapsed_time": "0:26:23", "remaining_time": "1:25:05", "throughput": 1036.29, "total_tokens": 1641128} {"current_steps": 18225, "total_steps": 76960, "loss": 0.1776, "lr": 4.7203477924178506e-05, "epoch": 4.736226611226611, "percentage": 23.68, "elapsed_time": "0:26:24", "remaining_time": "1:25:05", "throughput": 1036.32, "total_tokens": 1641608} {"current_steps": 18230, "total_steps": 76960, "loss": 0.3874, "lr": 4.720087174909886e-05, "epoch": 4.737525987525988, "percentage": 23.69, "elapsed_time": "0:26:24", "remaining_time": "1:25:04", "throughput": 1036.32, "total_tokens": 1642040} {"current_steps": 18235, "total_steps": 76960, "loss": 0.3458, "lr": 4.7198264432207106e-05, "epoch": 4.738825363825364, "percentage": 23.69, "elapsed_time": "0:26:24", "remaining_time": "1:25:04", "throughput": 1036.33, "total_tokens": 1642488} {"current_steps": 18240, "total_steps": 76960, "loss": 0.2328, "lr": 4.7195655973637345e-05, "epoch": 4.74012474012474, "percentage": 23.7, "elapsed_time": "0:26:25", "remaining_time": "1:25:03", "throughput": 1036.32, "total_tokens": 1642904} {"current_steps": 18245, "total_steps": 76960, "loss": 0.2605, "lr": 4.719304637352373e-05, "epoch": 4.741424116424117, "percentage": 23.71, "elapsed_time": "0:26:25", "remaining_time": "1:25:03", "throughput": 1036.34, "total_tokens": 1643368} {"current_steps": 18250, "total_steps": 76960, "loss": 0.2689, "lr": 4.719043563200047e-05, "epoch": 4.742723492723493, "percentage": 23.71, "elapsed_time": "0:26:26", "remaining_time": "1:25:02", "throughput": 1036.36, "total_tokens": 1643832} {"current_steps": 18255, "total_steps": 76960, "loss": 0.2768, "lr": 4.718782374920184e-05, "epoch": 4.744022869022869, "percentage": 23.72, "elapsed_time": "0:26:26", "remaining_time": "1:25:02", "throughput": 1036.38, "total_tokens": 1644296} {"current_steps": 18260, "total_steps": 76960, "loss": 0.3092, "lr": 4.718521072526219e-05, "epoch": 4.745322245322245, "percentage": 23.73, "elapsed_time": "0:26:27", "remaining_time": "1:25:01", "throughput": 1036.4, "total_tokens": 1644776} {"current_steps": 18265, "total_steps": 76960, "loss": 0.2614, "lr": 4.7182596560315886e-05, "epoch": 4.746621621621622, "percentage": 23.73, "elapsed_time": "0:26:27", "remaining_time": "1:25:01", "throughput": 1036.41, "total_tokens": 1645224} {"current_steps": 18270, "total_steps": 76960, "loss": 0.2615, "lr": 4.7179981254497385e-05, "epoch": 4.747920997920998, "percentage": 23.74, "elapsed_time": "0:26:27", "remaining_time": "1:25:00", "throughput": 1036.43, "total_tokens": 1645688} {"current_steps": 18275, "total_steps": 76960, "loss": 0.2734, "lr": 4.7177364807941206e-05, "epoch": 4.749220374220374, "percentage": 23.75, "elapsed_time": "0:26:28", "remaining_time": "1:25:00", "throughput": 1036.46, "total_tokens": 1646168} {"current_steps": 18280, "total_steps": 76960, "loss": 0.2998, "lr": 4.71747472207819e-05, "epoch": 4.75051975051975, "percentage": 23.75, "elapsed_time": "0:26:28", "remaining_time": "1:24:59", "throughput": 1036.46, "total_tokens": 1646600} {"current_steps": 18285, "total_steps": 76960, "loss": 0.2863, "lr": 4.7172128493154086e-05, "epoch": 4.751819126819127, "percentage": 23.76, "elapsed_time": "0:26:29", "remaining_time": "1:24:59", "throughput": 1036.47, "total_tokens": 1647048} {"current_steps": 18290, "total_steps": 76960, "loss": 0.2272, "lr": 4.7169508625192475e-05, "epoch": 4.753118503118503, "percentage": 23.77, "elapsed_time": "0:26:29", "remaining_time": "1:24:58", "throughput": 1036.49, "total_tokens": 1647512} {"current_steps": 18295, "total_steps": 76960, "loss": 0.2571, "lr": 4.716688761703179e-05, "epoch": 4.754417879417879, "percentage": 23.77, "elapsed_time": "0:26:29", "remaining_time": "1:24:58", "throughput": 1036.48, "total_tokens": 1647928} {"current_steps": 18300, "total_steps": 76960, "loss": 0.2252, "lr": 4.716426546880683e-05, "epoch": 4.755717255717256, "percentage": 23.78, "elapsed_time": "0:26:30", "remaining_time": "1:24:57", "throughput": 1036.48, "total_tokens": 1648360} {"current_steps": 18305, "total_steps": 76960, "loss": 0.2116, "lr": 4.7161642180652464e-05, "epoch": 4.757016632016632, "percentage": 23.79, "elapsed_time": "0:26:30", "remaining_time": "1:24:57", "throughput": 1036.5, "total_tokens": 1648824} {"current_steps": 18310, "total_steps": 76960, "loss": 0.2064, "lr": 4.715901775270361e-05, "epoch": 4.758316008316008, "percentage": 23.79, "elapsed_time": "0:26:31", "remaining_time": "1:24:56", "throughput": 1036.47, "total_tokens": 1649224} {"current_steps": 18315, "total_steps": 76960, "loss": 0.3805, "lr": 4.715639218509524e-05, "epoch": 4.759615384615385, "percentage": 23.8, "elapsed_time": "0:26:31", "remaining_time": "1:24:56", "throughput": 1036.48, "total_tokens": 1649672} {"current_steps": 18320, "total_steps": 76960, "loss": 0.2134, "lr": 4.715376547796239e-05, "epoch": 4.760914760914761, "percentage": 23.8, "elapsed_time": "0:26:32", "remaining_time": "1:24:55", "throughput": 1036.53, "total_tokens": 1650184} {"current_steps": 18325, "total_steps": 76960, "loss": 0.3145, "lr": 4.715113763144015e-05, "epoch": 4.762214137214137, "percentage": 23.81, "elapsed_time": "0:26:32", "remaining_time": "1:24:55", "throughput": 1036.55, "total_tokens": 1650648} {"current_steps": 18330, "total_steps": 76960, "loss": 0.2558, "lr": 4.714850864566368e-05, "epoch": 4.763513513513513, "percentage": 23.82, "elapsed_time": "0:26:32", "remaining_time": "1:24:54", "throughput": 1036.56, "total_tokens": 1651096} {"current_steps": 18335, "total_steps": 76960, "loss": 0.1996, "lr": 4.7145878520768194e-05, "epoch": 4.76481288981289, "percentage": 23.82, "elapsed_time": "0:26:33", "remaining_time": "1:24:54", "throughput": 1036.58, "total_tokens": 1651560} {"current_steps": 18340, "total_steps": 76960, "loss": 0.2504, "lr": 4.714324725688895e-05, "epoch": 4.766112266112266, "percentage": 23.83, "elapsed_time": "0:26:33", "remaining_time": "1:24:53", "throughput": 1036.59, "total_tokens": 1652008} {"current_steps": 18345, "total_steps": 76960, "loss": 0.1877, "lr": 4.7140614854161284e-05, "epoch": 4.767411642411642, "percentage": 23.84, "elapsed_time": "0:26:34", "remaining_time": "1:24:53", "throughput": 1036.58, "total_tokens": 1652424} {"current_steps": 18350, "total_steps": 76960, "loss": 0.2761, "lr": 4.713798131272058e-05, "epoch": 4.768711018711018, "percentage": 23.84, "elapsed_time": "0:26:34", "remaining_time": "1:24:52", "throughput": 1036.6, "total_tokens": 1652904} {"current_steps": 18355, "total_steps": 76960, "loss": 0.3164, "lr": 4.7135346632702293e-05, "epoch": 4.770010395010395, "percentage": 23.85, "elapsed_time": "0:26:34", "remaining_time": "1:24:52", "throughput": 1036.61, "total_tokens": 1653352} {"current_steps": 18360, "total_steps": 76960, "loss": 0.3578, "lr": 4.7132710814241914e-05, "epoch": 4.771309771309771, "percentage": 23.86, "elapsed_time": "0:26:35", "remaining_time": "1:24:51", "throughput": 1036.65, "total_tokens": 1653848} {"current_steps": 18365, "total_steps": 76960, "loss": 0.1945, "lr": 4.713007385747501e-05, "epoch": 4.772609147609147, "percentage": 23.86, "elapsed_time": "0:26:35", "remaining_time": "1:24:51", "throughput": 1036.65, "total_tokens": 1654280} {"current_steps": 18370, "total_steps": 76960, "loss": 0.1977, "lr": 4.712743576253721e-05, "epoch": 4.773908523908524, "percentage": 23.87, "elapsed_time": "0:26:36", "remaining_time": "1:24:51", "throughput": 1036.67, "total_tokens": 1654744} {"current_steps": 18375, "total_steps": 76960, "loss": 0.2605, "lr": 4.712479652956419e-05, "epoch": 4.7752079002079, "percentage": 23.88, "elapsed_time": "0:26:36", "remaining_time": "1:24:50", "throughput": 1036.67, "total_tokens": 1655176} {"current_steps": 18380, "total_steps": 76960, "loss": 0.159, "lr": 4.712215615869167e-05, "epoch": 4.776507276507276, "percentage": 23.88, "elapsed_time": "0:26:37", "remaining_time": "1:24:50", "throughput": 1036.68, "total_tokens": 1655624} {"current_steps": 18385, "total_steps": 76960, "loss": 0.4049, "lr": 4.7119514650055476e-05, "epoch": 4.777806652806653, "percentage": 23.89, "elapsed_time": "0:26:37", "remaining_time": "1:24:49", "throughput": 1036.7, "total_tokens": 1656088} {"current_steps": 18390, "total_steps": 76960, "loss": 0.2831, "lr": 4.711687200379144e-05, "epoch": 4.779106029106029, "percentage": 23.9, "elapsed_time": "0:26:37", "remaining_time": "1:24:49", "throughput": 1036.72, "total_tokens": 1656552} {"current_steps": 18395, "total_steps": 76960, "loss": 0.3143, "lr": 4.71142282200355e-05, "epoch": 4.780405405405405, "percentage": 23.9, "elapsed_time": "0:26:38", "remaining_time": "1:24:48", "throughput": 1036.73, "total_tokens": 1657000} {"current_steps": 18400, "total_steps": 76960, "loss": 0.291, "lr": 4.71115832989236e-05, "epoch": 4.781704781704782, "percentage": 23.91, "elapsed_time": "0:26:38", "remaining_time": "1:24:48", "throughput": 1036.74, "total_tokens": 1657464} {"current_steps": 18405, "total_steps": 76960, "loss": 0.6146, "lr": 4.710893724059179e-05, "epoch": 4.783004158004158, "percentage": 23.92, "elapsed_time": "0:26:39", "remaining_time": "1:24:47", "throughput": 1036.75, "total_tokens": 1657912} {"current_steps": 18410, "total_steps": 76960, "loss": 0.261, "lr": 4.710629004517615e-05, "epoch": 4.784303534303534, "percentage": 23.92, "elapsed_time": "0:26:39", "remaining_time": "1:24:47", "throughput": 1036.76, "total_tokens": 1658360} {"current_steps": 18415, "total_steps": 76960, "loss": 0.247, "lr": 4.710364171281283e-05, "epoch": 4.78560291060291, "percentage": 23.93, "elapsed_time": "0:26:39", "remaining_time": "1:24:46", "throughput": 1036.78, "total_tokens": 1658824} {"current_steps": 18420, "total_steps": 76960, "loss": 0.2337, "lr": 4.710099224363804e-05, "epoch": 4.786902286902287, "percentage": 23.93, "elapsed_time": "0:26:40", "remaining_time": "1:24:46", "throughput": 1036.82, "total_tokens": 1659320} {"current_steps": 18425, "total_steps": 76960, "loss": 0.2628, "lr": 4.709834163778805e-05, "epoch": 4.788201663201663, "percentage": 23.94, "elapsed_time": "0:26:40", "remaining_time": "1:24:45", "throughput": 1036.84, "total_tokens": 1659784} {"current_steps": 18430, "total_steps": 76960, "loss": 0.3614, "lr": 4.709568989539917e-05, "epoch": 4.789501039501039, "percentage": 23.95, "elapsed_time": "0:26:41", "remaining_time": "1:24:45", "throughput": 1036.86, "total_tokens": 1660248} {"current_steps": 18435, "total_steps": 76960, "loss": 0.2613, "lr": 4.709303701660779e-05, "epoch": 4.790800415800415, "percentage": 23.95, "elapsed_time": "0:26:41", "remaining_time": "1:24:44", "throughput": 1036.88, "total_tokens": 1660712} {"current_steps": 18440, "total_steps": 76960, "loss": 0.2453, "lr": 4.709038300155034e-05, "epoch": 4.792099792099792, "percentage": 23.96, "elapsed_time": "0:26:42", "remaining_time": "1:24:44", "throughput": 1036.92, "total_tokens": 1661208} {"current_steps": 18445, "total_steps": 76960, "loss": 0.2587, "lr": 4.708772785036334e-05, "epoch": 4.793399168399168, "percentage": 23.97, "elapsed_time": "0:26:42", "remaining_time": "1:24:43", "throughput": 1036.93, "total_tokens": 1661656} {"current_steps": 18450, "total_steps": 76960, "loss": 0.2841, "lr": 4.7085071563183325e-05, "epoch": 4.794698544698544, "percentage": 23.97, "elapsed_time": "0:26:42", "remaining_time": "1:24:43", "throughput": 1036.96, "total_tokens": 1662136} {"current_steps": 18455, "total_steps": 76960, "loss": 0.1894, "lr": 4.7082414140146914e-05, "epoch": 4.795997920997921, "percentage": 23.98, "elapsed_time": "0:26:43", "remaining_time": "1:24:42", "throughput": 1036.98, "total_tokens": 1662600} {"current_steps": 18460, "total_steps": 76960, "loss": 0.3316, "lr": 4.70797555813908e-05, "epoch": 4.797297297297297, "percentage": 23.99, "elapsed_time": "0:26:43", "remaining_time": "1:24:42", "throughput": 1036.98, "total_tokens": 1663048} {"current_steps": 18465, "total_steps": 76960, "loss": 0.2758, "lr": 4.7077095887051686e-05, "epoch": 4.798596673596673, "percentage": 23.99, "elapsed_time": "0:26:44", "remaining_time": "1:24:41", "throughput": 1036.99, "total_tokens": 1663496} {"current_steps": 18470, "total_steps": 76960, "loss": 0.2508, "lr": 4.707443505726639e-05, "epoch": 4.79989604989605, "percentage": 24.0, "elapsed_time": "0:26:44", "remaining_time": "1:24:41", "throughput": 1037.0, "total_tokens": 1663944} {"current_steps": 18475, "total_steps": 76960, "loss": 0.1737, "lr": 4.707177309217173e-05, "epoch": 4.801195426195426, "percentage": 24.01, "elapsed_time": "0:26:44", "remaining_time": "1:24:40", "throughput": 1036.99, "total_tokens": 1664360} {"current_steps": 18480, "total_steps": 76960, "loss": 0.2898, "lr": 4.706910999190465e-05, "epoch": 4.802494802494802, "percentage": 24.01, "elapsed_time": "0:26:45", "remaining_time": "1:24:40", "throughput": 1037.0, "total_tokens": 1664808} {"current_steps": 18485, "total_steps": 76960, "loss": 0.126, "lr": 4.706644575660209e-05, "epoch": 4.8037941787941785, "percentage": 24.02, "elapsed_time": "0:26:45", "remaining_time": "1:24:39", "throughput": 1037.0, "total_tokens": 1665240} {"current_steps": 18490, "total_steps": 76960, "loss": 0.3292, "lr": 4.706378038640108e-05, "epoch": 4.805093555093555, "percentage": 24.03, "elapsed_time": "0:26:46", "remaining_time": "1:24:39", "throughput": 1037.01, "total_tokens": 1665688} {"current_steps": 18495, "total_steps": 76960, "loss": 0.2785, "lr": 4.70611138814387e-05, "epoch": 4.8063929313929314, "percentage": 24.03, "elapsed_time": "0:26:46", "remaining_time": "1:24:38", "throughput": 1037.01, "total_tokens": 1666120} {"current_steps": 18500, "total_steps": 76960, "loss": 0.2032, "lr": 4.705844624185211e-05, "epoch": 4.8076923076923075, "percentage": 24.04, "elapsed_time": "0:26:47", "remaining_time": "1:24:38", "throughput": 1037.01, "total_tokens": 1666552} {"current_steps": 18505, "total_steps": 76960, "loss": 0.3401, "lr": 4.705577746777849e-05, "epoch": 4.8089916839916835, "percentage": 24.04, "elapsed_time": "0:26:47", "remaining_time": "1:24:37", "throughput": 1037.04, "total_tokens": 1667032} {"current_steps": 18510, "total_steps": 76960, "loss": 0.2465, "lr": 4.705310755935509e-05, "epoch": 4.8102910602910605, "percentage": 24.05, "elapsed_time": "0:26:47", "remaining_time": "1:24:37", "throughput": 1037.05, "total_tokens": 1667496} {"current_steps": 18515, "total_steps": 76960, "loss": 0.328, "lr": 4.705043651671924e-05, "epoch": 4.8115904365904365, "percentage": 24.06, "elapsed_time": "0:26:48", "remaining_time": "1:24:36", "throughput": 1037.07, "total_tokens": 1667960} {"current_steps": 18520, "total_steps": 76960, "loss": 0.2551, "lr": 4.7047764340008324e-05, "epoch": 4.8128898128898125, "percentage": 24.06, "elapsed_time": "0:26:48", "remaining_time": "1:24:36", "throughput": 1037.09, "total_tokens": 1668424} {"current_steps": 18525, "total_steps": 76960, "loss": 0.272, "lr": 4.704509102935976e-05, "epoch": 4.8141891891891895, "percentage": 24.07, "elapsed_time": "0:26:49", "remaining_time": "1:24:35", "throughput": 1037.12, "total_tokens": 1668904} {"current_steps": 18530, "total_steps": 76960, "loss": 0.2671, "lr": 4.704241658491104e-05, "epoch": 4.8154885654885655, "percentage": 24.08, "elapsed_time": "0:26:49", "remaining_time": "1:24:35", "throughput": 1037.12, "total_tokens": 1669336} {"current_steps": 18535, "total_steps": 76960, "loss": 0.2398, "lr": 4.703974100679971e-05, "epoch": 4.816787941787942, "percentage": 24.08, "elapsed_time": "0:26:50", "remaining_time": "1:24:34", "throughput": 1037.13, "total_tokens": 1669784} {"current_steps": 18540, "total_steps": 76960, "loss": 0.2727, "lr": 4.703706429516339e-05, "epoch": 4.8180873180873185, "percentage": 24.09, "elapsed_time": "0:26:50", "remaining_time": "1:24:34", "throughput": 1037.14, "total_tokens": 1670232} {"current_steps": 18545, "total_steps": 76960, "loss": 0.2673, "lr": 4.7034386450139735e-05, "epoch": 4.8193866943866945, "percentage": 24.1, "elapsed_time": "0:26:50", "remaining_time": "1:24:34", "throughput": 1037.14, "total_tokens": 1670664} {"current_steps": 18550, "total_steps": 76960, "loss": 0.1454, "lr": 4.703170747186647e-05, "epoch": 4.820686070686071, "percentage": 24.1, "elapsed_time": "0:26:51", "remaining_time": "1:24:33", "throughput": 1037.14, "total_tokens": 1671096} {"current_steps": 18555, "total_steps": 76960, "loss": 0.264, "lr": 4.702902736048138e-05, "epoch": 4.821985446985447, "percentage": 24.11, "elapsed_time": "0:26:51", "remaining_time": "1:24:33", "throughput": 1037.16, "total_tokens": 1671576} {"current_steps": 18560, "total_steps": 76960, "loss": 0.2673, "lr": 4.702634611612231e-05, "epoch": 4.8232848232848236, "percentage": 24.12, "elapsed_time": "0:26:52", "remaining_time": "1:24:32", "throughput": 1037.17, "total_tokens": 1672024} {"current_steps": 18565, "total_steps": 76960, "loss": 0.2797, "lr": 4.702366373892715e-05, "epoch": 4.8245841995842, "percentage": 24.12, "elapsed_time": "0:26:52", "remaining_time": "1:24:32", "throughput": 1037.19, "total_tokens": 1672488} {"current_steps": 18570, "total_steps": 76960, "loss": 0.3899, "lr": 4.702098022903386e-05, "epoch": 4.825883575883576, "percentage": 24.13, "elapsed_time": "0:26:52", "remaining_time": "1:24:31", "throughput": 1037.21, "total_tokens": 1672952} {"current_steps": 18575, "total_steps": 76960, "loss": 0.2641, "lr": 4.701829558658046e-05, "epoch": 4.827182952182953, "percentage": 24.14, "elapsed_time": "0:26:53", "remaining_time": "1:24:31", "throughput": 1037.24, "total_tokens": 1673432} {"current_steps": 18580, "total_steps": 76960, "loss": 0.2242, "lr": 4.701560981170503e-05, "epoch": 4.828482328482329, "percentage": 24.14, "elapsed_time": "0:26:53", "remaining_time": "1:24:30", "throughput": 1037.23, "total_tokens": 1673848} {"current_steps": 18585, "total_steps": 76960, "loss": 0.2688, "lr": 4.701292290454568e-05, "epoch": 4.829781704781705, "percentage": 24.15, "elapsed_time": "0:26:54", "remaining_time": "1:24:30", "throughput": 1037.26, "total_tokens": 1674328} {"current_steps": 18590, "total_steps": 76960, "loss": 0.2706, "lr": 4.7010234865240624e-05, "epoch": 4.831081081081081, "percentage": 24.16, "elapsed_time": "0:26:54", "remaining_time": "1:24:29", "throughput": 1037.27, "total_tokens": 1674776} {"current_steps": 18595, "total_steps": 76960, "loss": 0.2909, "lr": 4.700754569392809e-05, "epoch": 4.832380457380458, "percentage": 24.16, "elapsed_time": "0:26:55", "remaining_time": "1:24:29", "throughput": 1037.3, "total_tokens": 1675256} {"current_steps": 18600, "total_steps": 76960, "loss": 0.2594, "lr": 4.700485539074641e-05, "epoch": 4.833679833679834, "percentage": 24.17, "elapsed_time": "0:26:55", "remaining_time": "1:24:28", "throughput": 1037.29, "total_tokens": 1675672} {"current_steps": 18605, "total_steps": 76960, "loss": 0.2319, "lr": 4.700216395583391e-05, "epoch": 4.83497920997921, "percentage": 24.17, "elapsed_time": "0:26:55", "remaining_time": "1:24:28", "throughput": 1037.27, "total_tokens": 1676088} {"current_steps": 18610, "total_steps": 76960, "loss": 0.2359, "lr": 4.6999471389329055e-05, "epoch": 4.836278586278587, "percentage": 24.18, "elapsed_time": "0:26:56", "remaining_time": "1:24:27", "throughput": 1037.29, "total_tokens": 1676552} {"current_steps": 18615, "total_steps": 76960, "loss": 0.2587, "lr": 4.6996777691370295e-05, "epoch": 4.837577962577963, "percentage": 24.19, "elapsed_time": "0:26:56", "remaining_time": "1:24:27", "throughput": 1037.32, "total_tokens": 1677032} {"current_steps": 18620, "total_steps": 76960, "loss": 0.2685, "lr": 4.699408286209619e-05, "epoch": 4.838877338877339, "percentage": 24.19, "elapsed_time": "0:26:57", "remaining_time": "1:24:26", "throughput": 1037.34, "total_tokens": 1677496} {"current_steps": 18625, "total_steps": 76960, "loss": 0.2961, "lr": 4.699138690164533e-05, "epoch": 4.840176715176716, "percentage": 24.2, "elapsed_time": "0:26:57", "remaining_time": "1:24:26", "throughput": 1037.37, "total_tokens": 1677976} {"current_steps": 18630, "total_steps": 76960, "loss": 0.1951, "lr": 4.698868981015637e-05, "epoch": 4.841476091476092, "percentage": 24.21, "elapsed_time": "0:26:57", "remaining_time": "1:24:25", "throughput": 1037.36, "total_tokens": 1678392} {"current_steps": 18635, "total_steps": 76960, "loss": 0.2973, "lr": 4.6985991587768016e-05, "epoch": 4.842775467775468, "percentage": 24.21, "elapsed_time": "0:26:58", "remaining_time": "1:24:25", "throughput": 1037.36, "total_tokens": 1678824} {"current_steps": 18640, "total_steps": 76960, "loss": 0.2479, "lr": 4.698329223461906e-05, "epoch": 4.844074844074844, "percentage": 24.22, "elapsed_time": "0:26:58", "remaining_time": "1:24:24", "throughput": 1037.35, "total_tokens": 1679256} {"current_steps": 18645, "total_steps": 76960, "loss": 0.2974, "lr": 4.6980591750848315e-05, "epoch": 4.845374220374221, "percentage": 24.23, "elapsed_time": "0:26:59", "remaining_time": "1:24:24", "throughput": 1037.39, "total_tokens": 1679752} {"current_steps": 18650, "total_steps": 76960, "loss": 1.357, "lr": 4.697789013659468e-05, "epoch": 4.846673596673597, "percentage": 24.23, "elapsed_time": "0:26:59", "remaining_time": "1:24:23", "throughput": 1037.38, "total_tokens": 1680168} {"current_steps": 18655, "total_steps": 76960, "loss": 0.2679, "lr": 4.697518739199709e-05, "epoch": 4.847972972972973, "percentage": 24.24, "elapsed_time": "0:27:00", "remaining_time": "1:24:23", "throughput": 1037.4, "total_tokens": 1680632} {"current_steps": 18660, "total_steps": 76960, "loss": 0.2857, "lr": 4.697248351719457e-05, "epoch": 4.849272349272349, "percentage": 24.25, "elapsed_time": "0:27:00", "remaining_time": "1:24:22", "throughput": 1037.42, "total_tokens": 1681096} {"current_steps": 18665, "total_steps": 76960, "loss": 0.289, "lr": 4.6969778512326156e-05, "epoch": 4.850571725571726, "percentage": 24.25, "elapsed_time": "0:27:00", "remaining_time": "1:24:22", "throughput": 1037.42, "total_tokens": 1681544} {"current_steps": 18670, "total_steps": 76960, "loss": 0.2161, "lr": 4.6967072377530983e-05, "epoch": 4.851871101871102, "percentage": 24.26, "elapsed_time": "0:27:01", "remaining_time": "1:24:21", "throughput": 1037.43, "total_tokens": 1681992} {"current_steps": 18675, "total_steps": 76960, "loss": 0.2851, "lr": 4.6964365112948237e-05, "epoch": 4.853170478170478, "percentage": 24.27, "elapsed_time": "0:27:01", "remaining_time": "1:24:21", "throughput": 1037.43, "total_tokens": 1682424} {"current_steps": 18680, "total_steps": 76960, "loss": 0.2723, "lr": 4.696165671871714e-05, "epoch": 4.854469854469855, "percentage": 24.27, "elapsed_time": "0:27:02", "remaining_time": "1:24:20", "throughput": 1037.44, "total_tokens": 1682872} {"current_steps": 18685, "total_steps": 76960, "loss": 0.2446, "lr": 4.695894719497701e-05, "epoch": 4.855769230769231, "percentage": 24.28, "elapsed_time": "0:27:02", "remaining_time": "1:24:20", "throughput": 1037.44, "total_tokens": 1683304} {"current_steps": 18690, "total_steps": 76960, "loss": 0.2345, "lr": 4.695623654186717e-05, "epoch": 4.857068607068607, "percentage": 24.29, "elapsed_time": "0:27:02", "remaining_time": "1:24:19", "throughput": 1037.43, "total_tokens": 1683720} {"current_steps": 18695, "total_steps": 76960, "loss": 0.2919, "lr": 4.6953524759527054e-05, "epoch": 4.858367983367984, "percentage": 24.29, "elapsed_time": "0:27:03", "remaining_time": "1:24:19", "throughput": 1037.43, "total_tokens": 1684152} {"current_steps": 18700, "total_steps": 76960, "loss": 0.2666, "lr": 4.6950811848096124e-05, "epoch": 4.85966735966736, "percentage": 24.3, "elapsed_time": "0:27:03", "remaining_time": "1:24:18", "throughput": 1037.44, "total_tokens": 1684600} {"current_steps": 18705, "total_steps": 76960, "loss": 0.2208, "lr": 4.694809780771391e-05, "epoch": 4.860966735966736, "percentage": 24.3, "elapsed_time": "0:27:04", "remaining_time": "1:24:18", "throughput": 1037.44, "total_tokens": 1685048} {"current_steps": 18710, "total_steps": 76960, "loss": 0.2501, "lr": 4.694538263851999e-05, "epoch": 4.862266112266112, "percentage": 24.31, "elapsed_time": "0:27:04", "remaining_time": "1:24:18", "throughput": 1037.47, "total_tokens": 1685528} {"current_steps": 18715, "total_steps": 76960, "loss": 0.264, "lr": 4.694266634065402e-05, "epoch": 4.863565488565489, "percentage": 24.32, "elapsed_time": "0:27:05", "remaining_time": "1:24:17", "throughput": 1037.49, "total_tokens": 1685992} {"current_steps": 18720, "total_steps": 76960, "loss": 0.2208, "lr": 4.69399489142557e-05, "epoch": 4.864864864864865, "percentage": 24.32, "elapsed_time": "0:27:05", "remaining_time": "1:24:17", "throughput": 1037.48, "total_tokens": 1686408} {"current_steps": 18725, "total_steps": 76960, "loss": 0.3608, "lr": 4.6937230359464774e-05, "epoch": 4.866164241164241, "percentage": 24.33, "elapsed_time": "0:27:05", "remaining_time": "1:24:16", "throughput": 1037.49, "total_tokens": 1686856} {"current_steps": 18730, "total_steps": 76960, "loss": 0.2438, "lr": 4.6934510676421074e-05, "epoch": 4.867463617463617, "percentage": 24.34, "elapsed_time": "0:27:06", "remaining_time": "1:24:16", "throughput": 1037.5, "total_tokens": 1687304} {"current_steps": 18735, "total_steps": 76960, "loss": 0.294, "lr": 4.693178986526448e-05, "epoch": 4.868762993762994, "percentage": 24.34, "elapsed_time": "0:27:06", "remaining_time": "1:24:15", "throughput": 1037.51, "total_tokens": 1687768} {"current_steps": 18740, "total_steps": 76960, "loss": 0.2824, "lr": 4.6929067926134915e-05, "epoch": 4.87006237006237, "percentage": 24.35, "elapsed_time": "0:27:07", "remaining_time": "1:24:15", "throughput": 1037.55, "total_tokens": 1688264} {"current_steps": 18745, "total_steps": 76960, "loss": 0.2073, "lr": 4.692634485917238e-05, "epoch": 4.871361746361746, "percentage": 24.36, "elapsed_time": "0:27:07", "remaining_time": "1:24:14", "throughput": 1037.58, "total_tokens": 1688744} {"current_steps": 18750, "total_steps": 76960, "loss": 0.2571, "lr": 4.692362066451691e-05, "epoch": 4.872661122661123, "percentage": 24.36, "elapsed_time": "0:27:07", "remaining_time": "1:24:14", "throughput": 1037.6, "total_tokens": 1689208} {"current_steps": 18755, "total_steps": 76960, "loss": 0.2896, "lr": 4.6920895342308626e-05, "epoch": 4.873960498960499, "percentage": 24.37, "elapsed_time": "0:27:08", "remaining_time": "1:24:13", "throughput": 1037.6, "total_tokens": 1689640} {"current_steps": 18760, "total_steps": 76960, "loss": 0.1763, "lr": 4.69181688926877e-05, "epoch": 4.875259875259875, "percentage": 24.38, "elapsed_time": "0:27:08", "remaining_time": "1:24:13", "throughput": 1037.61, "total_tokens": 1690088} {"current_steps": 18765, "total_steps": 76960, "loss": 0.259, "lr": 4.691544131579434e-05, "epoch": 4.876559251559252, "percentage": 24.38, "elapsed_time": "0:27:09", "remaining_time": "1:24:12", "throughput": 1037.61, "total_tokens": 1690520} {"current_steps": 18770, "total_steps": 76960, "loss": 0.3159, "lr": 4.691271261176883e-05, "epoch": 4.877858627858628, "percentage": 24.39, "elapsed_time": "0:27:09", "remaining_time": "1:24:12", "throughput": 1037.63, "total_tokens": 1690984} {"current_steps": 18775, "total_steps": 76960, "loss": 0.23, "lr": 4.690998278075152e-05, "epoch": 4.879158004158004, "percentage": 24.4, "elapsed_time": "0:27:10", "remaining_time": "1:24:11", "throughput": 1037.63, "total_tokens": 1691416} {"current_steps": 18780, "total_steps": 76960, "loss": 0.2847, "lr": 4.69072518228828e-05, "epoch": 4.88045738045738, "percentage": 24.4, "elapsed_time": "0:27:10", "remaining_time": "1:24:11", "throughput": 1037.66, "total_tokens": 1691896} {"current_steps": 18785, "total_steps": 76960, "loss": 0.1797, "lr": 4.690451973830313e-05, "epoch": 4.881756756756757, "percentage": 24.41, "elapsed_time": "0:27:10", "remaining_time": "1:24:10", "throughput": 1037.68, "total_tokens": 1692360} {"current_steps": 18790, "total_steps": 76960, "loss": 0.2279, "lr": 4.690178652715302e-05, "epoch": 4.883056133056133, "percentage": 24.42, "elapsed_time": "0:27:11", "remaining_time": "1:24:10", "throughput": 1037.68, "total_tokens": 1692792} {"current_steps": 18795, "total_steps": 76960, "loss": 0.241, "lr": 4.689905218957305e-05, "epoch": 4.884355509355509, "percentage": 24.42, "elapsed_time": "0:27:11", "remaining_time": "1:24:09", "throughput": 1037.68, "total_tokens": 1693224} {"current_steps": 18800, "total_steps": 76960, "loss": 0.264, "lr": 4.6896316725703844e-05, "epoch": 4.885654885654886, "percentage": 24.43, "elapsed_time": "0:27:12", "remaining_time": "1:24:09", "throughput": 1037.66, "total_tokens": 1693640} {"current_steps": 18805, "total_steps": 76960, "loss": 0.2724, "lr": 4.689358013568608e-05, "epoch": 4.886954261954262, "percentage": 24.43, "elapsed_time": "0:27:12", "remaining_time": "1:24:08", "throughput": 1037.7, "total_tokens": 1694136} {"current_steps": 18810, "total_steps": 76960, "loss": 0.2921, "lr": 4.689084241966052e-05, "epoch": 4.888253638253638, "percentage": 24.44, "elapsed_time": "0:27:13", "remaining_time": "1:24:08", "throughput": 1037.7, "total_tokens": 1694568} {"current_steps": 18815, "total_steps": 76960, "loss": 0.3012, "lr": 4.688810357776795e-05, "epoch": 4.889553014553014, "percentage": 24.45, "elapsed_time": "0:27:13", "remaining_time": "1:24:07", "throughput": 1037.72, "total_tokens": 1695032} {"current_steps": 18820, "total_steps": 76960, "loss": 0.2655, "lr": 4.688536361014925e-05, "epoch": 4.890852390852391, "percentage": 24.45, "elapsed_time": "0:27:13", "remaining_time": "1:24:07", "throughput": 1037.74, "total_tokens": 1695496} {"current_steps": 18825, "total_steps": 76960, "loss": 0.2676, "lr": 4.688262251694533e-05, "epoch": 4.892151767151767, "percentage": 24.46, "elapsed_time": "0:27:14", "remaining_time": "1:24:06", "throughput": 1037.76, "total_tokens": 1695960} {"current_steps": 18830, "total_steps": 76960, "loss": 0.2716, "lr": 4.6879880298297164e-05, "epoch": 4.893451143451143, "percentage": 24.47, "elapsed_time": "0:27:14", "remaining_time": "1:24:06", "throughput": 1037.76, "total_tokens": 1696408} {"current_steps": 18835, "total_steps": 76960, "loss": 0.2303, "lr": 4.6877136954345785e-05, "epoch": 4.89475051975052, "percentage": 24.47, "elapsed_time": "0:27:15", "remaining_time": "1:24:05", "throughput": 1037.77, "total_tokens": 1696856} {"current_steps": 18840, "total_steps": 76960, "loss": 0.2019, "lr": 4.68743924852323e-05, "epoch": 4.896049896049896, "percentage": 24.48, "elapsed_time": "0:27:15", "remaining_time": "1:24:05", "throughput": 1037.76, "total_tokens": 1697272} {"current_steps": 18845, "total_steps": 76960, "loss": 0.3934, "lr": 4.6871646891097844e-05, "epoch": 4.897349272349272, "percentage": 24.49, "elapsed_time": "0:27:15", "remaining_time": "1:24:04", "throughput": 1037.79, "total_tokens": 1697752} {"current_steps": 18850, "total_steps": 76960, "loss": 0.2656, "lr": 4.686890017208363e-05, "epoch": 4.898648648648649, "percentage": 24.49, "elapsed_time": "0:27:16", "remaining_time": "1:24:04", "throughput": 1037.79, "total_tokens": 1698184} {"current_steps": 18855, "total_steps": 76960, "loss": 0.1943, "lr": 4.6866152328330933e-05, "epoch": 4.899948024948025, "percentage": 24.5, "elapsed_time": "0:27:16", "remaining_time": "1:24:03", "throughput": 1037.79, "total_tokens": 1698616} {"current_steps": 18860, "total_steps": 76960, "loss": 0.2257, "lr": 4.6863403359981065e-05, "epoch": 4.901247401247401, "percentage": 24.51, "elapsed_time": "0:27:17", "remaining_time": "1:24:03", "throughput": 1037.79, "total_tokens": 1699064} {"current_steps": 18865, "total_steps": 76960, "loss": 0.2873, "lr": 4.6860653267175416e-05, "epoch": 4.902546777546777, "percentage": 24.51, "elapsed_time": "0:27:17", "remaining_time": "1:24:03", "throughput": 1037.81, "total_tokens": 1699528} {"current_steps": 18870, "total_steps": 76960, "loss": 0.1754, "lr": 4.685790205005542e-05, "epoch": 4.903846153846154, "percentage": 24.52, "elapsed_time": "0:27:18", "remaining_time": "1:24:02", "throughput": 1037.82, "total_tokens": 1699976} {"current_steps": 18875, "total_steps": 76960, "loss": 0.2445, "lr": 4.685514970876259e-05, "epoch": 4.90514553014553, "percentage": 24.53, "elapsed_time": "0:27:18", "remaining_time": "1:24:02", "throughput": 1037.82, "total_tokens": 1700408} {"current_steps": 18880, "total_steps": 76960, "loss": 0.1946, "lr": 4.685239624343846e-05, "epoch": 4.906444906444906, "percentage": 24.53, "elapsed_time": "0:27:18", "remaining_time": "1:24:01", "throughput": 1037.82, "total_tokens": 1700840} {"current_steps": 18885, "total_steps": 76960, "loss": 0.3496, "lr": 4.684964165422466e-05, "epoch": 4.907744282744282, "percentage": 24.54, "elapsed_time": "0:27:19", "remaining_time": "1:24:01", "throughput": 1037.82, "total_tokens": 1701288} {"current_steps": 18890, "total_steps": 76960, "loss": 0.3149, "lr": 4.684688594126285e-05, "epoch": 4.909043659043659, "percentage": 24.55, "elapsed_time": "0:27:19", "remaining_time": "1:24:00", "throughput": 1037.81, "total_tokens": 1701704} {"current_steps": 18895, "total_steps": 76960, "loss": 0.1913, "lr": 4.684412910469476e-05, "epoch": 4.910343035343035, "percentage": 24.55, "elapsed_time": "0:27:20", "remaining_time": "1:24:00", "throughput": 1037.83, "total_tokens": 1702168} {"current_steps": 18900, "total_steps": 76960, "loss": 0.2496, "lr": 4.6841371144662185e-05, "epoch": 4.911642411642411, "percentage": 24.56, "elapsed_time": "0:27:20", "remaining_time": "1:23:59", "throughput": 1037.84, "total_tokens": 1702616} {"current_steps": 18905, "total_steps": 76960, "loss": 0.2849, "lr": 4.6838612061306966e-05, "epoch": 4.912941787941788, "percentage": 24.56, "elapsed_time": "0:27:20", "remaining_time": "1:23:59", "throughput": 1037.86, "total_tokens": 1703080} {"current_steps": 18910, "total_steps": 76960, "loss": 0.2178, "lr": 4.6835851854770996e-05, "epoch": 4.914241164241164, "percentage": 24.57, "elapsed_time": "0:27:21", "remaining_time": "1:23:58", "throughput": 1037.87, "total_tokens": 1703544} {"current_steps": 18915, "total_steps": 76960, "loss": 0.1753, "lr": 4.683309052519625e-05, "epoch": 4.91554054054054, "percentage": 24.58, "elapsed_time": "0:27:21", "remaining_time": "1:23:58", "throughput": 1037.87, "total_tokens": 1703976} {"current_steps": 18920, "total_steps": 76960, "loss": 0.3359, "lr": 4.683032807272474e-05, "epoch": 4.916839916839917, "percentage": 24.58, "elapsed_time": "0:27:22", "remaining_time": "1:23:57", "throughput": 1037.9, "total_tokens": 1704456} {"current_steps": 18925, "total_steps": 76960, "loss": 0.2691, "lr": 4.6827564497498534e-05, "epoch": 4.918139293139293, "percentage": 24.59, "elapsed_time": "0:27:22", "remaining_time": "1:23:57", "throughput": 1037.9, "total_tokens": 1704888} {"current_steps": 18930, "total_steps": 76960, "loss": 0.2891, "lr": 4.6824799799659773e-05, "epoch": 4.919438669438669, "percentage": 24.6, "elapsed_time": "0:27:23", "remaining_time": "1:23:56", "throughput": 1037.9, "total_tokens": 1705320} {"current_steps": 18935, "total_steps": 76960, "loss": 0.2382, "lr": 4.682203397935066e-05, "epoch": 4.920738045738045, "percentage": 24.6, "elapsed_time": "0:27:23", "remaining_time": "1:23:56", "throughput": 1037.92, "total_tokens": 1705784} {"current_steps": 18940, "total_steps": 76960, "loss": 0.3458, "lr": 4.681926703671341e-05, "epoch": 4.922037422037422, "percentage": 24.61, "elapsed_time": "0:27:23", "remaining_time": "1:23:55", "throughput": 1037.92, "total_tokens": 1706216} {"current_steps": 18945, "total_steps": 76960, "loss": 0.1824, "lr": 4.681649897189036e-05, "epoch": 4.923336798336798, "percentage": 24.62, "elapsed_time": "0:27:24", "remaining_time": "1:23:55", "throughput": 1037.91, "total_tokens": 1706648} {"current_steps": 18950, "total_steps": 76960, "loss": 0.2717, "lr": 4.681372978502386e-05, "epoch": 4.924636174636174, "percentage": 24.62, "elapsed_time": "0:27:24", "remaining_time": "1:23:54", "throughput": 1037.93, "total_tokens": 1707112} {"current_steps": 18955, "total_steps": 76960, "loss": 0.1892, "lr": 4.681095947625635e-05, "epoch": 4.9259355509355505, "percentage": 24.63, "elapsed_time": "0:27:25", "remaining_time": "1:23:54", "throughput": 1037.94, "total_tokens": 1707560} {"current_steps": 18960, "total_steps": 76960, "loss": 0.3551, "lr": 4.680818804573028e-05, "epoch": 4.927234927234927, "percentage": 24.64, "elapsed_time": "0:27:25", "remaining_time": "1:23:53", "throughput": 1037.95, "total_tokens": 1708008} {"current_steps": 18965, "total_steps": 76960, "loss": 0.2116, "lr": 4.6805415493588215e-05, "epoch": 4.928534303534303, "percentage": 24.64, "elapsed_time": "0:27:25", "remaining_time": "1:23:53", "throughput": 1037.96, "total_tokens": 1708456} {"current_steps": 18970, "total_steps": 76960, "loss": 0.2546, "lr": 4.680264181997273e-05, "epoch": 4.9298336798336795, "percentage": 24.65, "elapsed_time": "0:27:26", "remaining_time": "1:23:52", "throughput": 1037.97, "total_tokens": 1708904} {"current_steps": 18975, "total_steps": 76960, "loss": 0.2447, "lr": 4.6799867025026485e-05, "epoch": 4.931133056133056, "percentage": 24.66, "elapsed_time": "0:27:26", "remaining_time": "1:23:52", "throughput": 1037.98, "total_tokens": 1709368} {"current_steps": 18980, "total_steps": 76960, "loss": 0.2224, "lr": 4.679709110889219e-05, "epoch": 4.9324324324324325, "percentage": 24.66, "elapsed_time": "0:27:27", "remaining_time": "1:23:51", "throughput": 1037.99, "total_tokens": 1709816} {"current_steps": 18985, "total_steps": 76960, "loss": 0.2429, "lr": 4.679431407171262e-05, "epoch": 4.9337318087318085, "percentage": 24.67, "elapsed_time": "0:27:27", "remaining_time": "1:23:51", "throughput": 1038.01, "total_tokens": 1710280} {"current_steps": 18990, "total_steps": 76960, "loss": 0.2627, "lr": 4.67915359136306e-05, "epoch": 4.935031185031185, "percentage": 24.68, "elapsed_time": "0:27:28", "remaining_time": "1:23:50", "throughput": 1038.02, "total_tokens": 1710728} {"current_steps": 18995, "total_steps": 76960, "loss": 0.241, "lr": 4.6788756634789e-05, "epoch": 4.9363305613305615, "percentage": 24.68, "elapsed_time": "0:27:28", "remaining_time": "1:23:50", "throughput": 1038.03, "total_tokens": 1711176} {"current_steps": 19000, "total_steps": 76960, "loss": 0.1847, "lr": 4.678597623533077e-05, "epoch": 4.9376299376299375, "percentage": 24.69, "elapsed_time": "0:27:28", "remaining_time": "1:23:50", "throughput": 1038.04, "total_tokens": 1711624} {"current_steps": 19005, "total_steps": 76960, "loss": 0.2503, "lr": 4.678319471539891e-05, "epoch": 4.938929313929314, "percentage": 24.69, "elapsed_time": "0:27:29", "remaining_time": "1:23:49", "throughput": 1038.03, "total_tokens": 1712056} {"current_steps": 19010, "total_steps": 76960, "loss": 0.2741, "lr": 4.678041207513647e-05, "epoch": 4.9402286902286905, "percentage": 24.7, "elapsed_time": "0:27:29", "remaining_time": "1:23:49", "throughput": 1038.06, "total_tokens": 1712536} {"current_steps": 19015, "total_steps": 76960, "loss": 0.3289, "lr": 4.677762831468657e-05, "epoch": 4.9415280665280665, "percentage": 24.71, "elapsed_time": "0:27:30", "remaining_time": "1:23:48", "throughput": 1038.08, "total_tokens": 1713000} {"current_steps": 19020, "total_steps": 76960, "loss": 0.2625, "lr": 4.6774843434192384e-05, "epoch": 4.942827442827443, "percentage": 24.71, "elapsed_time": "0:27:30", "remaining_time": "1:23:48", "throughput": 1038.08, "total_tokens": 1713432} {"current_steps": 19025, "total_steps": 76960, "loss": 0.2386, "lr": 4.677205743379713e-05, "epoch": 4.9441268191268195, "percentage": 24.72, "elapsed_time": "0:27:31", "remaining_time": "1:23:47", "throughput": 1038.06, "total_tokens": 1713848} {"current_steps": 19030, "total_steps": 76960, "loss": 0.2591, "lr": 4.676927031364411e-05, "epoch": 4.9454261954261955, "percentage": 24.73, "elapsed_time": "0:27:31", "remaining_time": "1:23:47", "throughput": 1038.08, "total_tokens": 1714312} {"current_steps": 19035, "total_steps": 76960, "loss": 0.2842, "lr": 4.676648207387665e-05, "epoch": 4.946725571725572, "percentage": 24.73, "elapsed_time": "0:27:31", "remaining_time": "1:23:46", "throughput": 1038.07, "total_tokens": 1714728} {"current_steps": 19040, "total_steps": 76960, "loss": 0.2792, "lr": 4.6763692714638166e-05, "epoch": 4.948024948024948, "percentage": 24.74, "elapsed_time": "0:27:32", "remaining_time": "1:23:46", "throughput": 1038.1, "total_tokens": 1715208} {"current_steps": 19045, "total_steps": 76960, "loss": 0.2542, "lr": 4.6760902236072115e-05, "epoch": 4.949324324324325, "percentage": 24.75, "elapsed_time": "0:27:32", "remaining_time": "1:23:45", "throughput": 1038.11, "total_tokens": 1715656} {"current_steps": 19050, "total_steps": 76960, "loss": 0.2757, "lr": 4.6758110638322006e-05, "epoch": 4.950623700623701, "percentage": 24.75, "elapsed_time": "0:27:33", "remaining_time": "1:23:45", "throughput": 1038.13, "total_tokens": 1716136} {"current_steps": 19055, "total_steps": 76960, "loss": 0.2109, "lr": 4.675531792153143e-05, "epoch": 4.951923076923077, "percentage": 24.76, "elapsed_time": "0:27:33", "remaining_time": "1:23:44", "throughput": 1038.12, "total_tokens": 1716552} {"current_steps": 19060, "total_steps": 76960, "loss": 0.189, "lr": 4.675252408584399e-05, "epoch": 4.953222453222454, "percentage": 24.77, "elapsed_time": "0:27:33", "remaining_time": "1:23:44", "throughput": 1038.12, "total_tokens": 1716984} {"current_steps": 19065, "total_steps": 76960, "loss": 0.2685, "lr": 4.674972913140341e-05, "epoch": 4.95452182952183, "percentage": 24.77, "elapsed_time": "0:27:34", "remaining_time": "1:23:43", "throughput": 1038.11, "total_tokens": 1717400} {"current_steps": 19070, "total_steps": 76960, "loss": 0.2756, "lr": 4.6746933058353416e-05, "epoch": 4.955821205821206, "percentage": 24.78, "elapsed_time": "0:27:34", "remaining_time": "1:23:43", "throughput": 1038.12, "total_tokens": 1717848} {"current_steps": 19075, "total_steps": 76960, "loss": 0.3338, "lr": 4.674413586683781e-05, "epoch": 4.957120582120583, "percentage": 24.79, "elapsed_time": "0:27:35", "remaining_time": "1:23:42", "throughput": 1038.13, "total_tokens": 1718296} {"current_steps": 19080, "total_steps": 76960, "loss": 0.2488, "lr": 4.674133755700048e-05, "epoch": 4.958419958419959, "percentage": 24.79, "elapsed_time": "0:27:35", "remaining_time": "1:23:42", "throughput": 1038.13, "total_tokens": 1718744} {"current_steps": 19085, "total_steps": 76960, "loss": 0.2517, "lr": 4.673853812898531e-05, "epoch": 4.959719334719335, "percentage": 24.8, "elapsed_time": "0:27:36", "remaining_time": "1:23:41", "throughput": 1038.16, "total_tokens": 1719224} {"current_steps": 19090, "total_steps": 76960, "loss": 0.2023, "lr": 4.673573758293631e-05, "epoch": 4.961018711018711, "percentage": 24.81, "elapsed_time": "0:27:36", "remaining_time": "1:23:41", "throughput": 1038.17, "total_tokens": 1719672} {"current_steps": 19095, "total_steps": 76960, "loss": 0.2958, "lr": 4.673293591899749e-05, "epoch": 4.962318087318088, "percentage": 24.81, "elapsed_time": "0:27:36", "remaining_time": "1:23:40", "throughput": 1038.18, "total_tokens": 1720120} {"current_steps": 19100, "total_steps": 76960, "loss": 0.2197, "lr": 4.673013313731296e-05, "epoch": 4.963617463617464, "percentage": 24.82, "elapsed_time": "0:27:37", "remaining_time": "1:23:40", "throughput": 1038.17, "total_tokens": 1720552} {"current_steps": 19105, "total_steps": 76960, "loss": 0.246, "lr": 4.672732923802685e-05, "epoch": 4.96491683991684, "percentage": 24.82, "elapsed_time": "0:27:37", "remaining_time": "1:23:39", "throughput": 1038.16, "total_tokens": 1720968} {"current_steps": 19110, "total_steps": 76960, "loss": 0.3214, "lr": 4.672452422128338e-05, "epoch": 4.966216216216216, "percentage": 24.83, "elapsed_time": "0:27:38", "remaining_time": "1:23:39", "throughput": 1038.16, "total_tokens": 1721400} {"current_steps": 19115, "total_steps": 76960, "loss": 0.3441, "lr": 4.672171808722683e-05, "epoch": 4.967515592515593, "percentage": 24.84, "elapsed_time": "0:27:38", "remaining_time": "1:23:39", "throughput": 1038.17, "total_tokens": 1721848} {"current_steps": 19120, "total_steps": 76960, "loss": 0.2823, "lr": 4.671891083600149e-05, "epoch": 4.968814968814969, "percentage": 24.84, "elapsed_time": "0:27:38", "remaining_time": "1:23:38", "throughput": 1038.17, "total_tokens": 1722296} {"current_steps": 19125, "total_steps": 76960, "loss": 0.2746, "lr": 4.671610246775176e-05, "epoch": 4.970114345114345, "percentage": 24.85, "elapsed_time": "0:27:39", "remaining_time": "1:23:38", "throughput": 1038.21, "total_tokens": 1722792} {"current_steps": 19130, "total_steps": 76960, "loss": 0.3113, "lr": 4.671329298262208e-05, "epoch": 4.971413721413722, "percentage": 24.86, "elapsed_time": "0:27:39", "remaining_time": "1:23:37", "throughput": 1038.23, "total_tokens": 1723256} {"current_steps": 19135, "total_steps": 76960, "loss": 0.2775, "lr": 4.6710482380756926e-05, "epoch": 4.972713097713098, "percentage": 24.86, "elapsed_time": "0:27:40", "remaining_time": "1:23:37", "throughput": 1038.23, "total_tokens": 1723688} {"current_steps": 19140, "total_steps": 76960, "loss": 0.2526, "lr": 4.6707670662300873e-05, "epoch": 4.974012474012474, "percentage": 24.87, "elapsed_time": "0:27:40", "remaining_time": "1:23:36", "throughput": 1038.24, "total_tokens": 1724136} {"current_steps": 19145, "total_steps": 76960, "loss": 0.2673, "lr": 4.670485782739851e-05, "epoch": 4.975311850311851, "percentage": 24.88, "elapsed_time": "0:27:41", "remaining_time": "1:23:36", "throughput": 1038.24, "total_tokens": 1724568} {"current_steps": 19150, "total_steps": 76960, "loss": 0.2692, "lr": 4.6702043876194515e-05, "epoch": 4.976611226611227, "percentage": 24.88, "elapsed_time": "0:27:41", "remaining_time": "1:23:35", "throughput": 1038.26, "total_tokens": 1725032} {"current_steps": 19155, "total_steps": 76960, "loss": 0.1908, "lr": 4.66992288088336e-05, "epoch": 4.977910602910603, "percentage": 24.89, "elapsed_time": "0:27:41", "remaining_time": "1:23:35", "throughput": 1038.25, "total_tokens": 1725464} {"current_steps": 19160, "total_steps": 76960, "loss": 0.1814, "lr": 4.6696412625460575e-05, "epoch": 4.979209979209979, "percentage": 24.9, "elapsed_time": "0:27:42", "remaining_time": "1:23:34", "throughput": 1038.28, "total_tokens": 1725944} {"current_steps": 19165, "total_steps": 76960, "loss": 0.2743, "lr": 4.6693595326220255e-05, "epoch": 4.980509355509356, "percentage": 24.9, "elapsed_time": "0:27:42", "remaining_time": "1:23:34", "throughput": 1038.29, "total_tokens": 1726392} {"current_steps": 19170, "total_steps": 76960, "loss": 0.3823, "lr": 4.669077691125753e-05, "epoch": 4.981808731808732, "percentage": 24.91, "elapsed_time": "0:27:43", "remaining_time": "1:23:33", "throughput": 1038.29, "total_tokens": 1726824} {"current_steps": 19175, "total_steps": 76960, "loss": 0.3081, "lr": 4.6687957380717376e-05, "epoch": 4.983108108108108, "percentage": 24.92, "elapsed_time": "0:27:43", "remaining_time": "1:23:33", "throughput": 1038.3, "total_tokens": 1727272} {"current_steps": 19180, "total_steps": 76960, "loss": 0.2852, "lr": 4.668513673474479e-05, "epoch": 4.984407484407484, "percentage": 24.92, "elapsed_time": "0:27:43", "remaining_time": "1:23:32", "throughput": 1038.32, "total_tokens": 1727752} {"current_steps": 19185, "total_steps": 76960, "loss": 0.2612, "lr": 4.668231497348484e-05, "epoch": 4.985706860706861, "percentage": 24.93, "elapsed_time": "0:27:44", "remaining_time": "1:23:32", "throughput": 1038.33, "total_tokens": 1728200} {"current_steps": 19190, "total_steps": 76960, "loss": 0.2427, "lr": 4.667949209708266e-05, "epoch": 4.987006237006237, "percentage": 24.94, "elapsed_time": "0:27:44", "remaining_time": "1:23:31", "throughput": 1038.36, "total_tokens": 1728680} {"current_steps": 19195, "total_steps": 76960, "loss": 0.2339, "lr": 4.667666810568343e-05, "epoch": 4.988305613305613, "percentage": 24.94, "elapsed_time": "0:27:45", "remaining_time": "1:23:31", "throughput": 1038.38, "total_tokens": 1729144} {"current_steps": 19200, "total_steps": 76960, "loss": 0.2437, "lr": 4.667384299943239e-05, "epoch": 4.98960498960499, "percentage": 24.95, "elapsed_time": "0:27:45", "remaining_time": "1:23:30", "throughput": 1038.38, "total_tokens": 1729576} {"current_steps": 19205, "total_steps": 76960, "loss": 0.2559, "lr": 4.667101677847484e-05, "epoch": 4.990904365904366, "percentage": 24.95, "elapsed_time": "0:27:46", "remaining_time": "1:23:30", "throughput": 1038.37, "total_tokens": 1730008} {"current_steps": 19210, "total_steps": 76960, "loss": 0.2052, "lr": 4.666818944295612e-05, "epoch": 4.992203742203742, "percentage": 24.96, "elapsed_time": "0:27:46", "remaining_time": "1:23:29", "throughput": 1038.38, "total_tokens": 1730456} {"current_steps": 19215, "total_steps": 76960, "loss": 0.3322, "lr": 4.666536099302167e-05, "epoch": 4.993503118503119, "percentage": 24.97, "elapsed_time": "0:27:46", "remaining_time": "1:23:29", "throughput": 1038.37, "total_tokens": 1730872} {"current_steps": 19220, "total_steps": 76960, "loss": 0.3408, "lr": 4.666253142881694e-05, "epoch": 4.994802494802495, "percentage": 24.97, "elapsed_time": "0:27:47", "remaining_time": "1:23:28", "throughput": 1038.39, "total_tokens": 1731336} {"current_steps": 19225, "total_steps": 76960, "loss": 0.2837, "lr": 4.6659700750487464e-05, "epoch": 4.996101871101871, "percentage": 24.98, "elapsed_time": "0:27:47", "remaining_time": "1:23:28", "throughput": 1038.4, "total_tokens": 1731784} {"current_steps": 19230, "total_steps": 76960, "loss": 0.2535, "lr": 4.6656868958178825e-05, "epoch": 4.997401247401247, "percentage": 24.99, "elapsed_time": "0:27:48", "remaining_time": "1:23:27", "throughput": 1038.39, "total_tokens": 1732216} {"current_steps": 19235, "total_steps": 76960, "loss": 0.2682, "lr": 4.6654036052036665e-05, "epoch": 4.998700623700624, "percentage": 24.99, "elapsed_time": "0:27:48", "remaining_time": "1:23:27", "throughput": 1038.43, "total_tokens": 1732696} {"current_steps": 19240, "total_steps": 76960, "loss": 0.2187, "lr": 4.6651202032206676e-05, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:27:49", "remaining_time": "1:23:27", "throughput": 1038.35, "total_tokens": 1733072} {"current_steps": 19240, "total_steps": 76960, "eval_loss": 0.2433796525001526, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:28:02", "remaining_time": "1:24:06", "throughput": 1030.17, "total_tokens": 1733072} {"current_steps": 19245, "total_steps": 76960, "loss": 0.321, "lr": 4.664836689883463e-05, "epoch": 5.001299376299376, "percentage": 25.01, "elapsed_time": "0:28:04", "remaining_time": "1:24:11", "throughput": 1029.22, "total_tokens": 1733520} {"current_steps": 19250, "total_steps": 76960, "loss": 0.1913, "lr": 4.664553065206633e-05, "epoch": 5.002598752598753, "percentage": 25.01, "elapsed_time": "0:28:04", "remaining_time": "1:24:10", "throughput": 1029.22, "total_tokens": 1733984} {"current_steps": 19255, "total_steps": 76960, "loss": 0.2558, "lr": 4.6642693292047644e-05, "epoch": 5.003898128898129, "percentage": 25.02, "elapsed_time": "0:28:05", "remaining_time": "1:24:10", "throughput": 1029.2, "total_tokens": 1734400} {"current_steps": 19260, "total_steps": 76960, "loss": 0.1703, "lr": 4.663985481892451e-05, "epoch": 5.005197505197505, "percentage": 25.03, "elapsed_time": "0:28:05", "remaining_time": "1:24:09", "throughput": 1029.21, "total_tokens": 1734848} {"current_steps": 19265, "total_steps": 76960, "loss": 0.146, "lr": 4.663701523284291e-05, "epoch": 5.006496881496881, "percentage": 25.03, "elapsed_time": "0:28:06", "remaining_time": "1:24:09", "throughput": 1029.22, "total_tokens": 1735296} {"current_steps": 19270, "total_steps": 76960, "loss": 0.4655, "lr": 4.663417453394888e-05, "epoch": 5.007796257796258, "percentage": 25.04, "elapsed_time": "0:28:06", "remaining_time": "1:24:08", "throughput": 1029.21, "total_tokens": 1735712} {"current_steps": 19275, "total_steps": 76960, "loss": 0.3139, "lr": 4.663133272238853e-05, "epoch": 5.009095634095634, "percentage": 25.05, "elapsed_time": "0:28:06", "remaining_time": "1:24:08", "throughput": 1029.22, "total_tokens": 1736176} {"current_steps": 19280, "total_steps": 76960, "loss": 0.1971, "lr": 4.6628489798308006e-05, "epoch": 5.01039501039501, "percentage": 25.05, "elapsed_time": "0:28:07", "remaining_time": "1:24:07", "throughput": 1029.23, "total_tokens": 1736624} {"current_steps": 19285, "total_steps": 76960, "loss": 0.2002, "lr": 4.662564576185353e-05, "epoch": 5.011694386694387, "percentage": 25.06, "elapsed_time": "0:28:07", "remaining_time": "1:24:07", "throughput": 1029.25, "total_tokens": 1737088} {"current_steps": 19290, "total_steps": 76960, "loss": 0.2572, "lr": 4.6622800613171376e-05, "epoch": 5.012993762993763, "percentage": 25.06, "elapsed_time": "0:28:08", "remaining_time": "1:24:06", "throughput": 1029.27, "total_tokens": 1737552} {"current_steps": 19295, "total_steps": 76960, "loss": 0.2551, "lr": 4.6619954352407866e-05, "epoch": 5.014293139293139, "percentage": 25.07, "elapsed_time": "0:28:08", "remaining_time": "1:24:06", "throughput": 1029.28, "total_tokens": 1738000} {"current_steps": 19300, "total_steps": 76960, "loss": 0.2214, "lr": 4.6617106979709384e-05, "epoch": 5.015592515592515, "percentage": 25.08, "elapsed_time": "0:28:08", "remaining_time": "1:24:05", "throughput": 1029.3, "total_tokens": 1738464} {"current_steps": 19305, "total_steps": 76960, "loss": 0.1573, "lr": 4.6614258495222384e-05, "epoch": 5.016891891891892, "percentage": 25.08, "elapsed_time": "0:28:09", "remaining_time": "1:24:05", "throughput": 1029.31, "total_tokens": 1738912} {"current_steps": 19310, "total_steps": 76960, "loss": 0.224, "lr": 4.6611408899093355e-05, "epoch": 5.018191268191268, "percentage": 25.09, "elapsed_time": "0:28:09", "remaining_time": "1:24:04", "throughput": 1029.29, "total_tokens": 1739312} {"current_steps": 19315, "total_steps": 76960, "loss": 0.3791, "lr": 4.660855819146887e-05, "epoch": 5.019490644490644, "percentage": 25.1, "elapsed_time": "0:28:10", "remaining_time": "1:24:04", "throughput": 1029.29, "total_tokens": 1739744} {"current_steps": 19320, "total_steps": 76960, "loss": 0.316, "lr": 4.6605706372495515e-05, "epoch": 5.020790020790021, "percentage": 25.1, "elapsed_time": "0:28:10", "remaining_time": "1:24:03", "throughput": 1029.3, "total_tokens": 1740192} {"current_steps": 19325, "total_steps": 76960, "loss": 0.1885, "lr": 4.660285344231999e-05, "epoch": 5.022089397089397, "percentage": 25.11, "elapsed_time": "0:28:11", "remaining_time": "1:24:03", "throughput": 1029.32, "total_tokens": 1740656} {"current_steps": 19330, "total_steps": 76960, "loss": 0.2658, "lr": 4.659999940108901e-05, "epoch": 5.023388773388773, "percentage": 25.12, "elapsed_time": "0:28:11", "remaining_time": "1:24:02", "throughput": 1029.35, "total_tokens": 1741136} {"current_steps": 19335, "total_steps": 76960, "loss": 0.2827, "lr": 4.659714424894936e-05, "epoch": 5.024688149688149, "percentage": 25.12, "elapsed_time": "0:28:11", "remaining_time": "1:24:02", "throughput": 1029.34, "total_tokens": 1741552} {"current_steps": 19340, "total_steps": 76960, "loss": 0.2752, "lr": 4.65942879860479e-05, "epoch": 5.025987525987526, "percentage": 25.13, "elapsed_time": "0:28:12", "remaining_time": "1:24:02", "throughput": 1029.35, "total_tokens": 1742000} {"current_steps": 19345, "total_steps": 76960, "loss": 0.2579, "lr": 4.6591430612531515e-05, "epoch": 5.027286902286902, "percentage": 25.14, "elapsed_time": "0:28:12", "remaining_time": "1:24:01", "throughput": 1029.38, "total_tokens": 1742480} {"current_steps": 19350, "total_steps": 76960, "loss": 0.2546, "lr": 4.658857212854717e-05, "epoch": 5.028586278586278, "percentage": 25.14, "elapsed_time": "0:28:13", "remaining_time": "1:24:01", "throughput": 1029.38, "total_tokens": 1742912} {"current_steps": 19355, "total_steps": 76960, "loss": 0.2591, "lr": 4.6585712534241864e-05, "epoch": 5.029885654885655, "percentage": 25.15, "elapsed_time": "0:28:13", "remaining_time": "1:24:00", "throughput": 1029.39, "total_tokens": 1743360} {"current_steps": 19360, "total_steps": 76960, "loss": 0.2614, "lr": 4.658285182976269e-05, "epoch": 5.031185031185031, "percentage": 25.16, "elapsed_time": "0:28:14", "remaining_time": "1:24:00", "throughput": 1029.4, "total_tokens": 1743824} {"current_steps": 19365, "total_steps": 76960, "loss": 0.3153, "lr": 4.657999001525676e-05, "epoch": 5.032484407484407, "percentage": 25.16, "elapsed_time": "0:28:14", "remaining_time": "1:23:59", "throughput": 1029.4, "total_tokens": 1744256} {"current_steps": 19370, "total_steps": 76960, "loss": 0.218, "lr": 4.6577127090871265e-05, "epoch": 5.033783783783784, "percentage": 25.17, "elapsed_time": "0:28:14", "remaining_time": "1:23:59", "throughput": 1029.41, "total_tokens": 1744704} {"current_steps": 19375, "total_steps": 76960, "loss": 0.2503, "lr": 4.6574263056753455e-05, "epoch": 5.03508316008316, "percentage": 25.18, "elapsed_time": "0:28:15", "remaining_time": "1:23:58", "throughput": 1029.44, "total_tokens": 1745184} {"current_steps": 19380, "total_steps": 76960, "loss": 0.2221, "lr": 4.6571397913050625e-05, "epoch": 5.036382536382536, "percentage": 25.18, "elapsed_time": "0:28:15", "remaining_time": "1:23:58", "throughput": 1029.47, "total_tokens": 1745664} {"current_steps": 19385, "total_steps": 76960, "loss": 0.3214, "lr": 4.656853165991013e-05, "epoch": 5.037681912681912, "percentage": 25.19, "elapsed_time": "0:28:16", "remaining_time": "1:23:57", "throughput": 1029.49, "total_tokens": 1746128} {"current_steps": 19390, "total_steps": 76960, "loss": 0.2672, "lr": 4.656566429747938e-05, "epoch": 5.038981288981289, "percentage": 25.19, "elapsed_time": "0:28:16", "remaining_time": "1:23:57", "throughput": 1029.5, "total_tokens": 1746576} {"current_steps": 19395, "total_steps": 76960, "loss": 0.2975, "lr": 4.656279582590586e-05, "epoch": 5.040280665280665, "percentage": 25.2, "elapsed_time": "0:28:16", "remaining_time": "1:23:56", "throughput": 1029.51, "total_tokens": 1747040} {"current_steps": 19400, "total_steps": 76960, "loss": 0.2081, "lr": 4.655992624533708e-05, "epoch": 5.041580041580041, "percentage": 25.21, "elapsed_time": "0:28:17", "remaining_time": "1:23:56", "throughput": 1029.54, "total_tokens": 1747520} {"current_steps": 19405, "total_steps": 76960, "loss": 0.2444, "lr": 4.655705555592065e-05, "epoch": 5.042879417879418, "percentage": 25.21, "elapsed_time": "0:28:17", "remaining_time": "1:23:55", "throughput": 1029.6, "total_tokens": 1748048} {"current_steps": 19410, "total_steps": 76960, "loss": 0.1692, "lr": 4.655418375780419e-05, "epoch": 5.044178794178794, "percentage": 25.22, "elapsed_time": "0:28:18", "remaining_time": "1:23:55", "throughput": 1029.6, "total_tokens": 1748480} {"current_steps": 19415, "total_steps": 76960, "loss": 0.369, "lr": 4.655131085113541e-05, "epoch": 5.04547817047817, "percentage": 25.23, "elapsed_time": "0:28:18", "remaining_time": "1:23:54", "throughput": 1029.65, "total_tokens": 1748992} {"current_steps": 19420, "total_steps": 76960, "loss": 0.2837, "lr": 4.6548436836062056e-05, "epoch": 5.046777546777546, "percentage": 25.23, "elapsed_time": "0:28:19", "remaining_time": "1:23:54", "throughput": 1029.69, "total_tokens": 1749488} {"current_steps": 19425, "total_steps": 76960, "loss": 0.2705, "lr": 4.6545561712731954e-05, "epoch": 5.048076923076923, "percentage": 25.24, "elapsed_time": "0:28:19", "remaining_time": "1:23:53", "throughput": 1029.71, "total_tokens": 1749952} {"current_steps": 19430, "total_steps": 76960, "loss": 0.2962, "lr": 4.654268548129297e-05, "epoch": 5.049376299376299, "percentage": 25.25, "elapsed_time": "0:28:19", "remaining_time": "1:23:53", "throughput": 1029.7, "total_tokens": 1750368} {"current_steps": 19435, "total_steps": 76960, "loss": 0.2214, "lr": 4.653980814189303e-05, "epoch": 5.050675675675675, "percentage": 25.25, "elapsed_time": "0:28:20", "remaining_time": "1:23:52", "throughput": 1029.73, "total_tokens": 1750848} {"current_steps": 19440, "total_steps": 76960, "loss": 0.2545, "lr": 4.653692969468012e-05, "epoch": 5.051975051975052, "percentage": 25.26, "elapsed_time": "0:28:20", "remaining_time": "1:23:52", "throughput": 1029.73, "total_tokens": 1751280} {"current_steps": 19445, "total_steps": 76960, "loss": 0.2954, "lr": 4.6534050139802275e-05, "epoch": 5.053274428274428, "percentage": 25.27, "elapsed_time": "0:28:21", "remaining_time": "1:23:51", "throughput": 1029.76, "total_tokens": 1751760} {"current_steps": 19450, "total_steps": 76960, "loss": 0.2275, "lr": 4.65311694774076e-05, "epoch": 5.0545738045738045, "percentage": 25.27, "elapsed_time": "0:28:21", "remaining_time": "1:23:51", "throughput": 1029.78, "total_tokens": 1752224} {"current_steps": 19455, "total_steps": 76960, "loss": 0.2943, "lr": 4.6528287707644254e-05, "epoch": 5.0558731808731805, "percentage": 25.28, "elapsed_time": "0:28:21", "remaining_time": "1:23:50", "throughput": 1029.78, "total_tokens": 1752656} {"current_steps": 19460, "total_steps": 76960, "loss": 0.2619, "lr": 4.6525404830660435e-05, "epoch": 5.057172557172557, "percentage": 25.29, "elapsed_time": "0:28:22", "remaining_time": "1:23:50", "throughput": 1029.79, "total_tokens": 1753104} {"current_steps": 19465, "total_steps": 76960, "loss": 0.2523, "lr": 4.6522520846604425e-05, "epoch": 5.0584719334719335, "percentage": 25.29, "elapsed_time": "0:28:22", "remaining_time": "1:23:49", "throughput": 1029.8, "total_tokens": 1753552} {"current_steps": 19470, "total_steps": 76960, "loss": 0.2619, "lr": 4.651963575562455e-05, "epoch": 5.0597713097713095, "percentage": 25.3, "elapsed_time": "0:28:23", "remaining_time": "1:23:49", "throughput": 1029.82, "total_tokens": 1754016} {"current_steps": 19475, "total_steps": 76960, "loss": 0.2886, "lr": 4.651674955786919e-05, "epoch": 5.061070686070686, "percentage": 25.31, "elapsed_time": "0:28:23", "remaining_time": "1:23:48", "throughput": 1029.86, "total_tokens": 1754512} {"current_steps": 19480, "total_steps": 76960, "loss": 0.1919, "lr": 4.651386225348677e-05, "epoch": 5.0623700623700625, "percentage": 25.31, "elapsed_time": "0:28:24", "remaining_time": "1:23:48", "throughput": 1029.86, "total_tokens": 1754944} {"current_steps": 19485, "total_steps": 76960, "loss": 0.2556, "lr": 4.6510973842625816e-05, "epoch": 5.0636694386694385, "percentage": 25.32, "elapsed_time": "0:28:24", "remaining_time": "1:23:47", "throughput": 1029.88, "total_tokens": 1755408} {"current_steps": 19490, "total_steps": 76960, "loss": 0.2643, "lr": 4.650808432543486e-05, "epoch": 5.064968814968815, "percentage": 25.32, "elapsed_time": "0:28:24", "remaining_time": "1:23:47", "throughput": 1029.87, "total_tokens": 1755840} {"current_steps": 19495, "total_steps": 76960, "loss": 0.2587, "lr": 4.6505193702062524e-05, "epoch": 5.0662681912681915, "percentage": 25.33, "elapsed_time": "0:28:25", "remaining_time": "1:23:46", "throughput": 1029.87, "total_tokens": 1756272} {"current_steps": 19500, "total_steps": 76960, "loss": 0.2411, "lr": 4.650230197265746e-05, "epoch": 5.0675675675675675, "percentage": 25.34, "elapsed_time": "0:28:25", "remaining_time": "1:23:46", "throughput": 1029.89, "total_tokens": 1756736} {"current_steps": 19505, "total_steps": 76960, "loss": 0.1804, "lr": 4.649940913736841e-05, "epoch": 5.068866943866944, "percentage": 25.34, "elapsed_time": "0:28:26", "remaining_time": "1:23:45", "throughput": 1029.9, "total_tokens": 1757184} {"current_steps": 19510, "total_steps": 76960, "loss": 0.3021, "lr": 4.649651519634415e-05, "epoch": 5.0701663201663205, "percentage": 25.35, "elapsed_time": "0:28:26", "remaining_time": "1:23:45", "throughput": 1029.89, "total_tokens": 1757600} {"current_steps": 19515, "total_steps": 76960, "loss": 0.3354, "lr": 4.649362014973352e-05, "epoch": 5.071465696465697, "percentage": 25.36, "elapsed_time": "0:28:27", "remaining_time": "1:23:44", "throughput": 1029.89, "total_tokens": 1758016} {"current_steps": 19520, "total_steps": 76960, "loss": 0.279, "lr": 4.64907239976854e-05, "epoch": 5.072765072765073, "percentage": 25.36, "elapsed_time": "0:28:27", "remaining_time": "1:23:44", "throughput": 1029.93, "total_tokens": 1758528} {"current_steps": 19525, "total_steps": 76960, "loss": 0.2083, "lr": 4.648782674034876e-05, "epoch": 5.074064449064449, "percentage": 25.37, "elapsed_time": "0:28:27", "remaining_time": "1:23:43", "throughput": 1029.94, "total_tokens": 1758976} {"current_steps": 19530, "total_steps": 76960, "loss": 0.2749, "lr": 4.648492837787261e-05, "epoch": 5.075363825363826, "percentage": 25.38, "elapsed_time": "0:28:28", "remaining_time": "1:23:43", "throughput": 1029.95, "total_tokens": 1759424} {"current_steps": 19535, "total_steps": 76960, "loss": 0.2611, "lr": 4.6482028910406e-05, "epoch": 5.076663201663202, "percentage": 25.38, "elapsed_time": "0:28:28", "remaining_time": "1:23:42", "throughput": 1029.95, "total_tokens": 1759856} {"current_steps": 19540, "total_steps": 76960, "loss": 0.2832, "lr": 4.647912833809805e-05, "epoch": 5.077962577962578, "percentage": 25.39, "elapsed_time": "0:28:29", "remaining_time": "1:23:42", "throughput": 1029.98, "total_tokens": 1760336} {"current_steps": 19545, "total_steps": 76960, "loss": 0.2315, "lr": 4.647622666109796e-05, "epoch": 5.079261954261955, "percentage": 25.4, "elapsed_time": "0:28:29", "remaining_time": "1:23:41", "throughput": 1030.02, "total_tokens": 1760832} {"current_steps": 19550, "total_steps": 76960, "loss": 0.2191, "lr": 4.647332387955495e-05, "epoch": 5.080561330561331, "percentage": 25.4, "elapsed_time": "0:28:29", "remaining_time": "1:23:41", "throughput": 1030.03, "total_tokens": 1761280} {"current_steps": 19555, "total_steps": 76960, "loss": 0.2594, "lr": 4.647041999361833e-05, "epoch": 5.081860706860707, "percentage": 25.41, "elapsed_time": "0:28:30", "remaining_time": "1:23:40", "throughput": 1030.05, "total_tokens": 1761744} {"current_steps": 19560, "total_steps": 76960, "loss": 0.3417, "lr": 4.6467515003437425e-05, "epoch": 5.083160083160083, "percentage": 25.42, "elapsed_time": "0:28:30", "remaining_time": "1:23:40", "throughput": 1030.07, "total_tokens": 1762208} {"current_steps": 19565, "total_steps": 76960, "loss": 0.3458, "lr": 4.646460890916165e-05, "epoch": 5.08445945945946, "percentage": 25.42, "elapsed_time": "0:28:31", "remaining_time": "1:23:39", "throughput": 1030.09, "total_tokens": 1762672} {"current_steps": 19570, "total_steps": 76960, "loss": 0.2452, "lr": 4.646170171094049e-05, "epoch": 5.085758835758836, "percentage": 25.43, "elapsed_time": "0:28:31", "remaining_time": "1:23:39", "throughput": 1030.09, "total_tokens": 1763104} {"current_steps": 19575, "total_steps": 76960, "loss": 0.3018, "lr": 4.645879340892344e-05, "epoch": 5.087058212058212, "percentage": 25.44, "elapsed_time": "0:28:32", "remaining_time": "1:23:38", "throughput": 1030.07, "total_tokens": 1763504} {"current_steps": 19580, "total_steps": 76960, "loss": 0.2239, "lr": 4.645588400326008e-05, "epoch": 5.088357588357589, "percentage": 25.44, "elapsed_time": "0:28:32", "remaining_time": "1:23:38", "throughput": 1030.07, "total_tokens": 1763936} {"current_steps": 19585, "total_steps": 76960, "loss": 0.2576, "lr": 4.645297349410005e-05, "epoch": 5.089656964656965, "percentage": 25.45, "elapsed_time": "0:28:32", "remaining_time": "1:23:37", "throughput": 1030.09, "total_tokens": 1764400} {"current_steps": 19590, "total_steps": 76960, "loss": 0.2248, "lr": 4.645006188159304e-05, "epoch": 5.090956340956341, "percentage": 25.45, "elapsed_time": "0:28:33", "remaining_time": "1:23:37", "throughput": 1030.08, "total_tokens": 1764816} {"current_steps": 19595, "total_steps": 76960, "loss": 0.2243, "lr": 4.644714916588879e-05, "epoch": 5.092255717255718, "percentage": 25.46, "elapsed_time": "0:28:33", "remaining_time": "1:23:36", "throughput": 1030.07, "total_tokens": 1765232} {"current_steps": 19600, "total_steps": 76960, "loss": 0.332, "lr": 4.6444235347137115e-05, "epoch": 5.093555093555094, "percentage": 25.47, "elapsed_time": "0:28:34", "remaining_time": "1:23:36", "throughput": 1030.08, "total_tokens": 1765680} {"current_steps": 19605, "total_steps": 76960, "loss": 0.2163, "lr": 4.6441320425487865e-05, "epoch": 5.09485446985447, "percentage": 25.47, "elapsed_time": "0:28:34", "remaining_time": "1:23:35", "throughput": 1030.11, "total_tokens": 1766160} {"current_steps": 19610, "total_steps": 76960, "loss": 0.2502, "lr": 4.643840440109096e-05, "epoch": 5.096153846153846, "percentage": 25.48, "elapsed_time": "0:28:34", "remaining_time": "1:23:35", "throughput": 1030.1, "total_tokens": 1766576} {"current_steps": 19615, "total_steps": 76960, "loss": 0.1817, "lr": 4.643548727409638e-05, "epoch": 5.097453222453223, "percentage": 25.49, "elapsed_time": "0:28:35", "remaining_time": "1:23:34", "throughput": 1030.11, "total_tokens": 1767024} {"current_steps": 19620, "total_steps": 76960, "loss": 0.2614, "lr": 4.643256904465415e-05, "epoch": 5.098752598752599, "percentage": 25.49, "elapsed_time": "0:28:35", "remaining_time": "1:23:34", "throughput": 1030.11, "total_tokens": 1767456} {"current_steps": 19625, "total_steps": 76960, "loss": 0.1607, "lr": 4.642964971291436e-05, "epoch": 5.100051975051975, "percentage": 25.5, "elapsed_time": "0:28:36", "remaining_time": "1:23:33", "throughput": 1030.11, "total_tokens": 1767888} {"current_steps": 19630, "total_steps": 76960, "loss": 0.2533, "lr": 4.642672927902715e-05, "epoch": 5.101351351351352, "percentage": 25.51, "elapsed_time": "0:28:36", "remaining_time": "1:23:33", "throughput": 1030.1, "total_tokens": 1768304} {"current_steps": 19635, "total_steps": 76960, "loss": 0.3172, "lr": 4.642380774314272e-05, "epoch": 5.102650727650728, "percentage": 25.51, "elapsed_time": "0:28:37", "remaining_time": "1:23:32", "throughput": 1030.11, "total_tokens": 1768752} {"current_steps": 19640, "total_steps": 76960, "loss": 0.2467, "lr": 4.642088510541134e-05, "epoch": 5.103950103950104, "percentage": 25.52, "elapsed_time": "0:28:37", "remaining_time": "1:23:32", "throughput": 1030.12, "total_tokens": 1769200} {"current_steps": 19645, "total_steps": 76960, "loss": 0.1525, "lr": 4.64179613659833e-05, "epoch": 5.10524948024948, "percentage": 25.53, "elapsed_time": "0:28:37", "remaining_time": "1:23:31", "throughput": 1030.17, "total_tokens": 1769712} {"current_steps": 19650, "total_steps": 76960, "loss": 0.3581, "lr": 4.641503652500899e-05, "epoch": 5.106548856548857, "percentage": 25.53, "elapsed_time": "0:28:38", "remaining_time": "1:23:31", "throughput": 1030.18, "total_tokens": 1770160} {"current_steps": 19655, "total_steps": 76960, "loss": 0.2114, "lr": 4.641211058263884e-05, "epoch": 5.107848232848233, "percentage": 25.54, "elapsed_time": "0:28:38", "remaining_time": "1:23:30", "throughput": 1030.18, "total_tokens": 1770592} {"current_steps": 19660, "total_steps": 76960, "loss": 0.283, "lr": 4.6409183539023324e-05, "epoch": 5.109147609147609, "percentage": 25.55, "elapsed_time": "0:28:39", "remaining_time": "1:23:30", "throughput": 1030.2, "total_tokens": 1771056} {"current_steps": 19665, "total_steps": 76960, "loss": 0.2644, "lr": 4.640625539431298e-05, "epoch": 5.110446985446986, "percentage": 25.55, "elapsed_time": "0:28:39", "remaining_time": "1:23:30", "throughput": 1030.22, "total_tokens": 1771520} {"current_steps": 19670, "total_steps": 76960, "loss": 0.2457, "lr": 4.6403326148658424e-05, "epoch": 5.111746361746362, "percentage": 25.56, "elapsed_time": "0:28:39", "remaining_time": "1:23:29", "throughput": 1030.22, "total_tokens": 1771952} {"current_steps": 19675, "total_steps": 76960, "loss": 0.2707, "lr": 4.6400395802210285e-05, "epoch": 5.113045738045738, "percentage": 25.57, "elapsed_time": "0:28:40", "remaining_time": "1:23:29", "throughput": 1030.26, "total_tokens": 1772448} {"current_steps": 19680, "total_steps": 76960, "loss": 0.2429, "lr": 4.639746435511928e-05, "epoch": 5.114345114345114, "percentage": 25.57, "elapsed_time": "0:28:40", "remaining_time": "1:23:28", "throughput": 1030.26, "total_tokens": 1772880} {"current_steps": 19685, "total_steps": 76960, "loss": 0.2273, "lr": 4.639453180753619e-05, "epoch": 5.115644490644491, "percentage": 25.58, "elapsed_time": "0:28:41", "remaining_time": "1:23:28", "throughput": 1030.28, "total_tokens": 1773344} {"current_steps": 19690, "total_steps": 76960, "loss": 0.2376, "lr": 4.6391598159611825e-05, "epoch": 5.116943866943867, "percentage": 25.58, "elapsed_time": "0:28:41", "remaining_time": "1:23:27", "throughput": 1030.3, "total_tokens": 1773808} {"current_steps": 19695, "total_steps": 76960, "loss": 0.2889, "lr": 4.638866341149708e-05, "epoch": 5.118243243243243, "percentage": 25.59, "elapsed_time": "0:28:42", "remaining_time": "1:23:27", "throughput": 1030.32, "total_tokens": 1774272} {"current_steps": 19700, "total_steps": 76960, "loss": 0.3242, "lr": 4.6385727563342876e-05, "epoch": 5.11954261954262, "percentage": 25.6, "elapsed_time": "0:28:42", "remaining_time": "1:23:26", "throughput": 1030.33, "total_tokens": 1774720} {"current_steps": 19705, "total_steps": 76960, "loss": 0.2724, "lr": 4.638279061530021e-05, "epoch": 5.120841995841996, "percentage": 25.6, "elapsed_time": "0:28:42", "remaining_time": "1:23:26", "throughput": 1030.36, "total_tokens": 1775200} {"current_steps": 19710, "total_steps": 76960, "loss": 0.2759, "lr": 4.637985256752013e-05, "epoch": 5.122141372141372, "percentage": 25.61, "elapsed_time": "0:28:43", "remaining_time": "1:23:25", "throughput": 1030.37, "total_tokens": 1775648} {"current_steps": 19715, "total_steps": 76960, "loss": 0.2182, "lr": 4.6376913420153755e-05, "epoch": 5.123440748440748, "percentage": 25.62, "elapsed_time": "0:28:43", "remaining_time": "1:23:25", "throughput": 1030.37, "total_tokens": 1776080} {"current_steps": 19720, "total_steps": 76960, "loss": 0.2862, "lr": 4.6373973173352245e-05, "epoch": 5.124740124740125, "percentage": 25.62, "elapsed_time": "0:28:44", "remaining_time": "1:23:24", "throughput": 1030.4, "total_tokens": 1776560} {"current_steps": 19725, "total_steps": 76960, "loss": 0.3235, "lr": 4.637103182726681e-05, "epoch": 5.126039501039501, "percentage": 25.63, "elapsed_time": "0:28:44", "remaining_time": "1:23:24", "throughput": 1030.41, "total_tokens": 1777008} {"current_steps": 19730, "total_steps": 76960, "loss": 0.2388, "lr": 4.6368089382048726e-05, "epoch": 5.127338877338877, "percentage": 25.64, "elapsed_time": "0:28:44", "remaining_time": "1:23:23", "throughput": 1030.42, "total_tokens": 1777456} {"current_steps": 19735, "total_steps": 76960, "loss": 0.256, "lr": 4.636514583784933e-05, "epoch": 5.128638253638254, "percentage": 25.64, "elapsed_time": "0:28:45", "remaining_time": "1:23:23", "throughput": 1030.43, "total_tokens": 1777904} {"current_steps": 19740, "total_steps": 76960, "loss": 0.2457, "lr": 4.636220119482003e-05, "epoch": 5.12993762993763, "percentage": 25.65, "elapsed_time": "0:28:45", "remaining_time": "1:23:22", "throughput": 1030.44, "total_tokens": 1778368} {"current_steps": 19745, "total_steps": 76960, "loss": 0.2416, "lr": 4.635925545311224e-05, "epoch": 5.131237006237006, "percentage": 25.66, "elapsed_time": "0:28:46", "remaining_time": "1:23:22", "throughput": 1030.45, "total_tokens": 1778816} {"current_steps": 19750, "total_steps": 76960, "loss": 0.2319, "lr": 4.6356308612877476e-05, "epoch": 5.132536382536382, "percentage": 25.66, "elapsed_time": "0:28:46", "remaining_time": "1:23:21", "throughput": 1030.46, "total_tokens": 1779264} {"current_steps": 19755, "total_steps": 76960, "loss": 0.2832, "lr": 4.6353360674267296e-05, "epoch": 5.133835758835759, "percentage": 25.67, "elapsed_time": "0:28:47", "remaining_time": "1:23:21", "throughput": 1030.49, "total_tokens": 1779728} {"current_steps": 19760, "total_steps": 76960, "loss": 0.2476, "lr": 4.635041163743333e-05, "epoch": 5.135135135135135, "percentage": 25.68, "elapsed_time": "0:28:47", "remaining_time": "1:23:20", "throughput": 1030.5, "total_tokens": 1780176} {"current_steps": 19765, "total_steps": 76960, "loss": 0.3229, "lr": 4.634746150252722e-05, "epoch": 5.136434511434511, "percentage": 25.68, "elapsed_time": "0:28:47", "remaining_time": "1:23:20", "throughput": 1030.52, "total_tokens": 1780640} {"current_steps": 19770, "total_steps": 76960, "loss": 0.2262, "lr": 4.634451026970072e-05, "epoch": 5.137733887733888, "percentage": 25.69, "elapsed_time": "0:28:48", "remaining_time": "1:23:19", "throughput": 1030.53, "total_tokens": 1781104} {"current_steps": 19775, "total_steps": 76960, "loss": 0.1935, "lr": 4.6341557939105604e-05, "epoch": 5.139033264033264, "percentage": 25.7, "elapsed_time": "0:28:48", "remaining_time": "1:23:19", "throughput": 1030.54, "total_tokens": 1781552} {"current_steps": 19780, "total_steps": 76960, "loss": 0.3191, "lr": 4.633860451089371e-05, "epoch": 5.14033264033264, "percentage": 25.7, "elapsed_time": "0:28:49", "remaining_time": "1:23:18", "throughput": 1030.56, "total_tokens": 1782016} {"current_steps": 19785, "total_steps": 76960, "loss": 0.2037, "lr": 4.633564998521696e-05, "epoch": 5.141632016632016, "percentage": 25.71, "elapsed_time": "0:28:49", "remaining_time": "1:23:18", "throughput": 1030.57, "total_tokens": 1782464} {"current_steps": 19790, "total_steps": 76960, "loss": 0.2158, "lr": 4.633269436222727e-05, "epoch": 5.142931392931393, "percentage": 25.71, "elapsed_time": "0:28:50", "remaining_time": "1:23:17", "throughput": 1030.58, "total_tokens": 1782912} {"current_steps": 19795, "total_steps": 76960, "loss": 0.213, "lr": 4.632973764207666e-05, "epoch": 5.144230769230769, "percentage": 25.72, "elapsed_time": "0:28:50", "remaining_time": "1:23:17", "throughput": 1030.59, "total_tokens": 1783360} {"current_steps": 19800, "total_steps": 76960, "loss": 0.2566, "lr": 4.632677982491723e-05, "epoch": 5.145530145530145, "percentage": 25.73, "elapsed_time": "0:28:50", "remaining_time": "1:23:16", "throughput": 1030.6, "total_tokens": 1783808} {"current_steps": 19805, "total_steps": 76960, "loss": 0.367, "lr": 4.632382091090106e-05, "epoch": 5.146829521829522, "percentage": 25.73, "elapsed_time": "0:28:51", "remaining_time": "1:23:16", "throughput": 1030.64, "total_tokens": 1784304} {"current_steps": 19810, "total_steps": 76960, "loss": 0.2891, "lr": 4.6320860900180364e-05, "epoch": 5.148128898128898, "percentage": 25.74, "elapsed_time": "0:28:51", "remaining_time": "1:23:15", "throughput": 1030.68, "total_tokens": 1784800} {"current_steps": 19815, "total_steps": 76960, "loss": 0.2646, "lr": 4.631789979290735e-05, "epoch": 5.149428274428274, "percentage": 25.75, "elapsed_time": "0:28:52", "remaining_time": "1:23:15", "throughput": 1030.69, "total_tokens": 1785248} {"current_steps": 19820, "total_steps": 76960, "loss": 0.2086, "lr": 4.631493758923433e-05, "epoch": 5.150727650727651, "percentage": 25.75, "elapsed_time": "0:28:52", "remaining_time": "1:23:14", "throughput": 1030.71, "total_tokens": 1785712} {"current_steps": 19825, "total_steps": 76960, "loss": 0.2593, "lr": 4.6311974289313646e-05, "epoch": 5.152027027027027, "percentage": 25.76, "elapsed_time": "0:28:52", "remaining_time": "1:23:14", "throughput": 1030.71, "total_tokens": 1786144} {"current_steps": 19830, "total_steps": 76960, "loss": 0.2809, "lr": 4.630900989329771e-05, "epoch": 5.153326403326403, "percentage": 25.77, "elapsed_time": "0:28:53", "remaining_time": "1:23:13", "throughput": 1030.72, "total_tokens": 1786592} {"current_steps": 19835, "total_steps": 76960, "loss": 0.2615, "lr": 4.630604440133896e-05, "epoch": 5.154625779625779, "percentage": 25.77, "elapsed_time": "0:28:53", "remaining_time": "1:23:13", "throughput": 1030.72, "total_tokens": 1787024} {"current_steps": 19840, "total_steps": 76960, "loss": 0.2496, "lr": 4.6303077813589956e-05, "epoch": 5.155925155925156, "percentage": 25.78, "elapsed_time": "0:28:54", "remaining_time": "1:23:12", "throughput": 1030.72, "total_tokens": 1787456} {"current_steps": 19845, "total_steps": 76960, "loss": 0.2764, "lr": 4.6300110130203236e-05, "epoch": 5.157224532224532, "percentage": 25.79, "elapsed_time": "0:28:54", "remaining_time": "1:23:12", "throughput": 1030.71, "total_tokens": 1787872} {"current_steps": 19850, "total_steps": 76960, "loss": 0.2673, "lr": 4.629714135133144e-05, "epoch": 5.158523908523908, "percentage": 25.79, "elapsed_time": "0:28:55", "remaining_time": "1:23:11", "throughput": 1030.73, "total_tokens": 1788336} {"current_steps": 19855, "total_steps": 76960, "loss": 0.2405, "lr": 4.629417147712727e-05, "epoch": 5.159823284823285, "percentage": 25.8, "elapsed_time": "0:28:55", "remaining_time": "1:23:11", "throughput": 1030.74, "total_tokens": 1788784} {"current_steps": 19860, "total_steps": 76960, "loss": 0.244, "lr": 4.6291200507743446e-05, "epoch": 5.161122661122661, "percentage": 25.81, "elapsed_time": "0:28:55", "remaining_time": "1:23:10", "throughput": 1030.77, "total_tokens": 1789264} {"current_steps": 19865, "total_steps": 76960, "loss": 0.2885, "lr": 4.628822844333278e-05, "epoch": 5.162422037422037, "percentage": 25.81, "elapsed_time": "0:28:56", "remaining_time": "1:23:10", "throughput": 1030.79, "total_tokens": 1789728} {"current_steps": 19870, "total_steps": 76960, "loss": 0.3026, "lr": 4.6285255284048134e-05, "epoch": 5.163721413721413, "percentage": 25.82, "elapsed_time": "0:28:56", "remaining_time": "1:23:09", "throughput": 1030.8, "total_tokens": 1790176} {"current_steps": 19875, "total_steps": 76960, "loss": 0.2369, "lr": 4.628228103004242e-05, "epoch": 5.16502079002079, "percentage": 25.83, "elapsed_time": "0:28:57", "remaining_time": "1:23:09", "throughput": 1030.83, "total_tokens": 1790656} {"current_steps": 19880, "total_steps": 76960, "loss": 0.253, "lr": 4.627930568146859e-05, "epoch": 5.166320166320166, "percentage": 25.83, "elapsed_time": "0:28:57", "remaining_time": "1:23:08", "throughput": 1030.85, "total_tokens": 1791120} {"current_steps": 19885, "total_steps": 76960, "loss": 0.174, "lr": 4.627632923847968e-05, "epoch": 5.167619542619542, "percentage": 25.84, "elapsed_time": "0:28:57", "remaining_time": "1:23:08", "throughput": 1030.86, "total_tokens": 1791568} {"current_steps": 19890, "total_steps": 76960, "loss": 0.2213, "lr": 4.627335170122877e-05, "epoch": 5.168918918918919, "percentage": 25.84, "elapsed_time": "0:28:58", "remaining_time": "1:23:07", "throughput": 1030.88, "total_tokens": 1792032} {"current_steps": 19895, "total_steps": 76960, "loss": 0.3225, "lr": 4.627037306986901e-05, "epoch": 5.170218295218295, "percentage": 25.85, "elapsed_time": "0:28:58", "remaining_time": "1:23:07", "throughput": 1030.9, "total_tokens": 1792496} {"current_steps": 19900, "total_steps": 76960, "loss": 0.3684, "lr": 4.626739334455357e-05, "epoch": 5.171517671517671, "percentage": 25.86, "elapsed_time": "0:28:59", "remaining_time": "1:23:06", "throughput": 1030.92, "total_tokens": 1792960} {"current_steps": 19905, "total_steps": 76960, "loss": 0.301, "lr": 4.6264412525435716e-05, "epoch": 5.172817047817047, "percentage": 25.86, "elapsed_time": "0:28:59", "remaining_time": "1:23:06", "throughput": 1030.93, "total_tokens": 1793424} {"current_steps": 19910, "total_steps": 76960, "loss": 0.2781, "lr": 4.626143061266876e-05, "epoch": 5.174116424116424, "percentage": 25.87, "elapsed_time": "0:29:00", "remaining_time": "1:23:05", "throughput": 1030.97, "total_tokens": 1793920} {"current_steps": 19915, "total_steps": 76960, "loss": 0.2702, "lr": 4.625844760640605e-05, "epoch": 5.1754158004158, "percentage": 25.88, "elapsed_time": "0:29:00", "remaining_time": "1:23:05", "throughput": 1030.98, "total_tokens": 1794368} {"current_steps": 19920, "total_steps": 76960, "loss": 0.2648, "lr": 4.625546350680101e-05, "epoch": 5.1767151767151764, "percentage": 25.88, "elapsed_time": "0:29:00", "remaining_time": "1:23:04", "throughput": 1031.0, "total_tokens": 1794832} {"current_steps": 19925, "total_steps": 76960, "loss": 0.298, "lr": 4.625247831400712e-05, "epoch": 5.178014553014553, "percentage": 25.89, "elapsed_time": "0:29:01", "remaining_time": "1:23:04", "throughput": 1030.98, "total_tokens": 1795248} {"current_steps": 19930, "total_steps": 76960, "loss": 0.2865, "lr": 4.6249492028177896e-05, "epoch": 5.179313929313929, "percentage": 25.9, "elapsed_time": "0:29:01", "remaining_time": "1:23:03", "throughput": 1031.0, "total_tokens": 1795712} {"current_steps": 19935, "total_steps": 76960, "loss": 0.2383, "lr": 4.624650464946695e-05, "epoch": 5.1806133056133055, "percentage": 25.9, "elapsed_time": "0:29:02", "remaining_time": "1:23:03", "throughput": 1031.02, "total_tokens": 1796192} {"current_steps": 19940, "total_steps": 76960, "loss": 0.2042, "lr": 4.62435161780279e-05, "epoch": 5.1819126819126815, "percentage": 25.91, "elapsed_time": "0:29:02", "remaining_time": "1:23:03", "throughput": 1031.01, "total_tokens": 1796608} {"current_steps": 19945, "total_steps": 76960, "loss": 0.2981, "lr": 4.6240526614014465e-05, "epoch": 5.183212058212058, "percentage": 25.92, "elapsed_time": "0:29:02", "remaining_time": "1:23:02", "throughput": 1031.03, "total_tokens": 1797072} {"current_steps": 19950, "total_steps": 76960, "loss": 0.3281, "lr": 4.6237535957580405e-05, "epoch": 5.1845114345114345, "percentage": 25.92, "elapsed_time": "0:29:03", "remaining_time": "1:23:02", "throughput": 1031.06, "total_tokens": 1797552} {"current_steps": 19955, "total_steps": 76960, "loss": 0.2237, "lr": 4.6234544208879503e-05, "epoch": 5.1858108108108105, "percentage": 25.93, "elapsed_time": "0:29:03", "remaining_time": "1:23:01", "throughput": 1031.08, "total_tokens": 1798016} {"current_steps": 19960, "total_steps": 76960, "loss": 0.2046, "lr": 4.623155136806566e-05, "epoch": 5.1871101871101875, "percentage": 25.94, "elapsed_time": "0:29:04", "remaining_time": "1:23:01", "throughput": 1031.08, "total_tokens": 1798448} {"current_steps": 19965, "total_steps": 76960, "loss": 0.3322, "lr": 4.622855743529278e-05, "epoch": 5.1884095634095635, "percentage": 25.94, "elapsed_time": "0:29:04", "remaining_time": "1:23:00", "throughput": 1031.08, "total_tokens": 1798880} {"current_steps": 19970, "total_steps": 76960, "loss": 0.1797, "lr": 4.6225562410714854e-05, "epoch": 5.1897089397089395, "percentage": 25.95, "elapsed_time": "0:29:05", "remaining_time": "1:23:00", "throughput": 1031.1, "total_tokens": 1799344} {"current_steps": 19975, "total_steps": 76960, "loss": 0.2129, "lr": 4.622256629448591e-05, "epoch": 5.191008316008316, "percentage": 25.96, "elapsed_time": "0:29:05", "remaining_time": "1:22:59", "throughput": 1031.09, "total_tokens": 1799760} {"current_steps": 19980, "total_steps": 76960, "loss": 0.2318, "lr": 4.621956908676005e-05, "epoch": 5.1923076923076925, "percentage": 25.96, "elapsed_time": "0:29:05", "remaining_time": "1:22:59", "throughput": 1031.09, "total_tokens": 1800192} {"current_steps": 19985, "total_steps": 76960, "loss": 0.2679, "lr": 4.6216570787691423e-05, "epoch": 5.1936070686070686, "percentage": 25.97, "elapsed_time": "0:29:06", "remaining_time": "1:22:58", "throughput": 1031.11, "total_tokens": 1800656} {"current_steps": 19990, "total_steps": 76960, "loss": 0.2527, "lr": 4.621357139743423e-05, "epoch": 5.194906444906445, "percentage": 25.97, "elapsed_time": "0:29:06", "remaining_time": "1:22:58", "throughput": 1031.12, "total_tokens": 1801104} {"current_steps": 19995, "total_steps": 76960, "loss": 0.2117, "lr": 4.621057091614274e-05, "epoch": 5.1962058212058215, "percentage": 25.98, "elapsed_time": "0:29:07", "remaining_time": "1:22:57", "throughput": 1031.1, "total_tokens": 1801504} {"current_steps": 20000, "total_steps": 76960, "loss": 0.2495, "lr": 4.620756934397126e-05, "epoch": 5.197505197505198, "percentage": 25.99, "elapsed_time": "0:29:07", "remaining_time": "1:22:57", "throughput": 1031.09, "total_tokens": 1801920} {"current_steps": 20005, "total_steps": 76960, "loss": 0.1695, "lr": 4.620456668107417e-05, "epoch": 5.198804573804574, "percentage": 25.99, "elapsed_time": "0:29:08", "remaining_time": "1:22:56", "throughput": 1031.09, "total_tokens": 1802352} {"current_steps": 20010, "total_steps": 76960, "loss": 0.2846, "lr": 4.620156292760589e-05, "epoch": 5.20010395010395, "percentage": 26.0, "elapsed_time": "0:29:08", "remaining_time": "1:22:56", "throughput": 1031.1, "total_tokens": 1802800} {"current_steps": 20015, "total_steps": 76960, "loss": 0.2536, "lr": 4.619855808372092e-05, "epoch": 5.201403326403327, "percentage": 26.01, "elapsed_time": "0:29:08", "remaining_time": "1:22:55", "throughput": 1031.12, "total_tokens": 1803264} {"current_steps": 20020, "total_steps": 76960, "loss": 0.2141, "lr": 4.61955521495738e-05, "epoch": 5.202702702702703, "percentage": 26.01, "elapsed_time": "0:29:09", "remaining_time": "1:22:55", "throughput": 1031.14, "total_tokens": 1803728} {"current_steps": 20025, "total_steps": 76960, "loss": 0.2714, "lr": 4.619254512531912e-05, "epoch": 5.204002079002079, "percentage": 26.02, "elapsed_time": "0:29:09", "remaining_time": "1:22:54", "throughput": 1031.14, "total_tokens": 1804176} {"current_steps": 20030, "total_steps": 76960, "loss": 0.3275, "lr": 4.618953701111154e-05, "epoch": 5.205301455301456, "percentage": 26.03, "elapsed_time": "0:29:10", "remaining_time": "1:22:54", "throughput": 1031.14, "total_tokens": 1804624} {"current_steps": 20035, "total_steps": 76960, "loss": 0.234, "lr": 4.6186527807105775e-05, "epoch": 5.206600831600832, "percentage": 26.03, "elapsed_time": "0:29:10", "remaining_time": "1:22:53", "throughput": 1031.16, "total_tokens": 1805088} {"current_steps": 20040, "total_steps": 76960, "loss": 0.2485, "lr": 4.6183517513456576e-05, "epoch": 5.207900207900208, "percentage": 26.04, "elapsed_time": "0:29:10", "remaining_time": "1:22:53", "throughput": 1031.15, "total_tokens": 1805504} {"current_steps": 20045, "total_steps": 76960, "loss": 0.3391, "lr": 4.6180506130318776e-05, "epoch": 5.209199584199585, "percentage": 26.05, "elapsed_time": "0:29:11", "remaining_time": "1:22:52", "throughput": 1031.17, "total_tokens": 1805968} {"current_steps": 20050, "total_steps": 76960, "loss": 0.2875, "lr": 4.617749365784725e-05, "epoch": 5.210498960498961, "percentage": 26.05, "elapsed_time": "0:29:11", "remaining_time": "1:22:52", "throughput": 1031.18, "total_tokens": 1806416} {"current_steps": 20055, "total_steps": 76960, "loss": 0.3363, "lr": 4.617448009619694e-05, "epoch": 5.211798336798337, "percentage": 26.06, "elapsed_time": "0:29:12", "remaining_time": "1:22:51", "throughput": 1031.19, "total_tokens": 1806864} {"current_steps": 20060, "total_steps": 76960, "loss": 0.2658, "lr": 4.6171465445522824e-05, "epoch": 5.213097713097713, "percentage": 26.07, "elapsed_time": "0:29:12", "remaining_time": "1:22:51", "throughput": 1031.19, "total_tokens": 1807296} {"current_steps": 20065, "total_steps": 76960, "loss": 0.2628, "lr": 4.6168449705979956e-05, "epoch": 5.21439708939709, "percentage": 26.07, "elapsed_time": "0:29:13", "remaining_time": "1:22:50", "throughput": 1031.19, "total_tokens": 1807744} {"current_steps": 20070, "total_steps": 76960, "loss": 0.2299, "lr": 4.6165432877723435e-05, "epoch": 5.215696465696466, "percentage": 26.08, "elapsed_time": "0:29:13", "remaining_time": "1:22:50", "throughput": 1031.17, "total_tokens": 1808144} {"current_steps": 20075, "total_steps": 76960, "loss": 0.2171, "lr": 4.616241496090843e-05, "epoch": 5.216995841995842, "percentage": 26.08, "elapsed_time": "0:29:13", "remaining_time": "1:22:49", "throughput": 1031.17, "total_tokens": 1808576} {"current_steps": 20080, "total_steps": 76960, "loss": 0.1602, "lr": 4.615939595569014e-05, "epoch": 5.218295218295219, "percentage": 26.09, "elapsed_time": "0:29:14", "remaining_time": "1:22:49", "throughput": 1031.19, "total_tokens": 1809040} {"current_steps": 20085, "total_steps": 76960, "loss": 0.2669, "lr": 4.615637586222384e-05, "epoch": 5.219594594594595, "percentage": 26.1, "elapsed_time": "0:29:14", "remaining_time": "1:22:48", "throughput": 1031.2, "total_tokens": 1809488} {"current_steps": 20090, "total_steps": 76960, "loss": 0.3704, "lr": 4.615335468066486e-05, "epoch": 5.220893970893971, "percentage": 26.1, "elapsed_time": "0:29:15", "remaining_time": "1:22:48", "throughput": 1031.19, "total_tokens": 1809904} {"current_steps": 20095, "total_steps": 76960, "loss": 0.3405, "lr": 4.615033241116858e-05, "epoch": 5.222193347193347, "percentage": 26.11, "elapsed_time": "0:29:15", "remaining_time": "1:22:47", "throughput": 1031.22, "total_tokens": 1810384} {"current_steps": 20100, "total_steps": 76960, "loss": 0.2597, "lr": 4.614730905389044e-05, "epoch": 5.223492723492724, "percentage": 26.12, "elapsed_time": "0:29:15", "remaining_time": "1:22:47", "throughput": 1031.23, "total_tokens": 1810832} {"current_steps": 20105, "total_steps": 76960, "loss": 0.2739, "lr": 4.614428460898594e-05, "epoch": 5.2247920997921, "percentage": 26.12, "elapsed_time": "0:29:16", "remaining_time": "1:22:46", "throughput": 1031.24, "total_tokens": 1811280} {"current_steps": 20110, "total_steps": 76960, "loss": 0.2748, "lr": 4.614125907661061e-05, "epoch": 5.226091476091476, "percentage": 26.13, "elapsed_time": "0:29:16", "remaining_time": "1:22:46", "throughput": 1031.25, "total_tokens": 1811728} {"current_steps": 20115, "total_steps": 76960, "loss": 0.2504, "lr": 4.6138232456920084e-05, "epoch": 5.227390852390853, "percentage": 26.14, "elapsed_time": "0:29:17", "remaining_time": "1:22:45", "throughput": 1031.25, "total_tokens": 1812160} {"current_steps": 20120, "total_steps": 76960, "loss": 0.2534, "lr": 4.613520475006999e-05, "epoch": 5.228690228690229, "percentage": 26.14, "elapsed_time": "0:29:17", "remaining_time": "1:22:45", "throughput": 1031.27, "total_tokens": 1812624} {"current_steps": 20125, "total_steps": 76960, "loss": 0.1739, "lr": 4.613217595621608e-05, "epoch": 5.229989604989605, "percentage": 26.15, "elapsed_time": "0:29:18", "remaining_time": "1:22:45", "throughput": 1031.27, "total_tokens": 1813056} {"current_steps": 20130, "total_steps": 76960, "loss": 0.2566, "lr": 4.612914607551411e-05, "epoch": 5.231288981288981, "percentage": 26.16, "elapsed_time": "0:29:18", "remaining_time": "1:22:44", "throughput": 1031.25, "total_tokens": 1813456} {"current_steps": 20135, "total_steps": 76960, "loss": 0.2561, "lr": 4.612611510811991e-05, "epoch": 5.232588357588358, "percentage": 26.16, "elapsed_time": "0:29:18", "remaining_time": "1:22:44", "throughput": 1031.27, "total_tokens": 1813920} {"current_steps": 20140, "total_steps": 76960, "loss": 0.3021, "lr": 4.612308305418937e-05, "epoch": 5.233887733887734, "percentage": 26.17, "elapsed_time": "0:29:19", "remaining_time": "1:22:43", "throughput": 1031.28, "total_tokens": 1814368} {"current_steps": 20145, "total_steps": 76960, "loss": 0.1783, "lr": 4.612004991387843e-05, "epoch": 5.23518711018711, "percentage": 26.18, "elapsed_time": "0:29:19", "remaining_time": "1:22:43", "throughput": 1031.29, "total_tokens": 1814832} {"current_steps": 20150, "total_steps": 76960, "loss": 0.3277, "lr": 4.6117015687343086e-05, "epoch": 5.236486486486487, "percentage": 26.18, "elapsed_time": "0:29:20", "remaining_time": "1:22:42", "throughput": 1031.29, "total_tokens": 1815248} {"current_steps": 20155, "total_steps": 76960, "loss": 0.2988, "lr": 4.611398037473939e-05, "epoch": 5.237785862785863, "percentage": 26.19, "elapsed_time": "0:29:20", "remaining_time": "1:22:42", "throughput": 1031.27, "total_tokens": 1815648} {"current_steps": 20160, "total_steps": 76960, "loss": 0.2847, "lr": 4.611094397622345e-05, "epoch": 5.239085239085239, "percentage": 26.2, "elapsed_time": "0:29:21", "remaining_time": "1:22:41", "throughput": 1031.29, "total_tokens": 1816112} {"current_steps": 20165, "total_steps": 76960, "loss": 0.2125, "lr": 4.610790649195144e-05, "epoch": 5.240384615384615, "percentage": 26.2, "elapsed_time": "0:29:21", "remaining_time": "1:22:41", "throughput": 1031.3, "total_tokens": 1816560} {"current_steps": 20170, "total_steps": 76960, "loss": 0.3219, "lr": 4.6104867922079574e-05, "epoch": 5.241683991683992, "percentage": 26.21, "elapsed_time": "0:29:21", "remaining_time": "1:22:40", "throughput": 1031.31, "total_tokens": 1817024} {"current_steps": 20175, "total_steps": 76960, "loss": 0.259, "lr": 4.6101828266764126e-05, "epoch": 5.242983367983368, "percentage": 26.21, "elapsed_time": "0:29:22", "remaining_time": "1:22:40", "throughput": 1031.31, "total_tokens": 1817456} {"current_steps": 20180, "total_steps": 76960, "loss": 0.2406, "lr": 4.6098787526161435e-05, "epoch": 5.244282744282744, "percentage": 26.22, "elapsed_time": "0:29:22", "remaining_time": "1:22:39", "throughput": 1031.33, "total_tokens": 1817920} {"current_steps": 20185, "total_steps": 76960, "loss": 0.216, "lr": 4.609574570042788e-05, "epoch": 5.245582120582121, "percentage": 26.23, "elapsed_time": "0:29:23", "remaining_time": "1:22:39", "throughput": 1031.35, "total_tokens": 1818384} {"current_steps": 20190, "total_steps": 76960, "loss": 0.2952, "lr": 4.609270278971991e-05, "epoch": 5.246881496881497, "percentage": 26.23, "elapsed_time": "0:29:23", "remaining_time": "1:22:38", "throughput": 1031.34, "total_tokens": 1818800} {"current_steps": 20195, "total_steps": 76960, "loss": 0.3068, "lr": 4.6089658794194035e-05, "epoch": 5.248180873180873, "percentage": 26.24, "elapsed_time": "0:29:23", "remaining_time": "1:22:38", "throughput": 1031.34, "total_tokens": 1819232} {"current_steps": 20200, "total_steps": 76960, "loss": 0.2183, "lr": 4.608661371400679e-05, "epoch": 5.24948024948025, "percentage": 26.25, "elapsed_time": "0:29:24", "remaining_time": "1:22:37", "throughput": 1031.34, "total_tokens": 1819664} {"current_steps": 20205, "total_steps": 76960, "loss": 0.2815, "lr": 4.608356754931481e-05, "epoch": 5.250779625779626, "percentage": 26.25, "elapsed_time": "0:29:24", "remaining_time": "1:22:37", "throughput": 1031.36, "total_tokens": 1820128} {"current_steps": 20210, "total_steps": 76960, "loss": 0.1953, "lr": 4.608052030027474e-05, "epoch": 5.252079002079002, "percentage": 26.26, "elapsed_time": "0:29:25", "remaining_time": "1:22:36", "throughput": 1031.39, "total_tokens": 1820608} {"current_steps": 20215, "total_steps": 76960, "loss": 0.1758, "lr": 4.607747196704332e-05, "epoch": 5.253378378378378, "percentage": 26.27, "elapsed_time": "0:29:25", "remaining_time": "1:22:36", "throughput": 1031.42, "total_tokens": 1821088} {"current_steps": 20220, "total_steps": 76960, "loss": 0.2383, "lr": 4.6074422549777306e-05, "epoch": 5.254677754677755, "percentage": 26.27, "elapsed_time": "0:29:26", "remaining_time": "1:22:35", "throughput": 1031.43, "total_tokens": 1821552} {"current_steps": 20225, "total_steps": 76960, "loss": 0.3207, "lr": 4.6071372048633566e-05, "epoch": 5.255977130977131, "percentage": 26.28, "elapsed_time": "0:29:26", "remaining_time": "1:22:35", "throughput": 1031.43, "total_tokens": 1821984} {"current_steps": 20230, "total_steps": 76960, "loss": 0.1653, "lr": 4.606832046376896e-05, "epoch": 5.257276507276507, "percentage": 26.29, "elapsed_time": "0:29:26", "remaining_time": "1:22:34", "throughput": 1031.42, "total_tokens": 1822384} {"current_steps": 20235, "total_steps": 76960, "loss": 0.2685, "lr": 4.606526779534045e-05, "epoch": 5.258575883575883, "percentage": 26.29, "elapsed_time": "0:29:27", "remaining_time": "1:22:34", "throughput": 1031.42, "total_tokens": 1822832} {"current_steps": 20240, "total_steps": 76960, "loss": 0.1026, "lr": 4.6062214043505034e-05, "epoch": 5.25987525987526, "percentage": 26.3, "elapsed_time": "0:29:27", "remaining_time": "1:22:33", "throughput": 1031.43, "total_tokens": 1823264} {"current_steps": 20245, "total_steps": 76960, "loss": 0.1974, "lr": 4.6059159208419764e-05, "epoch": 5.261174636174636, "percentage": 26.31, "elapsed_time": "0:29:28", "remaining_time": "1:22:33", "throughput": 1031.43, "total_tokens": 1823696} {"current_steps": 20250, "total_steps": 76960, "loss": 0.3268, "lr": 4.6056103290241764e-05, "epoch": 5.262474012474012, "percentage": 26.31, "elapsed_time": "0:29:28", "remaining_time": "1:22:32", "throughput": 1031.43, "total_tokens": 1824144} {"current_steps": 20255, "total_steps": 76960, "loss": 0.3153, "lr": 4.60530462891282e-05, "epoch": 5.263773388773389, "percentage": 26.32, "elapsed_time": "0:29:28", "remaining_time": "1:22:32", "throughput": 1031.43, "total_tokens": 1824576} {"current_steps": 20260, "total_steps": 76960, "loss": 0.2638, "lr": 4.604998820523628e-05, "epoch": 5.265072765072765, "percentage": 26.33, "elapsed_time": "0:29:29", "remaining_time": "1:22:31", "throughput": 1031.44, "total_tokens": 1825008} {"current_steps": 20265, "total_steps": 76960, "loss": 0.2808, "lr": 4.6046929038723304e-05, "epoch": 5.266372141372141, "percentage": 26.33, "elapsed_time": "0:29:29", "remaining_time": "1:22:31", "throughput": 1031.45, "total_tokens": 1825472} {"current_steps": 20270, "total_steps": 76960, "loss": 0.1509, "lr": 4.604386878974661e-05, "epoch": 5.267671517671518, "percentage": 26.34, "elapsed_time": "0:29:30", "remaining_time": "1:22:30", "throughput": 1031.46, "total_tokens": 1825920} {"current_steps": 20275, "total_steps": 76960, "loss": 0.2525, "lr": 4.6040807458463576e-05, "epoch": 5.268970893970894, "percentage": 26.34, "elapsed_time": "0:29:30", "remaining_time": "1:22:30", "throughput": 1031.46, "total_tokens": 1826352} {"current_steps": 20280, "total_steps": 76960, "loss": 0.2514, "lr": 4.603774504503165e-05, "epoch": 5.27027027027027, "percentage": 26.35, "elapsed_time": "0:29:31", "remaining_time": "1:22:29", "throughput": 1031.49, "total_tokens": 1826832} {"current_steps": 20285, "total_steps": 76960, "loss": 0.3098, "lr": 4.6034681549608335e-05, "epoch": 5.271569646569646, "percentage": 26.36, "elapsed_time": "0:29:31", "remaining_time": "1:22:29", "throughput": 1031.48, "total_tokens": 1827248} {"current_steps": 20290, "total_steps": 76960, "loss": 0.2832, "lr": 4.60316169723512e-05, "epoch": 5.272869022869023, "percentage": 26.36, "elapsed_time": "0:29:31", "remaining_time": "1:22:28", "throughput": 1031.48, "total_tokens": 1827680} {"current_steps": 20295, "total_steps": 76960, "loss": 0.1825, "lr": 4.602855131341786e-05, "epoch": 5.274168399168399, "percentage": 26.37, "elapsed_time": "0:29:32", "remaining_time": "1:22:28", "throughput": 1031.5, "total_tokens": 1828144} {"current_steps": 20300, "total_steps": 76960, "loss": 0.2304, "lr": 4.602548457296597e-05, "epoch": 5.275467775467775, "percentage": 26.38, "elapsed_time": "0:29:32", "remaining_time": "1:22:27", "throughput": 1031.53, "total_tokens": 1828624} {"current_steps": 20305, "total_steps": 76960, "loss": 0.3441, "lr": 4.6022416751153255e-05, "epoch": 5.276767151767152, "percentage": 26.38, "elapsed_time": "0:29:33", "remaining_time": "1:22:27", "throughput": 1031.56, "total_tokens": 1829104} {"current_steps": 20310, "total_steps": 76960, "loss": 0.2934, "lr": 4.6019347848137516e-05, "epoch": 5.278066528066528, "percentage": 26.39, "elapsed_time": "0:29:33", "remaining_time": "1:22:26", "throughput": 1031.56, "total_tokens": 1829536} {"current_steps": 20315, "total_steps": 76960, "loss": 0.2435, "lr": 4.601627786407657e-05, "epoch": 5.279365904365904, "percentage": 26.4, "elapsed_time": "0:29:33", "remaining_time": "1:22:26", "throughput": 1031.56, "total_tokens": 1829968} {"current_steps": 20320, "total_steps": 76960, "loss": 0.3092, "lr": 4.601320679912832e-05, "epoch": 5.28066528066528, "percentage": 26.4, "elapsed_time": "0:29:34", "remaining_time": "1:22:25", "throughput": 1031.56, "total_tokens": 1830416} {"current_steps": 20325, "total_steps": 76960, "loss": 0.2624, "lr": 4.601013465345071e-05, "epoch": 5.281964656964657, "percentage": 26.41, "elapsed_time": "0:29:34", "remaining_time": "1:22:25", "throughput": 1031.57, "total_tokens": 1830848} {"current_steps": 20330, "total_steps": 76960, "loss": 0.2656, "lr": 4.600706142720174e-05, "epoch": 5.283264033264033, "percentage": 26.42, "elapsed_time": "0:29:35", "remaining_time": "1:22:25", "throughput": 1031.59, "total_tokens": 1831328} {"current_steps": 20335, "total_steps": 76960, "loss": 0.286, "lr": 4.6003987120539476e-05, "epoch": 5.284563409563409, "percentage": 26.42, "elapsed_time": "0:29:35", "remaining_time": "1:22:24", "throughput": 1031.62, "total_tokens": 1831808} {"current_steps": 20340, "total_steps": 76960, "loss": 0.2556, "lr": 4.600091173362203e-05, "epoch": 5.285862785862786, "percentage": 26.43, "elapsed_time": "0:29:36", "remaining_time": "1:22:24", "throughput": 1031.63, "total_tokens": 1832256} {"current_steps": 20345, "total_steps": 76960, "loss": 0.2613, "lr": 4.599783526660757e-05, "epoch": 5.287162162162162, "percentage": 26.44, "elapsed_time": "0:29:36", "remaining_time": "1:22:23", "throughput": 1031.63, "total_tokens": 1832688} {"current_steps": 20350, "total_steps": 76960, "loss": 0.298, "lr": 4.599475771965432e-05, "epoch": 5.288461538461538, "percentage": 26.44, "elapsed_time": "0:29:36", "remaining_time": "1:22:23", "throughput": 1031.65, "total_tokens": 1833152} {"current_steps": 20355, "total_steps": 76960, "loss": 0.256, "lr": 4.599167909292057e-05, "epoch": 5.289760914760914, "percentage": 26.45, "elapsed_time": "0:29:37", "remaining_time": "1:22:22", "throughput": 1031.65, "total_tokens": 1833584} {"current_steps": 20360, "total_steps": 76960, "loss": 0.3093, "lr": 4.5988599386564654e-05, "epoch": 5.291060291060291, "percentage": 26.46, "elapsed_time": "0:29:37", "remaining_time": "1:22:22", "throughput": 1031.66, "total_tokens": 1834032} {"current_steps": 20365, "total_steps": 76960, "loss": 0.2885, "lr": 4.5985518600744956e-05, "epoch": 5.292359667359667, "percentage": 26.46, "elapsed_time": "0:29:38", "remaining_time": "1:22:21", "throughput": 1031.68, "total_tokens": 1834496} {"current_steps": 20370, "total_steps": 76960, "loss": 0.3014, "lr": 4.5982436735619926e-05, "epoch": 5.293659043659043, "percentage": 26.47, "elapsed_time": "0:29:38", "remaining_time": "1:22:21", "throughput": 1031.68, "total_tokens": 1834928} {"current_steps": 20375, "total_steps": 76960, "loss": 0.2696, "lr": 4.597935379134808e-05, "epoch": 5.29495841995842, "percentage": 26.47, "elapsed_time": "0:29:39", "remaining_time": "1:22:20", "throughput": 1031.7, "total_tokens": 1835408} {"current_steps": 20380, "total_steps": 76960, "loss": 0.2564, "lr": 4.5976269768087956e-05, "epoch": 5.296257796257796, "percentage": 26.48, "elapsed_time": "0:29:39", "remaining_time": "1:22:20", "throughput": 1031.73, "total_tokens": 1835888} {"current_steps": 20385, "total_steps": 76960, "loss": 0.3111, "lr": 4.5973184665998186e-05, "epoch": 5.297557172557172, "percentage": 26.49, "elapsed_time": "0:29:39", "remaining_time": "1:22:19", "throughput": 1031.75, "total_tokens": 1836352} {"current_steps": 20390, "total_steps": 76960, "loss": 0.2803, "lr": 4.597009848523744e-05, "epoch": 5.298856548856548, "percentage": 26.49, "elapsed_time": "0:29:40", "remaining_time": "1:22:19", "throughput": 1031.79, "total_tokens": 1836848} {"current_steps": 20395, "total_steps": 76960, "loss": 0.2851, "lr": 4.5967011225964415e-05, "epoch": 5.300155925155925, "percentage": 26.5, "elapsed_time": "0:29:40", "remaining_time": "1:22:18", "throughput": 1031.81, "total_tokens": 1837312} {"current_steps": 20400, "total_steps": 76960, "loss": 0.2071, "lr": 4.596392288833793e-05, "epoch": 5.301455301455301, "percentage": 26.51, "elapsed_time": "0:29:41", "remaining_time": "1:22:18", "throughput": 1031.81, "total_tokens": 1837760} {"current_steps": 20405, "total_steps": 76960, "loss": 0.3043, "lr": 4.596083347251679e-05, "epoch": 5.3027546777546775, "percentage": 26.51, "elapsed_time": "0:29:41", "remaining_time": "1:22:17", "throughput": 1031.85, "total_tokens": 1838256} {"current_steps": 20410, "total_steps": 76960, "loss": 0.2878, "lr": 4.595774297865992e-05, "epoch": 5.304054054054054, "percentage": 26.52, "elapsed_time": "0:29:41", "remaining_time": "1:22:17", "throughput": 1031.85, "total_tokens": 1838688} {"current_steps": 20415, "total_steps": 76960, "loss": 0.2887, "lr": 4.595465140692624e-05, "epoch": 5.30535343035343, "percentage": 26.53, "elapsed_time": "0:29:42", "remaining_time": "1:22:16", "throughput": 1031.87, "total_tokens": 1839152} {"current_steps": 20420, "total_steps": 76960, "loss": 0.2197, "lr": 4.595155875747476e-05, "epoch": 5.3066528066528065, "percentage": 26.53, "elapsed_time": "0:29:42", "remaining_time": "1:22:16", "throughput": 1031.91, "total_tokens": 1839664} {"current_steps": 20425, "total_steps": 76960, "loss": 0.3274, "lr": 4.5948465030464536e-05, "epoch": 5.307952182952183, "percentage": 26.54, "elapsed_time": "0:29:43", "remaining_time": "1:22:15", "throughput": 1031.92, "total_tokens": 1840112} {"current_steps": 20430, "total_steps": 76960, "loss": 0.2732, "lr": 4.594537022605468e-05, "epoch": 5.3092515592515594, "percentage": 26.55, "elapsed_time": "0:29:43", "remaining_time": "1:22:15", "throughput": 1031.93, "total_tokens": 1840560} {"current_steps": 20435, "total_steps": 76960, "loss": 0.2566, "lr": 4.5942274344404367e-05, "epoch": 5.3105509355509355, "percentage": 26.55, "elapsed_time": "0:29:44", "remaining_time": "1:22:14", "throughput": 1031.93, "total_tokens": 1840992} {"current_steps": 20440, "total_steps": 76960, "loss": 0.2574, "lr": 4.593917738567283e-05, "epoch": 5.3118503118503115, "percentage": 26.56, "elapsed_time": "0:29:44", "remaining_time": "1:22:14", "throughput": 1031.95, "total_tokens": 1841456} {"current_steps": 20445, "total_steps": 76960, "loss": 0.1997, "lr": 4.593607935001932e-05, "epoch": 5.3131496881496885, "percentage": 26.57, "elapsed_time": "0:29:44", "remaining_time": "1:22:13", "throughput": 1031.94, "total_tokens": 1841872} {"current_steps": 20450, "total_steps": 76960, "loss": 0.2915, "lr": 4.59329802376032e-05, "epoch": 5.3144490644490645, "percentage": 26.57, "elapsed_time": "0:29:45", "remaining_time": "1:22:13", "throughput": 1031.95, "total_tokens": 1842320} {"current_steps": 20455, "total_steps": 76960, "loss": 0.2133, "lr": 4.5929880048583846e-05, "epoch": 5.3157484407484406, "percentage": 26.58, "elapsed_time": "0:29:45", "remaining_time": "1:22:12", "throughput": 1031.94, "total_tokens": 1842736} {"current_steps": 20460, "total_steps": 76960, "loss": 0.2134, "lr": 4.592677878312071e-05, "epoch": 5.317047817047817, "percentage": 26.59, "elapsed_time": "0:29:46", "remaining_time": "1:22:12", "throughput": 1031.94, "total_tokens": 1843168} {"current_steps": 20465, "total_steps": 76960, "loss": 0.0977, "lr": 4.5923676441373287e-05, "epoch": 5.3183471933471935, "percentage": 26.59, "elapsed_time": "0:29:46", "remaining_time": "1:22:11", "throughput": 1031.92, "total_tokens": 1843568} {"current_steps": 20470, "total_steps": 76960, "loss": 0.2452, "lr": 4.5920573023501134e-05, "epoch": 5.31964656964657, "percentage": 26.6, "elapsed_time": "0:29:46", "remaining_time": "1:22:11", "throughput": 1031.93, "total_tokens": 1844016} {"current_steps": 20475, "total_steps": 76960, "loss": 0.2753, "lr": 4.5917468529663866e-05, "epoch": 5.320945945945946, "percentage": 26.6, "elapsed_time": "0:29:47", "remaining_time": "1:22:10", "throughput": 1031.93, "total_tokens": 1844448} {"current_steps": 20480, "total_steps": 76960, "loss": 0.395, "lr": 4.591436296002115e-05, "epoch": 5.3222453222453225, "percentage": 26.61, "elapsed_time": "0:29:47", "remaining_time": "1:22:10", "throughput": 1031.97, "total_tokens": 1844944} {"current_steps": 20485, "total_steps": 76960, "loss": 0.3063, "lr": 4.591125631473271e-05, "epoch": 5.323544698544699, "percentage": 26.62, "elapsed_time": "0:29:48", "remaining_time": "1:22:09", "throughput": 1031.96, "total_tokens": 1845360} {"current_steps": 20490, "total_steps": 76960, "loss": 0.2813, "lr": 4.590814859395832e-05, "epoch": 5.324844074844075, "percentage": 26.62, "elapsed_time": "0:29:48", "remaining_time": "1:22:09", "throughput": 1031.96, "total_tokens": 1845792} {"current_steps": 20495, "total_steps": 76960, "loss": 0.3458, "lr": 4.590503979785782e-05, "epoch": 5.326143451143452, "percentage": 26.63, "elapsed_time": "0:29:49", "remaining_time": "1:22:08", "throughput": 1031.98, "total_tokens": 1846256} {"current_steps": 20500, "total_steps": 76960, "loss": 0.2485, "lr": 4.590192992659109e-05, "epoch": 5.327442827442828, "percentage": 26.64, "elapsed_time": "0:29:49", "remaining_time": "1:22:08", "throughput": 1031.99, "total_tokens": 1846704} {"current_steps": 20505, "total_steps": 76960, "loss": 0.2771, "lr": 4.589881898031807e-05, "epoch": 5.328742203742204, "percentage": 26.64, "elapsed_time": "0:29:49", "remaining_time": "1:22:07", "throughput": 1031.99, "total_tokens": 1847136} {"current_steps": 20510, "total_steps": 76960, "loss": 0.241, "lr": 4.589570695919877e-05, "epoch": 5.33004158004158, "percentage": 26.65, "elapsed_time": "0:29:50", "remaining_time": "1:22:07", "throughput": 1032.0, "total_tokens": 1847600} {"current_steps": 20515, "total_steps": 76960, "loss": 0.2401, "lr": 4.589259386339324e-05, "epoch": 5.331340956340957, "percentage": 26.66, "elapsed_time": "0:29:50", "remaining_time": "1:22:06", "throughput": 1032.01, "total_tokens": 1848048} {"current_steps": 20520, "total_steps": 76960, "loss": 0.1323, "lr": 4.588947969306159e-05, "epoch": 5.332640332640333, "percentage": 26.66, "elapsed_time": "0:29:51", "remaining_time": "1:22:06", "throughput": 1032.0, "total_tokens": 1848464} {"current_steps": 20525, "total_steps": 76960, "loss": 0.2866, "lr": 4.5886364448363985e-05, "epoch": 5.333939708939709, "percentage": 26.67, "elapsed_time": "0:29:51", "remaining_time": "1:22:06", "throughput": 1032.01, "total_tokens": 1848912} {"current_steps": 20530, "total_steps": 76960, "loss": 0.3591, "lr": 4.5883248129460644e-05, "epoch": 5.335239085239086, "percentage": 26.68, "elapsed_time": "0:29:51", "remaining_time": "1:22:05", "throughput": 1032.03, "total_tokens": 1849376} {"current_steps": 20535, "total_steps": 76960, "loss": 0.2025, "lr": 4.588013073651184e-05, "epoch": 5.336538461538462, "percentage": 26.68, "elapsed_time": "0:29:52", "remaining_time": "1:22:05", "throughput": 1032.05, "total_tokens": 1849840} {"current_steps": 20540, "total_steps": 76960, "loss": 0.3027, "lr": 4.587701226967791e-05, "epoch": 5.337837837837838, "percentage": 26.69, "elapsed_time": "0:29:52", "remaining_time": "1:22:04", "throughput": 1032.07, "total_tokens": 1850304} {"current_steps": 20545, "total_steps": 76960, "loss": 0.2334, "lr": 4.5873892729119225e-05, "epoch": 5.339137214137214, "percentage": 26.7, "elapsed_time": "0:29:53", "remaining_time": "1:22:04", "throughput": 1032.08, "total_tokens": 1850752} {"current_steps": 20550, "total_steps": 76960, "loss": 0.2819, "lr": 4.5870772114996254e-05, "epoch": 5.340436590436591, "percentage": 26.7, "elapsed_time": "0:29:53", "remaining_time": "1:22:03", "throughput": 1032.11, "total_tokens": 1851232} {"current_steps": 20555, "total_steps": 76960, "loss": 0.2809, "lr": 4.586765042746946e-05, "epoch": 5.341735966735967, "percentage": 26.71, "elapsed_time": "0:29:54", "remaining_time": "1:22:03", "throughput": 1032.13, "total_tokens": 1851696} {"current_steps": 20560, "total_steps": 76960, "loss": 0.2776, "lr": 4.586452766669942e-05, "epoch": 5.343035343035343, "percentage": 26.72, "elapsed_time": "0:29:54", "remaining_time": "1:22:02", "throughput": 1032.15, "total_tokens": 1852176} {"current_steps": 20565, "total_steps": 76960, "loss": 0.2944, "lr": 4.586140383284673e-05, "epoch": 5.34433471933472, "percentage": 26.72, "elapsed_time": "0:29:54", "remaining_time": "1:22:02", "throughput": 1032.13, "total_tokens": 1852576} {"current_steps": 20570, "total_steps": 76960, "loss": 0.2231, "lr": 4.585827892607204e-05, "epoch": 5.345634095634096, "percentage": 26.73, "elapsed_time": "0:29:55", "remaining_time": "1:22:01", "throughput": 1032.12, "total_tokens": 1852976} {"current_steps": 20575, "total_steps": 76960, "loss": 0.3127, "lr": 4.585515294653609e-05, "epoch": 5.346933471933472, "percentage": 26.73, "elapsed_time": "0:29:55", "remaining_time": "1:22:01", "throughput": 1032.12, "total_tokens": 1853408} {"current_steps": 20580, "total_steps": 76960, "loss": 0.185, "lr": 4.585202589439964e-05, "epoch": 5.348232848232848, "percentage": 26.74, "elapsed_time": "0:29:56", "remaining_time": "1:22:00", "throughput": 1032.12, "total_tokens": 1853856} {"current_steps": 20585, "total_steps": 76960, "loss": 0.26, "lr": 4.5848897769823515e-05, "epoch": 5.349532224532225, "percentage": 26.75, "elapsed_time": "0:29:56", "remaining_time": "1:22:00", "throughput": 1032.14, "total_tokens": 1854320} {"current_steps": 20590, "total_steps": 76960, "loss": 0.1689, "lr": 4.5845768572968607e-05, "epoch": 5.350831600831601, "percentage": 26.75, "elapsed_time": "0:29:56", "remaining_time": "1:21:59", "throughput": 1032.13, "total_tokens": 1854736} {"current_steps": 20595, "total_steps": 76960, "loss": 0.2903, "lr": 4.584263830399585e-05, "epoch": 5.352130977130977, "percentage": 26.76, "elapsed_time": "0:29:57", "remaining_time": "1:21:59", "throughput": 1032.17, "total_tokens": 1855232} {"current_steps": 20600, "total_steps": 76960, "loss": 0.1629, "lr": 4.5839506963066226e-05, "epoch": 5.353430353430354, "percentage": 26.77, "elapsed_time": "0:29:57", "remaining_time": "1:21:58", "throughput": 1032.15, "total_tokens": 1855632} {"current_steps": 20605, "total_steps": 76960, "loss": 0.4521, "lr": 4.58363745503408e-05, "epoch": 5.35472972972973, "percentage": 26.77, "elapsed_time": "0:29:58", "remaining_time": "1:21:58", "throughput": 1032.16, "total_tokens": 1856080} {"current_steps": 20610, "total_steps": 76960, "loss": 0.2318, "lr": 4.583324106598066e-05, "epoch": 5.356029106029106, "percentage": 26.78, "elapsed_time": "0:29:58", "remaining_time": "1:21:57", "throughput": 1032.15, "total_tokens": 1856496} {"current_steps": 20615, "total_steps": 76960, "loss": 0.2483, "lr": 4.5830106510146975e-05, "epoch": 5.357328482328482, "percentage": 26.79, "elapsed_time": "0:29:59", "remaining_time": "1:21:57", "throughput": 1032.15, "total_tokens": 1856928} {"current_steps": 20620, "total_steps": 76960, "loss": 0.2036, "lr": 4.582697088300095e-05, "epoch": 5.358627858627859, "percentage": 26.79, "elapsed_time": "0:29:59", "remaining_time": "1:21:56", "throughput": 1032.15, "total_tokens": 1857360} {"current_steps": 20625, "total_steps": 76960, "loss": 0.1689, "lr": 4.582383418470386e-05, "epoch": 5.359927234927235, "percentage": 26.8, "elapsed_time": "0:29:59", "remaining_time": "1:21:56", "throughput": 1032.16, "total_tokens": 1857808} {"current_steps": 20630, "total_steps": 76960, "loss": 0.2135, "lr": 4.582069641541702e-05, "epoch": 5.361226611226611, "percentage": 26.81, "elapsed_time": "0:30:00", "remaining_time": "1:21:55", "throughput": 1032.15, "total_tokens": 1858224} {"current_steps": 20635, "total_steps": 76960, "loss": 0.2137, "lr": 4.581755757530182e-05, "epoch": 5.362525987525988, "percentage": 26.81, "elapsed_time": "0:30:00", "remaining_time": "1:21:55", "throughput": 1032.17, "total_tokens": 1858704} {"current_steps": 20640, "total_steps": 76960, "loss": 0.3787, "lr": 4.581441766451968e-05, "epoch": 5.363825363825364, "percentage": 26.82, "elapsed_time": "0:30:01", "remaining_time": "1:21:54", "throughput": 1032.17, "total_tokens": 1859120} {"current_steps": 20645, "total_steps": 76960, "loss": 0.2054, "lr": 4.5811276683232104e-05, "epoch": 5.36512474012474, "percentage": 26.83, "elapsed_time": "0:30:01", "remaining_time": "1:21:54", "throughput": 1032.16, "total_tokens": 1859536} {"current_steps": 20650, "total_steps": 76960, "loss": 0.2295, "lr": 4.580813463160063e-05, "epoch": 5.366424116424117, "percentage": 26.83, "elapsed_time": "0:30:02", "remaining_time": "1:21:53", "throughput": 1032.18, "total_tokens": 1860016} {"current_steps": 20655, "total_steps": 76960, "loss": 0.2466, "lr": 4.580499150978685e-05, "epoch": 5.367723492723493, "percentage": 26.84, "elapsed_time": "0:30:02", "remaining_time": "1:21:53", "throughput": 1032.22, "total_tokens": 1860512} {"current_steps": 20660, "total_steps": 76960, "loss": 0.2167, "lr": 4.580184731795242e-05, "epoch": 5.369022869022869, "percentage": 26.85, "elapsed_time": "0:30:02", "remaining_time": "1:21:52", "throughput": 1032.22, "total_tokens": 1860944} {"current_steps": 20665, "total_steps": 76960, "loss": 0.2905, "lr": 4.579870205625905e-05, "epoch": 5.370322245322245, "percentage": 26.85, "elapsed_time": "0:30:03", "remaining_time": "1:21:52", "throughput": 1032.23, "total_tokens": 1861392} {"current_steps": 20670, "total_steps": 76960, "loss": 0.2858, "lr": 4.579555572486851e-05, "epoch": 5.371621621621622, "percentage": 26.86, "elapsed_time": "0:30:03", "remaining_time": "1:21:51", "throughput": 1032.24, "total_tokens": 1861840} {"current_steps": 20675, "total_steps": 76960, "loss": 0.2526, "lr": 4.5792408323942615e-05, "epoch": 5.372920997920998, "percentage": 26.86, "elapsed_time": "0:30:04", "remaining_time": "1:21:51", "throughput": 1032.24, "total_tokens": 1862272} {"current_steps": 20680, "total_steps": 76960, "loss": 0.1911, "lr": 4.5789259853643226e-05, "epoch": 5.374220374220374, "percentage": 26.87, "elapsed_time": "0:30:04", "remaining_time": "1:21:50", "throughput": 1032.26, "total_tokens": 1862736} {"current_steps": 20685, "total_steps": 76960, "loss": 0.1812, "lr": 4.57861103141323e-05, "epoch": 5.37551975051975, "percentage": 26.88, "elapsed_time": "0:30:04", "remaining_time": "1:21:50", "throughput": 1032.3, "total_tokens": 1863248} {"current_steps": 20690, "total_steps": 76960, "loss": 0.2167, "lr": 4.578295970557179e-05, "epoch": 5.376819126819127, "percentage": 26.88, "elapsed_time": "0:30:05", "remaining_time": "1:21:49", "throughput": 1032.3, "total_tokens": 1863680} {"current_steps": 20695, "total_steps": 76960, "loss": 0.1571, "lr": 4.577980802812376e-05, "epoch": 5.378118503118503, "percentage": 26.89, "elapsed_time": "0:30:05", "remaining_time": "1:21:49", "throughput": 1032.3, "total_tokens": 1864112} {"current_steps": 20700, "total_steps": 76960, "loss": 0.2283, "lr": 4.577665528195029e-05, "epoch": 5.379417879417879, "percentage": 26.9, "elapsed_time": "0:30:06", "remaining_time": "1:21:49", "throughput": 1032.33, "total_tokens": 1864592} {"current_steps": 20705, "total_steps": 76960, "loss": 0.219, "lr": 4.577350146721353e-05, "epoch": 5.380717255717256, "percentage": 26.9, "elapsed_time": "0:30:06", "remaining_time": "1:21:48", "throughput": 1032.33, "total_tokens": 1865024} {"current_steps": 20710, "total_steps": 76960, "loss": 0.2859, "lr": 4.577034658407568e-05, "epoch": 5.382016632016632, "percentage": 26.91, "elapsed_time": "0:30:07", "remaining_time": "1:21:48", "throughput": 1032.33, "total_tokens": 1865456} {"current_steps": 20715, "total_steps": 76960, "loss": 0.2345, "lr": 4.576719063269901e-05, "epoch": 5.383316008316008, "percentage": 26.92, "elapsed_time": "0:30:07", "remaining_time": "1:21:47", "throughput": 1032.33, "total_tokens": 1865888} {"current_steps": 20720, "total_steps": 76960, "loss": 0.1502, "lr": 4.5764033613245824e-05, "epoch": 5.384615384615385, "percentage": 26.92, "elapsed_time": "0:30:07", "remaining_time": "1:21:47", "throughput": 1032.34, "total_tokens": 1866352} {"current_steps": 20725, "total_steps": 76960, "loss": 0.2563, "lr": 4.57608755258785e-05, "epoch": 5.385914760914761, "percentage": 26.93, "elapsed_time": "0:30:08", "remaining_time": "1:21:46", "throughput": 1032.34, "total_tokens": 1866784} {"current_steps": 20730, "total_steps": 76960, "loss": 0.2547, "lr": 4.5757716370759455e-05, "epoch": 5.387214137214137, "percentage": 26.94, "elapsed_time": "0:30:08", "remaining_time": "1:21:46", "throughput": 1032.34, "total_tokens": 1867200} {"current_steps": 20735, "total_steps": 76960, "loss": 0.252, "lr": 4.5754556148051165e-05, "epoch": 5.388513513513513, "percentage": 26.94, "elapsed_time": "0:30:09", "remaining_time": "1:21:45", "throughput": 1032.35, "total_tokens": 1867648} {"current_steps": 20740, "total_steps": 76960, "loss": 0.2699, "lr": 4.575139485791616e-05, "epoch": 5.38981288981289, "percentage": 26.95, "elapsed_time": "0:30:09", "remaining_time": "1:21:45", "throughput": 1032.34, "total_tokens": 1868064} {"current_steps": 20745, "total_steps": 76960, "loss": 0.3227, "lr": 4.574823250051704e-05, "epoch": 5.391112266112266, "percentage": 26.96, "elapsed_time": "0:30:09", "remaining_time": "1:21:44", "throughput": 1032.37, "total_tokens": 1868560} {"current_steps": 20750, "total_steps": 76960, "loss": 0.204, "lr": 4.574506907601644e-05, "epoch": 5.392411642411642, "percentage": 26.96, "elapsed_time": "0:30:10", "remaining_time": "1:21:44", "throughput": 1032.37, "total_tokens": 1868992} {"current_steps": 20755, "total_steps": 76960, "loss": 0.272, "lr": 4.5741904584577065e-05, "epoch": 5.393711018711019, "percentage": 26.97, "elapsed_time": "0:30:10", "remaining_time": "1:21:43", "throughput": 1032.37, "total_tokens": 1869424} {"current_steps": 20760, "total_steps": 76960, "loss": 0.2844, "lr": 4.573873902636167e-05, "epoch": 5.395010395010395, "percentage": 26.98, "elapsed_time": "0:30:11", "remaining_time": "1:21:43", "throughput": 1032.39, "total_tokens": 1869888} {"current_steps": 20765, "total_steps": 76960, "loss": 0.2057, "lr": 4.573557240153305e-05, "epoch": 5.396309771309771, "percentage": 26.98, "elapsed_time": "0:30:11", "remaining_time": "1:21:42", "throughput": 1032.38, "total_tokens": 1870304} {"current_steps": 20770, "total_steps": 76960, "loss": 0.2095, "lr": 4.573240471025406e-05, "epoch": 5.397609147609147, "percentage": 26.99, "elapsed_time": "0:30:12", "remaining_time": "1:21:42", "throughput": 1032.38, "total_tokens": 1870736} {"current_steps": 20775, "total_steps": 76960, "loss": 0.2598, "lr": 4.572923595268764e-05, "epoch": 5.398908523908524, "percentage": 26.99, "elapsed_time": "0:30:12", "remaining_time": "1:21:41", "throughput": 1032.38, "total_tokens": 1871168} {"current_steps": 20780, "total_steps": 76960, "loss": 0.1591, "lr": 4.5726066128996765e-05, "epoch": 5.4002079002079, "percentage": 27.0, "elapsed_time": "0:30:12", "remaining_time": "1:21:41", "throughput": 1032.39, "total_tokens": 1871616} {"current_steps": 20785, "total_steps": 76960, "loss": 0.2186, "lr": 4.5722895239344435e-05, "epoch": 5.401507276507276, "percentage": 27.01, "elapsed_time": "0:30:13", "remaining_time": "1:21:40", "throughput": 1032.39, "total_tokens": 1872048} {"current_steps": 20790, "total_steps": 76960, "loss": 0.3849, "lr": 4.5719723283893756e-05, "epoch": 5.402806652806653, "percentage": 27.01, "elapsed_time": "0:30:13", "remaining_time": "1:21:40", "throughput": 1032.41, "total_tokens": 1872512} {"current_steps": 20795, "total_steps": 76960, "loss": 0.2328, "lr": 4.5716550262807854e-05, "epoch": 5.404106029106029, "percentage": 27.02, "elapsed_time": "0:30:14", "remaining_time": "1:21:39", "throughput": 1032.42, "total_tokens": 1872960} {"current_steps": 20800, "total_steps": 76960, "loss": 0.2093, "lr": 4.571337617624992e-05, "epoch": 5.405405405405405, "percentage": 27.03, "elapsed_time": "0:30:14", "remaining_time": "1:21:39", "throughput": 1032.42, "total_tokens": 1873408} {"current_steps": 20805, "total_steps": 76960, "loss": 0.2304, "lr": 4.57102010243832e-05, "epoch": 5.406704781704781, "percentage": 27.03, "elapsed_time": "0:30:14", "remaining_time": "1:21:38", "throughput": 1032.42, "total_tokens": 1873840} {"current_steps": 20810, "total_steps": 76960, "loss": 0.2493, "lr": 4.5707024807371e-05, "epoch": 5.408004158004158, "percentage": 27.04, "elapsed_time": "0:30:15", "remaining_time": "1:21:38", "throughput": 1032.4, "total_tokens": 1874240} {"current_steps": 20815, "total_steps": 76960, "loss": 0.2584, "lr": 4.570384752537668e-05, "epoch": 5.409303534303534, "percentage": 27.05, "elapsed_time": "0:30:15", "remaining_time": "1:21:37", "throughput": 1032.42, "total_tokens": 1874704} {"current_steps": 20820, "total_steps": 76960, "loss": 0.2166, "lr": 4.5700669178563635e-05, "epoch": 5.41060291060291, "percentage": 27.05, "elapsed_time": "0:30:16", "remaining_time": "1:21:37", "throughput": 1032.42, "total_tokens": 1875136} {"current_steps": 20825, "total_steps": 76960, "loss": 0.22, "lr": 4.569748976709535e-05, "epoch": 5.411902286902287, "percentage": 27.06, "elapsed_time": "0:30:16", "remaining_time": "1:21:36", "throughput": 1032.42, "total_tokens": 1875568} {"current_steps": 20830, "total_steps": 76960, "loss": 0.3185, "lr": 4.5694309291135326e-05, "epoch": 5.413201663201663, "percentage": 27.07, "elapsed_time": "0:30:17", "remaining_time": "1:21:36", "throughput": 1032.44, "total_tokens": 1876032} {"current_steps": 20835, "total_steps": 76960, "loss": 0.3416, "lr": 4.569112775084715e-05, "epoch": 5.414501039501039, "percentage": 27.07, "elapsed_time": "0:30:17", "remaining_time": "1:21:35", "throughput": 1032.43, "total_tokens": 1876448} {"current_steps": 20840, "total_steps": 76960, "loss": 0.2653, "lr": 4.568794514639445e-05, "epoch": 5.415800415800415, "percentage": 27.08, "elapsed_time": "0:30:17", "remaining_time": "1:21:35", "throughput": 1032.43, "total_tokens": 1876880} {"current_steps": 20845, "total_steps": 76960, "loss": 0.2534, "lr": 4.568476147794091e-05, "epoch": 5.417099792099792, "percentage": 27.09, "elapsed_time": "0:30:18", "remaining_time": "1:21:35", "throughput": 1032.44, "total_tokens": 1877328} {"current_steps": 20850, "total_steps": 76960, "loss": 0.2064, "lr": 4.568157674565027e-05, "epoch": 5.418399168399168, "percentage": 27.09, "elapsed_time": "0:30:18", "remaining_time": "1:21:34", "throughput": 1032.45, "total_tokens": 1877776} {"current_steps": 20855, "total_steps": 76960, "loss": 0.2386, "lr": 4.567839094968631e-05, "epoch": 5.419698544698544, "percentage": 27.1, "elapsed_time": "0:30:19", "remaining_time": "1:21:34", "throughput": 1032.47, "total_tokens": 1878256} {"current_steps": 20860, "total_steps": 76960, "loss": 0.3003, "lr": 4.5675204090212895e-05, "epoch": 5.420997920997921, "percentage": 27.1, "elapsed_time": "0:30:19", "remaining_time": "1:21:33", "throughput": 1032.49, "total_tokens": 1878720} {"current_steps": 20865, "total_steps": 76960, "loss": 0.2519, "lr": 4.567201616739393e-05, "epoch": 5.422297297297297, "percentage": 27.11, "elapsed_time": "0:30:20", "remaining_time": "1:21:33", "throughput": 1032.5, "total_tokens": 1879168} {"current_steps": 20870, "total_steps": 76960, "loss": 0.3422, "lr": 4.566882718139336e-05, "epoch": 5.423596673596673, "percentage": 27.12, "elapsed_time": "0:30:20", "remaining_time": "1:21:32", "throughput": 1032.51, "total_tokens": 1879616} {"current_steps": 20875, "total_steps": 76960, "loss": 0.2402, "lr": 4.56656371323752e-05, "epoch": 5.42489604989605, "percentage": 27.12, "elapsed_time": "0:30:20", "remaining_time": "1:21:32", "throughput": 1032.51, "total_tokens": 1880048} {"current_steps": 20880, "total_steps": 76960, "loss": 0.2847, "lr": 4.5662446020503535e-05, "epoch": 5.426195426195426, "percentage": 27.13, "elapsed_time": "0:30:21", "remaining_time": "1:21:31", "throughput": 1032.52, "total_tokens": 1880496} {"current_steps": 20885, "total_steps": 76960, "loss": 0.8448, "lr": 4.5659253845942473e-05, "epoch": 5.427494802494802, "percentage": 27.14, "elapsed_time": "0:30:21", "remaining_time": "1:21:31", "throughput": 1032.54, "total_tokens": 1880960} {"current_steps": 20890, "total_steps": 76960, "loss": 0.2172, "lr": 4.5656060608856175e-05, "epoch": 5.4287941787941785, "percentage": 27.14, "elapsed_time": "0:30:22", "remaining_time": "1:21:30", "throughput": 1032.53, "total_tokens": 1881376} {"current_steps": 20895, "total_steps": 76960, "loss": 0.3992, "lr": 4.56528663094089e-05, "epoch": 5.430093555093555, "percentage": 27.15, "elapsed_time": "0:30:22", "remaining_time": "1:21:30", "throughput": 1032.56, "total_tokens": 1881856} {"current_steps": 20900, "total_steps": 76960, "loss": 0.2415, "lr": 4.564967094776492e-05, "epoch": 5.4313929313929314, "percentage": 27.16, "elapsed_time": "0:30:22", "remaining_time": "1:21:29", "throughput": 1032.58, "total_tokens": 1882320} {"current_steps": 20905, "total_steps": 76960, "loss": 0.2938, "lr": 4.564647452408858e-05, "epoch": 5.4326923076923075, "percentage": 27.16, "elapsed_time": "0:30:23", "remaining_time": "1:21:29", "throughput": 1032.58, "total_tokens": 1882752} {"current_steps": 20910, "total_steps": 76960, "loss": 0.2772, "lr": 4.5643277038544276e-05, "epoch": 5.4339916839916835, "percentage": 27.17, "elapsed_time": "0:30:23", "remaining_time": "1:21:28", "throughput": 1032.59, "total_tokens": 1883216} {"current_steps": 20915, "total_steps": 76960, "loss": 0.3091, "lr": 4.5640078491296447e-05, "epoch": 5.4352910602910605, "percentage": 27.18, "elapsed_time": "0:30:24", "remaining_time": "1:21:28", "throughput": 1032.6, "total_tokens": 1883664} {"current_steps": 20920, "total_steps": 76960, "loss": 0.2598, "lr": 4.5636878882509604e-05, "epoch": 5.4365904365904365, "percentage": 27.18, "elapsed_time": "0:30:24", "remaining_time": "1:21:27", "throughput": 1032.62, "total_tokens": 1884128} {"current_steps": 20925, "total_steps": 76960, "loss": 0.231, "lr": 4.563367821234831e-05, "epoch": 5.4378898128898125, "percentage": 27.19, "elapsed_time": "0:30:25", "remaining_time": "1:21:27", "throughput": 1032.64, "total_tokens": 1884592} {"current_steps": 20930, "total_steps": 76960, "loss": 0.2221, "lr": 4.563047648097717e-05, "epoch": 5.4391891891891895, "percentage": 27.2, "elapsed_time": "0:30:25", "remaining_time": "1:21:26", "throughput": 1032.66, "total_tokens": 1885056} {"current_steps": 20935, "total_steps": 76960, "loss": 0.3619, "lr": 4.562727368856087e-05, "epoch": 5.4404885654885655, "percentage": 27.2, "elapsed_time": "0:30:25", "remaining_time": "1:21:26", "throughput": 1032.65, "total_tokens": 1885472} {"current_steps": 20940, "total_steps": 76960, "loss": 0.2268, "lr": 4.5624069835264106e-05, "epoch": 5.441787941787942, "percentage": 27.21, "elapsed_time": "0:30:26", "remaining_time": "1:21:25", "throughput": 1032.7, "total_tokens": 1885984} {"current_steps": 20945, "total_steps": 76960, "loss": 0.2818, "lr": 4.562086492125167e-05, "epoch": 5.4430873180873185, "percentage": 27.22, "elapsed_time": "0:30:26", "remaining_time": "1:21:25", "throughput": 1032.72, "total_tokens": 1886464} {"current_steps": 20950, "total_steps": 76960, "loss": 0.2125, "lr": 4.56176589466884e-05, "epoch": 5.4443866943866945, "percentage": 27.22, "elapsed_time": "0:30:27", "remaining_time": "1:21:24", "throughput": 1032.73, "total_tokens": 1886912} {"current_steps": 20955, "total_steps": 76960, "loss": 0.2193, "lr": 4.561445191173918e-05, "epoch": 5.445686070686071, "percentage": 27.23, "elapsed_time": "0:30:27", "remaining_time": "1:21:24", "throughput": 1032.75, "total_tokens": 1887376} {"current_steps": 20960, "total_steps": 76960, "loss": 0.2434, "lr": 4.561124381656894e-05, "epoch": 5.446985446985447, "percentage": 27.23, "elapsed_time": "0:30:27", "remaining_time": "1:21:23", "throughput": 1032.75, "total_tokens": 1887808} {"current_steps": 20965, "total_steps": 76960, "loss": 0.2006, "lr": 4.560803466134268e-05, "epoch": 5.4482848232848236, "percentage": 27.24, "elapsed_time": "0:30:28", "remaining_time": "1:21:23", "throughput": 1032.76, "total_tokens": 1888272} {"current_steps": 20970, "total_steps": 76960, "loss": 0.2028, "lr": 4.560482444622546e-05, "epoch": 5.4495841995842, "percentage": 27.25, "elapsed_time": "0:30:28", "remaining_time": "1:21:22", "throughput": 1032.78, "total_tokens": 1888736} {"current_steps": 20975, "total_steps": 76960, "loss": 0.3131, "lr": 4.560161317138236e-05, "epoch": 5.450883575883576, "percentage": 27.25, "elapsed_time": "0:30:29", "remaining_time": "1:21:22", "throughput": 1032.77, "total_tokens": 1889168} {"current_steps": 20980, "total_steps": 76960, "loss": 0.3052, "lr": 4.559840083697857e-05, "epoch": 5.452182952182953, "percentage": 27.26, "elapsed_time": "0:30:29", "remaining_time": "1:21:21", "throughput": 1032.79, "total_tokens": 1889632} {"current_steps": 20985, "total_steps": 76960, "loss": 0.2285, "lr": 4.559518744317929e-05, "epoch": 5.453482328482329, "percentage": 27.27, "elapsed_time": "0:30:30", "remaining_time": "1:21:21", "throughput": 1032.8, "total_tokens": 1890096} {"current_steps": 20990, "total_steps": 76960, "loss": 0.2241, "lr": 4.559197299014977e-05, "epoch": 5.454781704781705, "percentage": 27.27, "elapsed_time": "0:30:30", "remaining_time": "1:21:21", "throughput": 1032.79, "total_tokens": 1890512} {"current_steps": 20995, "total_steps": 76960, "loss": 0.2631, "lr": 4.558875747805537e-05, "epoch": 5.456081081081081, "percentage": 27.28, "elapsed_time": "0:30:30", "remaining_time": "1:21:20", "throughput": 1032.79, "total_tokens": 1890944} {"current_steps": 21000, "total_steps": 76960, "loss": 0.3014, "lr": 4.558554090706143e-05, "epoch": 5.457380457380458, "percentage": 27.29, "elapsed_time": "0:30:31", "remaining_time": "1:21:20", "throughput": 1032.8, "total_tokens": 1891392} {"current_steps": 21005, "total_steps": 76960, "loss": 0.2301, "lr": 4.55823232773334e-05, "epoch": 5.458679833679834, "percentage": 27.29, "elapsed_time": "0:30:31", "remaining_time": "1:21:19", "throughput": 1032.81, "total_tokens": 1891840} {"current_steps": 21010, "total_steps": 76960, "loss": 0.2867, "lr": 4.5579104589036764e-05, "epoch": 5.45997920997921, "percentage": 27.3, "elapsed_time": "0:30:32", "remaining_time": "1:21:19", "throughput": 1032.83, "total_tokens": 1892304} {"current_steps": 21015, "total_steps": 76960, "loss": 0.2231, "lr": 4.557588484233706e-05, "epoch": 5.461278586278587, "percentage": 27.31, "elapsed_time": "0:30:32", "remaining_time": "1:21:18", "throughput": 1032.83, "total_tokens": 1892736} {"current_steps": 21020, "total_steps": 76960, "loss": 0.1881, "lr": 4.5572664037399886e-05, "epoch": 5.462577962577963, "percentage": 27.31, "elapsed_time": "0:30:32", "remaining_time": "1:21:18", "throughput": 1032.86, "total_tokens": 1893216} {"current_steps": 21025, "total_steps": 76960, "loss": 0.2751, "lr": 4.556944217439088e-05, "epoch": 5.463877338877339, "percentage": 27.32, "elapsed_time": "0:30:33", "remaining_time": "1:21:17", "throughput": 1032.88, "total_tokens": 1893680} {"current_steps": 21030, "total_steps": 76960, "loss": 0.1993, "lr": 4.556621925347577e-05, "epoch": 5.465176715176715, "percentage": 27.33, "elapsed_time": "0:30:33", "remaining_time": "1:21:17", "throughput": 1032.88, "total_tokens": 1894112} {"current_steps": 21035, "total_steps": 76960, "loss": 0.2916, "lr": 4.5562995274820284e-05, "epoch": 5.466476091476092, "percentage": 27.33, "elapsed_time": "0:30:34", "remaining_time": "1:21:16", "throughput": 1032.88, "total_tokens": 1894544} {"current_steps": 21040, "total_steps": 76960, "loss": 0.3365, "lr": 4.5559770238590264e-05, "epoch": 5.467775467775468, "percentage": 27.34, "elapsed_time": "0:30:34", "remaining_time": "1:21:16", "throughput": 1032.87, "total_tokens": 1894960} {"current_steps": 21045, "total_steps": 76960, "loss": 0.2238, "lr": 4.555654414495155e-05, "epoch": 5.469074844074844, "percentage": 27.35, "elapsed_time": "0:30:35", "remaining_time": "1:21:15", "throughput": 1032.86, "total_tokens": 1895376} {"current_steps": 21050, "total_steps": 76960, "loss": 0.247, "lr": 4.5553316994070074e-05, "epoch": 5.470374220374221, "percentage": 27.35, "elapsed_time": "0:30:35", "remaining_time": "1:21:15", "throughput": 1032.88, "total_tokens": 1895840} {"current_steps": 21055, "total_steps": 76960, "loss": 0.159, "lr": 4.5550088786111814e-05, "epoch": 5.471673596673597, "percentage": 27.36, "elapsed_time": "0:30:35", "remaining_time": "1:21:14", "throughput": 1032.89, "total_tokens": 1896288} {"current_steps": 21060, "total_steps": 76960, "loss": 0.314, "lr": 4.55468595212428e-05, "epoch": 5.472972972972973, "percentage": 27.36, "elapsed_time": "0:30:36", "remaining_time": "1:21:14", "throughput": 1032.91, "total_tokens": 1896752} {"current_steps": 21065, "total_steps": 76960, "loss": 0.2323, "lr": 4.554362919962911e-05, "epoch": 5.474272349272349, "percentage": 27.37, "elapsed_time": "0:30:36", "remaining_time": "1:21:13", "throughput": 1032.93, "total_tokens": 1897216} {"current_steps": 21070, "total_steps": 76960, "loss": 0.2178, "lr": 4.5540397821436886e-05, "epoch": 5.475571725571726, "percentage": 27.38, "elapsed_time": "0:30:37", "remaining_time": "1:21:13", "throughput": 1032.94, "total_tokens": 1897680} {"current_steps": 21075, "total_steps": 76960, "loss": 0.2239, "lr": 4.553716538683232e-05, "epoch": 5.476871101871102, "percentage": 27.38, "elapsed_time": "0:30:37", "remaining_time": "1:21:12", "throughput": 1032.95, "total_tokens": 1898128} {"current_steps": 21080, "total_steps": 76960, "loss": 0.2562, "lr": 4.553393189598167e-05, "epoch": 5.478170478170478, "percentage": 27.39, "elapsed_time": "0:30:37", "remaining_time": "1:21:12", "throughput": 1032.96, "total_tokens": 1898576} {"current_steps": 21085, "total_steps": 76960, "loss": 0.2773, "lr": 4.553069734905122e-05, "epoch": 5.479469854469855, "percentage": 27.4, "elapsed_time": "0:30:38", "remaining_time": "1:21:11", "throughput": 1032.97, "total_tokens": 1899024} {"current_steps": 21090, "total_steps": 76960, "loss": 0.2173, "lr": 4.5527461746207337e-05, "epoch": 5.480769230769231, "percentage": 27.4, "elapsed_time": "0:30:38", "remaining_time": "1:21:11", "throughput": 1032.98, "total_tokens": 1899472} {"current_steps": 21095, "total_steps": 76960, "loss": 0.2125, "lr": 4.5524225087616426e-05, "epoch": 5.482068607068607, "percentage": 27.41, "elapsed_time": "0:30:39", "remaining_time": "1:21:10", "throughput": 1032.97, "total_tokens": 1899888} {"current_steps": 21100, "total_steps": 76960, "loss": 0.2984, "lr": 4.552098737344496e-05, "epoch": 5.483367983367984, "percentage": 27.42, "elapsed_time": "0:30:39", "remaining_time": "1:21:10", "throughput": 1032.97, "total_tokens": 1900320} {"current_steps": 21105, "total_steps": 76960, "loss": 0.2142, "lr": 4.5517748603859435e-05, "epoch": 5.48466735966736, "percentage": 27.42, "elapsed_time": "0:30:40", "remaining_time": "1:21:09", "throughput": 1032.98, "total_tokens": 1900768} {"current_steps": 21110, "total_steps": 76960, "loss": 0.2257, "lr": 4.5514508779026455e-05, "epoch": 5.485966735966736, "percentage": 27.43, "elapsed_time": "0:30:40", "remaining_time": "1:21:09", "throughput": 1033.01, "total_tokens": 1901248} {"current_steps": 21115, "total_steps": 76960, "loss": 0.3147, "lr": 4.551126789911263e-05, "epoch": 5.487266112266112, "percentage": 27.44, "elapsed_time": "0:30:40", "remaining_time": "1:21:08", "throughput": 1033.01, "total_tokens": 1901680} {"current_steps": 21120, "total_steps": 76960, "loss": 0.2322, "lr": 4.550802596428464e-05, "epoch": 5.488565488565489, "percentage": 27.44, "elapsed_time": "0:30:41", "remaining_time": "1:21:08", "throughput": 1033.02, "total_tokens": 1902128} {"current_steps": 21125, "total_steps": 76960, "loss": 0.2682, "lr": 4.550478297470922e-05, "epoch": 5.489864864864865, "percentage": 27.45, "elapsed_time": "0:30:41", "remaining_time": "1:21:07", "throughput": 1033.04, "total_tokens": 1902592} {"current_steps": 21130, "total_steps": 76960, "loss": 0.2563, "lr": 4.550153893055317e-05, "epoch": 5.491164241164241, "percentage": 27.46, "elapsed_time": "0:30:42", "remaining_time": "1:21:07", "throughput": 1033.03, "total_tokens": 1903008} {"current_steps": 21135, "total_steps": 76960, "loss": 0.1402, "lr": 4.549829383198333e-05, "epoch": 5.492463617463617, "percentage": 27.46, "elapsed_time": "0:30:42", "remaining_time": "1:21:06", "throughput": 1033.04, "total_tokens": 1903456} {"current_steps": 21140, "total_steps": 76960, "loss": 0.2209, "lr": 4.54950476791666e-05, "epoch": 5.493762993762994, "percentage": 27.47, "elapsed_time": "0:30:43", "remaining_time": "1:21:06", "throughput": 1033.06, "total_tokens": 1903936} {"current_steps": 21145, "total_steps": 76960, "loss": 0.3232, "lr": 4.549180047226993e-05, "epoch": 5.49506237006237, "percentage": 27.48, "elapsed_time": "0:30:43", "remaining_time": "1:21:05", "throughput": 1033.09, "total_tokens": 1904416} {"current_steps": 21150, "total_steps": 76960, "loss": 0.1255, "lr": 4.5488552211460324e-05, "epoch": 5.496361746361746, "percentage": 27.48, "elapsed_time": "0:30:43", "remaining_time": "1:21:05", "throughput": 1033.09, "total_tokens": 1904848} {"current_steps": 21155, "total_steps": 76960, "loss": 0.3799, "lr": 4.5485302896904846e-05, "epoch": 5.497661122661123, "percentage": 27.49, "elapsed_time": "0:30:44", "remaining_time": "1:21:04", "throughput": 1033.12, "total_tokens": 1905328} {"current_steps": 21160, "total_steps": 76960, "loss": 0.1919, "lr": 4.5482052528770615e-05, "epoch": 5.498960498960499, "percentage": 27.49, "elapsed_time": "0:30:44", "remaining_time": "1:21:04", "throughput": 1033.14, "total_tokens": 1905808} {"current_steps": 21165, "total_steps": 76960, "loss": 0.3339, "lr": 4.54788011072248e-05, "epoch": 5.500259875259875, "percentage": 27.5, "elapsed_time": "0:30:45", "remaining_time": "1:21:04", "throughput": 1033.15, "total_tokens": 1906256} {"current_steps": 21170, "total_steps": 76960, "loss": 0.1929, "lr": 4.5475548632434616e-05, "epoch": 5.501559251559252, "percentage": 27.51, "elapsed_time": "0:30:45", "remaining_time": "1:21:03", "throughput": 1033.15, "total_tokens": 1906688} {"current_steps": 21175, "total_steps": 76960, "loss": 0.3118, "lr": 4.547229510456735e-05, "epoch": 5.502858627858628, "percentage": 27.51, "elapsed_time": "0:30:45", "remaining_time": "1:21:03", "throughput": 1033.17, "total_tokens": 1907152} {"current_steps": 21180, "total_steps": 76960, "loss": 0.2634, "lr": 4.546904052379033e-05, "epoch": 5.504158004158004, "percentage": 27.52, "elapsed_time": "0:30:46", "remaining_time": "1:21:02", "throughput": 1033.2, "total_tokens": 1907648} {"current_steps": 21185, "total_steps": 76960, "loss": 0.2625, "lr": 4.546578489027095e-05, "epoch": 5.50545738045738, "percentage": 27.53, "elapsed_time": "0:30:46", "remaining_time": "1:21:02", "throughput": 1033.22, "total_tokens": 1908112} {"current_steps": 21190, "total_steps": 76960, "loss": 0.2597, "lr": 4.546252820417664e-05, "epoch": 5.506756756756757, "percentage": 27.53, "elapsed_time": "0:30:47", "remaining_time": "1:21:01", "throughput": 1033.23, "total_tokens": 1908560} {"current_steps": 21195, "total_steps": 76960, "loss": 0.2277, "lr": 4.545927046567489e-05, "epoch": 5.508056133056133, "percentage": 27.54, "elapsed_time": "0:30:47", "remaining_time": "1:21:01", "throughput": 1033.22, "total_tokens": 1908976} {"current_steps": 21200, "total_steps": 76960, "loss": 0.2003, "lr": 4.5456011674933264e-05, "epoch": 5.509355509355509, "percentage": 27.55, "elapsed_time": "0:30:48", "remaining_time": "1:21:00", "throughput": 1033.28, "total_tokens": 1909504} {"current_steps": 21205, "total_steps": 76960, "loss": 0.4303, "lr": 4.545275183211936e-05, "epoch": 5.510654885654886, "percentage": 27.55, "elapsed_time": "0:30:48", "remaining_time": "1:21:00", "throughput": 1033.29, "total_tokens": 1909968} {"current_steps": 21210, "total_steps": 76960, "loss": 0.1889, "lr": 4.5449490937400824e-05, "epoch": 5.511954261954262, "percentage": 27.56, "elapsed_time": "0:30:48", "remaining_time": "1:20:59", "throughput": 1033.29, "total_tokens": 1910400} {"current_steps": 21215, "total_steps": 76960, "loss": 0.2795, "lr": 4.5446228990945385e-05, "epoch": 5.513253638253638, "percentage": 27.57, "elapsed_time": "0:30:49", "remaining_time": "1:20:59", "throughput": 1033.29, "total_tokens": 1910832} {"current_steps": 21220, "total_steps": 76960, "loss": 0.2979, "lr": 4.5442965992920796e-05, "epoch": 5.514553014553014, "percentage": 27.57, "elapsed_time": "0:30:49", "remaining_time": "1:20:58", "throughput": 1033.31, "total_tokens": 1911296} {"current_steps": 21225, "total_steps": 76960, "loss": 0.2686, "lr": 4.543970194349487e-05, "epoch": 5.515852390852391, "percentage": 27.58, "elapsed_time": "0:30:50", "remaining_time": "1:20:58", "throughput": 1033.33, "total_tokens": 1911760} {"current_steps": 21230, "total_steps": 76960, "loss": 0.2993, "lr": 4.5436436842835495e-05, "epoch": 5.517151767151767, "percentage": 27.59, "elapsed_time": "0:30:50", "remaining_time": "1:20:57", "throughput": 1033.34, "total_tokens": 1912208} {"current_steps": 21235, "total_steps": 76960, "loss": 0.2735, "lr": 4.5433170691110596e-05, "epoch": 5.518451143451143, "percentage": 27.59, "elapsed_time": "0:30:50", "remaining_time": "1:20:57", "throughput": 1033.36, "total_tokens": 1912672} {"current_steps": 21240, "total_steps": 76960, "loss": 0.2837, "lr": 4.542990348848814e-05, "epoch": 5.51975051975052, "percentage": 27.6, "elapsed_time": "0:30:51", "remaining_time": "1:20:56", "throughput": 1033.36, "total_tokens": 1913104} {"current_steps": 21245, "total_steps": 76960, "loss": 0.2674, "lr": 4.542663523513618e-05, "epoch": 5.521049896049896, "percentage": 27.61, "elapsed_time": "0:30:51", "remaining_time": "1:20:56", "throughput": 1033.38, "total_tokens": 1913584} {"current_steps": 21250, "total_steps": 76960, "loss": 0.277, "lr": 4.542336593122279e-05, "epoch": 5.522349272349272, "percentage": 27.61, "elapsed_time": "0:30:52", "remaining_time": "1:20:55", "throughput": 1033.41, "total_tokens": 1914080} {"current_steps": 21255, "total_steps": 76960, "loss": 0.2244, "lr": 4.542009557691614e-05, "epoch": 5.523648648648649, "percentage": 27.62, "elapsed_time": "0:30:52", "remaining_time": "1:20:55", "throughput": 1033.41, "total_tokens": 1914496} {"current_steps": 21260, "total_steps": 76960, "loss": 0.2466, "lr": 4.541682417238439e-05, "epoch": 5.524948024948025, "percentage": 27.62, "elapsed_time": "0:30:53", "remaining_time": "1:20:54", "throughput": 1033.41, "total_tokens": 1914944} {"current_steps": 21265, "total_steps": 76960, "loss": 0.3449, "lr": 4.541355171779582e-05, "epoch": 5.526247401247401, "percentage": 27.63, "elapsed_time": "0:30:53", "remaining_time": "1:20:54", "throughput": 1033.41, "total_tokens": 1915376} {"current_steps": 21270, "total_steps": 76960, "loss": 0.2288, "lr": 4.541027821331872e-05, "epoch": 5.527546777546777, "percentage": 27.64, "elapsed_time": "0:30:53", "remaining_time": "1:20:53", "throughput": 1033.43, "total_tokens": 1915824} {"current_steps": 21275, "total_steps": 76960, "loss": 0.2409, "lr": 4.540700365912146e-05, "epoch": 5.528846153846154, "percentage": 27.64, "elapsed_time": "0:30:54", "remaining_time": "1:20:53", "throughput": 1033.43, "total_tokens": 1916272} {"current_steps": 21280, "total_steps": 76960, "loss": 0.9379, "lr": 4.540372805537245e-05, "epoch": 5.53014553014553, "percentage": 27.65, "elapsed_time": "0:30:54", "remaining_time": "1:20:52", "throughput": 1033.46, "total_tokens": 1916752} {"current_steps": 21285, "total_steps": 76960, "loss": 0.2182, "lr": 4.540045140224015e-05, "epoch": 5.531444906444906, "percentage": 27.66, "elapsed_time": "0:30:55", "remaining_time": "1:20:52", "throughput": 1033.47, "total_tokens": 1917200} {"current_steps": 21290, "total_steps": 76960, "loss": 0.225, "lr": 4.539717369989309e-05, "epoch": 5.532744282744282, "percentage": 27.66, "elapsed_time": "0:30:55", "remaining_time": "1:20:51", "throughput": 1033.49, "total_tokens": 1917664} {"current_steps": 21295, "total_steps": 76960, "loss": 0.2146, "lr": 4.539389494849985e-05, "epoch": 5.534043659043659, "percentage": 27.67, "elapsed_time": "0:30:55", "remaining_time": "1:20:51", "throughput": 1033.54, "total_tokens": 1918176} {"current_steps": 21300, "total_steps": 76960, "loss": 0.3524, "lr": 4.5390615148229044e-05, "epoch": 5.535343035343035, "percentage": 27.68, "elapsed_time": "0:30:56", "remaining_time": "1:20:50", "throughput": 1033.55, "total_tokens": 1918624} {"current_steps": 21305, "total_steps": 76960, "loss": 0.2862, "lr": 4.5387334299249366e-05, "epoch": 5.536642411642411, "percentage": 27.68, "elapsed_time": "0:30:56", "remaining_time": "1:20:50", "throughput": 1033.56, "total_tokens": 1919088} {"current_steps": 21310, "total_steps": 76960, "loss": 0.1557, "lr": 4.5384052401729546e-05, "epoch": 5.537941787941788, "percentage": 27.69, "elapsed_time": "0:30:57", "remaining_time": "1:20:50", "throughput": 1033.55, "total_tokens": 1919520} {"current_steps": 21315, "total_steps": 76960, "loss": 0.2576, "lr": 4.538076945583839e-05, "epoch": 5.539241164241164, "percentage": 27.7, "elapsed_time": "0:30:57", "remaining_time": "1:20:49", "throughput": 1033.53, "total_tokens": 1919936} {"current_steps": 21320, "total_steps": 76960, "loss": 0.1252, "lr": 4.537748546174473e-05, "epoch": 5.54054054054054, "percentage": 27.7, "elapsed_time": "0:30:58", "remaining_time": "1:20:49", "throughput": 1033.53, "total_tokens": 1920368} {"current_steps": 21325, "total_steps": 76960, "loss": 0.3532, "lr": 4.537420041961746e-05, "epoch": 5.541839916839917, "percentage": 27.71, "elapsed_time": "0:30:58", "remaining_time": "1:20:48", "throughput": 1033.51, "total_tokens": 1920768} {"current_steps": 21330, "total_steps": 76960, "loss": 0.1029, "lr": 4.537091432962555e-05, "epoch": 5.543139293139293, "percentage": 27.72, "elapsed_time": "0:30:58", "remaining_time": "1:20:48", "throughput": 1033.52, "total_tokens": 1921232} {"current_steps": 21335, "total_steps": 76960, "loss": 0.1618, "lr": 4.5367627191937994e-05, "epoch": 5.544438669438669, "percentage": 27.72, "elapsed_time": "0:30:59", "remaining_time": "1:20:47", "throughput": 1033.54, "total_tokens": 1921696} {"current_steps": 21340, "total_steps": 76960, "loss": 0.3252, "lr": 4.536433900672386e-05, "epoch": 5.545738045738045, "percentage": 27.73, "elapsed_time": "0:30:59", "remaining_time": "1:20:47", "throughput": 1033.53, "total_tokens": 1922128} {"current_steps": 21345, "total_steps": 76960, "loss": 0.2561, "lr": 4.5361049774152256e-05, "epoch": 5.547037422037422, "percentage": 27.74, "elapsed_time": "0:31:00", "remaining_time": "1:20:46", "throughput": 1033.56, "total_tokens": 1922608} {"current_steps": 21350, "total_steps": 76960, "loss": 0.3527, "lr": 4.535775949439235e-05, "epoch": 5.548336798336798, "percentage": 27.74, "elapsed_time": "0:31:00", "remaining_time": "1:20:46", "throughput": 1033.55, "total_tokens": 1923024} {"current_steps": 21355, "total_steps": 76960, "loss": 0.192, "lr": 4.5354468167613366e-05, "epoch": 5.549636174636174, "percentage": 27.75, "elapsed_time": "0:31:01", "remaining_time": "1:20:45", "throughput": 1033.54, "total_tokens": 1923440} {"current_steps": 21360, "total_steps": 76960, "loss": 0.2289, "lr": 4.535117579398459e-05, "epoch": 5.5509355509355505, "percentage": 27.75, "elapsed_time": "0:31:01", "remaining_time": "1:20:45", "throughput": 1033.57, "total_tokens": 1923936} {"current_steps": 21365, "total_steps": 76960, "loss": 0.2223, "lr": 4.534788237367533e-05, "epoch": 5.552234927234927, "percentage": 27.76, "elapsed_time": "0:31:01", "remaining_time": "1:20:44", "throughput": 1033.58, "total_tokens": 1924384} {"current_steps": 21370, "total_steps": 76960, "loss": 0.2226, "lr": 4.5344587906855e-05, "epoch": 5.553534303534303, "percentage": 27.77, "elapsed_time": "0:31:02", "remaining_time": "1:20:44", "throughput": 1033.59, "total_tokens": 1924848} {"current_steps": 21375, "total_steps": 76960, "loss": 0.2313, "lr": 4.534129239369301e-05, "epoch": 5.5548336798336795, "percentage": 27.77, "elapsed_time": "0:31:02", "remaining_time": "1:20:43", "throughput": 1033.59, "total_tokens": 1925280} {"current_steps": 21380, "total_steps": 76960, "loss": 0.2083, "lr": 4.533799583435886e-05, "epoch": 5.556133056133056, "percentage": 27.78, "elapsed_time": "0:31:03", "remaining_time": "1:20:43", "throughput": 1033.62, "total_tokens": 1925760} {"current_steps": 21385, "total_steps": 76960, "loss": 0.3571, "lr": 4.5334698229022096e-05, "epoch": 5.5574324324324325, "percentage": 27.79, "elapsed_time": "0:31:03", "remaining_time": "1:20:42", "throughput": 1033.65, "total_tokens": 1926256} {"current_steps": 21390, "total_steps": 76960, "loss": 0.2491, "lr": 4.533139957785233e-05, "epoch": 5.5587318087318085, "percentage": 27.79, "elapsed_time": "0:31:03", "remaining_time": "1:20:42", "throughput": 1033.67, "total_tokens": 1926736} {"current_steps": 21395, "total_steps": 76960, "loss": 0.2548, "lr": 4.53280998810192e-05, "epoch": 5.560031185031185, "percentage": 27.8, "elapsed_time": "0:31:04", "remaining_time": "1:20:42", "throughput": 1033.69, "total_tokens": 1927200} {"current_steps": 21400, "total_steps": 76960, "loss": 0.2523, "lr": 4.532479913869241e-05, "epoch": 5.5613305613305615, "percentage": 27.81, "elapsed_time": "0:31:04", "remaining_time": "1:20:41", "throughput": 1033.69, "total_tokens": 1927648} {"current_steps": 21405, "total_steps": 76960, "loss": 0.2529, "lr": 4.532149735104173e-05, "epoch": 5.5626299376299375, "percentage": 27.81, "elapsed_time": "0:31:05", "remaining_time": "1:20:41", "throughput": 1033.69, "total_tokens": 1928080} {"current_steps": 21410, "total_steps": 76960, "loss": 0.2738, "lr": 4.531819451823697e-05, "epoch": 5.563929313929314, "percentage": 27.82, "elapsed_time": "0:31:05", "remaining_time": "1:20:40", "throughput": 1033.71, "total_tokens": 1928560} {"current_steps": 21415, "total_steps": 76960, "loss": 0.2539, "lr": 4.5314890640447996e-05, "epoch": 5.5652286902286905, "percentage": 27.83, "elapsed_time": "0:31:06", "remaining_time": "1:20:40", "throughput": 1033.73, "total_tokens": 1929024} {"current_steps": 21420, "total_steps": 76960, "loss": 0.2146, "lr": 4.531158571784473e-05, "epoch": 5.5665280665280665, "percentage": 27.83, "elapsed_time": "0:31:06", "remaining_time": "1:20:39", "throughput": 1033.72, "total_tokens": 1929440} {"current_steps": 21425, "total_steps": 76960, "loss": 0.2866, "lr": 4.530827975059715e-05, "epoch": 5.567827442827443, "percentage": 27.84, "elapsed_time": "0:31:06", "remaining_time": "1:20:39", "throughput": 1033.76, "total_tokens": 1929952} {"current_steps": 21430, "total_steps": 76960, "loss": 0.2585, "lr": 4.530497273887529e-05, "epoch": 5.5691268191268195, "percentage": 27.85, "elapsed_time": "0:31:07", "remaining_time": "1:20:38", "throughput": 1033.76, "total_tokens": 1930384} {"current_steps": 21435, "total_steps": 76960, "loss": 0.1873, "lr": 4.530166468284922e-05, "epoch": 5.5704261954261955, "percentage": 27.85, "elapsed_time": "0:31:07", "remaining_time": "1:20:38", "throughput": 1033.77, "total_tokens": 1930832} {"current_steps": 21440, "total_steps": 76960, "loss": 0.2176, "lr": 4.5298355582689086e-05, "epoch": 5.571725571725572, "percentage": 27.86, "elapsed_time": "0:31:08", "remaining_time": "1:20:37", "throughput": 1033.77, "total_tokens": 1931280} {"current_steps": 21445, "total_steps": 76960, "loss": 0.2161, "lr": 4.529504543856507e-05, "epoch": 5.573024948024948, "percentage": 27.87, "elapsed_time": "0:31:08", "remaining_time": "1:20:37", "throughput": 1033.76, "total_tokens": 1931696} {"current_steps": 21450, "total_steps": 76960, "loss": 0.261, "lr": 4.529173425064743e-05, "epoch": 5.574324324324325, "percentage": 27.87, "elapsed_time": "0:31:09", "remaining_time": "1:20:36", "throughput": 1033.78, "total_tokens": 1932160} {"current_steps": 21455, "total_steps": 76960, "loss": 0.2126, "lr": 4.5288422019106446e-05, "epoch": 5.575623700623701, "percentage": 27.88, "elapsed_time": "0:31:09", "remaining_time": "1:20:36", "throughput": 1033.78, "total_tokens": 1932608} {"current_steps": 21460, "total_steps": 76960, "loss": 0.1605, "lr": 4.528510874411248e-05, "epoch": 5.576923076923077, "percentage": 27.88, "elapsed_time": "0:31:09", "remaining_time": "1:20:35", "throughput": 1033.8, "total_tokens": 1933072} {"current_steps": 21465, "total_steps": 76960, "loss": 0.349, "lr": 4.528179442583594e-05, "epoch": 5.578222453222454, "percentage": 27.89, "elapsed_time": "0:31:10", "remaining_time": "1:20:35", "throughput": 1033.84, "total_tokens": 1933584} {"current_steps": 21470, "total_steps": 76960, "loss": 0.2945, "lr": 4.5278479064447274e-05, "epoch": 5.57952182952183, "percentage": 27.9, "elapsed_time": "0:31:10", "remaining_time": "1:20:34", "throughput": 1033.83, "total_tokens": 1934000} {"current_steps": 21475, "total_steps": 76960, "loss": 0.2573, "lr": 4.527516266011701e-05, "epoch": 5.580821205821206, "percentage": 27.9, "elapsed_time": "0:31:11", "remaining_time": "1:20:34", "throughput": 1033.85, "total_tokens": 1934464} {"current_steps": 21480, "total_steps": 76960, "loss": 0.2181, "lr": 4.527184521301569e-05, "epoch": 5.582120582120583, "percentage": 27.91, "elapsed_time": "0:31:11", "remaining_time": "1:20:33", "throughput": 1033.85, "total_tokens": 1934896} {"current_steps": 21485, "total_steps": 76960, "loss": 0.2515, "lr": 4.526852672331396e-05, "epoch": 5.583419958419959, "percentage": 27.92, "elapsed_time": "0:31:11", "remaining_time": "1:20:33", "throughput": 1033.85, "total_tokens": 1935328} {"current_steps": 21490, "total_steps": 76960, "loss": 0.3201, "lr": 4.526520719118247e-05, "epoch": 5.584719334719335, "percentage": 27.92, "elapsed_time": "0:31:12", "remaining_time": "1:20:32", "throughput": 1033.88, "total_tokens": 1935824} {"current_steps": 21495, "total_steps": 76960, "loss": 0.2602, "lr": 4.5261886616791966e-05, "epoch": 5.586018711018711, "percentage": 27.93, "elapsed_time": "0:31:12", "remaining_time": "1:20:32", "throughput": 1033.87, "total_tokens": 1936256} {"current_steps": 21500, "total_steps": 76960, "loss": 0.2245, "lr": 4.525856500031321e-05, "epoch": 5.587318087318088, "percentage": 27.94, "elapsed_time": "0:31:13", "remaining_time": "1:20:32", "throughput": 1033.89, "total_tokens": 1936736} {"current_steps": 21505, "total_steps": 76960, "loss": 0.313, "lr": 4.5255242341917055e-05, "epoch": 5.588617463617464, "percentage": 27.94, "elapsed_time": "0:31:13", "remaining_time": "1:20:31", "throughput": 1033.89, "total_tokens": 1937184} {"current_steps": 21510, "total_steps": 76960, "loss": 0.272, "lr": 4.525191864177437e-05, "epoch": 5.58991683991684, "percentage": 27.95, "elapsed_time": "0:31:14", "remaining_time": "1:20:31", "throughput": 1033.9, "total_tokens": 1937632} {"current_steps": 21515, "total_steps": 76960, "loss": 0.2571, "lr": 4.524859390005611e-05, "epoch": 5.591216216216216, "percentage": 27.96, "elapsed_time": "0:31:14", "remaining_time": "1:20:30", "throughput": 1033.9, "total_tokens": 1938064} {"current_steps": 21520, "total_steps": 76960, "loss": 0.2345, "lr": 4.524526811693326e-05, "epoch": 5.592515592515593, "percentage": 27.96, "elapsed_time": "0:31:14", "remaining_time": "1:20:30", "throughput": 1033.9, "total_tokens": 1938512} {"current_steps": 21525, "total_steps": 76960, "loss": 0.1998, "lr": 4.524194129257688e-05, "epoch": 5.593814968814969, "percentage": 27.97, "elapsed_time": "0:31:15", "remaining_time": "1:20:29", "throughput": 1033.89, "total_tokens": 1938944} {"current_steps": 21530, "total_steps": 76960, "loss": 0.312, "lr": 4.523861342715806e-05, "epoch": 5.595114345114345, "percentage": 27.98, "elapsed_time": "0:31:15", "remaining_time": "1:20:29", "throughput": 1033.9, "total_tokens": 1939392} {"current_steps": 21535, "total_steps": 76960, "loss": 0.2471, "lr": 4.523528452084795e-05, "epoch": 5.596413721413722, "percentage": 27.98, "elapsed_time": "0:31:16", "remaining_time": "1:20:28", "throughput": 1033.9, "total_tokens": 1939824} {"current_steps": 21540, "total_steps": 76960, "loss": 0.2641, "lr": 4.5231954573817785e-05, "epoch": 5.597713097713098, "percentage": 27.99, "elapsed_time": "0:31:16", "remaining_time": "1:20:28", "throughput": 1033.9, "total_tokens": 1940256} {"current_steps": 21545, "total_steps": 76960, "loss": 0.253, "lr": 4.5228623586238806e-05, "epoch": 5.599012474012474, "percentage": 28.0, "elapsed_time": "0:31:17", "remaining_time": "1:20:27", "throughput": 1033.9, "total_tokens": 1940704} {"current_steps": 21550, "total_steps": 76960, "loss": 0.222, "lr": 4.5225291558282334e-05, "epoch": 5.600311850311851, "percentage": 28.0, "elapsed_time": "0:31:17", "remaining_time": "1:20:27", "throughput": 1033.9, "total_tokens": 1941136} {"current_steps": 21555, "total_steps": 76960, "loss": 0.2922, "lr": 4.522195849011973e-05, "epoch": 5.601611226611227, "percentage": 28.01, "elapsed_time": "0:31:17", "remaining_time": "1:20:26", "throughput": 1033.91, "total_tokens": 1941600} {"current_steps": 21560, "total_steps": 76960, "loss": 0.1808, "lr": 4.521862438192244e-05, "epoch": 5.602910602910603, "percentage": 28.01, "elapsed_time": "0:31:18", "remaining_time": "1:20:26", "throughput": 1033.92, "total_tokens": 1942048} {"current_steps": 21565, "total_steps": 76960, "loss": 0.289, "lr": 4.521528923386191e-05, "epoch": 5.604209979209979, "percentage": 28.02, "elapsed_time": "0:31:18", "remaining_time": "1:20:26", "throughput": 1033.9, "total_tokens": 1942448} {"current_steps": 21570, "total_steps": 76960, "loss": 0.2862, "lr": 4.521195304610969e-05, "epoch": 5.605509355509356, "percentage": 28.03, "elapsed_time": "0:31:19", "remaining_time": "1:20:25", "throughput": 1033.91, "total_tokens": 1942912} {"current_steps": 21575, "total_steps": 76960, "loss": 0.2182, "lr": 4.520861581883736e-05, "epoch": 5.606808731808732, "percentage": 28.03, "elapsed_time": "0:31:19", "remaining_time": "1:20:25", "throughput": 1033.9, "total_tokens": 1943328} {"current_steps": 21580, "total_steps": 76960, "loss": 0.2557, "lr": 4.520527755221656e-05, "epoch": 5.608108108108108, "percentage": 28.04, "elapsed_time": "0:31:20", "remaining_time": "1:20:24", "throughput": 1033.93, "total_tokens": 1943824} {"current_steps": 21585, "total_steps": 76960, "loss": 0.3212, "lr": 4.5201938246418976e-05, "epoch": 5.609407484407484, "percentage": 28.05, "elapsed_time": "0:31:20", "remaining_time": "1:20:24", "throughput": 1033.95, "total_tokens": 1944304} {"current_steps": 21590, "total_steps": 76960, "loss": 0.3023, "lr": 4.519859790161634e-05, "epoch": 5.610706860706861, "percentage": 28.05, "elapsed_time": "0:31:20", "remaining_time": "1:20:23", "throughput": 1033.94, "total_tokens": 1944736} {"current_steps": 21595, "total_steps": 76960, "loss": 0.2673, "lr": 4.519525651798047e-05, "epoch": 5.612006237006237, "percentage": 28.06, "elapsed_time": "0:31:21", "remaining_time": "1:20:23", "throughput": 1033.95, "total_tokens": 1945184} {"current_steps": 21600, "total_steps": 76960, "loss": 0.2657, "lr": 4.519191409568321e-05, "epoch": 5.613305613305613, "percentage": 28.07, "elapsed_time": "0:31:21", "remaining_time": "1:20:22", "throughput": 1033.96, "total_tokens": 1945632} {"current_steps": 21605, "total_steps": 76960, "loss": 0.2516, "lr": 4.5188570634896454e-05, "epoch": 5.61460498960499, "percentage": 28.07, "elapsed_time": "0:31:22", "remaining_time": "1:20:22", "throughput": 1033.96, "total_tokens": 1946080} {"current_steps": 21610, "total_steps": 76960, "loss": 0.2557, "lr": 4.518522613579217e-05, "epoch": 5.615904365904366, "percentage": 28.08, "elapsed_time": "0:31:22", "remaining_time": "1:20:21", "throughput": 1033.98, "total_tokens": 1946544} {"current_steps": 21615, "total_steps": 76960, "loss": 0.3365, "lr": 4.518188059854236e-05, "epoch": 5.617203742203742, "percentage": 28.09, "elapsed_time": "0:31:22", "remaining_time": "1:20:21", "throughput": 1034.0, "total_tokens": 1947008} {"current_steps": 21620, "total_steps": 76960, "loss": 0.237, "lr": 4.5178534023319096e-05, "epoch": 5.618503118503119, "percentage": 28.09, "elapsed_time": "0:31:23", "remaining_time": "1:20:20", "throughput": 1034.0, "total_tokens": 1947440} {"current_steps": 21625, "total_steps": 76960, "loss": 0.226, "lr": 4.5175186410294495e-05, "epoch": 5.619802494802495, "percentage": 28.1, "elapsed_time": "0:31:23", "remaining_time": "1:20:20", "throughput": 1033.99, "total_tokens": 1947856} {"current_steps": 21630, "total_steps": 76960, "loss": 0.2357, "lr": 4.517183775964073e-05, "epoch": 5.621101871101871, "percentage": 28.11, "elapsed_time": "0:31:24", "remaining_time": "1:20:19", "throughput": 1034.0, "total_tokens": 1948288} {"current_steps": 21635, "total_steps": 76960, "loss": 0.1352, "lr": 4.5168488071530015e-05, "epoch": 5.622401247401247, "percentage": 28.11, "elapsed_time": "0:31:24", "remaining_time": "1:20:19", "throughput": 1034.0, "total_tokens": 1948720} {"current_steps": 21640, "total_steps": 76960, "loss": 0.265, "lr": 4.5165137346134634e-05, "epoch": 5.623700623700624, "percentage": 28.12, "elapsed_time": "0:31:25", "remaining_time": "1:20:18", "throughput": 1034.01, "total_tokens": 1949184} {"current_steps": 21645, "total_steps": 76960, "loss": 0.1525, "lr": 4.516178558362692e-05, "epoch": 5.625, "percentage": 28.12, "elapsed_time": "0:31:25", "remaining_time": "1:20:18", "throughput": 1034.02, "total_tokens": 1949632} {"current_steps": 21650, "total_steps": 76960, "loss": 0.2077, "lr": 4.515843278417925e-05, "epoch": 5.626299376299376, "percentage": 28.13, "elapsed_time": "0:31:25", "remaining_time": "1:20:17", "throughput": 1034.03, "total_tokens": 1950064} {"current_steps": 21655, "total_steps": 76960, "loss": 0.2837, "lr": 4.515507894796408e-05, "epoch": 5.627598752598753, "percentage": 28.14, "elapsed_time": "0:31:26", "remaining_time": "1:20:17", "throughput": 1034.03, "total_tokens": 1950496} {"current_steps": 21660, "total_steps": 76960, "loss": 0.2612, "lr": 4.515172407515388e-05, "epoch": 5.628898128898129, "percentage": 28.14, "elapsed_time": "0:31:26", "remaining_time": "1:20:16", "throughput": 1034.03, "total_tokens": 1950928} {"current_steps": 21665, "total_steps": 76960, "loss": 0.0948, "lr": 4.51483681659212e-05, "epoch": 5.630197505197505, "percentage": 28.15, "elapsed_time": "0:31:27", "remaining_time": "1:20:16", "throughput": 1034.04, "total_tokens": 1951376} {"current_steps": 21670, "total_steps": 76960, "loss": 0.3196, "lr": 4.514501122043864e-05, "epoch": 5.631496881496881, "percentage": 28.16, "elapsed_time": "0:31:27", "remaining_time": "1:20:16", "throughput": 1034.03, "total_tokens": 1951792} {"current_steps": 21675, "total_steps": 76960, "loss": 0.2508, "lr": 4.5141653238878856e-05, "epoch": 5.632796257796258, "percentage": 28.16, "elapsed_time": "0:31:27", "remaining_time": "1:20:15", "throughput": 1034.03, "total_tokens": 1952224} {"current_steps": 21680, "total_steps": 76960, "loss": 0.2945, "lr": 4.5138294221414546e-05, "epoch": 5.634095634095634, "percentage": 28.17, "elapsed_time": "0:31:28", "remaining_time": "1:20:15", "throughput": 1034.04, "total_tokens": 1952672} {"current_steps": 21685, "total_steps": 76960, "loss": 0.2953, "lr": 4.513493416821847e-05, "epoch": 5.63539501039501, "percentage": 28.18, "elapsed_time": "0:31:28", "remaining_time": "1:20:14", "throughput": 1034.07, "total_tokens": 1953152} {"current_steps": 21690, "total_steps": 76960, "loss": 0.2269, "lr": 4.5131573079463426e-05, "epoch": 5.636694386694387, "percentage": 28.18, "elapsed_time": "0:31:29", "remaining_time": "1:20:14", "throughput": 1034.09, "total_tokens": 1953616} {"current_steps": 21695, "total_steps": 76960, "loss": 0.1811, "lr": 4.51282109553223e-05, "epoch": 5.637993762993763, "percentage": 28.19, "elapsed_time": "0:31:29", "remaining_time": "1:20:13", "throughput": 1034.1, "total_tokens": 1954064} {"current_steps": 21700, "total_steps": 76960, "loss": 0.3087, "lr": 4.5124847795967995e-05, "epoch": 5.639293139293139, "percentage": 28.2, "elapsed_time": "0:31:30", "remaining_time": "1:20:13", "throughput": 1034.09, "total_tokens": 1954480} {"current_steps": 21705, "total_steps": 76960, "loss": 0.1766, "lr": 4.512148360157349e-05, "epoch": 5.640592515592516, "percentage": 28.2, "elapsed_time": "0:31:30", "remaining_time": "1:20:12", "throughput": 1034.1, "total_tokens": 1954928} {"current_steps": 21710, "total_steps": 76960, "loss": 0.3001, "lr": 4.51181183723118e-05, "epoch": 5.641891891891892, "percentage": 28.21, "elapsed_time": "0:31:30", "remaining_time": "1:20:12", "throughput": 1034.09, "total_tokens": 1955344} {"current_steps": 21715, "total_steps": 76960, "loss": 0.3244, "lr": 4.5114752108356004e-05, "epoch": 5.643191268191268, "percentage": 28.22, "elapsed_time": "0:31:31", "remaining_time": "1:20:11", "throughput": 1034.1, "total_tokens": 1955792} {"current_steps": 21720, "total_steps": 76960, "loss": 0.297, "lr": 4.511138480987924e-05, "epoch": 5.644490644490644, "percentage": 28.22, "elapsed_time": "0:31:31", "remaining_time": "1:20:11", "throughput": 1034.11, "total_tokens": 1956240} {"current_steps": 21725, "total_steps": 76960, "loss": 0.2512, "lr": 4.510801647705468e-05, "epoch": 5.645790020790021, "percentage": 28.23, "elapsed_time": "0:31:32", "remaining_time": "1:20:10", "throughput": 1034.11, "total_tokens": 1956672} {"current_steps": 21730, "total_steps": 76960, "loss": 0.2467, "lr": 4.510464711005557e-05, "epoch": 5.647089397089397, "percentage": 28.24, "elapsed_time": "0:31:32", "remaining_time": "1:20:10", "throughput": 1034.14, "total_tokens": 1957152} {"current_steps": 21735, "total_steps": 76960, "loss": 0.2591, "lr": 4.510127670905519e-05, "epoch": 5.648388773388773, "percentage": 28.24, "elapsed_time": "0:31:32", "remaining_time": "1:20:09", "throughput": 1034.14, "total_tokens": 1957584} {"current_steps": 21740, "total_steps": 76960, "loss": 0.2672, "lr": 4.509790527422689e-05, "epoch": 5.649688149688149, "percentage": 28.25, "elapsed_time": "0:31:33", "remaining_time": "1:20:09", "throughput": 1034.15, "total_tokens": 1958032} {"current_steps": 21745, "total_steps": 76960, "loss": 0.2989, "lr": 4.509453280574407e-05, "epoch": 5.650987525987526, "percentage": 28.25, "elapsed_time": "0:31:33", "remaining_time": "1:20:08", "throughput": 1034.16, "total_tokens": 1958496} {"current_steps": 21750, "total_steps": 76960, "loss": 0.3009, "lr": 4.5091159303780175e-05, "epoch": 5.652286902286902, "percentage": 28.26, "elapsed_time": "0:31:34", "remaining_time": "1:20:08", "throughput": 1034.19, "total_tokens": 1958976} {"current_steps": 21755, "total_steps": 76960, "loss": 0.2829, "lr": 4.50877847685087e-05, "epoch": 5.653586278586278, "percentage": 28.27, "elapsed_time": "0:31:34", "remaining_time": "1:20:07", "throughput": 1034.2, "total_tokens": 1959424} {"current_steps": 21760, "total_steps": 76960, "loss": 0.278, "lr": 4.508440920010321e-05, "epoch": 5.654885654885655, "percentage": 28.27, "elapsed_time": "0:31:35", "remaining_time": "1:20:07", "throughput": 1034.19, "total_tokens": 1959840} {"current_steps": 21765, "total_steps": 76960, "loss": 0.3012, "lr": 4.508103259873732e-05, "epoch": 5.656185031185031, "percentage": 28.28, "elapsed_time": "0:31:35", "remaining_time": "1:20:06", "throughput": 1034.21, "total_tokens": 1960320} {"current_steps": 21770, "total_steps": 76960, "loss": 0.2815, "lr": 4.507765496458467e-05, "epoch": 5.657484407484407, "percentage": 28.29, "elapsed_time": "0:31:35", "remaining_time": "1:20:06", "throughput": 1034.24, "total_tokens": 1960800} {"current_steps": 21775, "total_steps": 76960, "loss": 0.2742, "lr": 4.507427629781899e-05, "epoch": 5.658783783783784, "percentage": 28.29, "elapsed_time": "0:31:36", "remaining_time": "1:20:05", "throughput": 1034.24, "total_tokens": 1961232} {"current_steps": 21780, "total_steps": 76960, "loss": 0.2663, "lr": 4.5070896598614045e-05, "epoch": 5.66008316008316, "percentage": 28.3, "elapsed_time": "0:31:36", "remaining_time": "1:20:05", "throughput": 1034.26, "total_tokens": 1961696} {"current_steps": 21785, "total_steps": 76960, "loss": 0.258, "lr": 4.506751586714366e-05, "epoch": 5.661382536382536, "percentage": 28.31, "elapsed_time": "0:31:37", "remaining_time": "1:20:04", "throughput": 1034.26, "total_tokens": 1962128} {"current_steps": 21790, "total_steps": 76960, "loss": 0.2427, "lr": 4.506413410358171e-05, "epoch": 5.662681912681912, "percentage": 28.31, "elapsed_time": "0:31:37", "remaining_time": "1:20:04", "throughput": 1034.28, "total_tokens": 1962592} {"current_steps": 21795, "total_steps": 76960, "loss": 0.2433, "lr": 4.506075130810211e-05, "epoch": 5.663981288981289, "percentage": 28.32, "elapsed_time": "0:31:37", "remaining_time": "1:20:03", "throughput": 1034.3, "total_tokens": 1963056} {"current_steps": 21800, "total_steps": 76960, "loss": 0.265, "lr": 4.5057367480878856e-05, "epoch": 5.665280665280665, "percentage": 28.33, "elapsed_time": "0:31:38", "remaining_time": "1:20:03", "throughput": 1034.32, "total_tokens": 1963536} {"current_steps": 21805, "total_steps": 76960, "loss": 0.3104, "lr": 4.5053982622085964e-05, "epoch": 5.666580041580041, "percentage": 28.33, "elapsed_time": "0:31:38", "remaining_time": "1:20:02", "throughput": 1034.33, "total_tokens": 1963984} {"current_steps": 21810, "total_steps": 76960, "loss": 0.2873, "lr": 4.505059673189754e-05, "epoch": 5.667879417879417, "percentage": 28.34, "elapsed_time": "0:31:39", "remaining_time": "1:20:02", "throughput": 1034.36, "total_tokens": 1964464} {"current_steps": 21815, "total_steps": 76960, "loss": 0.2264, "lr": 4.504720981048771e-05, "epoch": 5.669178794178794, "percentage": 28.35, "elapsed_time": "0:31:39", "remaining_time": "1:20:01", "throughput": 1034.38, "total_tokens": 1964944} {"current_steps": 21820, "total_steps": 76960, "loss": 0.2041, "lr": 4.5043821858030675e-05, "epoch": 5.67047817047817, "percentage": 28.35, "elapsed_time": "0:31:40", "remaining_time": "1:20:01", "throughput": 1034.39, "total_tokens": 1965392} {"current_steps": 21825, "total_steps": 76960, "loss": 0.3064, "lr": 4.504043287470068e-05, "epoch": 5.671777546777546, "percentage": 28.36, "elapsed_time": "0:31:40", "remaining_time": "1:20:01", "throughput": 1034.4, "total_tokens": 1965840} {"current_steps": 21830, "total_steps": 76960, "loss": 0.2678, "lr": 4.503704286067202e-05, "epoch": 5.673076923076923, "percentage": 28.37, "elapsed_time": "0:31:40", "remaining_time": "1:20:00", "throughput": 1034.43, "total_tokens": 1966320} {"current_steps": 21835, "total_steps": 76960, "loss": 0.2199, "lr": 4.503365181611904e-05, "epoch": 5.674376299376299, "percentage": 28.37, "elapsed_time": "0:31:41", "remaining_time": "1:20:00", "throughput": 1034.42, "total_tokens": 1966736} {"current_steps": 21840, "total_steps": 76960, "loss": 0.2995, "lr": 4.503025974121615e-05, "epoch": 5.675675675675675, "percentage": 28.38, "elapsed_time": "0:31:41", "remaining_time": "1:19:59", "throughput": 1034.42, "total_tokens": 1967168} {"current_steps": 21845, "total_steps": 76960, "loss": 0.2217, "lr": 4.502686663613782e-05, "epoch": 5.676975051975052, "percentage": 28.38, "elapsed_time": "0:31:42", "remaining_time": "1:19:59", "throughput": 1034.45, "total_tokens": 1967648} {"current_steps": 21850, "total_steps": 76960, "loss": 0.2377, "lr": 4.502347250105854e-05, "epoch": 5.678274428274428, "percentage": 28.39, "elapsed_time": "0:31:42", "remaining_time": "1:19:58", "throughput": 1034.44, "total_tokens": 1968064} {"current_steps": 21855, "total_steps": 76960, "loss": 0.2952, "lr": 4.502007733615289e-05, "epoch": 5.6795738045738045, "percentage": 28.4, "elapsed_time": "0:31:42", "remaining_time": "1:19:58", "throughput": 1034.46, "total_tokens": 1968528} {"current_steps": 21860, "total_steps": 76960, "loss": 0.3048, "lr": 4.501668114159548e-05, "epoch": 5.6808731808731805, "percentage": 28.4, "elapsed_time": "0:31:43", "remaining_time": "1:19:57", "throughput": 1034.44, "total_tokens": 1968928} {"current_steps": 21865, "total_steps": 76960, "loss": 0.2376, "lr": 4.5013283917560974e-05, "epoch": 5.682172557172557, "percentage": 28.41, "elapsed_time": "0:31:43", "remaining_time": "1:19:57", "throughput": 1034.46, "total_tokens": 1969392} {"current_steps": 21870, "total_steps": 76960, "loss": 0.1789, "lr": 4.5009885664224104e-05, "epoch": 5.6834719334719335, "percentage": 28.42, "elapsed_time": "0:31:44", "remaining_time": "1:19:56", "throughput": 1034.47, "total_tokens": 1969840} {"current_steps": 21875, "total_steps": 76960, "loss": 0.2202, "lr": 4.500648638175965e-05, "epoch": 5.6847713097713095, "percentage": 28.42, "elapsed_time": "0:31:44", "remaining_time": "1:19:56", "throughput": 1034.47, "total_tokens": 1970272} {"current_steps": 21880, "total_steps": 76960, "loss": 0.3259, "lr": 4.500308607034242e-05, "epoch": 5.686070686070686, "percentage": 28.43, "elapsed_time": "0:31:45", "remaining_time": "1:19:55", "throughput": 1034.48, "total_tokens": 1970720} {"current_steps": 21885, "total_steps": 76960, "loss": 0.2452, "lr": 4.499968473014731e-05, "epoch": 5.6873700623700625, "percentage": 28.44, "elapsed_time": "0:31:45", "remaining_time": "1:19:55", "throughput": 1034.49, "total_tokens": 1971184} {"current_steps": 21890, "total_steps": 76960, "loss": 0.2753, "lr": 4.4996282361349255e-05, "epoch": 5.6886694386694385, "percentage": 28.44, "elapsed_time": "0:31:45", "remaining_time": "1:19:54", "throughput": 1034.52, "total_tokens": 1971664} {"current_steps": 21895, "total_steps": 76960, "loss": 0.2667, "lr": 4.499287896412324e-05, "epoch": 5.689968814968815, "percentage": 28.45, "elapsed_time": "0:31:46", "remaining_time": "1:19:54", "throughput": 1034.52, "total_tokens": 1972096} {"current_steps": 21900, "total_steps": 76960, "loss": 0.1538, "lr": 4.49894745386443e-05, "epoch": 5.6912681912681915, "percentage": 28.46, "elapsed_time": "0:31:46", "remaining_time": "1:19:53", "throughput": 1034.54, "total_tokens": 1972560} {"current_steps": 21905, "total_steps": 76960, "loss": 0.262, "lr": 4.498606908508754e-05, "epoch": 5.6925675675675675, "percentage": 28.46, "elapsed_time": "0:31:47", "remaining_time": "1:19:53", "throughput": 1034.55, "total_tokens": 1973024} {"current_steps": 21910, "total_steps": 76960, "loss": 0.3772, "lr": 4.498266260362808e-05, "epoch": 5.693866943866944, "percentage": 28.47, "elapsed_time": "0:31:47", "remaining_time": "1:19:52", "throughput": 1034.55, "total_tokens": 1973440} {"current_steps": 21915, "total_steps": 76960, "loss": 0.2781, "lr": 4.4979255094441146e-05, "epoch": 5.6951663201663205, "percentage": 28.48, "elapsed_time": "0:31:47", "remaining_time": "1:19:52", "throughput": 1034.56, "total_tokens": 1973904} {"current_steps": 21920, "total_steps": 76960, "loss": 0.222, "lr": 4.497584655770198e-05, "epoch": 5.696465696465697, "percentage": 28.48, "elapsed_time": "0:31:48", "remaining_time": "1:19:51", "throughput": 1034.57, "total_tokens": 1974352} {"current_steps": 21925, "total_steps": 76960, "loss": 0.221, "lr": 4.497243699358588e-05, "epoch": 5.697765072765073, "percentage": 28.49, "elapsed_time": "0:31:48", "remaining_time": "1:19:51", "throughput": 1034.57, "total_tokens": 1974784} {"current_steps": 21930, "total_steps": 76960, "loss": 0.3095, "lr": 4.496902640226822e-05, "epoch": 5.6990644490644495, "percentage": 28.5, "elapsed_time": "0:31:49", "remaining_time": "1:19:50", "throughput": 1034.59, "total_tokens": 1975248} {"current_steps": 21935, "total_steps": 76960, "loss": 0.2432, "lr": 4.4965614783924385e-05, "epoch": 5.700363825363826, "percentage": 28.5, "elapsed_time": "0:31:49", "remaining_time": "1:19:50", "throughput": 1034.61, "total_tokens": 1975712} {"current_steps": 21940, "total_steps": 76960, "loss": 0.1955, "lr": 4.496220213872986e-05, "epoch": 5.701663201663202, "percentage": 28.51, "elapsed_time": "0:31:50", "remaining_time": "1:19:49", "throughput": 1034.6, "total_tokens": 1976128} {"current_steps": 21945, "total_steps": 76960, "loss": 0.215, "lr": 4.4958788466860154e-05, "epoch": 5.702962577962578, "percentage": 28.51, "elapsed_time": "0:31:50", "remaining_time": "1:19:49", "throughput": 1034.59, "total_tokens": 1976544} {"current_steps": 21950, "total_steps": 76960, "loss": 0.1665, "lr": 4.495537376849083e-05, "epoch": 5.704261954261955, "percentage": 28.52, "elapsed_time": "0:31:50", "remaining_time": "1:19:48", "throughput": 1034.59, "total_tokens": 1976976} {"current_steps": 21955, "total_steps": 76960, "loss": 0.32, "lr": 4.49519580437975e-05, "epoch": 5.705561330561331, "percentage": 28.53, "elapsed_time": "0:31:51", "remaining_time": "1:19:48", "throughput": 1034.61, "total_tokens": 1977440} {"current_steps": 21960, "total_steps": 76960, "loss": 0.4003, "lr": 4.494854129295587e-05, "epoch": 5.706860706860707, "percentage": 28.53, "elapsed_time": "0:31:51", "remaining_time": "1:19:47", "throughput": 1034.63, "total_tokens": 1977904} {"current_steps": 21965, "total_steps": 76960, "loss": 0.2617, "lr": 4.494512351614164e-05, "epoch": 5.708160083160083, "percentage": 28.54, "elapsed_time": "0:31:52", "remaining_time": "1:19:47", "throughput": 1034.64, "total_tokens": 1978352} {"current_steps": 21970, "total_steps": 76960, "loss": 0.2223, "lr": 4.49417047135306e-05, "epoch": 5.70945945945946, "percentage": 28.55, "elapsed_time": "0:31:52", "remaining_time": "1:19:46", "throughput": 1034.65, "total_tokens": 1978800} {"current_steps": 21975, "total_steps": 76960, "loss": 0.2577, "lr": 4.4938284885298575e-05, "epoch": 5.710758835758836, "percentage": 28.55, "elapsed_time": "0:31:52", "remaining_time": "1:19:46", "throughput": 1034.65, "total_tokens": 1979232} {"current_steps": 21980, "total_steps": 76960, "loss": 0.2622, "lr": 4.493486403162146e-05, "epoch": 5.712058212058212, "percentage": 28.56, "elapsed_time": "0:31:53", "remaining_time": "1:19:46", "throughput": 1034.67, "total_tokens": 1979712} {"current_steps": 21985, "total_steps": 76960, "loss": 0.2934, "lr": 4.4931442152675185e-05, "epoch": 5.713357588357589, "percentage": 28.57, "elapsed_time": "0:31:53", "remaining_time": "1:19:45", "throughput": 1034.7, "total_tokens": 1980192} {"current_steps": 21990, "total_steps": 76960, "loss": 0.3036, "lr": 4.492801924863575e-05, "epoch": 5.714656964656965, "percentage": 28.57, "elapsed_time": "0:31:54", "remaining_time": "1:19:45", "throughput": 1034.69, "total_tokens": 1980608} {"current_steps": 21995, "total_steps": 76960, "loss": 0.2021, "lr": 4.492459531967917e-05, "epoch": 5.715956340956341, "percentage": 28.58, "elapsed_time": "0:31:54", "remaining_time": "1:19:44", "throughput": 1034.73, "total_tokens": 1981104} {"current_steps": 22000, "total_steps": 76960, "loss": 0.2412, "lr": 4.492117036598158e-05, "epoch": 5.717255717255718, "percentage": 28.59, "elapsed_time": "0:31:55", "remaining_time": "1:19:44", "throughput": 1034.74, "total_tokens": 1981568} {"current_steps": 22005, "total_steps": 76960, "loss": 0.2776, "lr": 4.4917744387719105e-05, "epoch": 5.718555093555094, "percentage": 28.59, "elapsed_time": "0:31:55", "remaining_time": "1:19:43", "throughput": 1034.75, "total_tokens": 1982016} {"current_steps": 22010, "total_steps": 76960, "loss": 0.2222, "lr": 4.491431738506795e-05, "epoch": 5.71985446985447, "percentage": 28.6, "elapsed_time": "0:31:55", "remaining_time": "1:19:43", "throughput": 1034.78, "total_tokens": 1982496} {"current_steps": 22015, "total_steps": 76960, "loss": 0.2175, "lr": 4.491088935820437e-05, "epoch": 5.721153846153846, "percentage": 28.61, "elapsed_time": "0:31:56", "remaining_time": "1:19:42", "throughput": 1034.77, "total_tokens": 1982912} {"current_steps": 22020, "total_steps": 76960, "loss": 0.308, "lr": 4.490746030730468e-05, "epoch": 5.722453222453223, "percentage": 28.61, "elapsed_time": "0:31:56", "remaining_time": "1:19:42", "throughput": 1034.81, "total_tokens": 1983408} {"current_steps": 22025, "total_steps": 76960, "loss": 0.2869, "lr": 4.490403023254522e-05, "epoch": 5.723752598752599, "percentage": 28.62, "elapsed_time": "0:31:57", "remaining_time": "1:19:41", "throughput": 1034.82, "total_tokens": 1983872} {"current_steps": 22030, "total_steps": 76960, "loss": 0.2559, "lr": 4.4900599134102425e-05, "epoch": 5.725051975051975, "percentage": 28.63, "elapsed_time": "0:31:57", "remaining_time": "1:19:41", "throughput": 1034.82, "total_tokens": 1984288} {"current_steps": 22035, "total_steps": 76960, "loss": 0.2564, "lr": 4.4897167012152745e-05, "epoch": 5.726351351351351, "percentage": 28.63, "elapsed_time": "0:31:57", "remaining_time": "1:19:40", "throughput": 1034.82, "total_tokens": 1984720} {"current_steps": 22040, "total_steps": 76960, "loss": 0.2985, "lr": 4.48937338668727e-05, "epoch": 5.727650727650728, "percentage": 28.64, "elapsed_time": "0:31:58", "remaining_time": "1:19:40", "throughput": 1034.82, "total_tokens": 1985152} {"current_steps": 22045, "total_steps": 76960, "loss": 0.1955, "lr": 4.489029969843886e-05, "epoch": 5.728950103950104, "percentage": 28.64, "elapsed_time": "0:31:58", "remaining_time": "1:19:39", "throughput": 1034.82, "total_tokens": 1985584} {"current_steps": 22050, "total_steps": 76960, "loss": 0.2415, "lr": 4.488686450702785e-05, "epoch": 5.73024948024948, "percentage": 28.65, "elapsed_time": "0:31:59", "remaining_time": "1:19:39", "throughput": 1034.83, "total_tokens": 1986032} {"current_steps": 22055, "total_steps": 76960, "loss": 0.2523, "lr": 4.488342829281635e-05, "epoch": 5.731548856548857, "percentage": 28.66, "elapsed_time": "0:31:59", "remaining_time": "1:19:38", "throughput": 1034.83, "total_tokens": 1986464} {"current_steps": 22060, "total_steps": 76960, "loss": 0.2807, "lr": 4.487999105598108e-05, "epoch": 5.732848232848233, "percentage": 28.66, "elapsed_time": "0:32:00", "remaining_time": "1:19:38", "throughput": 1034.82, "total_tokens": 1986880} {"current_steps": 22065, "total_steps": 76960, "loss": 0.3126, "lr": 4.487655279669881e-05, "epoch": 5.734147609147609, "percentage": 28.67, "elapsed_time": "0:32:00", "remaining_time": "1:19:37", "throughput": 1034.85, "total_tokens": 1987360} {"current_steps": 22070, "total_steps": 76960, "loss": 0.2307, "lr": 4.4873113515146395e-05, "epoch": 5.735446985446986, "percentage": 28.68, "elapsed_time": "0:32:00", "remaining_time": "1:19:37", "throughput": 1034.85, "total_tokens": 1987792} {"current_steps": 22075, "total_steps": 76960, "loss": 0.2761, "lr": 4.4869673211500706e-05, "epoch": 5.736746361746362, "percentage": 28.68, "elapsed_time": "0:32:01", "remaining_time": "1:19:36", "throughput": 1034.86, "total_tokens": 1988240} {"current_steps": 22080, "total_steps": 76960, "loss": 0.182, "lr": 4.4866231885938694e-05, "epoch": 5.738045738045738, "percentage": 28.69, "elapsed_time": "0:32:01", "remaining_time": "1:19:36", "throughput": 1034.86, "total_tokens": 1988672} {"current_steps": 22085, "total_steps": 76960, "loss": 0.2258, "lr": 4.486278953863733e-05, "epoch": 5.739345114345114, "percentage": 28.7, "elapsed_time": "0:32:02", "remaining_time": "1:19:35", "throughput": 1034.88, "total_tokens": 1989136} {"current_steps": 22090, "total_steps": 76960, "loss": 0.2914, "lr": 4.485934616977367e-05, "epoch": 5.740644490644491, "percentage": 28.7, "elapsed_time": "0:32:02", "remaining_time": "1:19:35", "throughput": 1034.89, "total_tokens": 1989584} {"current_steps": 22095, "total_steps": 76960, "loss": 0.2854, "lr": 4.4855901779524816e-05, "epoch": 5.741943866943867, "percentage": 28.71, "elapsed_time": "0:32:02", "remaining_time": "1:19:34", "throughput": 1034.9, "total_tokens": 1990048} {"current_steps": 22100, "total_steps": 76960, "loss": 0.2145, "lr": 4.4852456368067905e-05, "epoch": 5.743243243243243, "percentage": 28.72, "elapsed_time": "0:32:03", "remaining_time": "1:19:34", "throughput": 1034.9, "total_tokens": 1990464} {"current_steps": 22105, "total_steps": 76960, "loss": 0.2499, "lr": 4.484900993558014e-05, "epoch": 5.74454261954262, "percentage": 28.72, "elapsed_time": "0:32:03", "remaining_time": "1:19:33", "throughput": 1034.9, "total_tokens": 1990896} {"current_steps": 22110, "total_steps": 76960, "loss": 0.2687, "lr": 4.484556248223877e-05, "epoch": 5.745841995841996, "percentage": 28.73, "elapsed_time": "0:32:04", "remaining_time": "1:19:33", "throughput": 1034.91, "total_tokens": 1991344} {"current_steps": 22115, "total_steps": 76960, "loss": 0.2152, "lr": 4.484211400822111e-05, "epoch": 5.747141372141372, "percentage": 28.74, "elapsed_time": "0:32:04", "remaining_time": "1:19:32", "throughput": 1034.92, "total_tokens": 1991808} {"current_steps": 22120, "total_steps": 76960, "loss": 0.2173, "lr": 4.483866451370452e-05, "epoch": 5.748440748440748, "percentage": 28.74, "elapsed_time": "0:32:05", "remaining_time": "1:19:32", "throughput": 1034.94, "total_tokens": 1992272} {"current_steps": 22125, "total_steps": 76960, "loss": 0.2251, "lr": 4.4835213998866405e-05, "epoch": 5.749740124740125, "percentage": 28.75, "elapsed_time": "0:32:05", "remaining_time": "1:19:32", "throughput": 1034.93, "total_tokens": 1992688} {"current_steps": 22130, "total_steps": 76960, "loss": 0.2572, "lr": 4.483176246388423e-05, "epoch": 5.751039501039501, "percentage": 28.76, "elapsed_time": "0:32:05", "remaining_time": "1:19:31", "throughput": 1034.94, "total_tokens": 1993136} {"current_steps": 22135, "total_steps": 76960, "loss": 0.2698, "lr": 4.482830990893551e-05, "epoch": 5.752338877338877, "percentage": 28.76, "elapsed_time": "0:32:06", "remaining_time": "1:19:31", "throughput": 1034.95, "total_tokens": 1993584} {"current_steps": 22140, "total_steps": 76960, "loss": 0.2179, "lr": 4.48248563341978e-05, "epoch": 5.753638253638254, "percentage": 28.77, "elapsed_time": "0:32:06", "remaining_time": "1:19:30", "throughput": 1034.94, "total_tokens": 1994000} {"current_steps": 22145, "total_steps": 76960, "loss": 0.1915, "lr": 4.482140173984875e-05, "epoch": 5.75493762993763, "percentage": 28.77, "elapsed_time": "0:32:07", "remaining_time": "1:19:30", "throughput": 1034.96, "total_tokens": 1994464} {"current_steps": 22150, "total_steps": 76960, "loss": 0.2039, "lr": 4.4817946126066e-05, "epoch": 5.756237006237006, "percentage": 28.78, "elapsed_time": "0:32:07", "remaining_time": "1:19:29", "throughput": 1034.96, "total_tokens": 1994896} {"current_steps": 22155, "total_steps": 76960, "loss": 0.1904, "lr": 4.48144894930273e-05, "epoch": 5.757536382536383, "percentage": 28.79, "elapsed_time": "0:32:07", "remaining_time": "1:19:29", "throughput": 1034.95, "total_tokens": 1995312} {"current_steps": 22160, "total_steps": 76960, "loss": 0.0678, "lr": 4.4811031840910424e-05, "epoch": 5.758835758835759, "percentage": 28.79, "elapsed_time": "0:32:08", "remaining_time": "1:19:28", "throughput": 1034.96, "total_tokens": 1995760} {"current_steps": 22165, "total_steps": 76960, "loss": 0.3915, "lr": 4.4807573169893193e-05, "epoch": 5.760135135135135, "percentage": 28.8, "elapsed_time": "0:32:08", "remaining_time": "1:19:28", "throughput": 1034.99, "total_tokens": 1996240} {"current_steps": 22170, "total_steps": 76960, "loss": 0.4249, "lr": 4.48041134801535e-05, "epoch": 5.761434511434511, "percentage": 28.81, "elapsed_time": "0:32:09", "remaining_time": "1:19:27", "throughput": 1035.0, "total_tokens": 1996688} {"current_steps": 22175, "total_steps": 76960, "loss": 0.2189, "lr": 4.480065277186927e-05, "epoch": 5.762733887733888, "percentage": 28.81, "elapsed_time": "0:32:09", "remaining_time": "1:19:27", "throughput": 1034.98, "total_tokens": 1997104} {"current_steps": 22180, "total_steps": 76960, "loss": 0.2654, "lr": 4.47971910452185e-05, "epoch": 5.764033264033264, "percentage": 28.82, "elapsed_time": "0:32:10", "remaining_time": "1:19:26", "throughput": 1034.99, "total_tokens": 1997552} {"current_steps": 22185, "total_steps": 76960, "loss": 0.3141, "lr": 4.479372830037922e-05, "epoch": 5.76533264033264, "percentage": 28.83, "elapsed_time": "0:32:10", "remaining_time": "1:19:26", "throughput": 1035.0, "total_tokens": 1998000} {"current_steps": 22190, "total_steps": 76960, "loss": 0.2635, "lr": 4.479026453752953e-05, "epoch": 5.766632016632016, "percentage": 28.83, "elapsed_time": "0:32:10", "remaining_time": "1:19:25", "throughput": 1035.01, "total_tokens": 1998448} {"current_steps": 22195, "total_steps": 76960, "loss": 0.2706, "lr": 4.478679975684759e-05, "epoch": 5.767931392931393, "percentage": 28.84, "elapsed_time": "0:32:11", "remaining_time": "1:19:25", "throughput": 1035.03, "total_tokens": 1998912} {"current_steps": 22200, "total_steps": 76960, "loss": 0.1904, "lr": 4.4783333958511555e-05, "epoch": 5.769230769230769, "percentage": 28.85, "elapsed_time": "0:32:11", "remaining_time": "1:19:24", "throughput": 1035.05, "total_tokens": 1999376} {"current_steps": 22205, "total_steps": 76960, "loss": 0.2303, "lr": 4.477986714269972e-05, "epoch": 5.770530145530145, "percentage": 28.85, "elapsed_time": "0:32:12", "remaining_time": "1:19:24", "throughput": 1035.04, "total_tokens": 1999792} {"current_steps": 22210, "total_steps": 76960, "loss": 0.1605, "lr": 4.477639930959034e-05, "epoch": 5.771829521829522, "percentage": 28.86, "elapsed_time": "0:32:12", "remaining_time": "1:19:23", "throughput": 1035.06, "total_tokens": 2000272} {"current_steps": 22215, "total_steps": 76960, "loss": 0.1367, "lr": 4.477293045936182e-05, "epoch": 5.773128898128898, "percentage": 28.87, "elapsed_time": "0:32:12", "remaining_time": "1:19:23", "throughput": 1035.07, "total_tokens": 2000720} {"current_steps": 22220, "total_steps": 76960, "loss": 0.3201, "lr": 4.4769460592192524e-05, "epoch": 5.774428274428274, "percentage": 28.87, "elapsed_time": "0:32:13", "remaining_time": "1:19:22", "throughput": 1035.11, "total_tokens": 2001216} {"current_steps": 22225, "total_steps": 76960, "loss": 0.3065, "lr": 4.476598970826094e-05, "epoch": 5.775727650727651, "percentage": 28.88, "elapsed_time": "0:32:13", "remaining_time": "1:19:22", "throughput": 1035.11, "total_tokens": 2001648} {"current_steps": 22230, "total_steps": 76960, "loss": 0.3575, "lr": 4.4762517807745564e-05, "epoch": 5.777027027027027, "percentage": 28.89, "elapsed_time": "0:32:14", "remaining_time": "1:19:21", "throughput": 1035.11, "total_tokens": 2002080} {"current_steps": 22235, "total_steps": 76960, "loss": 0.2735, "lr": 4.4759044890824954e-05, "epoch": 5.778326403326403, "percentage": 28.89, "elapsed_time": "0:32:14", "remaining_time": "1:19:21", "throughput": 1035.12, "total_tokens": 2002528} {"current_steps": 22240, "total_steps": 76960, "loss": 0.2872, "lr": 4.475557095767774e-05, "epoch": 5.779625779625779, "percentage": 28.9, "elapsed_time": "0:32:15", "remaining_time": "1:19:20", "throughput": 1035.13, "total_tokens": 2002992} {"current_steps": 22245, "total_steps": 76960, "loss": 0.207, "lr": 4.475209600848258e-05, "epoch": 5.780925155925156, "percentage": 28.9, "elapsed_time": "0:32:15", "remaining_time": "1:19:20", "throughput": 1035.15, "total_tokens": 2003456} {"current_steps": 22250, "total_steps": 76960, "loss": 0.2004, "lr": 4.474862004341819e-05, "epoch": 5.782224532224532, "percentage": 28.91, "elapsed_time": "0:32:15", "remaining_time": "1:19:19", "throughput": 1035.18, "total_tokens": 2003952} {"current_steps": 22255, "total_steps": 76960, "loss": 0.2693, "lr": 4.474514306266335e-05, "epoch": 5.783523908523908, "percentage": 28.92, "elapsed_time": "0:32:16", "remaining_time": "1:19:19", "throughput": 1035.17, "total_tokens": 2004368} {"current_steps": 22260, "total_steps": 76960, "loss": 0.2816, "lr": 4.47416650663969e-05, "epoch": 5.784823284823284, "percentage": 28.92, "elapsed_time": "0:32:16", "remaining_time": "1:19:19", "throughput": 1035.19, "total_tokens": 2004832} {"current_steps": 22265, "total_steps": 76960, "loss": 0.2026, "lr": 4.4738186054797685e-05, "epoch": 5.786122661122661, "percentage": 28.93, "elapsed_time": "0:32:17", "remaining_time": "1:19:18", "throughput": 1035.2, "total_tokens": 2005280} {"current_steps": 22270, "total_steps": 76960, "loss": 0.3163, "lr": 4.473470602804465e-05, "epoch": 5.787422037422037, "percentage": 28.94, "elapsed_time": "0:32:17", "remaining_time": "1:19:18", "throughput": 1035.21, "total_tokens": 2005728} {"current_steps": 22275, "total_steps": 76960, "loss": 0.2244, "lr": 4.4731224986316784e-05, "epoch": 5.788721413721413, "percentage": 28.94, "elapsed_time": "0:32:17", "remaining_time": "1:19:17", "throughput": 1035.19, "total_tokens": 2006128} {"current_steps": 22280, "total_steps": 76960, "loss": 0.2079, "lr": 4.4727742929793105e-05, "epoch": 5.79002079002079, "percentage": 28.95, "elapsed_time": "0:32:18", "remaining_time": "1:19:17", "throughput": 1035.19, "total_tokens": 2006560} {"current_steps": 22285, "total_steps": 76960, "loss": 0.316, "lr": 4.4724259858652704e-05, "epoch": 5.791320166320166, "percentage": 28.96, "elapsed_time": "0:32:18", "remaining_time": "1:19:16", "throughput": 1035.2, "total_tokens": 2007008} {"current_steps": 22290, "total_steps": 76960, "loss": 0.2652, "lr": 4.472077577307472e-05, "epoch": 5.792619542619542, "percentage": 28.96, "elapsed_time": "0:32:19", "remaining_time": "1:19:16", "throughput": 1035.21, "total_tokens": 2007472} {"current_steps": 22295, "total_steps": 76960, "loss": 0.2368, "lr": 4.4717290673238347e-05, "epoch": 5.793918918918919, "percentage": 28.97, "elapsed_time": "0:32:19", "remaining_time": "1:19:15", "throughput": 1035.24, "total_tokens": 2007952} {"current_steps": 22300, "total_steps": 76960, "loss": 0.2417, "lr": 4.4713804559322814e-05, "epoch": 5.795218295218295, "percentage": 28.98, "elapsed_time": "0:32:20", "remaining_time": "1:19:15", "throughput": 1035.25, "total_tokens": 2008416} {"current_steps": 22305, "total_steps": 76960, "loss": 0.2692, "lr": 4.4710317431507434e-05, "epoch": 5.796517671517671, "percentage": 28.98, "elapsed_time": "0:32:20", "remaining_time": "1:19:14", "throughput": 1035.26, "total_tokens": 2008864} {"current_steps": 22310, "total_steps": 76960, "loss": 0.2834, "lr": 4.470682928997153e-05, "epoch": 5.797817047817047, "percentage": 28.99, "elapsed_time": "0:32:20", "remaining_time": "1:19:14", "throughput": 1035.26, "total_tokens": 2009312} {"current_steps": 22315, "total_steps": 76960, "loss": 0.1738, "lr": 4.470334013489452e-05, "epoch": 5.799116424116424, "percentage": 29.0, "elapsed_time": "0:32:21", "remaining_time": "1:19:13", "throughput": 1035.28, "total_tokens": 2009776} {"current_steps": 22320, "total_steps": 76960, "loss": 0.2068, "lr": 4.4699849966455854e-05, "epoch": 5.8004158004158, "percentage": 29.0, "elapsed_time": "0:32:21", "remaining_time": "1:19:13", "throughput": 1035.29, "total_tokens": 2010224} {"current_steps": 22325, "total_steps": 76960, "loss": 0.3161, "lr": 4.4696358784835026e-05, "epoch": 5.8017151767151764, "percentage": 29.01, "elapsed_time": "0:32:22", "remaining_time": "1:19:12", "throughput": 1035.32, "total_tokens": 2010720} {"current_steps": 22330, "total_steps": 76960, "loss": 0.2329, "lr": 4.469286659021159e-05, "epoch": 5.803014553014553, "percentage": 29.02, "elapsed_time": "0:32:22", "remaining_time": "1:19:12", "throughput": 1035.31, "total_tokens": 2011136} {"current_steps": 22335, "total_steps": 76960, "loss": 0.2344, "lr": 4.4689373382765155e-05, "epoch": 5.804313929313929, "percentage": 29.02, "elapsed_time": "0:32:22", "remaining_time": "1:19:11", "throughput": 1035.35, "total_tokens": 2011632} {"current_steps": 22340, "total_steps": 76960, "loss": 0.2592, "lr": 4.468587916267539e-05, "epoch": 5.8056133056133055, "percentage": 29.03, "elapsed_time": "0:32:23", "remaining_time": "1:19:11", "throughput": 1035.36, "total_tokens": 2012096} {"current_steps": 22345, "total_steps": 76960, "loss": 0.2031, "lr": 4.4682383930121985e-05, "epoch": 5.8069126819126815, "percentage": 29.03, "elapsed_time": "0:32:23", "remaining_time": "1:19:10", "throughput": 1035.37, "total_tokens": 2012544} {"current_steps": 22350, "total_steps": 76960, "loss": 0.1737, "lr": 4.467888768528472e-05, "epoch": 5.808212058212058, "percentage": 29.04, "elapsed_time": "0:32:24", "remaining_time": "1:19:10", "throughput": 1035.39, "total_tokens": 2013008} {"current_steps": 22355, "total_steps": 76960, "loss": 0.2756, "lr": 4.467539042834342e-05, "epoch": 5.8095114345114345, "percentage": 29.05, "elapsed_time": "0:32:24", "remaining_time": "1:19:09", "throughput": 1035.4, "total_tokens": 2013456} {"current_steps": 22360, "total_steps": 76960, "loss": 0.1348, "lr": 4.4671892159477927e-05, "epoch": 5.8108108108108105, "percentage": 29.05, "elapsed_time": "0:32:25", "remaining_time": "1:19:09", "throughput": 1035.42, "total_tokens": 2013920} {"current_steps": 22365, "total_steps": 76960, "loss": 0.2901, "lr": 4.466839287886817e-05, "epoch": 5.8121101871101875, "percentage": 29.06, "elapsed_time": "0:32:25", "remaining_time": "1:19:09", "throughput": 1035.42, "total_tokens": 2014368} {"current_steps": 22370, "total_steps": 76960, "loss": 0.3892, "lr": 4.4664892586694116e-05, "epoch": 5.8134095634095635, "percentage": 29.07, "elapsed_time": "0:32:25", "remaining_time": "1:19:08", "throughput": 1035.42, "total_tokens": 2014800} {"current_steps": 22375, "total_steps": 76960, "loss": 0.139, "lr": 4.466139128313581e-05, "epoch": 5.8147089397089395, "percentage": 29.07, "elapsed_time": "0:32:26", "remaining_time": "1:19:08", "throughput": 1035.43, "total_tokens": 2015248} {"current_steps": 22380, "total_steps": 76960, "loss": 0.4182, "lr": 4.4657888968373295e-05, "epoch": 5.8160083160083165, "percentage": 29.08, "elapsed_time": "0:32:26", "remaining_time": "1:19:07", "throughput": 1035.44, "total_tokens": 2015696} {"current_steps": 22385, "total_steps": 76960, "loss": 0.2223, "lr": 4.465438564258673e-05, "epoch": 5.8173076923076925, "percentage": 29.09, "elapsed_time": "0:32:27", "remaining_time": "1:19:07", "throughput": 1035.45, "total_tokens": 2016144} {"current_steps": 22390, "total_steps": 76960, "loss": 0.3051, "lr": 4.4650881305956274e-05, "epoch": 5.8186070686070686, "percentage": 29.09, "elapsed_time": "0:32:27", "remaining_time": "1:19:06", "throughput": 1035.48, "total_tokens": 2016624} {"current_steps": 22395, "total_steps": 76960, "loss": 0.2201, "lr": 4.464737595866216e-05, "epoch": 5.819906444906445, "percentage": 29.1, "elapsed_time": "0:32:27", "remaining_time": "1:19:06", "throughput": 1035.48, "total_tokens": 2017056} {"current_steps": 22400, "total_steps": 76960, "loss": 0.2925, "lr": 4.4643869600884675e-05, "epoch": 5.8212058212058215, "percentage": 29.11, "elapsed_time": "0:32:28", "remaining_time": "1:19:05", "throughput": 1035.48, "total_tokens": 2017488} {"current_steps": 22405, "total_steps": 76960, "loss": 0.2097, "lr": 4.4640362232804156e-05, "epoch": 5.822505197505198, "percentage": 29.11, "elapsed_time": "0:32:28", "remaining_time": "1:19:05", "throughput": 1035.5, "total_tokens": 2017968} {"current_steps": 22410, "total_steps": 76960, "loss": 0.2574, "lr": 4.463685385460099e-05, "epoch": 5.823804573804574, "percentage": 29.12, "elapsed_time": "0:32:29", "remaining_time": "1:19:04", "throughput": 1035.53, "total_tokens": 2018448} {"current_steps": 22415, "total_steps": 76960, "loss": 0.3266, "lr": 4.4633344466455615e-05, "epoch": 5.82510395010395, "percentage": 29.13, "elapsed_time": "0:32:29", "remaining_time": "1:19:04", "throughput": 1035.53, "total_tokens": 2018880} {"current_steps": 22420, "total_steps": 76960, "loss": 0.2889, "lr": 4.4629834068548524e-05, "epoch": 5.826403326403327, "percentage": 29.13, "elapsed_time": "0:32:30", "remaining_time": "1:19:03", "throughput": 1035.53, "total_tokens": 2019312} {"current_steps": 22425, "total_steps": 76960, "loss": 0.2147, "lr": 4.462632266106026e-05, "epoch": 5.827702702702703, "percentage": 29.14, "elapsed_time": "0:32:30", "remaining_time": "1:19:03", "throughput": 1035.54, "total_tokens": 2019776} {"current_steps": 22430, "total_steps": 76960, "loss": 0.2716, "lr": 4.4622810244171406e-05, "epoch": 5.829002079002079, "percentage": 29.15, "elapsed_time": "0:32:30", "remaining_time": "1:19:02", "throughput": 1035.54, "total_tokens": 2020208} {"current_steps": 22435, "total_steps": 76960, "loss": 0.254, "lr": 4.4619296818062636e-05, "epoch": 5.830301455301456, "percentage": 29.15, "elapsed_time": "0:32:31", "remaining_time": "1:19:02", "throughput": 1035.56, "total_tokens": 2020672} {"current_steps": 22440, "total_steps": 76960, "loss": 0.227, "lr": 4.461578238291462e-05, "epoch": 5.831600831600832, "percentage": 29.16, "elapsed_time": "0:32:31", "remaining_time": "1:19:01", "throughput": 1035.55, "total_tokens": 2021088} {"current_steps": 22445, "total_steps": 76960, "loss": 0.3446, "lr": 4.461226693890812e-05, "epoch": 5.832900207900208, "percentage": 29.16, "elapsed_time": "0:32:32", "remaining_time": "1:19:01", "throughput": 1035.59, "total_tokens": 2021600} {"current_steps": 22450, "total_steps": 76960, "loss": 0.2652, "lr": 4.460875048622395e-05, "epoch": 5.834199584199585, "percentage": 29.17, "elapsed_time": "0:32:32", "remaining_time": "1:19:00", "throughput": 1035.59, "total_tokens": 2022016} {"current_steps": 22455, "total_steps": 76960, "loss": 0.2634, "lr": 4.460523302504295e-05, "epoch": 5.835498960498961, "percentage": 29.18, "elapsed_time": "0:32:32", "remaining_time": "1:19:00", "throughput": 1035.6, "total_tokens": 2022480} {"current_steps": 22460, "total_steps": 76960, "loss": 0.2514, "lr": 4.460171455554603e-05, "epoch": 5.836798336798337, "percentage": 29.18, "elapsed_time": "0:32:33", "remaining_time": "1:18:59", "throughput": 1035.63, "total_tokens": 2022960} {"current_steps": 22465, "total_steps": 76960, "loss": 0.2965, "lr": 4.4598195077914145e-05, "epoch": 5.838097713097713, "percentage": 29.19, "elapsed_time": "0:32:33", "remaining_time": "1:18:59", "throughput": 1035.63, "total_tokens": 2023392} {"current_steps": 22470, "total_steps": 76960, "loss": 0.2722, "lr": 4.4594674592328314e-05, "epoch": 5.83939708939709, "percentage": 29.2, "elapsed_time": "0:32:34", "remaining_time": "1:18:58", "throughput": 1035.64, "total_tokens": 2023840} {"current_steps": 22475, "total_steps": 76960, "loss": 0.2697, "lr": 4.459115309896959e-05, "epoch": 5.840696465696466, "percentage": 29.2, "elapsed_time": "0:32:34", "remaining_time": "1:18:58", "throughput": 1035.65, "total_tokens": 2024288} {"current_steps": 22480, "total_steps": 76960, "loss": 0.2475, "lr": 4.458763059801909e-05, "epoch": 5.841995841995842, "percentage": 29.21, "elapsed_time": "0:32:35", "remaining_time": "1:18:57", "throughput": 1035.64, "total_tokens": 2024704} {"current_steps": 22485, "total_steps": 76960, "loss": 0.2452, "lr": 4.458410708965799e-05, "epoch": 5.843295218295218, "percentage": 29.22, "elapsed_time": "0:32:35", "remaining_time": "1:18:57", "throughput": 1035.66, "total_tokens": 2025168} {"current_steps": 22490, "total_steps": 76960, "loss": 0.3132, "lr": 4.458058257406749e-05, "epoch": 5.844594594594595, "percentage": 29.22, "elapsed_time": "0:32:35", "remaining_time": "1:18:57", "throughput": 1035.67, "total_tokens": 2025616} {"current_steps": 22495, "total_steps": 76960, "loss": 0.2458, "lr": 4.4577057051428865e-05, "epoch": 5.845893970893971, "percentage": 29.23, "elapsed_time": "0:32:36", "remaining_time": "1:18:56", "throughput": 1035.67, "total_tokens": 2026048} {"current_steps": 22500, "total_steps": 76960, "loss": 0.3862, "lr": 4.4573530521923445e-05, "epoch": 5.847193347193347, "percentage": 29.24, "elapsed_time": "0:32:36", "remaining_time": "1:18:56", "throughput": 1035.66, "total_tokens": 2026464} {"current_steps": 22505, "total_steps": 76960, "loss": 0.2624, "lr": 4.457000298573259e-05, "epoch": 5.848492723492724, "percentage": 29.24, "elapsed_time": "0:32:37", "remaining_time": "1:18:55", "throughput": 1035.65, "total_tokens": 2026880} {"current_steps": 22510, "total_steps": 76960, "loss": 0.2201, "lr": 4.4566474443037733e-05, "epoch": 5.8497920997921, "percentage": 29.25, "elapsed_time": "0:32:37", "remaining_time": "1:18:55", "throughput": 1035.66, "total_tokens": 2027328} {"current_steps": 22515, "total_steps": 76960, "loss": 0.2761, "lr": 4.4562944894020345e-05, "epoch": 5.851091476091476, "percentage": 29.26, "elapsed_time": "0:32:37", "remaining_time": "1:18:54", "throughput": 1035.67, "total_tokens": 2027792} {"current_steps": 22520, "total_steps": 76960, "loss": 0.2249, "lr": 4.455941433886196e-05, "epoch": 5.852390852390853, "percentage": 29.26, "elapsed_time": "0:32:38", "remaining_time": "1:18:54", "throughput": 1035.69, "total_tokens": 2028256} {"current_steps": 22525, "total_steps": 76960, "loss": 0.2623, "lr": 4.455588277774416e-05, "epoch": 5.853690228690229, "percentage": 29.27, "elapsed_time": "0:32:38", "remaining_time": "1:18:53", "throughput": 1035.69, "total_tokens": 2028688} {"current_steps": 22530, "total_steps": 76960, "loss": 0.2527, "lr": 4.455235021084856e-05, "epoch": 5.854989604989605, "percentage": 29.27, "elapsed_time": "0:32:39", "remaining_time": "1:18:53", "throughput": 1035.69, "total_tokens": 2029120} {"current_steps": 22535, "total_steps": 76960, "loss": 0.2861, "lr": 4.454881663835686e-05, "epoch": 5.856288981288982, "percentage": 29.28, "elapsed_time": "0:32:39", "remaining_time": "1:18:52", "throughput": 1035.7, "total_tokens": 2029568} {"current_steps": 22540, "total_steps": 76960, "loss": 0.2252, "lr": 4.454528206045079e-05, "epoch": 5.857588357588358, "percentage": 29.29, "elapsed_time": "0:32:40", "remaining_time": "1:18:52", "throughput": 1035.7, "total_tokens": 2030000} {"current_steps": 22545, "total_steps": 76960, "loss": 0.2726, "lr": 4.454174647731213e-05, "epoch": 5.858887733887734, "percentage": 29.29, "elapsed_time": "0:32:40", "remaining_time": "1:18:51", "throughput": 1035.71, "total_tokens": 2030448} {"current_steps": 22550, "total_steps": 76960, "loss": 0.2217, "lr": 4.453820988912273e-05, "epoch": 5.86018711018711, "percentage": 29.3, "elapsed_time": "0:32:40", "remaining_time": "1:18:51", "throughput": 1035.74, "total_tokens": 2030944} {"current_steps": 22555, "total_steps": 76960, "loss": 0.2884, "lr": 4.453467229606448e-05, "epoch": 5.861486486486487, "percentage": 29.31, "elapsed_time": "0:32:41", "remaining_time": "1:18:50", "throughput": 1035.75, "total_tokens": 2031392} {"current_steps": 22560, "total_steps": 76960, "loss": 0.2433, "lr": 4.4531133698319306e-05, "epoch": 5.862785862785863, "percentage": 29.31, "elapsed_time": "0:32:41", "remaining_time": "1:18:50", "throughput": 1035.77, "total_tokens": 2031856} {"current_steps": 22565, "total_steps": 76960, "loss": 0.3269, "lr": 4.452759409606922e-05, "epoch": 5.864085239085239, "percentage": 29.32, "elapsed_time": "0:32:42", "remaining_time": "1:18:49", "throughput": 1035.77, "total_tokens": 2032288} {"current_steps": 22570, "total_steps": 76960, "loss": 0.2194, "lr": 4.4524053489496255e-05, "epoch": 5.865384615384615, "percentage": 29.33, "elapsed_time": "0:32:42", "remaining_time": "1:18:49", "throughput": 1035.8, "total_tokens": 2032784} {"current_steps": 22575, "total_steps": 76960, "loss": 0.3237, "lr": 4.452051187878251e-05, "epoch": 5.866683991683992, "percentage": 29.33, "elapsed_time": "0:32:42", "remaining_time": "1:18:48", "throughput": 1035.81, "total_tokens": 2033232} {"current_steps": 22580, "total_steps": 76960, "loss": 0.2384, "lr": 4.451696926411014e-05, "epoch": 5.867983367983368, "percentage": 29.34, "elapsed_time": "0:32:43", "remaining_time": "1:18:48", "throughput": 1035.8, "total_tokens": 2033648} {"current_steps": 22585, "total_steps": 76960, "loss": 0.2882, "lr": 4.451342564566134e-05, "epoch": 5.869282744282744, "percentage": 29.35, "elapsed_time": "0:32:43", "remaining_time": "1:18:47", "throughput": 1035.82, "total_tokens": 2034112} {"current_steps": 22590, "total_steps": 76960, "loss": 0.2337, "lr": 4.450988102361836e-05, "epoch": 5.870582120582121, "percentage": 29.35, "elapsed_time": "0:32:44", "remaining_time": "1:18:47", "throughput": 1035.84, "total_tokens": 2034592} {"current_steps": 22595, "total_steps": 76960, "loss": 0.1514, "lr": 4.450633539816351e-05, "epoch": 5.871881496881497, "percentage": 29.36, "elapsed_time": "0:32:44", "remaining_time": "1:18:46", "throughput": 1035.85, "total_tokens": 2035040} {"current_steps": 22600, "total_steps": 76960, "loss": 0.217, "lr": 4.4502788769479136e-05, "epoch": 5.873180873180873, "percentage": 29.37, "elapsed_time": "0:32:45", "remaining_time": "1:18:46", "throughput": 1035.85, "total_tokens": 2035472} {"current_steps": 22605, "total_steps": 76960, "loss": 0.2593, "lr": 4.449924113774765e-05, "epoch": 5.87448024948025, "percentage": 29.37, "elapsed_time": "0:32:45", "remaining_time": "1:18:46", "throughput": 1035.84, "total_tokens": 2035888} {"current_steps": 22610, "total_steps": 76960, "loss": 0.1899, "lr": 4.449569250315151e-05, "epoch": 5.875779625779626, "percentage": 29.38, "elapsed_time": "0:32:45", "remaining_time": "1:18:45", "throughput": 1035.85, "total_tokens": 2036336} {"current_steps": 22615, "total_steps": 76960, "loss": 0.1998, "lr": 4.4492142865873225e-05, "epoch": 5.877079002079002, "percentage": 29.39, "elapsed_time": "0:32:46", "remaining_time": "1:18:45", "throughput": 1035.84, "total_tokens": 2036752} {"current_steps": 22620, "total_steps": 76960, "loss": 0.4153, "lr": 4.448859222609536e-05, "epoch": 5.878378378378378, "percentage": 29.39, "elapsed_time": "0:32:46", "remaining_time": "1:18:44", "throughput": 1035.87, "total_tokens": 2037232} {"current_steps": 22625, "total_steps": 76960, "loss": 0.3149, "lr": 4.4485040584000514e-05, "epoch": 5.879677754677755, "percentage": 29.4, "elapsed_time": "0:32:47", "remaining_time": "1:18:44", "throughput": 1035.88, "total_tokens": 2037680} {"current_steps": 22630, "total_steps": 76960, "loss": 0.2525, "lr": 4.448148793977137e-05, "epoch": 5.880977130977131, "percentage": 29.4, "elapsed_time": "0:32:47", "remaining_time": "1:18:43", "throughput": 1035.89, "total_tokens": 2038144} {"current_steps": 22635, "total_steps": 76960, "loss": 0.2147, "lr": 4.447793429359063e-05, "epoch": 5.882276507276507, "percentage": 29.41, "elapsed_time": "0:32:47", "remaining_time": "1:18:43", "throughput": 1035.89, "total_tokens": 2038576} {"current_steps": 22640, "total_steps": 76960, "loss": 0.2383, "lr": 4.4474379645641064e-05, "epoch": 5.883575883575883, "percentage": 29.42, "elapsed_time": "0:32:48", "remaining_time": "1:18:42", "throughput": 1035.88, "total_tokens": 2038992} {"current_steps": 22645, "total_steps": 76960, "loss": 0.2568, "lr": 4.447082399610549e-05, "epoch": 5.88487525987526, "percentage": 29.42, "elapsed_time": "0:32:48", "remaining_time": "1:18:42", "throughput": 1035.89, "total_tokens": 2039440} {"current_steps": 22650, "total_steps": 76960, "loss": 0.2142, "lr": 4.44672673451668e-05, "epoch": 5.886174636174636, "percentage": 29.43, "elapsed_time": "0:32:49", "remaining_time": "1:18:41", "throughput": 1035.9, "total_tokens": 2039888} {"current_steps": 22655, "total_steps": 76960, "loss": 0.3103, "lr": 4.4463709693007884e-05, "epoch": 5.887474012474012, "percentage": 29.44, "elapsed_time": "0:32:49", "remaining_time": "1:18:41", "throughput": 1035.91, "total_tokens": 2040336} {"current_steps": 22660, "total_steps": 76960, "loss": 0.2715, "lr": 4.446015103981173e-05, "epoch": 5.888773388773389, "percentage": 29.44, "elapsed_time": "0:32:50", "remaining_time": "1:18:40", "throughput": 1035.93, "total_tokens": 2040816} {"current_steps": 22665, "total_steps": 76960, "loss": 0.2565, "lr": 4.445659138576136e-05, "epoch": 5.890072765072765, "percentage": 29.45, "elapsed_time": "0:32:50", "remaining_time": "1:18:40", "throughput": 1035.96, "total_tokens": 2041296} {"current_steps": 22670, "total_steps": 76960, "loss": 0.2203, "lr": 4.445303073103986e-05, "epoch": 5.891372141372141, "percentage": 29.46, "elapsed_time": "0:32:50", "remaining_time": "1:18:39", "throughput": 1035.98, "total_tokens": 2041760} {"current_steps": 22675, "total_steps": 76960, "loss": 0.2323, "lr": 4.4449469075830344e-05, "epoch": 5.892671517671518, "percentage": 29.46, "elapsed_time": "0:32:51", "remaining_time": "1:18:39", "throughput": 1035.97, "total_tokens": 2042176} {"current_steps": 22680, "total_steps": 76960, "loss": 0.2233, "lr": 4.4445906420316e-05, "epoch": 5.893970893970894, "percentage": 29.47, "elapsed_time": "0:32:51", "remaining_time": "1:18:38", "throughput": 1035.97, "total_tokens": 2042608} {"current_steps": 22685, "total_steps": 76960, "loss": 0.2176, "lr": 4.444234276468006e-05, "epoch": 5.89527027027027, "percentage": 29.48, "elapsed_time": "0:32:52", "remaining_time": "1:18:38", "throughput": 1035.96, "total_tokens": 2043024} {"current_steps": 22690, "total_steps": 76960, "loss": 0.2486, "lr": 4.44387781091058e-05, "epoch": 5.896569646569646, "percentage": 29.48, "elapsed_time": "0:32:52", "remaining_time": "1:18:37", "throughput": 1035.98, "total_tokens": 2043488} {"current_steps": 22695, "total_steps": 76960, "loss": 0.3273, "lr": 4.4435212453776553e-05, "epoch": 5.897869022869023, "percentage": 29.49, "elapsed_time": "0:32:52", "remaining_time": "1:18:37", "throughput": 1036.0, "total_tokens": 2043968} {"current_steps": 22700, "total_steps": 76960, "loss": 0.2777, "lr": 4.4431645798875715e-05, "epoch": 5.899168399168399, "percentage": 29.5, "elapsed_time": "0:32:53", "remaining_time": "1:18:36", "throughput": 1036.0, "total_tokens": 2044400} {"current_steps": 22705, "total_steps": 76960, "loss": 0.2603, "lr": 4.442807814458672e-05, "epoch": 5.900467775467775, "percentage": 29.5, "elapsed_time": "0:32:53", "remaining_time": "1:18:36", "throughput": 1036.05, "total_tokens": 2044912} {"current_steps": 22710, "total_steps": 76960, "loss": 0.2535, "lr": 4.442450949109304e-05, "epoch": 5.901767151767151, "percentage": 29.51, "elapsed_time": "0:32:54", "remaining_time": "1:18:35", "throughput": 1036.05, "total_tokens": 2045344} {"current_steps": 22715, "total_steps": 76960, "loss": 0.36, "lr": 4.4420939838578224e-05, "epoch": 5.903066528066528, "percentage": 29.52, "elapsed_time": "0:32:54", "remaining_time": "1:18:35", "throughput": 1036.08, "total_tokens": 2045840} {"current_steps": 22720, "total_steps": 76960, "loss": 0.2331, "lr": 4.441736918722587e-05, "epoch": 5.904365904365904, "percentage": 29.52, "elapsed_time": "0:32:55", "remaining_time": "1:18:34", "throughput": 1036.12, "total_tokens": 2046352} {"current_steps": 22725, "total_steps": 76960, "loss": 0.2328, "lr": 4.4413797537219605e-05, "epoch": 5.90566528066528, "percentage": 29.53, "elapsed_time": "0:32:55", "remaining_time": "1:18:34", "throughput": 1036.12, "total_tokens": 2046768} {"current_steps": 22730, "total_steps": 76960, "loss": 0.2442, "lr": 4.4410224888743136e-05, "epoch": 5.906964656964657, "percentage": 29.53, "elapsed_time": "0:32:55", "remaining_time": "1:18:34", "throughput": 1036.13, "total_tokens": 2047232} {"current_steps": 22735, "total_steps": 76960, "loss": 0.2324, "lr": 4.4406651241980205e-05, "epoch": 5.908264033264033, "percentage": 29.54, "elapsed_time": "0:32:56", "remaining_time": "1:18:33", "throughput": 1036.12, "total_tokens": 2047648} {"current_steps": 22740, "total_steps": 76960, "loss": 0.1601, "lr": 4.4403076597114605e-05, "epoch": 5.909563409563409, "percentage": 29.55, "elapsed_time": "0:32:56", "remaining_time": "1:18:33", "throughput": 1036.13, "total_tokens": 2048096} {"current_steps": 22745, "total_steps": 76960, "loss": 0.3001, "lr": 4.439950095433019e-05, "epoch": 5.910862785862786, "percentage": 29.55, "elapsed_time": "0:32:57", "remaining_time": "1:18:32", "throughput": 1036.15, "total_tokens": 2048560} {"current_steps": 22750, "total_steps": 76960, "loss": 0.3543, "lr": 4.4395924313810845e-05, "epoch": 5.912162162162162, "percentage": 29.56, "elapsed_time": "0:32:57", "remaining_time": "1:18:32", "throughput": 1036.17, "total_tokens": 2049024} {"current_steps": 22755, "total_steps": 76960, "loss": 0.2513, "lr": 4.4392346675740535e-05, "epoch": 5.913461538461538, "percentage": 29.57, "elapsed_time": "0:32:57", "remaining_time": "1:18:31", "throughput": 1036.18, "total_tokens": 2049488} {"current_steps": 22760, "total_steps": 76960, "loss": 0.2524, "lr": 4.438876804030325e-05, "epoch": 5.914760914760915, "percentage": 29.57, "elapsed_time": "0:32:58", "remaining_time": "1:18:31", "throughput": 1036.18, "total_tokens": 2049904} {"current_steps": 22765, "total_steps": 76960, "loss": 0.2611, "lr": 4.438518840768304e-05, "epoch": 5.916060291060291, "percentage": 29.58, "elapsed_time": "0:32:58", "remaining_time": "1:18:30", "throughput": 1036.17, "total_tokens": 2050320} {"current_steps": 22770, "total_steps": 76960, "loss": 0.2542, "lr": 4.438160777806403e-05, "epoch": 5.917359667359667, "percentage": 29.59, "elapsed_time": "0:32:59", "remaining_time": "1:18:30", "throughput": 1036.18, "total_tokens": 2050768} {"current_steps": 22775, "total_steps": 76960, "loss": 0.247, "lr": 4.437802615163036e-05, "epoch": 5.918659043659043, "percentage": 29.59, "elapsed_time": "0:32:59", "remaining_time": "1:18:29", "throughput": 1036.18, "total_tokens": 2051200} {"current_steps": 22780, "total_steps": 76960, "loss": 0.3364, "lr": 4.4374443528566236e-05, "epoch": 5.91995841995842, "percentage": 29.6, "elapsed_time": "0:33:00", "remaining_time": "1:18:29", "throughput": 1036.19, "total_tokens": 2051664} {"current_steps": 22785, "total_steps": 76960, "loss": 0.2952, "lr": 4.437085990905591e-05, "epoch": 5.921257796257796, "percentage": 29.61, "elapsed_time": "0:33:00", "remaining_time": "1:18:28", "throughput": 1036.21, "total_tokens": 2052128} {"current_steps": 22790, "total_steps": 76960, "loss": 0.256, "lr": 4.4367275293283704e-05, "epoch": 5.922557172557172, "percentage": 29.61, "elapsed_time": "0:33:00", "remaining_time": "1:18:28", "throughput": 1036.22, "total_tokens": 2052592} {"current_steps": 22795, "total_steps": 76960, "loss": 0.2622, "lr": 4.4363689681433974e-05, "epoch": 5.923856548856548, "percentage": 29.62, "elapsed_time": "0:33:01", "remaining_time": "1:18:27", "throughput": 1036.22, "total_tokens": 2053024} {"current_steps": 22800, "total_steps": 76960, "loss": 0.28, "lr": 4.4360103073691125e-05, "epoch": 5.925155925155925, "percentage": 29.63, "elapsed_time": "0:33:01", "remaining_time": "1:18:27", "throughput": 1036.26, "total_tokens": 2053520} {"current_steps": 22805, "total_steps": 76960, "loss": 0.2831, "lr": 4.435651547023963e-05, "epoch": 5.926455301455301, "percentage": 29.63, "elapsed_time": "0:33:02", "remaining_time": "1:18:26", "throughput": 1036.26, "total_tokens": 2053968} {"current_steps": 22810, "total_steps": 76960, "loss": 0.2516, "lr": 4.4352926871264e-05, "epoch": 5.9277546777546775, "percentage": 29.64, "elapsed_time": "0:33:02", "remaining_time": "1:18:26", "throughput": 1036.26, "total_tokens": 2054400} {"current_steps": 22815, "total_steps": 76960, "loss": 0.1545, "lr": 4.434933727694879e-05, "epoch": 5.929054054054054, "percentage": 29.65, "elapsed_time": "0:33:02", "remaining_time": "1:18:25", "throughput": 1036.27, "total_tokens": 2054848} {"current_steps": 22820, "total_steps": 76960, "loss": 0.2356, "lr": 4.4345746687478636e-05, "epoch": 5.93035343035343, "percentage": 29.65, "elapsed_time": "0:33:03", "remaining_time": "1:18:25", "throughput": 1036.27, "total_tokens": 2055280} {"current_steps": 22825, "total_steps": 76960, "loss": 0.2263, "lr": 4.4342155103038184e-05, "epoch": 5.9316528066528065, "percentage": 29.66, "elapsed_time": "0:33:03", "remaining_time": "1:18:24", "throughput": 1036.29, "total_tokens": 2055744} {"current_steps": 22830, "total_steps": 76960, "loss": 0.2176, "lr": 4.4338562523812166e-05, "epoch": 5.932952182952183, "percentage": 29.66, "elapsed_time": "0:33:04", "remaining_time": "1:18:24", "throughput": 1036.31, "total_tokens": 2056208} {"current_steps": 22835, "total_steps": 76960, "loss": 0.2598, "lr": 4.4334968949985344e-05, "epoch": 5.9342515592515594, "percentage": 29.67, "elapsed_time": "0:33:04", "remaining_time": "1:18:24", "throughput": 1036.3, "total_tokens": 2056624} {"current_steps": 22840, "total_steps": 76960, "loss": 0.3443, "lr": 4.433137438174255e-05, "epoch": 5.9355509355509355, "percentage": 29.68, "elapsed_time": "0:33:05", "remaining_time": "1:18:23", "throughput": 1036.3, "total_tokens": 2057072} {"current_steps": 22845, "total_steps": 76960, "loss": 0.2784, "lr": 4.4327778819268636e-05, "epoch": 5.9368503118503115, "percentage": 29.68, "elapsed_time": "0:33:05", "remaining_time": "1:18:23", "throughput": 1036.31, "total_tokens": 2057520} {"current_steps": 22850, "total_steps": 76960, "loss": 0.1757, "lr": 4.432418226274856e-05, "epoch": 5.9381496881496885, "percentage": 29.69, "elapsed_time": "0:33:05", "remaining_time": "1:18:22", "throughput": 1036.31, "total_tokens": 2057952} {"current_steps": 22855, "total_steps": 76960, "loss": 0.1217, "lr": 4.432058471236726e-05, "epoch": 5.9394490644490645, "percentage": 29.7, "elapsed_time": "0:33:06", "remaining_time": "1:18:22", "throughput": 1036.37, "total_tokens": 2058496} {"current_steps": 22860, "total_steps": 76960, "loss": 0.2847, "lr": 4.4316986168309774e-05, "epoch": 5.9407484407484406, "percentage": 29.7, "elapsed_time": "0:33:06", "remaining_time": "1:18:21", "throughput": 1036.38, "total_tokens": 2058944} {"current_steps": 22865, "total_steps": 76960, "loss": 0.261, "lr": 4.431338663076119e-05, "epoch": 5.942047817047817, "percentage": 29.71, "elapsed_time": "0:33:07", "remaining_time": "1:18:21", "throughput": 1036.39, "total_tokens": 2059392} {"current_steps": 22870, "total_steps": 76960, "loss": 0.2071, "lr": 4.430978609990662e-05, "epoch": 5.9433471933471935, "percentage": 29.72, "elapsed_time": "0:33:07", "remaining_time": "1:18:20", "throughput": 1036.39, "total_tokens": 2059840} {"current_steps": 22875, "total_steps": 76960, "loss": 0.1574, "lr": 4.430618457593125e-05, "epoch": 5.94464656964657, "percentage": 29.72, "elapsed_time": "0:33:07", "remaining_time": "1:18:20", "throughput": 1036.4, "total_tokens": 2060272} {"current_steps": 22880, "total_steps": 76960, "loss": 0.245, "lr": 4.4302582059020316e-05, "epoch": 5.945945945945946, "percentage": 29.73, "elapsed_time": "0:33:08", "remaining_time": "1:18:19", "throughput": 1036.4, "total_tokens": 2060720} {"current_steps": 22885, "total_steps": 76960, "loss": 0.1375, "lr": 4.4298978549359085e-05, "epoch": 5.9472453222453225, "percentage": 29.74, "elapsed_time": "0:33:08", "remaining_time": "1:18:19", "throughput": 1036.45, "total_tokens": 2061232} {"current_steps": 22890, "total_steps": 76960, "loss": 0.3888, "lr": 4.4295374047132896e-05, "epoch": 5.948544698544699, "percentage": 29.74, "elapsed_time": "0:33:09", "remaining_time": "1:18:18", "throughput": 1036.45, "total_tokens": 2061680} {"current_steps": 22895, "total_steps": 76960, "loss": 0.2666, "lr": 4.429176855252713e-05, "epoch": 5.949844074844075, "percentage": 29.75, "elapsed_time": "0:33:09", "remaining_time": "1:18:18", "throughput": 1036.46, "total_tokens": 2062128} {"current_steps": 22900, "total_steps": 76960, "loss": 0.2771, "lr": 4.4288162065727226e-05, "epoch": 5.951143451143452, "percentage": 29.76, "elapsed_time": "0:33:10", "remaining_time": "1:18:17", "throughput": 1036.48, "total_tokens": 2062608} {"current_steps": 22905, "total_steps": 76960, "loss": 0.2072, "lr": 4.428455458691866e-05, "epoch": 5.952442827442828, "percentage": 29.76, "elapsed_time": "0:33:10", "remaining_time": "1:18:17", "throughput": 1036.51, "total_tokens": 2063088} {"current_steps": 22910, "total_steps": 76960, "loss": 0.2285, "lr": 4.428094611628698e-05, "epoch": 5.953742203742204, "percentage": 29.77, "elapsed_time": "0:33:10", "remaining_time": "1:18:16", "throughput": 1036.52, "total_tokens": 2063536} {"current_steps": 22915, "total_steps": 76960, "loss": 0.2257, "lr": 4.427733665401776e-05, "epoch": 5.95504158004158, "percentage": 29.78, "elapsed_time": "0:33:11", "remaining_time": "1:18:16", "throughput": 1036.52, "total_tokens": 2063968} {"current_steps": 22920, "total_steps": 76960, "loss": 0.2011, "lr": 4.427372620029666e-05, "epoch": 5.956340956340957, "percentage": 29.78, "elapsed_time": "0:33:11", "remaining_time": "1:18:15", "throughput": 1036.54, "total_tokens": 2064448} {"current_steps": 22925, "total_steps": 76960, "loss": 0.2623, "lr": 4.427011475530934e-05, "epoch": 5.957640332640333, "percentage": 29.79, "elapsed_time": "0:33:12", "remaining_time": "1:18:15", "throughput": 1036.56, "total_tokens": 2064912} {"current_steps": 22930, "total_steps": 76960, "loss": 0.3263, "lr": 4.426650231924157e-05, "epoch": 5.958939708939709, "percentage": 29.79, "elapsed_time": "0:33:12", "remaining_time": "1:18:14", "throughput": 1036.55, "total_tokens": 2065328} {"current_steps": 22935, "total_steps": 76960, "loss": 0.2762, "lr": 4.426288889227911e-05, "epoch": 5.960239085239085, "percentage": 29.8, "elapsed_time": "0:33:12", "remaining_time": "1:18:14", "throughput": 1036.56, "total_tokens": 2065776} {"current_steps": 22940, "total_steps": 76960, "loss": 0.2053, "lr": 4.425927447460782e-05, "epoch": 5.961538461538462, "percentage": 29.81, "elapsed_time": "0:33:13", "remaining_time": "1:18:13", "throughput": 1036.58, "total_tokens": 2066256} {"current_steps": 22945, "total_steps": 76960, "loss": 0.2953, "lr": 4.4255659066413595e-05, "epoch": 5.962837837837838, "percentage": 29.81, "elapsed_time": "0:33:13", "remaining_time": "1:18:13", "throughput": 1036.59, "total_tokens": 2066704} {"current_steps": 22950, "total_steps": 76960, "loss": 0.3111, "lr": 4.425204266788238e-05, "epoch": 5.964137214137214, "percentage": 29.82, "elapsed_time": "0:33:14", "remaining_time": "1:18:13", "throughput": 1036.58, "total_tokens": 2067120} {"current_steps": 22955, "total_steps": 76960, "loss": 0.2757, "lr": 4.424842527920015e-05, "epoch": 5.965436590436591, "percentage": 29.83, "elapsed_time": "0:33:14", "remaining_time": "1:18:12", "throughput": 1036.6, "total_tokens": 2067600} {"current_steps": 22960, "total_steps": 76960, "loss": 0.2612, "lr": 4.424480690055297e-05, "epoch": 5.966735966735967, "percentage": 29.83, "elapsed_time": "0:33:15", "remaining_time": "1:18:12", "throughput": 1036.59, "total_tokens": 2068000} {"current_steps": 22965, "total_steps": 76960, "loss": 0.2112, "lr": 4.424118753212694e-05, "epoch": 5.968035343035343, "percentage": 29.84, "elapsed_time": "0:33:15", "remaining_time": "1:18:11", "throughput": 1036.61, "total_tokens": 2068480} {"current_steps": 22970, "total_steps": 76960, "loss": 0.2959, "lr": 4.4237567174108186e-05, "epoch": 5.96933471933472, "percentage": 29.85, "elapsed_time": "0:33:15", "remaining_time": "1:18:11", "throughput": 1036.64, "total_tokens": 2068976} {"current_steps": 22975, "total_steps": 76960, "loss": 0.3073, "lr": 4.423394582668293e-05, "epoch": 5.970634095634096, "percentage": 29.85, "elapsed_time": "0:33:16", "remaining_time": "1:18:10", "throughput": 1036.66, "total_tokens": 2069440} {"current_steps": 22980, "total_steps": 76960, "loss": 0.2917, "lr": 4.4230323490037405e-05, "epoch": 5.971933471933472, "percentage": 29.86, "elapsed_time": "0:33:16", "remaining_time": "1:18:10", "throughput": 1036.67, "total_tokens": 2069904} {"current_steps": 22985, "total_steps": 76960, "loss": 0.2604, "lr": 4.422670016435792e-05, "epoch": 5.973232848232849, "percentage": 29.87, "elapsed_time": "0:33:17", "remaining_time": "1:18:09", "throughput": 1036.69, "total_tokens": 2070368} {"current_steps": 22990, "total_steps": 76960, "loss": 0.3069, "lr": 4.4223075849830824e-05, "epoch": 5.974532224532225, "percentage": 29.87, "elapsed_time": "0:33:17", "remaining_time": "1:18:09", "throughput": 1036.7, "total_tokens": 2070816} {"current_steps": 22995, "total_steps": 76960, "loss": 0.2448, "lr": 4.421945054664251e-05, "epoch": 5.975831600831601, "percentage": 29.88, "elapsed_time": "0:33:17", "remaining_time": "1:18:08", "throughput": 1036.73, "total_tokens": 2071312} {"current_steps": 23000, "total_steps": 76960, "loss": 0.2937, "lr": 4.421582425497945e-05, "epoch": 5.977130977130977, "percentage": 29.89, "elapsed_time": "0:33:18", "remaining_time": "1:18:08", "throughput": 1036.75, "total_tokens": 2071776} {"current_steps": 23005, "total_steps": 76960, "loss": 0.2745, "lr": 4.421219697502814e-05, "epoch": 5.978430353430354, "percentage": 29.89, "elapsed_time": "0:33:18", "remaining_time": "1:18:07", "throughput": 1036.75, "total_tokens": 2072208} {"current_steps": 23010, "total_steps": 76960, "loss": 0.2884, "lr": 4.420856870697512e-05, "epoch": 5.97972972972973, "percentage": 29.9, "elapsed_time": "0:33:19", "remaining_time": "1:18:07", "throughput": 1036.77, "total_tokens": 2072672} {"current_steps": 23015, "total_steps": 76960, "loss": 0.2826, "lr": 4.420493945100702e-05, "epoch": 5.981029106029106, "percentage": 29.91, "elapsed_time": "0:33:19", "remaining_time": "1:18:06", "throughput": 1036.78, "total_tokens": 2073136} {"current_steps": 23020, "total_steps": 76960, "loss": 0.261, "lr": 4.420130920731047e-05, "epoch": 5.982328482328482, "percentage": 29.91, "elapsed_time": "0:33:20", "remaining_time": "1:18:06", "throughput": 1036.78, "total_tokens": 2073568} {"current_steps": 23025, "total_steps": 76960, "loss": 0.2645, "lr": 4.419767797607219e-05, "epoch": 5.983627858627859, "percentage": 29.92, "elapsed_time": "0:33:20", "remaining_time": "1:18:05", "throughput": 1036.79, "total_tokens": 2074016} {"current_steps": 23030, "total_steps": 76960, "loss": 0.2003, "lr": 4.419404575747894e-05, "epoch": 5.984927234927235, "percentage": 29.92, "elapsed_time": "0:33:20", "remaining_time": "1:18:05", "throughput": 1036.81, "total_tokens": 2074480} {"current_steps": 23035, "total_steps": 76960, "loss": 0.3067, "lr": 4.419041255171753e-05, "epoch": 5.986226611226611, "percentage": 29.93, "elapsed_time": "0:33:21", "remaining_time": "1:18:04", "throughput": 1036.81, "total_tokens": 2074928} {"current_steps": 23040, "total_steps": 76960, "loss": 0.2611, "lr": 4.4186778358974814e-05, "epoch": 5.987525987525988, "percentage": 29.94, "elapsed_time": "0:33:21", "remaining_time": "1:18:04", "throughput": 1036.84, "total_tokens": 2075408} {"current_steps": 23045, "total_steps": 76960, "loss": 0.2023, "lr": 4.41831431794377e-05, "epoch": 5.988825363825364, "percentage": 29.94, "elapsed_time": "0:33:22", "remaining_time": "1:18:03", "throughput": 1036.86, "total_tokens": 2075888} {"current_steps": 23050, "total_steps": 76960, "loss": 0.2962, "lr": 4.417950701329315e-05, "epoch": 5.99012474012474, "percentage": 29.95, "elapsed_time": "0:33:22", "remaining_time": "1:18:03", "throughput": 1036.87, "total_tokens": 2076336} {"current_steps": 23055, "total_steps": 76960, "loss": 0.2378, "lr": 4.417586986072819e-05, "epoch": 5.991424116424117, "percentage": 29.96, "elapsed_time": "0:33:22", "remaining_time": "1:18:03", "throughput": 1036.87, "total_tokens": 2076768} {"current_steps": 23060, "total_steps": 76960, "loss": 0.2325, "lr": 4.4172231721929856e-05, "epoch": 5.992723492723493, "percentage": 29.96, "elapsed_time": "0:33:23", "remaining_time": "1:18:02", "throughput": 1036.88, "total_tokens": 2077216} {"current_steps": 23065, "total_steps": 76960, "loss": 0.2872, "lr": 4.416859259708528e-05, "epoch": 5.994022869022869, "percentage": 29.97, "elapsed_time": "0:33:23", "remaining_time": "1:18:02", "throughput": 1036.88, "total_tokens": 2077648} {"current_steps": 23070, "total_steps": 76960, "loss": 0.2476, "lr": 4.4164952486381616e-05, "epoch": 5.995322245322245, "percentage": 29.98, "elapsed_time": "0:33:24", "remaining_time": "1:18:01", "throughput": 1036.86, "total_tokens": 2078048} {"current_steps": 23075, "total_steps": 76960, "loss": 0.2422, "lr": 4.4161311390006085e-05, "epoch": 5.996621621621622, "percentage": 29.98, "elapsed_time": "0:33:24", "remaining_time": "1:18:01", "throughput": 1036.87, "total_tokens": 2078496} {"current_steps": 23080, "total_steps": 76960, "loss": 0.2665, "lr": 4.415766930814595e-05, "epoch": 5.997920997920998, "percentage": 29.99, "elapsed_time": "0:33:24", "remaining_time": "1:18:00", "throughput": 1036.87, "total_tokens": 2078928} {"current_steps": 23085, "total_steps": 76960, "loss": 0.1872, "lr": 4.415402624098853e-05, "epoch": 5.999220374220374, "percentage": 30.0, "elapsed_time": "0:33:25", "remaining_time": "1:18:00", "throughput": 1036.91, "total_tokens": 2079424} {"current_steps": 23088, "total_steps": 76960, "eval_loss": 0.2394219934940338, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:33:38", "remaining_time": "1:18:30", "throughput": 1030.09, "total_tokens": 2079640} {"current_steps": 23090, "total_steps": 76960, "loss": 0.2024, "lr": 4.4150382188721184e-05, "epoch": 6.000519750519751, "percentage": 30.0, "elapsed_time": "0:33:40", "remaining_time": "1:18:34", "throughput": 1029.28, "total_tokens": 2079800} {"current_steps": 23095, "total_steps": 76960, "loss": 0.2395, "lr": 4.414673715153134e-05, "epoch": 6.001819126819127, "percentage": 30.01, "elapsed_time": "0:33:41", "remaining_time": "1:18:33", "throughput": 1029.28, "total_tokens": 2080248} {"current_steps": 23100, "total_steps": 76960, "loss": 0.2066, "lr": 4.414309112960645e-05, "epoch": 6.003118503118503, "percentage": 30.02, "elapsed_time": "0:33:41", "remaining_time": "1:18:33", "throughput": 1029.27, "total_tokens": 2080680} {"current_steps": 23105, "total_steps": 76960, "loss": 0.1966, "lr": 4.413944412313405e-05, "epoch": 6.004417879417879, "percentage": 30.02, "elapsed_time": "0:33:41", "remaining_time": "1:18:32", "throughput": 1029.3, "total_tokens": 2081176} {"current_steps": 23110, "total_steps": 76960, "loss": 0.1575, "lr": 4.413579613230169e-05, "epoch": 6.005717255717256, "percentage": 30.03, "elapsed_time": "0:33:42", "remaining_time": "1:18:32", "throughput": 1029.29, "total_tokens": 2081592} {"current_steps": 23115, "total_steps": 76960, "loss": 0.1409, "lr": 4.4132147157297e-05, "epoch": 6.007016632016632, "percentage": 30.04, "elapsed_time": "0:33:42", "remaining_time": "1:18:31", "throughput": 1029.28, "total_tokens": 2082024} {"current_steps": 23120, "total_steps": 76960, "loss": 0.2236, "lr": 4.412849719830765e-05, "epoch": 6.008316008316008, "percentage": 30.04, "elapsed_time": "0:33:43", "remaining_time": "1:18:31", "throughput": 1029.29, "total_tokens": 2082472} {"current_steps": 23125, "total_steps": 76960, "loss": 0.2259, "lr": 4.412484625552137e-05, "epoch": 6.009615384615385, "percentage": 30.05, "elapsed_time": "0:33:43", "remaining_time": "1:18:31", "throughput": 1029.28, "total_tokens": 2082888} {"current_steps": 23130, "total_steps": 76960, "loss": 0.2525, "lr": 4.412119432912592e-05, "epoch": 6.010914760914761, "percentage": 30.05, "elapsed_time": "0:33:44", "remaining_time": "1:18:30", "throughput": 1029.31, "total_tokens": 2083384} {"current_steps": 23135, "total_steps": 76960, "loss": 0.3148, "lr": 4.411754141930912e-05, "epoch": 6.012214137214137, "percentage": 30.06, "elapsed_time": "0:33:44", "remaining_time": "1:18:30", "throughput": 1029.32, "total_tokens": 2083832} {"current_steps": 23140, "total_steps": 76960, "loss": 0.3056, "lr": 4.411388752625885e-05, "epoch": 6.013513513513513, "percentage": 30.07, "elapsed_time": "0:33:44", "remaining_time": "1:18:29", "throughput": 1029.33, "total_tokens": 2084280} {"current_steps": 23145, "total_steps": 76960, "loss": 0.2948, "lr": 4.411023265016303e-05, "epoch": 6.01481288981289, "percentage": 30.07, "elapsed_time": "0:33:45", "remaining_time": "1:18:29", "throughput": 1029.33, "total_tokens": 2084712} {"current_steps": 23150, "total_steps": 76960, "loss": 0.2354, "lr": 4.410657679120964e-05, "epoch": 6.016112266112266, "percentage": 30.08, "elapsed_time": "0:33:45", "remaining_time": "1:18:28", "throughput": 1029.33, "total_tokens": 2085144} {"current_steps": 23155, "total_steps": 76960, "loss": 0.2789, "lr": 4.410291994958669e-05, "epoch": 6.017411642411642, "percentage": 30.09, "elapsed_time": "0:33:46", "remaining_time": "1:18:28", "throughput": 1029.35, "total_tokens": 2085608} {"current_steps": 23160, "total_steps": 76960, "loss": 0.1912, "lr": 4.409926212548227e-05, "epoch": 6.018711018711019, "percentage": 30.09, "elapsed_time": "0:33:46", "remaining_time": "1:18:27", "throughput": 1029.35, "total_tokens": 2086040} {"current_steps": 23165, "total_steps": 76960, "loss": 0.2327, "lr": 4.409560331908449e-05, "epoch": 6.020010395010395, "percentage": 30.1, "elapsed_time": "0:33:46", "remaining_time": "1:18:27", "throughput": 1029.36, "total_tokens": 2086504} {"current_steps": 23170, "total_steps": 76960, "loss": 0.2127, "lr": 4.4091943530581534e-05, "epoch": 6.021309771309771, "percentage": 30.11, "elapsed_time": "0:33:47", "remaining_time": "1:18:26", "throughput": 1029.37, "total_tokens": 2086952} {"current_steps": 23175, "total_steps": 76960, "loss": 0.2621, "lr": 4.408828276016164e-05, "epoch": 6.022609147609147, "percentage": 30.11, "elapsed_time": "0:33:47", "remaining_time": "1:18:26", "throughput": 1029.38, "total_tokens": 2087400} {"current_steps": 23180, "total_steps": 76960, "loss": 0.3548, "lr": 4.408462100801307e-05, "epoch": 6.023908523908524, "percentage": 30.12, "elapsed_time": "0:33:48", "remaining_time": "1:18:25", "throughput": 1029.38, "total_tokens": 2087832} {"current_steps": 23185, "total_steps": 76960, "loss": 0.267, "lr": 4.4080958274324155e-05, "epoch": 6.0252079002079, "percentage": 30.13, "elapsed_time": "0:33:48", "remaining_time": "1:18:25", "throughput": 1029.4, "total_tokens": 2088296} {"current_steps": 23190, "total_steps": 76960, "loss": 0.2688, "lr": 4.4077294559283274e-05, "epoch": 6.026507276507276, "percentage": 30.13, "elapsed_time": "0:33:49", "remaining_time": "1:18:24", "throughput": 1029.42, "total_tokens": 2088760} {"current_steps": 23195, "total_steps": 76960, "loss": 0.2333, "lr": 4.407362986307886e-05, "epoch": 6.027806652806653, "percentage": 30.14, "elapsed_time": "0:33:49", "remaining_time": "1:18:24", "throughput": 1029.41, "total_tokens": 2089176} {"current_steps": 23200, "total_steps": 76960, "loss": 0.2642, "lr": 4.406996418589937e-05, "epoch": 6.029106029106029, "percentage": 30.15, "elapsed_time": "0:33:49", "remaining_time": "1:18:23", "throughput": 1029.43, "total_tokens": 2089656} {"current_steps": 23205, "total_steps": 76960, "loss": 0.2267, "lr": 4.406629752793336e-05, "epoch": 6.030405405405405, "percentage": 30.15, "elapsed_time": "0:33:50", "remaining_time": "1:18:23", "throughput": 1029.46, "total_tokens": 2090136} {"current_steps": 23210, "total_steps": 76960, "loss": 0.3327, "lr": 4.406262988936941e-05, "epoch": 6.031704781704781, "percentage": 30.16, "elapsed_time": "0:33:50", "remaining_time": "1:18:22", "throughput": 1029.48, "total_tokens": 2090616} {"current_steps": 23215, "total_steps": 76960, "loss": 0.3163, "lr": 4.4058961270396125e-05, "epoch": 6.033004158004158, "percentage": 30.17, "elapsed_time": "0:33:51", "remaining_time": "1:18:22", "throughput": 1029.49, "total_tokens": 2091064} {"current_steps": 23220, "total_steps": 76960, "loss": 0.3137, "lr": 4.405529167120221e-05, "epoch": 6.034303534303534, "percentage": 30.17, "elapsed_time": "0:33:51", "remaining_time": "1:18:21", "throughput": 1029.5, "total_tokens": 2091512} {"current_steps": 23225, "total_steps": 76960, "loss": 0.2653, "lr": 4.405162109197638e-05, "epoch": 6.03560291060291, "percentage": 30.18, "elapsed_time": "0:33:51", "remaining_time": "1:18:21", "throughput": 1029.5, "total_tokens": 2091944} {"current_steps": 23230, "total_steps": 76960, "loss": 0.2776, "lr": 4.404794953290743e-05, "epoch": 6.036902286902287, "percentage": 30.18, "elapsed_time": "0:33:52", "remaining_time": "1:18:20", "throughput": 1029.52, "total_tokens": 2092408} {"current_steps": 23235, "total_steps": 76960, "loss": 0.2461, "lr": 4.4044276994184175e-05, "epoch": 6.038201663201663, "percentage": 30.19, "elapsed_time": "0:33:52", "remaining_time": "1:18:20", "throughput": 1029.53, "total_tokens": 2092856} {"current_steps": 23240, "total_steps": 76960, "loss": 0.1722, "lr": 4.404060347599551e-05, "epoch": 6.039501039501039, "percentage": 30.2, "elapsed_time": "0:33:53", "remaining_time": "1:18:19", "throughput": 1029.54, "total_tokens": 2093320} {"current_steps": 23245, "total_steps": 76960, "loss": 0.2554, "lr": 4.403692897853037e-05, "epoch": 6.040800415800415, "percentage": 30.2, "elapsed_time": "0:33:53", "remaining_time": "1:18:19", "throughput": 1029.55, "total_tokens": 2093768} {"current_steps": 23250, "total_steps": 76960, "loss": 0.141, "lr": 4.403325350197773e-05, "epoch": 6.042099792099792, "percentage": 30.21, "elapsed_time": "0:33:54", "remaining_time": "1:18:18", "throughput": 1029.55, "total_tokens": 2094200} {"current_steps": 23255, "total_steps": 76960, "loss": 0.218, "lr": 4.402957704652662e-05, "epoch": 6.043399168399168, "percentage": 30.22, "elapsed_time": "0:33:54", "remaining_time": "1:18:18", "throughput": 1029.55, "total_tokens": 2094632} {"current_steps": 23260, "total_steps": 76960, "loss": 0.3434, "lr": 4.4025899612366134e-05, "epoch": 6.044698544698544, "percentage": 30.22, "elapsed_time": "0:33:54", "remaining_time": "1:18:17", "throughput": 1029.56, "total_tokens": 2095064} {"current_steps": 23265, "total_steps": 76960, "loss": 0.2092, "lr": 4.40222211996854e-05, "epoch": 6.045997920997921, "percentage": 30.23, "elapsed_time": "0:33:55", "remaining_time": "1:18:17", "throughput": 1029.58, "total_tokens": 2095528} {"current_steps": 23270, "total_steps": 76960, "loss": 0.3067, "lr": 4.401854180867361e-05, "epoch": 6.047297297297297, "percentage": 30.24, "elapsed_time": "0:33:55", "remaining_time": "1:18:17", "throughput": 1029.59, "total_tokens": 2095992} {"current_steps": 23275, "total_steps": 76960, "loss": 0.2197, "lr": 4.4014861439519987e-05, "epoch": 6.048596673596673, "percentage": 30.24, "elapsed_time": "0:33:56", "remaining_time": "1:18:16", "throughput": 1029.6, "total_tokens": 2096440} {"current_steps": 23280, "total_steps": 76960, "loss": 0.1995, "lr": 4.401118009241382e-05, "epoch": 6.04989604989605, "percentage": 30.25, "elapsed_time": "0:33:56", "remaining_time": "1:18:16", "throughput": 1029.58, "total_tokens": 2096840} {"current_steps": 23285, "total_steps": 76960, "loss": 0.2266, "lr": 4.4007497767544435e-05, "epoch": 6.051195426195426, "percentage": 30.26, "elapsed_time": "0:33:57", "remaining_time": "1:18:15", "throughput": 1029.59, "total_tokens": 2097288} {"current_steps": 23290, "total_steps": 76960, "loss": 0.3374, "lr": 4.400381446510124e-05, "epoch": 6.052494802494802, "percentage": 30.26, "elapsed_time": "0:33:57", "remaining_time": "1:18:15", "throughput": 1029.64, "total_tokens": 2097816} {"current_steps": 23295, "total_steps": 76960, "loss": 0.295, "lr": 4.400013018527366e-05, "epoch": 6.0537941787941785, "percentage": 30.27, "elapsed_time": "0:33:57", "remaining_time": "1:18:14", "throughput": 1029.67, "total_tokens": 2098296} {"current_steps": 23300, "total_steps": 76960, "loss": 0.1885, "lr": 4.3996444928251174e-05, "epoch": 6.055093555093555, "percentage": 30.28, "elapsed_time": "0:33:58", "remaining_time": "1:18:14", "throughput": 1029.68, "total_tokens": 2098744} {"current_steps": 23305, "total_steps": 76960, "loss": 0.1835, "lr": 4.3992758694223326e-05, "epoch": 6.0563929313929314, "percentage": 30.28, "elapsed_time": "0:33:58", "remaining_time": "1:18:13", "throughput": 1029.68, "total_tokens": 2099176} {"current_steps": 23310, "total_steps": 76960, "loss": 0.1527, "lr": 4.39890714833797e-05, "epoch": 6.0576923076923075, "percentage": 30.29, "elapsed_time": "0:33:59", "remaining_time": "1:18:13", "throughput": 1029.7, "total_tokens": 2099656} {"current_steps": 23315, "total_steps": 76960, "loss": 0.2602, "lr": 4.398538329590993e-05, "epoch": 6.058991683991684, "percentage": 30.29, "elapsed_time": "0:33:59", "remaining_time": "1:18:12", "throughput": 1029.74, "total_tokens": 2100152} {"current_steps": 23320, "total_steps": 76960, "loss": 0.2117, "lr": 4.398169413200371e-05, "epoch": 6.0602910602910605, "percentage": 30.3, "elapsed_time": "0:33:59", "remaining_time": "1:18:12", "throughput": 1029.74, "total_tokens": 2100584} {"current_steps": 23325, "total_steps": 76960, "loss": 0.0865, "lr": 4.397800399185077e-05, "epoch": 6.0615904365904365, "percentage": 30.31, "elapsed_time": "0:34:00", "remaining_time": "1:18:11", "throughput": 1029.73, "total_tokens": 2101000} {"current_steps": 23330, "total_steps": 76960, "loss": 0.3301, "lr": 4.397431287564091e-05, "epoch": 6.0628898128898125, "percentage": 30.31, "elapsed_time": "0:34:00", "remaining_time": "1:18:11", "throughput": 1029.73, "total_tokens": 2101432} {"current_steps": 23335, "total_steps": 76960, "loss": 0.2555, "lr": 4.397062078356395e-05, "epoch": 6.0641891891891895, "percentage": 30.32, "elapsed_time": "0:34:01", "remaining_time": "1:18:10", "throughput": 1029.75, "total_tokens": 2101896} {"current_steps": 23340, "total_steps": 76960, "loss": 0.1926, "lr": 4.396692771580979e-05, "epoch": 6.0654885654885655, "percentage": 30.33, "elapsed_time": "0:34:01", "remaining_time": "1:18:10", "throughput": 1029.76, "total_tokens": 2102344} {"current_steps": 23345, "total_steps": 76960, "loss": 0.2936, "lr": 4.396323367256836e-05, "epoch": 6.066787941787942, "percentage": 30.33, "elapsed_time": "0:34:02", "remaining_time": "1:18:09", "throughput": 1029.77, "total_tokens": 2102792} {"current_steps": 23350, "total_steps": 76960, "loss": 0.3096, "lr": 4.395953865402966e-05, "epoch": 6.0680873180873185, "percentage": 30.34, "elapsed_time": "0:34:02", "remaining_time": "1:18:09", "throughput": 1029.77, "total_tokens": 2103224} {"current_steps": 23355, "total_steps": 76960, "loss": 0.2176, "lr": 4.395584266038372e-05, "epoch": 6.0693866943866945, "percentage": 30.35, "elapsed_time": "0:34:02", "remaining_time": "1:18:08", "throughput": 1029.79, "total_tokens": 2103704} {"current_steps": 23360, "total_steps": 76960, "loss": 0.2239, "lr": 4.395214569182062e-05, "epoch": 6.070686070686071, "percentage": 30.35, "elapsed_time": "0:34:03", "remaining_time": "1:18:08", "throughput": 1029.79, "total_tokens": 2104120} {"current_steps": 23365, "total_steps": 76960, "loss": 0.2178, "lr": 4.394844774853051e-05, "epoch": 6.071985446985447, "percentage": 30.36, "elapsed_time": "0:34:03", "remaining_time": "1:18:07", "throughput": 1029.8, "total_tokens": 2104568} {"current_steps": 23370, "total_steps": 76960, "loss": 0.2073, "lr": 4.3944748830703586e-05, "epoch": 6.0732848232848236, "percentage": 30.37, "elapsed_time": "0:34:04", "remaining_time": "1:18:07", "throughput": 1029.8, "total_tokens": 2105000} {"current_steps": 23375, "total_steps": 76960, "loss": 0.2762, "lr": 4.394104893853007e-05, "epoch": 6.0745841995842, "percentage": 30.37, "elapsed_time": "0:34:04", "remaining_time": "1:18:06", "throughput": 1029.81, "total_tokens": 2105448} {"current_steps": 23380, "total_steps": 76960, "loss": 0.2621, "lr": 4.393734807220026e-05, "epoch": 6.075883575883576, "percentage": 30.38, "elapsed_time": "0:34:04", "remaining_time": "1:18:06", "throughput": 1029.81, "total_tokens": 2105880} {"current_steps": 23385, "total_steps": 76960, "loss": 0.3066, "lr": 4.3933646231904504e-05, "epoch": 6.077182952182953, "percentage": 30.39, "elapsed_time": "0:34:05", "remaining_time": "1:18:05", "throughput": 1029.84, "total_tokens": 2106360} {"current_steps": 23390, "total_steps": 76960, "loss": 0.3473, "lr": 4.3929943417833166e-05, "epoch": 6.078482328482329, "percentage": 30.39, "elapsed_time": "0:34:05", "remaining_time": "1:18:05", "throughput": 1029.83, "total_tokens": 2106776} {"current_steps": 23395, "total_steps": 76960, "loss": 0.2367, "lr": 4.3926239630176703e-05, "epoch": 6.079781704781705, "percentage": 30.4, "elapsed_time": "0:34:06", "remaining_time": "1:18:04", "throughput": 1029.83, "total_tokens": 2107208} {"current_steps": 23400, "total_steps": 76960, "loss": 0.2526, "lr": 4.392253486912561e-05, "epoch": 6.081081081081081, "percentage": 30.41, "elapsed_time": "0:34:06", "remaining_time": "1:18:04", "throughput": 1029.84, "total_tokens": 2107656} {"current_steps": 23405, "total_steps": 76960, "loss": 0.2785, "lr": 4.391882913487041e-05, "epoch": 6.082380457380458, "percentage": 30.41, "elapsed_time": "0:34:06", "remaining_time": "1:18:03", "throughput": 1029.84, "total_tokens": 2108088} {"current_steps": 23410, "total_steps": 76960, "loss": 0.1797, "lr": 4.39151224276017e-05, "epoch": 6.083679833679834, "percentage": 30.42, "elapsed_time": "0:34:07", "remaining_time": "1:18:03", "throughput": 1029.88, "total_tokens": 2108584} {"current_steps": 23415, "total_steps": 76960, "loss": 0.2531, "lr": 4.3911414747510126e-05, "epoch": 6.08497920997921, "percentage": 30.42, "elapsed_time": "0:34:07", "remaining_time": "1:18:02", "throughput": 1029.91, "total_tokens": 2109080} {"current_steps": 23420, "total_steps": 76960, "loss": 0.2251, "lr": 4.3907706094786364e-05, "epoch": 6.086278586278587, "percentage": 30.43, "elapsed_time": "0:34:08", "remaining_time": "1:18:02", "throughput": 1029.92, "total_tokens": 2109528} {"current_steps": 23425, "total_steps": 76960, "loss": 0.2428, "lr": 4.390399646962117e-05, "epoch": 6.087577962577963, "percentage": 30.44, "elapsed_time": "0:34:08", "remaining_time": "1:18:01", "throughput": 1029.94, "total_tokens": 2109992} {"current_steps": 23430, "total_steps": 76960, "loss": 0.2997, "lr": 4.390028587220531e-05, "epoch": 6.088877338877339, "percentage": 30.44, "elapsed_time": "0:34:09", "remaining_time": "1:18:01", "throughput": 1029.95, "total_tokens": 2110440} {"current_steps": 23435, "total_steps": 76960, "loss": 0.1268, "lr": 4.3896574302729655e-05, "epoch": 6.090176715176715, "percentage": 30.45, "elapsed_time": "0:34:09", "remaining_time": "1:18:00", "throughput": 1029.93, "total_tokens": 2110840} {"current_steps": 23440, "total_steps": 76960, "loss": 0.4115, "lr": 4.3892861761385076e-05, "epoch": 6.091476091476092, "percentage": 30.46, "elapsed_time": "0:34:09", "remaining_time": "1:18:00", "throughput": 1029.93, "total_tokens": 2111272} {"current_steps": 23445, "total_steps": 76960, "loss": 0.2467, "lr": 4.3889148248362506e-05, "epoch": 6.092775467775468, "percentage": 30.46, "elapsed_time": "0:34:10", "remaining_time": "1:18:00", "throughput": 1029.94, "total_tokens": 2111704} {"current_steps": 23450, "total_steps": 76960, "loss": 0.2215, "lr": 4.3885433763852945e-05, "epoch": 6.094074844074844, "percentage": 30.47, "elapsed_time": "0:34:10", "remaining_time": "1:17:59", "throughput": 1029.94, "total_tokens": 2112136} {"current_steps": 23455, "total_steps": 76960, "loss": 0.302, "lr": 4.388171830804743e-05, "epoch": 6.095374220374221, "percentage": 30.48, "elapsed_time": "0:34:11", "remaining_time": "1:17:59", "throughput": 1029.95, "total_tokens": 2112600} {"current_steps": 23460, "total_steps": 76960, "loss": 0.23, "lr": 4.3878001881137054e-05, "epoch": 6.096673596673597, "percentage": 30.48, "elapsed_time": "0:34:11", "remaining_time": "1:17:58", "throughput": 1029.95, "total_tokens": 2113016} {"current_steps": 23465, "total_steps": 76960, "loss": 0.238, "lr": 4.387428448331295e-05, "epoch": 6.097972972972973, "percentage": 30.49, "elapsed_time": "0:34:11", "remaining_time": "1:17:58", "throughput": 1029.95, "total_tokens": 2113448} {"current_steps": 23470, "total_steps": 76960, "loss": 0.3056, "lr": 4.387056611476631e-05, "epoch": 6.099272349272349, "percentage": 30.5, "elapsed_time": "0:34:12", "remaining_time": "1:17:57", "throughput": 1029.97, "total_tokens": 2113912} {"current_steps": 23475, "total_steps": 76960, "loss": 0.3222, "lr": 4.386684677568838e-05, "epoch": 6.100571725571726, "percentage": 30.5, "elapsed_time": "0:34:12", "remaining_time": "1:17:57", "throughput": 1029.98, "total_tokens": 2114360} {"current_steps": 23480, "total_steps": 76960, "loss": 0.2736, "lr": 4.3863126466270436e-05, "epoch": 6.101871101871102, "percentage": 30.51, "elapsed_time": "0:34:13", "remaining_time": "1:17:56", "throughput": 1029.99, "total_tokens": 2114824} {"current_steps": 23485, "total_steps": 76960, "loss": 0.2805, "lr": 4.3859405186703825e-05, "epoch": 6.103170478170478, "percentage": 30.52, "elapsed_time": "0:34:13", "remaining_time": "1:17:56", "throughput": 1030.01, "total_tokens": 2115288} {"current_steps": 23490, "total_steps": 76960, "loss": 0.3335, "lr": 4.3855682937179945e-05, "epoch": 6.104469854469855, "percentage": 30.52, "elapsed_time": "0:34:14", "remaining_time": "1:17:55", "throughput": 1030.03, "total_tokens": 2115752} {"current_steps": 23495, "total_steps": 76960, "loss": 0.2332, "lr": 4.385195971789021e-05, "epoch": 6.105769230769231, "percentage": 30.53, "elapsed_time": "0:34:14", "remaining_time": "1:17:55", "throughput": 1030.07, "total_tokens": 2116280} {"current_steps": 23500, "total_steps": 76960, "loss": 0.3931, "lr": 4.384823552902613e-05, "epoch": 6.107068607068607, "percentage": 30.54, "elapsed_time": "0:34:14", "remaining_time": "1:17:54", "throughput": 1030.09, "total_tokens": 2116744} {"current_steps": 23505, "total_steps": 76960, "loss": 0.251, "lr": 4.384451037077924e-05, "epoch": 6.108367983367984, "percentage": 30.54, "elapsed_time": "0:34:15", "remaining_time": "1:17:54", "throughput": 1030.1, "total_tokens": 2117192} {"current_steps": 23510, "total_steps": 76960, "loss": 0.2638, "lr": 4.3840784243341126e-05, "epoch": 6.10966735966736, "percentage": 30.55, "elapsed_time": "0:34:15", "remaining_time": "1:17:53", "throughput": 1030.12, "total_tokens": 2117672} {"current_steps": 23515, "total_steps": 76960, "loss": 0.2739, "lr": 4.383705714690342e-05, "epoch": 6.110966735966736, "percentage": 30.55, "elapsed_time": "0:34:16", "remaining_time": "1:17:53", "throughput": 1030.16, "total_tokens": 2118168} {"current_steps": 23520, "total_steps": 76960, "loss": 0.216, "lr": 4.383332908165782e-05, "epoch": 6.112266112266112, "percentage": 30.56, "elapsed_time": "0:34:16", "remaining_time": "1:17:52", "throughput": 1030.17, "total_tokens": 2118616} {"current_steps": 23525, "total_steps": 76960, "loss": 0.1962, "lr": 4.382960004779606e-05, "epoch": 6.113565488565489, "percentage": 30.57, "elapsed_time": "0:34:16", "remaining_time": "1:17:52", "throughput": 1030.18, "total_tokens": 2119080} {"current_steps": 23530, "total_steps": 76960, "loss": 0.2963, "lr": 4.382587004550993e-05, "epoch": 6.114864864864865, "percentage": 30.57, "elapsed_time": "0:34:17", "remaining_time": "1:17:51", "throughput": 1030.22, "total_tokens": 2119576} {"current_steps": 23535, "total_steps": 76960, "loss": 0.3278, "lr": 4.3822139074991264e-05, "epoch": 6.116164241164241, "percentage": 30.58, "elapsed_time": "0:34:17", "remaining_time": "1:17:51", "throughput": 1030.26, "total_tokens": 2120088} {"current_steps": 23540, "total_steps": 76960, "loss": 0.3555, "lr": 4.381840713643195e-05, "epoch": 6.117463617463618, "percentage": 30.59, "elapsed_time": "0:34:18", "remaining_time": "1:17:50", "throughput": 1030.26, "total_tokens": 2120520} {"current_steps": 23545, "total_steps": 76960, "loss": 0.2383, "lr": 4.381467423002392e-05, "epoch": 6.118762993762994, "percentage": 30.59, "elapsed_time": "0:34:18", "remaining_time": "1:17:50", "throughput": 1030.29, "total_tokens": 2121032} {"current_steps": 23550, "total_steps": 76960, "loss": 0.2074, "lr": 4.381094035595917e-05, "epoch": 6.12006237006237, "percentage": 30.6, "elapsed_time": "0:34:19", "remaining_time": "1:17:49", "throughput": 1030.31, "total_tokens": 2121496} {"current_steps": 23555, "total_steps": 76960, "loss": 0.2293, "lr": 4.3807205514429736e-05, "epoch": 6.121361746361746, "percentage": 30.61, "elapsed_time": "0:34:19", "remaining_time": "1:17:49", "throughput": 1030.31, "total_tokens": 2121928} {"current_steps": 23560, "total_steps": 76960, "loss": 0.2135, "lr": 4.380346970562771e-05, "epoch": 6.122661122661123, "percentage": 30.61, "elapsed_time": "0:34:19", "remaining_time": "1:17:48", "throughput": 1030.32, "total_tokens": 2122376} {"current_steps": 23565, "total_steps": 76960, "loss": 0.129, "lr": 4.3799732929745214e-05, "epoch": 6.123960498960499, "percentage": 30.62, "elapsed_time": "0:34:20", "remaining_time": "1:17:48", "throughput": 1030.34, "total_tokens": 2122840} {"current_steps": 23570, "total_steps": 76960, "loss": 0.2666, "lr": 4.379599518697444e-05, "epoch": 6.125259875259875, "percentage": 30.63, "elapsed_time": "0:34:20", "remaining_time": "1:17:47", "throughput": 1030.36, "total_tokens": 2123304} {"current_steps": 23575, "total_steps": 76960, "loss": 0.2711, "lr": 4.379225647750762e-05, "epoch": 6.126559251559252, "percentage": 30.63, "elapsed_time": "0:34:21", "remaining_time": "1:17:47", "throughput": 1030.35, "total_tokens": 2123720} {"current_steps": 23580, "total_steps": 76960, "loss": 0.3145, "lr": 4.378851680153705e-05, "epoch": 6.127858627858628, "percentage": 30.64, "elapsed_time": "0:34:21", "remaining_time": "1:17:46", "throughput": 1030.37, "total_tokens": 2124184} {"current_steps": 23585, "total_steps": 76960, "loss": 0.2083, "lr": 4.378477615925505e-05, "epoch": 6.129158004158004, "percentage": 30.65, "elapsed_time": "0:34:21", "remaining_time": "1:17:46", "throughput": 1030.38, "total_tokens": 2124632} {"current_steps": 23590, "total_steps": 76960, "loss": 0.2529, "lr": 4.378103455085402e-05, "epoch": 6.13045738045738, "percentage": 30.65, "elapsed_time": "0:34:22", "remaining_time": "1:17:45", "throughput": 1030.41, "total_tokens": 2125128} {"current_steps": 23595, "total_steps": 76960, "loss": 0.2102, "lr": 4.377729197652639e-05, "epoch": 6.131756756756757, "percentage": 30.66, "elapsed_time": "0:34:22", "remaining_time": "1:17:45", "throughput": 1030.42, "total_tokens": 2125576} {"current_steps": 23600, "total_steps": 76960, "loss": 0.1673, "lr": 4.377354843646464e-05, "epoch": 6.133056133056133, "percentage": 30.67, "elapsed_time": "0:34:23", "remaining_time": "1:17:45", "throughput": 1030.41, "total_tokens": 2125976} {"current_steps": 23605, "total_steps": 76960, "loss": 0.2091, "lr": 4.376980393086131e-05, "epoch": 6.134355509355509, "percentage": 30.67, "elapsed_time": "0:34:23", "remaining_time": "1:17:44", "throughput": 1030.41, "total_tokens": 2126408} {"current_steps": 23610, "total_steps": 76960, "loss": 0.3054, "lr": 4.376605845990897e-05, "epoch": 6.135654885654886, "percentage": 30.68, "elapsed_time": "0:34:24", "remaining_time": "1:17:44", "throughput": 1030.42, "total_tokens": 2126856} {"current_steps": 23615, "total_steps": 76960, "loss": 0.3873, "lr": 4.376231202380027e-05, "epoch": 6.136954261954262, "percentage": 30.68, "elapsed_time": "0:34:24", "remaining_time": "1:17:43", "throughput": 1030.43, "total_tokens": 2127320} {"current_steps": 23620, "total_steps": 76960, "loss": 0.2675, "lr": 4.375856462272788e-05, "epoch": 6.138253638253638, "percentage": 30.69, "elapsed_time": "0:34:24", "remaining_time": "1:17:43", "throughput": 1030.44, "total_tokens": 2127768} {"current_steps": 23625, "total_steps": 76960, "loss": 0.261, "lr": 4.375481625688454e-05, "epoch": 6.139553014553014, "percentage": 30.7, "elapsed_time": "0:34:25", "remaining_time": "1:17:42", "throughput": 1030.45, "total_tokens": 2128216} {"current_steps": 23630, "total_steps": 76960, "loss": 0.2065, "lr": 4.375106692646304e-05, "epoch": 6.140852390852391, "percentage": 30.7, "elapsed_time": "0:34:25", "remaining_time": "1:17:42", "throughput": 1030.48, "total_tokens": 2128696} {"current_steps": 23635, "total_steps": 76960, "loss": 0.2886, "lr": 4.374731663165619e-05, "epoch": 6.142151767151767, "percentage": 30.71, "elapsed_time": "0:34:26", "remaining_time": "1:17:41", "throughput": 1030.49, "total_tokens": 2129144} {"current_steps": 23640, "total_steps": 76960, "loss": 0.3216, "lr": 4.374356537265688e-05, "epoch": 6.143451143451143, "percentage": 30.72, "elapsed_time": "0:34:26", "remaining_time": "1:17:41", "throughput": 1030.49, "total_tokens": 2129576} {"current_steps": 23645, "total_steps": 76960, "loss": 0.2952, "lr": 4.373981314965805e-05, "epoch": 6.14475051975052, "percentage": 30.72, "elapsed_time": "0:34:26", "remaining_time": "1:17:40", "throughput": 1030.51, "total_tokens": 2130040} {"current_steps": 23650, "total_steps": 76960, "loss": 0.2766, "lr": 4.373605996285267e-05, "epoch": 6.146049896049896, "percentage": 30.73, "elapsed_time": "0:34:27", "remaining_time": "1:17:40", "throughput": 1030.51, "total_tokens": 2130488} {"current_steps": 23655, "total_steps": 76960, "loss": 0.2446, "lr": 4.3732305812433774e-05, "epoch": 6.147349272349272, "percentage": 30.74, "elapsed_time": "0:34:27", "remaining_time": "1:17:39", "throughput": 1030.52, "total_tokens": 2130936} {"current_steps": 23660, "total_steps": 76960, "loss": 0.2742, "lr": 4.372855069859445e-05, "epoch": 6.148648648648648, "percentage": 30.74, "elapsed_time": "0:34:28", "remaining_time": "1:17:39", "throughput": 1030.54, "total_tokens": 2131400} {"current_steps": 23665, "total_steps": 76960, "loss": 0.2382, "lr": 4.372479462152781e-05, "epoch": 6.149948024948025, "percentage": 30.75, "elapsed_time": "0:34:28", "remaining_time": "1:17:38", "throughput": 1030.52, "total_tokens": 2131800} {"current_steps": 23670, "total_steps": 76960, "loss": 0.2308, "lr": 4.372103758142705e-05, "epoch": 6.151247401247401, "percentage": 30.76, "elapsed_time": "0:34:29", "remaining_time": "1:17:38", "throughput": 1030.52, "total_tokens": 2132216} {"current_steps": 23675, "total_steps": 76960, "loss": 0.177, "lr": 4.3717279578485385e-05, "epoch": 6.152546777546777, "percentage": 30.76, "elapsed_time": "0:34:29", "remaining_time": "1:17:37", "throughput": 1030.53, "total_tokens": 2132664} {"current_steps": 23680, "total_steps": 76960, "loss": 0.217, "lr": 4.371352061289609e-05, "epoch": 6.153846153846154, "percentage": 30.77, "elapsed_time": "0:34:29", "remaining_time": "1:17:37", "throughput": 1030.54, "total_tokens": 2133128} {"current_steps": 23685, "total_steps": 76960, "loss": 0.3653, "lr": 4.370976068485251e-05, "epoch": 6.15514553014553, "percentage": 30.78, "elapsed_time": "0:34:30", "remaining_time": "1:17:36", "throughput": 1030.57, "total_tokens": 2133608} {"current_steps": 23690, "total_steps": 76960, "loss": 0.2107, "lr": 4.3705999794548e-05, "epoch": 6.156444906444906, "percentage": 30.78, "elapsed_time": "0:34:30", "remaining_time": "1:17:36", "throughput": 1030.6, "total_tokens": 2134104} {"current_steps": 23695, "total_steps": 76960, "loss": 0.2136, "lr": 4.3702237942176e-05, "epoch": 6.157744282744282, "percentage": 30.79, "elapsed_time": "0:34:31", "remaining_time": "1:17:35", "throughput": 1030.6, "total_tokens": 2134536} {"current_steps": 23700, "total_steps": 76960, "loss": 0.2014, "lr": 4.3698475127929995e-05, "epoch": 6.159043659043659, "percentage": 30.8, "elapsed_time": "0:34:31", "remaining_time": "1:17:35", "throughput": 1030.62, "total_tokens": 2135000} {"current_steps": 23705, "total_steps": 76960, "loss": 0.1834, "lr": 4.369471135200349e-05, "epoch": 6.160343035343035, "percentage": 30.8, "elapsed_time": "0:34:32", "remaining_time": "1:17:34", "throughput": 1030.62, "total_tokens": 2135448} {"current_steps": 23710, "total_steps": 76960, "loss": 0.3318, "lr": 4.369094661459007e-05, "epoch": 6.161642411642411, "percentage": 30.81, "elapsed_time": "0:34:32", "remaining_time": "1:17:34", "throughput": 1030.63, "total_tokens": 2135912} {"current_steps": 23715, "total_steps": 76960, "loss": 0.3261, "lr": 4.368718091588335e-05, "epoch": 6.162941787941788, "percentage": 30.81, "elapsed_time": "0:34:32", "remaining_time": "1:17:33", "throughput": 1030.62, "total_tokens": 2136328} {"current_steps": 23720, "total_steps": 76960, "loss": 0.2241, "lr": 4.3683414256077014e-05, "epoch": 6.164241164241164, "percentage": 30.82, "elapsed_time": "0:34:33", "remaining_time": "1:17:33", "throughput": 1030.64, "total_tokens": 2136792} {"current_steps": 23725, "total_steps": 76960, "loss": 0.2538, "lr": 4.367964663536479e-05, "epoch": 6.16554054054054, "percentage": 30.83, "elapsed_time": "0:34:33", "remaining_time": "1:17:33", "throughput": 1030.65, "total_tokens": 2137240} {"current_steps": 23730, "total_steps": 76960, "loss": 0.2454, "lr": 4.367587805394043e-05, "epoch": 6.166839916839917, "percentage": 30.83, "elapsed_time": "0:34:34", "remaining_time": "1:17:32", "throughput": 1030.66, "total_tokens": 2137704} {"current_steps": 23735, "total_steps": 76960, "loss": 0.2493, "lr": 4.367210851199778e-05, "epoch": 6.168139293139293, "percentage": 30.84, "elapsed_time": "0:34:34", "remaining_time": "1:17:32", "throughput": 1030.67, "total_tokens": 2138136} {"current_steps": 23740, "total_steps": 76960, "loss": 0.2715, "lr": 4.366833800973068e-05, "epoch": 6.169438669438669, "percentage": 30.85, "elapsed_time": "0:34:34", "remaining_time": "1:17:31", "throughput": 1030.68, "total_tokens": 2138600} {"current_steps": 23745, "total_steps": 76960, "loss": 0.2261, "lr": 4.366456654733308e-05, "epoch": 6.170738045738045, "percentage": 30.85, "elapsed_time": "0:34:35", "remaining_time": "1:17:31", "throughput": 1030.69, "total_tokens": 2139048} {"current_steps": 23750, "total_steps": 76960, "loss": 0.2335, "lr": 4.366079412499894e-05, "epoch": 6.172037422037422, "percentage": 30.86, "elapsed_time": "0:34:35", "remaining_time": "1:17:30", "throughput": 1030.72, "total_tokens": 2139544} {"current_steps": 23755, "total_steps": 76960, "loss": 0.2052, "lr": 4.365702074292227e-05, "epoch": 6.173336798336798, "percentage": 30.87, "elapsed_time": "0:34:36", "remaining_time": "1:17:30", "throughput": 1030.72, "total_tokens": 2139976} {"current_steps": 23760, "total_steps": 76960, "loss": 0.3198, "lr": 4.365324640129716e-05, "epoch": 6.174636174636174, "percentage": 30.87, "elapsed_time": "0:34:36", "remaining_time": "1:17:29", "throughput": 1030.73, "total_tokens": 2140408} {"current_steps": 23765, "total_steps": 76960, "loss": 0.1631, "lr": 4.364947110031771e-05, "epoch": 6.175935550935551, "percentage": 30.88, "elapsed_time": "0:34:37", "remaining_time": "1:17:29", "throughput": 1030.73, "total_tokens": 2140840} {"current_steps": 23770, "total_steps": 76960, "loss": 0.2292, "lr": 4.3645694840178084e-05, "epoch": 6.177234927234927, "percentage": 30.89, "elapsed_time": "0:34:37", "remaining_time": "1:17:28", "throughput": 1030.74, "total_tokens": 2141288} {"current_steps": 23775, "total_steps": 76960, "loss": 0.1641, "lr": 4.3641917621072515e-05, "epoch": 6.178534303534303, "percentage": 30.89, "elapsed_time": "0:34:37", "remaining_time": "1:17:28", "throughput": 1030.73, "total_tokens": 2141704} {"current_steps": 23780, "total_steps": 76960, "loss": 0.3162, "lr": 4.3638139443195256e-05, "epoch": 6.1798336798336795, "percentage": 30.9, "elapsed_time": "0:34:38", "remaining_time": "1:17:27", "throughput": 1030.72, "total_tokens": 2142120} {"current_steps": 23785, "total_steps": 76960, "loss": 0.2835, "lr": 4.3634360306740636e-05, "epoch": 6.181133056133056, "percentage": 30.91, "elapsed_time": "0:34:38", "remaining_time": "1:17:27", "throughput": 1030.76, "total_tokens": 2142616} {"current_steps": 23790, "total_steps": 76960, "loss": 0.2712, "lr": 4.3630580211903006e-05, "epoch": 6.1824324324324325, "percentage": 30.91, "elapsed_time": "0:34:39", "remaining_time": "1:17:26", "throughput": 1030.78, "total_tokens": 2143096} {"current_steps": 23795, "total_steps": 76960, "loss": 0.2366, "lr": 4.362679915887679e-05, "epoch": 6.1837318087318085, "percentage": 30.92, "elapsed_time": "0:34:39", "remaining_time": "1:17:26", "throughput": 1030.79, "total_tokens": 2143544} {"current_steps": 23800, "total_steps": 76960, "loss": 0.2784, "lr": 4.362301714785643e-05, "epoch": 6.185031185031185, "percentage": 30.93, "elapsed_time": "0:34:39", "remaining_time": "1:17:25", "throughput": 1030.78, "total_tokens": 2143960} {"current_steps": 23805, "total_steps": 76960, "loss": 0.2855, "lr": 4.3619234179036463e-05, "epoch": 6.1863305613305615, "percentage": 30.93, "elapsed_time": "0:34:40", "remaining_time": "1:17:25", "throughput": 1030.8, "total_tokens": 2144424} {"current_steps": 23810, "total_steps": 76960, "loss": 0.2586, "lr": 4.361545025261145e-05, "epoch": 6.1876299376299375, "percentage": 30.94, "elapsed_time": "0:34:40", "remaining_time": "1:17:24", "throughput": 1030.82, "total_tokens": 2144888} {"current_steps": 23815, "total_steps": 76960, "loss": 0.3149, "lr": 4.3611665368775986e-05, "epoch": 6.188929313929314, "percentage": 30.94, "elapsed_time": "0:34:41", "remaining_time": "1:17:24", "throughput": 1030.84, "total_tokens": 2145368} {"current_steps": 23820, "total_steps": 76960, "loss": 0.296, "lr": 4.360787952772474e-05, "epoch": 6.1902286902286905, "percentage": 30.95, "elapsed_time": "0:34:41", "remaining_time": "1:17:23", "throughput": 1030.86, "total_tokens": 2145832} {"current_steps": 23825, "total_steps": 76960, "loss": 0.2872, "lr": 4.360409272965242e-05, "epoch": 6.1915280665280665, "percentage": 30.96, "elapsed_time": "0:34:42", "remaining_time": "1:17:23", "throughput": 1030.86, "total_tokens": 2146264} {"current_steps": 23830, "total_steps": 76960, "loss": 0.2476, "lr": 4.360030497475379e-05, "epoch": 6.192827442827443, "percentage": 30.96, "elapsed_time": "0:34:42", "remaining_time": "1:17:22", "throughput": 1030.89, "total_tokens": 2146760} {"current_steps": 23835, "total_steps": 76960, "loss": 0.3113, "lr": 4.359651626322364e-05, "epoch": 6.1941268191268195, "percentage": 30.97, "elapsed_time": "0:34:42", "remaining_time": "1:17:22", "throughput": 1030.91, "total_tokens": 2147224} {"current_steps": 23840, "total_steps": 76960, "loss": 0.2221, "lr": 4.3592726595256854e-05, "epoch": 6.1954261954261955, "percentage": 30.98, "elapsed_time": "0:34:43", "remaining_time": "1:17:21", "throughput": 1030.91, "total_tokens": 2147656} {"current_steps": 23845, "total_steps": 76960, "loss": 0.2369, "lr": 4.358893597104832e-05, "epoch": 6.196725571725572, "percentage": 30.98, "elapsed_time": "0:34:43", "remaining_time": "1:17:21", "throughput": 1030.93, "total_tokens": 2148120} {"current_steps": 23850, "total_steps": 76960, "loss": 0.2867, "lr": 4.3585144390793e-05, "epoch": 6.198024948024948, "percentage": 30.99, "elapsed_time": "0:34:44", "remaining_time": "1:17:20", "throughput": 1030.92, "total_tokens": 2148536} {"current_steps": 23855, "total_steps": 76960, "loss": 0.2202, "lr": 4.358135185468589e-05, "epoch": 6.199324324324325, "percentage": 31.0, "elapsed_time": "0:34:44", "remaining_time": "1:17:20", "throughput": 1030.95, "total_tokens": 2149032} {"current_steps": 23860, "total_steps": 76960, "loss": 0.3476, "lr": 4.357755836292207e-05, "epoch": 6.200623700623701, "percentage": 31.0, "elapsed_time": "0:34:44", "remaining_time": "1:17:19", "throughput": 1030.96, "total_tokens": 2149480} {"current_steps": 23865, "total_steps": 76960, "loss": 0.2643, "lr": 4.3573763915696594e-05, "epoch": 6.201923076923077, "percentage": 31.01, "elapsed_time": "0:34:45", "remaining_time": "1:17:19", "throughput": 1030.97, "total_tokens": 2149928} {"current_steps": 23870, "total_steps": 76960, "loss": 0.2442, "lr": 4.356996851320466e-05, "epoch": 6.203222453222454, "percentage": 31.02, "elapsed_time": "0:34:45", "remaining_time": "1:17:19", "throughput": 1031.0, "total_tokens": 2150424} {"current_steps": 23875, "total_steps": 76960, "loss": 0.2647, "lr": 4.356617215564146e-05, "epoch": 6.20452182952183, "percentage": 31.02, "elapsed_time": "0:34:46", "remaining_time": "1:17:18", "throughput": 1031.01, "total_tokens": 2150872} {"current_steps": 23880, "total_steps": 76960, "loss": 0.2425, "lr": 4.356237484320222e-05, "epoch": 6.205821205821206, "percentage": 31.03, "elapsed_time": "0:34:46", "remaining_time": "1:17:18", "throughput": 1031.02, "total_tokens": 2151320} {"current_steps": 23885, "total_steps": 76960, "loss": 0.2491, "lr": 4.355857657608227e-05, "epoch": 6.207120582120582, "percentage": 31.04, "elapsed_time": "0:34:47", "remaining_time": "1:17:17", "throughput": 1031.03, "total_tokens": 2151784} {"current_steps": 23890, "total_steps": 76960, "loss": 0.2216, "lr": 4.355477735447693e-05, "epoch": 6.208419958419959, "percentage": 31.04, "elapsed_time": "0:34:47", "remaining_time": "1:17:17", "throughput": 1031.03, "total_tokens": 2152216} {"current_steps": 23895, "total_steps": 76960, "loss": 0.319, "lr": 4.355097717858162e-05, "epoch": 6.209719334719335, "percentage": 31.05, "elapsed_time": "0:34:47", "remaining_time": "1:17:16", "throughput": 1031.06, "total_tokens": 2152696} {"current_steps": 23900, "total_steps": 76960, "loss": 0.2525, "lr": 4.354717604859178e-05, "epoch": 6.211018711018711, "percentage": 31.06, "elapsed_time": "0:34:48", "remaining_time": "1:17:16", "throughput": 1031.08, "total_tokens": 2153176} {"current_steps": 23905, "total_steps": 76960, "loss": 0.2266, "lr": 4.3543373964702907e-05, "epoch": 6.212318087318088, "percentage": 31.06, "elapsed_time": "0:34:48", "remaining_time": "1:17:15", "throughput": 1031.11, "total_tokens": 2153656} {"current_steps": 23910, "total_steps": 76960, "loss": 0.2704, "lr": 4.353957092711054e-05, "epoch": 6.213617463617464, "percentage": 31.07, "elapsed_time": "0:34:49", "remaining_time": "1:17:15", "throughput": 1031.12, "total_tokens": 2154120} {"current_steps": 23915, "total_steps": 76960, "loss": 0.2375, "lr": 4.353576693601028e-05, "epoch": 6.21491683991684, "percentage": 31.07, "elapsed_time": "0:34:49", "remaining_time": "1:17:14", "throughput": 1031.13, "total_tokens": 2154568} {"current_steps": 23920, "total_steps": 76960, "loss": 0.2264, "lr": 4.353196199159776e-05, "epoch": 6.216216216216216, "percentage": 31.08, "elapsed_time": "0:34:49", "remaining_time": "1:17:14", "throughput": 1031.2, "total_tokens": 2155128} {"current_steps": 23925, "total_steps": 76960, "loss": 0.2875, "lr": 4.352815609406868e-05, "epoch": 6.217515592515593, "percentage": 31.09, "elapsed_time": "0:34:50", "remaining_time": "1:17:13", "throughput": 1031.21, "total_tokens": 2155576} {"current_steps": 23930, "total_steps": 76960, "loss": 0.2025, "lr": 4.3524349243618785e-05, "epoch": 6.218814968814969, "percentage": 31.09, "elapsed_time": "0:34:50", "remaining_time": "1:17:13", "throughput": 1031.22, "total_tokens": 2156040} {"current_steps": 23935, "total_steps": 76960, "loss": 0.1594, "lr": 4.3520541440443854e-05, "epoch": 6.220114345114345, "percentage": 31.1, "elapsed_time": "0:34:51", "remaining_time": "1:17:12", "throughput": 1031.26, "total_tokens": 2156536} {"current_steps": 23940, "total_steps": 76960, "loss": 0.3409, "lr": 4.351673268473974e-05, "epoch": 6.221413721413722, "percentage": 31.11, "elapsed_time": "0:34:51", "remaining_time": "1:17:12", "throughput": 1031.27, "total_tokens": 2156984} {"current_steps": 23945, "total_steps": 76960, "loss": 0.2184, "lr": 4.351292297670231e-05, "epoch": 6.222713097713098, "percentage": 31.11, "elapsed_time": "0:34:52", "remaining_time": "1:17:11", "throughput": 1031.27, "total_tokens": 2157416} {"current_steps": 23950, "total_steps": 76960, "loss": 0.2948, "lr": 4.350911231652751e-05, "epoch": 6.224012474012474, "percentage": 31.12, "elapsed_time": "0:34:52", "remaining_time": "1:17:11", "throughput": 1031.26, "total_tokens": 2157832} {"current_steps": 23955, "total_steps": 76960, "loss": 0.2034, "lr": 4.350530070441135e-05, "epoch": 6.225311850311851, "percentage": 31.13, "elapsed_time": "0:34:52", "remaining_time": "1:17:10", "throughput": 1031.25, "total_tokens": 2158232} {"current_steps": 23960, "total_steps": 76960, "loss": 0.2797, "lr": 4.350148814054982e-05, "epoch": 6.226611226611227, "percentage": 31.13, "elapsed_time": "0:34:53", "remaining_time": "1:17:10", "throughput": 1031.25, "total_tokens": 2158664} {"current_steps": 23965, "total_steps": 76960, "loss": 0.2949, "lr": 4.349767462513904e-05, "epoch": 6.227910602910603, "percentage": 31.14, "elapsed_time": "0:34:53", "remaining_time": "1:17:09", "throughput": 1031.28, "total_tokens": 2159160} {"current_steps": 23970, "total_steps": 76960, "loss": 0.304, "lr": 4.3493860158375135e-05, "epoch": 6.229209979209979, "percentage": 31.15, "elapsed_time": "0:34:54", "remaining_time": "1:17:09", "throughput": 1031.3, "total_tokens": 2159624} {"current_steps": 23975, "total_steps": 76960, "loss": 0.2399, "lr": 4.3490044740454274e-05, "epoch": 6.230509355509356, "percentage": 31.15, "elapsed_time": "0:34:54", "remaining_time": "1:17:08", "throughput": 1031.31, "total_tokens": 2160072} {"current_steps": 23980, "total_steps": 76960, "loss": 0.1653, "lr": 4.3486228371572694e-05, "epoch": 6.231808731808732, "percentage": 31.16, "elapsed_time": "0:34:54", "remaining_time": "1:17:08", "throughput": 1031.31, "total_tokens": 2160520} {"current_steps": 23985, "total_steps": 76960, "loss": 0.2605, "lr": 4.348241105192668e-05, "epoch": 6.233108108108108, "percentage": 31.17, "elapsed_time": "0:34:55", "remaining_time": "1:17:07", "throughput": 1031.32, "total_tokens": 2160968} {"current_steps": 23990, "total_steps": 76960, "loss": 0.3546, "lr": 4.347859278171256e-05, "epoch": 6.234407484407485, "percentage": 31.17, "elapsed_time": "0:34:55", "remaining_time": "1:17:07", "throughput": 1031.34, "total_tokens": 2161432} {"current_steps": 23995, "total_steps": 76960, "loss": 0.268, "lr": 4.3474773561126705e-05, "epoch": 6.235706860706861, "percentage": 31.18, "elapsed_time": "0:34:56", "remaining_time": "1:17:06", "throughput": 1031.34, "total_tokens": 2161864} {"current_steps": 24000, "total_steps": 76960, "loss": 0.246, "lr": 4.3470953390365545e-05, "epoch": 6.237006237006237, "percentage": 31.19, "elapsed_time": "0:34:56", "remaining_time": "1:17:06", "throughput": 1031.35, "total_tokens": 2162312} {"current_steps": 24005, "total_steps": 76960, "loss": 0.2735, "lr": 4.3467132269625546e-05, "epoch": 6.238305613305613, "percentage": 31.19, "elapsed_time": "0:34:57", "remaining_time": "1:17:05", "throughput": 1031.37, "total_tokens": 2162776} {"current_steps": 24010, "total_steps": 76960, "loss": 0.2671, "lr": 4.346331019910325e-05, "epoch": 6.23960498960499, "percentage": 31.2, "elapsed_time": "0:34:57", "remaining_time": "1:17:05", "throughput": 1031.38, "total_tokens": 2163224} {"current_steps": 24015, "total_steps": 76960, "loss": 0.245, "lr": 4.345948717899521e-05, "epoch": 6.240904365904366, "percentage": 31.2, "elapsed_time": "0:34:57", "remaining_time": "1:17:05", "throughput": 1031.38, "total_tokens": 2163672} {"current_steps": 24020, "total_steps": 76960, "loss": 0.2626, "lr": 4.3455663209498065e-05, "epoch": 6.242203742203742, "percentage": 31.21, "elapsed_time": "0:34:58", "remaining_time": "1:17:04", "throughput": 1031.39, "total_tokens": 2164104} {"current_steps": 24025, "total_steps": 76960, "loss": 0.2016, "lr": 4.3451838290808475e-05, "epoch": 6.243503118503119, "percentage": 31.22, "elapsed_time": "0:34:58", "remaining_time": "1:17:04", "throughput": 1031.42, "total_tokens": 2164600} {"current_steps": 24030, "total_steps": 76960, "loss": 0.2279, "lr": 4.344801242312317e-05, "epoch": 6.244802494802495, "percentage": 31.22, "elapsed_time": "0:34:59", "remaining_time": "1:17:03", "throughput": 1031.45, "total_tokens": 2165096} {"current_steps": 24035, "total_steps": 76960, "loss": 0.2808, "lr": 4.34441856066389e-05, "epoch": 6.246101871101871, "percentage": 31.23, "elapsed_time": "0:34:59", "remaining_time": "1:17:03", "throughput": 1031.46, "total_tokens": 2165560} {"current_steps": 24040, "total_steps": 76960, "loss": 0.1594, "lr": 4.3440357841552496e-05, "epoch": 6.247401247401247, "percentage": 31.24, "elapsed_time": "0:34:59", "remaining_time": "1:17:02", "throughput": 1031.46, "total_tokens": 2165992} {"current_steps": 24045, "total_steps": 76960, "loss": 0.2899, "lr": 4.343652912806081e-05, "epoch": 6.248700623700624, "percentage": 31.24, "elapsed_time": "0:35:00", "remaining_time": "1:17:02", "throughput": 1031.47, "total_tokens": 2166440} {"current_steps": 24050, "total_steps": 76960, "loss": 0.3999, "lr": 4.343269946636078e-05, "epoch": 6.25, "percentage": 31.25, "elapsed_time": "0:35:00", "remaining_time": "1:17:01", "throughput": 1031.49, "total_tokens": 2166904} {"current_steps": 24055, "total_steps": 76960, "loss": 0.3922, "lr": 4.342886885664935e-05, "epoch": 6.251299376299376, "percentage": 31.26, "elapsed_time": "0:35:01", "remaining_time": "1:17:01", "throughput": 1031.51, "total_tokens": 2167368} {"current_steps": 24060, "total_steps": 76960, "loss": 0.2692, "lr": 4.342503729912354e-05, "epoch": 6.252598752598753, "percentage": 31.26, "elapsed_time": "0:35:01", "remaining_time": "1:17:00", "throughput": 1031.51, "total_tokens": 2167816} {"current_steps": 24065, "total_steps": 76960, "loss": 0.2866, "lr": 4.34212047939804e-05, "epoch": 6.253898128898129, "percentage": 31.27, "elapsed_time": "0:35:02", "remaining_time": "1:17:00", "throughput": 1031.52, "total_tokens": 2168264} {"current_steps": 24070, "total_steps": 76960, "loss": 0.29, "lr": 4.3417371341417056e-05, "epoch": 6.255197505197505, "percentage": 31.28, "elapsed_time": "0:35:02", "remaining_time": "1:16:59", "throughput": 1031.53, "total_tokens": 2168696} {"current_steps": 24075, "total_steps": 76960, "loss": 0.2941, "lr": 4.341353694163065e-05, "epoch": 6.256496881496881, "percentage": 31.28, "elapsed_time": "0:35:02", "remaining_time": "1:16:59", "throughput": 1031.54, "total_tokens": 2169160} {"current_steps": 24080, "total_steps": 76960, "loss": 0.2988, "lr": 4.34097015948184e-05, "epoch": 6.257796257796258, "percentage": 31.29, "elapsed_time": "0:35:03", "remaining_time": "1:16:58", "throughput": 1031.54, "total_tokens": 2169592} {"current_steps": 24085, "total_steps": 76960, "loss": 0.222, "lr": 4.3405865301177555e-05, "epoch": 6.259095634095634, "percentage": 31.3, "elapsed_time": "0:35:03", "remaining_time": "1:16:58", "throughput": 1031.55, "total_tokens": 2170040} {"current_steps": 24090, "total_steps": 76960, "loss": 0.2639, "lr": 4.340202806090543e-05, "epoch": 6.26039501039501, "percentage": 31.3, "elapsed_time": "0:35:04", "remaining_time": "1:16:57", "throughput": 1031.55, "total_tokens": 2170456} {"current_steps": 24095, "total_steps": 76960, "loss": 0.4624, "lr": 4.339818987419936e-05, "epoch": 6.261694386694387, "percentage": 31.31, "elapsed_time": "0:35:04", "remaining_time": "1:16:57", "throughput": 1031.58, "total_tokens": 2170952} {"current_steps": 24100, "total_steps": 76960, "loss": 0.1986, "lr": 4.339435074125676e-05, "epoch": 6.262993762993763, "percentage": 31.31, "elapsed_time": "0:35:04", "remaining_time": "1:16:56", "throughput": 1031.58, "total_tokens": 2171384} {"current_steps": 24105, "total_steps": 76960, "loss": 0.2034, "lr": 4.3390510662275076e-05, "epoch": 6.264293139293139, "percentage": 31.32, "elapsed_time": "0:35:05", "remaining_time": "1:16:56", "throughput": 1031.58, "total_tokens": 2171816} {"current_steps": 24110, "total_steps": 76960, "loss": 0.2037, "lr": 4.3386669637451806e-05, "epoch": 6.265592515592515, "percentage": 31.33, "elapsed_time": "0:35:05", "remaining_time": "1:16:55", "throughput": 1031.59, "total_tokens": 2172264} {"current_steps": 24115, "total_steps": 76960, "loss": 0.1617, "lr": 4.33828276669845e-05, "epoch": 6.266891891891892, "percentage": 31.33, "elapsed_time": "0:35:06", "remaining_time": "1:16:55", "throughput": 1031.6, "total_tokens": 2172712} {"current_steps": 24120, "total_steps": 76960, "loss": 0.287, "lr": 4.3378984751070764e-05, "epoch": 6.268191268191268, "percentage": 31.34, "elapsed_time": "0:35:06", "remaining_time": "1:16:54", "throughput": 1031.6, "total_tokens": 2173144} {"current_steps": 24125, "total_steps": 76960, "loss": 0.3733, "lr": 4.337514088990822e-05, "epoch": 6.269490644490644, "percentage": 31.35, "elapsed_time": "0:35:06", "remaining_time": "1:16:54", "throughput": 1031.61, "total_tokens": 2173608} {"current_steps": 24130, "total_steps": 76960, "loss": 0.3719, "lr": 4.337129608369457e-05, "epoch": 6.270790020790021, "percentage": 31.35, "elapsed_time": "0:35:07", "remaining_time": "1:16:53", "throughput": 1031.63, "total_tokens": 2174072} {"current_steps": 24135, "total_steps": 76960, "loss": 0.2845, "lr": 4.3367450332627566e-05, "epoch": 6.272089397089397, "percentage": 31.36, "elapsed_time": "0:35:07", "remaining_time": "1:16:53", "throughput": 1031.65, "total_tokens": 2174536} {"current_steps": 24140, "total_steps": 76960, "loss": 0.2808, "lr": 4.3363603636905e-05, "epoch": 6.273388773388773, "percentage": 31.37, "elapsed_time": "0:35:08", "remaining_time": "1:16:52", "throughput": 1031.65, "total_tokens": 2174968} {"current_steps": 24145, "total_steps": 76960, "loss": 0.2731, "lr": 4.335975599672469e-05, "epoch": 6.274688149688149, "percentage": 31.37, "elapsed_time": "0:35:08", "remaining_time": "1:16:52", "throughput": 1031.67, "total_tokens": 2175448} {"current_steps": 24150, "total_steps": 76960, "loss": 0.2466, "lr": 4.335590741228455e-05, "epoch": 6.275987525987526, "percentage": 31.38, "elapsed_time": "0:35:09", "remaining_time": "1:16:52", "throughput": 1031.67, "total_tokens": 2175880} {"current_steps": 24155, "total_steps": 76960, "loss": 0.2687, "lr": 4.3352057883782505e-05, "epoch": 6.277286902286902, "percentage": 31.39, "elapsed_time": "0:35:09", "remaining_time": "1:16:51", "throughput": 1031.67, "total_tokens": 2176312} {"current_steps": 24160, "total_steps": 76960, "loss": 0.2163, "lr": 4.334820741141653e-05, "epoch": 6.278586278586278, "percentage": 31.39, "elapsed_time": "0:35:09", "remaining_time": "1:16:51", "throughput": 1031.68, "total_tokens": 2176760} {"current_steps": 24165, "total_steps": 76960, "loss": 0.2775, "lr": 4.3344355995384664e-05, "epoch": 6.279885654885655, "percentage": 31.4, "elapsed_time": "0:35:10", "remaining_time": "1:16:50", "throughput": 1031.7, "total_tokens": 2177224} {"current_steps": 24170, "total_steps": 76960, "loss": 0.2684, "lr": 4.3340503635885006e-05, "epoch": 6.281185031185031, "percentage": 31.41, "elapsed_time": "0:35:10", "remaining_time": "1:16:50", "throughput": 1031.69, "total_tokens": 2177640} {"current_steps": 24175, "total_steps": 76960, "loss": 0.3191, "lr": 4.333665033311566e-05, "epoch": 6.282484407484407, "percentage": 31.41, "elapsed_time": "0:35:11", "remaining_time": "1:16:49", "throughput": 1031.69, "total_tokens": 2178072} {"current_steps": 24180, "total_steps": 76960, "loss": 0.2455, "lr": 4.333279608727483e-05, "epoch": 6.283783783783784, "percentage": 31.42, "elapsed_time": "0:35:11", "remaining_time": "1:16:49", "throughput": 1031.71, "total_tokens": 2178536} {"current_steps": 24185, "total_steps": 76960, "loss": 0.2728, "lr": 4.332894089856072e-05, "epoch": 6.28508316008316, "percentage": 31.43, "elapsed_time": "0:35:11", "remaining_time": "1:16:48", "throughput": 1031.71, "total_tokens": 2178968} {"current_steps": 24190, "total_steps": 76960, "loss": 0.225, "lr": 4.332508476717163e-05, "epoch": 6.286382536382536, "percentage": 31.43, "elapsed_time": "0:35:12", "remaining_time": "1:16:48", "throughput": 1031.72, "total_tokens": 2179416} {"current_steps": 24195, "total_steps": 76960, "loss": 0.2832, "lr": 4.332122769330586e-05, "epoch": 6.287681912681912, "percentage": 31.44, "elapsed_time": "0:35:12", "remaining_time": "1:16:47", "throughput": 1031.74, "total_tokens": 2179896} {"current_steps": 24200, "total_steps": 76960, "loss": 0.2447, "lr": 4.33173696771618e-05, "epoch": 6.288981288981289, "percentage": 31.44, "elapsed_time": "0:35:13", "remaining_time": "1:16:47", "throughput": 1031.75, "total_tokens": 2180344} {"current_steps": 24205, "total_steps": 76960, "loss": 0.2249, "lr": 4.331351071893787e-05, "epoch": 6.290280665280665, "percentage": 31.45, "elapsed_time": "0:35:13", "remaining_time": "1:16:46", "throughput": 1031.74, "total_tokens": 2180744} {"current_steps": 24210, "total_steps": 76960, "loss": 0.2569, "lr": 4.330965081883254e-05, "epoch": 6.291580041580041, "percentage": 31.46, "elapsed_time": "0:35:14", "remaining_time": "1:16:46", "throughput": 1031.74, "total_tokens": 2181192} {"current_steps": 24215, "total_steps": 76960, "loss": 0.203, "lr": 4.330578997704431e-05, "epoch": 6.292879417879418, "percentage": 31.46, "elapsed_time": "0:35:14", "remaining_time": "1:16:45", "throughput": 1031.74, "total_tokens": 2181608} {"current_steps": 24220, "total_steps": 76960, "loss": 0.2319, "lr": 4.3301928193771766e-05, "epoch": 6.294178794178794, "percentage": 31.47, "elapsed_time": "0:35:14", "remaining_time": "1:16:45", "throughput": 1031.75, "total_tokens": 2182056} {"current_steps": 24225, "total_steps": 76960, "loss": 0.1579, "lr": 4.329806546921353e-05, "epoch": 6.29547817047817, "percentage": 31.48, "elapsed_time": "0:35:15", "remaining_time": "1:16:44", "throughput": 1031.76, "total_tokens": 2182520} {"current_steps": 24230, "total_steps": 76960, "loss": 0.3537, "lr": 4.3294201803568243e-05, "epoch": 6.296777546777546, "percentage": 31.48, "elapsed_time": "0:35:15", "remaining_time": "1:16:44", "throughput": 1031.79, "total_tokens": 2183000} {"current_steps": 24235, "total_steps": 76960, "loss": 0.3787, "lr": 4.329033719703464e-05, "epoch": 6.298076923076923, "percentage": 31.49, "elapsed_time": "0:35:16", "remaining_time": "1:16:43", "throughput": 1031.79, "total_tokens": 2183432} {"current_steps": 24240, "total_steps": 76960, "loss": 0.2423, "lr": 4.328647164981146e-05, "epoch": 6.299376299376299, "percentage": 31.5, "elapsed_time": "0:35:16", "remaining_time": "1:16:43", "throughput": 1031.8, "total_tokens": 2183880} {"current_steps": 24245, "total_steps": 76960, "loss": 0.1697, "lr": 4.328260516209752e-05, "epoch": 6.300675675675675, "percentage": 31.5, "elapsed_time": "0:35:16", "remaining_time": "1:16:42", "throughput": 1031.82, "total_tokens": 2184360} {"current_steps": 24250, "total_steps": 76960, "loss": 0.3442, "lr": 4.327873773409169e-05, "epoch": 6.301975051975052, "percentage": 31.51, "elapsed_time": "0:35:17", "remaining_time": "1:16:42", "throughput": 1031.82, "total_tokens": 2184792} {"current_steps": 24255, "total_steps": 76960, "loss": 0.3295, "lr": 4.327486936599286e-05, "epoch": 6.303274428274428, "percentage": 31.52, "elapsed_time": "0:35:17", "remaining_time": "1:16:41", "throughput": 1031.84, "total_tokens": 2185272} {"current_steps": 24260, "total_steps": 76960, "loss": 0.213, "lr": 4.327100005799999e-05, "epoch": 6.3045738045738045, "percentage": 31.52, "elapsed_time": "0:35:18", "remaining_time": "1:16:41", "throughput": 1031.86, "total_tokens": 2185736} {"current_steps": 24265, "total_steps": 76960, "loss": 0.2499, "lr": 4.3267129810312074e-05, "epoch": 6.3058731808731805, "percentage": 31.53, "elapsed_time": "0:35:18", "remaining_time": "1:16:40", "throughput": 1031.87, "total_tokens": 2186184} {"current_steps": 24270, "total_steps": 76960, "loss": 0.2897, "lr": 4.326325862312817e-05, "epoch": 6.307172557172557, "percentage": 31.54, "elapsed_time": "0:35:19", "remaining_time": "1:16:40", "throughput": 1031.85, "total_tokens": 2186584} {"current_steps": 24275, "total_steps": 76960, "loss": 0.184, "lr": 4.3259386496647384e-05, "epoch": 6.3084719334719335, "percentage": 31.54, "elapsed_time": "0:35:19", "remaining_time": "1:16:40", "throughput": 1031.85, "total_tokens": 2187000} {"current_steps": 24280, "total_steps": 76960, "loss": 0.2651, "lr": 4.325551343106885e-05, "epoch": 6.3097713097713095, "percentage": 31.55, "elapsed_time": "0:35:19", "remaining_time": "1:16:39", "throughput": 1031.87, "total_tokens": 2187480} {"current_steps": 24285, "total_steps": 76960, "loss": 0.2126, "lr": 4.325163942659177e-05, "epoch": 6.311070686070686, "percentage": 31.56, "elapsed_time": "0:35:20", "remaining_time": "1:16:39", "throughput": 1031.87, "total_tokens": 2187912} {"current_steps": 24290, "total_steps": 76960, "loss": 0.3062, "lr": 4.324776448341538e-05, "epoch": 6.3123700623700625, "percentage": 31.56, "elapsed_time": "0:35:20", "remaining_time": "1:16:38", "throughput": 1031.89, "total_tokens": 2188376} {"current_steps": 24295, "total_steps": 76960, "loss": 0.3074, "lr": 4.3243888601738984e-05, "epoch": 6.3136694386694385, "percentage": 31.57, "elapsed_time": "0:35:21", "remaining_time": "1:16:38", "throughput": 1031.89, "total_tokens": 2188808} {"current_steps": 24300, "total_steps": 76960, "loss": 0.2302, "lr": 4.324001178176191e-05, "epoch": 6.314968814968815, "percentage": 31.57, "elapsed_time": "0:35:21", "remaining_time": "1:16:37", "throughput": 1031.92, "total_tokens": 2189304} {"current_steps": 24305, "total_steps": 76960, "loss": 0.2928, "lr": 4.323613402368357e-05, "epoch": 6.3162681912681915, "percentage": 31.58, "elapsed_time": "0:35:22", "remaining_time": "1:16:37", "throughput": 1031.91, "total_tokens": 2189720} {"current_steps": 24310, "total_steps": 76960, "loss": 0.2905, "lr": 4.323225532770337e-05, "epoch": 6.3175675675675675, "percentage": 31.59, "elapsed_time": "0:35:22", "remaining_time": "1:16:36", "throughput": 1031.91, "total_tokens": 2190136} {"current_steps": 24315, "total_steps": 76960, "loss": 0.2482, "lr": 4.322837569402081e-05, "epoch": 6.318866943866944, "percentage": 31.59, "elapsed_time": "0:35:22", "remaining_time": "1:16:36", "throughput": 1031.92, "total_tokens": 2190600} {"current_steps": 24320, "total_steps": 76960, "loss": 0.2735, "lr": 4.322449512283543e-05, "epoch": 6.3201663201663205, "percentage": 31.6, "elapsed_time": "0:35:23", "remaining_time": "1:16:35", "throughput": 1031.93, "total_tokens": 2191048} {"current_steps": 24325, "total_steps": 76960, "loss": 0.2068, "lr": 4.32206136143468e-05, "epoch": 6.321465696465697, "percentage": 31.61, "elapsed_time": "0:35:23", "remaining_time": "1:16:35", "throughput": 1031.94, "total_tokens": 2191496} {"current_steps": 24330, "total_steps": 76960, "loss": 0.2714, "lr": 4.321673116875455e-05, "epoch": 6.322765072765073, "percentage": 31.61, "elapsed_time": "0:35:24", "remaining_time": "1:16:34", "throughput": 1031.94, "total_tokens": 2191928} {"current_steps": 24335, "total_steps": 76960, "loss": 0.1692, "lr": 4.321284778625836e-05, "epoch": 6.3240644490644495, "percentage": 31.62, "elapsed_time": "0:35:24", "remaining_time": "1:16:34", "throughput": 1031.96, "total_tokens": 2192392} {"current_steps": 24340, "total_steps": 76960, "loss": 0.2602, "lr": 4.320896346705797e-05, "epoch": 6.325363825363826, "percentage": 31.63, "elapsed_time": "0:35:24", "remaining_time": "1:16:33", "throughput": 1031.97, "total_tokens": 2192840} {"current_steps": 24345, "total_steps": 76960, "loss": 0.1621, "lr": 4.3205078211353135e-05, "epoch": 6.326663201663202, "percentage": 31.63, "elapsed_time": "0:35:25", "remaining_time": "1:16:33", "throughput": 1031.98, "total_tokens": 2193304} {"current_steps": 24350, "total_steps": 76960, "loss": 0.3561, "lr": 4.3201192019343685e-05, "epoch": 6.327962577962578, "percentage": 31.64, "elapsed_time": "0:35:25", "remaining_time": "1:16:32", "throughput": 1031.99, "total_tokens": 2193752} {"current_steps": 24355, "total_steps": 76960, "loss": 0.3268, "lr": 4.3197304891229485e-05, "epoch": 6.329261954261955, "percentage": 31.65, "elapsed_time": "0:35:26", "remaining_time": "1:16:32", "throughput": 1032.01, "total_tokens": 2194232} {"current_steps": 24360, "total_steps": 76960, "loss": 0.1752, "lr": 4.319341682721046e-05, "epoch": 6.330561330561331, "percentage": 31.65, "elapsed_time": "0:35:26", "remaining_time": "1:16:31", "throughput": 1032.03, "total_tokens": 2194696} {"current_steps": 24365, "total_steps": 76960, "loss": 0.3357, "lr": 4.3189527827486575e-05, "epoch": 6.331860706860707, "percentage": 31.66, "elapsed_time": "0:35:26", "remaining_time": "1:16:31", "throughput": 1032.06, "total_tokens": 2195192} {"current_steps": 24370, "total_steps": 76960, "loss": 0.2994, "lr": 4.318563789225785e-05, "epoch": 6.333160083160083, "percentage": 31.67, "elapsed_time": "0:35:27", "remaining_time": "1:16:30", "throughput": 1032.06, "total_tokens": 2195624} {"current_steps": 24375, "total_steps": 76960, "loss": 0.2588, "lr": 4.318174702172434e-05, "epoch": 6.33445945945946, "percentage": 31.67, "elapsed_time": "0:35:27", "remaining_time": "1:16:30", "throughput": 1032.06, "total_tokens": 2196040} {"current_steps": 24380, "total_steps": 76960, "loss": 0.2325, "lr": 4.317785521608616e-05, "epoch": 6.335758835758836, "percentage": 31.68, "elapsed_time": "0:35:28", "remaining_time": "1:16:29", "throughput": 1032.06, "total_tokens": 2196472} {"current_steps": 24385, "total_steps": 76960, "loss": 0.2026, "lr": 4.317396247554347e-05, "epoch": 6.337058212058212, "percentage": 31.69, "elapsed_time": "0:35:28", "remaining_time": "1:16:29", "throughput": 1032.05, "total_tokens": 2196888} {"current_steps": 24390, "total_steps": 76960, "loss": 0.2956, "lr": 4.317006880029648e-05, "epoch": 6.338357588357589, "percentage": 31.69, "elapsed_time": "0:35:29", "remaining_time": "1:16:29", "throughput": 1032.07, "total_tokens": 2197368} {"current_steps": 24395, "total_steps": 76960, "loss": 0.2628, "lr": 4.316617419054544e-05, "epoch": 6.339656964656965, "percentage": 31.7, "elapsed_time": "0:35:29", "remaining_time": "1:16:28", "throughput": 1032.07, "total_tokens": 2197800} {"current_steps": 24400, "total_steps": 76960, "loss": 0.263, "lr": 4.316227864649065e-05, "epoch": 6.340956340956341, "percentage": 31.7, "elapsed_time": "0:35:29", "remaining_time": "1:16:28", "throughput": 1032.08, "total_tokens": 2198264} {"current_steps": 24405, "total_steps": 76960, "loss": 0.1627, "lr": 4.315838216833247e-05, "epoch": 6.342255717255718, "percentage": 31.71, "elapsed_time": "0:35:30", "remaining_time": "1:16:27", "throughput": 1032.1, "total_tokens": 2198744} {"current_steps": 24410, "total_steps": 76960, "loss": 0.3115, "lr": 4.31544847562713e-05, "epoch": 6.343555093555094, "percentage": 31.72, "elapsed_time": "0:35:30", "remaining_time": "1:16:27", "throughput": 1032.1, "total_tokens": 2199176} {"current_steps": 24415, "total_steps": 76960, "loss": 0.1882, "lr": 4.315058641050758e-05, "epoch": 6.34485446985447, "percentage": 31.72, "elapsed_time": "0:35:31", "remaining_time": "1:16:26", "throughput": 1032.1, "total_tokens": 2199608} {"current_steps": 24420, "total_steps": 76960, "loss": 0.2603, "lr": 4.3146687131241815e-05, "epoch": 6.346153846153846, "percentage": 31.73, "elapsed_time": "0:35:31", "remaining_time": "1:16:26", "throughput": 1032.09, "total_tokens": 2200008} {"current_steps": 24425, "total_steps": 76960, "loss": 0.2678, "lr": 4.314278691867454e-05, "epoch": 6.347453222453223, "percentage": 31.74, "elapsed_time": "0:35:32", "remaining_time": "1:16:25", "throughput": 1032.1, "total_tokens": 2200472} {"current_steps": 24430, "total_steps": 76960, "loss": 0.2542, "lr": 4.313888577300635e-05, "epoch": 6.348752598752599, "percentage": 31.74, "elapsed_time": "0:35:32", "remaining_time": "1:16:25", "throughput": 1032.12, "total_tokens": 2200936} {"current_steps": 24435, "total_steps": 76960, "loss": 0.2245, "lr": 4.313498369443788e-05, "epoch": 6.350051975051975, "percentage": 31.75, "elapsed_time": "0:35:32", "remaining_time": "1:16:24", "throughput": 1032.13, "total_tokens": 2201400} {"current_steps": 24440, "total_steps": 76960, "loss": 0.2037, "lr": 4.313108068316983e-05, "epoch": 6.351351351351352, "percentage": 31.76, "elapsed_time": "0:35:33", "remaining_time": "1:16:24", "throughput": 1032.13, "total_tokens": 2201832} {"current_steps": 24445, "total_steps": 76960, "loss": 0.2232, "lr": 4.312717673940293e-05, "epoch": 6.352650727650728, "percentage": 31.76, "elapsed_time": "0:35:33", "remaining_time": "1:16:23", "throughput": 1032.12, "total_tokens": 2202232} {"current_steps": 24450, "total_steps": 76960, "loss": 0.2639, "lr": 4.3123271863337954e-05, "epoch": 6.353950103950104, "percentage": 31.77, "elapsed_time": "0:35:34", "remaining_time": "1:16:23", "throughput": 1032.15, "total_tokens": 2202728} {"current_steps": 24455, "total_steps": 76960, "loss": 0.3312, "lr": 4.3119366055175746e-05, "epoch": 6.35524948024948, "percentage": 31.78, "elapsed_time": "0:35:34", "remaining_time": "1:16:22", "throughput": 1032.15, "total_tokens": 2203160} {"current_steps": 24460, "total_steps": 76960, "loss": 0.3006, "lr": 4.311545931511718e-05, "epoch": 6.356548856548857, "percentage": 31.78, "elapsed_time": "0:35:34", "remaining_time": "1:16:22", "throughput": 1032.15, "total_tokens": 2203592} {"current_steps": 24465, "total_steps": 76960, "loss": 0.2531, "lr": 4.311155164336318e-05, "epoch": 6.357848232848233, "percentage": 31.79, "elapsed_time": "0:35:35", "remaining_time": "1:16:21", "throughput": 1032.14, "total_tokens": 2203992} {"current_steps": 24470, "total_steps": 76960, "loss": 0.2383, "lr": 4.310764304011473e-05, "epoch": 6.359147609147609, "percentage": 31.8, "elapsed_time": "0:35:35", "remaining_time": "1:16:21", "throughput": 1032.13, "total_tokens": 2204408} {"current_steps": 24475, "total_steps": 76960, "loss": 0.1769, "lr": 4.3103733505572854e-05, "epoch": 6.360446985446986, "percentage": 31.8, "elapsed_time": "0:35:36", "remaining_time": "1:16:20", "throughput": 1032.16, "total_tokens": 2204888} {"current_steps": 24480, "total_steps": 76960, "loss": 0.4159, "lr": 4.30998230399386e-05, "epoch": 6.361746361746362, "percentage": 31.81, "elapsed_time": "0:35:36", "remaining_time": "1:16:20", "throughput": 1032.18, "total_tokens": 2205368} {"current_steps": 24485, "total_steps": 76960, "loss": 0.178, "lr": 4.3095911643413124e-05, "epoch": 6.363045738045738, "percentage": 31.82, "elapsed_time": "0:35:37", "remaining_time": "1:16:19", "throughput": 1032.2, "total_tokens": 2205832} {"current_steps": 24490, "total_steps": 76960, "loss": 0.3371, "lr": 4.309199931619756e-05, "epoch": 6.364345114345114, "percentage": 31.82, "elapsed_time": "0:35:37", "remaining_time": "1:16:19", "throughput": 1032.21, "total_tokens": 2206296} {"current_steps": 24495, "total_steps": 76960, "loss": 0.3046, "lr": 4.308808605849314e-05, "epoch": 6.365644490644491, "percentage": 31.83, "elapsed_time": "0:35:37", "remaining_time": "1:16:19", "throughput": 1032.22, "total_tokens": 2206744} {"current_steps": 24500, "total_steps": 76960, "loss": 0.2105, "lr": 4.308417187050113e-05, "epoch": 6.366943866943867, "percentage": 31.83, "elapsed_time": "0:35:38", "remaining_time": "1:16:18", "throughput": 1032.21, "total_tokens": 2207160} {"current_steps": 24505, "total_steps": 76960, "loss": 0.2218, "lr": 4.308025675242282e-05, "epoch": 6.368243243243243, "percentage": 31.84, "elapsed_time": "0:35:38", "remaining_time": "1:16:18", "throughput": 1032.22, "total_tokens": 2207592} {"current_steps": 24510, "total_steps": 76960, "loss": 0.2143, "lr": 4.307634070445959e-05, "epoch": 6.36954261954262, "percentage": 31.85, "elapsed_time": "0:35:39", "remaining_time": "1:16:17", "throughput": 1032.21, "total_tokens": 2208008} {"current_steps": 24515, "total_steps": 76960, "loss": 0.2652, "lr": 4.307242372681284e-05, "epoch": 6.370841995841996, "percentage": 31.85, "elapsed_time": "0:35:39", "remaining_time": "1:16:17", "throughput": 1032.23, "total_tokens": 2208472} {"current_steps": 24520, "total_steps": 76960, "loss": 0.3359, "lr": 4.306850581968402e-05, "epoch": 6.372141372141372, "percentage": 31.86, "elapsed_time": "0:35:39", "remaining_time": "1:16:16", "throughput": 1032.26, "total_tokens": 2208968} {"current_steps": 24525, "total_steps": 76960, "loss": 0.2348, "lr": 4.306458698327463e-05, "epoch": 6.373440748440748, "percentage": 31.87, "elapsed_time": "0:35:40", "remaining_time": "1:16:16", "throughput": 1032.27, "total_tokens": 2209416} {"current_steps": 24530, "total_steps": 76960, "loss": 0.26, "lr": 4.306066721778622e-05, "epoch": 6.374740124740125, "percentage": 31.87, "elapsed_time": "0:35:40", "remaining_time": "1:16:15", "throughput": 1032.28, "total_tokens": 2209880} {"current_steps": 24535, "total_steps": 76960, "loss": 0.2686, "lr": 4.30567465234204e-05, "epoch": 6.376039501039501, "percentage": 31.88, "elapsed_time": "0:35:41", "remaining_time": "1:16:15", "throughput": 1032.3, "total_tokens": 2210344} {"current_steps": 24540, "total_steps": 76960, "loss": 0.2583, "lr": 4.30528249003788e-05, "epoch": 6.377338877338877, "percentage": 31.89, "elapsed_time": "0:35:41", "remaining_time": "1:16:14", "throughput": 1032.29, "total_tokens": 2210760} {"current_steps": 24545, "total_steps": 76960, "loss": 0.2677, "lr": 4.3048902348863116e-05, "epoch": 6.378638253638254, "percentage": 31.89, "elapsed_time": "0:35:42", "remaining_time": "1:16:14", "throughput": 1032.3, "total_tokens": 2211208} {"current_steps": 24550, "total_steps": 76960, "loss": 0.2133, "lr": 4.3044978869075094e-05, "epoch": 6.37993762993763, "percentage": 31.9, "elapsed_time": "0:35:42", "remaining_time": "1:16:13", "throughput": 1032.3, "total_tokens": 2211640} {"current_steps": 24555, "total_steps": 76960, "loss": 0.2042, "lr": 4.304105446121651e-05, "epoch": 6.381237006237006, "percentage": 31.91, "elapsed_time": "0:35:42", "remaining_time": "1:16:13", "throughput": 1032.31, "total_tokens": 2212088} {"current_steps": 24560, "total_steps": 76960, "loss": 0.3324, "lr": 4.303712912548922e-05, "epoch": 6.382536382536383, "percentage": 31.91, "elapsed_time": "0:35:43", "remaining_time": "1:16:12", "throughput": 1032.33, "total_tokens": 2212568} {"current_steps": 24565, "total_steps": 76960, "loss": 0.2015, "lr": 4.303320286209509e-05, "epoch": 6.383835758835759, "percentage": 31.92, "elapsed_time": "0:35:43", "remaining_time": "1:16:12", "throughput": 1032.35, "total_tokens": 2213032} {"current_steps": 24570, "total_steps": 76960, "loss": 0.2992, "lr": 4.302927567123606e-05, "epoch": 6.385135135135135, "percentage": 31.93, "elapsed_time": "0:35:44", "remaining_time": "1:16:11", "throughput": 1032.34, "total_tokens": 2213448} {"current_steps": 24575, "total_steps": 76960, "loss": 0.2932, "lr": 4.302534755311411e-05, "epoch": 6.386434511434511, "percentage": 31.93, "elapsed_time": "0:35:44", "remaining_time": "1:16:11", "throughput": 1032.35, "total_tokens": 2213896} {"current_steps": 24580, "total_steps": 76960, "loss": 0.3036, "lr": 4.3021418507931266e-05, "epoch": 6.387733887733888, "percentage": 31.94, "elapsed_time": "0:35:44", "remaining_time": "1:16:10", "throughput": 1032.36, "total_tokens": 2214344} {"current_steps": 24585, "total_steps": 76960, "loss": 0.2349, "lr": 4.30174885358896e-05, "epoch": 6.389033264033264, "percentage": 31.95, "elapsed_time": "0:35:45", "remaining_time": "1:16:10", "throughput": 1032.36, "total_tokens": 2214776} {"current_steps": 24590, "total_steps": 76960, "loss": 0.278, "lr": 4.301355763719123e-05, "epoch": 6.39033264033264, "percentage": 31.95, "elapsed_time": "0:35:45", "remaining_time": "1:16:09", "throughput": 1032.36, "total_tokens": 2215208} {"current_steps": 24595, "total_steps": 76960, "loss": 0.2562, "lr": 4.300962581203833e-05, "epoch": 6.391632016632016, "percentage": 31.96, "elapsed_time": "0:35:46", "remaining_time": "1:16:09", "throughput": 1032.38, "total_tokens": 2215672} {"current_steps": 24600, "total_steps": 76960, "loss": 0.2866, "lr": 4.300569306063312e-05, "epoch": 6.392931392931393, "percentage": 31.96, "elapsed_time": "0:35:46", "remaining_time": "1:16:08", "throughput": 1032.39, "total_tokens": 2216136} {"current_steps": 24605, "total_steps": 76960, "loss": 0.2918, "lr": 4.3001759383177864e-05, "epoch": 6.394230769230769, "percentage": 31.97, "elapsed_time": "0:35:47", "remaining_time": "1:16:08", "throughput": 1032.4, "total_tokens": 2216584} {"current_steps": 24610, "total_steps": 76960, "loss": 0.2832, "lr": 4.299782477987488e-05, "epoch": 6.395530145530145, "percentage": 31.98, "elapsed_time": "0:35:47", "remaining_time": "1:16:07", "throughput": 1032.42, "total_tokens": 2217048} {"current_steps": 24615, "total_steps": 76960, "loss": 0.2855, "lr": 4.299388925092652e-05, "epoch": 6.396829521829522, "percentage": 31.98, "elapsed_time": "0:35:47", "remaining_time": "1:16:07", "throughput": 1032.44, "total_tokens": 2217528} {"current_steps": 24620, "total_steps": 76960, "loss": 0.2607, "lr": 4.2989952796535196e-05, "epoch": 6.398128898128898, "percentage": 31.99, "elapsed_time": "0:35:48", "remaining_time": "1:16:07", "throughput": 1032.45, "total_tokens": 2217976} {"current_steps": 24625, "total_steps": 76960, "loss": 0.2523, "lr": 4.298601541690336e-05, "epoch": 6.399428274428274, "percentage": 32.0, "elapsed_time": "0:35:48", "remaining_time": "1:16:06", "throughput": 1032.47, "total_tokens": 2218456} {"current_steps": 24630, "total_steps": 76960, "loss": 0.2855, "lr": 4.298207711223351e-05, "epoch": 6.400727650727651, "percentage": 32.0, "elapsed_time": "0:35:49", "remaining_time": "1:16:06", "throughput": 1032.49, "total_tokens": 2218920} {"current_steps": 24635, "total_steps": 76960, "loss": 0.1782, "lr": 4.297813788272822e-05, "epoch": 6.402027027027027, "percentage": 32.01, "elapsed_time": "0:35:49", "remaining_time": "1:16:05", "throughput": 1032.5, "total_tokens": 2219368} {"current_steps": 24640, "total_steps": 76960, "loss": 0.2574, "lr": 4.297419772859006e-05, "epoch": 6.403326403326403, "percentage": 32.02, "elapsed_time": "0:35:49", "remaining_time": "1:16:05", "throughput": 1032.48, "total_tokens": 2219768} {"current_steps": 24645, "total_steps": 76960, "loss": 0.3221, "lr": 4.29702566500217e-05, "epoch": 6.404625779625779, "percentage": 32.02, "elapsed_time": "0:35:50", "remaining_time": "1:16:04", "throughput": 1032.49, "total_tokens": 2220216} {"current_steps": 24650, "total_steps": 76960, "loss": 0.2533, "lr": 4.296631464722581e-05, "epoch": 6.405925155925156, "percentage": 32.03, "elapsed_time": "0:35:50", "remaining_time": "1:16:04", "throughput": 1032.52, "total_tokens": 2220696} {"current_steps": 24655, "total_steps": 76960, "loss": 0.2865, "lr": 4.2962371720405155e-05, "epoch": 6.407224532224532, "percentage": 32.04, "elapsed_time": "0:35:51", "remaining_time": "1:16:03", "throughput": 1032.52, "total_tokens": 2221128} {"current_steps": 24660, "total_steps": 76960, "loss": 0.2794, "lr": 4.2958427869762506e-05, "epoch": 6.408523908523908, "percentage": 32.04, "elapsed_time": "0:35:51", "remaining_time": "1:16:03", "throughput": 1032.52, "total_tokens": 2221560} {"current_steps": 24665, "total_steps": 76960, "loss": 0.2658, "lr": 4.2954483095500705e-05, "epoch": 6.409823284823285, "percentage": 32.05, "elapsed_time": "0:35:52", "remaining_time": "1:16:02", "throughput": 1032.52, "total_tokens": 2221992} {"current_steps": 24670, "total_steps": 76960, "loss": 0.276, "lr": 4.295053739782263e-05, "epoch": 6.411122661122661, "percentage": 32.06, "elapsed_time": "0:35:52", "remaining_time": "1:16:02", "throughput": 1032.53, "total_tokens": 2222456} {"current_steps": 24675, "total_steps": 76960, "loss": 0.2056, "lr": 4.2946590776931226e-05, "epoch": 6.412422037422037, "percentage": 32.06, "elapsed_time": "0:35:52", "remaining_time": "1:16:01", "throughput": 1032.54, "total_tokens": 2222904} {"current_steps": 24680, "total_steps": 76960, "loss": 0.2134, "lr": 4.294264323302946e-05, "epoch": 6.413721413721413, "percentage": 32.07, "elapsed_time": "0:35:53", "remaining_time": "1:16:01", "throughput": 1032.56, "total_tokens": 2223368} {"current_steps": 24685, "total_steps": 76960, "loss": 0.2756, "lr": 4.2938694766320356e-05, "epoch": 6.41502079002079, "percentage": 32.08, "elapsed_time": "0:35:53", "remaining_time": "1:16:00", "throughput": 1032.58, "total_tokens": 2223832} {"current_steps": 24690, "total_steps": 76960, "loss": 0.2508, "lr": 4.2934745377007e-05, "epoch": 6.416320166320166, "percentage": 32.08, "elapsed_time": "0:35:54", "remaining_time": "1:16:00", "throughput": 1032.59, "total_tokens": 2224296} {"current_steps": 24695, "total_steps": 76960, "loss": 0.3743, "lr": 4.2930795065292503e-05, "epoch": 6.417619542619542, "percentage": 32.09, "elapsed_time": "0:35:54", "remaining_time": "1:15:59", "throughput": 1032.59, "total_tokens": 2224728} {"current_steps": 24700, "total_steps": 76960, "loss": 0.2052, "lr": 4.292684383138003e-05, "epoch": 6.418918918918919, "percentage": 32.09, "elapsed_time": "0:35:54", "remaining_time": "1:15:59", "throughput": 1032.58, "total_tokens": 2225128} {"current_steps": 24705, "total_steps": 76960, "loss": 0.1511, "lr": 4.292289167547281e-05, "epoch": 6.420218295218295, "percentage": 32.1, "elapsed_time": "0:35:55", "remaining_time": "1:15:58", "throughput": 1032.6, "total_tokens": 2225592} {"current_steps": 24710, "total_steps": 76960, "loss": 0.3005, "lr": 4.291893859777409e-05, "epoch": 6.421517671517671, "percentage": 32.11, "elapsed_time": "0:35:55", "remaining_time": "1:15:58", "throughput": 1032.59, "total_tokens": 2226008} {"current_steps": 24715, "total_steps": 76960, "loss": 0.3518, "lr": 4.2914984598487197e-05, "epoch": 6.422817047817047, "percentage": 32.11, "elapsed_time": "0:35:56", "remaining_time": "1:15:57", "throughput": 1032.61, "total_tokens": 2226472} {"current_steps": 24720, "total_steps": 76960, "loss": 0.2768, "lr": 4.291102967781547e-05, "epoch": 6.424116424116424, "percentage": 32.12, "elapsed_time": "0:35:56", "remaining_time": "1:15:57", "throughput": 1032.61, "total_tokens": 2226904} {"current_steps": 24725, "total_steps": 76960, "loss": 0.1538, "lr": 4.2907073835962336e-05, "epoch": 6.4254158004158, "percentage": 32.13, "elapsed_time": "0:35:57", "remaining_time": "1:15:56", "throughput": 1032.61, "total_tokens": 2227336} {"current_steps": 24730, "total_steps": 76960, "loss": 0.2572, "lr": 4.2903117073131225e-05, "epoch": 6.4267151767151764, "percentage": 32.13, "elapsed_time": "0:35:57", "remaining_time": "1:15:56", "throughput": 1032.6, "total_tokens": 2227752} {"current_steps": 24735, "total_steps": 76960, "loss": 0.29, "lr": 4.2899159389525664e-05, "epoch": 6.428014553014553, "percentage": 32.14, "elapsed_time": "0:35:57", "remaining_time": "1:15:56", "throughput": 1032.61, "total_tokens": 2228200} {"current_steps": 24740, "total_steps": 76960, "loss": 0.3132, "lr": 4.289520078534918e-05, "epoch": 6.429313929313929, "percentage": 32.15, "elapsed_time": "0:35:58", "remaining_time": "1:15:55", "throughput": 1032.6, "total_tokens": 2228616} {"current_steps": 24745, "total_steps": 76960, "loss": 0.3019, "lr": 4.2891241260805374e-05, "epoch": 6.4306133056133055, "percentage": 32.15, "elapsed_time": "0:35:58", "remaining_time": "1:15:55", "throughput": 1032.6, "total_tokens": 2229048} {"current_steps": 24750, "total_steps": 76960, "loss": 0.2645, "lr": 4.288728081609787e-05, "epoch": 6.4319126819126815, "percentage": 32.16, "elapsed_time": "0:35:59", "remaining_time": "1:15:54", "throughput": 1032.6, "total_tokens": 2229480} {"current_steps": 24755, "total_steps": 76960, "loss": 0.2708, "lr": 4.28833194514304e-05, "epoch": 6.433212058212058, "percentage": 32.17, "elapsed_time": "0:35:59", "remaining_time": "1:15:54", "throughput": 1032.61, "total_tokens": 2229928} {"current_steps": 24760, "total_steps": 76960, "loss": 0.2701, "lr": 4.2879357167006664e-05, "epoch": 6.4345114345114345, "percentage": 32.17, "elapsed_time": "0:35:59", "remaining_time": "1:15:53", "throughput": 1032.64, "total_tokens": 2230408} {"current_steps": 24765, "total_steps": 76960, "loss": 0.2908, "lr": 4.287539396303046e-05, "epoch": 6.4358108108108105, "percentage": 32.18, "elapsed_time": "0:36:00", "remaining_time": "1:15:53", "throughput": 1032.66, "total_tokens": 2230888} {"current_steps": 24770, "total_steps": 76960, "loss": 0.2748, "lr": 4.2871429839705614e-05, "epoch": 6.4371101871101875, "percentage": 32.19, "elapsed_time": "0:36:00", "remaining_time": "1:15:52", "throughput": 1032.67, "total_tokens": 2231336} {"current_steps": 24775, "total_steps": 76960, "loss": 0.228, "lr": 4.286746479723601e-05, "epoch": 6.4384095634095635, "percentage": 32.19, "elapsed_time": "0:36:01", "remaining_time": "1:15:52", "throughput": 1032.67, "total_tokens": 2231784} {"current_steps": 24780, "total_steps": 76960, "loss": 0.2076, "lr": 4.286349883582557e-05, "epoch": 6.4397089397089395, "percentage": 32.2, "elapsed_time": "0:36:01", "remaining_time": "1:15:51", "throughput": 1032.69, "total_tokens": 2232248} {"current_steps": 24785, "total_steps": 76960, "loss": 0.2013, "lr": 4.285953195567827e-05, "epoch": 6.4410083160083165, "percentage": 32.21, "elapsed_time": "0:36:02", "remaining_time": "1:15:51", "throughput": 1032.71, "total_tokens": 2232728} {"current_steps": 24790, "total_steps": 76960, "loss": 0.2184, "lr": 4.285556415699813e-05, "epoch": 6.4423076923076925, "percentage": 32.21, "elapsed_time": "0:36:02", "remaining_time": "1:15:50", "throughput": 1032.71, "total_tokens": 2233160} {"current_steps": 24795, "total_steps": 76960, "loss": 0.2331, "lr": 4.285159543998922e-05, "epoch": 6.4436070686070686, "percentage": 32.22, "elapsed_time": "0:36:02", "remaining_time": "1:15:50", "throughput": 1032.71, "total_tokens": 2233576} {"current_steps": 24800, "total_steps": 76960, "loss": 0.0483, "lr": 4.284762580485565e-05, "epoch": 6.444906444906445, "percentage": 32.22, "elapsed_time": "0:36:03", "remaining_time": "1:15:49", "throughput": 1032.71, "total_tokens": 2234008} {"current_steps": 24805, "total_steps": 76960, "loss": 0.4348, "lr": 4.284365525180158e-05, "epoch": 6.4462058212058215, "percentage": 32.23, "elapsed_time": "0:36:03", "remaining_time": "1:15:49", "throughput": 1032.72, "total_tokens": 2234472} {"current_steps": 24810, "total_steps": 76960, "loss": 0.181, "lr": 4.283968378103123e-05, "epoch": 6.447505197505198, "percentage": 32.24, "elapsed_time": "0:36:04", "remaining_time": "1:15:48", "throughput": 1032.73, "total_tokens": 2234904} {"current_steps": 24815, "total_steps": 76960, "loss": 0.2703, "lr": 4.2835711392748846e-05, "epoch": 6.448804573804574, "percentage": 32.24, "elapsed_time": "0:36:04", "remaining_time": "1:15:48", "throughput": 1032.74, "total_tokens": 2235368} {"current_steps": 24820, "total_steps": 76960, "loss": 0.178, "lr": 4.283173808715873e-05, "epoch": 6.45010395010395, "percentage": 32.25, "elapsed_time": "0:36:04", "remaining_time": "1:15:47", "throughput": 1032.74, "total_tokens": 2235800} {"current_steps": 24825, "total_steps": 76960, "loss": 0.2492, "lr": 4.282776386446524e-05, "epoch": 6.451403326403327, "percentage": 32.26, "elapsed_time": "0:36:05", "remaining_time": "1:15:47", "throughput": 1032.76, "total_tokens": 2236264} {"current_steps": 24830, "total_steps": 76960, "loss": 0.2544, "lr": 4.282378872487278e-05, "epoch": 6.452702702702703, "percentage": 32.26, "elapsed_time": "0:36:05", "remaining_time": "1:15:46", "throughput": 1032.76, "total_tokens": 2236696} {"current_steps": 24835, "total_steps": 76960, "loss": 0.1619, "lr": 4.281981266858579e-05, "epoch": 6.454002079002079, "percentage": 32.27, "elapsed_time": "0:36:06", "remaining_time": "1:15:46", "throughput": 1032.78, "total_tokens": 2237160} {"current_steps": 24840, "total_steps": 76960, "loss": 0.1331, "lr": 4.2815835695808754e-05, "epoch": 6.455301455301456, "percentage": 32.28, "elapsed_time": "0:36:06", "remaining_time": "1:15:45", "throughput": 1032.77, "total_tokens": 2237576} {"current_steps": 24845, "total_steps": 76960, "loss": 0.4693, "lr": 4.2811857806746215e-05, "epoch": 6.456600831600832, "percentage": 32.28, "elapsed_time": "0:36:06", "remaining_time": "1:15:45", "throughput": 1032.77, "total_tokens": 2238008} {"current_steps": 24850, "total_steps": 76960, "loss": 0.1343, "lr": 4.2807879001602766e-05, "epoch": 6.457900207900208, "percentage": 32.29, "elapsed_time": "0:36:07", "remaining_time": "1:15:45", "throughput": 1032.78, "total_tokens": 2238456} {"current_steps": 24855, "total_steps": 76960, "loss": 0.2427, "lr": 4.2803899280583034e-05, "epoch": 6.459199584199585, "percentage": 32.3, "elapsed_time": "0:36:07", "remaining_time": "1:15:44", "throughput": 1032.77, "total_tokens": 2238872} {"current_steps": 24860, "total_steps": 76960, "loss": 0.2023, "lr": 4.279991864389171e-05, "epoch": 6.460498960498961, "percentage": 32.3, "elapsed_time": "0:36:08", "remaining_time": "1:15:44", "throughput": 1032.78, "total_tokens": 2239320} {"current_steps": 24865, "total_steps": 76960, "loss": 0.1959, "lr": 4.2795937091733515e-05, "epoch": 6.461798336798337, "percentage": 32.31, "elapsed_time": "0:36:08", "remaining_time": "1:15:43", "throughput": 1032.78, "total_tokens": 2239752} {"current_steps": 24870, "total_steps": 76960, "loss": 0.3203, "lr": 4.2791954624313224e-05, "epoch": 6.463097713097713, "percentage": 32.32, "elapsed_time": "0:36:09", "remaining_time": "1:15:43", "throughput": 1032.79, "total_tokens": 2240200} {"current_steps": 24875, "total_steps": 76960, "loss": 0.2669, "lr": 4.278797124183566e-05, "epoch": 6.46439708939709, "percentage": 32.32, "elapsed_time": "0:36:09", "remaining_time": "1:15:42", "throughput": 1032.81, "total_tokens": 2240664} {"current_steps": 24880, "total_steps": 76960, "loss": 0.2339, "lr": 4.278398694450568e-05, "epoch": 6.465696465696466, "percentage": 32.33, "elapsed_time": "0:36:09", "remaining_time": "1:15:42", "throughput": 1032.81, "total_tokens": 2241096} {"current_steps": 24885, "total_steps": 76960, "loss": 0.3475, "lr": 4.2780001732528224e-05, "epoch": 6.466995841995842, "percentage": 32.33, "elapsed_time": "0:36:10", "remaining_time": "1:15:41", "throughput": 1032.82, "total_tokens": 2241560} {"current_steps": 24890, "total_steps": 76960, "loss": 0.3283, "lr": 4.277601560610824e-05, "epoch": 6.468295218295219, "percentage": 32.34, "elapsed_time": "0:36:10", "remaining_time": "1:15:41", "throughput": 1032.83, "total_tokens": 2242008} {"current_steps": 24895, "total_steps": 76960, "loss": 0.2795, "lr": 4.277202856545074e-05, "epoch": 6.469594594594595, "percentage": 32.35, "elapsed_time": "0:36:11", "remaining_time": "1:15:40", "throughput": 1032.85, "total_tokens": 2242472} {"current_steps": 24900, "total_steps": 76960, "loss": 0.3028, "lr": 4.276804061076078e-05, "epoch": 6.470893970893971, "percentage": 32.35, "elapsed_time": "0:36:11", "remaining_time": "1:15:40", "throughput": 1032.85, "total_tokens": 2242920} {"current_steps": 24905, "total_steps": 76960, "loss": 0.29, "lr": 4.276405174224347e-05, "epoch": 6.472193347193347, "percentage": 32.36, "elapsed_time": "0:36:11", "remaining_time": "1:15:39", "throughput": 1032.87, "total_tokens": 2243384} {"current_steps": 24910, "total_steps": 76960, "loss": 0.2648, "lr": 4.2760061960103956e-05, "epoch": 6.473492723492724, "percentage": 32.37, "elapsed_time": "0:36:12", "remaining_time": "1:15:39", "throughput": 1032.9, "total_tokens": 2243880} {"current_steps": 24915, "total_steps": 76960, "loss": 0.2701, "lr": 4.275607126454744e-05, "epoch": 6.4747920997921, "percentage": 32.37, "elapsed_time": "0:36:12", "remaining_time": "1:15:38", "throughput": 1032.91, "total_tokens": 2244328} {"current_steps": 24920, "total_steps": 76960, "loss": 0.2887, "lr": 4.2752079655779165e-05, "epoch": 6.476091476091476, "percentage": 32.38, "elapsed_time": "0:36:13", "remaining_time": "1:15:38", "throughput": 1032.93, "total_tokens": 2244808} {"current_steps": 24925, "total_steps": 76960, "loss": 0.2942, "lr": 4.274808713400443e-05, "epoch": 6.477390852390853, "percentage": 32.39, "elapsed_time": "0:36:13", "remaining_time": "1:15:37", "throughput": 1032.96, "total_tokens": 2245304} {"current_steps": 24930, "total_steps": 76960, "loss": 0.3145, "lr": 4.274409369942856e-05, "epoch": 6.478690228690229, "percentage": 32.39, "elapsed_time": "0:36:14", "remaining_time": "1:15:37", "throughput": 1032.96, "total_tokens": 2245736} {"current_steps": 24935, "total_steps": 76960, "loss": 0.2659, "lr": 4.274009935225696e-05, "epoch": 6.479989604989605, "percentage": 32.4, "elapsed_time": "0:36:14", "remaining_time": "1:15:36", "throughput": 1032.99, "total_tokens": 2246216} {"current_steps": 24940, "total_steps": 76960, "loss": 0.2664, "lr": 4.273610409269504e-05, "epoch": 6.481288981288981, "percentage": 32.41, "elapsed_time": "0:36:14", "remaining_time": "1:15:36", "throughput": 1032.99, "total_tokens": 2246664} {"current_steps": 24945, "total_steps": 76960, "loss": 0.265, "lr": 4.27321079209483e-05, "epoch": 6.482588357588358, "percentage": 32.41, "elapsed_time": "0:36:15", "remaining_time": "1:15:35", "throughput": 1033.0, "total_tokens": 2247112} {"current_steps": 24950, "total_steps": 76960, "loss": 0.2642, "lr": 4.2728110837222255e-05, "epoch": 6.483887733887734, "percentage": 32.42, "elapsed_time": "0:36:15", "remaining_time": "1:15:35", "throughput": 1033.02, "total_tokens": 2247576} {"current_steps": 24955, "total_steps": 76960, "loss": 0.2717, "lr": 4.2724112841722484e-05, "epoch": 6.48518711018711, "percentage": 32.43, "elapsed_time": "0:36:16", "remaining_time": "1:15:34", "throughput": 1033.04, "total_tokens": 2248056} {"current_steps": 24960, "total_steps": 76960, "loss": 0.3054, "lr": 4.272011393465461e-05, "epoch": 6.486486486486487, "percentage": 32.43, "elapsed_time": "0:36:16", "remaining_time": "1:15:34", "throughput": 1033.05, "total_tokens": 2248504} {"current_steps": 24965, "total_steps": 76960, "loss": 0.2759, "lr": 4.271611411622429e-05, "epoch": 6.487785862785863, "percentage": 32.44, "elapsed_time": "0:36:16", "remaining_time": "1:15:34", "throughput": 1033.04, "total_tokens": 2248904} {"current_steps": 24970, "total_steps": 76960, "loss": 0.3172, "lr": 4.271211338663726e-05, "epoch": 6.489085239085239, "percentage": 32.45, "elapsed_time": "0:36:17", "remaining_time": "1:15:33", "throughput": 1033.04, "total_tokens": 2249336} {"current_steps": 24975, "total_steps": 76960, "loss": 0.2765, "lr": 4.270811174609926e-05, "epoch": 6.490384615384615, "percentage": 32.45, "elapsed_time": "0:36:17", "remaining_time": "1:15:33", "throughput": 1033.03, "total_tokens": 2249752} {"current_steps": 24980, "total_steps": 76960, "loss": 0.2495, "lr": 4.270410919481611e-05, "epoch": 6.491683991683992, "percentage": 32.46, "elapsed_time": "0:36:18", "remaining_time": "1:15:32", "throughput": 1033.05, "total_tokens": 2250216} {"current_steps": 24985, "total_steps": 76960, "loss": 0.2218, "lr": 4.270010573299366e-05, "epoch": 6.492983367983368, "percentage": 32.46, "elapsed_time": "0:36:18", "remaining_time": "1:15:32", "throughput": 1033.03, "total_tokens": 2250616} {"current_steps": 24990, "total_steps": 76960, "loss": 0.2248, "lr": 4.2696101360837806e-05, "epoch": 6.494282744282744, "percentage": 32.47, "elapsed_time": "0:36:19", "remaining_time": "1:15:31", "throughput": 1033.04, "total_tokens": 2251064} {"current_steps": 24995, "total_steps": 76960, "loss": 0.2745, "lr": 4.26920960785545e-05, "epoch": 6.495582120582121, "percentage": 32.48, "elapsed_time": "0:36:19", "remaining_time": "1:15:31", "throughput": 1033.04, "total_tokens": 2251496} {"current_steps": 25000, "total_steps": 76960, "loss": 0.212, "lr": 4.268808988634975e-05, "epoch": 6.496881496881497, "percentage": 32.48, "elapsed_time": "0:36:19", "remaining_time": "1:15:30", "throughput": 1033.05, "total_tokens": 2251944} {"current_steps": 25005, "total_steps": 76960, "loss": 0.3065, "lr": 4.2684082784429593e-05, "epoch": 6.498180873180873, "percentage": 32.49, "elapsed_time": "0:36:20", "remaining_time": "1:15:30", "throughput": 1033.07, "total_tokens": 2252408} {"current_steps": 25010, "total_steps": 76960, "loss": 0.1629, "lr": 4.2680074773000106e-05, "epoch": 6.49948024948025, "percentage": 32.5, "elapsed_time": "0:36:20", "remaining_time": "1:15:29", "throughput": 1033.06, "total_tokens": 2252824} {"current_steps": 25015, "total_steps": 76960, "loss": 0.2987, "lr": 4.2676065852267435e-05, "epoch": 6.500779625779626, "percentage": 32.5, "elapsed_time": "0:36:21", "remaining_time": "1:15:29", "throughput": 1033.07, "total_tokens": 2253288} {"current_steps": 25020, "total_steps": 76960, "loss": 0.2391, "lr": 4.267205602243777e-05, "epoch": 6.502079002079002, "percentage": 32.51, "elapsed_time": "0:36:21", "remaining_time": "1:15:28", "throughput": 1033.1, "total_tokens": 2253768} {"current_steps": 25025, "total_steps": 76960, "loss": 0.2541, "lr": 4.266804528371732e-05, "epoch": 6.503378378378378, "percentage": 32.52, "elapsed_time": "0:36:21", "remaining_time": "1:15:28", "throughput": 1033.11, "total_tokens": 2254232} {"current_steps": 25030, "total_steps": 76960, "loss": 0.2266, "lr": 4.2664033636312374e-05, "epoch": 6.504677754677755, "percentage": 32.52, "elapsed_time": "0:36:22", "remaining_time": "1:15:27", "throughput": 1033.11, "total_tokens": 2254664} {"current_steps": 25035, "total_steps": 76960, "loss": 0.2492, "lr": 4.2660021080429253e-05, "epoch": 6.505977130977131, "percentage": 32.53, "elapsed_time": "0:36:22", "remaining_time": "1:15:27", "throughput": 1033.11, "total_tokens": 2255096} {"current_steps": 25040, "total_steps": 76960, "loss": 0.1902, "lr": 4.265600761627433e-05, "epoch": 6.507276507276507, "percentage": 32.54, "elapsed_time": "0:36:23", "remaining_time": "1:15:26", "throughput": 1033.14, "total_tokens": 2255592} {"current_steps": 25045, "total_steps": 76960, "loss": 0.2327, "lr": 4.265199324405401e-05, "epoch": 6.508575883575883, "percentage": 32.54, "elapsed_time": "0:36:23", "remaining_time": "1:15:26", "throughput": 1033.14, "total_tokens": 2256024} {"current_steps": 25050, "total_steps": 76960, "loss": 0.2436, "lr": 4.264797796397477e-05, "epoch": 6.50987525987526, "percentage": 32.55, "elapsed_time": "0:36:24", "remaining_time": "1:15:25", "throughput": 1033.15, "total_tokens": 2256472} {"current_steps": 25055, "total_steps": 76960, "loss": 0.1361, "lr": 4.264396177624312e-05, "epoch": 6.511174636174636, "percentage": 32.56, "elapsed_time": "0:36:24", "remaining_time": "1:15:25", "throughput": 1033.17, "total_tokens": 2256936} {"current_steps": 25060, "total_steps": 76960, "loss": 0.2948, "lr": 4.26399446810656e-05, "epoch": 6.512474012474012, "percentage": 32.56, "elapsed_time": "0:36:24", "remaining_time": "1:15:24", "throughput": 1033.17, "total_tokens": 2257368} {"current_steps": 25065, "total_steps": 76960, "loss": 0.2271, "lr": 4.263592667864883e-05, "epoch": 6.513773388773389, "percentage": 32.57, "elapsed_time": "0:36:25", "remaining_time": "1:15:24", "throughput": 1033.19, "total_tokens": 2257832} {"current_steps": 25070, "total_steps": 76960, "loss": 0.2152, "lr": 4.2631907769199456e-05, "epoch": 6.515072765072765, "percentage": 32.58, "elapsed_time": "0:36:25", "remaining_time": "1:15:24", "throughput": 1033.22, "total_tokens": 2258328} {"current_steps": 25075, "total_steps": 76960, "loss": 0.3497, "lr": 4.2627887952924165e-05, "epoch": 6.516372141372141, "percentage": 32.58, "elapsed_time": "0:36:26", "remaining_time": "1:15:23", "throughput": 1033.22, "total_tokens": 2258776} {"current_steps": 25080, "total_steps": 76960, "loss": 0.3182, "lr": 4.26238672300297e-05, "epoch": 6.517671517671518, "percentage": 32.59, "elapsed_time": "0:36:26", "remaining_time": "1:15:23", "throughput": 1033.24, "total_tokens": 2259240} {"current_steps": 25085, "total_steps": 76960, "loss": 0.1193, "lr": 4.261984560072287e-05, "epoch": 6.518970893970894, "percentage": 32.59, "elapsed_time": "0:36:26", "remaining_time": "1:15:22", "throughput": 1033.25, "total_tokens": 2259688} {"current_steps": 25090, "total_steps": 76960, "loss": 0.213, "lr": 4.2615823065210494e-05, "epoch": 6.52027027027027, "percentage": 32.6, "elapsed_time": "0:36:27", "remaining_time": "1:15:22", "throughput": 1033.25, "total_tokens": 2260120} {"current_steps": 25095, "total_steps": 76960, "loss": 0.1737, "lr": 4.261179962369946e-05, "epoch": 6.521569646569646, "percentage": 32.61, "elapsed_time": "0:36:27", "remaining_time": "1:15:21", "throughput": 1033.26, "total_tokens": 2260584} {"current_steps": 25100, "total_steps": 76960, "loss": 0.284, "lr": 4.260777527639669e-05, "epoch": 6.522869022869023, "percentage": 32.61, "elapsed_time": "0:36:28", "remaining_time": "1:15:21", "throughput": 1033.28, "total_tokens": 2261048} {"current_steps": 25105, "total_steps": 76960, "loss": 0.1046, "lr": 4.260375002350917e-05, "epoch": 6.524168399168399, "percentage": 32.62, "elapsed_time": "0:36:28", "remaining_time": "1:15:20", "throughput": 1033.32, "total_tokens": 2261560} {"current_steps": 25110, "total_steps": 76960, "loss": 0.2038, "lr": 4.2599723865243926e-05, "epoch": 6.525467775467775, "percentage": 32.63, "elapsed_time": "0:36:29", "remaining_time": "1:15:20", "throughput": 1033.32, "total_tokens": 2262008} {"current_steps": 25115, "total_steps": 76960, "loss": 0.2824, "lr": 4.2595696801808014e-05, "epoch": 6.526767151767151, "percentage": 32.63, "elapsed_time": "0:36:29", "remaining_time": "1:15:19", "throughput": 1033.33, "total_tokens": 2262456} {"current_steps": 25120, "total_steps": 76960, "loss": 0.2557, "lr": 4.259166883340856e-05, "epoch": 6.528066528066528, "percentage": 32.64, "elapsed_time": "0:36:29", "remaining_time": "1:15:19", "throughput": 1033.33, "total_tokens": 2262872} {"current_steps": 25125, "total_steps": 76960, "loss": 0.3749, "lr": 4.258763996025271e-05, "epoch": 6.529365904365904, "percentage": 32.65, "elapsed_time": "0:36:30", "remaining_time": "1:15:18", "throughput": 1033.32, "total_tokens": 2263288} {"current_steps": 25130, "total_steps": 76960, "loss": 0.1705, "lr": 4.258361018254769e-05, "epoch": 6.53066528066528, "percentage": 32.65, "elapsed_time": "0:36:30", "remaining_time": "1:15:18", "throughput": 1033.35, "total_tokens": 2263784} {"current_steps": 25135, "total_steps": 76960, "loss": 0.2424, "lr": 4.257957950050076e-05, "epoch": 6.531964656964657, "percentage": 32.66, "elapsed_time": "0:36:31", "remaining_time": "1:15:17", "throughput": 1033.34, "total_tokens": 2264200} {"current_steps": 25140, "total_steps": 76960, "loss": 0.2576, "lr": 4.2575547914319206e-05, "epoch": 6.533264033264033, "percentage": 32.67, "elapsed_time": "0:36:31", "remaining_time": "1:15:17", "throughput": 1033.37, "total_tokens": 2264696} {"current_steps": 25145, "total_steps": 76960, "loss": 0.2122, "lr": 4.257151542421038e-05, "epoch": 6.534563409563409, "percentage": 32.67, "elapsed_time": "0:36:31", "remaining_time": "1:15:16", "throughput": 1033.38, "total_tokens": 2265144} {"current_steps": 25150, "total_steps": 76960, "loss": 0.2262, "lr": 4.256748203038169e-05, "epoch": 6.535862785862786, "percentage": 32.68, "elapsed_time": "0:36:32", "remaining_time": "1:15:16", "throughput": 1033.38, "total_tokens": 2265576} {"current_steps": 25155, "total_steps": 76960, "loss": 0.1713, "lr": 4.256344773304056e-05, "epoch": 6.537162162162162, "percentage": 32.69, "elapsed_time": "0:36:32", "remaining_time": "1:15:15", "throughput": 1033.39, "total_tokens": 2266024} {"current_steps": 25160, "total_steps": 76960, "loss": 0.2705, "lr": 4.2559412532394486e-05, "epoch": 6.538461538461538, "percentage": 32.69, "elapsed_time": "0:36:33", "remaining_time": "1:15:15", "throughput": 1033.38, "total_tokens": 2266440} {"current_steps": 25165, "total_steps": 76960, "loss": 0.2495, "lr": 4.2555376428651e-05, "epoch": 6.539760914760915, "percentage": 32.7, "elapsed_time": "0:36:33", "remaining_time": "1:15:15", "throughput": 1033.39, "total_tokens": 2266904} {"current_steps": 25170, "total_steps": 76960, "loss": 0.1465, "lr": 4.2551339422017686e-05, "epoch": 6.541060291060291, "percentage": 32.71, "elapsed_time": "0:36:34", "remaining_time": "1:15:14", "throughput": 1033.4, "total_tokens": 2267352} {"current_steps": 25175, "total_steps": 76960, "loss": 0.2197, "lr": 4.2547301512702166e-05, "epoch": 6.542359667359667, "percentage": 32.71, "elapsed_time": "0:36:34", "remaining_time": "1:15:14", "throughput": 1033.4, "total_tokens": 2267768} {"current_steps": 25180, "total_steps": 76960, "loss": 0.3273, "lr": 4.254326270091211e-05, "epoch": 6.543659043659043, "percentage": 32.72, "elapsed_time": "0:36:34", "remaining_time": "1:15:13", "throughput": 1033.39, "total_tokens": 2268184} {"current_steps": 25185, "total_steps": 76960, "loss": 0.282, "lr": 4.253922298685525e-05, "epoch": 6.54495841995842, "percentage": 32.72, "elapsed_time": "0:36:35", "remaining_time": "1:15:13", "throughput": 1033.41, "total_tokens": 2268648} {"current_steps": 25190, "total_steps": 76960, "loss": 0.2872, "lr": 4.2535182370739345e-05, "epoch": 6.546257796257796, "percentage": 32.73, "elapsed_time": "0:36:35", "remaining_time": "1:15:12", "throughput": 1033.43, "total_tokens": 2269128} {"current_steps": 25195, "total_steps": 76960, "loss": 0.2234, "lr": 4.253114085277221e-05, "epoch": 6.547557172557172, "percentage": 32.74, "elapsed_time": "0:36:36", "remaining_time": "1:15:12", "throughput": 1033.42, "total_tokens": 2269544} {"current_steps": 25200, "total_steps": 76960, "loss": 0.1779, "lr": 4.252709843316171e-05, "epoch": 6.548856548856548, "percentage": 32.74, "elapsed_time": "0:36:36", "remaining_time": "1:15:11", "throughput": 1033.43, "total_tokens": 2269992} {"current_steps": 25205, "total_steps": 76960, "loss": 0.2304, "lr": 4.252305511211574e-05, "epoch": 6.550155925155925, "percentage": 32.75, "elapsed_time": "0:36:36", "remaining_time": "1:15:11", "throughput": 1033.44, "total_tokens": 2270456} {"current_steps": 25210, "total_steps": 76960, "loss": 0.3535, "lr": 4.251901088984225e-05, "epoch": 6.551455301455301, "percentage": 32.76, "elapsed_time": "0:36:37", "remaining_time": "1:15:10", "throughput": 1033.47, "total_tokens": 2270936} {"current_steps": 25215, "total_steps": 76960, "loss": 0.218, "lr": 4.2514965766549245e-05, "epoch": 6.5527546777546775, "percentage": 32.76, "elapsed_time": "0:36:37", "remaining_time": "1:15:10", "throughput": 1033.47, "total_tokens": 2271384} {"current_steps": 25220, "total_steps": 76960, "loss": 0.2627, "lr": 4.251091974244478e-05, "epoch": 6.554054054054054, "percentage": 32.77, "elapsed_time": "0:36:38", "remaining_time": "1:15:09", "throughput": 1033.47, "total_tokens": 2271800} {"current_steps": 25225, "total_steps": 76960, "loss": 0.2267, "lr": 4.250687281773692e-05, "epoch": 6.55535343035343, "percentage": 32.78, "elapsed_time": "0:36:38", "remaining_time": "1:15:09", "throughput": 1033.48, "total_tokens": 2272264} {"current_steps": 25230, "total_steps": 76960, "loss": 0.3252, "lr": 4.2502824992633826e-05, "epoch": 6.5566528066528065, "percentage": 32.78, "elapsed_time": "0:36:39", "remaining_time": "1:15:08", "throughput": 1033.49, "total_tokens": 2272712} {"current_steps": 25235, "total_steps": 76960, "loss": 0.2629, "lr": 4.2498776267343664e-05, "epoch": 6.557952182952183, "percentage": 32.79, "elapsed_time": "0:36:39", "remaining_time": "1:15:08", "throughput": 1033.49, "total_tokens": 2273144} {"current_steps": 25240, "total_steps": 76960, "loss": 0.2575, "lr": 4.249472664207468e-05, "epoch": 6.5592515592515594, "percentage": 32.8, "elapsed_time": "0:36:39", "remaining_time": "1:15:07", "throughput": 1033.5, "total_tokens": 2273592} {"current_steps": 25245, "total_steps": 76960, "loss": 0.2542, "lr": 4.249067611703514e-05, "epoch": 6.5605509355509355, "percentage": 32.8, "elapsed_time": "0:36:40", "remaining_time": "1:15:07", "throughput": 1033.53, "total_tokens": 2274072} {"current_steps": 25250, "total_steps": 76960, "loss": 0.2718, "lr": 4.248662469243336e-05, "epoch": 6.5618503118503115, "percentage": 32.81, "elapsed_time": "0:36:40", "remaining_time": "1:15:06", "throughput": 1033.53, "total_tokens": 2274520} {"current_steps": 25255, "total_steps": 76960, "loss": 0.193, "lr": 4.248257236847774e-05, "epoch": 6.5631496881496885, "percentage": 32.82, "elapsed_time": "0:36:41", "remaining_time": "1:15:06", "throughput": 1033.55, "total_tokens": 2274984} {"current_steps": 25260, "total_steps": 76960, "loss": 0.3085, "lr": 4.247851914537665e-05, "epoch": 6.5644490644490645, "percentage": 32.82, "elapsed_time": "0:36:41", "remaining_time": "1:15:05", "throughput": 1033.56, "total_tokens": 2275448} {"current_steps": 25265, "total_steps": 76960, "loss": 0.1641, "lr": 4.247446502333858e-05, "epoch": 6.5657484407484406, "percentage": 32.83, "elapsed_time": "0:36:41", "remaining_time": "1:15:05", "throughput": 1033.58, "total_tokens": 2275912} {"current_steps": 25270, "total_steps": 76960, "loss": 0.2097, "lr": 4.247041000257203e-05, "epoch": 6.567047817047817, "percentage": 32.84, "elapsed_time": "0:36:42", "remaining_time": "1:15:05", "throughput": 1033.59, "total_tokens": 2276360} {"current_steps": 25275, "total_steps": 76960, "loss": 0.4262, "lr": 4.2466354083285556e-05, "epoch": 6.5683471933471935, "percentage": 32.84, "elapsed_time": "0:36:42", "remaining_time": "1:15:04", "throughput": 1033.59, "total_tokens": 2276808} {"current_steps": 25280, "total_steps": 76960, "loss": 0.2935, "lr": 4.2462297265687754e-05, "epoch": 6.56964656964657, "percentage": 32.85, "elapsed_time": "0:36:43", "remaining_time": "1:15:04", "throughput": 1033.61, "total_tokens": 2277272} {"current_steps": 25285, "total_steps": 76960, "loss": 0.227, "lr": 4.245823954998728e-05, "epoch": 6.570945945945946, "percentage": 32.85, "elapsed_time": "0:36:43", "remaining_time": "1:15:03", "throughput": 1033.61, "total_tokens": 2277704} {"current_steps": 25290, "total_steps": 76960, "loss": 0.2282, "lr": 4.2454180936392805e-05, "epoch": 6.5722453222453225, "percentage": 32.86, "elapsed_time": "0:36:44", "remaining_time": "1:15:03", "throughput": 1033.63, "total_tokens": 2278168} {"current_steps": 25295, "total_steps": 76960, "loss": 0.3195, "lr": 4.245012142511309e-05, "epoch": 6.573544698544699, "percentage": 32.87, "elapsed_time": "0:36:44", "remaining_time": "1:15:02", "throughput": 1033.64, "total_tokens": 2278632} {"current_steps": 25300, "total_steps": 76960, "loss": 0.3015, "lr": 4.244606101635691e-05, "epoch": 6.574844074844075, "percentage": 32.87, "elapsed_time": "0:36:44", "remaining_time": "1:15:02", "throughput": 1033.66, "total_tokens": 2279096} {"current_steps": 25305, "total_steps": 76960, "loss": 0.2594, "lr": 4.2441999710333094e-05, "epoch": 6.576143451143452, "percentage": 32.88, "elapsed_time": "0:36:45", "remaining_time": "1:15:01", "throughput": 1033.66, "total_tokens": 2279544} {"current_steps": 25310, "total_steps": 76960, "loss": 0.2251, "lr": 4.243793750725052e-05, "epoch": 6.577442827442828, "percentage": 32.89, "elapsed_time": "0:36:45", "remaining_time": "1:15:01", "throughput": 1033.68, "total_tokens": 2280008} {"current_steps": 25315, "total_steps": 76960, "loss": 0.1927, "lr": 4.243387440731811e-05, "epoch": 6.578742203742204, "percentage": 32.89, "elapsed_time": "0:36:46", "remaining_time": "1:15:00", "throughput": 1033.69, "total_tokens": 2280456} {"current_steps": 25320, "total_steps": 76960, "loss": 0.2577, "lr": 4.2429810410744835e-05, "epoch": 6.58004158004158, "percentage": 32.9, "elapsed_time": "0:36:46", "remaining_time": "1:15:00", "throughput": 1033.7, "total_tokens": 2280920} {"current_steps": 25325, "total_steps": 76960, "loss": 0.3257, "lr": 4.242574551773971e-05, "epoch": 6.581340956340957, "percentage": 32.91, "elapsed_time": "0:36:46", "remaining_time": "1:14:59", "throughput": 1033.7, "total_tokens": 2281352} {"current_steps": 25330, "total_steps": 76960, "loss": 0.2969, "lr": 4.24216797285118e-05, "epoch": 6.582640332640333, "percentage": 32.91, "elapsed_time": "0:36:47", "remaining_time": "1:14:59", "throughput": 1033.7, "total_tokens": 2281768} {"current_steps": 25335, "total_steps": 76960, "loss": 0.2405, "lr": 4.241761304327021e-05, "epoch": 6.583939708939709, "percentage": 32.92, "elapsed_time": "0:36:47", "remaining_time": "1:14:58", "throughput": 1033.71, "total_tokens": 2282232} {"current_steps": 25340, "total_steps": 76960, "loss": 0.2202, "lr": 4.241354546222408e-05, "epoch": 6.585239085239085, "percentage": 32.93, "elapsed_time": "0:36:48", "remaining_time": "1:14:58", "throughput": 1033.73, "total_tokens": 2282696} {"current_steps": 25345, "total_steps": 76960, "loss": 0.2834, "lr": 4.2409476985582644e-05, "epoch": 6.586538461538462, "percentage": 32.93, "elapsed_time": "0:36:48", "remaining_time": "1:14:57", "throughput": 1033.73, "total_tokens": 2283128} {"current_steps": 25350, "total_steps": 76960, "loss": 0.4142, "lr": 4.240540761355512e-05, "epoch": 6.587837837837838, "percentage": 32.94, "elapsed_time": "0:36:49", "remaining_time": "1:14:57", "throughput": 1033.74, "total_tokens": 2283592} {"current_steps": 25355, "total_steps": 76960, "loss": 0.2302, "lr": 4.240133734635079e-05, "epoch": 6.589137214137214, "percentage": 32.95, "elapsed_time": "0:36:49", "remaining_time": "1:14:56", "throughput": 1033.75, "total_tokens": 2284040} {"current_steps": 25360, "total_steps": 76960, "loss": 0.3075, "lr": 4.2397266184179015e-05, "epoch": 6.590436590436591, "percentage": 32.95, "elapsed_time": "0:36:49", "remaining_time": "1:14:56", "throughput": 1033.77, "total_tokens": 2284504} {"current_steps": 25365, "total_steps": 76960, "loss": 0.268, "lr": 4.2393194127249166e-05, "epoch": 6.591735966735967, "percentage": 32.96, "elapsed_time": "0:36:50", "remaining_time": "1:14:55", "throughput": 1033.77, "total_tokens": 2284952} {"current_steps": 25370, "total_steps": 76960, "loss": 0.246, "lr": 4.238912117577069e-05, "epoch": 6.593035343035343, "percentage": 32.97, "elapsed_time": "0:36:50", "remaining_time": "1:14:55", "throughput": 1033.78, "total_tokens": 2285400} {"current_steps": 25375, "total_steps": 76960, "loss": 0.2709, "lr": 4.238504732995304e-05, "epoch": 6.59433471933472, "percentage": 32.97, "elapsed_time": "0:36:51", "remaining_time": "1:14:55", "throughput": 1033.78, "total_tokens": 2285832} {"current_steps": 25380, "total_steps": 76960, "loss": 0.1732, "lr": 4.238097259000575e-05, "epoch": 6.595634095634096, "percentage": 32.98, "elapsed_time": "0:36:51", "remaining_time": "1:14:54", "throughput": 1033.78, "total_tokens": 2286264} {"current_steps": 25385, "total_steps": 76960, "loss": 0.1955, "lr": 4.237689695613839e-05, "epoch": 6.596933471933472, "percentage": 32.98, "elapsed_time": "0:36:51", "remaining_time": "1:14:54", "throughput": 1033.79, "total_tokens": 2286712} {"current_steps": 25390, "total_steps": 76960, "loss": 0.1165, "lr": 4.237282042856057e-05, "epoch": 6.598232848232849, "percentage": 32.99, "elapsed_time": "0:36:52", "remaining_time": "1:14:53", "throughput": 1033.81, "total_tokens": 2287192} {"current_steps": 25395, "total_steps": 76960, "loss": 0.28, "lr": 4.236874300748195e-05, "epoch": 6.599532224532225, "percentage": 33.0, "elapsed_time": "0:36:52", "remaining_time": "1:14:53", "throughput": 1033.82, "total_tokens": 2287640} {"current_steps": 25400, "total_steps": 76960, "loss": 0.1377, "lr": 4.2364664693112234e-05, "epoch": 6.600831600831601, "percentage": 33.0, "elapsed_time": "0:36:53", "remaining_time": "1:14:52", "throughput": 1033.82, "total_tokens": 2288072} {"current_steps": 25405, "total_steps": 76960, "loss": 0.3084, "lr": 4.2360585485661175e-05, "epoch": 6.602130977130977, "percentage": 33.01, "elapsed_time": "0:36:53", "remaining_time": "1:14:52", "throughput": 1033.82, "total_tokens": 2288504} {"current_steps": 25410, "total_steps": 76960, "loss": 0.2948, "lr": 4.2356505385338565e-05, "epoch": 6.603430353430354, "percentage": 33.02, "elapsed_time": "0:36:54", "remaining_time": "1:14:51", "throughput": 1033.83, "total_tokens": 2288968} {"current_steps": 25415, "total_steps": 76960, "loss": 0.1954, "lr": 4.2352424392354264e-05, "epoch": 6.60472972972973, "percentage": 33.02, "elapsed_time": "0:36:54", "remaining_time": "1:14:51", "throughput": 1033.83, "total_tokens": 2289400} {"current_steps": 25420, "total_steps": 76960, "loss": 0.2148, "lr": 4.234834250691814e-05, "epoch": 6.606029106029106, "percentage": 33.03, "elapsed_time": "0:36:54", "remaining_time": "1:14:50", "throughput": 1033.85, "total_tokens": 2289864} {"current_steps": 25425, "total_steps": 76960, "loss": 0.2139, "lr": 4.234425972924014e-05, "epoch": 6.607328482328482, "percentage": 33.04, "elapsed_time": "0:36:55", "remaining_time": "1:14:50", "throughput": 1033.86, "total_tokens": 2290312} {"current_steps": 25430, "total_steps": 76960, "loss": 0.3051, "lr": 4.234017605953025e-05, "epoch": 6.608627858627859, "percentage": 33.04, "elapsed_time": "0:36:55", "remaining_time": "1:14:49", "throughput": 1033.87, "total_tokens": 2290776} {"current_steps": 25435, "total_steps": 76960, "loss": 0.1891, "lr": 4.2336091497998484e-05, "epoch": 6.609927234927235, "percentage": 33.05, "elapsed_time": "0:36:56", "remaining_time": "1:14:49", "throughput": 1033.87, "total_tokens": 2291208} {"current_steps": 25440, "total_steps": 76960, "loss": 0.3616, "lr": 4.2332006044854925e-05, "epoch": 6.611226611226611, "percentage": 33.06, "elapsed_time": "0:36:56", "remaining_time": "1:14:48", "throughput": 1033.88, "total_tokens": 2291656} {"current_steps": 25445, "total_steps": 76960, "loss": 0.342, "lr": 4.232791970030968e-05, "epoch": 6.612525987525988, "percentage": 33.06, "elapsed_time": "0:36:56", "remaining_time": "1:14:48", "throughput": 1033.89, "total_tokens": 2292104} {"current_steps": 25450, "total_steps": 76960, "loss": 0.3065, "lr": 4.232383246457293e-05, "epoch": 6.613825363825364, "percentage": 33.07, "elapsed_time": "0:36:57", "remaining_time": "1:14:47", "throughput": 1033.9, "total_tokens": 2292552} {"current_steps": 25455, "total_steps": 76960, "loss": 0.2689, "lr": 4.231974433785488e-05, "epoch": 6.61512474012474, "percentage": 33.08, "elapsed_time": "0:36:57", "remaining_time": "1:14:47", "throughput": 1033.91, "total_tokens": 2293016} {"current_steps": 25460, "total_steps": 76960, "loss": 0.2734, "lr": 4.231565532036578e-05, "epoch": 6.616424116424117, "percentage": 33.08, "elapsed_time": "0:36:58", "remaining_time": "1:14:46", "throughput": 1033.92, "total_tokens": 2293464} {"current_steps": 25465, "total_steps": 76960, "loss": 0.2839, "lr": 4.2311565412315934e-05, "epoch": 6.617723492723493, "percentage": 33.09, "elapsed_time": "0:36:58", "remaining_time": "1:14:46", "throughput": 1033.94, "total_tokens": 2293928} {"current_steps": 25470, "total_steps": 76960, "loss": 0.2085, "lr": 4.2307474613915694e-05, "epoch": 6.619022869022869, "percentage": 33.1, "elapsed_time": "0:36:59", "remaining_time": "1:14:46", "throughput": 1033.94, "total_tokens": 2294360} {"current_steps": 25475, "total_steps": 76960, "loss": 0.2336, "lr": 4.230338292537545e-05, "epoch": 6.620322245322245, "percentage": 33.1, "elapsed_time": "0:36:59", "remaining_time": "1:14:45", "throughput": 1033.93, "total_tokens": 2294776} {"current_steps": 25480, "total_steps": 76960, "loss": 0.3477, "lr": 4.2299290346905646e-05, "epoch": 6.621621621621622, "percentage": 33.11, "elapsed_time": "0:36:59", "remaining_time": "1:14:45", "throughput": 1033.95, "total_tokens": 2295256} {"current_steps": 25485, "total_steps": 76960, "loss": 0.2641, "lr": 4.229519687871676e-05, "epoch": 6.622920997920998, "percentage": 33.11, "elapsed_time": "0:37:00", "remaining_time": "1:14:44", "throughput": 1033.96, "total_tokens": 2295704} {"current_steps": 25490, "total_steps": 76960, "loss": 0.1796, "lr": 4.2291102521019335e-05, "epoch": 6.624220374220374, "percentage": 33.12, "elapsed_time": "0:37:00", "remaining_time": "1:14:44", "throughput": 1033.97, "total_tokens": 2296152} {"current_steps": 25495, "total_steps": 76960, "loss": 0.2922, "lr": 4.228700727402393e-05, "epoch": 6.62551975051975, "percentage": 33.13, "elapsed_time": "0:37:01", "remaining_time": "1:14:43", "throughput": 1033.96, "total_tokens": 2296568} {"current_steps": 25500, "total_steps": 76960, "loss": 0.3249, "lr": 4.2282911137941184e-05, "epoch": 6.626819126819127, "percentage": 33.13, "elapsed_time": "0:37:01", "remaining_time": "1:14:43", "throughput": 1033.98, "total_tokens": 2297048} {"current_steps": 25505, "total_steps": 76960, "loss": 0.23, "lr": 4.227881411298175e-05, "epoch": 6.628118503118503, "percentage": 33.14, "elapsed_time": "0:37:01", "remaining_time": "1:14:42", "throughput": 1033.99, "total_tokens": 2297496} {"current_steps": 25510, "total_steps": 76960, "loss": 0.2404, "lr": 4.2274716199356354e-05, "epoch": 6.629417879417879, "percentage": 33.15, "elapsed_time": "0:37:02", "remaining_time": "1:14:42", "throughput": 1034.0, "total_tokens": 2297960} {"current_steps": 25515, "total_steps": 76960, "loss": 0.2632, "lr": 4.227061739727576e-05, "epoch": 6.630717255717256, "percentage": 33.15, "elapsed_time": "0:37:02", "remaining_time": "1:14:41", "throughput": 1034.01, "total_tokens": 2298408} {"current_steps": 25520, "total_steps": 76960, "loss": 0.2379, "lr": 4.226651770695076e-05, "epoch": 6.632016632016632, "percentage": 33.16, "elapsed_time": "0:37:03", "remaining_time": "1:14:41", "throughput": 1034.02, "total_tokens": 2298856} {"current_steps": 25525, "total_steps": 76960, "loss": 0.2146, "lr": 4.226241712859221e-05, "epoch": 6.633316008316008, "percentage": 33.17, "elapsed_time": "0:37:03", "remaining_time": "1:14:40", "throughput": 1034.03, "total_tokens": 2299304} {"current_steps": 25530, "total_steps": 76960, "loss": 0.199, "lr": 4.2258315662411e-05, "epoch": 6.634615384615385, "percentage": 33.17, "elapsed_time": "0:37:04", "remaining_time": "1:14:40", "throughput": 1034.02, "total_tokens": 2299720} {"current_steps": 25535, "total_steps": 76960, "loss": 0.2757, "lr": 4.225421330861809e-05, "epoch": 6.635914760914761, "percentage": 33.18, "elapsed_time": "0:37:04", "remaining_time": "1:14:39", "throughput": 1034.01, "total_tokens": 2300136} {"current_steps": 25540, "total_steps": 76960, "loss": 0.2928, "lr": 4.225011006742445e-05, "epoch": 6.637214137214137, "percentage": 33.19, "elapsed_time": "0:37:04", "remaining_time": "1:14:39", "throughput": 1034.01, "total_tokens": 2300568} {"current_steps": 25545, "total_steps": 76960, "loss": 0.2055, "lr": 4.224600593904113e-05, "epoch": 6.638513513513513, "percentage": 33.19, "elapsed_time": "0:37:05", "remaining_time": "1:14:38", "throughput": 1034.01, "total_tokens": 2301000} {"current_steps": 25550, "total_steps": 76960, "loss": 0.2572, "lr": 4.2241900923679196e-05, "epoch": 6.63981288981289, "percentage": 33.2, "elapsed_time": "0:37:05", "remaining_time": "1:14:38", "throughput": 1034.03, "total_tokens": 2301464} {"current_steps": 25555, "total_steps": 76960, "loss": 0.2675, "lr": 4.2237795021549776e-05, "epoch": 6.641112266112266, "percentage": 33.21, "elapsed_time": "0:37:06", "remaining_time": "1:14:37", "throughput": 1034.06, "total_tokens": 2301976} {"current_steps": 25560, "total_steps": 76960, "loss": 0.1753, "lr": 4.223368823286404e-05, "epoch": 6.642411642411642, "percentage": 33.21, "elapsed_time": "0:37:06", "remaining_time": "1:14:37", "throughput": 1034.08, "total_tokens": 2302440} {"current_steps": 25565, "total_steps": 76960, "loss": 0.1996, "lr": 4.2229580557833204e-05, "epoch": 6.643711018711018, "percentage": 33.22, "elapsed_time": "0:37:06", "remaining_time": "1:14:37", "throughput": 1034.08, "total_tokens": 2302872} {"current_steps": 25570, "total_steps": 76960, "loss": 0.2958, "lr": 4.222547199666854e-05, "epoch": 6.645010395010395, "percentage": 33.23, "elapsed_time": "0:37:07", "remaining_time": "1:14:36", "throughput": 1034.07, "total_tokens": 2303288} {"current_steps": 25575, "total_steps": 76960, "loss": 0.2593, "lr": 4.2221362549581334e-05, "epoch": 6.646309771309771, "percentage": 33.23, "elapsed_time": "0:37:07", "remaining_time": "1:14:36", "throughput": 1034.09, "total_tokens": 2303752} {"current_steps": 25580, "total_steps": 76960, "loss": 0.3048, "lr": 4.221725221678296e-05, "epoch": 6.647609147609147, "percentage": 33.24, "elapsed_time": "0:37:08", "remaining_time": "1:14:35", "throughput": 1034.1, "total_tokens": 2304216} {"current_steps": 25585, "total_steps": 76960, "loss": 0.2255, "lr": 4.221314099848481e-05, "epoch": 6.648908523908524, "percentage": 33.24, "elapsed_time": "0:37:08", "remaining_time": "1:14:35", "throughput": 1034.11, "total_tokens": 2304664} {"current_steps": 25590, "total_steps": 76960, "loss": 0.262, "lr": 4.220902889489832e-05, "epoch": 6.6502079002079, "percentage": 33.25, "elapsed_time": "0:37:09", "remaining_time": "1:14:34", "throughput": 1034.11, "total_tokens": 2305096} {"current_steps": 25595, "total_steps": 76960, "loss": 0.2685, "lr": 4.220491590623499e-05, "epoch": 6.651507276507276, "percentage": 33.26, "elapsed_time": "0:37:09", "remaining_time": "1:14:34", "throughput": 1034.12, "total_tokens": 2305544} {"current_steps": 25600, "total_steps": 76960, "loss": 0.2753, "lr": 4.220080203270634e-05, "epoch": 6.652806652806653, "percentage": 33.26, "elapsed_time": "0:37:09", "remaining_time": "1:14:33", "throughput": 1034.13, "total_tokens": 2306008} {"current_steps": 25605, "total_steps": 76960, "loss": 0.2183, "lr": 4.219668727452397e-05, "epoch": 6.654106029106029, "percentage": 33.27, "elapsed_time": "0:37:10", "remaining_time": "1:14:33", "throughput": 1034.13, "total_tokens": 2306440} {"current_steps": 25610, "total_steps": 76960, "loss": 0.193, "lr": 4.219257163189949e-05, "epoch": 6.655405405405405, "percentage": 33.28, "elapsed_time": "0:37:10", "remaining_time": "1:14:32", "throughput": 1034.14, "total_tokens": 2306888} {"current_steps": 25615, "total_steps": 76960, "loss": 0.2538, "lr": 4.218845510504458e-05, "epoch": 6.656704781704782, "percentage": 33.28, "elapsed_time": "0:37:11", "remaining_time": "1:14:32", "throughput": 1034.13, "total_tokens": 2307304} {"current_steps": 25620, "total_steps": 76960, "loss": 0.4324, "lr": 4.218433769417096e-05, "epoch": 6.658004158004158, "percentage": 33.29, "elapsed_time": "0:37:11", "remaining_time": "1:14:31", "throughput": 1034.13, "total_tokens": 2307720} {"current_steps": 25625, "total_steps": 76960, "loss": 0.2447, "lr": 4.218021939949038e-05, "epoch": 6.659303534303534, "percentage": 33.3, "elapsed_time": "0:37:11", "remaining_time": "1:14:31", "throughput": 1034.13, "total_tokens": 2308152} {"current_steps": 25630, "total_steps": 76960, "loss": 0.2359, "lr": 4.2176100221214666e-05, "epoch": 6.66060291060291, "percentage": 33.3, "elapsed_time": "0:37:12", "remaining_time": "1:14:30", "throughput": 1034.14, "total_tokens": 2308600} {"current_steps": 25635, "total_steps": 76960, "loss": 0.2607, "lr": 4.2171980159555644e-05, "epoch": 6.661902286902287, "percentage": 33.31, "elapsed_time": "0:37:12", "remaining_time": "1:14:30", "throughput": 1034.14, "total_tokens": 2309032} {"current_steps": 25640, "total_steps": 76960, "loss": 0.2393, "lr": 4.216785921472524e-05, "epoch": 6.663201663201663, "percentage": 33.32, "elapsed_time": "0:37:13", "remaining_time": "1:14:29", "throughput": 1034.14, "total_tokens": 2309480} {"current_steps": 25645, "total_steps": 76960, "loss": 0.2065, "lr": 4.216373738693539e-05, "epoch": 6.664501039501039, "percentage": 33.32, "elapsed_time": "0:37:13", "remaining_time": "1:14:29", "throughput": 1034.15, "total_tokens": 2309912} {"current_steps": 25650, "total_steps": 76960, "loss": 0.2721, "lr": 4.215961467639807e-05, "epoch": 6.665800415800415, "percentage": 33.33, "elapsed_time": "0:37:14", "remaining_time": "1:14:28", "throughput": 1034.17, "total_tokens": 2310392} {"current_steps": 25655, "total_steps": 76960, "loss": 0.223, "lr": 4.215549108332533e-05, "epoch": 6.667099792099792, "percentage": 33.34, "elapsed_time": "0:37:14", "remaining_time": "1:14:28", "throughput": 1034.17, "total_tokens": 2310824} {"current_steps": 25660, "total_steps": 76960, "loss": 0.2847, "lr": 4.2151366607929246e-05, "epoch": 6.668399168399168, "percentage": 33.34, "elapsed_time": "0:37:14", "remaining_time": "1:14:28", "throughput": 1034.19, "total_tokens": 2311304} {"current_steps": 25665, "total_steps": 76960, "loss": 0.1842, "lr": 4.2147241250421944e-05, "epoch": 6.669698544698544, "percentage": 33.35, "elapsed_time": "0:37:15", "remaining_time": "1:14:27", "throughput": 1034.19, "total_tokens": 2311736} {"current_steps": 25670, "total_steps": 76960, "loss": 0.3353, "lr": 4.2143115011015597e-05, "epoch": 6.670997920997921, "percentage": 33.35, "elapsed_time": "0:37:15", "remaining_time": "1:14:27", "throughput": 1034.2, "total_tokens": 2312184} {"current_steps": 25675, "total_steps": 76960, "loss": 0.2375, "lr": 4.213898788992242e-05, "epoch": 6.672297297297297, "percentage": 33.36, "elapsed_time": "0:37:16", "remaining_time": "1:14:26", "throughput": 1034.21, "total_tokens": 2312648} {"current_steps": 25680, "total_steps": 76960, "loss": 0.2038, "lr": 4.213485988735467e-05, "epoch": 6.673596673596673, "percentage": 33.37, "elapsed_time": "0:37:16", "remaining_time": "1:14:26", "throughput": 1034.22, "total_tokens": 2313096} {"current_steps": 25685, "total_steps": 76960, "loss": 0.2935, "lr": 4.213073100352466e-05, "epoch": 6.67489604989605, "percentage": 33.37, "elapsed_time": "0:37:16", "remaining_time": "1:14:25", "throughput": 1034.22, "total_tokens": 2313528} {"current_steps": 25690, "total_steps": 76960, "loss": 0.2553, "lr": 4.212660123864474e-05, "epoch": 6.676195426195426, "percentage": 33.38, "elapsed_time": "0:37:17", "remaining_time": "1:14:25", "throughput": 1034.22, "total_tokens": 2313960} {"current_steps": 25695, "total_steps": 76960, "loss": 0.2327, "lr": 4.212247059292731e-05, "epoch": 6.677494802494802, "percentage": 33.39, "elapsed_time": "0:37:17", "remaining_time": "1:14:24", "throughput": 1034.26, "total_tokens": 2314472} {"current_steps": 25700, "total_steps": 76960, "loss": 0.2357, "lr": 4.211833906658481e-05, "epoch": 6.6787941787941785, "percentage": 33.39, "elapsed_time": "0:37:18", "remaining_time": "1:14:24", "throughput": 1034.27, "total_tokens": 2314936} {"current_steps": 25705, "total_steps": 76960, "loss": 0.1721, "lr": 4.211420665982973e-05, "epoch": 6.680093555093555, "percentage": 33.4, "elapsed_time": "0:37:18", "remaining_time": "1:14:23", "throughput": 1034.27, "total_tokens": 2315368} {"current_steps": 25710, "total_steps": 76960, "loss": 0.2648, "lr": 4.2110073372874604e-05, "epoch": 6.6813929313929314, "percentage": 33.41, "elapsed_time": "0:37:19", "remaining_time": "1:14:23", "throughput": 1034.28, "total_tokens": 2315816} {"current_steps": 25715, "total_steps": 76960, "loss": 0.2525, "lr": 4.210593920593201e-05, "epoch": 6.6826923076923075, "percentage": 33.41, "elapsed_time": "0:37:19", "remaining_time": "1:14:22", "throughput": 1034.3, "total_tokens": 2316280} {"current_steps": 25720, "total_steps": 76960, "loss": 0.1471, "lr": 4.2101804159214576e-05, "epoch": 6.6839916839916835, "percentage": 33.42, "elapsed_time": "0:37:19", "remaining_time": "1:14:22", "throughput": 1034.31, "total_tokens": 2316744} {"current_steps": 25725, "total_steps": 76960, "loss": 0.3016, "lr": 4.209766823293496e-05, "epoch": 6.6852910602910605, "percentage": 33.43, "elapsed_time": "0:37:20", "remaining_time": "1:14:21", "throughput": 1034.32, "total_tokens": 2317192} {"current_steps": 25730, "total_steps": 76960, "loss": 0.1893, "lr": 4.2093531427305886e-05, "epoch": 6.6865904365904365, "percentage": 33.43, "elapsed_time": "0:37:20", "remaining_time": "1:14:21", "throughput": 1034.32, "total_tokens": 2317624} {"current_steps": 25735, "total_steps": 76960, "loss": 0.2009, "lr": 4.2089393742540115e-05, "epoch": 6.6878898128898125, "percentage": 33.44, "elapsed_time": "0:37:21", "remaining_time": "1:14:20", "throughput": 1034.34, "total_tokens": 2318104} {"current_steps": 25740, "total_steps": 76960, "loss": 0.2749, "lr": 4.2085255178850457e-05, "epoch": 6.6891891891891895, "percentage": 33.45, "elapsed_time": "0:37:21", "remaining_time": "1:14:20", "throughput": 1034.34, "total_tokens": 2318536} {"current_steps": 25745, "total_steps": 76960, "loss": 0.111, "lr": 4.208111573644975e-05, "epoch": 6.6904885654885655, "percentage": 33.45, "elapsed_time": "0:37:21", "remaining_time": "1:14:19", "throughput": 1034.35, "total_tokens": 2318984} {"current_steps": 25750, "total_steps": 76960, "loss": 0.172, "lr": 4.207697541555089e-05, "epoch": 6.691787941787942, "percentage": 33.46, "elapsed_time": "0:37:22", "remaining_time": "1:14:19", "throughput": 1034.37, "total_tokens": 2319448} {"current_steps": 25755, "total_steps": 76960, "loss": 0.3268, "lr": 4.207283421636682e-05, "epoch": 6.6930873180873185, "percentage": 33.47, "elapsed_time": "0:37:22", "remaining_time": "1:14:19", "throughput": 1034.42, "total_tokens": 2319992} {"current_steps": 25760, "total_steps": 76960, "loss": 0.3229, "lr": 4.2068692139110536e-05, "epoch": 6.6943866943866945, "percentage": 33.47, "elapsed_time": "0:37:23", "remaining_time": "1:14:18", "throughput": 1034.41, "total_tokens": 2320408} {"current_steps": 25765, "total_steps": 76960, "loss": 0.3063, "lr": 4.2064549183995056e-05, "epoch": 6.695686070686071, "percentage": 33.48, "elapsed_time": "0:37:23", "remaining_time": "1:14:18", "throughput": 1034.43, "total_tokens": 2320888} {"current_steps": 25770, "total_steps": 76960, "loss": 0.2898, "lr": 4.206040535123346e-05, "epoch": 6.696985446985447, "percentage": 33.48, "elapsed_time": "0:37:24", "remaining_time": "1:14:17", "throughput": 1034.44, "total_tokens": 2321336} {"current_steps": 25775, "total_steps": 76960, "loss": 0.2281, "lr": 4.2056260641038874e-05, "epoch": 6.6982848232848236, "percentage": 33.49, "elapsed_time": "0:37:24", "remaining_time": "1:14:17", "throughput": 1034.46, "total_tokens": 2321800} {"current_steps": 25780, "total_steps": 76960, "loss": 0.2399, "lr": 4.205211505362446e-05, "epoch": 6.6995841995842, "percentage": 33.5, "elapsed_time": "0:37:24", "remaining_time": "1:14:16", "throughput": 1034.46, "total_tokens": 2322248} {"current_steps": 25785, "total_steps": 76960, "loss": 0.3105, "lr": 4.204796858920343e-05, "epoch": 6.700883575883576, "percentage": 33.5, "elapsed_time": "0:37:25", "remaining_time": "1:14:16", "throughput": 1034.49, "total_tokens": 2322744} {"current_steps": 25790, "total_steps": 76960, "loss": 0.29, "lr": 4.204382124798904e-05, "epoch": 6.702182952182953, "percentage": 33.51, "elapsed_time": "0:37:25", "remaining_time": "1:14:15", "throughput": 1034.5, "total_tokens": 2323192} {"current_steps": 25795, "total_steps": 76960, "loss": 0.2673, "lr": 4.203967303019459e-05, "epoch": 6.703482328482329, "percentage": 33.52, "elapsed_time": "0:37:26", "remaining_time": "1:14:15", "throughput": 1034.51, "total_tokens": 2323640} {"current_steps": 25800, "total_steps": 76960, "loss": 0.2589, "lr": 4.203552393603343e-05, "epoch": 6.704781704781705, "percentage": 33.52, "elapsed_time": "0:37:26", "remaining_time": "1:14:14", "throughput": 1034.51, "total_tokens": 2324072} {"current_steps": 25805, "total_steps": 76960, "loss": 0.2785, "lr": 4.203137396571896e-05, "epoch": 6.706081081081081, "percentage": 33.53, "elapsed_time": "0:37:26", "remaining_time": "1:14:14", "throughput": 1034.51, "total_tokens": 2324504} {"current_steps": 25810, "total_steps": 76960, "loss": 0.2863, "lr": 4.20272231194646e-05, "epoch": 6.707380457380458, "percentage": 33.54, "elapsed_time": "0:37:27", "remaining_time": "1:14:13", "throughput": 1034.55, "total_tokens": 2325032} {"current_steps": 25815, "total_steps": 76960, "loss": 0.2451, "lr": 4.202307139748384e-05, "epoch": 6.708679833679834, "percentage": 33.54, "elapsed_time": "0:37:27", "remaining_time": "1:14:13", "throughput": 1034.55, "total_tokens": 2325464} {"current_steps": 25820, "total_steps": 76960, "loss": 0.2322, "lr": 4.2018918799990216e-05, "epoch": 6.70997920997921, "percentage": 33.55, "elapsed_time": "0:37:28", "remaining_time": "1:14:12", "throughput": 1034.55, "total_tokens": 2325896} {"current_steps": 25825, "total_steps": 76960, "loss": 0.2583, "lr": 4.201476532719728e-05, "epoch": 6.711278586278587, "percentage": 33.56, "elapsed_time": "0:37:28", "remaining_time": "1:14:12", "throughput": 1034.56, "total_tokens": 2326328} {"current_steps": 25830, "total_steps": 76960, "loss": 0.1143, "lr": 4.2010610979318665e-05, "epoch": 6.712577962577963, "percentage": 33.56, "elapsed_time": "0:37:29", "remaining_time": "1:14:11", "throughput": 1034.57, "total_tokens": 2326792} {"current_steps": 25835, "total_steps": 76960, "loss": 0.3442, "lr": 4.200645575656803e-05, "epoch": 6.713877338877339, "percentage": 33.57, "elapsed_time": "0:37:29", "remaining_time": "1:14:11", "throughput": 1034.58, "total_tokens": 2327240} {"current_steps": 25840, "total_steps": 76960, "loss": 0.2155, "lr": 4.2002299659159074e-05, "epoch": 6.715176715176716, "percentage": 33.58, "elapsed_time": "0:37:29", "remaining_time": "1:14:10", "throughput": 1034.58, "total_tokens": 2327672} {"current_steps": 25845, "total_steps": 76960, "loss": 0.2665, "lr": 4.199814268730556e-05, "epoch": 6.716476091476092, "percentage": 33.58, "elapsed_time": "0:37:30", "remaining_time": "1:14:10", "throughput": 1034.58, "total_tokens": 2328104} {"current_steps": 25850, "total_steps": 76960, "loss": 0.1662, "lr": 4.1993984841221286e-05, "epoch": 6.717775467775468, "percentage": 33.59, "elapsed_time": "0:37:30", "remaining_time": "1:14:10", "throughput": 1034.58, "total_tokens": 2328536} {"current_steps": 25855, "total_steps": 76960, "loss": 0.3045, "lr": 4.198982612112008e-05, "epoch": 6.719074844074844, "percentage": 33.6, "elapsed_time": "0:37:31", "remaining_time": "1:14:09", "throughput": 1034.59, "total_tokens": 2328984} {"current_steps": 25860, "total_steps": 76960, "loss": 0.1973, "lr": 4.1985666527215845e-05, "epoch": 6.720374220374221, "percentage": 33.6, "elapsed_time": "0:37:31", "remaining_time": "1:14:09", "throughput": 1034.59, "total_tokens": 2329416} {"current_steps": 25865, "total_steps": 76960, "loss": 0.3103, "lr": 4.1981506059722505e-05, "epoch": 6.721673596673597, "percentage": 33.61, "elapsed_time": "0:37:31", "remaining_time": "1:14:08", "throughput": 1034.59, "total_tokens": 2329848} {"current_steps": 25870, "total_steps": 76960, "loss": 0.3101, "lr": 4.197734471885404e-05, "epoch": 6.722972972972973, "percentage": 33.61, "elapsed_time": "0:37:32", "remaining_time": "1:14:08", "throughput": 1034.6, "total_tokens": 2330312} {"current_steps": 25875, "total_steps": 76960, "loss": 0.2269, "lr": 4.197318250482446e-05, "epoch": 6.724272349272349, "percentage": 33.62, "elapsed_time": "0:37:32", "remaining_time": "1:14:07", "throughput": 1034.62, "total_tokens": 2330776} {"current_steps": 25880, "total_steps": 76960, "loss": 0.2874, "lr": 4.196901941784784e-05, "epoch": 6.725571725571726, "percentage": 33.63, "elapsed_time": "0:37:33", "remaining_time": "1:14:07", "throughput": 1034.62, "total_tokens": 2331224} {"current_steps": 25885, "total_steps": 76960, "loss": 0.2806, "lr": 4.19648554581383e-05, "epoch": 6.726871101871102, "percentage": 33.63, "elapsed_time": "0:37:33", "remaining_time": "1:14:06", "throughput": 1034.65, "total_tokens": 2331720} {"current_steps": 25890, "total_steps": 76960, "loss": 0.2566, "lr": 4.1960690625909994e-05, "epoch": 6.728170478170478, "percentage": 33.64, "elapsed_time": "0:37:34", "remaining_time": "1:14:06", "throughput": 1034.65, "total_tokens": 2332152} {"current_steps": 25895, "total_steps": 76960, "loss": 0.2258, "lr": 4.1956524921377106e-05, "epoch": 6.729469854469855, "percentage": 33.65, "elapsed_time": "0:37:34", "remaining_time": "1:14:05", "throughput": 1034.65, "total_tokens": 2332584} {"current_steps": 25900, "total_steps": 76960, "loss": 0.2804, "lr": 4.1952358344753895e-05, "epoch": 6.730769230769231, "percentage": 33.65, "elapsed_time": "0:37:34", "remaining_time": "1:14:05", "throughput": 1034.66, "total_tokens": 2333032} {"current_steps": 25905, "total_steps": 76960, "loss": 0.2637, "lr": 4.194819089625466e-05, "epoch": 6.732068607068607, "percentage": 33.66, "elapsed_time": "0:37:35", "remaining_time": "1:14:04", "throughput": 1034.7, "total_tokens": 2333544} {"current_steps": 25910, "total_steps": 76960, "loss": 0.2312, "lr": 4.194402257609372e-05, "epoch": 6.733367983367984, "percentage": 33.67, "elapsed_time": "0:37:35", "remaining_time": "1:14:04", "throughput": 1034.73, "total_tokens": 2334040} {"current_steps": 25915, "total_steps": 76960, "loss": 0.3499, "lr": 4.193985338448547e-05, "epoch": 6.73466735966736, "percentage": 33.67, "elapsed_time": "0:37:36", "remaining_time": "1:14:03", "throughput": 1034.73, "total_tokens": 2334472} {"current_steps": 25920, "total_steps": 76960, "loss": 0.2148, "lr": 4.193568332164433e-05, "epoch": 6.735966735966736, "percentage": 33.68, "elapsed_time": "0:37:36", "remaining_time": "1:14:03", "throughput": 1034.73, "total_tokens": 2334920} {"current_steps": 25925, "total_steps": 76960, "loss": 0.2226, "lr": 4.1931512387784764e-05, "epoch": 6.737266112266112, "percentage": 33.69, "elapsed_time": "0:37:36", "remaining_time": "1:14:02", "throughput": 1034.75, "total_tokens": 2335384} {"current_steps": 25930, "total_steps": 76960, "loss": 0.2555, "lr": 4.1927340583121296e-05, "epoch": 6.738565488565489, "percentage": 33.69, "elapsed_time": "0:37:37", "remaining_time": "1:14:02", "throughput": 1034.74, "total_tokens": 2335800} {"current_steps": 25935, "total_steps": 76960, "loss": 0.2243, "lr": 4.1923167907868475e-05, "epoch": 6.739864864864865, "percentage": 33.7, "elapsed_time": "0:37:37", "remaining_time": "1:14:02", "throughput": 1034.78, "total_tokens": 2336312} {"current_steps": 25940, "total_steps": 76960, "loss": 0.2855, "lr": 4.1918994362240924e-05, "epoch": 6.741164241164241, "percentage": 33.71, "elapsed_time": "0:37:38", "remaining_time": "1:14:01", "throughput": 1034.79, "total_tokens": 2336776} {"current_steps": 25945, "total_steps": 76960, "loss": 0.2423, "lr": 4.191481994645329e-05, "epoch": 6.742463617463617, "percentage": 33.71, "elapsed_time": "0:37:38", "remaining_time": "1:14:01", "throughput": 1034.81, "total_tokens": 2337240} {"current_steps": 25950, "total_steps": 76960, "loss": 0.2616, "lr": 4.191064466072024e-05, "epoch": 6.743762993762994, "percentage": 33.72, "elapsed_time": "0:37:39", "remaining_time": "1:14:00", "throughput": 1034.81, "total_tokens": 2337688} {"current_steps": 25955, "total_steps": 76960, "loss": 0.244, "lr": 4.1906468505256544e-05, "epoch": 6.74506237006237, "percentage": 33.73, "elapsed_time": "0:37:39", "remaining_time": "1:14:00", "throughput": 1034.81, "total_tokens": 2338120} {"current_steps": 25960, "total_steps": 76960, "loss": 0.354, "lr": 4.190229148027697e-05, "epoch": 6.746361746361746, "percentage": 33.73, "elapsed_time": "0:37:39", "remaining_time": "1:13:59", "throughput": 1034.82, "total_tokens": 2338568} {"current_steps": 25965, "total_steps": 76960, "loss": 0.2456, "lr": 4.1898113585996346e-05, "epoch": 6.747661122661123, "percentage": 33.74, "elapsed_time": "0:37:40", "remaining_time": "1:13:59", "throughput": 1034.83, "total_tokens": 2339016} {"current_steps": 25970, "total_steps": 76960, "loss": 0.2877, "lr": 4.189393482262956e-05, "epoch": 6.748960498960499, "percentage": 33.74, "elapsed_time": "0:37:40", "remaining_time": "1:13:58", "throughput": 1034.85, "total_tokens": 2339480} {"current_steps": 25975, "total_steps": 76960, "loss": 0.1826, "lr": 4.188975519039151e-05, "epoch": 6.750259875259875, "percentage": 33.75, "elapsed_time": "0:37:41", "remaining_time": "1:13:58", "throughput": 1034.85, "total_tokens": 2339912} {"current_steps": 25980, "total_steps": 76960, "loss": 0.2191, "lr": 4.1885574689497165e-05, "epoch": 6.751559251559252, "percentage": 33.76, "elapsed_time": "0:37:41", "remaining_time": "1:13:57", "throughput": 1034.85, "total_tokens": 2340344} {"current_steps": 25985, "total_steps": 76960, "loss": 0.2142, "lr": 4.188139332016154e-05, "epoch": 6.752858627858628, "percentage": 33.76, "elapsed_time": "0:37:41", "remaining_time": "1:13:57", "throughput": 1034.85, "total_tokens": 2340776} {"current_steps": 25990, "total_steps": 76960, "loss": 0.3339, "lr": 4.187721108259969e-05, "epoch": 6.754158004158004, "percentage": 33.77, "elapsed_time": "0:37:42", "remaining_time": "1:13:56", "throughput": 1034.86, "total_tokens": 2341224} {"current_steps": 25995, "total_steps": 76960, "loss": 0.3366, "lr": 4.187302797702669e-05, "epoch": 6.75545738045738, "percentage": 33.78, "elapsed_time": "0:37:42", "remaining_time": "1:13:56", "throughput": 1034.85, "total_tokens": 2341640} {"current_steps": 26000, "total_steps": 76960, "loss": 0.2896, "lr": 4.18688440036577e-05, "epoch": 6.756756756756757, "percentage": 33.78, "elapsed_time": "0:37:43", "remaining_time": "1:13:55", "throughput": 1034.86, "total_tokens": 2342088} {"current_steps": 26005, "total_steps": 76960, "loss": 0.284, "lr": 4.18646591627079e-05, "epoch": 6.758056133056133, "percentage": 33.79, "elapsed_time": "0:37:43", "remaining_time": "1:13:55", "throughput": 1034.86, "total_tokens": 2342520} {"current_steps": 26010, "total_steps": 76960, "loss": 0.2627, "lr": 4.1860473454392515e-05, "epoch": 6.759355509355509, "percentage": 33.8, "elapsed_time": "0:37:44", "remaining_time": "1:13:54", "throughput": 1034.86, "total_tokens": 2342952} {"current_steps": 26015, "total_steps": 76960, "loss": 0.2996, "lr": 4.185628687892683e-05, "epoch": 6.760654885654886, "percentage": 33.8, "elapsed_time": "0:37:44", "remaining_time": "1:13:54", "throughput": 1034.85, "total_tokens": 2343368} {"current_steps": 26020, "total_steps": 76960, "loss": 0.2892, "lr": 4.185209943652616e-05, "epoch": 6.761954261954262, "percentage": 33.81, "elapsed_time": "0:37:44", "remaining_time": "1:13:53", "throughput": 1034.85, "total_tokens": 2343800} {"current_steps": 26025, "total_steps": 76960, "loss": 0.2425, "lr": 4.184791112740587e-05, "epoch": 6.763253638253638, "percentage": 33.82, "elapsed_time": "0:37:45", "remaining_time": "1:13:53", "throughput": 1034.85, "total_tokens": 2344232} {"current_steps": 26030, "total_steps": 76960, "loss": 0.2057, "lr": 4.184372195178137e-05, "epoch": 6.764553014553014, "percentage": 33.82, "elapsed_time": "0:37:45", "remaining_time": "1:13:53", "throughput": 1034.84, "total_tokens": 2344632} {"current_steps": 26035, "total_steps": 76960, "loss": 0.195, "lr": 4.1839531909868104e-05, "epoch": 6.765852390852391, "percentage": 33.83, "elapsed_time": "0:37:46", "remaining_time": "1:13:52", "throughput": 1034.83, "total_tokens": 2345048} {"current_steps": 26040, "total_steps": 76960, "loss": 0.1085, "lr": 4.183534100188158e-05, "epoch": 6.767151767151767, "percentage": 33.84, "elapsed_time": "0:37:46", "remaining_time": "1:13:52", "throughput": 1034.83, "total_tokens": 2345480} {"current_steps": 26045, "total_steps": 76960, "loss": 0.2715, "lr": 4.183114922803734e-05, "epoch": 6.768451143451143, "percentage": 33.84, "elapsed_time": "0:37:46", "remaining_time": "1:13:51", "throughput": 1034.86, "total_tokens": 2345976} {"current_steps": 26050, "total_steps": 76960, "loss": 0.1407, "lr": 4.182695658855096e-05, "epoch": 6.76975051975052, "percentage": 33.85, "elapsed_time": "0:37:47", "remaining_time": "1:13:51", "throughput": 1034.86, "total_tokens": 2346408} {"current_steps": 26055, "total_steps": 76960, "loss": 0.2986, "lr": 4.182276308363809e-05, "epoch": 6.771049896049896, "percentage": 33.86, "elapsed_time": "0:37:47", "remaining_time": "1:13:50", "throughput": 1034.86, "total_tokens": 2346840} {"current_steps": 26060, "total_steps": 76960, "loss": 0.0678, "lr": 4.181856871351439e-05, "epoch": 6.772349272349272, "percentage": 33.86, "elapsed_time": "0:37:48", "remaining_time": "1:13:50", "throughput": 1034.87, "total_tokens": 2347304} {"current_steps": 26065, "total_steps": 76960, "loss": 0.2795, "lr": 4.1814373478395586e-05, "epoch": 6.773648648648649, "percentage": 33.87, "elapsed_time": "0:37:48", "remaining_time": "1:13:49", "throughput": 1034.87, "total_tokens": 2347720} {"current_steps": 26070, "total_steps": 76960, "loss": 0.3376, "lr": 4.181017737849745e-05, "epoch": 6.774948024948025, "percentage": 33.87, "elapsed_time": "0:37:49", "remaining_time": "1:13:49", "throughput": 1034.86, "total_tokens": 2348136} {"current_steps": 26075, "total_steps": 76960, "loss": 0.2134, "lr": 4.180598041403578e-05, "epoch": 6.776247401247401, "percentage": 33.88, "elapsed_time": "0:37:49", "remaining_time": "1:13:48", "throughput": 1034.88, "total_tokens": 2348616} {"current_steps": 26080, "total_steps": 76960, "loss": 0.105, "lr": 4.1801782585226435e-05, "epoch": 6.777546777546777, "percentage": 33.89, "elapsed_time": "0:37:49", "remaining_time": "1:13:48", "throughput": 1034.89, "total_tokens": 2349064} {"current_steps": 26085, "total_steps": 76960, "loss": 0.2024, "lr": 4.179758389228531e-05, "epoch": 6.778846153846154, "percentage": 33.89, "elapsed_time": "0:37:50", "remaining_time": "1:13:47", "throughput": 1034.89, "total_tokens": 2349496} {"current_steps": 26090, "total_steps": 76960, "loss": 0.2546, "lr": 4.1793384335428356e-05, "epoch": 6.78014553014553, "percentage": 33.9, "elapsed_time": "0:37:50", "remaining_time": "1:13:47", "throughput": 1034.91, "total_tokens": 2349976} {"current_steps": 26095, "total_steps": 76960, "loss": 0.2346, "lr": 4.178918391487155e-05, "epoch": 6.781444906444906, "percentage": 33.91, "elapsed_time": "0:37:51", "remaining_time": "1:13:46", "throughput": 1034.92, "total_tokens": 2350424} {"current_steps": 26100, "total_steps": 76960, "loss": 0.2183, "lr": 4.178498263083093e-05, "epoch": 6.782744282744282, "percentage": 33.91, "elapsed_time": "0:37:51", "remaining_time": "1:13:46", "throughput": 1034.93, "total_tokens": 2350872} {"current_steps": 26105, "total_steps": 76960, "loss": 0.2525, "lr": 4.1780780483522575e-05, "epoch": 6.784043659043659, "percentage": 33.92, "elapsed_time": "0:37:51", "remaining_time": "1:13:45", "throughput": 1034.93, "total_tokens": 2351304} {"current_steps": 26110, "total_steps": 76960, "loss": 0.1634, "lr": 4.177657747316259e-05, "epoch": 6.785343035343035, "percentage": 33.93, "elapsed_time": "0:37:52", "remaining_time": "1:13:45", "throughput": 1034.92, "total_tokens": 2351704} {"current_steps": 26115, "total_steps": 76960, "loss": 0.0862, "lr": 4.1772373599967165e-05, "epoch": 6.786642411642411, "percentage": 33.93, "elapsed_time": "0:37:52", "remaining_time": "1:13:45", "throughput": 1034.94, "total_tokens": 2352184} {"current_steps": 26120, "total_steps": 76960, "loss": 0.278, "lr": 4.176816886415248e-05, "epoch": 6.787941787941788, "percentage": 33.94, "elapsed_time": "0:37:53", "remaining_time": "1:13:44", "throughput": 1034.94, "total_tokens": 2352616} {"current_steps": 26125, "total_steps": 76960, "loss": 0.381, "lr": 4.176396326593482e-05, "epoch": 6.789241164241164, "percentage": 33.95, "elapsed_time": "0:37:53", "remaining_time": "1:13:44", "throughput": 1034.95, "total_tokens": 2353064} {"current_steps": 26130, "total_steps": 76960, "loss": 0.2514, "lr": 4.175975680553046e-05, "epoch": 6.79054054054054, "percentage": 33.95, "elapsed_time": "0:37:54", "remaining_time": "1:13:43", "throughput": 1034.95, "total_tokens": 2353512} {"current_steps": 26135, "total_steps": 76960, "loss": 0.338, "lr": 4.175554948315575e-05, "epoch": 6.791839916839917, "percentage": 33.96, "elapsed_time": "0:37:54", "remaining_time": "1:13:43", "throughput": 1034.97, "total_tokens": 2353976} {"current_steps": 26140, "total_steps": 76960, "loss": 0.2363, "lr": 4.175134129902707e-05, "epoch": 6.793139293139293, "percentage": 33.97, "elapsed_time": "0:37:54", "remaining_time": "1:13:42", "throughput": 1034.97, "total_tokens": 2354408} {"current_steps": 26145, "total_steps": 76960, "loss": 0.2066, "lr": 4.174713225336086e-05, "epoch": 6.794438669438669, "percentage": 33.97, "elapsed_time": "0:37:55", "remaining_time": "1:13:42", "throughput": 1034.98, "total_tokens": 2354872} {"current_steps": 26150, "total_steps": 76960, "loss": 0.2632, "lr": 4.1742922346373595e-05, "epoch": 6.795738045738045, "percentage": 33.98, "elapsed_time": "0:37:55", "remaining_time": "1:13:41", "throughput": 1034.99, "total_tokens": 2355320} {"current_steps": 26155, "total_steps": 76960, "loss": 0.3236, "lr": 4.173871157828179e-05, "epoch": 6.797037422037422, "percentage": 33.99, "elapsed_time": "0:37:56", "remaining_time": "1:13:41", "throughput": 1035.01, "total_tokens": 2355784} {"current_steps": 26160, "total_steps": 76960, "loss": 0.2524, "lr": 4.173449994930201e-05, "epoch": 6.798336798336798, "percentage": 33.99, "elapsed_time": "0:37:56", "remaining_time": "1:13:40", "throughput": 1034.99, "total_tokens": 2356184} {"current_steps": 26165, "total_steps": 76960, "loss": 0.2832, "lr": 4.1730287459650866e-05, "epoch": 6.799636174636174, "percentage": 34.0, "elapsed_time": "0:37:56", "remaining_time": "1:13:40", "throughput": 1034.99, "total_tokens": 2356616} {"current_steps": 26170, "total_steps": 76960, "loss": 0.2727, "lr": 4.1726074109545e-05, "epoch": 6.8009355509355505, "percentage": 34.0, "elapsed_time": "0:37:57", "remaining_time": "1:13:39", "throughput": 1035.01, "total_tokens": 2357080} {"current_steps": 26175, "total_steps": 76960, "loss": 0.2724, "lr": 4.172185989920112e-05, "epoch": 6.802234927234927, "percentage": 34.01, "elapsed_time": "0:37:57", "remaining_time": "1:13:39", "throughput": 1035.01, "total_tokens": 2357512} {"current_steps": 26180, "total_steps": 76960, "loss": 0.2586, "lr": 4.1717644828835965e-05, "epoch": 6.803534303534303, "percentage": 34.02, "elapsed_time": "0:37:58", "remaining_time": "1:13:38", "throughput": 1035.0, "total_tokens": 2357928} {"current_steps": 26185, "total_steps": 76960, "loss": 0.3165, "lr": 4.171342889866632e-05, "epoch": 6.8048336798336795, "percentage": 34.02, "elapsed_time": "0:37:58", "remaining_time": "1:13:38", "throughput": 1035.01, "total_tokens": 2358376} {"current_steps": 26190, "total_steps": 76960, "loss": 0.2542, "lr": 4.170921210890901e-05, "epoch": 6.806133056133056, "percentage": 34.03, "elapsed_time": "0:37:59", "remaining_time": "1:13:37", "throughput": 1035.02, "total_tokens": 2358824} {"current_steps": 26195, "total_steps": 76960, "loss": 0.2796, "lr": 4.1704994459780914e-05, "epoch": 6.8074324324324325, "percentage": 34.04, "elapsed_time": "0:37:59", "remaining_time": "1:13:37", "throughput": 1035.02, "total_tokens": 2359256} {"current_steps": 26200, "total_steps": 76960, "loss": 0.253, "lr": 4.170077595149894e-05, "epoch": 6.8087318087318085, "percentage": 34.04, "elapsed_time": "0:37:59", "remaining_time": "1:13:37", "throughput": 1035.04, "total_tokens": 2359752} {"current_steps": 26205, "total_steps": 76960, "loss": 0.2325, "lr": 4.1696556584280064e-05, "epoch": 6.810031185031185, "percentage": 34.05, "elapsed_time": "0:38:00", "remaining_time": "1:13:36", "throughput": 1035.05, "total_tokens": 2360200} {"current_steps": 26210, "total_steps": 76960, "loss": 0.2693, "lr": 4.1692336358341285e-05, "epoch": 6.8113305613305615, "percentage": 34.06, "elapsed_time": "0:38:00", "remaining_time": "1:13:36", "throughput": 1035.05, "total_tokens": 2360632} {"current_steps": 26215, "total_steps": 76960, "loss": 0.1758, "lr": 4.168811527389965e-05, "epoch": 6.8126299376299375, "percentage": 34.06, "elapsed_time": "0:38:01", "remaining_time": "1:13:35", "throughput": 1035.05, "total_tokens": 2361064} {"current_steps": 26220, "total_steps": 76960, "loss": 0.3454, "lr": 4.168389333117226e-05, "epoch": 6.813929313929314, "percentage": 34.07, "elapsed_time": "0:38:01", "remaining_time": "1:13:35", "throughput": 1035.07, "total_tokens": 2361528} {"current_steps": 26225, "total_steps": 76960, "loss": 0.2371, "lr": 4.1679670530376244e-05, "epoch": 6.8152286902286905, "percentage": 34.08, "elapsed_time": "0:38:01", "remaining_time": "1:13:34", "throughput": 1035.07, "total_tokens": 2361976} {"current_steps": 26230, "total_steps": 76960, "loss": 0.2112, "lr": 4.16754468717288e-05, "epoch": 6.8165280665280665, "percentage": 34.08, "elapsed_time": "0:38:02", "remaining_time": "1:13:34", "throughput": 1035.09, "total_tokens": 2362440} {"current_steps": 26235, "total_steps": 76960, "loss": 0.2599, "lr": 4.167122235544714e-05, "epoch": 6.817827442827443, "percentage": 34.09, "elapsed_time": "0:38:02", "remaining_time": "1:13:33", "throughput": 1035.1, "total_tokens": 2362888} {"current_steps": 26240, "total_steps": 76960, "loss": 0.2817, "lr": 4.166699698174854e-05, "epoch": 6.8191268191268195, "percentage": 34.1, "elapsed_time": "0:38:03", "remaining_time": "1:13:33", "throughput": 1035.12, "total_tokens": 2363368} {"current_steps": 26245, "total_steps": 76960, "loss": 0.2737, "lr": 4.166277075085031e-05, "epoch": 6.8204261954261955, "percentage": 34.1, "elapsed_time": "0:38:03", "remaining_time": "1:13:32", "throughput": 1035.13, "total_tokens": 2363816} {"current_steps": 26250, "total_steps": 76960, "loss": 0.1842, "lr": 4.165854366296983e-05, "epoch": 6.821725571725572, "percentage": 34.11, "elapsed_time": "0:38:04", "remaining_time": "1:13:32", "throughput": 1035.14, "total_tokens": 2364280} {"current_steps": 26255, "total_steps": 76960, "loss": 0.121, "lr": 4.1654315718324475e-05, "epoch": 6.823024948024948, "percentage": 34.12, "elapsed_time": "0:38:04", "remaining_time": "1:13:31", "throughput": 1035.16, "total_tokens": 2364744} {"current_steps": 26260, "total_steps": 76960, "loss": 0.223, "lr": 4.165008691713171e-05, "epoch": 6.824324324324325, "percentage": 34.12, "elapsed_time": "0:38:04", "remaining_time": "1:13:31", "throughput": 1035.17, "total_tokens": 2365208} {"current_steps": 26265, "total_steps": 76960, "loss": 0.3451, "lr": 4.164585725960902e-05, "epoch": 6.825623700623701, "percentage": 34.13, "elapsed_time": "0:38:05", "remaining_time": "1:13:30", "throughput": 1035.19, "total_tokens": 2365672} {"current_steps": 26270, "total_steps": 76960, "loss": 0.2811, "lr": 4.164162674597395e-05, "epoch": 6.826923076923077, "percentage": 34.13, "elapsed_time": "0:38:05", "remaining_time": "1:13:30", "throughput": 1035.19, "total_tokens": 2366120} {"current_steps": 26275, "total_steps": 76960, "loss": 0.1861, "lr": 4.163739537644406e-05, "epoch": 6.828222453222454, "percentage": 34.14, "elapsed_time": "0:38:06", "remaining_time": "1:13:29", "throughput": 1035.2, "total_tokens": 2366568} {"current_steps": 26280, "total_steps": 76960, "loss": 0.3035, "lr": 4.1633163151236986e-05, "epoch": 6.82952182952183, "percentage": 34.15, "elapsed_time": "0:38:06", "remaining_time": "1:13:29", "throughput": 1035.22, "total_tokens": 2367032} {"current_steps": 26285, "total_steps": 76960, "loss": 0.3085, "lr": 4.162893007057041e-05, "epoch": 6.830821205821206, "percentage": 34.15, "elapsed_time": "0:38:06", "remaining_time": "1:13:28", "throughput": 1035.22, "total_tokens": 2367464} {"current_steps": 26290, "total_steps": 76960, "loss": 0.2565, "lr": 4.1624696134662e-05, "epoch": 6.832120582120583, "percentage": 34.16, "elapsed_time": "0:38:07", "remaining_time": "1:13:28", "throughput": 1035.22, "total_tokens": 2367912} {"current_steps": 26295, "total_steps": 76960, "loss": 0.2026, "lr": 4.1620461343729554e-05, "epoch": 6.833419958419959, "percentage": 34.17, "elapsed_time": "0:38:07", "remaining_time": "1:13:28", "throughput": 1035.24, "total_tokens": 2368376} {"current_steps": 26300, "total_steps": 76960, "loss": 0.2767, "lr": 4.161622569799086e-05, "epoch": 6.834719334719335, "percentage": 34.17, "elapsed_time": "0:38:08", "remaining_time": "1:13:27", "throughput": 1035.25, "total_tokens": 2368840} {"current_steps": 26305, "total_steps": 76960, "loss": 0.252, "lr": 4.161198919766375e-05, "epoch": 6.836018711018711, "percentage": 34.18, "elapsed_time": "0:38:08", "remaining_time": "1:13:27", "throughput": 1035.26, "total_tokens": 2369288} {"current_steps": 26310, "total_steps": 76960, "loss": 0.2552, "lr": 4.160775184296612e-05, "epoch": 6.837318087318088, "percentage": 34.19, "elapsed_time": "0:38:09", "remaining_time": "1:13:26", "throughput": 1035.26, "total_tokens": 2369720} {"current_steps": 26315, "total_steps": 76960, "loss": 0.3173, "lr": 4.16035136341159e-05, "epoch": 6.838617463617464, "percentage": 34.19, "elapsed_time": "0:38:09", "remaining_time": "1:13:26", "throughput": 1035.27, "total_tokens": 2370184} {"current_steps": 26320, "total_steps": 76960, "loss": 0.3065, "lr": 4.159927457133107e-05, "epoch": 6.83991683991684, "percentage": 34.2, "elapsed_time": "0:38:09", "remaining_time": "1:13:25", "throughput": 1035.27, "total_tokens": 2370616} {"current_steps": 26325, "total_steps": 76960, "loss": 0.2012, "lr": 4.159503465482964e-05, "epoch": 6.841216216216216, "percentage": 34.21, "elapsed_time": "0:38:10", "remaining_time": "1:13:25", "throughput": 1035.27, "total_tokens": 2371048} {"current_steps": 26330, "total_steps": 76960, "loss": 0.2671, "lr": 4.159079388482968e-05, "epoch": 6.842515592515593, "percentage": 34.21, "elapsed_time": "0:38:10", "remaining_time": "1:13:24", "throughput": 1035.3, "total_tokens": 2371528} {"current_steps": 26335, "total_steps": 76960, "loss": 0.1379, "lr": 4.1586552261549295e-05, "epoch": 6.843814968814969, "percentage": 34.22, "elapsed_time": "0:38:11", "remaining_time": "1:13:24", "throughput": 1035.3, "total_tokens": 2371976} {"current_steps": 26340, "total_steps": 76960, "loss": 0.1984, "lr": 4.158230978520663e-05, "epoch": 6.845114345114345, "percentage": 34.23, "elapsed_time": "0:38:11", "remaining_time": "1:13:23", "throughput": 1035.32, "total_tokens": 2372440} {"current_steps": 26345, "total_steps": 76960, "loss": 0.1467, "lr": 4.157806645601988e-05, "epoch": 6.846413721413722, "percentage": 34.23, "elapsed_time": "0:38:11", "remaining_time": "1:13:23", "throughput": 1035.35, "total_tokens": 2372936} {"current_steps": 26350, "total_steps": 76960, "loss": 0.3833, "lr": 4.15738222742073e-05, "epoch": 6.847713097713098, "percentage": 34.24, "elapsed_time": "0:38:12", "remaining_time": "1:13:22", "throughput": 1035.37, "total_tokens": 2373432} {"current_steps": 26355, "total_steps": 76960, "loss": 0.1467, "lr": 4.156957723998715e-05, "epoch": 6.849012474012474, "percentage": 34.25, "elapsed_time": "0:38:12", "remaining_time": "1:13:22", "throughput": 1035.39, "total_tokens": 2373896} {"current_steps": 26360, "total_steps": 76960, "loss": 0.3347, "lr": 4.156533135357777e-05, "epoch": 6.850311850311851, "percentage": 34.25, "elapsed_time": "0:38:13", "remaining_time": "1:13:21", "throughput": 1035.41, "total_tokens": 2374376} {"current_steps": 26365, "total_steps": 76960, "loss": 0.2582, "lr": 4.156108461519753e-05, "epoch": 6.851611226611227, "percentage": 34.26, "elapsed_time": "0:38:13", "remaining_time": "1:13:21", "throughput": 1035.42, "total_tokens": 2374824} {"current_steps": 26370, "total_steps": 76960, "loss": 0.2604, "lr": 4.155683702506483e-05, "epoch": 6.852910602910603, "percentage": 34.26, "elapsed_time": "0:38:14", "remaining_time": "1:13:20", "throughput": 1035.42, "total_tokens": 2375256} {"current_steps": 26375, "total_steps": 76960, "loss": 0.2912, "lr": 4.1552588583398143e-05, "epoch": 6.854209979209979, "percentage": 34.27, "elapsed_time": "0:38:14", "remaining_time": "1:13:20", "throughput": 1035.43, "total_tokens": 2375720} {"current_steps": 26380, "total_steps": 76960, "loss": 0.2929, "lr": 4.154833929041597e-05, "epoch": 6.855509355509356, "percentage": 34.28, "elapsed_time": "0:38:14", "remaining_time": "1:13:20", "throughput": 1035.43, "total_tokens": 2376152} {"current_steps": 26385, "total_steps": 76960, "loss": 0.3008, "lr": 4.154408914633685e-05, "epoch": 6.856808731808732, "percentage": 34.28, "elapsed_time": "0:38:15", "remaining_time": "1:13:19", "throughput": 1035.43, "total_tokens": 2376584} {"current_steps": 26390, "total_steps": 76960, "loss": 0.2492, "lr": 4.153983815137937e-05, "epoch": 6.858108108108108, "percentage": 34.29, "elapsed_time": "0:38:15", "remaining_time": "1:13:19", "throughput": 1035.44, "total_tokens": 2377032} {"current_steps": 26395, "total_steps": 76960, "loss": 0.278, "lr": 4.153558630576217e-05, "epoch": 6.859407484407484, "percentage": 34.3, "elapsed_time": "0:38:16", "remaining_time": "1:13:18", "throughput": 1035.44, "total_tokens": 2377464} {"current_steps": 26400, "total_steps": 76960, "loss": 0.2324, "lr": 4.153133360970392e-05, "epoch": 6.860706860706861, "percentage": 34.3, "elapsed_time": "0:38:16", "remaining_time": "1:13:18", "throughput": 1035.45, "total_tokens": 2377928} {"current_steps": 26405, "total_steps": 76960, "loss": 0.2291, "lr": 4.152708006342334e-05, "epoch": 6.862006237006237, "percentage": 34.31, "elapsed_time": "0:38:16", "remaining_time": "1:13:17", "throughput": 1035.47, "total_tokens": 2378392} {"current_steps": 26410, "total_steps": 76960, "loss": 0.1805, "lr": 4.1522825667139206e-05, "epoch": 6.863305613305613, "percentage": 34.32, "elapsed_time": "0:38:17", "remaining_time": "1:13:17", "throughput": 1035.48, "total_tokens": 2378856} {"current_steps": 26415, "total_steps": 76960, "loss": 0.2056, "lr": 4.151857042107031e-05, "epoch": 6.86460498960499, "percentage": 34.32, "elapsed_time": "0:38:17", "remaining_time": "1:13:16", "throughput": 1035.5, "total_tokens": 2379320} {"current_steps": 26420, "total_steps": 76960, "loss": 0.156, "lr": 4.151431432543551e-05, "epoch": 6.865904365904366, "percentage": 34.33, "elapsed_time": "0:38:18", "remaining_time": "1:13:16", "throughput": 1035.49, "total_tokens": 2379736} {"current_steps": 26425, "total_steps": 76960, "loss": 0.2178, "lr": 4.15100573804537e-05, "epoch": 6.867203742203742, "percentage": 34.34, "elapsed_time": "0:38:18", "remaining_time": "1:13:15", "throughput": 1035.5, "total_tokens": 2380200} {"current_steps": 26430, "total_steps": 76960, "loss": 0.2151, "lr": 4.150579958634382e-05, "epoch": 6.868503118503119, "percentage": 34.34, "elapsed_time": "0:38:19", "remaining_time": "1:13:15", "throughput": 1035.52, "total_tokens": 2380664} {"current_steps": 26435, "total_steps": 76960, "loss": 0.1341, "lr": 4.150154094332486e-05, "epoch": 6.869802494802495, "percentage": 34.35, "elapsed_time": "0:38:19", "remaining_time": "1:13:14", "throughput": 1035.52, "total_tokens": 2381096} {"current_steps": 26440, "total_steps": 76960, "loss": 0.2172, "lr": 4.1497281451615824e-05, "epoch": 6.871101871101871, "percentage": 34.36, "elapsed_time": "0:38:19", "remaining_time": "1:13:14", "throughput": 1035.53, "total_tokens": 2381544} {"current_steps": 26445, "total_steps": 76960, "loss": 0.2862, "lr": 4.1493021111435805e-05, "epoch": 6.872401247401247, "percentage": 34.36, "elapsed_time": "0:38:20", "remaining_time": "1:13:13", "throughput": 1035.52, "total_tokens": 2381960} {"current_steps": 26450, "total_steps": 76960, "loss": 0.2676, "lr": 4.1488759923003904e-05, "epoch": 6.873700623700624, "percentage": 34.37, "elapsed_time": "0:38:20", "remaining_time": "1:13:13", "throughput": 1035.53, "total_tokens": 2382408} {"current_steps": 26455, "total_steps": 76960, "loss": 0.3344, "lr": 4.1484497886539286e-05, "epoch": 6.875, "percentage": 34.38, "elapsed_time": "0:38:21", "remaining_time": "1:13:12", "throughput": 1035.54, "total_tokens": 2382856} {"current_steps": 26460, "total_steps": 76960, "loss": 0.1632, "lr": 4.148023500226115e-05, "epoch": 6.876299376299376, "percentage": 34.38, "elapsed_time": "0:38:21", "remaining_time": "1:13:12", "throughput": 1035.54, "total_tokens": 2383288} {"current_steps": 26465, "total_steps": 76960, "loss": 0.2822, "lr": 4.147597127038873e-05, "epoch": 6.877598752598753, "percentage": 34.39, "elapsed_time": "0:38:21", "remaining_time": "1:13:12", "throughput": 1035.54, "total_tokens": 2383720} {"current_steps": 26470, "total_steps": 76960, "loss": 0.2756, "lr": 4.147170669114132e-05, "epoch": 6.878898128898129, "percentage": 34.39, "elapsed_time": "0:38:22", "remaining_time": "1:13:11", "throughput": 1035.54, "total_tokens": 2384168} {"current_steps": 26475, "total_steps": 76960, "loss": 0.2449, "lr": 4.146744126473826e-05, "epoch": 6.880197505197505, "percentage": 34.4, "elapsed_time": "0:38:22", "remaining_time": "1:13:11", "throughput": 1035.54, "total_tokens": 2384584} {"current_steps": 26480, "total_steps": 76960, "loss": 0.2719, "lr": 4.1463174991398914e-05, "epoch": 6.881496881496881, "percentage": 34.41, "elapsed_time": "0:38:23", "remaining_time": "1:13:10", "throughput": 1035.54, "total_tokens": 2385016} {"current_steps": 26485, "total_steps": 76960, "loss": 0.2009, "lr": 4.1458907871342694e-05, "epoch": 6.882796257796258, "percentage": 34.41, "elapsed_time": "0:38:23", "remaining_time": "1:13:10", "throughput": 1035.54, "total_tokens": 2385448} {"current_steps": 26490, "total_steps": 76960, "loss": 0.2278, "lr": 4.145463990478908e-05, "epoch": 6.884095634095634, "percentage": 34.42, "elapsed_time": "0:38:23", "remaining_time": "1:13:09", "throughput": 1035.56, "total_tokens": 2385928} {"current_steps": 26495, "total_steps": 76960, "loss": 0.183, "lr": 4.1450371091957576e-05, "epoch": 6.88539501039501, "percentage": 34.43, "elapsed_time": "0:38:24", "remaining_time": "1:13:09", "throughput": 1035.57, "total_tokens": 2386376} {"current_steps": 26500, "total_steps": 76960, "loss": 0.2203, "lr": 4.144610143306772e-05, "epoch": 6.886694386694387, "percentage": 34.43, "elapsed_time": "0:38:24", "remaining_time": "1:13:08", "throughput": 1035.56, "total_tokens": 2386792} {"current_steps": 26505, "total_steps": 76960, "loss": 0.2502, "lr": 4.144183092833911e-05, "epoch": 6.887993762993763, "percentage": 34.44, "elapsed_time": "0:38:25", "remaining_time": "1:13:08", "throughput": 1035.55, "total_tokens": 2387208} {"current_steps": 26510, "total_steps": 76960, "loss": 0.2488, "lr": 4.1437559577991376e-05, "epoch": 6.889293139293139, "percentage": 34.45, "elapsed_time": "0:38:25", "remaining_time": "1:13:07", "throughput": 1035.57, "total_tokens": 2387672} {"current_steps": 26515, "total_steps": 76960, "loss": 0.2208, "lr": 4.14332873822442e-05, "epoch": 6.890592515592516, "percentage": 34.45, "elapsed_time": "0:38:26", "remaining_time": "1:13:07", "throughput": 1035.55, "total_tokens": 2388072} {"current_steps": 26520, "total_steps": 76960, "loss": 0.0835, "lr": 4.142901434131732e-05, "epoch": 6.891891891891892, "percentage": 34.46, "elapsed_time": "0:38:26", "remaining_time": "1:13:06", "throughput": 1035.59, "total_tokens": 2388584} {"current_steps": 26525, "total_steps": 76960, "loss": 0.1382, "lr": 4.1424740455430486e-05, "epoch": 6.893191268191268, "percentage": 34.47, "elapsed_time": "0:38:26", "remaining_time": "1:13:06", "throughput": 1035.59, "total_tokens": 2389016} {"current_steps": 26530, "total_steps": 76960, "loss": 0.2379, "lr": 4.1420465724803516e-05, "epoch": 6.894490644490644, "percentage": 34.47, "elapsed_time": "0:38:27", "remaining_time": "1:13:05", "throughput": 1035.6, "total_tokens": 2389464} {"current_steps": 26535, "total_steps": 76960, "loss": 0.2369, "lr": 4.141619014965626e-05, "epoch": 6.895790020790021, "percentage": 34.48, "elapsed_time": "0:38:27", "remaining_time": "1:13:05", "throughput": 1035.58, "total_tokens": 2389864} {"current_steps": 26540, "total_steps": 76960, "loss": 0.4794, "lr": 4.141191373020861e-05, "epoch": 6.897089397089397, "percentage": 34.49, "elapsed_time": "0:38:28", "remaining_time": "1:13:04", "throughput": 1035.59, "total_tokens": 2390312} {"current_steps": 26545, "total_steps": 76960, "loss": 0.3769, "lr": 4.140763646668052e-05, "epoch": 6.898388773388773, "percentage": 34.49, "elapsed_time": "0:38:28", "remaining_time": "1:13:04", "throughput": 1035.6, "total_tokens": 2390776} {"current_steps": 26550, "total_steps": 76960, "loss": 0.223, "lr": 4.140335835929196e-05, "epoch": 6.899688149688149, "percentage": 34.5, "elapsed_time": "0:38:29", "remaining_time": "1:13:04", "throughput": 1035.61, "total_tokens": 2391224} {"current_steps": 26555, "total_steps": 76960, "loss": 0.2532, "lr": 4.139907940826296e-05, "epoch": 6.900987525987526, "percentage": 34.5, "elapsed_time": "0:38:29", "remaining_time": "1:13:03", "throughput": 1035.6, "total_tokens": 2391640} {"current_steps": 26560, "total_steps": 76960, "loss": 0.2656, "lr": 4.1394799613813595e-05, "epoch": 6.902286902286902, "percentage": 34.51, "elapsed_time": "0:38:29", "remaining_time": "1:13:03", "throughput": 1035.62, "total_tokens": 2392104} {"current_steps": 26565, "total_steps": 76960, "loss": 0.2168, "lr": 4.139051897616397e-05, "epoch": 6.903586278586278, "percentage": 34.52, "elapsed_time": "0:38:30", "remaining_time": "1:13:02", "throughput": 1035.62, "total_tokens": 2392552} {"current_steps": 26570, "total_steps": 76960, "loss": 0.3134, "lr": 4.1386237495534266e-05, "epoch": 6.904885654885655, "percentage": 34.52, "elapsed_time": "0:38:30", "remaining_time": "1:13:02", "throughput": 1035.63, "total_tokens": 2393000} {"current_steps": 26575, "total_steps": 76960, "loss": 0.2288, "lr": 4.138195517214466e-05, "epoch": 6.906185031185031, "percentage": 34.53, "elapsed_time": "0:38:31", "remaining_time": "1:13:01", "throughput": 1035.64, "total_tokens": 2393448} {"current_steps": 26580, "total_steps": 76960, "loss": 0.2502, "lr": 4.13776720062154e-05, "epoch": 6.907484407484407, "percentage": 34.54, "elapsed_time": "0:38:31", "remaining_time": "1:13:01", "throughput": 1035.64, "total_tokens": 2393896} {"current_steps": 26585, "total_steps": 76960, "loss": 0.2914, "lr": 4.1373387997966775e-05, "epoch": 6.908783783783784, "percentage": 34.54, "elapsed_time": "0:38:31", "remaining_time": "1:13:00", "throughput": 1035.65, "total_tokens": 2394344} {"current_steps": 26590, "total_steps": 76960, "loss": 0.3724, "lr": 4.1369103147619125e-05, "epoch": 6.91008316008316, "percentage": 34.55, "elapsed_time": "0:38:32", "remaining_time": "1:13:00", "throughput": 1035.66, "total_tokens": 2394808} {"current_steps": 26595, "total_steps": 76960, "loss": 0.2406, "lr": 4.136481745539281e-05, "epoch": 6.911382536382536, "percentage": 34.56, "elapsed_time": "0:38:32", "remaining_time": "1:12:59", "throughput": 1035.67, "total_tokens": 2395256} {"current_steps": 26600, "total_steps": 76960, "loss": 0.2993, "lr": 4.136053092150826e-05, "epoch": 6.912681912681912, "percentage": 34.56, "elapsed_time": "0:38:33", "remaining_time": "1:12:59", "throughput": 1035.69, "total_tokens": 2395736} {"current_steps": 26605, "total_steps": 76960, "loss": 0.2358, "lr": 4.135624354618592e-05, "epoch": 6.913981288981289, "percentage": 34.57, "elapsed_time": "0:38:33", "remaining_time": "1:12:58", "throughput": 1035.72, "total_tokens": 2396232} {"current_steps": 26610, "total_steps": 76960, "loss": 0.2713, "lr": 4.13519553296463e-05, "epoch": 6.915280665280665, "percentage": 34.58, "elapsed_time": "0:38:34", "remaining_time": "1:12:58", "throughput": 1035.72, "total_tokens": 2396664} {"current_steps": 26615, "total_steps": 76960, "loss": 0.2934, "lr": 4.1347666272109955e-05, "epoch": 6.916580041580041, "percentage": 34.58, "elapsed_time": "0:38:34", "remaining_time": "1:12:57", "throughput": 1035.72, "total_tokens": 2397096} {"current_steps": 26620, "total_steps": 76960, "loss": 0.1747, "lr": 4.134337637379747e-05, "epoch": 6.917879417879417, "percentage": 34.59, "elapsed_time": "0:38:34", "remaining_time": "1:12:57", "throughput": 1035.72, "total_tokens": 2397528} {"current_steps": 26625, "total_steps": 76960, "loss": 0.1537, "lr": 4.1339085634929485e-05, "epoch": 6.919178794178794, "percentage": 34.6, "elapsed_time": "0:38:35", "remaining_time": "1:12:57", "throughput": 1035.73, "total_tokens": 2397976} {"current_steps": 26630, "total_steps": 76960, "loss": 0.2004, "lr": 4.133479405572667e-05, "epoch": 6.92047817047817, "percentage": 34.6, "elapsed_time": "0:38:35", "remaining_time": "1:12:56", "throughput": 1035.74, "total_tokens": 2398440} {"current_steps": 26635, "total_steps": 76960, "loss": 0.2222, "lr": 4.133050163640974e-05, "epoch": 6.921777546777546, "percentage": 34.61, "elapsed_time": "0:38:36", "remaining_time": "1:12:56", "throughput": 1035.74, "total_tokens": 2398856} {"current_steps": 26640, "total_steps": 76960, "loss": 0.2512, "lr": 4.132620837719946e-05, "epoch": 6.923076923076923, "percentage": 34.62, "elapsed_time": "0:38:36", "remaining_time": "1:12:55", "throughput": 1035.76, "total_tokens": 2399336} {"current_steps": 26645, "total_steps": 76960, "loss": 0.2437, "lr": 4.132191427831664e-05, "epoch": 6.924376299376299, "percentage": 34.62, "elapsed_time": "0:38:36", "remaining_time": "1:12:55", "throughput": 1035.76, "total_tokens": 2399768} {"current_steps": 26650, "total_steps": 76960, "loss": 0.2647, "lr": 4.1317619339982136e-05, "epoch": 6.925675675675675, "percentage": 34.63, "elapsed_time": "0:38:37", "remaining_time": "1:12:54", "throughput": 1035.77, "total_tokens": 2400232} {"current_steps": 26655, "total_steps": 76960, "loss": 0.1384, "lr": 4.131332356241683e-05, "epoch": 6.926975051975052, "percentage": 34.63, "elapsed_time": "0:38:37", "remaining_time": "1:12:54", "throughput": 1035.77, "total_tokens": 2400664} {"current_steps": 26660, "total_steps": 76960, "loss": 0.3107, "lr": 4.130902694584167e-05, "epoch": 6.928274428274428, "percentage": 34.64, "elapsed_time": "0:38:38", "remaining_time": "1:12:53", "throughput": 1035.79, "total_tokens": 2401144} {"current_steps": 26665, "total_steps": 76960, "loss": 0.2986, "lr": 4.1304729490477624e-05, "epoch": 6.9295738045738045, "percentage": 34.65, "elapsed_time": "0:38:38", "remaining_time": "1:12:53", "throughput": 1035.8, "total_tokens": 2401608} {"current_steps": 26670, "total_steps": 76960, "loss": 0.3523, "lr": 4.1300431196545715e-05, "epoch": 6.9308731808731805, "percentage": 34.65, "elapsed_time": "0:38:39", "remaining_time": "1:12:52", "throughput": 1035.81, "total_tokens": 2402072} {"current_steps": 26675, "total_steps": 76960, "loss": 0.267, "lr": 4.129613206426701e-05, "epoch": 6.932172557172557, "percentage": 34.66, "elapsed_time": "0:38:39", "remaining_time": "1:12:52", "throughput": 1035.81, "total_tokens": 2402520} {"current_steps": 26680, "total_steps": 76960, "loss": 0.2946, "lr": 4.1291832093862625e-05, "epoch": 6.9334719334719335, "percentage": 34.67, "elapsed_time": "0:38:39", "remaining_time": "1:12:51", "throughput": 1035.81, "total_tokens": 2402952} {"current_steps": 26685, "total_steps": 76960, "loss": 0.2993, "lr": 4.12875312855537e-05, "epoch": 6.9347713097713095, "percentage": 34.67, "elapsed_time": "0:38:40", "remaining_time": "1:12:51", "throughput": 1035.83, "total_tokens": 2403416} {"current_steps": 26690, "total_steps": 76960, "loss": 0.2735, "lr": 4.128322963956143e-05, "epoch": 6.936070686070686, "percentage": 34.68, "elapsed_time": "0:38:40", "remaining_time": "1:12:51", "throughput": 1035.83, "total_tokens": 2403848} {"current_steps": 26695, "total_steps": 76960, "loss": 0.181, "lr": 4.127892715610707e-05, "epoch": 6.9373700623700625, "percentage": 34.69, "elapsed_time": "0:38:41", "remaining_time": "1:12:50", "throughput": 1035.83, "total_tokens": 2404280} {"current_steps": 26700, "total_steps": 76960, "loss": 0.2067, "lr": 4.127462383541188e-05, "epoch": 6.9386694386694385, "percentage": 34.69, "elapsed_time": "0:38:41", "remaining_time": "1:12:50", "throughput": 1035.85, "total_tokens": 2404760} {"current_steps": 26705, "total_steps": 76960, "loss": 0.2216, "lr": 4.12703196776972e-05, "epoch": 6.939968814968815, "percentage": 34.7, "elapsed_time": "0:38:41", "remaining_time": "1:12:49", "throughput": 1035.87, "total_tokens": 2405240} {"current_steps": 26710, "total_steps": 76960, "loss": 0.3691, "lr": 4.1266014683184384e-05, "epoch": 6.9412681912681915, "percentage": 34.71, "elapsed_time": "0:38:42", "remaining_time": "1:12:49", "throughput": 1035.88, "total_tokens": 2405688} {"current_steps": 26715, "total_steps": 76960, "loss": 0.3145, "lr": 4.126170885209485e-05, "epoch": 6.9425675675675675, "percentage": 34.71, "elapsed_time": "0:38:42", "remaining_time": "1:12:48", "throughput": 1035.89, "total_tokens": 2406152} {"current_steps": 26720, "total_steps": 76960, "loss": 0.3026, "lr": 4.125740218465005e-05, "epoch": 6.943866943866944, "percentage": 34.72, "elapsed_time": "0:38:43", "remaining_time": "1:12:48", "throughput": 1035.9, "total_tokens": 2406600} {"current_steps": 26725, "total_steps": 76960, "loss": 0.2274, "lr": 4.125309468107147e-05, "epoch": 6.9451663201663205, "percentage": 34.73, "elapsed_time": "0:38:43", "remaining_time": "1:12:47", "throughput": 1035.9, "total_tokens": 2407032} {"current_steps": 26730, "total_steps": 76960, "loss": 0.2712, "lr": 4.124878634158067e-05, "epoch": 6.946465696465697, "percentage": 34.73, "elapsed_time": "0:38:44", "remaining_time": "1:12:47", "throughput": 1035.89, "total_tokens": 2407448} {"current_steps": 26735, "total_steps": 76960, "loss": 0.2788, "lr": 4.124447716639921e-05, "epoch": 6.947765072765073, "percentage": 34.74, "elapsed_time": "0:38:44", "remaining_time": "1:12:46", "throughput": 1035.91, "total_tokens": 2407912} {"current_steps": 26740, "total_steps": 76960, "loss": 0.2778, "lr": 4.124016715574873e-05, "epoch": 6.9490644490644495, "percentage": 34.75, "elapsed_time": "0:38:44", "remaining_time": "1:12:46", "throughput": 1035.92, "total_tokens": 2408376} {"current_steps": 26745, "total_steps": 76960, "loss": 0.2854, "lr": 4.123585630985088e-05, "epoch": 6.950363825363826, "percentage": 34.75, "elapsed_time": "0:38:45", "remaining_time": "1:12:45", "throughput": 1035.93, "total_tokens": 2408840} {"current_steps": 26750, "total_steps": 76960, "loss": 0.3243, "lr": 4.12315446289274e-05, "epoch": 6.951663201663202, "percentage": 34.76, "elapsed_time": "0:38:45", "remaining_time": "1:12:45", "throughput": 1035.95, "total_tokens": 2409304} {"current_steps": 26755, "total_steps": 76960, "loss": 0.2157, "lr": 4.122723211320002e-05, "epoch": 6.952962577962578, "percentage": 34.76, "elapsed_time": "0:38:46", "remaining_time": "1:12:44", "throughput": 1035.95, "total_tokens": 2409736} {"current_steps": 26760, "total_steps": 76960, "loss": 0.3048, "lr": 4.122291876289055e-05, "epoch": 6.954261954261955, "percentage": 34.77, "elapsed_time": "0:38:46", "remaining_time": "1:12:44", "throughput": 1035.96, "total_tokens": 2410200} {"current_steps": 26765, "total_steps": 76960, "loss": 0.2826, "lr": 4.121860457822082e-05, "epoch": 6.955561330561331, "percentage": 34.78, "elapsed_time": "0:38:46", "remaining_time": "1:12:43", "throughput": 1035.99, "total_tokens": 2410696} {"current_steps": 26770, "total_steps": 76960, "loss": 0.3082, "lr": 4.121428955941271e-05, "epoch": 6.956860706860707, "percentage": 34.78, "elapsed_time": "0:38:47", "remaining_time": "1:12:43", "throughput": 1035.99, "total_tokens": 2411128} {"current_steps": 26775, "total_steps": 76960, "loss": 0.3294, "lr": 4.120997370668815e-05, "epoch": 6.958160083160083, "percentage": 34.79, "elapsed_time": "0:38:47", "remaining_time": "1:12:43", "throughput": 1036.01, "total_tokens": 2411608} {"current_steps": 26780, "total_steps": 76960, "loss": 0.2663, "lr": 4.1205657020269126e-05, "epoch": 6.95945945945946, "percentage": 34.8, "elapsed_time": "0:38:48", "remaining_time": "1:12:42", "throughput": 1036.01, "total_tokens": 2412040} {"current_steps": 26785, "total_steps": 76960, "loss": 0.2766, "lr": 4.120133950037763e-05, "epoch": 6.960758835758836, "percentage": 34.8, "elapsed_time": "0:38:48", "remaining_time": "1:12:42", "throughput": 1035.99, "total_tokens": 2412440} {"current_steps": 26790, "total_steps": 76960, "loss": 0.271, "lr": 4.1197021147235715e-05, "epoch": 6.962058212058212, "percentage": 34.81, "elapsed_time": "0:38:49", "remaining_time": "1:12:41", "throughput": 1036.0, "total_tokens": 2412888} {"current_steps": 26795, "total_steps": 76960, "loss": 0.2539, "lr": 4.119270196106549e-05, "epoch": 6.963357588357589, "percentage": 34.82, "elapsed_time": "0:38:49", "remaining_time": "1:12:41", "throughput": 1036.02, "total_tokens": 2413368} {"current_steps": 26800, "total_steps": 76960, "loss": 0.2562, "lr": 4.118838194208908e-05, "epoch": 6.964656964656965, "percentage": 34.82, "elapsed_time": "0:38:49", "remaining_time": "1:12:40", "throughput": 1036.02, "total_tokens": 2413800} {"current_steps": 26805, "total_steps": 76960, "loss": 0.2155, "lr": 4.1184061090528683e-05, "epoch": 6.965956340956341, "percentage": 34.83, "elapsed_time": "0:38:50", "remaining_time": "1:12:40", "throughput": 1036.04, "total_tokens": 2414264} {"current_steps": 26810, "total_steps": 76960, "loss": 0.401, "lr": 4.117973940660651e-05, "epoch": 6.967255717255718, "percentage": 34.84, "elapsed_time": "0:38:50", "remaining_time": "1:12:39", "throughput": 1036.04, "total_tokens": 2414712} {"current_steps": 26815, "total_steps": 76960, "loss": 0.2381, "lr": 4.1175416890544836e-05, "epoch": 6.968555093555094, "percentage": 34.84, "elapsed_time": "0:38:51", "remaining_time": "1:12:39", "throughput": 1036.04, "total_tokens": 2415144} {"current_steps": 26820, "total_steps": 76960, "loss": 0.2953, "lr": 4.1171093542565976e-05, "epoch": 6.96985446985447, "percentage": 34.85, "elapsed_time": "0:38:51", "remaining_time": "1:12:38", "throughput": 1036.05, "total_tokens": 2415592} {"current_steps": 26825, "total_steps": 76960, "loss": 0.2841, "lr": 4.116676936289228e-05, "epoch": 6.971153846153846, "percentage": 34.86, "elapsed_time": "0:38:51", "remaining_time": "1:12:38", "throughput": 1036.07, "total_tokens": 2416056} {"current_steps": 26830, "total_steps": 76960, "loss": 0.2847, "lr": 4.116244435174615e-05, "epoch": 6.972453222453223, "percentage": 34.86, "elapsed_time": "0:38:52", "remaining_time": "1:12:37", "throughput": 1036.07, "total_tokens": 2416504} {"current_steps": 26835, "total_steps": 76960, "loss": 0.2354, "lr": 4.115811850935002e-05, "epoch": 6.973752598752599, "percentage": 34.87, "elapsed_time": "0:38:52", "remaining_time": "1:12:37", "throughput": 1036.07, "total_tokens": 2416920} {"current_steps": 26840, "total_steps": 76960, "loss": 0.2088, "lr": 4.115379183592637e-05, "epoch": 6.975051975051975, "percentage": 34.88, "elapsed_time": "0:38:53", "remaining_time": "1:12:36", "throughput": 1036.07, "total_tokens": 2417352} {"current_steps": 26845, "total_steps": 76960, "loss": 0.247, "lr": 4.114946433169773e-05, "epoch": 6.976351351351351, "percentage": 34.88, "elapsed_time": "0:38:53", "remaining_time": "1:12:36", "throughput": 1036.08, "total_tokens": 2417816} {"current_steps": 26850, "total_steps": 76960, "loss": 0.2876, "lr": 4.1145135996886665e-05, "epoch": 6.977650727650728, "percentage": 34.89, "elapsed_time": "0:38:54", "remaining_time": "1:12:35", "throughput": 1036.09, "total_tokens": 2418264} {"current_steps": 26855, "total_steps": 76960, "loss": 0.2531, "lr": 4.114080683171579e-05, "epoch": 6.978950103950104, "percentage": 34.89, "elapsed_time": "0:38:54", "remaining_time": "1:12:35", "throughput": 1036.09, "total_tokens": 2418696} {"current_steps": 26860, "total_steps": 76960, "loss": 0.2145, "lr": 4.113647683640774e-05, "epoch": 6.98024948024948, "percentage": 34.9, "elapsed_time": "0:38:54", "remaining_time": "1:12:35", "throughput": 1036.09, "total_tokens": 2419128} {"current_steps": 26865, "total_steps": 76960, "loss": 0.3036, "lr": 4.113214601118524e-05, "epoch": 6.981548856548857, "percentage": 34.91, "elapsed_time": "0:38:55", "remaining_time": "1:12:34", "throughput": 1036.1, "total_tokens": 2419592} {"current_steps": 26870, "total_steps": 76960, "loss": 0.2215, "lr": 4.112781435627101e-05, "epoch": 6.982848232848233, "percentage": 34.91, "elapsed_time": "0:38:55", "remaining_time": "1:12:34", "throughput": 1036.1, "total_tokens": 2420024} {"current_steps": 26875, "total_steps": 76960, "loss": 0.2485, "lr": 4.112348187188783e-05, "epoch": 6.984147609147609, "percentage": 34.92, "elapsed_time": "0:38:56", "remaining_time": "1:12:33", "throughput": 1036.11, "total_tokens": 2420472} {"current_steps": 26880, "total_steps": 76960, "loss": 0.1753, "lr": 4.111914855825853e-05, "epoch": 6.985446985446986, "percentage": 34.93, "elapsed_time": "0:38:56", "remaining_time": "1:12:33", "throughput": 1036.12, "total_tokens": 2420920} {"current_steps": 26885, "total_steps": 76960, "loss": 0.2261, "lr": 4.111481441560598e-05, "epoch": 6.986746361746362, "percentage": 34.93, "elapsed_time": "0:38:56", "remaining_time": "1:12:32", "throughput": 1036.1, "total_tokens": 2421320} {"current_steps": 26890, "total_steps": 76960, "loss": 0.3989, "lr": 4.1110479444153084e-05, "epoch": 6.988045738045738, "percentage": 34.94, "elapsed_time": "0:38:57", "remaining_time": "1:12:32", "throughput": 1036.1, "total_tokens": 2421752} {"current_steps": 26895, "total_steps": 76960, "loss": 0.2066, "lr": 4.110614364412278e-05, "epoch": 6.989345114345114, "percentage": 34.95, "elapsed_time": "0:38:57", "remaining_time": "1:12:31", "throughput": 1036.12, "total_tokens": 2422216} {"current_steps": 26900, "total_steps": 76960, "loss": 0.2608, "lr": 4.1101807015738095e-05, "epoch": 6.990644490644491, "percentage": 34.95, "elapsed_time": "0:38:58", "remaining_time": "1:12:31", "throughput": 1036.13, "total_tokens": 2422680} {"current_steps": 26905, "total_steps": 76960, "loss": 0.265, "lr": 4.1097469559222034e-05, "epoch": 6.991943866943867, "percentage": 34.96, "elapsed_time": "0:38:58", "remaining_time": "1:12:30", "throughput": 1036.15, "total_tokens": 2423144} {"current_steps": 26910, "total_steps": 76960, "loss": 0.2791, "lr": 4.1093131274797694e-05, "epoch": 6.993243243243243, "percentage": 34.97, "elapsed_time": "0:38:59", "remaining_time": "1:12:30", "throughput": 1036.15, "total_tokens": 2423576} {"current_steps": 26915, "total_steps": 76960, "loss": 0.2647, "lr": 4.108879216268819e-05, "epoch": 6.99454261954262, "percentage": 34.97, "elapsed_time": "0:38:59", "remaining_time": "1:12:29", "throughput": 1036.15, "total_tokens": 2424024} {"current_steps": 26920, "total_steps": 76960, "loss": 0.3123, "lr": 4.10844522231167e-05, "epoch": 6.995841995841996, "percentage": 34.98, "elapsed_time": "0:38:59", "remaining_time": "1:12:29", "throughput": 1036.17, "total_tokens": 2424488} {"current_steps": 26925, "total_steps": 76960, "loss": 0.2563, "lr": 4.108011145630642e-05, "epoch": 6.997141372141372, "percentage": 34.99, "elapsed_time": "0:39:00", "remaining_time": "1:12:28", "throughput": 1036.17, "total_tokens": 2424936} {"current_steps": 26930, "total_steps": 76960, "loss": 0.2252, "lr": 4.10757698624806e-05, "epoch": 6.998440748440748, "percentage": 34.99, "elapsed_time": "0:39:00", "remaining_time": "1:12:28", "throughput": 1036.18, "total_tokens": 2425384} {"current_steps": 26935, "total_steps": 76960, "loss": 0.2849, "lr": 4.107142744186252e-05, "epoch": 6.999740124740125, "percentage": 35.0, "elapsed_time": "0:39:01", "remaining_time": "1:12:28", "throughput": 1036.21, "total_tokens": 2425880} {"current_steps": 26936, "total_steps": 76960, "eval_loss": 0.2418590486049652, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:39:14", "remaining_time": "1:12:52", "throughput": 1030.37, "total_tokens": 2425920} {"current_steps": 26940, "total_steps": 76960, "loss": 0.2311, "lr": 4.106708419467553e-05, "epoch": 7.001039501039501, "percentage": 35.01, "elapsed_time": "0:39:16", "remaining_time": "1:12:54", "throughput": 1029.69, "total_tokens": 2426272} {"current_steps": 26945, "total_steps": 76960, "loss": 0.2141, "lr": 4.1062740121143016e-05, "epoch": 7.002338877338877, "percentage": 35.01, "elapsed_time": "0:39:16", "remaining_time": "1:12:54", "throughput": 1029.7, "total_tokens": 2426736} {"current_steps": 26950, "total_steps": 76960, "loss": 0.212, "lr": 4.1058395221488375e-05, "epoch": 7.003638253638254, "percentage": 35.02, "elapsed_time": "0:39:17", "remaining_time": "1:12:54", "throughput": 1029.69, "total_tokens": 2427168} {"current_steps": 26955, "total_steps": 76960, "loss": 0.2139, "lr": 4.105404949593509e-05, "epoch": 7.00493762993763, "percentage": 35.02, "elapsed_time": "0:39:17", "remaining_time": "1:12:53", "throughput": 1029.7, "total_tokens": 2427616} {"current_steps": 26960, "total_steps": 76960, "loss": 0.1528, "lr": 4.104970294470666e-05, "epoch": 7.006237006237006, "percentage": 35.03, "elapsed_time": "0:39:18", "remaining_time": "1:12:53", "throughput": 1029.7, "total_tokens": 2428064} {"current_steps": 26965, "total_steps": 76960, "loss": 0.2468, "lr": 4.1045355568026625e-05, "epoch": 7.007536382536382, "percentage": 35.04, "elapsed_time": "0:39:18", "remaining_time": "1:12:52", "throughput": 1029.69, "total_tokens": 2428480} {"current_steps": 26970, "total_steps": 76960, "loss": 0.1501, "lr": 4.1041007366118575e-05, "epoch": 7.008835758835759, "percentage": 35.04, "elapsed_time": "0:39:18", "remaining_time": "1:12:52", "throughput": 1029.69, "total_tokens": 2428912} {"current_steps": 26975, "total_steps": 76960, "loss": 0.3277, "lr": 4.1036658339206146e-05, "epoch": 7.010135135135135, "percentage": 35.05, "elapsed_time": "0:39:19", "remaining_time": "1:12:51", "throughput": 1029.7, "total_tokens": 2429360} {"current_steps": 26980, "total_steps": 76960, "loss": 0.3944, "lr": 4.1032308487513023e-05, "epoch": 7.011434511434511, "percentage": 35.06, "elapsed_time": "0:39:19", "remaining_time": "1:12:51", "throughput": 1029.72, "total_tokens": 2429840} {"current_steps": 26985, "total_steps": 76960, "loss": 0.1699, "lr": 4.1027957811262905e-05, "epoch": 7.012733887733888, "percentage": 35.06, "elapsed_time": "0:39:20", "remaining_time": "1:12:50", "throughput": 1029.7, "total_tokens": 2430240} {"current_steps": 26990, "total_steps": 76960, "loss": 0.3029, "lr": 4.1023606310679563e-05, "epoch": 7.014033264033264, "percentage": 35.07, "elapsed_time": "0:39:20", "remaining_time": "1:12:50", "throughput": 1029.72, "total_tokens": 2430704} {"current_steps": 26995, "total_steps": 76960, "loss": 0.1623, "lr": 4.101925398598679e-05, "epoch": 7.01533264033264, "percentage": 35.08, "elapsed_time": "0:39:20", "remaining_time": "1:12:49", "throughput": 1029.71, "total_tokens": 2431120} {"current_steps": 27000, "total_steps": 76960, "loss": 0.1789, "lr": 4.101490083740844e-05, "epoch": 7.016632016632016, "percentage": 35.08, "elapsed_time": "0:39:21", "remaining_time": "1:12:49", "throughput": 1029.74, "total_tokens": 2431616} {"current_steps": 27005, "total_steps": 76960, "loss": 0.3112, "lr": 4.10105468651684e-05, "epoch": 7.017931392931393, "percentage": 35.09, "elapsed_time": "0:39:21", "remaining_time": "1:12:48", "throughput": 1029.73, "total_tokens": 2432032} {"current_steps": 27010, "total_steps": 76960, "loss": 0.3535, "lr": 4.100619206949059e-05, "epoch": 7.019230769230769, "percentage": 35.1, "elapsed_time": "0:39:22", "remaining_time": "1:12:48", "throughput": 1029.75, "total_tokens": 2432512} {"current_steps": 27015, "total_steps": 76960, "loss": 0.298, "lr": 4.1001836450598986e-05, "epoch": 7.020530145530145, "percentage": 35.1, "elapsed_time": "0:39:22", "remaining_time": "1:12:48", "throughput": 1029.75, "total_tokens": 2432944} {"current_steps": 27020, "total_steps": 76960, "loss": 0.2914, "lr": 4.0997480008717596e-05, "epoch": 7.021829521829522, "percentage": 35.11, "elapsed_time": "0:39:23", "remaining_time": "1:12:47", "throughput": 1029.75, "total_tokens": 2433360} {"current_steps": 27025, "total_steps": 76960, "loss": 0.1871, "lr": 4.099312274407048e-05, "epoch": 7.023128898128898, "percentage": 35.12, "elapsed_time": "0:39:23", "remaining_time": "1:12:47", "throughput": 1029.75, "total_tokens": 2433792} {"current_steps": 27030, "total_steps": 76960, "loss": 0.2856, "lr": 4.098876465688175e-05, "epoch": 7.024428274428274, "percentage": 35.12, "elapsed_time": "0:39:23", "remaining_time": "1:12:46", "throughput": 1029.78, "total_tokens": 2434288} {"current_steps": 27035, "total_steps": 76960, "loss": 0.1683, "lr": 4.0984405747375524e-05, "epoch": 7.025727650727651, "percentage": 35.13, "elapsed_time": "0:39:24", "remaining_time": "1:12:46", "throughput": 1029.79, "total_tokens": 2434752} {"current_steps": 27040, "total_steps": 76960, "loss": 0.1524, "lr": 4.0980046015776e-05, "epoch": 7.027027027027027, "percentage": 35.14, "elapsed_time": "0:39:24", "remaining_time": "1:12:45", "throughput": 1029.78, "total_tokens": 2435168} {"current_steps": 27045, "total_steps": 76960, "loss": 0.2114, "lr": 4.097568546230739e-05, "epoch": 7.028326403326403, "percentage": 35.14, "elapsed_time": "0:39:25", "remaining_time": "1:12:45", "throughput": 1029.8, "total_tokens": 2435632} {"current_steps": 27050, "total_steps": 76960, "loss": 0.3144, "lr": 4.0971324087193976e-05, "epoch": 7.029625779625779, "percentage": 35.15, "elapsed_time": "0:39:25", "remaining_time": "1:12:44", "throughput": 1029.81, "total_tokens": 2436096} {"current_steps": 27055, "total_steps": 76960, "loss": 0.2261, "lr": 4.096696189066006e-05, "epoch": 7.030925155925156, "percentage": 35.15, "elapsed_time": "0:39:25", "remaining_time": "1:12:44", "throughput": 1029.82, "total_tokens": 2436544} {"current_steps": 27060, "total_steps": 76960, "loss": 0.293, "lr": 4.096259887293e-05, "epoch": 7.032224532224532, "percentage": 35.16, "elapsed_time": "0:39:26", "remaining_time": "1:12:43", "throughput": 1029.84, "total_tokens": 2437008} {"current_steps": 27065, "total_steps": 76960, "loss": 0.3425, "lr": 4.0958235034228174e-05, "epoch": 7.033523908523908, "percentage": 35.17, "elapsed_time": "0:39:26", "remaining_time": "1:12:43", "throughput": 1029.86, "total_tokens": 2437488} {"current_steps": 27070, "total_steps": 76960, "loss": 0.2607, "lr": 4.095387037477904e-05, "epoch": 7.034823284823285, "percentage": 35.17, "elapsed_time": "0:39:27", "remaining_time": "1:12:42", "throughput": 1029.86, "total_tokens": 2437936} {"current_steps": 27075, "total_steps": 76960, "loss": 0.2305, "lr": 4.094950489480706e-05, "epoch": 7.036122661122661, "percentage": 35.18, "elapsed_time": "0:39:27", "remaining_time": "1:12:42", "throughput": 1029.87, "total_tokens": 2438384} {"current_steps": 27080, "total_steps": 76960, "loss": 0.2745, "lr": 4.094513859453676e-05, "epoch": 7.037422037422037, "percentage": 35.19, "elapsed_time": "0:39:28", "remaining_time": "1:12:41", "throughput": 1029.89, "total_tokens": 2438848} {"current_steps": 27085, "total_steps": 76960, "loss": 0.2907, "lr": 4.094077147419271e-05, "epoch": 7.038721413721413, "percentage": 35.19, "elapsed_time": "0:39:28", "remaining_time": "1:12:41", "throughput": 1029.89, "total_tokens": 2439280} {"current_steps": 27090, "total_steps": 76960, "loss": 0.2038, "lr": 4.093640353399951e-05, "epoch": 7.04002079002079, "percentage": 35.2, "elapsed_time": "0:39:28", "remaining_time": "1:12:40", "throughput": 1029.89, "total_tokens": 2439728} {"current_steps": 27095, "total_steps": 76960, "loss": 0.2193, "lr": 4.0932034774181805e-05, "epoch": 7.041320166320166, "percentage": 35.21, "elapsed_time": "0:39:29", "remaining_time": "1:12:40", "throughput": 1029.92, "total_tokens": 2440224} {"current_steps": 27100, "total_steps": 76960, "loss": 0.2108, "lr": 4.092766519496428e-05, "epoch": 7.042619542619542, "percentage": 35.21, "elapsed_time": "0:39:29", "remaining_time": "1:12:39", "throughput": 1029.93, "total_tokens": 2440688} {"current_steps": 27105, "total_steps": 76960, "loss": 0.3049, "lr": 4.0923294796571676e-05, "epoch": 7.043918918918919, "percentage": 35.22, "elapsed_time": "0:39:30", "remaining_time": "1:12:39", "throughput": 1029.93, "total_tokens": 2441120} {"current_steps": 27110, "total_steps": 76960, "loss": 0.2545, "lr": 4.091892357922877e-05, "epoch": 7.045218295218295, "percentage": 35.23, "elapsed_time": "0:39:30", "remaining_time": "1:12:39", "throughput": 1029.95, "total_tokens": 2441584} {"current_steps": 27115, "total_steps": 76960, "loss": 0.1482, "lr": 4.0914551543160374e-05, "epoch": 7.046517671517671, "percentage": 35.23, "elapsed_time": "0:39:31", "remaining_time": "1:12:38", "throughput": 1029.96, "total_tokens": 2442032} {"current_steps": 27120, "total_steps": 76960, "loss": 0.2708, "lr": 4.0910178688591335e-05, "epoch": 7.047817047817047, "percentage": 35.24, "elapsed_time": "0:39:31", "remaining_time": "1:12:38", "throughput": 1029.98, "total_tokens": 2442512} {"current_steps": 27125, "total_steps": 76960, "loss": 0.2047, "lr": 4.0905805015746564e-05, "epoch": 7.049116424116424, "percentage": 35.25, "elapsed_time": "0:39:31", "remaining_time": "1:12:37", "throughput": 1029.99, "total_tokens": 2442976} {"current_steps": 27130, "total_steps": 76960, "loss": 0.296, "lr": 4.090143052485099e-05, "epoch": 7.0504158004158, "percentage": 35.25, "elapsed_time": "0:39:32", "remaining_time": "1:12:37", "throughput": 1030.0, "total_tokens": 2443424} {"current_steps": 27135, "total_steps": 76960, "loss": 0.3314, "lr": 4.089705521612963e-05, "epoch": 7.0517151767151764, "percentage": 35.26, "elapsed_time": "0:39:32", "remaining_time": "1:12:36", "throughput": 1030.01, "total_tokens": 2443872} {"current_steps": 27140, "total_steps": 76960, "loss": 0.2399, "lr": 4.089267908980747e-05, "epoch": 7.053014553014553, "percentage": 35.27, "elapsed_time": "0:39:33", "remaining_time": "1:12:36", "throughput": 1030.02, "total_tokens": 2444320} {"current_steps": 27145, "total_steps": 76960, "loss": 0.2548, "lr": 4.0888302146109604e-05, "epoch": 7.054313929313929, "percentage": 35.27, "elapsed_time": "0:39:33", "remaining_time": "1:12:35", "throughput": 1030.03, "total_tokens": 2444784} {"current_steps": 27150, "total_steps": 76960, "loss": 0.2597, "lr": 4.0883924385261134e-05, "epoch": 7.0556133056133055, "percentage": 35.28, "elapsed_time": "0:39:33", "remaining_time": "1:12:35", "throughput": 1030.04, "total_tokens": 2445232} {"current_steps": 27155, "total_steps": 76960, "loss": 0.2735, "lr": 4.087954580748722e-05, "epoch": 7.0569126819126815, "percentage": 35.28, "elapsed_time": "0:39:34", "remaining_time": "1:12:34", "throughput": 1030.05, "total_tokens": 2445680} {"current_steps": 27160, "total_steps": 76960, "loss": 0.3058, "lr": 4.087516641301304e-05, "epoch": 7.058212058212058, "percentage": 35.29, "elapsed_time": "0:39:34", "remaining_time": "1:12:34", "throughput": 1030.05, "total_tokens": 2446112} {"current_steps": 27165, "total_steps": 76960, "loss": 0.2981, "lr": 4.0870786202063847e-05, "epoch": 7.0595114345114345, "percentage": 35.3, "elapsed_time": "0:39:35", "remaining_time": "1:12:33", "throughput": 1030.06, "total_tokens": 2446576} {"current_steps": 27170, "total_steps": 76960, "loss": 0.256, "lr": 4.086640517486491e-05, "epoch": 7.0608108108108105, "percentage": 35.3, "elapsed_time": "0:39:35", "remaining_time": "1:12:33", "throughput": 1030.07, "total_tokens": 2447024} {"current_steps": 27175, "total_steps": 76960, "loss": 0.2671, "lr": 4.086202333164155e-05, "epoch": 7.0621101871101875, "percentage": 35.31, "elapsed_time": "0:39:36", "remaining_time": "1:12:32", "throughput": 1030.08, "total_tokens": 2447472} {"current_steps": 27180, "total_steps": 76960, "loss": 0.2715, "lr": 4.085764067261914e-05, "epoch": 7.0634095634095635, "percentage": 35.32, "elapsed_time": "0:39:36", "remaining_time": "1:12:32", "throughput": 1030.11, "total_tokens": 2447968} {"current_steps": 27185, "total_steps": 76960, "loss": 0.2286, "lr": 4.085325719802307e-05, "epoch": 7.0647089397089395, "percentage": 35.32, "elapsed_time": "0:39:36", "remaining_time": "1:12:31", "throughput": 1030.1, "total_tokens": 2448384} {"current_steps": 27190, "total_steps": 76960, "loss": 0.1685, "lr": 4.084887290807879e-05, "epoch": 7.066008316008316, "percentage": 35.33, "elapsed_time": "0:39:37", "remaining_time": "1:12:31", "throughput": 1030.1, "total_tokens": 2448816} {"current_steps": 27195, "total_steps": 76960, "loss": 0.3704, "lr": 4.08444878030118e-05, "epoch": 7.0673076923076925, "percentage": 35.34, "elapsed_time": "0:39:37", "remaining_time": "1:12:30", "throughput": 1030.13, "total_tokens": 2449296} {"current_steps": 27200, "total_steps": 76960, "loss": 0.1664, "lr": 4.084010188304761e-05, "epoch": 7.0686070686070686, "percentage": 35.34, "elapsed_time": "0:39:38", "remaining_time": "1:12:30", "throughput": 1030.13, "total_tokens": 2449728} {"current_steps": 27205, "total_steps": 76960, "loss": 0.2041, "lr": 4.0835715148411814e-05, "epoch": 7.069906444906445, "percentage": 35.35, "elapsed_time": "0:39:38", "remaining_time": "1:12:30", "throughput": 1030.14, "total_tokens": 2450192} {"current_steps": 27210, "total_steps": 76960, "loss": 0.2187, "lr": 4.0831327599330004e-05, "epoch": 7.0712058212058215, "percentage": 35.36, "elapsed_time": "0:39:38", "remaining_time": "1:12:29", "throughput": 1030.14, "total_tokens": 2450624} {"current_steps": 27215, "total_steps": 76960, "loss": 0.2076, "lr": 4.082693923602785e-05, "epoch": 7.072505197505198, "percentage": 35.36, "elapsed_time": "0:39:39", "remaining_time": "1:12:29", "throughput": 1030.14, "total_tokens": 2451056} {"current_steps": 27220, "total_steps": 76960, "loss": 0.3158, "lr": 4.082255005873104e-05, "epoch": 7.073804573804574, "percentage": 35.37, "elapsed_time": "0:39:39", "remaining_time": "1:12:28", "throughput": 1030.16, "total_tokens": 2451520} {"current_steps": 27225, "total_steps": 76960, "loss": 0.2807, "lr": 4.081816006766534e-05, "epoch": 7.07510395010395, "percentage": 35.38, "elapsed_time": "0:39:40", "remaining_time": "1:12:28", "throughput": 1030.17, "total_tokens": 2451984} {"current_steps": 27230, "total_steps": 76960, "loss": 0.2158, "lr": 4.08137692630565e-05, "epoch": 7.076403326403327, "percentage": 35.38, "elapsed_time": "0:39:40", "remaining_time": "1:12:27", "throughput": 1030.17, "total_tokens": 2452400} {"current_steps": 27235, "total_steps": 76960, "loss": 0.1362, "lr": 4.080937764513035e-05, "epoch": 7.077702702702703, "percentage": 35.39, "elapsed_time": "0:39:41", "remaining_time": "1:12:27", "throughput": 1030.17, "total_tokens": 2452832} {"current_steps": 27240, "total_steps": 76960, "loss": 0.1623, "lr": 4.080498521411277e-05, "epoch": 7.079002079002079, "percentage": 35.4, "elapsed_time": "0:39:41", "remaining_time": "1:12:26", "throughput": 1030.17, "total_tokens": 2453264} {"current_steps": 27245, "total_steps": 76960, "loss": 0.1291, "lr": 4.080059197022965e-05, "epoch": 7.080301455301456, "percentage": 35.4, "elapsed_time": "0:39:41", "remaining_time": "1:12:26", "throughput": 1030.18, "total_tokens": 2453728} {"current_steps": 27250, "total_steps": 76960, "loss": 0.1359, "lr": 4.079619791370695e-05, "epoch": 7.081600831600832, "percentage": 35.41, "elapsed_time": "0:39:42", "remaining_time": "1:12:25", "throughput": 1030.21, "total_tokens": 2454208} {"current_steps": 27255, "total_steps": 76960, "loss": 0.7199, "lr": 4.079180304477065e-05, "epoch": 7.082900207900208, "percentage": 35.41, "elapsed_time": "0:39:42", "remaining_time": "1:12:25", "throughput": 1030.21, "total_tokens": 2454640} {"current_steps": 27260, "total_steps": 76960, "loss": 0.2677, "lr": 4.078740736364679e-05, "epoch": 7.084199584199585, "percentage": 35.42, "elapsed_time": "0:39:43", "remaining_time": "1:12:24", "throughput": 1030.22, "total_tokens": 2455104} {"current_steps": 27265, "total_steps": 76960, "loss": 0.3645, "lr": 4.078301087056144e-05, "epoch": 7.085498960498961, "percentage": 35.43, "elapsed_time": "0:39:43", "remaining_time": "1:12:24", "throughput": 1030.25, "total_tokens": 2455600} {"current_steps": 27270, "total_steps": 76960, "loss": 0.2309, "lr": 4.077861356574073e-05, "epoch": 7.086798336798337, "percentage": 35.43, "elapsed_time": "0:39:43", "remaining_time": "1:12:23", "throughput": 1030.24, "total_tokens": 2456016} {"current_steps": 27275, "total_steps": 76960, "loss": 0.2768, "lr": 4.0774215449410794e-05, "epoch": 7.088097713097713, "percentage": 35.44, "elapsed_time": "0:39:44", "remaining_time": "1:12:23", "throughput": 1030.26, "total_tokens": 2456496} {"current_steps": 27280, "total_steps": 76960, "loss": 0.2608, "lr": 4.076981652179785e-05, "epoch": 7.08939708939709, "percentage": 35.45, "elapsed_time": "0:39:44", "remaining_time": "1:12:22", "throughput": 1030.26, "total_tokens": 2456928} {"current_steps": 27285, "total_steps": 76960, "loss": 0.2099, "lr": 4.076541678312813e-05, "epoch": 7.090696465696466, "percentage": 35.45, "elapsed_time": "0:39:45", "remaining_time": "1:12:22", "throughput": 1030.26, "total_tokens": 2457360} {"current_steps": 27290, "total_steps": 76960, "loss": 0.2585, "lr": 4.076101623362791e-05, "epoch": 7.091995841995842, "percentage": 35.46, "elapsed_time": "0:39:45", "remaining_time": "1:12:21", "throughput": 1030.26, "total_tokens": 2457792} {"current_steps": 27295, "total_steps": 76960, "loss": 0.2422, "lr": 4.075661487352354e-05, "epoch": 7.093295218295219, "percentage": 35.47, "elapsed_time": "0:39:46", "remaining_time": "1:12:21", "throughput": 1030.26, "total_tokens": 2458208} {"current_steps": 27300, "total_steps": 76960, "loss": 0.3779, "lr": 4.0752212703041356e-05, "epoch": 7.094594594594595, "percentage": 35.47, "elapsed_time": "0:39:46", "remaining_time": "1:12:21", "throughput": 1030.26, "total_tokens": 2458640} {"current_steps": 27305, "total_steps": 76960, "loss": 0.2996, "lr": 4.074780972240779e-05, "epoch": 7.095893970893971, "percentage": 35.48, "elapsed_time": "0:39:46", "remaining_time": "1:12:20", "throughput": 1030.26, "total_tokens": 2459072} {"current_steps": 27310, "total_steps": 76960, "loss": 0.2678, "lr": 4.074340593184928e-05, "epoch": 7.097193347193347, "percentage": 35.49, "elapsed_time": "0:39:47", "remaining_time": "1:12:20", "throughput": 1030.28, "total_tokens": 2459536} {"current_steps": 27315, "total_steps": 76960, "loss": 0.2568, "lr": 4.073900133159231e-05, "epoch": 7.098492723492724, "percentage": 35.49, "elapsed_time": "0:39:47", "remaining_time": "1:12:19", "throughput": 1030.28, "total_tokens": 2459984} {"current_steps": 27320, "total_steps": 76960, "loss": 0.2607, "lr": 4.073459592186343e-05, "epoch": 7.0997920997921, "percentage": 35.5, "elapsed_time": "0:39:48", "remaining_time": "1:12:19", "throughput": 1030.28, "total_tokens": 2460416} {"current_steps": 27325, "total_steps": 76960, "loss": 0.2622, "lr": 4.0730189702889205e-05, "epoch": 7.101091476091476, "percentage": 35.51, "elapsed_time": "0:39:48", "remaining_time": "1:12:18", "throughput": 1030.29, "total_tokens": 2460864} {"current_steps": 27330, "total_steps": 76960, "loss": 0.2408, "lr": 4.072578267489625e-05, "epoch": 7.102390852390853, "percentage": 35.51, "elapsed_time": "0:39:48", "remaining_time": "1:12:18", "throughput": 1030.3, "total_tokens": 2461312} {"current_steps": 27335, "total_steps": 76960, "loss": 0.2375, "lr": 4.072137483811122e-05, "epoch": 7.103690228690229, "percentage": 35.52, "elapsed_time": "0:39:49", "remaining_time": "1:12:17", "throughput": 1030.31, "total_tokens": 2461776} {"current_steps": 27340, "total_steps": 76960, "loss": 0.1964, "lr": 4.0716966192760816e-05, "epoch": 7.104989604989605, "percentage": 35.52, "elapsed_time": "0:39:49", "remaining_time": "1:12:17", "throughput": 1030.33, "total_tokens": 2462256} {"current_steps": 27345, "total_steps": 76960, "loss": 0.2767, "lr": 4.0712556739071795e-05, "epoch": 7.106288981288981, "percentage": 35.53, "elapsed_time": "0:39:50", "remaining_time": "1:12:16", "throughput": 1030.36, "total_tokens": 2462752} {"current_steps": 27350, "total_steps": 76960, "loss": 0.2481, "lr": 4.0708146477270916e-05, "epoch": 7.107588357588358, "percentage": 35.54, "elapsed_time": "0:39:50", "remaining_time": "1:12:16", "throughput": 1030.38, "total_tokens": 2463216} {"current_steps": 27355, "total_steps": 76960, "loss": 0.2261, "lr": 4.0703735407585014e-05, "epoch": 7.108887733887734, "percentage": 35.54, "elapsed_time": "0:39:51", "remaining_time": "1:12:15", "throughput": 1030.39, "total_tokens": 2463664} {"current_steps": 27360, "total_steps": 76960, "loss": 0.269, "lr": 4.069932353024096e-05, "epoch": 7.11018711018711, "percentage": 35.55, "elapsed_time": "0:39:51", "remaining_time": "1:12:15", "throughput": 1030.41, "total_tokens": 2464144} {"current_steps": 27365, "total_steps": 76960, "loss": 0.3297, "lr": 4.069491084546564e-05, "epoch": 7.111486486486487, "percentage": 35.56, "elapsed_time": "0:39:51", "remaining_time": "1:12:14", "throughput": 1030.42, "total_tokens": 2464608} {"current_steps": 27370, "total_steps": 76960, "loss": 0.3031, "lr": 4.069049735348603e-05, "epoch": 7.112785862785863, "percentage": 35.56, "elapsed_time": "0:39:52", "remaining_time": "1:12:14", "throughput": 1030.42, "total_tokens": 2465040} {"current_steps": 27375, "total_steps": 76960, "loss": 0.2238, "lr": 4.0686083054529105e-05, "epoch": 7.114085239085239, "percentage": 35.57, "elapsed_time": "0:39:52", "remaining_time": "1:12:13", "throughput": 1030.42, "total_tokens": 2465456} {"current_steps": 27380, "total_steps": 76960, "loss": 0.3219, "lr": 4.06816679488219e-05, "epoch": 7.115384615384615, "percentage": 35.58, "elapsed_time": "0:39:53", "remaining_time": "1:12:13", "throughput": 1030.42, "total_tokens": 2465904} {"current_steps": 27385, "total_steps": 76960, "loss": 0.224, "lr": 4.0677252036591484e-05, "epoch": 7.116683991683992, "percentage": 35.58, "elapsed_time": "0:39:53", "remaining_time": "1:12:12", "throughput": 1030.43, "total_tokens": 2466352} {"current_steps": 27390, "total_steps": 76960, "loss": 0.2148, "lr": 4.0672835318064975e-05, "epoch": 7.117983367983368, "percentage": 35.59, "elapsed_time": "0:39:53", "remaining_time": "1:12:12", "throughput": 1030.44, "total_tokens": 2466784} {"current_steps": 27395, "total_steps": 76960, "loss": 0.2532, "lr": 4.066841779346953e-05, "epoch": 7.119282744282744, "percentage": 35.6, "elapsed_time": "0:39:54", "remaining_time": "1:12:12", "throughput": 1030.44, "total_tokens": 2467216} {"current_steps": 27400, "total_steps": 76960, "loss": 0.2183, "lr": 4.0663999463032336e-05, "epoch": 7.120582120582121, "percentage": 35.6, "elapsed_time": "0:39:54", "remaining_time": "1:12:11", "throughput": 1030.44, "total_tokens": 2467648} {"current_steps": 27405, "total_steps": 76960, "loss": 0.21, "lr": 4.065958032698065e-05, "epoch": 7.121881496881497, "percentage": 35.61, "elapsed_time": "0:39:55", "remaining_time": "1:12:11", "throughput": 1030.45, "total_tokens": 2468096} {"current_steps": 27410, "total_steps": 76960, "loss": 0.3246, "lr": 4.065516038554174e-05, "epoch": 7.123180873180873, "percentage": 35.62, "elapsed_time": "0:39:55", "remaining_time": "1:12:10", "throughput": 1030.46, "total_tokens": 2468560} {"current_steps": 27415, "total_steps": 76960, "loss": 0.2687, "lr": 4.065073963894294e-05, "epoch": 7.124480249480249, "percentage": 35.62, "elapsed_time": "0:39:55", "remaining_time": "1:12:10", "throughput": 1030.46, "total_tokens": 2468992} {"current_steps": 27420, "total_steps": 76960, "loss": 0.2889, "lr": 4.064631808741159e-05, "epoch": 7.125779625779626, "percentage": 35.63, "elapsed_time": "0:39:56", "remaining_time": "1:12:09", "throughput": 1030.49, "total_tokens": 2469488} {"current_steps": 27425, "total_steps": 76960, "loss": 0.2484, "lr": 4.064189573117512e-05, "epoch": 7.127079002079002, "percentage": 35.64, "elapsed_time": "0:39:56", "remaining_time": "1:12:09", "throughput": 1030.48, "total_tokens": 2469888} {"current_steps": 27430, "total_steps": 76960, "loss": 0.1451, "lr": 4.063747257046096e-05, "epoch": 7.128378378378378, "percentage": 35.64, "elapsed_time": "0:39:57", "remaining_time": "1:12:08", "throughput": 1030.5, "total_tokens": 2470368} {"current_steps": 27435, "total_steps": 76960, "loss": 0.1312, "lr": 4.06330486054966e-05, "epoch": 7.129677754677755, "percentage": 35.65, "elapsed_time": "0:39:57", "remaining_time": "1:12:08", "throughput": 1030.5, "total_tokens": 2470800} {"current_steps": 27440, "total_steps": 76960, "loss": 0.273, "lr": 4.062862383650958e-05, "epoch": 7.130977130977131, "percentage": 35.65, "elapsed_time": "0:39:58", "remaining_time": "1:12:07", "throughput": 1030.5, "total_tokens": 2471232} {"current_steps": 27445, "total_steps": 76960, "loss": 0.3106, "lr": 4.062419826372746e-05, "epoch": 7.132276507276507, "percentage": 35.66, "elapsed_time": "0:39:58", "remaining_time": "1:12:07", "throughput": 1030.5, "total_tokens": 2471664} {"current_steps": 27450, "total_steps": 76960, "loss": 0.2667, "lr": 4.0619771887377846e-05, "epoch": 7.133575883575883, "percentage": 35.67, "elapsed_time": "0:39:58", "remaining_time": "1:12:06", "throughput": 1030.52, "total_tokens": 2472128} {"current_steps": 27455, "total_steps": 76960, "loss": 0.3019, "lr": 4.061534470768841e-05, "epoch": 7.13487525987526, "percentage": 35.67, "elapsed_time": "0:39:59", "remaining_time": "1:12:06", "throughput": 1030.53, "total_tokens": 2472576} {"current_steps": 27460, "total_steps": 76960, "loss": 0.2716, "lr": 4.061091672488682e-05, "epoch": 7.136174636174636, "percentage": 35.68, "elapsed_time": "0:39:59", "remaining_time": "1:12:05", "throughput": 1030.53, "total_tokens": 2473024} {"current_steps": 27465, "total_steps": 76960, "loss": 0.2602, "lr": 4.0606487939200834e-05, "epoch": 7.137474012474012, "percentage": 35.69, "elapsed_time": "0:40:00", "remaining_time": "1:12:05", "throughput": 1030.55, "total_tokens": 2473488} {"current_steps": 27470, "total_steps": 76960, "loss": 0.3187, "lr": 4.060205835085821e-05, "epoch": 7.138773388773389, "percentage": 35.69, "elapsed_time": "0:40:00", "remaining_time": "1:12:04", "throughput": 1030.54, "total_tokens": 2473920} {"current_steps": 27475, "total_steps": 76960, "loss": 0.1758, "lr": 4.059762796008679e-05, "epoch": 7.140072765072765, "percentage": 35.7, "elapsed_time": "0:40:01", "remaining_time": "1:12:04", "throughput": 1030.55, "total_tokens": 2474384} {"current_steps": 27480, "total_steps": 76960, "loss": 0.2388, "lr": 4.0593196767114405e-05, "epoch": 7.141372141372141, "percentage": 35.71, "elapsed_time": "0:40:01", "remaining_time": "1:12:04", "throughput": 1030.55, "total_tokens": 2474800} {"current_steps": 27485, "total_steps": 76960, "loss": 0.3332, "lr": 4.058876477216898e-05, "epoch": 7.142671517671518, "percentage": 35.71, "elapsed_time": "0:40:01", "remaining_time": "1:12:03", "throughput": 1030.54, "total_tokens": 2475216} {"current_steps": 27490, "total_steps": 76960, "loss": 0.1834, "lr": 4.058433197547844e-05, "epoch": 7.143970893970894, "percentage": 35.72, "elapsed_time": "0:40:02", "remaining_time": "1:12:03", "throughput": 1030.54, "total_tokens": 2475664} {"current_steps": 27495, "total_steps": 76960, "loss": 0.2672, "lr": 4.0579898377270774e-05, "epoch": 7.14527027027027, "percentage": 35.73, "elapsed_time": "0:40:02", "remaining_time": "1:12:02", "throughput": 1030.57, "total_tokens": 2476160} {"current_steps": 27500, "total_steps": 76960, "loss": 0.1746, "lr": 4.057546397777401e-05, "epoch": 7.146569646569646, "percentage": 35.73, "elapsed_time": "0:40:03", "remaining_time": "1:12:02", "throughput": 1030.59, "total_tokens": 2476624} {"current_steps": 27505, "total_steps": 76960, "loss": 0.2021, "lr": 4.0571028777216214e-05, "epoch": 7.147869022869023, "percentage": 35.74, "elapsed_time": "0:40:03", "remaining_time": "1:12:01", "throughput": 1030.6, "total_tokens": 2477088} {"current_steps": 27510, "total_steps": 76960, "loss": 0.272, "lr": 4.0566592775825486e-05, "epoch": 7.149168399168399, "percentage": 35.75, "elapsed_time": "0:40:03", "remaining_time": "1:12:01", "throughput": 1030.61, "total_tokens": 2477536} {"current_steps": 27515, "total_steps": 76960, "loss": 0.2359, "lr": 4.056215597382997e-05, "epoch": 7.150467775467775, "percentage": 35.75, "elapsed_time": "0:40:04", "remaining_time": "1:12:00", "throughput": 1030.62, "total_tokens": 2478000} {"current_steps": 27520, "total_steps": 76960, "loss": 0.0997, "lr": 4.055771837145787e-05, "epoch": 7.151767151767152, "percentage": 35.76, "elapsed_time": "0:40:04", "remaining_time": "1:12:00", "throughput": 1030.62, "total_tokens": 2478432} {"current_steps": 27525, "total_steps": 76960, "loss": 0.2856, "lr": 4.05532799689374e-05, "epoch": 7.153066528066528, "percentage": 35.77, "elapsed_time": "0:40:05", "remaining_time": "1:11:59", "throughput": 1030.63, "total_tokens": 2478880} {"current_steps": 27530, "total_steps": 76960, "loss": 0.2017, "lr": 4.054884076649684e-05, "epoch": 7.154365904365904, "percentage": 35.77, "elapsed_time": "0:40:05", "remaining_time": "1:11:59", "throughput": 1030.64, "total_tokens": 2479344} {"current_steps": 27535, "total_steps": 76960, "loss": 0.148, "lr": 4.054440076436451e-05, "epoch": 7.15566528066528, "percentage": 35.78, "elapsed_time": "0:40:06", "remaining_time": "1:11:58", "throughput": 1030.67, "total_tokens": 2479824} {"current_steps": 27540, "total_steps": 76960, "loss": 0.2812, "lr": 4.053995996276875e-05, "epoch": 7.156964656964657, "percentage": 35.78, "elapsed_time": "0:40:06", "remaining_time": "1:11:58", "throughput": 1030.67, "total_tokens": 2480256} {"current_steps": 27545, "total_steps": 76960, "loss": 0.1464, "lr": 4.053551836193795e-05, "epoch": 7.158264033264033, "percentage": 35.79, "elapsed_time": "0:40:06", "remaining_time": "1:11:57", "throughput": 1030.68, "total_tokens": 2480720} {"current_steps": 27550, "total_steps": 76960, "loss": 0.2135, "lr": 4.0531075962100564e-05, "epoch": 7.159563409563409, "percentage": 35.8, "elapsed_time": "0:40:07", "remaining_time": "1:11:57", "throughput": 1030.69, "total_tokens": 2481168} {"current_steps": 27555, "total_steps": 76960, "loss": 0.2362, "lr": 4.052663276348506e-05, "epoch": 7.160862785862786, "percentage": 35.8, "elapsed_time": "0:40:07", "remaining_time": "1:11:56", "throughput": 1030.7, "total_tokens": 2481632} {"current_steps": 27560, "total_steps": 76960, "loss": 0.2299, "lr": 4.0522188766319954e-05, "epoch": 7.162162162162162, "percentage": 35.81, "elapsed_time": "0:40:08", "remaining_time": "1:11:56", "throughput": 1030.71, "total_tokens": 2482080} {"current_steps": 27565, "total_steps": 76960, "loss": 0.26, "lr": 4.051774397083381e-05, "epoch": 7.163461538461538, "percentage": 35.82, "elapsed_time": "0:40:08", "remaining_time": "1:11:55", "throughput": 1030.71, "total_tokens": 2482496} {"current_steps": 27570, "total_steps": 76960, "loss": 0.2538, "lr": 4.0513298377255225e-05, "epoch": 7.164760914760914, "percentage": 35.82, "elapsed_time": "0:40:08", "remaining_time": "1:11:55", "throughput": 1030.71, "total_tokens": 2482928} {"current_steps": 27575, "total_steps": 76960, "loss": 0.1934, "lr": 4.050885198581283e-05, "epoch": 7.166060291060291, "percentage": 35.83, "elapsed_time": "0:40:09", "remaining_time": "1:11:55", "throughput": 1030.72, "total_tokens": 2483376} {"current_steps": 27580, "total_steps": 76960, "loss": 0.3698, "lr": 4.050440479673533e-05, "epoch": 7.167359667359667, "percentage": 35.84, "elapsed_time": "0:40:09", "remaining_time": "1:11:54", "throughput": 1030.72, "total_tokens": 2483808} {"current_steps": 27585, "total_steps": 76960, "loss": 0.2836, "lr": 4.049995681025143e-05, "epoch": 7.168659043659043, "percentage": 35.84, "elapsed_time": "0:40:10", "remaining_time": "1:11:54", "throughput": 1030.72, "total_tokens": 2484256} {"current_steps": 27590, "total_steps": 76960, "loss": 0.2887, "lr": 4.04955080265899e-05, "epoch": 7.16995841995842, "percentage": 35.85, "elapsed_time": "0:40:10", "remaining_time": "1:11:53", "throughput": 1030.74, "total_tokens": 2484720} {"current_steps": 27595, "total_steps": 76960, "loss": 0.2927, "lr": 4.0491058445979545e-05, "epoch": 7.171257796257796, "percentage": 35.86, "elapsed_time": "0:40:11", "remaining_time": "1:11:53", "throughput": 1030.74, "total_tokens": 2485152} {"current_steps": 27600, "total_steps": 76960, "loss": 0.2558, "lr": 4.0486608068649217e-05, "epoch": 7.172557172557172, "percentage": 35.86, "elapsed_time": "0:40:11", "remaining_time": "1:11:52", "throughput": 1030.73, "total_tokens": 2485568} {"current_steps": 27605, "total_steps": 76960, "loss": 0.3015, "lr": 4.0482156894827794e-05, "epoch": 7.173856548856548, "percentage": 35.87, "elapsed_time": "0:40:11", "remaining_time": "1:11:52", "throughput": 1030.76, "total_tokens": 2486064} {"current_steps": 27610, "total_steps": 76960, "loss": 0.3042, "lr": 4.0477704924744207e-05, "epoch": 7.175155925155925, "percentage": 35.88, "elapsed_time": "0:40:12", "remaining_time": "1:11:51", "throughput": 1030.75, "total_tokens": 2486480} {"current_steps": 27615, "total_steps": 76960, "loss": 0.2066, "lr": 4.047325215862743e-05, "epoch": 7.176455301455301, "percentage": 35.88, "elapsed_time": "0:40:12", "remaining_time": "1:11:51", "throughput": 1030.75, "total_tokens": 2486896} {"current_steps": 27620, "total_steps": 76960, "loss": 0.2446, "lr": 4.046879859670646e-05, "epoch": 7.1777546777546775, "percentage": 35.89, "elapsed_time": "0:40:13", "remaining_time": "1:11:50", "throughput": 1030.76, "total_tokens": 2487344} {"current_steps": 27625, "total_steps": 76960, "loss": 0.2699, "lr": 4.046434423921036e-05, "epoch": 7.179054054054054, "percentage": 35.9, "elapsed_time": "0:40:13", "remaining_time": "1:11:50", "throughput": 1030.75, "total_tokens": 2487760} {"current_steps": 27630, "total_steps": 76960, "loss": 0.1691, "lr": 4.045988908636822e-05, "epoch": 7.18035343035343, "percentage": 35.9, "elapsed_time": "0:40:13", "remaining_time": "1:11:49", "throughput": 1030.75, "total_tokens": 2488192} {"current_steps": 27635, "total_steps": 76960, "loss": 0.1391, "lr": 4.045543313840917e-05, "epoch": 7.1816528066528065, "percentage": 35.91, "elapsed_time": "0:40:14", "remaining_time": "1:11:49", "throughput": 1030.78, "total_tokens": 2488688} {"current_steps": 27640, "total_steps": 76960, "loss": 0.2602, "lr": 4.045097639556239e-05, "epoch": 7.182952182952183, "percentage": 35.91, "elapsed_time": "0:40:14", "remaining_time": "1:11:48", "throughput": 1030.79, "total_tokens": 2489152} {"current_steps": 27645, "total_steps": 76960, "loss": 0.2203, "lr": 4.0446518858057083e-05, "epoch": 7.1842515592515594, "percentage": 35.92, "elapsed_time": "0:40:15", "remaining_time": "1:11:48", "throughput": 1030.79, "total_tokens": 2489568} {"current_steps": 27650, "total_steps": 76960, "loss": 0.4037, "lr": 4.0442060526122515e-05, "epoch": 7.1855509355509355, "percentage": 35.93, "elapsed_time": "0:40:15", "remaining_time": "1:11:47", "throughput": 1030.8, "total_tokens": 2490032} {"current_steps": 27655, "total_steps": 76960, "loss": 0.3147, "lr": 4.043760139998798e-05, "epoch": 7.1868503118503115, "percentage": 35.93, "elapsed_time": "0:40:16", "remaining_time": "1:11:47", "throughput": 1030.8, "total_tokens": 2490464} {"current_steps": 27660, "total_steps": 76960, "loss": 0.328, "lr": 4.0433141479882806e-05, "epoch": 7.1881496881496885, "percentage": 35.94, "elapsed_time": "0:40:16", "remaining_time": "1:11:47", "throughput": 1030.81, "total_tokens": 2490928} {"current_steps": 27665, "total_steps": 76960, "loss": 0.2831, "lr": 4.0428680766036384e-05, "epoch": 7.1894490644490645, "percentage": 35.95, "elapsed_time": "0:40:16", "remaining_time": "1:11:46", "throughput": 1030.82, "total_tokens": 2491376} {"current_steps": 27670, "total_steps": 76960, "loss": 0.2969, "lr": 4.0424219258678126e-05, "epoch": 7.1907484407484406, "percentage": 35.95, "elapsed_time": "0:40:17", "remaining_time": "1:11:46", "throughput": 1030.82, "total_tokens": 2491808} {"current_steps": 27675, "total_steps": 76960, "loss": 0.2529, "lr": 4.041975695803749e-05, "epoch": 7.192047817047817, "percentage": 35.96, "elapsed_time": "0:40:17", "remaining_time": "1:11:45", "throughput": 1030.82, "total_tokens": 2492224} {"current_steps": 27680, "total_steps": 76960, "loss": 0.2376, "lr": 4.041529386434398e-05, "epoch": 7.1933471933471935, "percentage": 35.97, "elapsed_time": "0:40:18", "remaining_time": "1:11:45", "throughput": 1030.81, "total_tokens": 2492640} {"current_steps": 27685, "total_steps": 76960, "loss": 0.2909, "lr": 4.0410829977827135e-05, "epoch": 7.19464656964657, "percentage": 35.97, "elapsed_time": "0:40:18", "remaining_time": "1:11:44", "throughput": 1030.82, "total_tokens": 2493088} {"current_steps": 27690, "total_steps": 76960, "loss": 0.2394, "lr": 4.040636529871654e-05, "epoch": 7.195945945945946, "percentage": 35.98, "elapsed_time": "0:40:18", "remaining_time": "1:11:44", "throughput": 1030.82, "total_tokens": 2493520} {"current_steps": 27695, "total_steps": 76960, "loss": 0.2307, "lr": 4.040189982724182e-05, "epoch": 7.1972453222453225, "percentage": 35.99, "elapsed_time": "0:40:19", "remaining_time": "1:11:43", "throughput": 1030.82, "total_tokens": 2493936} {"current_steps": 27700, "total_steps": 76960, "loss": 0.1741, "lr": 4.0397433563632634e-05, "epoch": 7.198544698544699, "percentage": 35.99, "elapsed_time": "0:40:19", "remaining_time": "1:11:43", "throughput": 1030.81, "total_tokens": 2494352} {"current_steps": 27705, "total_steps": 76960, "loss": 0.2732, "lr": 4.039296650811869e-05, "epoch": 7.199844074844075, "percentage": 36.0, "elapsed_time": "0:40:20", "remaining_time": "1:11:42", "throughput": 1030.81, "total_tokens": 2494784} {"current_steps": 27710, "total_steps": 76960, "loss": 0.251, "lr": 4.038849866092972e-05, "epoch": 7.201143451143452, "percentage": 36.01, "elapsed_time": "0:40:20", "remaining_time": "1:11:42", "throughput": 1030.82, "total_tokens": 2495216} {"current_steps": 27715, "total_steps": 76960, "loss": 0.2546, "lr": 4.038403002229553e-05, "epoch": 7.202442827442828, "percentage": 36.01, "elapsed_time": "0:40:21", "remaining_time": "1:11:41", "throughput": 1030.83, "total_tokens": 2495680} {"current_steps": 27720, "total_steps": 76960, "loss": 0.2991, "lr": 4.037956059244592e-05, "epoch": 7.203742203742204, "percentage": 36.02, "elapsed_time": "0:40:21", "remaining_time": "1:11:41", "throughput": 1030.84, "total_tokens": 2496144} {"current_steps": 27725, "total_steps": 76960, "loss": 0.1264, "lr": 4.037509037161079e-05, "epoch": 7.20504158004158, "percentage": 36.03, "elapsed_time": "0:40:21", "remaining_time": "1:11:40", "throughput": 1030.84, "total_tokens": 2496560} {"current_steps": 27730, "total_steps": 76960, "loss": 0.3347, "lr": 4.037061936002002e-05, "epoch": 7.206340956340957, "percentage": 36.03, "elapsed_time": "0:40:22", "remaining_time": "1:11:40", "throughput": 1030.86, "total_tokens": 2497040} {"current_steps": 27735, "total_steps": 76960, "loss": 0.2257, "lr": 4.0366147557903565e-05, "epoch": 7.207640332640333, "percentage": 36.04, "elapsed_time": "0:40:22", "remaining_time": "1:11:39", "throughput": 1030.87, "total_tokens": 2497488} {"current_steps": 27740, "total_steps": 76960, "loss": 0.1886, "lr": 4.0361674965491426e-05, "epoch": 7.208939708939709, "percentage": 36.04, "elapsed_time": "0:40:23", "remaining_time": "1:11:39", "throughput": 1030.89, "total_tokens": 2497968} {"current_steps": 27745, "total_steps": 76960, "loss": 0.1979, "lr": 4.035720158301363e-05, "epoch": 7.210239085239086, "percentage": 36.05, "elapsed_time": "0:40:23", "remaining_time": "1:11:38", "throughput": 1030.9, "total_tokens": 2498432} {"current_steps": 27750, "total_steps": 76960, "loss": 0.2161, "lr": 4.035272741070023e-05, "epoch": 7.211538461538462, "percentage": 36.06, "elapsed_time": "0:40:23", "remaining_time": "1:11:38", "throughput": 1030.9, "total_tokens": 2498864} {"current_steps": 27755, "total_steps": 76960, "loss": 0.1983, "lr": 4.0348252448781356e-05, "epoch": 7.212837837837838, "percentage": 36.06, "elapsed_time": "0:40:24", "remaining_time": "1:11:38", "throughput": 1030.91, "total_tokens": 2499312} {"current_steps": 27760, "total_steps": 76960, "loss": 0.3258, "lr": 4.0343776697487145e-05, "epoch": 7.214137214137214, "percentage": 36.07, "elapsed_time": "0:40:24", "remaining_time": "1:11:37", "throughput": 1030.92, "total_tokens": 2499760} {"current_steps": 27765, "total_steps": 76960, "loss": 0.2158, "lr": 4.0339300157047805e-05, "epoch": 7.215436590436591, "percentage": 36.08, "elapsed_time": "0:40:25", "remaining_time": "1:11:37", "throughput": 1030.93, "total_tokens": 2500224} {"current_steps": 27770, "total_steps": 76960, "loss": 0.3131, "lr": 4.0334822827693565e-05, "epoch": 7.216735966735967, "percentage": 36.08, "elapsed_time": "0:40:25", "remaining_time": "1:11:36", "throughput": 1030.95, "total_tokens": 2500688} {"current_steps": 27775, "total_steps": 76960, "loss": 0.2538, "lr": 4.033034470965468e-05, "epoch": 7.218035343035343, "percentage": 36.09, "elapsed_time": "0:40:26", "remaining_time": "1:11:36", "throughput": 1030.95, "total_tokens": 2501120} {"current_steps": 27780, "total_steps": 76960, "loss": 0.3655, "lr": 4.032586580316149e-05, "epoch": 7.21933471933472, "percentage": 36.1, "elapsed_time": "0:40:26", "remaining_time": "1:11:35", "throughput": 1030.94, "total_tokens": 2501536} {"current_steps": 27785, "total_steps": 76960, "loss": 0.2008, "lr": 4.0321386108444325e-05, "epoch": 7.220634095634096, "percentage": 36.1, "elapsed_time": "0:40:26", "remaining_time": "1:11:35", "throughput": 1030.96, "total_tokens": 2502000} {"current_steps": 27790, "total_steps": 76960, "loss": 0.2164, "lr": 4.03169056257336e-05, "epoch": 7.221933471933472, "percentage": 36.11, "elapsed_time": "0:40:27", "remaining_time": "1:11:34", "throughput": 1030.96, "total_tokens": 2502432} {"current_steps": 27795, "total_steps": 76960, "loss": 0.2098, "lr": 4.031242435525974e-05, "epoch": 7.223232848232848, "percentage": 36.12, "elapsed_time": "0:40:27", "remaining_time": "1:11:34", "throughput": 1030.95, "total_tokens": 2502848} {"current_steps": 27800, "total_steps": 76960, "loss": 0.2435, "lr": 4.0307942297253225e-05, "epoch": 7.224532224532225, "percentage": 36.12, "elapsed_time": "0:40:28", "remaining_time": "1:11:33", "throughput": 1030.95, "total_tokens": 2503280} {"current_steps": 27805, "total_steps": 76960, "loss": 0.2952, "lr": 4.030345945194457e-05, "epoch": 7.225831600831601, "percentage": 36.13, "elapsed_time": "0:40:28", "remaining_time": "1:11:33", "throughput": 1030.94, "total_tokens": 2503696} {"current_steps": 27810, "total_steps": 76960, "loss": 0.2917, "lr": 4.029897581956433e-05, "epoch": 7.227130977130977, "percentage": 36.14, "elapsed_time": "0:40:28", "remaining_time": "1:11:32", "throughput": 1030.95, "total_tokens": 2504144} {"current_steps": 27815, "total_steps": 76960, "loss": 0.2827, "lr": 4.0294491400343116e-05, "epoch": 7.228430353430354, "percentage": 36.14, "elapsed_time": "0:40:29", "remaining_time": "1:11:32", "throughput": 1030.97, "total_tokens": 2504608} {"current_steps": 27820, "total_steps": 76960, "loss": 0.2856, "lr": 4.029000619451154e-05, "epoch": 7.22972972972973, "percentage": 36.15, "elapsed_time": "0:40:29", "remaining_time": "1:11:31", "throughput": 1031.0, "total_tokens": 2505120} {"current_steps": 27825, "total_steps": 76960, "loss": 0.2517, "lr": 4.028552020230031e-05, "epoch": 7.231029106029106, "percentage": 36.16, "elapsed_time": "0:40:30", "remaining_time": "1:11:31", "throughput": 1031.0, "total_tokens": 2505552} {"current_steps": 27830, "total_steps": 76960, "loss": 0.2273, "lr": 4.028103342394012e-05, "epoch": 7.232328482328482, "percentage": 36.16, "elapsed_time": "0:40:30", "remaining_time": "1:11:30", "throughput": 1031.0, "total_tokens": 2505984} {"current_steps": 27835, "total_steps": 76960, "loss": 0.1749, "lr": 4.0276545859661744e-05, "epoch": 7.233627858627859, "percentage": 36.17, "elapsed_time": "0:40:31", "remaining_time": "1:11:30", "throughput": 1030.98, "total_tokens": 2506384} {"current_steps": 27840, "total_steps": 76960, "loss": 0.3109, "lr": 4.027205750969597e-05, "epoch": 7.234927234927235, "percentage": 36.17, "elapsed_time": "0:40:31", "remaining_time": "1:11:30", "throughput": 1031.0, "total_tokens": 2506848} {"current_steps": 27845, "total_steps": 76960, "loss": 0.2562, "lr": 4.0267568374273644e-05, "epoch": 7.236226611226611, "percentage": 36.18, "elapsed_time": "0:40:31", "remaining_time": "1:11:29", "throughput": 1031.01, "total_tokens": 2507296} {"current_steps": 27850, "total_steps": 76960, "loss": 0.2213, "lr": 4.026307845362566e-05, "epoch": 7.237525987525988, "percentage": 36.19, "elapsed_time": "0:40:32", "remaining_time": "1:11:29", "throughput": 1031.02, "total_tokens": 2507760} {"current_steps": 27855, "total_steps": 76960, "loss": 0.1738, "lr": 4.025858774798292e-05, "epoch": 7.238825363825364, "percentage": 36.19, "elapsed_time": "0:40:32", "remaining_time": "1:11:28", "throughput": 1031.02, "total_tokens": 2508176} {"current_steps": 27860, "total_steps": 76960, "loss": 0.2443, "lr": 4.025409625757639e-05, "epoch": 7.24012474012474, "percentage": 36.2, "elapsed_time": "0:40:33", "remaining_time": "1:11:28", "throughput": 1031.04, "total_tokens": 2508656} {"current_steps": 27865, "total_steps": 76960, "loss": 0.2844, "lr": 4.024960398263708e-05, "epoch": 7.241424116424117, "percentage": 36.21, "elapsed_time": "0:40:33", "remaining_time": "1:11:27", "throughput": 1031.04, "total_tokens": 2509104} {"current_steps": 27870, "total_steps": 76960, "loss": 0.2766, "lr": 4.024511092339602e-05, "epoch": 7.242723492723493, "percentage": 36.21, "elapsed_time": "0:40:33", "remaining_time": "1:11:27", "throughput": 1031.06, "total_tokens": 2509568} {"current_steps": 27875, "total_steps": 76960, "loss": 0.1678, "lr": 4.02406170800843e-05, "epoch": 7.244022869022869, "percentage": 36.22, "elapsed_time": "0:40:34", "remaining_time": "1:11:26", "throughput": 1031.07, "total_tokens": 2510032} {"current_steps": 27880, "total_steps": 76960, "loss": 0.1666, "lr": 4.023612245293304e-05, "epoch": 7.245322245322245, "percentage": 36.23, "elapsed_time": "0:40:34", "remaining_time": "1:11:26", "throughput": 1031.07, "total_tokens": 2510464} {"current_steps": 27885, "total_steps": 76960, "loss": 0.1488, "lr": 4.02316270421734e-05, "epoch": 7.246621621621622, "percentage": 36.23, "elapsed_time": "0:40:35", "remaining_time": "1:11:25", "throughput": 1031.08, "total_tokens": 2510912} {"current_steps": 27890, "total_steps": 76960, "loss": 0.2583, "lr": 4.0227130848036595e-05, "epoch": 7.247920997920998, "percentage": 36.24, "elapsed_time": "0:40:35", "remaining_time": "1:11:25", "throughput": 1031.09, "total_tokens": 2511360} {"current_steps": 27895, "total_steps": 76960, "loss": 0.2214, "lr": 4.0222633870753855e-05, "epoch": 7.249220374220374, "percentage": 36.25, "elapsed_time": "0:40:36", "remaining_time": "1:11:24", "throughput": 1031.09, "total_tokens": 2511792} {"current_steps": 27900, "total_steps": 76960, "loss": 0.2522, "lr": 4.0218136110556474e-05, "epoch": 7.25051975051975, "percentage": 36.25, "elapsed_time": "0:40:36", "remaining_time": "1:11:24", "throughput": 1031.11, "total_tokens": 2512272} {"current_steps": 27905, "total_steps": 76960, "loss": 0.1653, "lr": 4.0213637567675774e-05, "epoch": 7.251819126819127, "percentage": 36.26, "elapsed_time": "0:40:36", "remaining_time": "1:11:23", "throughput": 1031.12, "total_tokens": 2512720} {"current_steps": 27910, "total_steps": 76960, "loss": 0.1293, "lr": 4.0209138242343104e-05, "epoch": 7.253118503118503, "percentage": 36.27, "elapsed_time": "0:40:37", "remaining_time": "1:11:23", "throughput": 1031.12, "total_tokens": 2513168} {"current_steps": 27915, "total_steps": 76960, "loss": 0.3695, "lr": 4.020463813478989e-05, "epoch": 7.254417879417879, "percentage": 36.27, "elapsed_time": "0:40:37", "remaining_time": "1:11:22", "throughput": 1031.12, "total_tokens": 2513584} {"current_steps": 27920, "total_steps": 76960, "loss": 0.2788, "lr": 4.020013724524757e-05, "epoch": 7.255717255717256, "percentage": 36.28, "elapsed_time": "0:40:38", "remaining_time": "1:11:22", "throughput": 1031.13, "total_tokens": 2514048} {"current_steps": 27925, "total_steps": 76960, "loss": 0.2546, "lr": 4.019563557394762e-05, "epoch": 7.257016632016632, "percentage": 36.29, "elapsed_time": "0:40:38", "remaining_time": "1:11:21", "throughput": 1031.14, "total_tokens": 2514496} {"current_steps": 27930, "total_steps": 76960, "loss": 0.2387, "lr": 4.0191133121121584e-05, "epoch": 7.258316008316008, "percentage": 36.29, "elapsed_time": "0:40:38", "remaining_time": "1:11:21", "throughput": 1031.15, "total_tokens": 2514944} {"current_steps": 27935, "total_steps": 76960, "loss": 0.3206, "lr": 4.0186629887001e-05, "epoch": 7.259615384615385, "percentage": 36.3, "elapsed_time": "0:40:39", "remaining_time": "1:11:21", "throughput": 1031.16, "total_tokens": 2515392} {"current_steps": 27940, "total_steps": 76960, "loss": 0.2894, "lr": 4.018212587181751e-05, "epoch": 7.260914760914761, "percentage": 36.3, "elapsed_time": "0:40:39", "remaining_time": "1:11:20", "throughput": 1031.15, "total_tokens": 2515808} {"current_steps": 27945, "total_steps": 76960, "loss": 0.2807, "lr": 4.0177621075802724e-05, "epoch": 7.262214137214137, "percentage": 36.31, "elapsed_time": "0:40:40", "remaining_time": "1:11:20", "throughput": 1031.16, "total_tokens": 2516272} {"current_steps": 27950, "total_steps": 76960, "loss": 0.279, "lr": 4.0173115499188355e-05, "epoch": 7.263513513513513, "percentage": 36.32, "elapsed_time": "0:40:40", "remaining_time": "1:11:19", "throughput": 1031.17, "total_tokens": 2516720} {"current_steps": 27955, "total_steps": 76960, "loss": 0.2805, "lr": 4.01686091422061e-05, "epoch": 7.26481288981289, "percentage": 36.32, "elapsed_time": "0:40:41", "remaining_time": "1:11:19", "throughput": 1031.19, "total_tokens": 2517184} {"current_steps": 27960, "total_steps": 76960, "loss": 0.2633, "lr": 4.016410200508776e-05, "epoch": 7.266112266112266, "percentage": 36.33, "elapsed_time": "0:40:41", "remaining_time": "1:11:18", "throughput": 1031.19, "total_tokens": 2517616} {"current_steps": 27965, "total_steps": 76960, "loss": 0.249, "lr": 4.0159594088065126e-05, "epoch": 7.267411642411642, "percentage": 36.34, "elapsed_time": "0:40:41", "remaining_time": "1:11:18", "throughput": 1031.18, "total_tokens": 2518032} {"current_steps": 27970, "total_steps": 76960, "loss": 0.2773, "lr": 4.015508539137003e-05, "epoch": 7.268711018711019, "percentage": 36.34, "elapsed_time": "0:40:42", "remaining_time": "1:11:17", "throughput": 1031.18, "total_tokens": 2518464} {"current_steps": 27975, "total_steps": 76960, "loss": 0.2215, "lr": 4.015057591523438e-05, "epoch": 7.270010395010395, "percentage": 36.35, "elapsed_time": "0:40:42", "remaining_time": "1:11:17", "throughput": 1031.19, "total_tokens": 2518912} {"current_steps": 27980, "total_steps": 76960, "loss": 0.1955, "lr": 4.014606565989009e-05, "epoch": 7.271309771309771, "percentage": 36.36, "elapsed_time": "0:40:43", "remaining_time": "1:11:16", "throughput": 1031.2, "total_tokens": 2519376} {"current_steps": 27985, "total_steps": 76960, "loss": 0.3761, "lr": 4.0141554625569125e-05, "epoch": 7.272609147609147, "percentage": 36.36, "elapsed_time": "0:40:43", "remaining_time": "1:11:16", "throughput": 1031.2, "total_tokens": 2519792} {"current_steps": 27990, "total_steps": 76960, "loss": 0.3514, "lr": 4.013704281250351e-05, "epoch": 7.273908523908524, "percentage": 36.37, "elapsed_time": "0:40:43", "remaining_time": "1:11:15", "throughput": 1031.23, "total_tokens": 2520288} {"current_steps": 27995, "total_steps": 76960, "loss": 0.2588, "lr": 4.0132530220925266e-05, "epoch": 7.2752079002079, "percentage": 36.38, "elapsed_time": "0:40:44", "remaining_time": "1:11:15", "throughput": 1031.24, "total_tokens": 2520752} {"current_steps": 28000, "total_steps": 76960, "loss": 0.1821, "lr": 4.012801685106651e-05, "epoch": 7.276507276507276, "percentage": 36.38, "elapsed_time": "0:40:44", "remaining_time": "1:11:14", "throughput": 1031.24, "total_tokens": 2521184} {"current_steps": 28005, "total_steps": 76960, "loss": 0.1757, "lr": 4.012350270315934e-05, "epoch": 7.277806652806653, "percentage": 36.39, "elapsed_time": "0:40:45", "remaining_time": "1:11:14", "throughput": 1031.25, "total_tokens": 2521648} {"current_steps": 28010, "total_steps": 76960, "loss": 0.1217, "lr": 4.011898777743594e-05, "epoch": 7.279106029106029, "percentage": 36.4, "elapsed_time": "0:40:45", "remaining_time": "1:11:13", "throughput": 1031.25, "total_tokens": 2522080} {"current_steps": 28015, "total_steps": 76960, "loss": 0.1414, "lr": 4.011447207412851e-05, "epoch": 7.280405405405405, "percentage": 36.4, "elapsed_time": "0:40:46", "remaining_time": "1:11:13", "throughput": 1031.27, "total_tokens": 2522544} {"current_steps": 28020, "total_steps": 76960, "loss": 0.2288, "lr": 4.01099555934693e-05, "epoch": 7.281704781704781, "percentage": 36.41, "elapsed_time": "0:40:46", "remaining_time": "1:11:13", "throughput": 1031.28, "total_tokens": 2523008} {"current_steps": 28025, "total_steps": 76960, "loss": 0.4001, "lr": 4.0105438335690597e-05, "epoch": 7.283004158004158, "percentage": 36.42, "elapsed_time": "0:40:46", "remaining_time": "1:11:12", "throughput": 1031.28, "total_tokens": 2523440} {"current_steps": 28030, "total_steps": 76960, "loss": 0.2992, "lr": 4.010092030102473e-05, "epoch": 7.284303534303534, "percentage": 36.42, "elapsed_time": "0:40:47", "remaining_time": "1:11:12", "throughput": 1031.28, "total_tokens": 2523856} {"current_steps": 28035, "total_steps": 76960, "loss": 0.217, "lr": 4.009640148970406e-05, "epoch": 7.28560291060291, "percentage": 36.43, "elapsed_time": "0:40:47", "remaining_time": "1:11:11", "throughput": 1031.28, "total_tokens": 2524304} {"current_steps": 28040, "total_steps": 76960, "loss": 0.3153, "lr": 4.0091881901961e-05, "epoch": 7.286902286902287, "percentage": 36.43, "elapsed_time": "0:40:48", "remaining_time": "1:11:11", "throughput": 1031.29, "total_tokens": 2524752} {"current_steps": 28045, "total_steps": 76960, "loss": 0.2853, "lr": 4.008736153802799e-05, "epoch": 7.288201663201663, "percentage": 36.44, "elapsed_time": "0:40:48", "remaining_time": "1:11:10", "throughput": 1031.29, "total_tokens": 2525184} {"current_steps": 28050, "total_steps": 76960, "loss": 0.299, "lr": 4.0082840398137514e-05, "epoch": 7.289501039501039, "percentage": 36.45, "elapsed_time": "0:40:48", "remaining_time": "1:11:10", "throughput": 1031.3, "total_tokens": 2525632} {"current_steps": 28055, "total_steps": 76960, "loss": 0.2908, "lr": 4.007831848252211e-05, "epoch": 7.290800415800415, "percentage": 36.45, "elapsed_time": "0:40:49", "remaining_time": "1:11:09", "throughput": 1031.31, "total_tokens": 2526080} {"current_steps": 28060, "total_steps": 76960, "loss": 0.2618, "lr": 4.007379579141434e-05, "epoch": 7.292099792099792, "percentage": 36.46, "elapsed_time": "0:40:49", "remaining_time": "1:11:09", "throughput": 1031.32, "total_tokens": 2526528} {"current_steps": 28065, "total_steps": 76960, "loss": 0.2811, "lr": 4.0069272325046816e-05, "epoch": 7.293399168399168, "percentage": 36.47, "elapsed_time": "0:40:50", "remaining_time": "1:11:08", "throughput": 1031.32, "total_tokens": 2526960} {"current_steps": 28070, "total_steps": 76960, "loss": 0.2571, "lr": 4.006474808365217e-05, "epoch": 7.294698544698544, "percentage": 36.47, "elapsed_time": "0:40:50", "remaining_time": "1:11:08", "throughput": 1031.32, "total_tokens": 2527392} {"current_steps": 28075, "total_steps": 76960, "loss": 0.3215, "lr": 4.0060223067463094e-05, "epoch": 7.295997920997921, "percentage": 36.48, "elapsed_time": "0:40:51", "remaining_time": "1:11:07", "throughput": 1031.32, "total_tokens": 2527824} {"current_steps": 28080, "total_steps": 76960, "loss": 0.2761, "lr": 4.005569727671231e-05, "epoch": 7.297297297297297, "percentage": 36.49, "elapsed_time": "0:40:51", "remaining_time": "1:11:07", "throughput": 1031.33, "total_tokens": 2528272} {"current_steps": 28085, "total_steps": 76960, "loss": 0.2526, "lr": 4.00511707116326e-05, "epoch": 7.298596673596673, "percentage": 36.49, "elapsed_time": "0:40:51", "remaining_time": "1:11:06", "throughput": 1031.32, "total_tokens": 2528688} {"current_steps": 28090, "total_steps": 76960, "loss": 0.2375, "lr": 4.004664337245676e-05, "epoch": 7.29989604989605, "percentage": 36.5, "elapsed_time": "0:40:52", "remaining_time": "1:11:06", "throughput": 1031.34, "total_tokens": 2529168} {"current_steps": 28095, "total_steps": 76960, "loss": 0.2899, "lr": 4.004211525941763e-05, "epoch": 7.301195426195426, "percentage": 36.51, "elapsed_time": "0:40:52", "remaining_time": "1:11:05", "throughput": 1031.35, "total_tokens": 2529616} {"current_steps": 28100, "total_steps": 76960, "loss": 0.3207, "lr": 4.00375863727481e-05, "epoch": 7.302494802494802, "percentage": 36.51, "elapsed_time": "0:40:53", "remaining_time": "1:11:05", "throughput": 1031.35, "total_tokens": 2530048} {"current_steps": 28105, "total_steps": 76960, "loss": 0.2048, "lr": 4.00330567126811e-05, "epoch": 7.3037941787941785, "percentage": 36.52, "elapsed_time": "0:40:53", "remaining_time": "1:11:05", "throughput": 1031.36, "total_tokens": 2530512} {"current_steps": 28110, "total_steps": 76960, "loss": 0.2599, "lr": 4.002852627944958e-05, "epoch": 7.305093555093555, "percentage": 36.53, "elapsed_time": "0:40:53", "remaining_time": "1:11:04", "throughput": 1031.37, "total_tokens": 2530960} {"current_steps": 28115, "total_steps": 76960, "loss": 0.2004, "lr": 4.002399507328656e-05, "epoch": 7.3063929313929314, "percentage": 36.53, "elapsed_time": "0:40:54", "remaining_time": "1:11:04", "throughput": 1031.37, "total_tokens": 2531376} {"current_steps": 28120, "total_steps": 76960, "loss": 0.2068, "lr": 4.001946309442508e-05, "epoch": 7.3076923076923075, "percentage": 36.54, "elapsed_time": "0:40:54", "remaining_time": "1:11:03", "throughput": 1031.37, "total_tokens": 2531824} {"current_steps": 28125, "total_steps": 76960, "loss": 0.2435, "lr": 4.0014930343098214e-05, "epoch": 7.3089916839916835, "percentage": 36.54, "elapsed_time": "0:40:55", "remaining_time": "1:11:03", "throughput": 1031.39, "total_tokens": 2532304} {"current_steps": 28130, "total_steps": 76960, "loss": 0.3021, "lr": 4.00103968195391e-05, "epoch": 7.3102910602910605, "percentage": 36.55, "elapsed_time": "0:40:55", "remaining_time": "1:11:02", "throughput": 1031.41, "total_tokens": 2532784} {"current_steps": 28135, "total_steps": 76960, "loss": 0.2216, "lr": 4.000586252398089e-05, "epoch": 7.3115904365904365, "percentage": 36.56, "elapsed_time": "0:40:56", "remaining_time": "1:11:02", "throughput": 1031.42, "total_tokens": 2533232} {"current_steps": 28140, "total_steps": 76960, "loss": 0.2282, "lr": 4.00013274566568e-05, "epoch": 7.3128898128898125, "percentage": 36.56, "elapsed_time": "0:40:56", "remaining_time": "1:11:01", "throughput": 1031.44, "total_tokens": 2533696} {"current_steps": 28145, "total_steps": 76960, "loss": 0.2058, "lr": 3.999679161780005e-05, "epoch": 7.3141891891891895, "percentage": 36.57, "elapsed_time": "0:40:56", "remaining_time": "1:11:01", "throughput": 1031.45, "total_tokens": 2534160} {"current_steps": 28150, "total_steps": 76960, "loss": 0.2736, "lr": 3.999225500764396e-05, "epoch": 7.3154885654885655, "percentage": 36.58, "elapsed_time": "0:40:57", "remaining_time": "1:11:00", "throughput": 1031.46, "total_tokens": 2534608} {"current_steps": 28155, "total_steps": 76960, "loss": 0.2051, "lr": 3.998771762642182e-05, "epoch": 7.316787941787942, "percentage": 36.58, "elapsed_time": "0:40:57", "remaining_time": "1:11:00", "throughput": 1031.46, "total_tokens": 2535040} {"current_steps": 28160, "total_steps": 76960, "loss": 0.2561, "lr": 3.998317947436701e-05, "epoch": 7.3180873180873185, "percentage": 36.59, "elapsed_time": "0:40:58", "remaining_time": "1:10:59", "throughput": 1031.47, "total_tokens": 2535488} {"current_steps": 28165, "total_steps": 76960, "loss": 0.1335, "lr": 3.997864055171291e-05, "epoch": 7.3193866943866945, "percentage": 36.6, "elapsed_time": "0:40:58", "remaining_time": "1:10:59", "throughput": 1031.48, "total_tokens": 2535952} {"current_steps": 28170, "total_steps": 76960, "loss": 0.1983, "lr": 3.997410085869297e-05, "epoch": 7.320686070686071, "percentage": 36.6, "elapsed_time": "0:40:58", "remaining_time": "1:10:58", "throughput": 1031.49, "total_tokens": 2536416} {"current_steps": 28175, "total_steps": 76960, "loss": 0.2151, "lr": 3.9969560395540685e-05, "epoch": 7.321985446985447, "percentage": 36.61, "elapsed_time": "0:40:59", "remaining_time": "1:10:58", "throughput": 1031.49, "total_tokens": 2536832} {"current_steps": 28180, "total_steps": 76960, "loss": 0.1373, "lr": 3.996501916248957e-05, "epoch": 7.3232848232848236, "percentage": 36.62, "elapsed_time": "0:40:59", "remaining_time": "1:10:57", "throughput": 1031.5, "total_tokens": 2537280} {"current_steps": 28185, "total_steps": 76960, "loss": 0.4448, "lr": 3.996047715977318e-05, "epoch": 7.3245841995842, "percentage": 36.62, "elapsed_time": "0:41:00", "remaining_time": "1:10:57", "throughput": 1031.5, "total_tokens": 2537728} {"current_steps": 28190, "total_steps": 76960, "loss": 0.2937, "lr": 3.995593438762511e-05, "epoch": 7.325883575883576, "percentage": 36.63, "elapsed_time": "0:41:00", "remaining_time": "1:10:57", "throughput": 1031.51, "total_tokens": 2538176} {"current_steps": 28195, "total_steps": 76960, "loss": 0.2028, "lr": 3.9951390846279004e-05, "epoch": 7.327182952182953, "percentage": 36.64, "elapsed_time": "0:41:01", "remaining_time": "1:10:56", "throughput": 1031.53, "total_tokens": 2538656} {"current_steps": 28200, "total_steps": 76960, "loss": 0.1893, "lr": 3.994684653596854e-05, "epoch": 7.328482328482329, "percentage": 36.64, "elapsed_time": "0:41:01", "remaining_time": "1:10:56", "throughput": 1031.53, "total_tokens": 2539104} {"current_steps": 28205, "total_steps": 76960, "loss": 0.2626, "lr": 3.994230145692744e-05, "epoch": 7.329781704781705, "percentage": 36.65, "elapsed_time": "0:41:01", "remaining_time": "1:10:55", "throughput": 1031.55, "total_tokens": 2539568} {"current_steps": 28210, "total_steps": 76960, "loss": 0.2247, "lr": 3.993775560938946e-05, "epoch": 7.331081081081081, "percentage": 36.66, "elapsed_time": "0:41:02", "remaining_time": "1:10:55", "throughput": 1031.55, "total_tokens": 2540000} {"current_steps": 28215, "total_steps": 76960, "loss": 0.193, "lr": 3.993320899358839e-05, "epoch": 7.332380457380458, "percentage": 36.66, "elapsed_time": "0:41:02", "remaining_time": "1:10:54", "throughput": 1031.56, "total_tokens": 2540464} {"current_steps": 28220, "total_steps": 76960, "loss": 0.2006, "lr": 3.9928661609758076e-05, "epoch": 7.333679833679834, "percentage": 36.67, "elapsed_time": "0:41:03", "remaining_time": "1:10:54", "throughput": 1031.58, "total_tokens": 2540928} {"current_steps": 28225, "total_steps": 76960, "loss": 0.2539, "lr": 3.99241134581324e-05, "epoch": 7.33497920997921, "percentage": 36.67, "elapsed_time": "0:41:03", "remaining_time": "1:10:53", "throughput": 1031.59, "total_tokens": 2541392} {"current_steps": 28230, "total_steps": 76960, "loss": 0.206, "lr": 3.991956453894526e-05, "epoch": 7.336278586278587, "percentage": 36.68, "elapsed_time": "0:41:03", "remaining_time": "1:10:53", "throughput": 1031.59, "total_tokens": 2541808} {"current_steps": 28235, "total_steps": 76960, "loss": 0.2302, "lr": 3.9915014852430626e-05, "epoch": 7.337577962577963, "percentage": 36.69, "elapsed_time": "0:41:04", "remaining_time": "1:10:52", "throughput": 1031.6, "total_tokens": 2542272} {"current_steps": 28240, "total_steps": 76960, "loss": 0.1607, "lr": 3.991046439882249e-05, "epoch": 7.338877338877339, "percentage": 36.69, "elapsed_time": "0:41:04", "remaining_time": "1:10:52", "throughput": 1031.6, "total_tokens": 2542704} {"current_steps": 28245, "total_steps": 76960, "loss": 0.2746, "lr": 3.990591317835488e-05, "epoch": 7.340176715176715, "percentage": 36.7, "elapsed_time": "0:41:05", "remaining_time": "1:10:51", "throughput": 1031.61, "total_tokens": 2543152} {"current_steps": 28250, "total_steps": 76960, "loss": 0.2151, "lr": 3.9901361191261866e-05, "epoch": 7.341476091476092, "percentage": 36.71, "elapsed_time": "0:41:05", "remaining_time": "1:10:51", "throughput": 1031.62, "total_tokens": 2543616} {"current_steps": 28255, "total_steps": 76960, "loss": 0.2127, "lr": 3.989680843777757e-05, "epoch": 7.342775467775468, "percentage": 36.71, "elapsed_time": "0:41:06", "remaining_time": "1:10:50", "throughput": 1031.63, "total_tokens": 2544064} {"current_steps": 28260, "total_steps": 76960, "loss": 0.3127, "lr": 3.989225491813615e-05, "epoch": 7.344074844074844, "percentage": 36.72, "elapsed_time": "0:41:06", "remaining_time": "1:10:50", "throughput": 1031.65, "total_tokens": 2544544} {"current_steps": 28265, "total_steps": 76960, "loss": 0.389, "lr": 3.988770063257179e-05, "epoch": 7.345374220374221, "percentage": 36.73, "elapsed_time": "0:41:06", "remaining_time": "1:10:49", "throughput": 1031.65, "total_tokens": 2544960} {"current_steps": 28270, "total_steps": 76960, "loss": 0.288, "lr": 3.988314558131871e-05, "epoch": 7.346673596673597, "percentage": 36.73, "elapsed_time": "0:41:07", "remaining_time": "1:10:49", "throughput": 1031.67, "total_tokens": 2545440} {"current_steps": 28275, "total_steps": 76960, "loss": 0.281, "lr": 3.9878589764611205e-05, "epoch": 7.347972972972973, "percentage": 36.74, "elapsed_time": "0:41:07", "remaining_time": "1:10:49", "throughput": 1031.68, "total_tokens": 2545904} {"current_steps": 28280, "total_steps": 76960, "loss": 0.2358, "lr": 3.987403318268357e-05, "epoch": 7.349272349272349, "percentage": 36.75, "elapsed_time": "0:41:08", "remaining_time": "1:10:48", "throughput": 1031.72, "total_tokens": 2546416} {"current_steps": 28285, "total_steps": 76960, "loss": 0.256, "lr": 3.9869475835770153e-05, "epoch": 7.350571725571726, "percentage": 36.75, "elapsed_time": "0:41:08", "remaining_time": "1:10:48", "throughput": 1031.73, "total_tokens": 2546880} {"current_steps": 28290, "total_steps": 76960, "loss": 0.1466, "lr": 3.986491772410535e-05, "epoch": 7.351871101871102, "percentage": 36.76, "elapsed_time": "0:41:08", "remaining_time": "1:10:47", "throughput": 1031.72, "total_tokens": 2547296} {"current_steps": 28295, "total_steps": 76960, "loss": 0.3562, "lr": 3.9860358847923586e-05, "epoch": 7.353170478170478, "percentage": 36.77, "elapsed_time": "0:41:09", "remaining_time": "1:10:47", "throughput": 1031.74, "total_tokens": 2547760} {"current_steps": 28300, "total_steps": 76960, "loss": 0.2508, "lr": 3.9855799207459324e-05, "epoch": 7.354469854469855, "percentage": 36.77, "elapsed_time": "0:41:09", "remaining_time": "1:10:46", "throughput": 1031.77, "total_tokens": 2548272} {"current_steps": 28305, "total_steps": 76960, "loss": 0.2435, "lr": 3.985123880294708e-05, "epoch": 7.355769230769231, "percentage": 36.78, "elapsed_time": "0:41:10", "remaining_time": "1:10:46", "throughput": 1031.79, "total_tokens": 2548752} {"current_steps": 28310, "total_steps": 76960, "loss": 0.2644, "lr": 3.984667763462139e-05, "epoch": 7.357068607068607, "percentage": 36.79, "elapsed_time": "0:41:10", "remaining_time": "1:10:45", "throughput": 1031.81, "total_tokens": 2549216} {"current_steps": 28315, "total_steps": 76960, "loss": 0.1988, "lr": 3.984211570271684e-05, "epoch": 7.358367983367984, "percentage": 36.79, "elapsed_time": "0:41:11", "remaining_time": "1:10:45", "throughput": 1031.81, "total_tokens": 2549664} {"current_steps": 28320, "total_steps": 76960, "loss": 0.242, "lr": 3.9837553007468063e-05, "epoch": 7.35966735966736, "percentage": 36.8, "elapsed_time": "0:41:11", "remaining_time": "1:10:44", "throughput": 1031.82, "total_tokens": 2550096} {"current_steps": 28325, "total_steps": 76960, "loss": 0.3194, "lr": 3.983298954910972e-05, "epoch": 7.360966735966736, "percentage": 36.8, "elapsed_time": "0:41:11", "remaining_time": "1:10:44", "throughput": 1031.81, "total_tokens": 2550512} {"current_steps": 28330, "total_steps": 76960, "loss": 0.2717, "lr": 3.982842532787651e-05, "epoch": 7.362266112266112, "percentage": 36.81, "elapsed_time": "0:41:12", "remaining_time": "1:10:43", "throughput": 1031.82, "total_tokens": 2550976} {"current_steps": 28335, "total_steps": 76960, "loss": 0.2657, "lr": 3.982386034400318e-05, "epoch": 7.363565488565489, "percentage": 36.82, "elapsed_time": "0:41:12", "remaining_time": "1:10:43", "throughput": 1031.84, "total_tokens": 2551440} {"current_steps": 28340, "total_steps": 76960, "loss": 0.3024, "lr": 3.9819294597724504e-05, "epoch": 7.364864864864865, "percentage": 36.82, "elapsed_time": "0:41:13", "remaining_time": "1:10:42", "throughput": 1031.84, "total_tokens": 2551872} {"current_steps": 28345, "total_steps": 76960, "loss": 0.251, "lr": 3.981472808927531e-05, "epoch": 7.366164241164241, "percentage": 36.83, "elapsed_time": "0:41:13", "remaining_time": "1:10:42", "throughput": 1031.86, "total_tokens": 2552352} {"current_steps": 28350, "total_steps": 76960, "loss": 0.2205, "lr": 3.981016081889046e-05, "epoch": 7.367463617463617, "percentage": 36.84, "elapsed_time": "0:41:13", "remaining_time": "1:10:41", "throughput": 1031.86, "total_tokens": 2552800} {"current_steps": 28355, "total_steps": 76960, "loss": 0.2268, "lr": 3.980559278680485e-05, "epoch": 7.368762993762994, "percentage": 36.84, "elapsed_time": "0:41:14", "remaining_time": "1:10:41", "throughput": 1031.89, "total_tokens": 2553296} {"current_steps": 28360, "total_steps": 76960, "loss": 0.2813, "lr": 3.980102399325341e-05, "epoch": 7.37006237006237, "percentage": 36.85, "elapsed_time": "0:41:14", "remaining_time": "1:10:41", "throughput": 1031.91, "total_tokens": 2553776} {"current_steps": 28365, "total_steps": 76960, "loss": 0.1669, "lr": 3.979645443847112e-05, "epoch": 7.371361746361746, "percentage": 36.86, "elapsed_time": "0:41:15", "remaining_time": "1:10:40", "throughput": 1031.93, "total_tokens": 2554240} {"current_steps": 28370, "total_steps": 76960, "loss": 0.2365, "lr": 3.979188412269301e-05, "epoch": 7.372661122661123, "percentage": 36.86, "elapsed_time": "0:41:15", "remaining_time": "1:10:40", "throughput": 1031.93, "total_tokens": 2554672} {"current_steps": 28375, "total_steps": 76960, "loss": 0.3342, "lr": 3.978731304615413e-05, "epoch": 7.373960498960499, "percentage": 36.87, "elapsed_time": "0:41:16", "remaining_time": "1:10:39", "throughput": 1031.94, "total_tokens": 2555136} {"current_steps": 28380, "total_steps": 76960, "loss": 0.2685, "lr": 3.978274120908956e-05, "epoch": 7.375259875259875, "percentage": 36.88, "elapsed_time": "0:41:16", "remaining_time": "1:10:39", "throughput": 1031.94, "total_tokens": 2555568} {"current_steps": 28385, "total_steps": 76960, "loss": 0.1804, "lr": 3.9778168611734456e-05, "epoch": 7.376559251559252, "percentage": 36.88, "elapsed_time": "0:41:16", "remaining_time": "1:10:38", "throughput": 1031.94, "total_tokens": 2555984} {"current_steps": 28390, "total_steps": 76960, "loss": 0.1616, "lr": 3.977359525432397e-05, "epoch": 7.377858627858628, "percentage": 36.89, "elapsed_time": "0:41:17", "remaining_time": "1:10:38", "throughput": 1031.93, "total_tokens": 2556400} {"current_steps": 28395, "total_steps": 76960, "loss": 0.2291, "lr": 3.9769021137093335e-05, "epoch": 7.379158004158004, "percentage": 36.9, "elapsed_time": "0:41:17", "remaining_time": "1:10:37", "throughput": 1031.96, "total_tokens": 2556896} {"current_steps": 28400, "total_steps": 76960, "loss": 0.2333, "lr": 3.976444626027779e-05, "epoch": 7.38045738045738, "percentage": 36.9, "elapsed_time": "0:41:18", "remaining_time": "1:10:37", "throughput": 1031.97, "total_tokens": 2557360} {"current_steps": 28405, "total_steps": 76960, "loss": 0.2479, "lr": 3.9759870624112615e-05, "epoch": 7.381756756756757, "percentage": 36.91, "elapsed_time": "0:41:18", "remaining_time": "1:10:36", "throughput": 1031.98, "total_tokens": 2557808} {"current_steps": 28410, "total_steps": 76960, "loss": 0.3806, "lr": 3.975529422883316e-05, "epoch": 7.383056133056133, "percentage": 36.92, "elapsed_time": "0:41:18", "remaining_time": "1:10:36", "throughput": 1031.99, "total_tokens": 2558256} {"current_steps": 28415, "total_steps": 76960, "loss": 0.2744, "lr": 3.9750717074674796e-05, "epoch": 7.384355509355509, "percentage": 36.92, "elapsed_time": "0:41:19", "remaining_time": "1:10:35", "throughput": 1032.02, "total_tokens": 2558752} {"current_steps": 28420, "total_steps": 76960, "loss": 0.297, "lr": 3.974613916187291e-05, "epoch": 7.385654885654886, "percentage": 36.93, "elapsed_time": "0:41:19", "remaining_time": "1:10:35", "throughput": 1032.04, "total_tokens": 2559232} {"current_steps": 28425, "total_steps": 76960, "loss": 0.2836, "lr": 3.9741560490662954e-05, "epoch": 7.386954261954262, "percentage": 36.93, "elapsed_time": "0:41:20", "remaining_time": "1:10:34", "throughput": 1032.05, "total_tokens": 2559696} {"current_steps": 28430, "total_steps": 76960, "loss": 0.271, "lr": 3.973698106128042e-05, "epoch": 7.388253638253638, "percentage": 36.94, "elapsed_time": "0:41:20", "remaining_time": "1:10:34", "throughput": 1032.07, "total_tokens": 2560160} {"current_steps": 28435, "total_steps": 76960, "loss": 0.2621, "lr": 3.973240087396083e-05, "epoch": 7.389553014553014, "percentage": 36.95, "elapsed_time": "0:41:21", "remaining_time": "1:10:33", "throughput": 1032.05, "total_tokens": 2560560} {"current_steps": 28440, "total_steps": 76960, "loss": 0.2798, "lr": 3.972781992893975e-05, "epoch": 7.390852390852391, "percentage": 36.95, "elapsed_time": "0:41:21", "remaining_time": "1:10:33", "throughput": 1032.06, "total_tokens": 2560992} {"current_steps": 28445, "total_steps": 76960, "loss": 0.2467, "lr": 3.972323822645278e-05, "epoch": 7.392151767151767, "percentage": 36.96, "elapsed_time": "0:41:21", "remaining_time": "1:10:32", "throughput": 1032.06, "total_tokens": 2561424} {"current_steps": 28450, "total_steps": 76960, "loss": 0.2173, "lr": 3.971865576673556e-05, "epoch": 7.393451143451143, "percentage": 36.97, "elapsed_time": "0:41:22", "remaining_time": "1:10:32", "throughput": 1032.07, "total_tokens": 2561872} {"current_steps": 28455, "total_steps": 76960, "loss": 0.3136, "lr": 3.971407255002376e-05, "epoch": 7.39475051975052, "percentage": 36.97, "elapsed_time": "0:41:22", "remaining_time": "1:10:32", "throughput": 1032.07, "total_tokens": 2562320} {"current_steps": 28460, "total_steps": 76960, "loss": 0.1844, "lr": 3.9709488576553125e-05, "epoch": 7.396049896049896, "percentage": 36.98, "elapsed_time": "0:41:23", "remaining_time": "1:10:31", "throughput": 1032.08, "total_tokens": 2562768} {"current_steps": 28465, "total_steps": 76960, "loss": 0.1921, "lr": 3.970490384655939e-05, "epoch": 7.397349272349272, "percentage": 36.99, "elapsed_time": "0:41:23", "remaining_time": "1:10:31", "throughput": 1032.09, "total_tokens": 2563232} {"current_steps": 28470, "total_steps": 76960, "loss": 0.2037, "lr": 3.970031836027837e-05, "epoch": 7.398648648648648, "percentage": 36.99, "elapsed_time": "0:41:23", "remaining_time": "1:10:30", "throughput": 1032.09, "total_tokens": 2563664} {"current_steps": 28475, "total_steps": 76960, "loss": 0.215, "lr": 3.9695732117945876e-05, "epoch": 7.399948024948025, "percentage": 37.0, "elapsed_time": "0:41:24", "remaining_time": "1:10:30", "throughput": 1032.1, "total_tokens": 2564112} {"current_steps": 28480, "total_steps": 76960, "loss": 0.2885, "lr": 3.9691145119797814e-05, "epoch": 7.401247401247401, "percentage": 37.01, "elapsed_time": "0:41:24", "remaining_time": "1:10:29", "throughput": 1032.11, "total_tokens": 2564560} {"current_steps": 28485, "total_steps": 76960, "loss": 0.2164, "lr": 3.968655736607007e-05, "epoch": 7.402546777546777, "percentage": 37.01, "elapsed_time": "0:41:25", "remaining_time": "1:10:29", "throughput": 1032.13, "total_tokens": 2565056} {"current_steps": 28490, "total_steps": 76960, "loss": 0.2613, "lr": 3.968196885699862e-05, "epoch": 7.403846153846154, "percentage": 37.02, "elapsed_time": "0:41:25", "remaining_time": "1:10:28", "throughput": 1032.14, "total_tokens": 2565488} {"current_steps": 28495, "total_steps": 76960, "loss": 0.3641, "lr": 3.967737959281944e-05, "epoch": 7.40514553014553, "percentage": 37.03, "elapsed_time": "0:41:26", "remaining_time": "1:10:28", "throughput": 1032.17, "total_tokens": 2566000} {"current_steps": 28500, "total_steps": 76960, "loss": 0.2937, "lr": 3.967278957376856e-05, "epoch": 7.406444906444906, "percentage": 37.03, "elapsed_time": "0:41:26", "remaining_time": "1:10:27", "throughput": 1032.18, "total_tokens": 2566464} {"current_steps": 28505, "total_steps": 76960, "loss": 0.235, "lr": 3.9668198800082055e-05, "epoch": 7.407744282744282, "percentage": 37.04, "elapsed_time": "0:41:26", "remaining_time": "1:10:27", "throughput": 1032.18, "total_tokens": 2566896} {"current_steps": 28510, "total_steps": 76960, "loss": 0.2306, "lr": 3.9663607271996025e-05, "epoch": 7.409043659043659, "percentage": 37.05, "elapsed_time": "0:41:27", "remaining_time": "1:10:26", "throughput": 1032.18, "total_tokens": 2567312} {"current_steps": 28515, "total_steps": 76960, "loss": 0.1737, "lr": 3.9659014989746634e-05, "epoch": 7.410343035343035, "percentage": 37.05, "elapsed_time": "0:41:27", "remaining_time": "1:10:26", "throughput": 1032.18, "total_tokens": 2567760} {"current_steps": 28520, "total_steps": 76960, "loss": 0.272, "lr": 3.9654421953570056e-05, "epoch": 7.411642411642411, "percentage": 37.06, "elapsed_time": "0:41:28", "remaining_time": "1:10:25", "throughput": 1032.19, "total_tokens": 2568208} {"current_steps": 28525, "total_steps": 76960, "loss": 0.3132, "lr": 3.964982816370252e-05, "epoch": 7.412941787941788, "percentage": 37.06, "elapsed_time": "0:41:28", "remaining_time": "1:10:25", "throughput": 1032.2, "total_tokens": 2568672} {"current_steps": 28530, "total_steps": 76960, "loss": 0.3112, "lr": 3.9645233620380274e-05, "epoch": 7.414241164241164, "percentage": 37.07, "elapsed_time": "0:41:28", "remaining_time": "1:10:25", "throughput": 1032.22, "total_tokens": 2569152} {"current_steps": 28535, "total_steps": 76960, "loss": 0.2639, "lr": 3.964063832383963e-05, "epoch": 7.41554054054054, "percentage": 37.08, "elapsed_time": "0:41:29", "remaining_time": "1:10:24", "throughput": 1032.23, "total_tokens": 2569600} {"current_steps": 28540, "total_steps": 76960, "loss": 0.2679, "lr": 3.963604227431693e-05, "epoch": 7.416839916839917, "percentage": 37.08, "elapsed_time": "0:41:29", "remaining_time": "1:10:24", "throughput": 1032.23, "total_tokens": 2570032} {"current_steps": 28545, "total_steps": 76960, "loss": 0.2763, "lr": 3.963144547204856e-05, "epoch": 7.418139293139293, "percentage": 37.09, "elapsed_time": "0:41:30", "remaining_time": "1:10:23", "throughput": 1032.24, "total_tokens": 2570480} {"current_steps": 28550, "total_steps": 76960, "loss": 0.2679, "lr": 3.9626847917270925e-05, "epoch": 7.419438669438669, "percentage": 37.1, "elapsed_time": "0:41:30", "remaining_time": "1:10:23", "throughput": 1032.25, "total_tokens": 2570944} {"current_steps": 28555, "total_steps": 76960, "loss": 0.2285, "lr": 3.962224961022049e-05, "epoch": 7.420738045738045, "percentage": 37.1, "elapsed_time": "0:41:31", "remaining_time": "1:10:22", "throughput": 1032.28, "total_tokens": 2571456} {"current_steps": 28560, "total_steps": 76960, "loss": 0.1681, "lr": 3.9617650551133746e-05, "epoch": 7.422037422037422, "percentage": 37.11, "elapsed_time": "0:41:31", "remaining_time": "1:10:22", "throughput": 1032.28, "total_tokens": 2571872} {"current_steps": 28565, "total_steps": 76960, "loss": 0.241, "lr": 3.9613050740247224e-05, "epoch": 7.423336798336798, "percentage": 37.12, "elapsed_time": "0:41:31", "remaining_time": "1:10:21", "throughput": 1032.29, "total_tokens": 2572336} {"current_steps": 28570, "total_steps": 76960, "loss": 0.248, "lr": 3.960845017779751e-05, "epoch": 7.424636174636174, "percentage": 37.12, "elapsed_time": "0:41:32", "remaining_time": "1:10:21", "throughput": 1032.31, "total_tokens": 2572816} {"current_steps": 28575, "total_steps": 76960, "loss": 0.3131, "lr": 3.9603848864021196e-05, "epoch": 7.4259355509355505, "percentage": 37.13, "elapsed_time": "0:41:32", "remaining_time": "1:10:20", "throughput": 1032.3, "total_tokens": 2573232} {"current_steps": 28580, "total_steps": 76960, "loss": 0.156, "lr": 3.959924679915494e-05, "epoch": 7.427234927234927, "percentage": 37.14, "elapsed_time": "0:41:33", "remaining_time": "1:10:20", "throughput": 1032.3, "total_tokens": 2573648} {"current_steps": 28585, "total_steps": 76960, "loss": 0.2438, "lr": 3.959464398343544e-05, "epoch": 7.428534303534303, "percentage": 37.14, "elapsed_time": "0:41:33", "remaining_time": "1:10:19", "throughput": 1032.3, "total_tokens": 2574096} {"current_steps": 28590, "total_steps": 76960, "loss": 0.2964, "lr": 3.9590040417099415e-05, "epoch": 7.4298336798336795, "percentage": 37.15, "elapsed_time": "0:41:33", "remaining_time": "1:10:19", "throughput": 1032.31, "total_tokens": 2574544} {"current_steps": 28595, "total_steps": 76960, "loss": 0.1153, "lr": 3.958543610038363e-05, "epoch": 7.431133056133056, "percentage": 37.16, "elapsed_time": "0:41:34", "remaining_time": "1:10:18", "throughput": 1032.33, "total_tokens": 2575024} {"current_steps": 28600, "total_steps": 76960, "loss": 0.279, "lr": 3.95808310335249e-05, "epoch": 7.4324324324324325, "percentage": 37.16, "elapsed_time": "0:41:34", "remaining_time": "1:10:18", "throughput": 1032.33, "total_tokens": 2575440} {"current_steps": 28605, "total_steps": 76960, "loss": 0.2897, "lr": 3.957622521676005e-05, "epoch": 7.4337318087318085, "percentage": 37.17, "elapsed_time": "0:41:35", "remaining_time": "1:10:18", "throughput": 1032.33, "total_tokens": 2575872} {"current_steps": 28610, "total_steps": 76960, "loss": 0.2515, "lr": 3.957161865032597e-05, "epoch": 7.435031185031185, "percentage": 37.18, "elapsed_time": "0:41:35", "remaining_time": "1:10:17", "throughput": 1032.33, "total_tokens": 2576320} {"current_steps": 28615, "total_steps": 76960, "loss": 0.2434, "lr": 3.9567011334459585e-05, "epoch": 7.4363305613305615, "percentage": 37.18, "elapsed_time": "0:41:36", "remaining_time": "1:10:17", "throughput": 1032.34, "total_tokens": 2576768} {"current_steps": 28620, "total_steps": 76960, "loss": 0.2603, "lr": 3.9562403269397854e-05, "epoch": 7.4376299376299375, "percentage": 37.19, "elapsed_time": "0:41:36", "remaining_time": "1:10:16", "throughput": 1032.37, "total_tokens": 2577280} {"current_steps": 28625, "total_steps": 76960, "loss": 0.1978, "lr": 3.955779445537776e-05, "epoch": 7.438929313929314, "percentage": 37.19, "elapsed_time": "0:41:36", "remaining_time": "1:10:16", "throughput": 1032.36, "total_tokens": 2577680} {"current_steps": 28630, "total_steps": 76960, "loss": 0.2964, "lr": 3.955318489263635e-05, "epoch": 7.4402286902286905, "percentage": 37.2, "elapsed_time": "0:41:37", "remaining_time": "1:10:15", "throughput": 1032.36, "total_tokens": 2578112} {"current_steps": 28635, "total_steps": 76960, "loss": 0.258, "lr": 3.9548574581410705e-05, "epoch": 7.4415280665280665, "percentage": 37.21, "elapsed_time": "0:41:37", "remaining_time": "1:10:15", "throughput": 1032.38, "total_tokens": 2578592} {"current_steps": 28640, "total_steps": 76960, "loss": 0.3101, "lr": 3.954396352193792e-05, "epoch": 7.442827442827443, "percentage": 37.21, "elapsed_time": "0:41:38", "remaining_time": "1:10:14", "throughput": 1032.39, "total_tokens": 2579040} {"current_steps": 28645, "total_steps": 76960, "loss": 0.2473, "lr": 3.953935171445516e-05, "epoch": 7.4441268191268195, "percentage": 37.22, "elapsed_time": "0:41:38", "remaining_time": "1:10:14", "throughput": 1032.39, "total_tokens": 2579472} {"current_steps": 28650, "total_steps": 76960, "loss": 0.2631, "lr": 3.953473915919962e-05, "epoch": 7.4454261954261955, "percentage": 37.23, "elapsed_time": "0:41:38", "remaining_time": "1:10:13", "throughput": 1032.39, "total_tokens": 2579904} {"current_steps": 28655, "total_steps": 76960, "loss": 0.252, "lr": 3.953012585640851e-05, "epoch": 7.446725571725572, "percentage": 37.23, "elapsed_time": "0:41:39", "remaining_time": "1:10:13", "throughput": 1032.37, "total_tokens": 2580304} {"current_steps": 28660, "total_steps": 76960, "loss": 0.293, "lr": 3.952551180631909e-05, "epoch": 7.448024948024948, "percentage": 37.24, "elapsed_time": "0:41:39", "remaining_time": "1:10:12", "throughput": 1032.38, "total_tokens": 2580752} {"current_steps": 28665, "total_steps": 76960, "loss": 0.2539, "lr": 3.95208970091687e-05, "epoch": 7.449324324324325, "percentage": 37.25, "elapsed_time": "0:41:40", "remaining_time": "1:10:12", "throughput": 1032.4, "total_tokens": 2581232} {"current_steps": 28670, "total_steps": 76960, "loss": 0.2338, "lr": 3.951628146519466e-05, "epoch": 7.450623700623701, "percentage": 37.25, "elapsed_time": "0:41:40", "remaining_time": "1:10:11", "throughput": 1032.41, "total_tokens": 2581680} {"current_steps": 28675, "total_steps": 76960, "loss": 0.1823, "lr": 3.951166517463435e-05, "epoch": 7.451923076923077, "percentage": 37.26, "elapsed_time": "0:41:41", "remaining_time": "1:10:11", "throughput": 1032.42, "total_tokens": 2582128} {"current_steps": 28680, "total_steps": 76960, "loss": 0.2195, "lr": 3.95070481377252e-05, "epoch": 7.453222453222454, "percentage": 37.27, "elapsed_time": "0:41:41", "remaining_time": "1:10:10", "throughput": 1032.43, "total_tokens": 2582592} {"current_steps": 28685, "total_steps": 76960, "loss": 0.264, "lr": 3.950243035470467e-05, "epoch": 7.45452182952183, "percentage": 37.27, "elapsed_time": "0:41:41", "remaining_time": "1:10:10", "throughput": 1032.45, "total_tokens": 2583072} {"current_steps": 28690, "total_steps": 76960, "loss": 0.3398, "lr": 3.9497811825810235e-05, "epoch": 7.455821205821206, "percentage": 37.28, "elapsed_time": "0:41:42", "remaining_time": "1:10:10", "throughput": 1032.46, "total_tokens": 2583520} {"current_steps": 28695, "total_steps": 76960, "loss": 0.1645, "lr": 3.949319255127946e-05, "epoch": 7.457120582120582, "percentage": 37.29, "elapsed_time": "0:41:42", "remaining_time": "1:10:09", "throughput": 1032.46, "total_tokens": 2583952} {"current_steps": 28700, "total_steps": 76960, "loss": 0.2588, "lr": 3.9488572531349904e-05, "epoch": 7.458419958419959, "percentage": 37.29, "elapsed_time": "0:41:43", "remaining_time": "1:10:09", "throughput": 1032.46, "total_tokens": 2584400} {"current_steps": 28705, "total_steps": 76960, "loss": 0.2362, "lr": 3.948395176625918e-05, "epoch": 7.459719334719335, "percentage": 37.3, "elapsed_time": "0:41:43", "remaining_time": "1:10:08", "throughput": 1032.48, "total_tokens": 2584864} {"current_steps": 28710, "total_steps": 76960, "loss": 0.1636, "lr": 3.947933025624493e-05, "epoch": 7.461018711018711, "percentage": 37.31, "elapsed_time": "0:41:43", "remaining_time": "1:10:08", "throughput": 1032.48, "total_tokens": 2585296} {"current_steps": 28715, "total_steps": 76960, "loss": 0.1739, "lr": 3.947470800154486e-05, "epoch": 7.462318087318088, "percentage": 37.31, "elapsed_time": "0:41:44", "remaining_time": "1:10:07", "throughput": 1032.48, "total_tokens": 2585728} {"current_steps": 28720, "total_steps": 76960, "loss": 0.3664, "lr": 3.947008500239669e-05, "epoch": 7.463617463617464, "percentage": 37.32, "elapsed_time": "0:41:44", "remaining_time": "1:10:07", "throughput": 1032.49, "total_tokens": 2586176} {"current_steps": 28725, "total_steps": 76960, "loss": 0.353, "lr": 3.9465461259038176e-05, "epoch": 7.46491683991684, "percentage": 37.32, "elapsed_time": "0:41:45", "remaining_time": "1:10:06", "throughput": 1032.5, "total_tokens": 2586624} {"current_steps": 28730, "total_steps": 76960, "loss": 0.1943, "lr": 3.946083677170713e-05, "epoch": 7.466216216216216, "percentage": 37.33, "elapsed_time": "0:41:45", "remaining_time": "1:10:06", "throughput": 1032.51, "total_tokens": 2587104} {"current_steps": 28735, "total_steps": 76960, "loss": 0.2806, "lr": 3.9456211540641405e-05, "epoch": 7.467515592515593, "percentage": 37.34, "elapsed_time": "0:41:46", "remaining_time": "1:10:05", "throughput": 1032.53, "total_tokens": 2587568} {"current_steps": 28740, "total_steps": 76960, "loss": 0.1514, "lr": 3.945158556607886e-05, "epoch": 7.468814968814969, "percentage": 37.34, "elapsed_time": "0:41:46", "remaining_time": "1:10:05", "throughput": 1032.53, "total_tokens": 2588016} {"current_steps": 28745, "total_steps": 76960, "loss": 0.2611, "lr": 3.944695884825742e-05, "epoch": 7.470114345114345, "percentage": 37.35, "elapsed_time": "0:41:46", "remaining_time": "1:10:04", "throughput": 1032.54, "total_tokens": 2588464} {"current_steps": 28750, "total_steps": 76960, "loss": 0.2474, "lr": 3.9442331387415054e-05, "epoch": 7.471413721413722, "percentage": 37.36, "elapsed_time": "0:41:47", "remaining_time": "1:10:04", "throughput": 1032.55, "total_tokens": 2588928} {"current_steps": 28755, "total_steps": 76960, "loss": 0.116, "lr": 3.943770318378974e-05, "epoch": 7.472713097713098, "percentage": 37.36, "elapsed_time": "0:41:47", "remaining_time": "1:10:03", "throughput": 1032.56, "total_tokens": 2589376} {"current_steps": 28760, "total_steps": 76960, "loss": 0.3491, "lr": 3.943307423761952e-05, "epoch": 7.474012474012474, "percentage": 37.37, "elapsed_time": "0:41:48", "remaining_time": "1:10:03", "throughput": 1032.55, "total_tokens": 2589808} {"current_steps": 28765, "total_steps": 76960, "loss": 0.4449, "lr": 3.942844454914246e-05, "epoch": 7.475311850311851, "percentage": 37.38, "elapsed_time": "0:41:48", "remaining_time": "1:10:03", "throughput": 1032.55, "total_tokens": 2590224} {"current_steps": 28770, "total_steps": 76960, "loss": 0.3583, "lr": 3.9423814118596666e-05, "epoch": 7.476611226611227, "percentage": 37.38, "elapsed_time": "0:41:48", "remaining_time": "1:10:02", "throughput": 1032.55, "total_tokens": 2590672} {"current_steps": 28775, "total_steps": 76960, "loss": 0.32, "lr": 3.94191829462203e-05, "epoch": 7.477910602910603, "percentage": 37.39, "elapsed_time": "0:41:49", "remaining_time": "1:10:02", "throughput": 1032.58, "total_tokens": 2591168} {"current_steps": 28780, "total_steps": 76960, "loss": 0.2447, "lr": 3.941455103225154e-05, "epoch": 7.479209979209979, "percentage": 37.4, "elapsed_time": "0:41:49", "remaining_time": "1:10:01", "throughput": 1032.58, "total_tokens": 2591600} {"current_steps": 28785, "total_steps": 76960, "loss": 0.2759, "lr": 3.9409918376928604e-05, "epoch": 7.480509355509356, "percentage": 37.4, "elapsed_time": "0:41:50", "remaining_time": "1:10:01", "throughput": 1032.61, "total_tokens": 2592096} {"current_steps": 28790, "total_steps": 76960, "loss": 0.2686, "lr": 3.940528498048977e-05, "epoch": 7.481808731808732, "percentage": 37.41, "elapsed_time": "0:41:50", "remaining_time": "1:10:00", "throughput": 1032.63, "total_tokens": 2592592} {"current_steps": 28795, "total_steps": 76960, "loss": 0.2886, "lr": 3.9400650843173317e-05, "epoch": 7.483108108108108, "percentage": 37.42, "elapsed_time": "0:41:51", "remaining_time": "1:10:00", "throughput": 1032.64, "total_tokens": 2593040} {"current_steps": 28800, "total_steps": 76960, "loss": 0.299, "lr": 3.939601596521759e-05, "epoch": 7.484407484407485, "percentage": 37.42, "elapsed_time": "0:41:51", "remaining_time": "1:09:59", "throughput": 1032.67, "total_tokens": 2593536} {"current_steps": 28805, "total_steps": 76960, "loss": 0.286, "lr": 3.939138034686097e-05, "epoch": 7.485706860706861, "percentage": 37.43, "elapsed_time": "0:41:51", "remaining_time": "1:09:59", "throughput": 1032.67, "total_tokens": 2593984} {"current_steps": 28810, "total_steps": 76960, "loss": 0.2409, "lr": 3.938674398834188e-05, "epoch": 7.487006237006237, "percentage": 37.44, "elapsed_time": "0:41:52", "remaining_time": "1:09:58", "throughput": 1032.68, "total_tokens": 2594432} {"current_steps": 28815, "total_steps": 76960, "loss": 0.2654, "lr": 3.938210688989876e-05, "epoch": 7.488305613305613, "percentage": 37.44, "elapsed_time": "0:41:52", "remaining_time": "1:09:58", "throughput": 1032.69, "total_tokens": 2594896} {"current_steps": 28820, "total_steps": 76960, "loss": 0.2701, "lr": 3.9377469051770094e-05, "epoch": 7.48960498960499, "percentage": 37.45, "elapsed_time": "0:41:53", "remaining_time": "1:09:57", "throughput": 1032.72, "total_tokens": 2595392} {"current_steps": 28825, "total_steps": 76960, "loss": 0.2435, "lr": 3.937283047419442e-05, "epoch": 7.490904365904366, "percentage": 37.45, "elapsed_time": "0:41:53", "remaining_time": "1:09:57", "throughput": 1032.72, "total_tokens": 2595824} {"current_steps": 28830, "total_steps": 76960, "loss": 0.2368, "lr": 3.936819115741031e-05, "epoch": 7.492203742203742, "percentage": 37.46, "elapsed_time": "0:41:53", "remaining_time": "1:09:56", "throughput": 1032.73, "total_tokens": 2596288} {"current_steps": 28835, "total_steps": 76960, "loss": 0.2192, "lr": 3.936355110165636e-05, "epoch": 7.493503118503119, "percentage": 37.47, "elapsed_time": "0:41:54", "remaining_time": "1:09:56", "throughput": 1032.74, "total_tokens": 2596736} {"current_steps": 28840, "total_steps": 76960, "loss": 0.2585, "lr": 3.935891030717121e-05, "epoch": 7.494802494802495, "percentage": 37.47, "elapsed_time": "0:41:54", "remaining_time": "1:09:56", "throughput": 1032.75, "total_tokens": 2597200} {"current_steps": 28845, "total_steps": 76960, "loss": 0.2169, "lr": 3.935426877419355e-05, "epoch": 7.496101871101871, "percentage": 37.48, "elapsed_time": "0:41:55", "remaining_time": "1:09:55", "throughput": 1032.76, "total_tokens": 2597648} {"current_steps": 28850, "total_steps": 76960, "loss": 0.1837, "lr": 3.9349626502962084e-05, "epoch": 7.497401247401247, "percentage": 37.49, "elapsed_time": "0:41:55", "remaining_time": "1:09:55", "throughput": 1032.77, "total_tokens": 2598112} {"current_steps": 28855, "total_steps": 76960, "loss": 0.2797, "lr": 3.934498349371558e-05, "epoch": 7.498700623700624, "percentage": 37.49, "elapsed_time": "0:41:56", "remaining_time": "1:09:54", "throughput": 1032.78, "total_tokens": 2598560} {"current_steps": 28860, "total_steps": 76960, "loss": 0.3113, "lr": 3.9340339746692835e-05, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "0:41:56", "remaining_time": "1:09:54", "throughput": 1032.77, "total_tokens": 2598960} {"current_steps": 28865, "total_steps": 76960, "loss": 0.2633, "lr": 3.933569526213268e-05, "epoch": 7.501299376299376, "percentage": 37.51, "elapsed_time": "0:41:56", "remaining_time": "1:09:53", "throughput": 1032.78, "total_tokens": 2599424} {"current_steps": 28870, "total_steps": 76960, "loss": 0.2948, "lr": 3.9331050040273974e-05, "epoch": 7.502598752598753, "percentage": 37.51, "elapsed_time": "0:41:57", "remaining_time": "1:09:53", "throughput": 1032.78, "total_tokens": 2599856} {"current_steps": 28875, "total_steps": 76960, "loss": 0.2501, "lr": 3.932640408135564e-05, "epoch": 7.503898128898129, "percentage": 37.52, "elapsed_time": "0:41:57", "remaining_time": "1:09:52", "throughput": 1032.78, "total_tokens": 2600288} {"current_steps": 28880, "total_steps": 76960, "loss": 0.2399, "lr": 3.932175738561662e-05, "epoch": 7.505197505197505, "percentage": 37.53, "elapsed_time": "0:41:58", "remaining_time": "1:09:52", "throughput": 1032.79, "total_tokens": 2600736} {"current_steps": 28885, "total_steps": 76960, "loss": 0.2087, "lr": 3.931710995329588e-05, "epoch": 7.506496881496881, "percentage": 37.53, "elapsed_time": "0:41:58", "remaining_time": "1:09:51", "throughput": 1032.79, "total_tokens": 2601168} {"current_steps": 28890, "total_steps": 76960, "loss": 0.2218, "lr": 3.931246178463247e-05, "epoch": 7.507796257796258, "percentage": 37.54, "elapsed_time": "0:41:58", "remaining_time": "1:09:51", "throughput": 1032.8, "total_tokens": 2601632} {"current_steps": 28895, "total_steps": 76960, "loss": 0.309, "lr": 3.930781287986543e-05, "epoch": 7.509095634095634, "percentage": 37.55, "elapsed_time": "0:41:59", "remaining_time": "1:09:50", "throughput": 1032.82, "total_tokens": 2602096} {"current_steps": 28900, "total_steps": 76960, "loss": 0.2958, "lr": 3.930316323923387e-05, "epoch": 7.51039501039501, "percentage": 37.55, "elapsed_time": "0:41:59", "remaining_time": "1:09:50", "throughput": 1032.82, "total_tokens": 2602544} {"current_steps": 28905, "total_steps": 76960, "loss": 0.2114, "lr": 3.9298512862976915e-05, "epoch": 7.511694386694387, "percentage": 37.56, "elapsed_time": "0:42:00", "remaining_time": "1:09:49", "throughput": 1032.84, "total_tokens": 2603008} {"current_steps": 28910, "total_steps": 76960, "loss": 0.2592, "lr": 3.929386175133374e-05, "epoch": 7.512993762993763, "percentage": 37.56, "elapsed_time": "0:42:00", "remaining_time": "1:09:49", "throughput": 1032.84, "total_tokens": 2603440} {"current_steps": 28915, "total_steps": 76960, "loss": 0.2043, "lr": 3.9289209904543565e-05, "epoch": 7.514293139293139, "percentage": 37.57, "elapsed_time": "0:42:01", "remaining_time": "1:09:49", "throughput": 1032.84, "total_tokens": 2603872} {"current_steps": 28920, "total_steps": 76960, "loss": 0.2247, "lr": 3.928455732284564e-05, "epoch": 7.515592515592516, "percentage": 37.58, "elapsed_time": "0:42:01", "remaining_time": "1:09:48", "throughput": 1032.85, "total_tokens": 2604336} {"current_steps": 28925, "total_steps": 76960, "loss": 0.222, "lr": 3.927990400647924e-05, "epoch": 7.516891891891892, "percentage": 37.58, "elapsed_time": "0:42:01", "remaining_time": "1:09:48", "throughput": 1032.88, "total_tokens": 2604832} {"current_steps": 28930, "total_steps": 76960, "loss": 0.1845, "lr": 3.927524995568369e-05, "epoch": 7.518191268191268, "percentage": 37.59, "elapsed_time": "0:42:02", "remaining_time": "1:09:47", "throughput": 1032.89, "total_tokens": 2605296} {"current_steps": 28935, "total_steps": 76960, "loss": 0.2721, "lr": 3.927059517069836e-05, "epoch": 7.519490644490644, "percentage": 37.6, "elapsed_time": "0:42:02", "remaining_time": "1:09:47", "throughput": 1032.9, "total_tokens": 2605760} {"current_steps": 28940, "total_steps": 76960, "loss": 0.2701, "lr": 3.926593965176265e-05, "epoch": 7.520790020790021, "percentage": 37.6, "elapsed_time": "0:42:03", "remaining_time": "1:09:46", "throughput": 1032.9, "total_tokens": 2606192} {"current_steps": 28945, "total_steps": 76960, "loss": 0.2479, "lr": 3.926128339911599e-05, "epoch": 7.522089397089397, "percentage": 37.61, "elapsed_time": "0:42:03", "remaining_time": "1:09:46", "throughput": 1032.93, "total_tokens": 2606688} {"current_steps": 28950, "total_steps": 76960, "loss": 0.3498, "lr": 3.925662641299787e-05, "epoch": 7.523388773388773, "percentage": 37.62, "elapsed_time": "0:42:04", "remaining_time": "1:09:45", "throughput": 1032.94, "total_tokens": 2607152} {"current_steps": 28955, "total_steps": 76960, "loss": 0.3223, "lr": 3.925196869364778e-05, "epoch": 7.524688149688149, "percentage": 37.62, "elapsed_time": "0:42:04", "remaining_time": "1:09:45", "throughput": 1032.96, "total_tokens": 2607616} {"current_steps": 28960, "total_steps": 76960, "loss": 0.2485, "lr": 3.9247310241305294e-05, "epoch": 7.525987525987526, "percentage": 37.63, "elapsed_time": "0:42:04", "remaining_time": "1:09:44", "throughput": 1032.96, "total_tokens": 2608064} {"current_steps": 28965, "total_steps": 76960, "loss": 0.2523, "lr": 3.9242651056209976e-05, "epoch": 7.527286902286902, "percentage": 37.64, "elapsed_time": "0:42:05", "remaining_time": "1:09:44", "throughput": 1032.96, "total_tokens": 2608496} {"current_steps": 28970, "total_steps": 76960, "loss": 0.2691, "lr": 3.923799113860148e-05, "epoch": 7.528586278586278, "percentage": 37.64, "elapsed_time": "0:42:05", "remaining_time": "1:09:43", "throughput": 1032.97, "total_tokens": 2608944} {"current_steps": 28975, "total_steps": 76960, "loss": 0.2291, "lr": 3.923333048871946e-05, "epoch": 7.529885654885655, "percentage": 37.65, "elapsed_time": "0:42:06", "remaining_time": "1:09:43", "throughput": 1032.98, "total_tokens": 2609408} {"current_steps": 28980, "total_steps": 76960, "loss": 0.2271, "lr": 3.922866910680361e-05, "epoch": 7.531185031185031, "percentage": 37.66, "elapsed_time": "0:42:06", "remaining_time": "1:09:42", "throughput": 1032.98, "total_tokens": 2609824} {"current_steps": 28985, "total_steps": 76960, "loss": 0.2443, "lr": 3.9224006993093675e-05, "epoch": 7.532484407484407, "percentage": 37.66, "elapsed_time": "0:42:06", "remaining_time": "1:09:42", "throughput": 1032.99, "total_tokens": 2610288} {"current_steps": 28990, "total_steps": 76960, "loss": 0.2839, "lr": 3.921934414782944e-05, "epoch": 7.533783783783784, "percentage": 37.67, "elapsed_time": "0:42:07", "remaining_time": "1:09:42", "throughput": 1033.0, "total_tokens": 2610736} {"current_steps": 28995, "total_steps": 76960, "loss": 0.149, "lr": 3.9214680571250696e-05, "epoch": 7.53508316008316, "percentage": 37.68, "elapsed_time": "0:42:07", "remaining_time": "1:09:41", "throughput": 1033.01, "total_tokens": 2611184} {"current_steps": 29000, "total_steps": 76960, "loss": 0.3214, "lr": 3.921001626359732e-05, "epoch": 7.536382536382536, "percentage": 37.68, "elapsed_time": "0:42:08", "remaining_time": "1:09:41", "throughput": 1033.02, "total_tokens": 2611648} {"current_steps": 29005, "total_steps": 76960, "loss": 0.1942, "lr": 3.9205351225109185e-05, "epoch": 7.537681912681912, "percentage": 37.69, "elapsed_time": "0:42:08", "remaining_time": "1:09:40", "throughput": 1033.03, "total_tokens": 2612096} {"current_steps": 29010, "total_steps": 76960, "loss": 0.3603, "lr": 3.920068545602624e-05, "epoch": 7.538981288981289, "percentage": 37.69, "elapsed_time": "0:42:09", "remaining_time": "1:09:40", "throughput": 1033.04, "total_tokens": 2612576} {"current_steps": 29015, "total_steps": 76960, "loss": 0.1631, "lr": 3.919601895658843e-05, "epoch": 7.540280665280665, "percentage": 37.7, "elapsed_time": "0:42:09", "remaining_time": "1:09:39", "throughput": 1033.05, "total_tokens": 2613024} {"current_steps": 29020, "total_steps": 76960, "loss": 0.2134, "lr": 3.919135172703575e-05, "epoch": 7.541580041580041, "percentage": 37.71, "elapsed_time": "0:42:09", "remaining_time": "1:09:39", "throughput": 1033.06, "total_tokens": 2613472} {"current_steps": 29025, "total_steps": 76960, "loss": 0.1883, "lr": 3.918668376760827e-05, "epoch": 7.542879417879417, "percentage": 37.71, "elapsed_time": "0:42:10", "remaining_time": "1:09:38", "throughput": 1033.1, "total_tokens": 2614000} {"current_steps": 29030, "total_steps": 76960, "loss": 0.2393, "lr": 3.918201507854604e-05, "epoch": 7.544178794178794, "percentage": 37.72, "elapsed_time": "0:42:10", "remaining_time": "1:09:38", "throughput": 1033.1, "total_tokens": 2614432} {"current_steps": 29035, "total_steps": 76960, "loss": 0.2865, "lr": 3.9177345660089196e-05, "epoch": 7.54547817047817, "percentage": 37.73, "elapsed_time": "0:42:11", "remaining_time": "1:09:37", "throughput": 1033.1, "total_tokens": 2614880} {"current_steps": 29040, "total_steps": 76960, "loss": 0.1998, "lr": 3.917267551247787e-05, "epoch": 7.546777546777546, "percentage": 37.73, "elapsed_time": "0:42:11", "remaining_time": "1:09:37", "throughput": 1033.1, "total_tokens": 2615312} {"current_steps": 29045, "total_steps": 76960, "loss": 0.324, "lr": 3.916800463595227e-05, "epoch": 7.548076923076923, "percentage": 37.74, "elapsed_time": "0:42:11", "remaining_time": "1:09:36", "throughput": 1033.12, "total_tokens": 2615776} {"current_steps": 29050, "total_steps": 76960, "loss": 0.1428, "lr": 3.916333303075261e-05, "epoch": 7.549376299376299, "percentage": 37.75, "elapsed_time": "0:42:12", "remaining_time": "1:09:36", "throughput": 1033.12, "total_tokens": 2616224} {"current_steps": 29055, "total_steps": 76960, "loss": 0.1972, "lr": 3.9158660697119167e-05, "epoch": 7.550675675675675, "percentage": 37.75, "elapsed_time": "0:42:12", "remaining_time": "1:09:35", "throughput": 1033.14, "total_tokens": 2616704} {"current_steps": 29060, "total_steps": 76960, "loss": 0.3036, "lr": 3.915398763529223e-05, "epoch": 7.551975051975052, "percentage": 37.76, "elapsed_time": "0:42:13", "remaining_time": "1:09:35", "throughput": 1033.16, "total_tokens": 2617168} {"current_steps": 29065, "total_steps": 76960, "loss": 0.2623, "lr": 3.914931384551216e-05, "epoch": 7.553274428274428, "percentage": 37.77, "elapsed_time": "0:42:13", "remaining_time": "1:09:35", "throughput": 1033.16, "total_tokens": 2617600} {"current_steps": 29070, "total_steps": 76960, "loss": 0.1806, "lr": 3.9144639328019314e-05, "epoch": 7.5545738045738045, "percentage": 37.77, "elapsed_time": "0:42:14", "remaining_time": "1:09:34", "throughput": 1033.17, "total_tokens": 2618064} {"current_steps": 29075, "total_steps": 76960, "loss": 0.2231, "lr": 3.913996408305412e-05, "epoch": 7.5558731808731805, "percentage": 37.78, "elapsed_time": "0:42:14", "remaining_time": "1:09:34", "throughput": 1033.17, "total_tokens": 2618496} {"current_steps": 29080, "total_steps": 76960, "loss": 0.1997, "lr": 3.9135288110857014e-05, "epoch": 7.557172557172557, "percentage": 37.79, "elapsed_time": "0:42:14", "remaining_time": "1:09:33", "throughput": 1033.18, "total_tokens": 2618944} {"current_steps": 29085, "total_steps": 76960, "loss": 0.2606, "lr": 3.9130611411668507e-05, "epoch": 7.5584719334719335, "percentage": 37.79, "elapsed_time": "0:42:15", "remaining_time": "1:09:33", "throughput": 1033.19, "total_tokens": 2619408} {"current_steps": 29090, "total_steps": 76960, "loss": 0.2547, "lr": 3.912593398572911e-05, "epoch": 7.5597713097713095, "percentage": 37.8, "elapsed_time": "0:42:15", "remaining_time": "1:09:32", "throughput": 1033.2, "total_tokens": 2619872} {"current_steps": 29095, "total_steps": 76960, "loss": 0.2181, "lr": 3.912125583327939e-05, "epoch": 7.561070686070686, "percentage": 37.81, "elapsed_time": "0:42:16", "remaining_time": "1:09:32", "throughput": 1033.22, "total_tokens": 2620352} {"current_steps": 29100, "total_steps": 76960, "loss": 0.2309, "lr": 3.911657695455996e-05, "epoch": 7.5623700623700625, "percentage": 37.81, "elapsed_time": "0:42:16", "remaining_time": "1:09:31", "throughput": 1033.21, "total_tokens": 2620752} {"current_steps": 29105, "total_steps": 76960, "loss": 0.237, "lr": 3.9111897349811454e-05, "epoch": 7.5636694386694385, "percentage": 37.82, "elapsed_time": "0:42:16", "remaining_time": "1:09:31", "throughput": 1033.21, "total_tokens": 2621184} {"current_steps": 29110, "total_steps": 76960, "loss": 0.1889, "lr": 3.910721701927454e-05, "epoch": 7.564968814968815, "percentage": 37.82, "elapsed_time": "0:42:17", "remaining_time": "1:09:30", "throughput": 1033.22, "total_tokens": 2621648} {"current_steps": 29115, "total_steps": 76960, "loss": 0.1525, "lr": 3.910253596318994e-05, "epoch": 7.5662681912681915, "percentage": 37.83, "elapsed_time": "0:42:17", "remaining_time": "1:09:30", "throughput": 1033.23, "total_tokens": 2622096} {"current_steps": 29120, "total_steps": 76960, "loss": 0.2846, "lr": 3.90978541817984e-05, "epoch": 7.5675675675675675, "percentage": 37.84, "elapsed_time": "0:42:18", "remaining_time": "1:09:29", "throughput": 1033.22, "total_tokens": 2622496} {"current_steps": 29125, "total_steps": 76960, "loss": 0.2917, "lr": 3.909317167534071e-05, "epoch": 7.568866943866944, "percentage": 37.84, "elapsed_time": "0:42:18", "remaining_time": "1:09:29", "throughput": 1033.22, "total_tokens": 2622944} {"current_steps": 29130, "total_steps": 76960, "loss": 0.312, "lr": 3.9088488444057704e-05, "epoch": 7.5701663201663205, "percentage": 37.85, "elapsed_time": "0:42:19", "remaining_time": "1:09:28", "throughput": 1033.22, "total_tokens": 2623376} {"current_steps": 29135, "total_steps": 76960, "loss": 0.3056, "lr": 3.9083804488190235e-05, "epoch": 7.571465696465697, "percentage": 37.86, "elapsed_time": "0:42:19", "remaining_time": "1:09:28", "throughput": 1033.23, "total_tokens": 2623824} {"current_steps": 29140, "total_steps": 76960, "loss": 0.2365, "lr": 3.9079119807979214e-05, "epoch": 7.572765072765073, "percentage": 37.86, "elapsed_time": "0:42:19", "remaining_time": "1:09:28", "throughput": 1033.25, "total_tokens": 2624304} {"current_steps": 29145, "total_steps": 76960, "loss": 0.2324, "lr": 3.907443440366556e-05, "epoch": 7.5740644490644495, "percentage": 37.87, "elapsed_time": "0:42:20", "remaining_time": "1:09:27", "throughput": 1033.24, "total_tokens": 2624720} {"current_steps": 29150, "total_steps": 76960, "loss": 0.3138, "lr": 3.906974827549026e-05, "epoch": 7.575363825363826, "percentage": 37.88, "elapsed_time": "0:42:20", "remaining_time": "1:09:27", "throughput": 1033.27, "total_tokens": 2625216} {"current_steps": 29155, "total_steps": 76960, "loss": 0.2704, "lr": 3.906506142369433e-05, "epoch": 7.576663201663202, "percentage": 37.88, "elapsed_time": "0:42:21", "remaining_time": "1:09:26", "throughput": 1033.27, "total_tokens": 2625648} {"current_steps": 29160, "total_steps": 76960, "loss": 0.3021, "lr": 3.906037384851881e-05, "epoch": 7.577962577962578, "percentage": 37.89, "elapsed_time": "0:42:21", "remaining_time": "1:09:26", "throughput": 1033.28, "total_tokens": 2626112} {"current_steps": 29165, "total_steps": 76960, "loss": 0.2599, "lr": 3.90556855502048e-05, "epoch": 7.579261954261955, "percentage": 37.9, "elapsed_time": "0:42:21", "remaining_time": "1:09:25", "throughput": 1033.3, "total_tokens": 2626576} {"current_steps": 29170, "total_steps": 76960, "loss": 0.2535, "lr": 3.90509965289934e-05, "epoch": 7.580561330561331, "percentage": 37.9, "elapsed_time": "0:42:22", "remaining_time": "1:09:25", "throughput": 1033.3, "total_tokens": 2627024} {"current_steps": 29175, "total_steps": 76960, "loss": 0.2599, "lr": 3.90463067851258e-05, "epoch": 7.581860706860707, "percentage": 37.91, "elapsed_time": "0:42:22", "remaining_time": "1:09:24", "throughput": 1033.32, "total_tokens": 2627504} {"current_steps": 29180, "total_steps": 76960, "loss": 0.2216, "lr": 3.904161631884318e-05, "epoch": 7.583160083160083, "percentage": 37.92, "elapsed_time": "0:42:23", "remaining_time": "1:09:24", "throughput": 1033.34, "total_tokens": 2627984} {"current_steps": 29185, "total_steps": 76960, "loss": 0.2948, "lr": 3.903692513038677e-05, "epoch": 7.58445945945946, "percentage": 37.92, "elapsed_time": "0:42:23", "remaining_time": "1:09:23", "throughput": 1033.34, "total_tokens": 2628400} {"current_steps": 29190, "total_steps": 76960, "loss": 0.2457, "lr": 3.903223321999786e-05, "epoch": 7.585758835758836, "percentage": 37.93, "elapsed_time": "0:42:24", "remaining_time": "1:09:23", "throughput": 1033.34, "total_tokens": 2628832} {"current_steps": 29195, "total_steps": 76960, "loss": 0.3191, "lr": 3.9027540587917744e-05, "epoch": 7.587058212058212, "percentage": 37.94, "elapsed_time": "0:42:24", "remaining_time": "1:09:22", "throughput": 1033.35, "total_tokens": 2629296} {"current_steps": 29200, "total_steps": 76960, "loss": 0.1904, "lr": 3.902284723438778e-05, "epoch": 7.588357588357589, "percentage": 37.94, "elapsed_time": "0:42:24", "remaining_time": "1:09:22", "throughput": 1033.36, "total_tokens": 2629760} {"current_steps": 29205, "total_steps": 76960, "loss": 0.1612, "lr": 3.901815315964935e-05, "epoch": 7.589656964656965, "percentage": 37.95, "elapsed_time": "0:42:25", "remaining_time": "1:09:21", "throughput": 1033.37, "total_tokens": 2630208} {"current_steps": 29210, "total_steps": 76960, "loss": 0.1974, "lr": 3.901345836394387e-05, "epoch": 7.590956340956341, "percentage": 37.95, "elapsed_time": "0:42:25", "remaining_time": "1:09:21", "throughput": 1033.37, "total_tokens": 2630640} {"current_steps": 29215, "total_steps": 76960, "loss": 0.2689, "lr": 3.900876284751279e-05, "epoch": 7.592255717255718, "percentage": 37.96, "elapsed_time": "0:42:26", "remaining_time": "1:09:21", "throughput": 1033.39, "total_tokens": 2631120} {"current_steps": 29220, "total_steps": 76960, "loss": 0.268, "lr": 3.900406661059762e-05, "epoch": 7.593555093555094, "percentage": 37.97, "elapsed_time": "0:42:26", "remaining_time": "1:09:20", "throughput": 1033.4, "total_tokens": 2631584} {"current_steps": 29225, "total_steps": 76960, "loss": 0.3147, "lr": 3.899936965343989e-05, "epoch": 7.59485446985447, "percentage": 37.97, "elapsed_time": "0:42:26", "remaining_time": "1:09:20", "throughput": 1033.4, "total_tokens": 2632016} {"current_steps": 29230, "total_steps": 76960, "loss": 0.1798, "lr": 3.899467197628116e-05, "epoch": 7.596153846153846, "percentage": 37.98, "elapsed_time": "0:42:27", "remaining_time": "1:09:19", "throughput": 1033.42, "total_tokens": 2632496} {"current_steps": 29235, "total_steps": 76960, "loss": 0.1547, "lr": 3.8989973579363045e-05, "epoch": 7.597453222453223, "percentage": 37.99, "elapsed_time": "0:42:27", "remaining_time": "1:09:19", "throughput": 1033.41, "total_tokens": 2632896} {"current_steps": 29240, "total_steps": 76960, "loss": 0.2107, "lr": 3.898527446292718e-05, "epoch": 7.598752598752599, "percentage": 37.99, "elapsed_time": "0:42:28", "remaining_time": "1:09:18", "throughput": 1033.41, "total_tokens": 2633328} {"current_steps": 29245, "total_steps": 76960, "loss": 0.1366, "lr": 3.898057462721525e-05, "epoch": 7.600051975051975, "percentage": 38.0, "elapsed_time": "0:42:28", "remaining_time": "1:09:18", "throughput": 1033.41, "total_tokens": 2633760} {"current_steps": 29250, "total_steps": 76960, "loss": 0.0891, "lr": 3.897587407246898e-05, "epoch": 7.601351351351351, "percentage": 38.01, "elapsed_time": "0:42:29", "remaining_time": "1:09:17", "throughput": 1033.41, "total_tokens": 2634176} {"current_steps": 29255, "total_steps": 76960, "loss": 0.1862, "lr": 3.89711727989301e-05, "epoch": 7.602650727650728, "percentage": 38.01, "elapsed_time": "0:42:29", "remaining_time": "1:09:17", "throughput": 1033.43, "total_tokens": 2634656} {"current_steps": 29260, "total_steps": 76960, "loss": 0.1929, "lr": 3.8966470806840426e-05, "epoch": 7.603950103950104, "percentage": 38.02, "elapsed_time": "0:42:29", "remaining_time": "1:09:16", "throughput": 1033.43, "total_tokens": 2635088} {"current_steps": 29265, "total_steps": 76960, "loss": 0.1555, "lr": 3.896176809644178e-05, "epoch": 7.60524948024948, "percentage": 38.03, "elapsed_time": "0:42:30", "remaining_time": "1:09:16", "throughput": 1033.42, "total_tokens": 2635504} {"current_steps": 29270, "total_steps": 76960, "loss": 0.3356, "lr": 3.895706466797601e-05, "epoch": 7.606548856548857, "percentage": 38.03, "elapsed_time": "0:42:30", "remaining_time": "1:09:15", "throughput": 1033.42, "total_tokens": 2635920} {"current_steps": 29275, "total_steps": 76960, "loss": 0.2226, "lr": 3.895236052168505e-05, "epoch": 7.607848232848233, "percentage": 38.04, "elapsed_time": "0:42:31", "remaining_time": "1:09:15", "throughput": 1033.44, "total_tokens": 2636416} {"current_steps": 29280, "total_steps": 76960, "loss": 0.2398, "lr": 3.8947655657810805e-05, "epoch": 7.609147609147609, "percentage": 38.05, "elapsed_time": "0:42:31", "remaining_time": "1:09:14", "throughput": 1033.44, "total_tokens": 2636832} {"current_steps": 29285, "total_steps": 76960, "loss": 0.3526, "lr": 3.894295007659527e-05, "epoch": 7.610446985446986, "percentage": 38.05, "elapsed_time": "0:42:31", "remaining_time": "1:09:14", "throughput": 1033.46, "total_tokens": 2637312} {"current_steps": 29290, "total_steps": 76960, "loss": 0.3459, "lr": 3.893824377828045e-05, "epoch": 7.611746361746362, "percentage": 38.06, "elapsed_time": "0:42:32", "remaining_time": "1:09:13", "throughput": 1033.46, "total_tokens": 2637760} {"current_steps": 29295, "total_steps": 76960, "loss": 0.1926, "lr": 3.89335367631084e-05, "epoch": 7.613045738045738, "percentage": 38.07, "elapsed_time": "0:42:32", "remaining_time": "1:09:13", "throughput": 1033.47, "total_tokens": 2638208} {"current_steps": 29300, "total_steps": 76960, "loss": 0.3441, "lr": 3.892882903132121e-05, "epoch": 7.614345114345114, "percentage": 38.07, "elapsed_time": "0:42:33", "remaining_time": "1:09:13", "throughput": 1033.47, "total_tokens": 2638640} {"current_steps": 29305, "total_steps": 76960, "loss": 0.2186, "lr": 3.8924120583160985e-05, "epoch": 7.615644490644491, "percentage": 38.08, "elapsed_time": "0:42:33", "remaining_time": "1:09:12", "throughput": 1033.47, "total_tokens": 2639072} {"current_steps": 29310, "total_steps": 76960, "loss": 0.1861, "lr": 3.8919411418869904e-05, "epoch": 7.616943866943867, "percentage": 38.08, "elapsed_time": "0:42:34", "remaining_time": "1:09:12", "throughput": 1033.46, "total_tokens": 2639472} {"current_steps": 29315, "total_steps": 76960, "loss": 0.2713, "lr": 3.891470153869016e-05, "epoch": 7.618243243243243, "percentage": 38.09, "elapsed_time": "0:42:34", "remaining_time": "1:09:11", "throughput": 1033.47, "total_tokens": 2639936} {"current_steps": 29320, "total_steps": 76960, "loss": 0.2137, "lr": 3.8909990942863976e-05, "epoch": 7.61954261954262, "percentage": 38.1, "elapsed_time": "0:42:34", "remaining_time": "1:09:11", "throughput": 1033.48, "total_tokens": 2640384} {"current_steps": 29325, "total_steps": 76960, "loss": 0.2626, "lr": 3.890527963163363e-05, "epoch": 7.620841995841996, "percentage": 38.1, "elapsed_time": "0:42:35", "remaining_time": "1:09:10", "throughput": 1033.48, "total_tokens": 2640816} {"current_steps": 29330, "total_steps": 76960, "loss": 0.2237, "lr": 3.890056760524143e-05, "epoch": 7.622141372141372, "percentage": 38.11, "elapsed_time": "0:42:35", "remaining_time": "1:09:10", "throughput": 1033.5, "total_tokens": 2641296} {"current_steps": 29335, "total_steps": 76960, "loss": 0.2651, "lr": 3.8895854863929725e-05, "epoch": 7.623440748440748, "percentage": 38.12, "elapsed_time": "0:42:36", "remaining_time": "1:09:09", "throughput": 1033.5, "total_tokens": 2641728} {"current_steps": 29340, "total_steps": 76960, "loss": 0.273, "lr": 3.889114140794089e-05, "epoch": 7.624740124740125, "percentage": 38.12, "elapsed_time": "0:42:36", "remaining_time": "1:09:09", "throughput": 1033.51, "total_tokens": 2642176} {"current_steps": 29345, "total_steps": 76960, "loss": 0.2187, "lr": 3.8886427237517344e-05, "epoch": 7.626039501039501, "percentage": 38.13, "elapsed_time": "0:42:36", "remaining_time": "1:09:08", "throughput": 1033.51, "total_tokens": 2642624} {"current_steps": 29350, "total_steps": 76960, "loss": 0.2721, "lr": 3.8881712352901536e-05, "epoch": 7.627338877338877, "percentage": 38.14, "elapsed_time": "0:42:37", "remaining_time": "1:09:08", "throughput": 1033.52, "total_tokens": 2643072} {"current_steps": 29355, "total_steps": 76960, "loss": 0.2621, "lr": 3.887699675433596e-05, "epoch": 7.628638253638254, "percentage": 38.14, "elapsed_time": "0:42:37", "remaining_time": "1:09:07", "throughput": 1033.51, "total_tokens": 2643488} {"current_steps": 29360, "total_steps": 76960, "loss": 0.1776, "lr": 3.887228044206314e-05, "epoch": 7.62993762993763, "percentage": 38.15, "elapsed_time": "0:42:38", "remaining_time": "1:09:07", "throughput": 1033.53, "total_tokens": 2643968} {"current_steps": 29365, "total_steps": 76960, "loss": 0.3351, "lr": 3.8867563416325644e-05, "epoch": 7.631237006237006, "percentage": 38.16, "elapsed_time": "0:42:38", "remaining_time": "1:09:06", "throughput": 1033.53, "total_tokens": 2644400} {"current_steps": 29370, "total_steps": 76960, "loss": 0.205, "lr": 3.886284567736608e-05, "epoch": 7.632536382536383, "percentage": 38.16, "elapsed_time": "0:42:39", "remaining_time": "1:09:06", "throughput": 1033.55, "total_tokens": 2644864} {"current_steps": 29375, "total_steps": 76960, "loss": 0.324, "lr": 3.8858127225427086e-05, "epoch": 7.633835758835759, "percentage": 38.17, "elapsed_time": "0:42:39", "remaining_time": "1:09:06", "throughput": 1033.55, "total_tokens": 2645296} {"current_steps": 29380, "total_steps": 76960, "loss": 0.2395, "lr": 3.8853408060751315e-05, "epoch": 7.635135135135135, "percentage": 38.18, "elapsed_time": "0:42:39", "remaining_time": "1:09:05", "throughput": 1033.54, "total_tokens": 2645712} {"current_steps": 29385, "total_steps": 76960, "loss": 0.3249, "lr": 3.884868818358151e-05, "epoch": 7.636434511434511, "percentage": 38.18, "elapsed_time": "0:42:40", "remaining_time": "1:09:05", "throughput": 1033.55, "total_tokens": 2646160} {"current_steps": 29390, "total_steps": 76960, "loss": 0.1661, "lr": 3.884396759416039e-05, "epoch": 7.637733887733888, "percentage": 38.19, "elapsed_time": "0:42:40", "remaining_time": "1:09:04", "throughput": 1033.55, "total_tokens": 2646592} {"current_steps": 29395, "total_steps": 76960, "loss": 0.1723, "lr": 3.8839246292730756e-05, "epoch": 7.639033264033264, "percentage": 38.2, "elapsed_time": "0:42:41", "remaining_time": "1:09:04", "throughput": 1033.56, "total_tokens": 2647056} {"current_steps": 29400, "total_steps": 76960, "loss": 0.3965, "lr": 3.8834524279535436e-05, "epoch": 7.64033264033264, "percentage": 38.2, "elapsed_time": "0:42:41", "remaining_time": "1:09:03", "throughput": 1033.58, "total_tokens": 2647536} {"current_steps": 29405, "total_steps": 76960, "loss": 0.2297, "lr": 3.882980155481727e-05, "epoch": 7.641632016632016, "percentage": 38.21, "elapsed_time": "0:42:41", "remaining_time": "1:09:03", "throughput": 1033.59, "total_tokens": 2648000} {"current_steps": 29410, "total_steps": 76960, "loss": 0.2184, "lr": 3.8825078118819155e-05, "epoch": 7.642931392931393, "percentage": 38.21, "elapsed_time": "0:42:42", "remaining_time": "1:09:02", "throughput": 1033.59, "total_tokens": 2648432} {"current_steps": 29415, "total_steps": 76960, "loss": 0.2869, "lr": 3.882035397178403e-05, "epoch": 7.644230769230769, "percentage": 38.22, "elapsed_time": "0:42:42", "remaining_time": "1:09:02", "throughput": 1033.59, "total_tokens": 2648864} {"current_steps": 29420, "total_steps": 76960, "loss": 0.2811, "lr": 3.8815629113954847e-05, "epoch": 7.645530145530145, "percentage": 38.23, "elapsed_time": "0:42:43", "remaining_time": "1:09:01", "throughput": 1033.59, "total_tokens": 2649280} {"current_steps": 29425, "total_steps": 76960, "loss": 0.2018, "lr": 3.881090354557463e-05, "epoch": 7.646829521829522, "percentage": 38.23, "elapsed_time": "0:42:43", "remaining_time": "1:09:01", "throughput": 1033.61, "total_tokens": 2649760} {"current_steps": 29430, "total_steps": 76960, "loss": 0.291, "lr": 3.880617726688641e-05, "epoch": 7.648128898128898, "percentage": 38.24, "elapsed_time": "0:42:44", "remaining_time": "1:09:00", "throughput": 1033.62, "total_tokens": 2650224} {"current_steps": 29435, "total_steps": 76960, "loss": 0.2703, "lr": 3.8801450278133264e-05, "epoch": 7.649428274428274, "percentage": 38.25, "elapsed_time": "0:42:44", "remaining_time": "1:09:00", "throughput": 1033.65, "total_tokens": 2650720} {"current_steps": 29440, "total_steps": 76960, "loss": 0.309, "lr": 3.879672257955831e-05, "epoch": 7.650727650727651, "percentage": 38.25, "elapsed_time": "0:42:44", "remaining_time": "1:09:00", "throughput": 1033.66, "total_tokens": 2651184} {"current_steps": 29445, "total_steps": 76960, "loss": 0.2931, "lr": 3.8791994171404694e-05, "epoch": 7.652027027027027, "percentage": 38.26, "elapsed_time": "0:42:45", "remaining_time": "1:08:59", "throughput": 1033.68, "total_tokens": 2651664} {"current_steps": 29450, "total_steps": 76960, "loss": 0.2464, "lr": 3.8787265053915603e-05, "epoch": 7.653326403326403, "percentage": 38.27, "elapsed_time": "0:42:45", "remaining_time": "1:08:59", "throughput": 1033.68, "total_tokens": 2652096} {"current_steps": 29455, "total_steps": 76960, "loss": 0.2635, "lr": 3.878253522733426e-05, "epoch": 7.654625779625779, "percentage": 38.27, "elapsed_time": "0:42:46", "remaining_time": "1:08:58", "throughput": 1033.69, "total_tokens": 2652560} {"current_steps": 29460, "total_steps": 76960, "loss": 0.2551, "lr": 3.8777804691903916e-05, "epoch": 7.655925155925156, "percentage": 38.28, "elapsed_time": "0:42:46", "remaining_time": "1:08:58", "throughput": 1033.7, "total_tokens": 2653024} {"current_steps": 29465, "total_steps": 76960, "loss": 0.2312, "lr": 3.877307344786788e-05, "epoch": 7.657224532224532, "percentage": 38.29, "elapsed_time": "0:42:46", "remaining_time": "1:08:57", "throughput": 1033.7, "total_tokens": 2653456} {"current_steps": 29470, "total_steps": 76960, "loss": 0.3239, "lr": 3.876834149546948e-05, "epoch": 7.658523908523908, "percentage": 38.29, "elapsed_time": "0:42:47", "remaining_time": "1:08:57", "throughput": 1033.72, "total_tokens": 2653936} {"current_steps": 29475, "total_steps": 76960, "loss": 0.2577, "lr": 3.8763608834952094e-05, "epoch": 7.659823284823284, "percentage": 38.3, "elapsed_time": "0:42:47", "remaining_time": "1:08:56", "throughput": 1033.75, "total_tokens": 2654448} {"current_steps": 29480, "total_steps": 76960, "loss": 0.2197, "lr": 3.875887546655911e-05, "epoch": 7.661122661122661, "percentage": 38.31, "elapsed_time": "0:42:48", "remaining_time": "1:08:56", "throughput": 1033.77, "total_tokens": 2654912} {"current_steps": 29485, "total_steps": 76960, "loss": 0.2222, "lr": 3.8754141390533974e-05, "epoch": 7.662422037422037, "percentage": 38.31, "elapsed_time": "0:42:48", "remaining_time": "1:08:55", "throughput": 1033.77, "total_tokens": 2655344} {"current_steps": 29490, "total_steps": 76960, "loss": 0.2347, "lr": 3.874940660712018e-05, "epoch": 7.663721413721413, "percentage": 38.32, "elapsed_time": "0:42:49", "remaining_time": "1:08:55", "throughput": 1033.77, "total_tokens": 2655776} {"current_steps": 29495, "total_steps": 76960, "loss": 0.2601, "lr": 3.8744671116561216e-05, "epoch": 7.66502079002079, "percentage": 38.33, "elapsed_time": "0:42:49", "remaining_time": "1:08:54", "throughput": 1033.77, "total_tokens": 2656224} {"current_steps": 29500, "total_steps": 76960, "loss": 0.2548, "lr": 3.873993491910065e-05, "epoch": 7.666320166320166, "percentage": 38.33, "elapsed_time": "0:42:49", "remaining_time": "1:08:54", "throughput": 1033.78, "total_tokens": 2656672} {"current_steps": 29505, "total_steps": 76960, "loss": 0.2938, "lr": 3.8735198014982064e-05, "epoch": 7.667619542619542, "percentage": 38.34, "elapsed_time": "0:42:50", "remaining_time": "1:08:53", "throughput": 1033.79, "total_tokens": 2657136} {"current_steps": 29510, "total_steps": 76960, "loss": 0.2888, "lr": 3.873046040444909e-05, "epoch": 7.668918918918919, "percentage": 38.34, "elapsed_time": "0:42:50", "remaining_time": "1:08:53", "throughput": 1033.79, "total_tokens": 2657568} {"current_steps": 29515, "total_steps": 76960, "loss": 0.2741, "lr": 3.8725722087745384e-05, "epoch": 7.670218295218295, "percentage": 38.35, "elapsed_time": "0:42:51", "remaining_time": "1:08:53", "throughput": 1033.81, "total_tokens": 2658032} {"current_steps": 29520, "total_steps": 76960, "loss": 0.2934, "lr": 3.872098306511463e-05, "epoch": 7.671517671517671, "percentage": 38.36, "elapsed_time": "0:42:51", "remaining_time": "1:08:52", "throughput": 1033.82, "total_tokens": 2658496} {"current_steps": 29525, "total_steps": 76960, "loss": 0.2747, "lr": 3.871624333680057e-05, "epoch": 7.672817047817047, "percentage": 38.36, "elapsed_time": "0:42:51", "remaining_time": "1:08:52", "throughput": 1033.83, "total_tokens": 2658960} {"current_steps": 29530, "total_steps": 76960, "loss": 0.3088, "lr": 3.871150290304698e-05, "epoch": 7.674116424116424, "percentage": 38.37, "elapsed_time": "0:42:52", "remaining_time": "1:08:51", "throughput": 1033.83, "total_tokens": 2659376} {"current_steps": 29535, "total_steps": 76960, "loss": 0.2433, "lr": 3.870676176409767e-05, "epoch": 7.6754158004158, "percentage": 38.38, "elapsed_time": "0:42:52", "remaining_time": "1:08:51", "throughput": 1033.83, "total_tokens": 2659824} {"current_steps": 29540, "total_steps": 76960, "loss": 0.271, "lr": 3.870201992019645e-05, "epoch": 7.6767151767151764, "percentage": 38.38, "elapsed_time": "0:42:53", "remaining_time": "1:08:50", "throughput": 1033.85, "total_tokens": 2660304} {"current_steps": 29545, "total_steps": 76960, "loss": 0.2718, "lr": 3.869727737158722e-05, "epoch": 7.678014553014553, "percentage": 38.39, "elapsed_time": "0:42:53", "remaining_time": "1:08:50", "throughput": 1033.87, "total_tokens": 2660784} {"current_steps": 29550, "total_steps": 76960, "loss": 0.2542, "lr": 3.86925341185139e-05, "epoch": 7.679313929313929, "percentage": 38.4, "elapsed_time": "0:42:54", "remaining_time": "1:08:49", "throughput": 1033.87, "total_tokens": 2661200} {"current_steps": 29555, "total_steps": 76960, "loss": 0.239, "lr": 3.8687790161220414e-05, "epoch": 7.6806133056133055, "percentage": 38.4, "elapsed_time": "0:42:54", "remaining_time": "1:08:49", "throughput": 1033.87, "total_tokens": 2661632} {"current_steps": 29560, "total_steps": 76960, "loss": 0.2782, "lr": 3.8683045499950774e-05, "epoch": 7.6819126819126815, "percentage": 38.41, "elapsed_time": "0:42:54", "remaining_time": "1:08:48", "throughput": 1033.89, "total_tokens": 2662112} {"current_steps": 29565, "total_steps": 76960, "loss": 0.252, "lr": 3.8678300134948996e-05, "epoch": 7.683212058212058, "percentage": 38.42, "elapsed_time": "0:42:55", "remaining_time": "1:08:48", "throughput": 1033.9, "total_tokens": 2662576} {"current_steps": 29570, "total_steps": 76960, "loss": 0.1938, "lr": 3.8673554066459136e-05, "epoch": 7.6845114345114345, "percentage": 38.42, "elapsed_time": "0:42:55", "remaining_time": "1:08:47", "throughput": 1033.9, "total_tokens": 2663008} {"current_steps": 29575, "total_steps": 76960, "loss": 0.2033, "lr": 3.866880729472529e-05, "epoch": 7.6858108108108105, "percentage": 38.43, "elapsed_time": "0:42:56", "remaining_time": "1:08:47", "throughput": 1033.92, "total_tokens": 2663488} {"current_steps": 29580, "total_steps": 76960, "loss": 0.1557, "lr": 3.8664059819991586e-05, "epoch": 7.6871101871101875, "percentage": 38.44, "elapsed_time": "0:42:56", "remaining_time": "1:08:46", "throughput": 1033.95, "total_tokens": 2663984} {"current_steps": 29585, "total_steps": 76960, "loss": 0.2696, "lr": 3.865931164250219e-05, "epoch": 7.6884095634095635, "percentage": 38.44, "elapsed_time": "0:42:56", "remaining_time": "1:08:46", "throughput": 1033.95, "total_tokens": 2664432} {"current_steps": 29590, "total_steps": 76960, "loss": 0.154, "lr": 3.865456276250131e-05, "epoch": 7.6897089397089395, "percentage": 38.45, "elapsed_time": "0:42:57", "remaining_time": "1:08:46", "throughput": 1033.96, "total_tokens": 2664880} {"current_steps": 29595, "total_steps": 76960, "loss": 0.252, "lr": 3.864981318023319e-05, "epoch": 7.6910083160083165, "percentage": 38.46, "elapsed_time": "0:42:57", "remaining_time": "1:08:45", "throughput": 1033.97, "total_tokens": 2665328} {"current_steps": 29600, "total_steps": 76960, "loss": 0.3642, "lr": 3.8645062895942096e-05, "epoch": 7.6923076923076925, "percentage": 38.46, "elapsed_time": "0:42:58", "remaining_time": "1:08:45", "throughput": 1033.99, "total_tokens": 2665808} {"current_steps": 29605, "total_steps": 76960, "loss": 0.2763, "lr": 3.864031190987234e-05, "epoch": 7.6936070686070686, "percentage": 38.47, "elapsed_time": "0:42:58", "remaining_time": "1:08:44", "throughput": 1033.99, "total_tokens": 2666240} {"current_steps": 29610, "total_steps": 76960, "loss": 0.3265, "lr": 3.863556022226827e-05, "epoch": 7.694906444906445, "percentage": 38.47, "elapsed_time": "0:42:59", "remaining_time": "1:08:44", "throughput": 1034.0, "total_tokens": 2666704} {"current_steps": 29615, "total_steps": 76960, "loss": 0.2298, "lr": 3.8630807833374286e-05, "epoch": 7.6962058212058215, "percentage": 38.48, "elapsed_time": "0:42:59", "remaining_time": "1:08:43", "throughput": 1034.01, "total_tokens": 2667152} {"current_steps": 29620, "total_steps": 76960, "loss": 0.2479, "lr": 3.862605474343478e-05, "epoch": 7.697505197505198, "percentage": 38.49, "elapsed_time": "0:42:59", "remaining_time": "1:08:43", "throughput": 1034.01, "total_tokens": 2667584} {"current_steps": 29625, "total_steps": 76960, "loss": 0.1863, "lr": 3.862130095269423e-05, "epoch": 7.698804573804574, "percentage": 38.49, "elapsed_time": "0:43:00", "remaining_time": "1:08:42", "throughput": 1034.02, "total_tokens": 2668048} {"current_steps": 29630, "total_steps": 76960, "loss": 0.1619, "lr": 3.861654646139712e-05, "epoch": 7.70010395010395, "percentage": 38.5, "elapsed_time": "0:43:00", "remaining_time": "1:08:42", "throughput": 1034.04, "total_tokens": 2668528} {"current_steps": 29635, "total_steps": 76960, "loss": 0.2736, "lr": 3.861179126978798e-05, "epoch": 7.701403326403327, "percentage": 38.51, "elapsed_time": "0:43:01", "remaining_time": "1:08:41", "throughput": 1034.05, "total_tokens": 2669008} {"current_steps": 29640, "total_steps": 76960, "loss": 0.2128, "lr": 3.8607035378111375e-05, "epoch": 7.702702702702703, "percentage": 38.51, "elapsed_time": "0:43:01", "remaining_time": "1:08:41", "throughput": 1034.07, "total_tokens": 2669488} {"current_steps": 29645, "total_steps": 76960, "loss": 0.1183, "lr": 3.860227878661189e-05, "epoch": 7.704002079002079, "percentage": 38.52, "elapsed_time": "0:43:01", "remaining_time": "1:08:40", "throughput": 1034.09, "total_tokens": 2669952} {"current_steps": 29650, "total_steps": 76960, "loss": 0.3794, "lr": 3.859752149553419e-05, "epoch": 7.705301455301456, "percentage": 38.53, "elapsed_time": "0:43:02", "remaining_time": "1:08:40", "throughput": 1034.09, "total_tokens": 2670400} {"current_steps": 29655, "total_steps": 76960, "loss": 0.1656, "lr": 3.859276350512292e-05, "epoch": 7.706600831600832, "percentage": 38.53, "elapsed_time": "0:43:02", "remaining_time": "1:08:39", "throughput": 1034.11, "total_tokens": 2670864} {"current_steps": 29660, "total_steps": 76960, "loss": 0.3193, "lr": 3.8588004815622805e-05, "epoch": 7.707900207900208, "percentage": 38.54, "elapsed_time": "0:43:03", "remaining_time": "1:08:39", "throughput": 1034.11, "total_tokens": 2671312} {"current_steps": 29665, "total_steps": 76960, "loss": 0.226, "lr": 3.8583245427278584e-05, "epoch": 7.709199584199585, "percentage": 38.55, "elapsed_time": "0:43:03", "remaining_time": "1:08:39", "throughput": 1034.13, "total_tokens": 2671776} {"current_steps": 29670, "total_steps": 76960, "loss": 0.2546, "lr": 3.8578485340335035e-05, "epoch": 7.710498960498961, "percentage": 38.55, "elapsed_time": "0:43:04", "remaining_time": "1:08:38", "throughput": 1034.13, "total_tokens": 2672208} {"current_steps": 29675, "total_steps": 76960, "loss": 0.2781, "lr": 3.857372455503697e-05, "epoch": 7.711798336798337, "percentage": 38.56, "elapsed_time": "0:43:04", "remaining_time": "1:08:38", "throughput": 1034.13, "total_tokens": 2672656} {"current_steps": 29680, "total_steps": 76960, "loss": 0.1948, "lr": 3.856896307162925e-05, "epoch": 7.713097713097713, "percentage": 38.57, "elapsed_time": "0:43:04", "remaining_time": "1:08:37", "throughput": 1034.13, "total_tokens": 2673072} {"current_steps": 29685, "total_steps": 76960, "loss": 0.3171, "lr": 3.856420089035676e-05, "epoch": 7.71439708939709, "percentage": 38.57, "elapsed_time": "0:43:05", "remaining_time": "1:08:37", "throughput": 1034.13, "total_tokens": 2673504} {"current_steps": 29690, "total_steps": 76960, "loss": 0.2143, "lr": 3.855943801146441e-05, "epoch": 7.715696465696466, "percentage": 38.58, "elapsed_time": "0:43:05", "remaining_time": "1:08:36", "throughput": 1034.14, "total_tokens": 2673968} {"current_steps": 29695, "total_steps": 76960, "loss": 0.2907, "lr": 3.855467443519718e-05, "epoch": 7.716995841995842, "percentage": 38.58, "elapsed_time": "0:43:06", "remaining_time": "1:08:36", "throughput": 1034.13, "total_tokens": 2674384} {"current_steps": 29700, "total_steps": 76960, "loss": 0.268, "lr": 3.854991016180005e-05, "epoch": 7.718295218295218, "percentage": 38.59, "elapsed_time": "0:43:06", "remaining_time": "1:08:35", "throughput": 1034.14, "total_tokens": 2674832} {"current_steps": 29705, "total_steps": 76960, "loss": 0.1984, "lr": 3.854514519151807e-05, "epoch": 7.719594594594595, "percentage": 38.6, "elapsed_time": "0:43:06", "remaining_time": "1:08:35", "throughput": 1034.15, "total_tokens": 2675296} {"current_steps": 29710, "total_steps": 76960, "loss": 0.2075, "lr": 3.854037952459628e-05, "epoch": 7.720893970893971, "percentage": 38.6, "elapsed_time": "0:43:07", "remaining_time": "1:08:34", "throughput": 1034.15, "total_tokens": 2675728} {"current_steps": 29715, "total_steps": 76960, "loss": 0.2335, "lr": 3.853561316127981e-05, "epoch": 7.722193347193347, "percentage": 38.61, "elapsed_time": "0:43:07", "remaining_time": "1:08:34", "throughput": 1034.17, "total_tokens": 2676192} {"current_steps": 29720, "total_steps": 76960, "loss": 0.2429, "lr": 3.853084610181378e-05, "epoch": 7.723492723492724, "percentage": 38.62, "elapsed_time": "0:43:08", "remaining_time": "1:08:33", "throughput": 1034.15, "total_tokens": 2676592} {"current_steps": 29725, "total_steps": 76960, "loss": 0.2507, "lr": 3.852607834644337e-05, "epoch": 7.7247920997921, "percentage": 38.62, "elapsed_time": "0:43:08", "remaining_time": "1:08:33", "throughput": 1034.15, "total_tokens": 2677024} {"current_steps": 29730, "total_steps": 76960, "loss": 0.1949, "lr": 3.852130989541379e-05, "epoch": 7.726091476091476, "percentage": 38.63, "elapsed_time": "0:43:09", "remaining_time": "1:08:33", "throughput": 1034.16, "total_tokens": 2677472} {"current_steps": 29735, "total_steps": 76960, "loss": 0.2853, "lr": 3.851654074897029e-05, "epoch": 7.727390852390853, "percentage": 38.64, "elapsed_time": "0:43:09", "remaining_time": "1:08:32", "throughput": 1034.16, "total_tokens": 2677904} {"current_steps": 29740, "total_steps": 76960, "loss": 0.2172, "lr": 3.851177090735815e-05, "epoch": 7.728690228690229, "percentage": 38.64, "elapsed_time": "0:43:09", "remaining_time": "1:08:32", "throughput": 1034.17, "total_tokens": 2678352} {"current_steps": 29745, "total_steps": 76960, "loss": 0.2688, "lr": 3.850700037082268e-05, "epoch": 7.729989604989605, "percentage": 38.65, "elapsed_time": "0:43:10", "remaining_time": "1:08:31", "throughput": 1034.18, "total_tokens": 2678816} {"current_steps": 29750, "total_steps": 76960, "loss": 0.2971, "lr": 3.8502229139609236e-05, "epoch": 7.731288981288982, "percentage": 38.66, "elapsed_time": "0:43:10", "remaining_time": "1:08:31", "throughput": 1034.19, "total_tokens": 2679280} {"current_steps": 29755, "total_steps": 76960, "loss": 0.2702, "lr": 3.849745721396322e-05, "epoch": 7.732588357588358, "percentage": 38.66, "elapsed_time": "0:43:11", "remaining_time": "1:08:30", "throughput": 1034.18, "total_tokens": 2679680} {"current_steps": 29760, "total_steps": 76960, "loss": 0.2016, "lr": 3.849268459413003e-05, "epoch": 7.733887733887734, "percentage": 38.67, "elapsed_time": "0:43:11", "remaining_time": "1:08:30", "throughput": 1034.18, "total_tokens": 2680128} {"current_steps": 29765, "total_steps": 76960, "loss": 0.3257, "lr": 3.8487911280355164e-05, "epoch": 7.73518711018711, "percentage": 38.68, "elapsed_time": "0:43:11", "remaining_time": "1:08:29", "throughput": 1034.19, "total_tokens": 2680576} {"current_steps": 29770, "total_steps": 76960, "loss": 0.2714, "lr": 3.848313727288409e-05, "epoch": 7.736486486486487, "percentage": 38.68, "elapsed_time": "0:43:12", "remaining_time": "1:08:29", "throughput": 1034.2, "total_tokens": 2681040} {"current_steps": 29775, "total_steps": 76960, "loss": 0.255, "lr": 3.847836257196235e-05, "epoch": 7.737785862785863, "percentage": 38.69, "elapsed_time": "0:43:12", "remaining_time": "1:08:28", "throughput": 1034.2, "total_tokens": 2681472} {"current_steps": 29780, "total_steps": 76960, "loss": 0.2495, "lr": 3.8473587177835504e-05, "epoch": 7.739085239085239, "percentage": 38.7, "elapsed_time": "0:43:13", "remaining_time": "1:08:28", "throughput": 1034.2, "total_tokens": 2681888} {"current_steps": 29785, "total_steps": 76960, "loss": 0.1897, "lr": 3.8468811090749155e-05, "epoch": 7.740384615384615, "percentage": 38.7, "elapsed_time": "0:43:13", "remaining_time": "1:08:27", "throughput": 1034.21, "total_tokens": 2682352} {"current_steps": 29790, "total_steps": 76960, "loss": 0.2949, "lr": 3.846403431094895e-05, "epoch": 7.741683991683992, "percentage": 38.71, "elapsed_time": "0:43:14", "remaining_time": "1:08:27", "throughput": 1034.23, "total_tokens": 2682832} {"current_steps": 29795, "total_steps": 76960, "loss": 0.2576, "lr": 3.845925683868057e-05, "epoch": 7.742983367983368, "percentage": 38.71, "elapsed_time": "0:43:14", "remaining_time": "1:08:26", "throughput": 1034.22, "total_tokens": 2683248} {"current_steps": 29800, "total_steps": 76960, "loss": 0.3126, "lr": 3.84544786741897e-05, "epoch": 7.744282744282744, "percentage": 38.72, "elapsed_time": "0:43:14", "remaining_time": "1:08:26", "throughput": 1034.23, "total_tokens": 2683696} {"current_steps": 29805, "total_steps": 76960, "loss": 0.2427, "lr": 3.844969981772211e-05, "epoch": 7.745582120582121, "percentage": 38.73, "elapsed_time": "0:43:15", "remaining_time": "1:08:26", "throughput": 1034.25, "total_tokens": 2684176} {"current_steps": 29810, "total_steps": 76960, "loss": 0.2179, "lr": 3.844492026952356e-05, "epoch": 7.746881496881497, "percentage": 38.73, "elapsed_time": "0:43:15", "remaining_time": "1:08:25", "throughput": 1034.26, "total_tokens": 2684640} {"current_steps": 29815, "total_steps": 76960, "loss": 0.2364, "lr": 3.844014002983989e-05, "epoch": 7.748180873180873, "percentage": 38.74, "elapsed_time": "0:43:16", "remaining_time": "1:08:25", "throughput": 1034.26, "total_tokens": 2685072} {"current_steps": 29820, "total_steps": 76960, "loss": 0.1908, "lr": 3.843535909891694e-05, "epoch": 7.74948024948025, "percentage": 38.75, "elapsed_time": "0:43:16", "remaining_time": "1:08:24", "throughput": 1034.27, "total_tokens": 2685520} {"current_steps": 29825, "total_steps": 76960, "loss": 0.2898, "lr": 3.8430577477000595e-05, "epoch": 7.750779625779626, "percentage": 38.75, "elapsed_time": "0:43:16", "remaining_time": "1:08:24", "throughput": 1034.27, "total_tokens": 2685968} {"current_steps": 29830, "total_steps": 76960, "loss": 0.2329, "lr": 3.842579516433677e-05, "epoch": 7.752079002079002, "percentage": 38.76, "elapsed_time": "0:43:17", "remaining_time": "1:08:23", "throughput": 1034.27, "total_tokens": 2686400} {"current_steps": 29835, "total_steps": 76960, "loss": 0.2487, "lr": 3.8421012161171454e-05, "epoch": 7.753378378378378, "percentage": 38.77, "elapsed_time": "0:43:17", "remaining_time": "1:08:23", "throughput": 1034.27, "total_tokens": 2686832} {"current_steps": 29840, "total_steps": 76960, "loss": 0.2192, "lr": 3.841622846775062e-05, "epoch": 7.754677754677755, "percentage": 38.77, "elapsed_time": "0:43:18", "remaining_time": "1:08:22", "throughput": 1034.27, "total_tokens": 2687264} {"current_steps": 29845, "total_steps": 76960, "loss": 0.2485, "lr": 3.84114440843203e-05, "epoch": 7.755977130977131, "percentage": 38.78, "elapsed_time": "0:43:18", "remaining_time": "1:08:22", "throughput": 1034.28, "total_tokens": 2687712} {"current_steps": 29850, "total_steps": 76960, "loss": 0.3013, "lr": 3.840665901112656e-05, "epoch": 7.757276507276507, "percentage": 38.79, "elapsed_time": "0:43:19", "remaining_time": "1:08:21", "throughput": 1034.29, "total_tokens": 2688160} {"current_steps": 29855, "total_steps": 76960, "loss": 0.2606, "lr": 3.8401873248415494e-05, "epoch": 7.758575883575883, "percentage": 38.79, "elapsed_time": "0:43:19", "remaining_time": "1:08:21", "throughput": 1034.29, "total_tokens": 2688608} {"current_steps": 29860, "total_steps": 76960, "loss": 0.2517, "lr": 3.839708679643326e-05, "epoch": 7.75987525987526, "percentage": 38.8, "elapsed_time": "0:43:19", "remaining_time": "1:08:20", "throughput": 1034.29, "total_tokens": 2689040} {"current_steps": 29865, "total_steps": 76960, "loss": 0.2268, "lr": 3.8392299655426e-05, "epoch": 7.761174636174636, "percentage": 38.81, "elapsed_time": "0:43:20", "remaining_time": "1:08:20", "throughput": 1034.29, "total_tokens": 2689472} {"current_steps": 29870, "total_steps": 76960, "loss": 0.356, "lr": 3.8387511825639946e-05, "epoch": 7.762474012474012, "percentage": 38.81, "elapsed_time": "0:43:20", "remaining_time": "1:08:20", "throughput": 1034.31, "total_tokens": 2689952} {"current_steps": 29875, "total_steps": 76960, "loss": 0.2275, "lr": 3.8382723307321325e-05, "epoch": 7.763773388773389, "percentage": 38.82, "elapsed_time": "0:43:21", "remaining_time": "1:08:19", "throughput": 1034.31, "total_tokens": 2690384} {"current_steps": 29880, "total_steps": 76960, "loss": 0.2031, "lr": 3.837793410071643e-05, "epoch": 7.765072765072765, "percentage": 38.83, "elapsed_time": "0:43:21", "remaining_time": "1:08:19", "throughput": 1034.31, "total_tokens": 2690816} {"current_steps": 29885, "total_steps": 76960, "loss": 0.216, "lr": 3.8373144206071556e-05, "epoch": 7.766372141372141, "percentage": 38.83, "elapsed_time": "0:43:21", "remaining_time": "1:08:18", "throughput": 1034.32, "total_tokens": 2691264} {"current_steps": 29890, "total_steps": 76960, "loss": 0.1798, "lr": 3.836835362363307e-05, "epoch": 7.767671517671518, "percentage": 38.84, "elapsed_time": "0:43:22", "remaining_time": "1:08:18", "throughput": 1034.32, "total_tokens": 2691712} {"current_steps": 29895, "total_steps": 76960, "loss": 0.236, "lr": 3.836356235364735e-05, "epoch": 7.768970893970894, "percentage": 38.84, "elapsed_time": "0:43:22", "remaining_time": "1:08:17", "throughput": 1034.32, "total_tokens": 2692144} {"current_steps": 29900, "total_steps": 76960, "loss": 0.3529, "lr": 3.835877039636081e-05, "epoch": 7.77027027027027, "percentage": 38.85, "elapsed_time": "0:43:23", "remaining_time": "1:08:17", "throughput": 1034.34, "total_tokens": 2692624} {"current_steps": 29905, "total_steps": 76960, "loss": 0.1285, "lr": 3.835397775201991e-05, "epoch": 7.771569646569646, "percentage": 38.86, "elapsed_time": "0:43:23", "remaining_time": "1:08:16", "throughput": 1034.36, "total_tokens": 2693088} {"current_steps": 29910, "total_steps": 76960, "loss": 0.4278, "lr": 3.8349184420871134e-05, "epoch": 7.772869022869023, "percentage": 38.86, "elapsed_time": "0:43:24", "remaining_time": "1:08:16", "throughput": 1034.35, "total_tokens": 2693504} {"current_steps": 29915, "total_steps": 76960, "loss": 0.3728, "lr": 3.8344390403161016e-05, "epoch": 7.774168399168399, "percentage": 38.87, "elapsed_time": "0:43:24", "remaining_time": "1:08:15", "throughput": 1034.36, "total_tokens": 2693952} {"current_steps": 29920, "total_steps": 76960, "loss": 0.1805, "lr": 3.833959569913611e-05, "epoch": 7.775467775467775, "percentage": 38.88, "elapsed_time": "0:43:24", "remaining_time": "1:08:15", "throughput": 1034.36, "total_tokens": 2694400} {"current_steps": 29925, "total_steps": 76960, "loss": 0.237, "lr": 3.833480030904303e-05, "epoch": 7.776767151767151, "percentage": 38.88, "elapsed_time": "0:43:25", "remaining_time": "1:08:14", "throughput": 1034.37, "total_tokens": 2694848} {"current_steps": 29930, "total_steps": 76960, "loss": 0.2398, "lr": 3.833000423312838e-05, "epoch": 7.778066528066528, "percentage": 38.89, "elapsed_time": "0:43:25", "remaining_time": "1:08:14", "throughput": 1034.4, "total_tokens": 2695360} {"current_steps": 29935, "total_steps": 76960, "loss": 0.2337, "lr": 3.8325207471638844e-05, "epoch": 7.779365904365904, "percentage": 38.9, "elapsed_time": "0:43:26", "remaining_time": "1:08:13", "throughput": 1034.39, "total_tokens": 2695776} {"current_steps": 29940, "total_steps": 76960, "loss": 0.2241, "lr": 3.8320410024821115e-05, "epoch": 7.78066528066528, "percentage": 38.9, "elapsed_time": "0:43:26", "remaining_time": "1:08:13", "throughput": 1034.39, "total_tokens": 2696208} {"current_steps": 29945, "total_steps": 76960, "loss": 0.2435, "lr": 3.8315611892921946e-05, "epoch": 7.781964656964657, "percentage": 38.91, "elapsed_time": "0:43:26", "remaining_time": "1:08:13", "throughput": 1034.41, "total_tokens": 2696688} {"current_steps": 29950, "total_steps": 76960, "loss": 0.2503, "lr": 3.831081307618809e-05, "epoch": 7.783264033264033, "percentage": 38.92, "elapsed_time": "0:43:27", "remaining_time": "1:08:12", "throughput": 1034.42, "total_tokens": 2697136} {"current_steps": 29955, "total_steps": 76960, "loss": 0.3634, "lr": 3.8306013574866365e-05, "epoch": 7.784563409563409, "percentage": 38.92, "elapsed_time": "0:43:27", "remaining_time": "1:08:12", "throughput": 1034.44, "total_tokens": 2697616} {"current_steps": 29960, "total_steps": 76960, "loss": 0.2465, "lr": 3.830121338920362e-05, "epoch": 7.785862785862786, "percentage": 38.93, "elapsed_time": "0:43:28", "remaining_time": "1:08:11", "throughput": 1034.45, "total_tokens": 2698064} {"current_steps": 29965, "total_steps": 76960, "loss": 0.3404, "lr": 3.829641251944672e-05, "epoch": 7.787162162162162, "percentage": 38.94, "elapsed_time": "0:43:28", "remaining_time": "1:08:11", "throughput": 1034.47, "total_tokens": 2698560} {"current_steps": 29970, "total_steps": 76960, "loss": 0.2633, "lr": 3.8291610965842584e-05, "epoch": 7.788461538461538, "percentage": 38.94, "elapsed_time": "0:43:29", "remaining_time": "1:08:10", "throughput": 1034.47, "total_tokens": 2698992} {"current_steps": 29975, "total_steps": 76960, "loss": 0.2559, "lr": 3.8286808728638154e-05, "epoch": 7.789760914760915, "percentage": 38.95, "elapsed_time": "0:43:29", "remaining_time": "1:08:10", "throughput": 1034.48, "total_tokens": 2699440} {"current_steps": 29980, "total_steps": 76960, "loss": 0.2864, "lr": 3.828200580808043e-05, "epoch": 7.791060291060291, "percentage": 38.96, "elapsed_time": "0:43:29", "remaining_time": "1:08:09", "throughput": 1034.49, "total_tokens": 2699904} {"current_steps": 29985, "total_steps": 76960, "loss": 0.2201, "lr": 3.827720220441642e-05, "epoch": 7.792359667359667, "percentage": 38.96, "elapsed_time": "0:43:30", "remaining_time": "1:08:09", "throughput": 1034.5, "total_tokens": 2700368} {"current_steps": 29990, "total_steps": 76960, "loss": 0.2804, "lr": 3.827239791789318e-05, "epoch": 7.793659043659043, "percentage": 38.97, "elapsed_time": "0:43:30", "remaining_time": "1:08:08", "throughput": 1034.5, "total_tokens": 2700784} {"current_steps": 29995, "total_steps": 76960, "loss": 0.265, "lr": 3.826759294875779e-05, "epoch": 7.79495841995842, "percentage": 38.97, "elapsed_time": "0:43:31", "remaining_time": "1:08:08", "throughput": 1034.5, "total_tokens": 2701232} {"current_steps": 30000, "total_steps": 76960, "loss": 0.2857, "lr": 3.826278729725739e-05, "epoch": 7.796257796257796, "percentage": 38.98, "elapsed_time": "0:43:31", "remaining_time": "1:08:07", "throughput": 1034.5, "total_tokens": 2701664} {"current_steps": 30005, "total_steps": 76960, "loss": 0.2967, "lr": 3.8257980963639125e-05, "epoch": 7.797557172557172, "percentage": 38.99, "elapsed_time": "0:43:31", "remaining_time": "1:08:07", "throughput": 1034.5, "total_tokens": 2702096} {"current_steps": 30010, "total_steps": 76960, "loss": 0.2693, "lr": 3.82531739481502e-05, "epoch": 7.798856548856548, "percentage": 38.99, "elapsed_time": "0:43:32", "remaining_time": "1:08:07", "throughput": 1034.52, "total_tokens": 2702560} {"current_steps": 30015, "total_steps": 76960, "loss": 0.2549, "lr": 3.824836625103784e-05, "epoch": 7.800155925155925, "percentage": 39.0, "elapsed_time": "0:43:32", "remaining_time": "1:08:06", "throughput": 1034.53, "total_tokens": 2703024} {"current_steps": 30020, "total_steps": 76960, "loss": 0.2592, "lr": 3.824355787254931e-05, "epoch": 7.801455301455301, "percentage": 39.01, "elapsed_time": "0:43:33", "remaining_time": "1:08:06", "throughput": 1034.55, "total_tokens": 2703504} {"current_steps": 30025, "total_steps": 76960, "loss": 0.2718, "lr": 3.8238748812931904e-05, "epoch": 7.8027546777546775, "percentage": 39.01, "elapsed_time": "0:43:33", "remaining_time": "1:08:05", "throughput": 1034.55, "total_tokens": 2703952} {"current_steps": 30030, "total_steps": 76960, "loss": 0.2789, "lr": 3.823393907243297e-05, "epoch": 7.804054054054054, "percentage": 39.02, "elapsed_time": "0:43:34", "remaining_time": "1:08:05", "throughput": 1034.55, "total_tokens": 2704384} {"current_steps": 30035, "total_steps": 76960, "loss": 0.2832, "lr": 3.8229128651299875e-05, "epoch": 7.80535343035343, "percentage": 39.03, "elapsed_time": "0:43:34", "remaining_time": "1:08:04", "throughput": 1034.55, "total_tokens": 2704816} {"current_steps": 30040, "total_steps": 76960, "loss": 0.2922, "lr": 3.822431754978e-05, "epoch": 7.8066528066528065, "percentage": 39.03, "elapsed_time": "0:43:34", "remaining_time": "1:08:04", "throughput": 1034.56, "total_tokens": 2705264} {"current_steps": 30045, "total_steps": 76960, "loss": 0.3603, "lr": 3.821950576812081e-05, "epoch": 7.807952182952183, "percentage": 39.04, "elapsed_time": "0:43:35", "remaining_time": "1:08:03", "throughput": 1034.56, "total_tokens": 2705696} {"current_steps": 30050, "total_steps": 76960, "loss": 0.2532, "lr": 3.821469330656978e-05, "epoch": 7.8092515592515594, "percentage": 39.05, "elapsed_time": "0:43:35", "remaining_time": "1:08:03", "throughput": 1034.57, "total_tokens": 2706144} {"current_steps": 30055, "total_steps": 76960, "loss": 0.2509, "lr": 3.8209880165374415e-05, "epoch": 7.8105509355509355, "percentage": 39.05, "elapsed_time": "0:43:36", "remaining_time": "1:08:02", "throughput": 1034.57, "total_tokens": 2706576} {"current_steps": 30060, "total_steps": 76960, "loss": 0.2019, "lr": 3.820506634478224e-05, "epoch": 7.8118503118503115, "percentage": 39.06, "elapsed_time": "0:43:36", "remaining_time": "1:08:02", "throughput": 1034.56, "total_tokens": 2706992} {"current_steps": 30065, "total_steps": 76960, "loss": 0.2557, "lr": 3.8200251845040855e-05, "epoch": 7.8131496881496885, "percentage": 39.07, "elapsed_time": "0:43:36", "remaining_time": "1:08:01", "throughput": 1034.57, "total_tokens": 2707440} {"current_steps": 30070, "total_steps": 76960, "loss": 0.1884, "lr": 3.8195436666397874e-05, "epoch": 7.8144490644490645, "percentage": 39.07, "elapsed_time": "0:43:37", "remaining_time": "1:08:01", "throughput": 1034.56, "total_tokens": 2707856} {"current_steps": 30075, "total_steps": 76960, "loss": 0.1266, "lr": 3.8190620809100936e-05, "epoch": 7.8157484407484406, "percentage": 39.08, "elapsed_time": "0:43:37", "remaining_time": "1:08:00", "throughput": 1034.56, "total_tokens": 2708288} {"current_steps": 30080, "total_steps": 76960, "loss": 0.247, "lr": 3.8185804273397726e-05, "epoch": 7.817047817047817, "percentage": 39.09, "elapsed_time": "0:43:38", "remaining_time": "1:08:00", "throughput": 1034.57, "total_tokens": 2708736} {"current_steps": 30085, "total_steps": 76960, "loss": 0.2345, "lr": 3.8180987059535984e-05, "epoch": 7.8183471933471935, "percentage": 39.09, "elapsed_time": "0:43:38", "remaining_time": "1:08:00", "throughput": 1034.6, "total_tokens": 2709248} {"current_steps": 30090, "total_steps": 76960, "loss": 0.0792, "lr": 3.8176169167763444e-05, "epoch": 7.81964656964657, "percentage": 39.1, "elapsed_time": "0:43:39", "remaining_time": "1:07:59", "throughput": 1034.61, "total_tokens": 2709712} {"current_steps": 30095, "total_steps": 76960, "loss": 0.2637, "lr": 3.8171350598327894e-05, "epoch": 7.820945945945946, "percentage": 39.1, "elapsed_time": "0:43:39", "remaining_time": "1:07:59", "throughput": 1034.64, "total_tokens": 2710208} {"current_steps": 30100, "total_steps": 76960, "loss": 0.2029, "lr": 3.816653135147716e-05, "epoch": 7.8222453222453225, "percentage": 39.11, "elapsed_time": "0:43:39", "remaining_time": "1:07:58", "throughput": 1034.64, "total_tokens": 2710656} {"current_steps": 30105, "total_steps": 76960, "loss": 0.4429, "lr": 3.816171142745911e-05, "epoch": 7.823544698544699, "percentage": 39.12, "elapsed_time": "0:43:40", "remaining_time": "1:07:58", "throughput": 1034.65, "total_tokens": 2711104} {"current_steps": 30110, "total_steps": 76960, "loss": 0.2218, "lr": 3.815689082652163e-05, "epoch": 7.824844074844075, "percentage": 39.12, "elapsed_time": "0:43:40", "remaining_time": "1:07:57", "throughput": 1034.66, "total_tokens": 2711568} {"current_steps": 30115, "total_steps": 76960, "loss": 0.3026, "lr": 3.8152069548912646e-05, "epoch": 7.826143451143452, "percentage": 39.13, "elapsed_time": "0:43:41", "remaining_time": "1:07:57", "throughput": 1034.66, "total_tokens": 2711984} {"current_steps": 30120, "total_steps": 76960, "loss": 0.2329, "lr": 3.814724759488012e-05, "epoch": 7.827442827442828, "percentage": 39.14, "elapsed_time": "0:43:41", "remaining_time": "1:07:56", "throughput": 1034.66, "total_tokens": 2712432} {"current_steps": 30125, "total_steps": 76960, "loss": 0.2394, "lr": 3.814242496467206e-05, "epoch": 7.828742203742204, "percentage": 39.14, "elapsed_time": "0:43:41", "remaining_time": "1:07:56", "throughput": 1034.66, "total_tokens": 2712864} {"current_steps": 30130, "total_steps": 76960, "loss": 0.243, "lr": 3.813760165853649e-05, "epoch": 7.83004158004158, "percentage": 39.15, "elapsed_time": "0:43:42", "remaining_time": "1:07:55", "throughput": 1034.67, "total_tokens": 2713328} {"current_steps": 30135, "total_steps": 76960, "loss": 0.2265, "lr": 3.8132777676721475e-05, "epoch": 7.831340956340957, "percentage": 39.16, "elapsed_time": "0:43:42", "remaining_time": "1:07:55", "throughput": 1034.69, "total_tokens": 2713808} {"current_steps": 30140, "total_steps": 76960, "loss": 0.3038, "lr": 3.812795301947512e-05, "epoch": 7.832640332640333, "percentage": 39.16, "elapsed_time": "0:43:43", "remaining_time": "1:07:54", "throughput": 1034.72, "total_tokens": 2714304} {"current_steps": 30145, "total_steps": 76960, "loss": 0.1852, "lr": 3.812312768704557e-05, "epoch": 7.833939708939709, "percentage": 39.17, "elapsed_time": "0:43:43", "remaining_time": "1:07:54", "throughput": 1034.74, "total_tokens": 2714784} {"current_steps": 30150, "total_steps": 76960, "loss": 0.2606, "lr": 3.811830167968098e-05, "epoch": 7.835239085239085, "percentage": 39.18, "elapsed_time": "0:43:44", "remaining_time": "1:07:54", "throughput": 1034.75, "total_tokens": 2715248} {"current_steps": 30155, "total_steps": 76960, "loss": 0.2577, "lr": 3.8113474997629573e-05, "epoch": 7.836538461538462, "percentage": 39.18, "elapsed_time": "0:43:44", "remaining_time": "1:07:53", "throughput": 1034.76, "total_tokens": 2715696} {"current_steps": 30160, "total_steps": 76960, "loss": 0.3392, "lr": 3.810864764113957e-05, "epoch": 7.837837837837838, "percentage": 39.19, "elapsed_time": "0:43:44", "remaining_time": "1:07:53", "throughput": 1034.77, "total_tokens": 2716160} {"current_steps": 30165, "total_steps": 76960, "loss": 0.2582, "lr": 3.810381961045927e-05, "epoch": 7.839137214137214, "percentage": 39.2, "elapsed_time": "0:43:45", "remaining_time": "1:07:52", "throughput": 1034.77, "total_tokens": 2716592} {"current_steps": 30170, "total_steps": 76960, "loss": 0.2766, "lr": 3.809899090583697e-05, "epoch": 7.840436590436591, "percentage": 39.2, "elapsed_time": "0:43:45", "remaining_time": "1:07:52", "throughput": 1034.78, "total_tokens": 2717056} {"current_steps": 30175, "total_steps": 76960, "loss": 0.297, "lr": 3.809416152752102e-05, "epoch": 7.841735966735967, "percentage": 39.21, "elapsed_time": "0:43:46", "remaining_time": "1:07:51", "throughput": 1034.78, "total_tokens": 2717488} {"current_steps": 30180, "total_steps": 76960, "loss": 0.2459, "lr": 3.808933147575979e-05, "epoch": 7.843035343035343, "percentage": 39.22, "elapsed_time": "0:43:46", "remaining_time": "1:07:51", "throughput": 1034.79, "total_tokens": 2717952} {"current_steps": 30185, "total_steps": 76960, "loss": 0.2786, "lr": 3.808450075080171e-05, "epoch": 7.84433471933472, "percentage": 39.22, "elapsed_time": "0:43:46", "remaining_time": "1:07:50", "throughput": 1034.79, "total_tokens": 2718384} {"current_steps": 30190, "total_steps": 76960, "loss": 0.3115, "lr": 3.8079669352895206e-05, "epoch": 7.845634095634096, "percentage": 39.23, "elapsed_time": "0:43:47", "remaining_time": "1:07:50", "throughput": 1034.79, "total_tokens": 2718816} {"current_steps": 30195, "total_steps": 76960, "loss": 0.2898, "lr": 3.807483728228879e-05, "epoch": 7.846933471933472, "percentage": 39.23, "elapsed_time": "0:43:47", "remaining_time": "1:07:49", "throughput": 1034.8, "total_tokens": 2719264} {"current_steps": 30200, "total_steps": 76960, "loss": 0.3057, "lr": 3.807000453923095e-05, "epoch": 7.848232848232849, "percentage": 39.24, "elapsed_time": "0:43:48", "remaining_time": "1:07:49", "throughput": 1034.81, "total_tokens": 2719728} {"current_steps": 30205, "total_steps": 76960, "loss": 0.2995, "lr": 3.806517112397026e-05, "epoch": 7.849532224532225, "percentage": 39.25, "elapsed_time": "0:43:48", "remaining_time": "1:07:48", "throughput": 1034.82, "total_tokens": 2720176} {"current_steps": 30210, "total_steps": 76960, "loss": 0.2001, "lr": 3.80603370367553e-05, "epoch": 7.850831600831601, "percentage": 39.25, "elapsed_time": "0:43:49", "remaining_time": "1:07:48", "throughput": 1034.83, "total_tokens": 2720640} {"current_steps": 30215, "total_steps": 76960, "loss": 0.3026, "lr": 3.8055502277834695e-05, "epoch": 7.852130977130977, "percentage": 39.26, "elapsed_time": "0:43:49", "remaining_time": "1:07:48", "throughput": 1034.84, "total_tokens": 2721104} {"current_steps": 30220, "total_steps": 76960, "loss": 0.2749, "lr": 3.80506668474571e-05, "epoch": 7.853430353430354, "percentage": 39.27, "elapsed_time": "0:43:49", "remaining_time": "1:07:47", "throughput": 1034.85, "total_tokens": 2721552} {"current_steps": 30225, "total_steps": 76960, "loss": 0.297, "lr": 3.8045830745871195e-05, "epoch": 7.85472972972973, "percentage": 39.27, "elapsed_time": "0:43:50", "remaining_time": "1:07:47", "throughput": 1034.86, "total_tokens": 2722016} {"current_steps": 30230, "total_steps": 76960, "loss": 0.2522, "lr": 3.804099397332572e-05, "epoch": 7.856029106029106, "percentage": 39.28, "elapsed_time": "0:43:50", "remaining_time": "1:07:46", "throughput": 1034.86, "total_tokens": 2722432} {"current_steps": 30235, "total_steps": 76960, "loss": 0.2918, "lr": 3.803615653006943e-05, "epoch": 7.857328482328482, "percentage": 39.29, "elapsed_time": "0:43:51", "remaining_time": "1:07:46", "throughput": 1034.86, "total_tokens": 2722864} {"current_steps": 30240, "total_steps": 76960, "loss": 0.1876, "lr": 3.803131841635112e-05, "epoch": 7.858627858627859, "percentage": 39.29, "elapsed_time": "0:43:51", "remaining_time": "1:07:45", "throughput": 1034.86, "total_tokens": 2723312} {"current_steps": 30245, "total_steps": 76960, "loss": 0.2122, "lr": 3.802647963241962e-05, "epoch": 7.859927234927235, "percentage": 39.3, "elapsed_time": "0:43:51", "remaining_time": "1:07:45", "throughput": 1034.88, "total_tokens": 2723776} {"current_steps": 30250, "total_steps": 76960, "loss": 0.2116, "lr": 3.8021640178523786e-05, "epoch": 7.861226611226611, "percentage": 39.31, "elapsed_time": "0:43:52", "remaining_time": "1:07:44", "throughput": 1034.88, "total_tokens": 2724208} {"current_steps": 30255, "total_steps": 76960, "loss": 0.1786, "lr": 3.801680005491254e-05, "epoch": 7.862525987525988, "percentage": 39.31, "elapsed_time": "0:43:52", "remaining_time": "1:07:44", "throughput": 1034.91, "total_tokens": 2724720} {"current_steps": 30260, "total_steps": 76960, "loss": 0.2152, "lr": 3.801195926183477e-05, "epoch": 7.863825363825364, "percentage": 39.32, "elapsed_time": "0:43:53", "remaining_time": "1:07:43", "throughput": 1034.92, "total_tokens": 2725200} {"current_steps": 30265, "total_steps": 76960, "loss": 0.2894, "lr": 3.8007117799539475e-05, "epoch": 7.86512474012474, "percentage": 39.33, "elapsed_time": "0:43:53", "remaining_time": "1:07:43", "throughput": 1034.93, "total_tokens": 2725648} {"current_steps": 30270, "total_steps": 76960, "loss": 0.2828, "lr": 3.8002275668275655e-05, "epoch": 7.866424116424117, "percentage": 39.33, "elapsed_time": "0:43:54", "remaining_time": "1:07:42", "throughput": 1034.95, "total_tokens": 2726128} {"current_steps": 30275, "total_steps": 76960, "loss": 0.3436, "lr": 3.7997432868292326e-05, "epoch": 7.867723492723493, "percentage": 39.34, "elapsed_time": "0:43:54", "remaining_time": "1:07:42", "throughput": 1034.96, "total_tokens": 2726576} {"current_steps": 30280, "total_steps": 76960, "loss": 0.3035, "lr": 3.7992589399838585e-05, "epoch": 7.869022869022869, "percentage": 39.35, "elapsed_time": "0:43:54", "remaining_time": "1:07:41", "throughput": 1034.97, "total_tokens": 2727040} {"current_steps": 30285, "total_steps": 76960, "loss": 0.2178, "lr": 3.798774526316351e-05, "epoch": 7.870322245322245, "percentage": 39.35, "elapsed_time": "0:43:55", "remaining_time": "1:07:41", "throughput": 1034.97, "total_tokens": 2727488} {"current_steps": 30290, "total_steps": 76960, "loss": 0.2033, "lr": 3.7982900458516267e-05, "epoch": 7.871621621621622, "percentage": 39.36, "elapsed_time": "0:43:55", "remaining_time": "1:07:41", "throughput": 1034.97, "total_tokens": 2727920} {"current_steps": 30295, "total_steps": 76960, "loss": 0.1988, "lr": 3.7978054986146e-05, "epoch": 7.872920997920998, "percentage": 39.36, "elapsed_time": "0:43:56", "remaining_time": "1:07:40", "throughput": 1034.99, "total_tokens": 2728384} {"current_steps": 30300, "total_steps": 76960, "loss": 0.1717, "lr": 3.797320884630194e-05, "epoch": 7.874220374220374, "percentage": 39.37, "elapsed_time": "0:43:56", "remaining_time": "1:07:40", "throughput": 1034.99, "total_tokens": 2728832} {"current_steps": 30305, "total_steps": 76960, "loss": 0.1334, "lr": 3.7968362039233316e-05, "epoch": 7.87551975051975, "percentage": 39.38, "elapsed_time": "0:43:56", "remaining_time": "1:07:39", "throughput": 1034.99, "total_tokens": 2729264} {"current_steps": 30310, "total_steps": 76960, "loss": 0.3604, "lr": 3.7963514565189404e-05, "epoch": 7.876819126819127, "percentage": 39.38, "elapsed_time": "0:43:57", "remaining_time": "1:07:39", "throughput": 1034.99, "total_tokens": 2729696} {"current_steps": 30315, "total_steps": 76960, "loss": 0.2277, "lr": 3.7958666424419506e-05, "epoch": 7.878118503118503, "percentage": 39.39, "elapsed_time": "0:43:57", "remaining_time": "1:07:38", "throughput": 1034.99, "total_tokens": 2730112} {"current_steps": 30320, "total_steps": 76960, "loss": 0.3896, "lr": 3.7953817617173e-05, "epoch": 7.879417879417879, "percentage": 39.4, "elapsed_time": "0:43:58", "remaining_time": "1:07:38", "throughput": 1035.0, "total_tokens": 2730576} {"current_steps": 30325, "total_steps": 76960, "loss": 0.2656, "lr": 3.794896814369924e-05, "epoch": 7.880717255717256, "percentage": 39.4, "elapsed_time": "0:43:58", "remaining_time": "1:07:37", "throughput": 1035.01, "total_tokens": 2731024} {"current_steps": 30330, "total_steps": 76960, "loss": 0.3215, "lr": 3.794411800424762e-05, "epoch": 7.882016632016632, "percentage": 39.41, "elapsed_time": "0:43:59", "remaining_time": "1:07:37", "throughput": 1035.02, "total_tokens": 2731488} {"current_steps": 30335, "total_steps": 76960, "loss": 0.2015, "lr": 3.7939267199067624e-05, "epoch": 7.883316008316008, "percentage": 39.42, "elapsed_time": "0:43:59", "remaining_time": "1:07:36", "throughput": 1035.03, "total_tokens": 2731936} {"current_steps": 30340, "total_steps": 76960, "loss": 0.1666, "lr": 3.7934415728408715e-05, "epoch": 7.884615384615385, "percentage": 39.42, "elapsed_time": "0:43:59", "remaining_time": "1:07:36", "throughput": 1035.03, "total_tokens": 2732384} {"current_steps": 30345, "total_steps": 76960, "loss": 0.2314, "lr": 3.792956359252041e-05, "epoch": 7.885914760914761, "percentage": 39.43, "elapsed_time": "0:44:00", "remaining_time": "1:07:35", "throughput": 1035.04, "total_tokens": 2732848} {"current_steps": 30350, "total_steps": 76960, "loss": 0.1033, "lr": 3.792471079165226e-05, "epoch": 7.887214137214137, "percentage": 39.44, "elapsed_time": "0:44:00", "remaining_time": "1:07:35", "throughput": 1035.06, "total_tokens": 2733312} {"current_steps": 30355, "total_steps": 76960, "loss": 0.2557, "lr": 3.791985732605386e-05, "epoch": 7.888513513513513, "percentage": 39.44, "elapsed_time": "0:44:01", "remaining_time": "1:07:35", "throughput": 1035.07, "total_tokens": 2733792} {"current_steps": 30360, "total_steps": 76960, "loss": 0.3421, "lr": 3.7915003195974815e-05, "epoch": 7.88981288981289, "percentage": 39.45, "elapsed_time": "0:44:01", "remaining_time": "1:07:34", "throughput": 1035.1, "total_tokens": 2734304} {"current_steps": 30365, "total_steps": 76960, "loss": 0.2843, "lr": 3.791014840166478e-05, "epoch": 7.891112266112266, "percentage": 39.46, "elapsed_time": "0:44:01", "remaining_time": "1:07:34", "throughput": 1035.1, "total_tokens": 2734736} {"current_steps": 30370, "total_steps": 76960, "loss": 0.2268, "lr": 3.7905292943373434e-05, "epoch": 7.892411642411642, "percentage": 39.46, "elapsed_time": "0:44:02", "remaining_time": "1:07:33", "throughput": 1035.11, "total_tokens": 2735184} {"current_steps": 30375, "total_steps": 76960, "loss": 0.2209, "lr": 3.7900436821350514e-05, "epoch": 7.893711018711018, "percentage": 39.47, "elapsed_time": "0:44:02", "remaining_time": "1:07:33", "throughput": 1035.12, "total_tokens": 2735632} {"current_steps": 30380, "total_steps": 76960, "loss": 0.2981, "lr": 3.7895580035845766e-05, "epoch": 7.895010395010395, "percentage": 39.48, "elapsed_time": "0:44:03", "remaining_time": "1:07:32", "throughput": 1035.12, "total_tokens": 2736064} {"current_steps": 30385, "total_steps": 76960, "loss": 0.3146, "lr": 3.789072258710898e-05, "epoch": 7.896309771309771, "percentage": 39.48, "elapsed_time": "0:44:03", "remaining_time": "1:07:32", "throughput": 1035.12, "total_tokens": 2736496} {"current_steps": 30390, "total_steps": 76960, "loss": 0.2537, "lr": 3.788586447538999e-05, "epoch": 7.897609147609147, "percentage": 39.49, "elapsed_time": "0:44:04", "remaining_time": "1:07:31", "throughput": 1035.11, "total_tokens": 2736912} {"current_steps": 30395, "total_steps": 76960, "loss": 0.2462, "lr": 3.7881005700938635e-05, "epoch": 7.898908523908524, "percentage": 39.49, "elapsed_time": "0:44:04", "remaining_time": "1:07:31", "throughput": 1035.11, "total_tokens": 2737344} {"current_steps": 30400, "total_steps": 76960, "loss": 0.2275, "lr": 3.787614626400481e-05, "epoch": 7.9002079002079, "percentage": 39.5, "elapsed_time": "0:44:04", "remaining_time": "1:07:30", "throughput": 1035.11, "total_tokens": 2737760} {"current_steps": 30405, "total_steps": 76960, "loss": 0.2209, "lr": 3.7871286164838445e-05, "epoch": 7.901507276507276, "percentage": 39.51, "elapsed_time": "0:44:05", "remaining_time": "1:07:30", "throughput": 1035.12, "total_tokens": 2738224} {"current_steps": 30410, "total_steps": 76960, "loss": 0.2092, "lr": 3.786642540368951e-05, "epoch": 7.902806652806653, "percentage": 39.51, "elapsed_time": "0:44:05", "remaining_time": "1:07:29", "throughput": 1035.11, "total_tokens": 2738640} {"current_steps": 30415, "total_steps": 76960, "loss": 0.2131, "lr": 3.7861563980807994e-05, "epoch": 7.904106029106029, "percentage": 39.52, "elapsed_time": "0:44:06", "remaining_time": "1:07:29", "throughput": 1035.12, "total_tokens": 2739104} {"current_steps": 30420, "total_steps": 76960, "loss": 0.3068, "lr": 3.7856701896443905e-05, "epoch": 7.905405405405405, "percentage": 39.53, "elapsed_time": "0:44:06", "remaining_time": "1:07:29", "throughput": 1035.12, "total_tokens": 2739536} {"current_steps": 30425, "total_steps": 76960, "loss": 0.3243, "lr": 3.785183915084732e-05, "epoch": 7.906704781704782, "percentage": 39.53, "elapsed_time": "0:44:06", "remaining_time": "1:07:28", "throughput": 1035.14, "total_tokens": 2740016} {"current_steps": 30430, "total_steps": 76960, "loss": 0.3156, "lr": 3.784697574426833e-05, "epoch": 7.908004158004158, "percentage": 39.54, "elapsed_time": "0:44:07", "remaining_time": "1:07:28", "throughput": 1035.15, "total_tokens": 2740464} {"current_steps": 30435, "total_steps": 76960, "loss": 0.2341, "lr": 3.7842111676957085e-05, "epoch": 7.909303534303534, "percentage": 39.55, "elapsed_time": "0:44:07", "remaining_time": "1:07:27", "throughput": 1035.14, "total_tokens": 2740880} {"current_steps": 30440, "total_steps": 76960, "loss": 0.2272, "lr": 3.783724694916371e-05, "epoch": 7.91060291060291, "percentage": 39.55, "elapsed_time": "0:44:08", "remaining_time": "1:07:27", "throughput": 1035.14, "total_tokens": 2741312} {"current_steps": 30445, "total_steps": 76960, "loss": 0.218, "lr": 3.783238156113844e-05, "epoch": 7.911902286902287, "percentage": 39.56, "elapsed_time": "0:44:08", "remaining_time": "1:07:26", "throughput": 1035.16, "total_tokens": 2741792} {"current_steps": 30450, "total_steps": 76960, "loss": 0.2505, "lr": 3.7827515513131486e-05, "epoch": 7.913201663201663, "percentage": 39.57, "elapsed_time": "0:44:09", "remaining_time": "1:07:26", "throughput": 1035.19, "total_tokens": 2742304} {"current_steps": 30455, "total_steps": 76960, "loss": 0.2531, "lr": 3.7822648805393117e-05, "epoch": 7.914501039501039, "percentage": 39.57, "elapsed_time": "0:44:09", "remaining_time": "1:07:25", "throughput": 1035.22, "total_tokens": 2742800} {"current_steps": 30460, "total_steps": 76960, "loss": 0.2418, "lr": 3.781778143817364e-05, "epoch": 7.915800415800415, "percentage": 39.58, "elapsed_time": "0:44:09", "remaining_time": "1:07:25", "throughput": 1035.23, "total_tokens": 2743264} {"current_steps": 30465, "total_steps": 76960, "loss": 0.2623, "lr": 3.781291341172338e-05, "epoch": 7.917099792099792, "percentage": 39.59, "elapsed_time": "0:44:10", "remaining_time": "1:07:24", "throughput": 1035.24, "total_tokens": 2743712} {"current_steps": 30470, "total_steps": 76960, "loss": 0.2044, "lr": 3.7808044726292705e-05, "epoch": 7.918399168399168, "percentage": 39.59, "elapsed_time": "0:44:10", "remaining_time": "1:07:24", "throughput": 1035.24, "total_tokens": 2744160} {"current_steps": 30475, "total_steps": 76960, "loss": 0.2615, "lr": 3.780317538213201e-05, "epoch": 7.919698544698544, "percentage": 39.6, "elapsed_time": "0:44:11", "remaining_time": "1:07:23", "throughput": 1035.23, "total_tokens": 2744560} {"current_steps": 30480, "total_steps": 76960, "loss": 0.2415, "lr": 3.779830537949175e-05, "epoch": 7.920997920997921, "percentage": 39.6, "elapsed_time": "0:44:11", "remaining_time": "1:07:23", "throughput": 1035.23, "total_tokens": 2744992} {"current_steps": 30485, "total_steps": 76960, "loss": 0.3709, "lr": 3.7793434718622376e-05, "epoch": 7.922297297297297, "percentage": 39.61, "elapsed_time": "0:44:11", "remaining_time": "1:07:23", "throughput": 1035.26, "total_tokens": 2745504} {"current_steps": 30490, "total_steps": 76960, "loss": 0.2289, "lr": 3.778856339977439e-05, "epoch": 7.923596673596673, "percentage": 39.62, "elapsed_time": "0:44:12", "remaining_time": "1:07:22", "throughput": 1035.27, "total_tokens": 2745968} {"current_steps": 30495, "total_steps": 76960, "loss": 0.2953, "lr": 3.778369142319834e-05, "epoch": 7.92489604989605, "percentage": 39.62, "elapsed_time": "0:44:12", "remaining_time": "1:07:22", "throughput": 1035.29, "total_tokens": 2746432} {"current_steps": 30500, "total_steps": 76960, "loss": 0.2636, "lr": 3.77788187891448e-05, "epoch": 7.926195426195426, "percentage": 39.63, "elapsed_time": "0:44:13", "remaining_time": "1:07:21", "throughput": 1035.29, "total_tokens": 2746864} {"current_steps": 30505, "total_steps": 76960, "loss": 0.2312, "lr": 3.7773945497864354e-05, "epoch": 7.927494802494802, "percentage": 39.64, "elapsed_time": "0:44:13", "remaining_time": "1:07:21", "throughput": 1035.29, "total_tokens": 2747296} {"current_steps": 30510, "total_steps": 76960, "loss": 0.2284, "lr": 3.776907154960765e-05, "epoch": 7.9287941787941785, "percentage": 39.64, "elapsed_time": "0:44:14", "remaining_time": "1:07:20", "throughput": 1035.29, "total_tokens": 2747744} {"current_steps": 30515, "total_steps": 76960, "loss": 0.2651, "lr": 3.7764196944625375e-05, "epoch": 7.930093555093555, "percentage": 39.65, "elapsed_time": "0:44:14", "remaining_time": "1:07:20", "throughput": 1035.28, "total_tokens": 2748160} {"current_steps": 30520, "total_steps": 76960, "loss": 0.2796, "lr": 3.775932168316822e-05, "epoch": 7.9313929313929314, "percentage": 39.66, "elapsed_time": "0:44:14", "remaining_time": "1:07:19", "throughput": 1035.28, "total_tokens": 2748592} {"current_steps": 30525, "total_steps": 76960, "loss": 0.2091, "lr": 3.775444576548691e-05, "epoch": 7.9326923076923075, "percentage": 39.66, "elapsed_time": "0:44:15", "remaining_time": "1:07:19", "throughput": 1035.28, "total_tokens": 2749008} {"current_steps": 30530, "total_steps": 76960, "loss": 0.3425, "lr": 3.7749569191832245e-05, "epoch": 7.9339916839916835, "percentage": 39.67, "elapsed_time": "0:44:15", "remaining_time": "1:07:18", "throughput": 1035.27, "total_tokens": 2749424} {"current_steps": 30535, "total_steps": 76960, "loss": 0.1743, "lr": 3.774469196245502e-05, "epoch": 7.9352910602910605, "percentage": 39.68, "elapsed_time": "0:44:16", "remaining_time": "1:07:18", "throughput": 1035.28, "total_tokens": 2749888} {"current_steps": 30540, "total_steps": 76960, "loss": 0.2192, "lr": 3.773981407760607e-05, "epoch": 7.9365904365904365, "percentage": 39.68, "elapsed_time": "0:44:16", "remaining_time": "1:07:17", "throughput": 1035.28, "total_tokens": 2750320} {"current_steps": 30545, "total_steps": 76960, "loss": 0.3326, "lr": 3.7734935537536276e-05, "epoch": 7.9378898128898125, "percentage": 39.69, "elapsed_time": "0:44:16", "remaining_time": "1:07:17", "throughput": 1035.29, "total_tokens": 2750768} {"current_steps": 30550, "total_steps": 76960, "loss": 0.1897, "lr": 3.773005634249656e-05, "epoch": 7.9391891891891895, "percentage": 39.7, "elapsed_time": "0:44:17", "remaining_time": "1:07:17", "throughput": 1035.3, "total_tokens": 2751232} {"current_steps": 30555, "total_steps": 76960, "loss": 0.1944, "lr": 3.772517649273783e-05, "epoch": 7.9404885654885655, "percentage": 39.7, "elapsed_time": "0:44:17", "remaining_time": "1:07:16", "throughput": 1035.31, "total_tokens": 2751664} {"current_steps": 30560, "total_steps": 76960, "loss": 0.204, "lr": 3.772029598851109e-05, "epoch": 7.941787941787942, "percentage": 39.71, "elapsed_time": "0:44:18", "remaining_time": "1:07:16", "throughput": 1035.31, "total_tokens": 2752112} {"current_steps": 30565, "total_steps": 76960, "loss": 0.3427, "lr": 3.771541483006733e-05, "epoch": 7.9430873180873185, "percentage": 39.72, "elapsed_time": "0:44:18", "remaining_time": "1:07:15", "throughput": 1035.31, "total_tokens": 2752544} {"current_steps": 30570, "total_steps": 76960, "loss": 0.3334, "lr": 3.771053301765761e-05, "epoch": 7.9443866943866945, "percentage": 39.72, "elapsed_time": "0:44:19", "remaining_time": "1:07:15", "throughput": 1035.31, "total_tokens": 2752976} {"current_steps": 30575, "total_steps": 76960, "loss": 0.3062, "lr": 3.7705650551533e-05, "epoch": 7.945686070686071, "percentage": 39.73, "elapsed_time": "0:44:19", "remaining_time": "1:07:14", "throughput": 1035.32, "total_tokens": 2753424} {"current_steps": 30580, "total_steps": 76960, "loss": 0.3035, "lr": 3.770076743194461e-05, "epoch": 7.946985446985447, "percentage": 39.73, "elapsed_time": "0:44:19", "remaining_time": "1:07:14", "throughput": 1035.31, "total_tokens": 2753824} {"current_steps": 30585, "total_steps": 76960, "loss": 0.3002, "lr": 3.769588365914358e-05, "epoch": 7.9482848232848236, "percentage": 39.74, "elapsed_time": "0:44:20", "remaining_time": "1:07:13", "throughput": 1035.31, "total_tokens": 2754256} {"current_steps": 30590, "total_steps": 76960, "loss": 0.2626, "lr": 3.769099923338108e-05, "epoch": 7.9495841995842, "percentage": 39.75, "elapsed_time": "0:44:20", "remaining_time": "1:07:13", "throughput": 1035.32, "total_tokens": 2754720} {"current_steps": 30595, "total_steps": 76960, "loss": 0.3098, "lr": 3.7686114154908336e-05, "epoch": 7.950883575883576, "percentage": 39.75, "elapsed_time": "0:44:21", "remaining_time": "1:07:12", "throughput": 1035.31, "total_tokens": 2755136} {"current_steps": 30600, "total_steps": 76960, "loss": 0.263, "lr": 3.7681228423976586e-05, "epoch": 7.952182952182953, "percentage": 39.76, "elapsed_time": "0:44:21", "remaining_time": "1:07:12", "throughput": 1035.32, "total_tokens": 2755584} {"current_steps": 30605, "total_steps": 76960, "loss": 0.1906, "lr": 3.767634204083711e-05, "epoch": 7.953482328482329, "percentage": 39.77, "elapsed_time": "0:44:21", "remaining_time": "1:07:11", "throughput": 1035.33, "total_tokens": 2756032} {"current_steps": 30610, "total_steps": 76960, "loss": 0.2388, "lr": 3.7671455005741207e-05, "epoch": 7.954781704781705, "percentage": 39.77, "elapsed_time": "0:44:22", "remaining_time": "1:07:11", "throughput": 1035.33, "total_tokens": 2756480} {"current_steps": 30615, "total_steps": 76960, "loss": 0.25, "lr": 3.766656731894024e-05, "epoch": 7.956081081081081, "percentage": 39.78, "elapsed_time": "0:44:22", "remaining_time": "1:07:10", "throughput": 1035.34, "total_tokens": 2756944} {"current_steps": 30620, "total_steps": 76960, "loss": 0.282, "lr": 3.766167898068558e-05, "epoch": 7.957380457380458, "percentage": 39.79, "elapsed_time": "0:44:23", "remaining_time": "1:07:10", "throughput": 1035.33, "total_tokens": 2757344} {"current_steps": 30625, "total_steps": 76960, "loss": 0.235, "lr": 3.7656789991228636e-05, "epoch": 7.958679833679834, "percentage": 39.79, "elapsed_time": "0:44:23", "remaining_time": "1:07:10", "throughput": 1035.35, "total_tokens": 2757824} {"current_steps": 30630, "total_steps": 76960, "loss": 0.196, "lr": 3.765190035082086e-05, "epoch": 7.95997920997921, "percentage": 39.8, "elapsed_time": "0:44:24", "remaining_time": "1:07:09", "throughput": 1035.36, "total_tokens": 2758288} {"current_steps": 30635, "total_steps": 76960, "loss": 0.2981, "lr": 3.764701005971372e-05, "epoch": 7.961278586278587, "percentage": 39.81, "elapsed_time": "0:44:24", "remaining_time": "1:07:09", "throughput": 1035.37, "total_tokens": 2758736} {"current_steps": 30640, "total_steps": 76960, "loss": 0.1332, "lr": 3.764211911815873e-05, "epoch": 7.962577962577963, "percentage": 39.81, "elapsed_time": "0:44:24", "remaining_time": "1:07:08", "throughput": 1035.37, "total_tokens": 2759168} {"current_steps": 30645, "total_steps": 76960, "loss": 0.233, "lr": 3.7637227526407456e-05, "epoch": 7.963877338877339, "percentage": 39.82, "elapsed_time": "0:44:25", "remaining_time": "1:07:08", "throughput": 1035.4, "total_tokens": 2759680} {"current_steps": 30650, "total_steps": 76960, "loss": 0.2956, "lr": 3.763233528471145e-05, "epoch": 7.965176715176716, "percentage": 39.83, "elapsed_time": "0:44:25", "remaining_time": "1:07:07", "throughput": 1035.4, "total_tokens": 2760128} {"current_steps": 30655, "total_steps": 76960, "loss": 0.3919, "lr": 3.7627442393322344e-05, "epoch": 7.966476091476092, "percentage": 39.83, "elapsed_time": "0:44:26", "remaining_time": "1:07:07", "throughput": 1035.42, "total_tokens": 2760592} {"current_steps": 30660, "total_steps": 76960, "loss": 0.2927, "lr": 3.762254885249177e-05, "epoch": 7.967775467775468, "percentage": 39.84, "elapsed_time": "0:44:26", "remaining_time": "1:07:06", "throughput": 1035.41, "total_tokens": 2760992} {"current_steps": 30665, "total_steps": 76960, "loss": 0.2548, "lr": 3.761765466247142e-05, "epoch": 7.969074844074844, "percentage": 39.85, "elapsed_time": "0:44:26", "remaining_time": "1:07:06", "throughput": 1035.41, "total_tokens": 2761440} {"current_steps": 30670, "total_steps": 76960, "loss": 0.2372, "lr": 3.761275982351299e-05, "epoch": 7.970374220374221, "percentage": 39.85, "elapsed_time": "0:44:27", "remaining_time": "1:07:05", "throughput": 1035.41, "total_tokens": 2761872} {"current_steps": 30675, "total_steps": 76960, "loss": 0.2996, "lr": 3.7607864335868246e-05, "epoch": 7.971673596673597, "percentage": 39.86, "elapsed_time": "0:44:27", "remaining_time": "1:07:05", "throughput": 1035.42, "total_tokens": 2762320} {"current_steps": 30680, "total_steps": 76960, "loss": 0.3118, "lr": 3.760296819978896e-05, "epoch": 7.972972972972973, "percentage": 39.86, "elapsed_time": "0:44:28", "remaining_time": "1:07:04", "throughput": 1035.43, "total_tokens": 2762768} {"current_steps": 30685, "total_steps": 76960, "loss": 0.3026, "lr": 3.759807141552695e-05, "epoch": 7.974272349272349, "percentage": 39.87, "elapsed_time": "0:44:28", "remaining_time": "1:07:04", "throughput": 1035.41, "total_tokens": 2763168} {"current_steps": 30690, "total_steps": 76960, "loss": 0.2332, "lr": 3.759317398333404e-05, "epoch": 7.975571725571726, "percentage": 39.88, "elapsed_time": "0:44:29", "remaining_time": "1:07:04", "throughput": 1035.42, "total_tokens": 2763632} {"current_steps": 30695, "total_steps": 76960, "loss": 0.272, "lr": 3.758827590346213e-05, "epoch": 7.976871101871102, "percentage": 39.88, "elapsed_time": "0:44:29", "remaining_time": "1:07:03", "throughput": 1035.42, "total_tokens": 2764064} {"current_steps": 30700, "total_steps": 76960, "loss": 0.2153, "lr": 3.7583377176163135e-05, "epoch": 7.978170478170478, "percentage": 39.89, "elapsed_time": "0:44:29", "remaining_time": "1:07:03", "throughput": 1035.42, "total_tokens": 2764496} {"current_steps": 30705, "total_steps": 76960, "loss": 0.2924, "lr": 3.7578477801689e-05, "epoch": 7.979469854469855, "percentage": 39.9, "elapsed_time": "0:44:30", "remaining_time": "1:07:02", "throughput": 1035.42, "total_tokens": 2764912} {"current_steps": 30710, "total_steps": 76960, "loss": 0.2962, "lr": 3.757357778029169e-05, "epoch": 7.980769230769231, "percentage": 39.9, "elapsed_time": "0:44:30", "remaining_time": "1:07:02", "throughput": 1035.44, "total_tokens": 2765408} {"current_steps": 30715, "total_steps": 76960, "loss": 0.2793, "lr": 3.7568677112223235e-05, "epoch": 7.982068607068607, "percentage": 39.91, "elapsed_time": "0:44:31", "remaining_time": "1:07:01", "throughput": 1035.47, "total_tokens": 2765920} {"current_steps": 30720, "total_steps": 76960, "loss": 0.2841, "lr": 3.756377579773567e-05, "epoch": 7.983367983367984, "percentage": 39.92, "elapsed_time": "0:44:31", "remaining_time": "1:07:01", "throughput": 1035.49, "total_tokens": 2766400} {"current_steps": 30725, "total_steps": 76960, "loss": 0.2382, "lr": 3.755887383708107e-05, "epoch": 7.98466735966736, "percentage": 39.92, "elapsed_time": "0:44:32", "remaining_time": "1:07:00", "throughput": 1035.5, "total_tokens": 2766864} {"current_steps": 30730, "total_steps": 76960, "loss": 0.2784, "lr": 3.755397123051157e-05, "epoch": 7.985966735966736, "percentage": 39.93, "elapsed_time": "0:44:32", "remaining_time": "1:07:00", "throughput": 1035.51, "total_tokens": 2767328} {"current_steps": 30735, "total_steps": 76960, "loss": 0.2533, "lr": 3.7549067978279285e-05, "epoch": 7.987266112266112, "percentage": 39.94, "elapsed_time": "0:44:32", "remaining_time": "1:06:59", "throughput": 1035.52, "total_tokens": 2767792} {"current_steps": 30740, "total_steps": 76960, "loss": 0.2535, "lr": 3.754416408063642e-05, "epoch": 7.988565488565489, "percentage": 39.94, "elapsed_time": "0:44:33", "remaining_time": "1:06:59", "throughput": 1035.54, "total_tokens": 2768272} {"current_steps": 30745, "total_steps": 76960, "loss": 0.2921, "lr": 3.753925953783517e-05, "epoch": 7.989864864864865, "percentage": 39.95, "elapsed_time": "0:44:33", "remaining_time": "1:06:58", "throughput": 1035.54, "total_tokens": 2768704} {"current_steps": 30750, "total_steps": 76960, "loss": 0.1564, "lr": 3.7534354350127796e-05, "epoch": 7.991164241164241, "percentage": 39.96, "elapsed_time": "0:44:34", "remaining_time": "1:06:58", "throughput": 1035.54, "total_tokens": 2769136} {"current_steps": 30755, "total_steps": 76960, "loss": 0.2547, "lr": 3.7529448517766566e-05, "epoch": 7.992463617463617, "percentage": 39.96, "elapsed_time": "0:44:34", "remaining_time": "1:06:58", "throughput": 1035.56, "total_tokens": 2769600} {"current_steps": 30760, "total_steps": 76960, "loss": 0.3862, "lr": 3.7524542041003785e-05, "epoch": 7.993762993762994, "percentage": 39.97, "elapsed_time": "0:44:34", "remaining_time": "1:06:57", "throughput": 1035.58, "total_tokens": 2770096} {"current_steps": 30765, "total_steps": 76960, "loss": 0.2258, "lr": 3.7519634920091814e-05, "epoch": 7.99506237006237, "percentage": 39.98, "elapsed_time": "0:44:35", "remaining_time": "1:06:57", "throughput": 1035.59, "total_tokens": 2770544} {"current_steps": 30770, "total_steps": 76960, "loss": 0.2407, "lr": 3.751472715528302e-05, "epoch": 7.996361746361746, "percentage": 39.98, "elapsed_time": "0:44:35", "remaining_time": "1:06:56", "throughput": 1035.59, "total_tokens": 2770976} {"current_steps": 30775, "total_steps": 76960, "loss": 0.2296, "lr": 3.750981874682982e-05, "epoch": 7.997661122661123, "percentage": 39.99, "elapsed_time": "0:44:36", "remaining_time": "1:06:56", "throughput": 1035.59, "total_tokens": 2771408} {"current_steps": 30780, "total_steps": 76960, "loss": 0.1858, "lr": 3.750490969498466e-05, "epoch": 7.998960498960499, "percentage": 39.99, "elapsed_time": "0:44:36", "remaining_time": "1:06:55", "throughput": 1035.59, "total_tokens": 2771840} {"current_steps": 30784, "total_steps": 76960, "eval_loss": 0.23655234277248383, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:44:50", "remaining_time": "1:07:15", "throughput": 1030.48, "total_tokens": 2772144} {"current_steps": 30785, "total_steps": 76960, "loss": 0.4073, "lr": 3.7500000000000003e-05, "epoch": 8.000259875259875, "percentage": 40.0, "elapsed_time": "0:44:51", "remaining_time": "1:07:17", "throughput": 1029.88, "total_tokens": 2772224} {"current_steps": 30790, "total_steps": 76960, "loss": 0.2191, "lr": 3.7495089662128375e-05, "epoch": 8.001559251559252, "percentage": 40.01, "elapsed_time": "0:44:52", "remaining_time": "1:07:17", "throughput": 1029.89, "total_tokens": 2772688} {"current_steps": 30795, "total_steps": 76960, "loss": 0.2937, "lr": 3.749017868162231e-05, "epoch": 8.002858627858627, "percentage": 40.01, "elapsed_time": "0:44:52", "remaining_time": "1:07:16", "throughput": 1029.89, "total_tokens": 2773168} {"current_steps": 30800, "total_steps": 76960, "loss": 0.2985, "lr": 3.748526705873439e-05, "epoch": 8.004158004158004, "percentage": 40.02, "elapsed_time": "0:44:53", "remaining_time": "1:07:16", "throughput": 1029.89, "total_tokens": 2773600} {"current_steps": 30805, "total_steps": 76960, "loss": 0.174, "lr": 3.748035479371722e-05, "epoch": 8.005457380457381, "percentage": 40.03, "elapsed_time": "0:44:53", "remaining_time": "1:07:15", "throughput": 1029.9, "total_tokens": 2774048} {"current_steps": 30810, "total_steps": 76960, "loss": 0.3373, "lr": 3.7475441886823454e-05, "epoch": 8.006756756756756, "percentage": 40.03, "elapsed_time": "0:44:53", "remaining_time": "1:07:15", "throughput": 1029.91, "total_tokens": 2774512} {"current_steps": 30815, "total_steps": 76960, "loss": 0.3074, "lr": 3.747052833830574e-05, "epoch": 8.008056133056133, "percentage": 40.04, "elapsed_time": "0:44:54", "remaining_time": "1:07:14", "throughput": 1029.91, "total_tokens": 2774960} {"current_steps": 30820, "total_steps": 76960, "loss": 0.189, "lr": 3.746561414841682e-05, "epoch": 8.00935550935551, "percentage": 40.05, "elapsed_time": "0:44:54", "remaining_time": "1:07:14", "throughput": 1029.9, "total_tokens": 2775376} {"current_steps": 30825, "total_steps": 76960, "loss": 0.2131, "lr": 3.746069931740942e-05, "epoch": 8.010654885654885, "percentage": 40.05, "elapsed_time": "0:44:55", "remaining_time": "1:07:13", "throughput": 1029.91, "total_tokens": 2775840} {"current_steps": 30830, "total_steps": 76960, "loss": 0.3261, "lr": 3.7455783845536316e-05, "epoch": 8.011954261954262, "percentage": 40.06, "elapsed_time": "0:44:55", "remaining_time": "1:07:13", "throughput": 1029.91, "total_tokens": 2776256} {"current_steps": 30835, "total_steps": 76960, "loss": 0.1953, "lr": 3.7450867733050306e-05, "epoch": 8.013253638253639, "percentage": 40.07, "elapsed_time": "0:44:56", "remaining_time": "1:07:12", "throughput": 1029.92, "total_tokens": 2776720} {"current_steps": 30840, "total_steps": 76960, "loss": 0.293, "lr": 3.744595098020425e-05, "epoch": 8.014553014553014, "percentage": 40.07, "elapsed_time": "0:44:56", "remaining_time": "1:07:12", "throughput": 1029.93, "total_tokens": 2777184} {"current_steps": 30845, "total_steps": 76960, "loss": 0.2662, "lr": 3.7441033587251e-05, "epoch": 8.015852390852391, "percentage": 40.08, "elapsed_time": "0:44:56", "remaining_time": "1:07:12", "throughput": 1029.93, "total_tokens": 2777632} {"current_steps": 30850, "total_steps": 76960, "loss": 0.2015, "lr": 3.7436115554443474e-05, "epoch": 8.017151767151768, "percentage": 40.09, "elapsed_time": "0:44:57", "remaining_time": "1:07:11", "throughput": 1029.93, "total_tokens": 2778064} {"current_steps": 30855, "total_steps": 76960, "loss": 0.2129, "lr": 3.743119688203461e-05, "epoch": 8.018451143451143, "percentage": 40.09, "elapsed_time": "0:44:57", "remaining_time": "1:07:11", "throughput": 1029.93, "total_tokens": 2778496} {"current_steps": 30860, "total_steps": 76960, "loss": 0.1965, "lr": 3.742627757027738e-05, "epoch": 8.01975051975052, "percentage": 40.1, "elapsed_time": "0:44:58", "remaining_time": "1:07:10", "throughput": 1029.93, "total_tokens": 2778928} {"current_steps": 30865, "total_steps": 76960, "loss": 0.2801, "lr": 3.742135761942479e-05, "epoch": 8.021049896049895, "percentage": 40.11, "elapsed_time": "0:44:58", "remaining_time": "1:07:10", "throughput": 1029.95, "total_tokens": 2779408} {"current_steps": 30870, "total_steps": 76960, "loss": 0.2602, "lr": 3.7416437029729865e-05, "epoch": 8.022349272349272, "percentage": 40.11, "elapsed_time": "0:44:59", "remaining_time": "1:07:09", "throughput": 1029.96, "total_tokens": 2779872} {"current_steps": 30875, "total_steps": 76960, "loss": 0.3048, "lr": 3.7411515801445695e-05, "epoch": 8.02364864864865, "percentage": 40.12, "elapsed_time": "0:44:59", "remaining_time": "1:07:09", "throughput": 1029.97, "total_tokens": 2780336} {"current_steps": 30880, "total_steps": 76960, "loss": 0.1806, "lr": 3.740659393482538e-05, "epoch": 8.024948024948024, "percentage": 40.12, "elapsed_time": "0:44:59", "remaining_time": "1:07:08", "throughput": 1029.97, "total_tokens": 2780768} {"current_steps": 30885, "total_steps": 76960, "loss": 0.266, "lr": 3.740167143012204e-05, "epoch": 8.026247401247401, "percentage": 40.13, "elapsed_time": "0:45:00", "remaining_time": "1:07:08", "throughput": 1029.97, "total_tokens": 2781184} {"current_steps": 30890, "total_steps": 76960, "loss": 0.2127, "lr": 3.739674828758887e-05, "epoch": 8.027546777546778, "percentage": 40.14, "elapsed_time": "0:45:00", "remaining_time": "1:07:07", "throughput": 1029.97, "total_tokens": 2781632} {"current_steps": 30895, "total_steps": 76960, "loss": 0.2126, "lr": 3.739182450747905e-05, "epoch": 8.028846153846153, "percentage": 40.14, "elapsed_time": "0:45:01", "remaining_time": "1:07:07", "throughput": 1029.97, "total_tokens": 2782048} {"current_steps": 30900, "total_steps": 76960, "loss": 0.2346, "lr": 3.738690009004582e-05, "epoch": 8.03014553014553, "percentage": 40.15, "elapsed_time": "0:45:01", "remaining_time": "1:07:06", "throughput": 1029.97, "total_tokens": 2782480} {"current_steps": 30905, "total_steps": 76960, "loss": 0.153, "lr": 3.738197503554245e-05, "epoch": 8.031444906444907, "percentage": 40.16, "elapsed_time": "0:45:01", "remaining_time": "1:07:06", "throughput": 1029.97, "total_tokens": 2782928} {"current_steps": 30910, "total_steps": 76960, "loss": 0.2775, "lr": 3.737704934422225e-05, "epoch": 8.032744282744282, "percentage": 40.16, "elapsed_time": "0:45:02", "remaining_time": "1:07:06", "throughput": 1029.98, "total_tokens": 2783376} {"current_steps": 30915, "total_steps": 76960, "loss": 0.2327, "lr": 3.737212301633853e-05, "epoch": 8.03404365904366, "percentage": 40.17, "elapsed_time": "0:45:02", "remaining_time": "1:07:05", "throughput": 1029.99, "total_tokens": 2783840} {"current_steps": 30920, "total_steps": 76960, "loss": 0.2293, "lr": 3.7367196052144676e-05, "epoch": 8.035343035343036, "percentage": 40.18, "elapsed_time": "0:45:03", "remaining_time": "1:07:05", "throughput": 1029.99, "total_tokens": 2784272} {"current_steps": 30925, "total_steps": 76960, "loss": 0.2942, "lr": 3.7362268451894075e-05, "epoch": 8.036642411642411, "percentage": 40.18, "elapsed_time": "0:45:03", "remaining_time": "1:07:04", "throughput": 1030.01, "total_tokens": 2784752} {"current_steps": 30930, "total_steps": 76960, "loss": 0.404, "lr": 3.7357340215840175e-05, "epoch": 8.037941787941788, "percentage": 40.19, "elapsed_time": "0:45:04", "remaining_time": "1:07:04", "throughput": 1030.01, "total_tokens": 2785184} {"current_steps": 30935, "total_steps": 76960, "loss": 0.2551, "lr": 3.7352411344236414e-05, "epoch": 8.039241164241163, "percentage": 40.2, "elapsed_time": "0:45:04", "remaining_time": "1:07:03", "throughput": 1030.0, "total_tokens": 2785600} {"current_steps": 30940, "total_steps": 76960, "loss": 0.2238, "lr": 3.7347481837336306e-05, "epoch": 8.04054054054054, "percentage": 40.2, "elapsed_time": "0:45:04", "remaining_time": "1:07:03", "throughput": 1030.0, "total_tokens": 2786032} {"current_steps": 30945, "total_steps": 76960, "loss": 0.2274, "lr": 3.734255169539337e-05, "epoch": 8.041839916839917, "percentage": 40.21, "elapsed_time": "0:45:05", "remaining_time": "1:07:02", "throughput": 1030.01, "total_tokens": 2786480} {"current_steps": 30950, "total_steps": 76960, "loss": 0.2543, "lr": 3.7337620918661185e-05, "epoch": 8.043139293139292, "percentage": 40.22, "elapsed_time": "0:45:05", "remaining_time": "1:07:02", "throughput": 1030.03, "total_tokens": 2786976} {"current_steps": 30955, "total_steps": 76960, "loss": 0.2945, "lr": 3.7332689507393334e-05, "epoch": 8.04443866943867, "percentage": 40.22, "elapsed_time": "0:45:06", "remaining_time": "1:07:01", "throughput": 1030.04, "total_tokens": 2787424} {"current_steps": 30960, "total_steps": 76960, "loss": 0.221, "lr": 3.7327757461843435e-05, "epoch": 8.045738045738046, "percentage": 40.23, "elapsed_time": "0:45:06", "remaining_time": "1:07:01", "throughput": 1030.05, "total_tokens": 2787888} {"current_steps": 30965, "total_steps": 76960, "loss": 0.2576, "lr": 3.732282478226516e-05, "epoch": 8.047037422037421, "percentage": 40.24, "elapsed_time": "0:45:06", "remaining_time": "1:07:00", "throughput": 1030.08, "total_tokens": 2788384} {"current_steps": 30970, "total_steps": 76960, "loss": 0.2521, "lr": 3.7317891468912214e-05, "epoch": 8.048336798336798, "percentage": 40.24, "elapsed_time": "0:45:07", "remaining_time": "1:07:00", "throughput": 1030.09, "total_tokens": 2788848} {"current_steps": 30975, "total_steps": 76960, "loss": 0.2887, "lr": 3.7312957522038293e-05, "epoch": 8.049636174636175, "percentage": 40.25, "elapsed_time": "0:45:07", "remaining_time": "1:06:59", "throughput": 1030.09, "total_tokens": 2789280} {"current_steps": 30980, "total_steps": 76960, "loss": 0.2188, "lr": 3.730802294189718e-05, "epoch": 8.05093555093555, "percentage": 40.25, "elapsed_time": "0:45:08", "remaining_time": "1:06:59", "throughput": 1030.1, "total_tokens": 2789744} {"current_steps": 30985, "total_steps": 76960, "loss": 0.2954, "lr": 3.7303087728742644e-05, "epoch": 8.052234927234927, "percentage": 40.26, "elapsed_time": "0:45:08", "remaining_time": "1:06:59", "throughput": 1030.11, "total_tokens": 2790208} {"current_steps": 30990, "total_steps": 76960, "loss": 0.2381, "lr": 3.7298151882828526e-05, "epoch": 8.053534303534304, "percentage": 40.27, "elapsed_time": "0:45:09", "remaining_time": "1:06:58", "throughput": 1030.12, "total_tokens": 2790656} {"current_steps": 30995, "total_steps": 76960, "loss": 0.1785, "lr": 3.729321540440866e-05, "epoch": 8.05483367983368, "percentage": 40.27, "elapsed_time": "0:45:09", "remaining_time": "1:06:58", "throughput": 1030.13, "total_tokens": 2791120} {"current_steps": 31000, "total_steps": 76960, "loss": 0.0911, "lr": 3.728827829373696e-05, "epoch": 8.056133056133056, "percentage": 40.28, "elapsed_time": "0:45:09", "remaining_time": "1:06:57", "throughput": 1030.14, "total_tokens": 2791568} {"current_steps": 31005, "total_steps": 76960, "loss": 0.4338, "lr": 3.728334055106732e-05, "epoch": 8.057432432432432, "percentage": 40.29, "elapsed_time": "0:45:10", "remaining_time": "1:06:57", "throughput": 1030.13, "total_tokens": 2791984} {"current_steps": 31010, "total_steps": 76960, "loss": 0.3222, "lr": 3.727840217665371e-05, "epoch": 8.058731808731808, "percentage": 40.29, "elapsed_time": "0:45:10", "remaining_time": "1:06:56", "throughput": 1030.13, "total_tokens": 2792400} {"current_steps": 31015, "total_steps": 76960, "loss": 0.1452, "lr": 3.727346317075012e-05, "epoch": 8.060031185031185, "percentage": 40.3, "elapsed_time": "0:45:11", "remaining_time": "1:06:56", "throughput": 1030.14, "total_tokens": 2792848} {"current_steps": 31020, "total_steps": 76960, "loss": 0.3931, "lr": 3.7268523533610564e-05, "epoch": 8.06133056133056, "percentage": 40.31, "elapsed_time": "0:45:11", "remaining_time": "1:06:55", "throughput": 1030.14, "total_tokens": 2793296} {"current_steps": 31025, "total_steps": 76960, "loss": 0.3496, "lr": 3.7263583265489074e-05, "epoch": 8.062629937629938, "percentage": 40.31, "elapsed_time": "0:45:11", "remaining_time": "1:06:55", "throughput": 1030.14, "total_tokens": 2793728} {"current_steps": 31030, "total_steps": 76960, "loss": 0.1798, "lr": 3.7258642366639754e-05, "epoch": 8.063929313929314, "percentage": 40.32, "elapsed_time": "0:45:12", "remaining_time": "1:06:54", "throughput": 1030.15, "total_tokens": 2794176} {"current_steps": 31035, "total_steps": 76960, "loss": 0.3691, "lr": 3.72537008373167e-05, "epoch": 8.06522869022869, "percentage": 40.33, "elapsed_time": "0:45:12", "remaining_time": "1:06:54", "throughput": 1030.15, "total_tokens": 2794608} {"current_steps": 31040, "total_steps": 76960, "loss": 0.2424, "lr": 3.724875867777409e-05, "epoch": 8.066528066528067, "percentage": 40.33, "elapsed_time": "0:45:13", "remaining_time": "1:06:53", "throughput": 1030.15, "total_tokens": 2795024} {"current_steps": 31045, "total_steps": 76960, "loss": 0.2975, "lr": 3.724381588826607e-05, "epoch": 8.067827442827443, "percentage": 40.34, "elapsed_time": "0:45:13", "remaining_time": "1:06:53", "throughput": 1030.16, "total_tokens": 2795488} {"current_steps": 31050, "total_steps": 76960, "loss": 0.2831, "lr": 3.723887246904687e-05, "epoch": 8.069126819126819, "percentage": 40.35, "elapsed_time": "0:45:14", "remaining_time": "1:06:52", "throughput": 1030.17, "total_tokens": 2795952} {"current_steps": 31055, "total_steps": 76960, "loss": 0.2673, "lr": 3.7233928420370735e-05, "epoch": 8.070426195426196, "percentage": 40.35, "elapsed_time": "0:45:14", "remaining_time": "1:06:52", "throughput": 1030.17, "total_tokens": 2796384} {"current_steps": 31060, "total_steps": 76960, "loss": 0.2438, "lr": 3.722898374249194e-05, "epoch": 8.071725571725572, "percentage": 40.36, "elapsed_time": "0:45:14", "remaining_time": "1:06:52", "throughput": 1030.17, "total_tokens": 2796800} {"current_steps": 31065, "total_steps": 76960, "loss": 0.1827, "lr": 3.722403843566479e-05, "epoch": 8.073024948024948, "percentage": 40.37, "elapsed_time": "0:45:15", "remaining_time": "1:06:51", "throughput": 1030.17, "total_tokens": 2797232} {"current_steps": 31070, "total_steps": 76960, "loss": 0.1862, "lr": 3.721909250014363e-05, "epoch": 8.074324324324325, "percentage": 40.37, "elapsed_time": "0:45:15", "remaining_time": "1:06:51", "throughput": 1030.16, "total_tokens": 2797648} {"current_steps": 31075, "total_steps": 76960, "loss": 0.2705, "lr": 3.721414593618284e-05, "epoch": 8.075623700623701, "percentage": 40.38, "elapsed_time": "0:45:16", "remaining_time": "1:06:50", "throughput": 1030.17, "total_tokens": 2798096} {"current_steps": 31080, "total_steps": 76960, "loss": 0.2467, "lr": 3.720919874403682e-05, "epoch": 8.076923076923077, "percentage": 40.38, "elapsed_time": "0:45:16", "remaining_time": "1:06:50", "throughput": 1030.17, "total_tokens": 2798528} {"current_steps": 31085, "total_steps": 76960, "loss": 0.3253, "lr": 3.720425092396001e-05, "epoch": 8.078222453222454, "percentage": 40.39, "elapsed_time": "0:45:17", "remaining_time": "1:06:49", "throughput": 1030.17, "total_tokens": 2798976} {"current_steps": 31090, "total_steps": 76960, "loss": 0.1835, "lr": 3.7199302476206883e-05, "epoch": 8.079521829521829, "percentage": 40.4, "elapsed_time": "0:45:17", "remaining_time": "1:06:49", "throughput": 1030.17, "total_tokens": 2799408} {"current_steps": 31095, "total_steps": 76960, "loss": 0.3684, "lr": 3.719435340103193e-05, "epoch": 8.080821205821206, "percentage": 40.4, "elapsed_time": "0:45:17", "remaining_time": "1:06:48", "throughput": 1030.17, "total_tokens": 2799840} {"current_steps": 31100, "total_steps": 76960, "loss": 0.2984, "lr": 3.718940369868972e-05, "epoch": 8.082120582120583, "percentage": 40.41, "elapsed_time": "0:45:18", "remaining_time": "1:06:48", "throughput": 1030.18, "total_tokens": 2800288} {"current_steps": 31105, "total_steps": 76960, "loss": 0.2923, "lr": 3.718445336943478e-05, "epoch": 8.083419958419958, "percentage": 40.42, "elapsed_time": "0:45:18", "remaining_time": "1:06:47", "throughput": 1030.19, "total_tokens": 2800736} {"current_steps": 31110, "total_steps": 76960, "loss": 0.2694, "lr": 3.717950241352173e-05, "epoch": 8.084719334719335, "percentage": 40.42, "elapsed_time": "0:45:19", "remaining_time": "1:06:47", "throughput": 1030.2, "total_tokens": 2801200} {"current_steps": 31115, "total_steps": 76960, "loss": 0.2586, "lr": 3.717455083120521e-05, "epoch": 8.086018711018712, "percentage": 40.43, "elapsed_time": "0:45:19", "remaining_time": "1:06:46", "throughput": 1030.21, "total_tokens": 2801664} {"current_steps": 31120, "total_steps": 76960, "loss": 0.1841, "lr": 3.716959862273987e-05, "epoch": 8.087318087318087, "percentage": 40.44, "elapsed_time": "0:45:19", "remaining_time": "1:06:46", "throughput": 1030.21, "total_tokens": 2802096} {"current_steps": 31125, "total_steps": 76960, "loss": 0.2713, "lr": 3.716464578838041e-05, "epoch": 8.088617463617464, "percentage": 40.44, "elapsed_time": "0:45:20", "remaining_time": "1:06:45", "throughput": 1030.22, "total_tokens": 2802544} {"current_steps": 31130, "total_steps": 76960, "loss": 0.2851, "lr": 3.715969232838157e-05, "epoch": 8.08991683991684, "percentage": 40.45, "elapsed_time": "0:45:20", "remaining_time": "1:06:45", "throughput": 1030.22, "total_tokens": 2802976} {"current_steps": 31135, "total_steps": 76960, "loss": 0.1999, "lr": 3.715473824299809e-05, "epoch": 8.091216216216216, "percentage": 40.46, "elapsed_time": "0:45:21", "remaining_time": "1:06:45", "throughput": 1030.23, "total_tokens": 2803440} {"current_steps": 31140, "total_steps": 76960, "loss": 0.246, "lr": 3.7149783532484784e-05, "epoch": 8.092515592515593, "percentage": 40.46, "elapsed_time": "0:45:21", "remaining_time": "1:06:44", "throughput": 1030.25, "total_tokens": 2803920} {"current_steps": 31145, "total_steps": 76960, "loss": 0.267, "lr": 3.714482819709647e-05, "epoch": 8.09381496881497, "percentage": 40.47, "elapsed_time": "0:45:22", "remaining_time": "1:06:44", "throughput": 1030.26, "total_tokens": 2804368} {"current_steps": 31150, "total_steps": 76960, "loss": 0.2483, "lr": 3.7139872237088e-05, "epoch": 8.095114345114345, "percentage": 40.48, "elapsed_time": "0:45:22", "remaining_time": "1:06:43", "throughput": 1030.27, "total_tokens": 2804832} {"current_steps": 31155, "total_steps": 76960, "loss": 0.2681, "lr": 3.713491565271427e-05, "epoch": 8.096413721413722, "percentage": 40.48, "elapsed_time": "0:45:22", "remaining_time": "1:06:43", "throughput": 1030.3, "total_tokens": 2805328} {"current_steps": 31160, "total_steps": 76960, "loss": 0.2034, "lr": 3.712995844423021e-05, "epoch": 8.097713097713097, "percentage": 40.49, "elapsed_time": "0:45:23", "remaining_time": "1:06:42", "throughput": 1030.3, "total_tokens": 2805760} {"current_steps": 31165, "total_steps": 76960, "loss": 0.1528, "lr": 3.7125000611890754e-05, "epoch": 8.099012474012474, "percentage": 40.5, "elapsed_time": "0:45:23", "remaining_time": "1:06:42", "throughput": 1030.31, "total_tokens": 2806208} {"current_steps": 31170, "total_steps": 76960, "loss": 0.2664, "lr": 3.712004215595091e-05, "epoch": 8.10031185031185, "percentage": 40.5, "elapsed_time": "0:45:24", "remaining_time": "1:06:41", "throughput": 1030.31, "total_tokens": 2806656} {"current_steps": 31175, "total_steps": 76960, "loss": 0.3121, "lr": 3.711508307666568e-05, "epoch": 8.101611226611226, "percentage": 40.51, "elapsed_time": "0:45:24", "remaining_time": "1:06:41", "throughput": 1030.31, "total_tokens": 2807088} {"current_steps": 31180, "total_steps": 76960, "loss": 0.261, "lr": 3.711012337429011e-05, "epoch": 8.102910602910603, "percentage": 40.51, "elapsed_time": "0:45:24", "remaining_time": "1:06:40", "throughput": 1030.32, "total_tokens": 2807536} {"current_steps": 31185, "total_steps": 76960, "loss": 0.1503, "lr": 3.710516304907931e-05, "epoch": 8.10420997920998, "percentage": 40.52, "elapsed_time": "0:45:25", "remaining_time": "1:06:40", "throughput": 1030.32, "total_tokens": 2807968} {"current_steps": 31190, "total_steps": 76960, "loss": 0.1569, "lr": 3.7100202101288355e-05, "epoch": 8.105509355509355, "percentage": 40.53, "elapsed_time": "0:45:25", "remaining_time": "1:06:39", "throughput": 1030.33, "total_tokens": 2808432} {"current_steps": 31195, "total_steps": 76960, "loss": 0.3294, "lr": 3.709524053117242e-05, "epoch": 8.106808731808732, "percentage": 40.53, "elapsed_time": "0:45:26", "remaining_time": "1:06:39", "throughput": 1030.33, "total_tokens": 2808848} {"current_steps": 31200, "total_steps": 76960, "loss": 0.216, "lr": 3.7090278338986685e-05, "epoch": 8.108108108108109, "percentage": 40.54, "elapsed_time": "0:45:26", "remaining_time": "1:06:38", "throughput": 1030.33, "total_tokens": 2809296} {"current_steps": 31205, "total_steps": 76960, "loss": 0.2257, "lr": 3.708531552498634e-05, "epoch": 8.109407484407484, "percentage": 40.55, "elapsed_time": "0:45:27", "remaining_time": "1:06:38", "throughput": 1030.34, "total_tokens": 2809744} {"current_steps": 31210, "total_steps": 76960, "loss": 0.3703, "lr": 3.708035208942664e-05, "epoch": 8.11070686070686, "percentage": 40.55, "elapsed_time": "0:45:27", "remaining_time": "1:06:38", "throughput": 1030.36, "total_tokens": 2810224} {"current_steps": 31215, "total_steps": 76960, "loss": 0.1997, "lr": 3.7075388032562855e-05, "epoch": 8.112006237006238, "percentage": 40.56, "elapsed_time": "0:45:27", "remaining_time": "1:06:37", "throughput": 1030.37, "total_tokens": 2810688} {"current_steps": 31220, "total_steps": 76960, "loss": 0.4748, "lr": 3.7070423354650296e-05, "epoch": 8.113305613305613, "percentage": 40.57, "elapsed_time": "0:45:28", "remaining_time": "1:06:37", "throughput": 1030.39, "total_tokens": 2811152} {"current_steps": 31225, "total_steps": 76960, "loss": 0.813, "lr": 3.70654580559443e-05, "epoch": 8.11460498960499, "percentage": 40.57, "elapsed_time": "0:45:28", "remaining_time": "1:06:36", "throughput": 1030.4, "total_tokens": 2811616} {"current_steps": 31230, "total_steps": 76960, "loss": 0.2291, "lr": 3.706049213670023e-05, "epoch": 8.115904365904365, "percentage": 40.58, "elapsed_time": "0:45:29", "remaining_time": "1:06:36", "throughput": 1030.41, "total_tokens": 2812080} {"current_steps": 31235, "total_steps": 76960, "loss": 0.718, "lr": 3.705552559717351e-05, "epoch": 8.117203742203742, "percentage": 40.59, "elapsed_time": "0:45:29", "remaining_time": "1:06:35", "throughput": 1030.43, "total_tokens": 2812576} {"current_steps": 31240, "total_steps": 76960, "loss": 0.2385, "lr": 3.7050558437619544e-05, "epoch": 8.118503118503119, "percentage": 40.59, "elapsed_time": "0:45:29", "remaining_time": "1:06:35", "throughput": 1030.45, "total_tokens": 2813040} {"current_steps": 31245, "total_steps": 76960, "loss": 0.2039, "lr": 3.704559065829381e-05, "epoch": 8.119802494802494, "percentage": 40.6, "elapsed_time": "0:45:30", "remaining_time": "1:06:34", "throughput": 1030.45, "total_tokens": 2813488} {"current_steps": 31250, "total_steps": 76960, "loss": 0.2993, "lr": 3.7040622259451815e-05, "epoch": 8.121101871101871, "percentage": 40.61, "elapsed_time": "0:45:30", "remaining_time": "1:06:34", "throughput": 1030.45, "total_tokens": 2813936} {"current_steps": 31255, "total_steps": 76960, "loss": 0.2922, "lr": 3.7035653241349075e-05, "epoch": 8.122401247401248, "percentage": 40.61, "elapsed_time": "0:45:31", "remaining_time": "1:06:33", "throughput": 1030.45, "total_tokens": 2814368} {"current_steps": 31260, "total_steps": 76960, "loss": 0.2792, "lr": 3.703068360424115e-05, "epoch": 8.123700623700623, "percentage": 40.62, "elapsed_time": "0:45:31", "remaining_time": "1:06:33", "throughput": 1030.45, "total_tokens": 2814800} {"current_steps": 31265, "total_steps": 76960, "loss": 0.1997, "lr": 3.702571334838365e-05, "epoch": 8.125, "percentage": 40.62, "elapsed_time": "0:45:32", "remaining_time": "1:06:32", "throughput": 1030.46, "total_tokens": 2815248} {"current_steps": 31270, "total_steps": 76960, "loss": 0.2514, "lr": 3.702074247403219e-05, "epoch": 8.126299376299377, "percentage": 40.63, "elapsed_time": "0:45:32", "remaining_time": "1:06:32", "throughput": 1030.46, "total_tokens": 2815696} {"current_steps": 31275, "total_steps": 76960, "loss": 0.2991, "lr": 3.701577098144242e-05, "epoch": 8.127598752598752, "percentage": 40.64, "elapsed_time": "0:45:32", "remaining_time": "1:06:32", "throughput": 1030.47, "total_tokens": 2816144} {"current_steps": 31280, "total_steps": 76960, "loss": 0.1448, "lr": 3.7010798870870036e-05, "epoch": 8.128898128898129, "percentage": 40.64, "elapsed_time": "0:45:33", "remaining_time": "1:06:31", "throughput": 1030.48, "total_tokens": 2816592} {"current_steps": 31285, "total_steps": 76960, "loss": 0.3055, "lr": 3.7005826142570765e-05, "epoch": 8.130197505197506, "percentage": 40.65, "elapsed_time": "0:45:33", "remaining_time": "1:06:31", "throughput": 1030.5, "total_tokens": 2817088} {"current_steps": 31290, "total_steps": 76960, "loss": 0.464, "lr": 3.700085279680035e-05, "epoch": 8.131496881496881, "percentage": 40.66, "elapsed_time": "0:45:34", "remaining_time": "1:06:30", "throughput": 1030.51, "total_tokens": 2817536} {"current_steps": 31295, "total_steps": 76960, "loss": 0.2194, "lr": 3.699587883381458e-05, "epoch": 8.132796257796258, "percentage": 40.66, "elapsed_time": "0:45:34", "remaining_time": "1:06:30", "throughput": 1030.51, "total_tokens": 2817984} {"current_steps": 31300, "total_steps": 76960, "loss": 0.2016, "lr": 3.699090425386926e-05, "epoch": 8.134095634095635, "percentage": 40.67, "elapsed_time": "0:45:34", "remaining_time": "1:06:29", "throughput": 1030.52, "total_tokens": 2818432} {"current_steps": 31305, "total_steps": 76960, "loss": 0.1227, "lr": 3.698592905722025e-05, "epoch": 8.13539501039501, "percentage": 40.68, "elapsed_time": "0:45:35", "remaining_time": "1:06:29", "throughput": 1030.53, "total_tokens": 2818880} {"current_steps": 31310, "total_steps": 76960, "loss": 0.2246, "lr": 3.698095324412342e-05, "epoch": 8.136694386694387, "percentage": 40.68, "elapsed_time": "0:45:35", "remaining_time": "1:06:28", "throughput": 1030.55, "total_tokens": 2819360} {"current_steps": 31315, "total_steps": 76960, "loss": 0.4023, "lr": 3.6975976814834685e-05, "epoch": 8.137993762993762, "percentage": 40.69, "elapsed_time": "0:45:36", "remaining_time": "1:06:28", "throughput": 1030.55, "total_tokens": 2819792} {"current_steps": 31320, "total_steps": 76960, "loss": 0.2599, "lr": 3.6970999769609995e-05, "epoch": 8.13929313929314, "percentage": 40.7, "elapsed_time": "0:45:36", "remaining_time": "1:06:27", "throughput": 1030.56, "total_tokens": 2820256} {"current_steps": 31325, "total_steps": 76960, "loss": 0.3165, "lr": 3.696602210870531e-05, "epoch": 8.140592515592516, "percentage": 40.7, "elapsed_time": "0:45:37", "remaining_time": "1:06:27", "throughput": 1030.57, "total_tokens": 2820720} {"current_steps": 31330, "total_steps": 76960, "loss": 0.2448, "lr": 3.6961043832376646e-05, "epoch": 8.141891891891891, "percentage": 40.71, "elapsed_time": "0:45:37", "remaining_time": "1:06:26", "throughput": 1030.59, "total_tokens": 2821184} {"current_steps": 31335, "total_steps": 76960, "loss": 0.2703, "lr": 3.695606494088003e-05, "epoch": 8.143191268191268, "percentage": 40.72, "elapsed_time": "0:45:37", "remaining_time": "1:06:26", "throughput": 1030.59, "total_tokens": 2821616} {"current_steps": 31340, "total_steps": 76960, "loss": 0.3021, "lr": 3.695108543447154e-05, "epoch": 8.144490644490645, "percentage": 40.72, "elapsed_time": "0:45:38", "remaining_time": "1:06:25", "throughput": 1030.61, "total_tokens": 2822112} {"current_steps": 31345, "total_steps": 76960, "loss": 0.238, "lr": 3.694610531340729e-05, "epoch": 8.14579002079002, "percentage": 40.73, "elapsed_time": "0:45:38", "remaining_time": "1:06:25", "throughput": 1030.63, "total_tokens": 2822576} {"current_steps": 31350, "total_steps": 76960, "loss": 0.3003, "lr": 3.6941124577943384e-05, "epoch": 8.147089397089397, "percentage": 40.74, "elapsed_time": "0:45:39", "remaining_time": "1:06:25", "throughput": 1030.63, "total_tokens": 2823024} {"current_steps": 31355, "total_steps": 76960, "loss": 0.2514, "lr": 3.6936143228336e-05, "epoch": 8.148388773388774, "percentage": 40.74, "elapsed_time": "0:45:39", "remaining_time": "1:06:24", "throughput": 1030.66, "total_tokens": 2823520} {"current_steps": 31360, "total_steps": 76960, "loss": 0.2359, "lr": 3.6931161264841334e-05, "epoch": 8.14968814968815, "percentage": 40.75, "elapsed_time": "0:45:39", "remaining_time": "1:06:24", "throughput": 1030.67, "total_tokens": 2823984} {"current_steps": 31365, "total_steps": 76960, "loss": 0.3142, "lr": 3.692617868771562e-05, "epoch": 8.150987525987526, "percentage": 40.75, "elapsed_time": "0:45:40", "remaining_time": "1:06:23", "throughput": 1030.69, "total_tokens": 2824464} {"current_steps": 31370, "total_steps": 76960, "loss": 0.2677, "lr": 3.69211954972151e-05, "epoch": 8.152286902286903, "percentage": 40.76, "elapsed_time": "0:45:40", "remaining_time": "1:06:23", "throughput": 1030.7, "total_tokens": 2824912} {"current_steps": 31375, "total_steps": 76960, "loss": 0.2569, "lr": 3.6916211693596074e-05, "epoch": 8.153586278586278, "percentage": 40.77, "elapsed_time": "0:45:41", "remaining_time": "1:06:22", "throughput": 1030.7, "total_tokens": 2825344} {"current_steps": 31380, "total_steps": 76960, "loss": 0.2412, "lr": 3.6911227277114866e-05, "epoch": 8.154885654885655, "percentage": 40.77, "elapsed_time": "0:45:41", "remaining_time": "1:06:22", "throughput": 1030.69, "total_tokens": 2825760} {"current_steps": 31385, "total_steps": 76960, "loss": 0.1889, "lr": 3.6906242248027826e-05, "epoch": 8.15618503118503, "percentage": 40.78, "elapsed_time": "0:45:42", "remaining_time": "1:06:21", "throughput": 1030.73, "total_tokens": 2826288} {"current_steps": 31390, "total_steps": 76960, "loss": 0.2321, "lr": 3.690125660659134e-05, "epoch": 8.157484407484407, "percentage": 40.79, "elapsed_time": "0:45:42", "remaining_time": "1:06:21", "throughput": 1030.74, "total_tokens": 2826752} {"current_steps": 31395, "total_steps": 76960, "loss": 0.3044, "lr": 3.6896270353061824e-05, "epoch": 8.158783783783784, "percentage": 40.79, "elapsed_time": "0:45:42", "remaining_time": "1:06:20", "throughput": 1030.74, "total_tokens": 2827184} {"current_steps": 31400, "total_steps": 76960, "loss": 0.2507, "lr": 3.6891283487695723e-05, "epoch": 8.16008316008316, "percentage": 40.8, "elapsed_time": "0:45:43", "remaining_time": "1:06:20", "throughput": 1030.74, "total_tokens": 2827616} {"current_steps": 31405, "total_steps": 76960, "loss": 0.2707, "lr": 3.688629601074951e-05, "epoch": 8.161382536382536, "percentage": 40.81, "elapsed_time": "0:45:43", "remaining_time": "1:06:19", "throughput": 1030.74, "total_tokens": 2828048} {"current_steps": 31410, "total_steps": 76960, "loss": 0.2686, "lr": 3.688130792247971e-05, "epoch": 8.162681912681913, "percentage": 40.81, "elapsed_time": "0:45:44", "remaining_time": "1:06:19", "throughput": 1030.77, "total_tokens": 2828544} {"current_steps": 31415, "total_steps": 76960, "loss": 0.299, "lr": 3.687631922314287e-05, "epoch": 8.163981288981288, "percentage": 40.82, "elapsed_time": "0:45:44", "remaining_time": "1:06:18", "throughput": 1030.77, "total_tokens": 2828976} {"current_steps": 31420, "total_steps": 76960, "loss": 0.2318, "lr": 3.687132991299554e-05, "epoch": 8.165280665280665, "percentage": 40.83, "elapsed_time": "0:45:44", "remaining_time": "1:06:18", "throughput": 1030.77, "total_tokens": 2829424} {"current_steps": 31425, "total_steps": 76960, "loss": 0.2926, "lr": 3.6866339992294344e-05, "epoch": 8.166580041580042, "percentage": 40.83, "elapsed_time": "0:45:45", "remaining_time": "1:06:18", "throughput": 1030.79, "total_tokens": 2829904} {"current_steps": 31430, "total_steps": 76960, "loss": 0.2835, "lr": 3.686134946129592e-05, "epoch": 8.167879417879417, "percentage": 40.84, "elapsed_time": "0:45:45", "remaining_time": "1:06:17", "throughput": 1030.79, "total_tokens": 2830336} {"current_steps": 31435, "total_steps": 76960, "loss": 0.2291, "lr": 3.685635832025692e-05, "epoch": 8.169178794178794, "percentage": 40.85, "elapsed_time": "0:45:46", "remaining_time": "1:06:17", "throughput": 1030.8, "total_tokens": 2830800} {"current_steps": 31440, "total_steps": 76960, "loss": 0.2417, "lr": 3.685136656943405e-05, "epoch": 8.170478170478171, "percentage": 40.85, "elapsed_time": "0:45:46", "remaining_time": "1:06:16", "throughput": 1030.82, "total_tokens": 2831264} {"current_steps": 31445, "total_steps": 76960, "loss": 0.2197, "lr": 3.684637420908405e-05, "epoch": 8.171777546777546, "percentage": 40.86, "elapsed_time": "0:45:47", "remaining_time": "1:06:16", "throughput": 1030.82, "total_tokens": 2831712} {"current_steps": 31450, "total_steps": 76960, "loss": 0.214, "lr": 3.6841381239463665e-05, "epoch": 8.173076923076923, "percentage": 40.87, "elapsed_time": "0:45:47", "remaining_time": "1:06:15", "throughput": 1030.84, "total_tokens": 2832176} {"current_steps": 31455, "total_steps": 76960, "loss": 0.4397, "lr": 3.68363876608297e-05, "epoch": 8.174376299376299, "percentage": 40.87, "elapsed_time": "0:45:47", "remaining_time": "1:06:15", "throughput": 1030.84, "total_tokens": 2832624} {"current_steps": 31460, "total_steps": 76960, "loss": 0.2206, "lr": 3.683139347343897e-05, "epoch": 8.175675675675675, "percentage": 40.88, "elapsed_time": "0:45:48", "remaining_time": "1:06:14", "throughput": 1030.84, "total_tokens": 2833040} {"current_steps": 31465, "total_steps": 76960, "loss": 0.2254, "lr": 3.682639867754834e-05, "epoch": 8.176975051975052, "percentage": 40.88, "elapsed_time": "0:45:48", "remaining_time": "1:06:14", "throughput": 1030.85, "total_tokens": 2833488} {"current_steps": 31470, "total_steps": 76960, "loss": 0.2196, "lr": 3.68214032734147e-05, "epoch": 8.178274428274428, "percentage": 40.89, "elapsed_time": "0:45:49", "remaining_time": "1:06:13", "throughput": 1030.85, "total_tokens": 2833936} {"current_steps": 31475, "total_steps": 76960, "loss": 0.1918, "lr": 3.681640726129496e-05, "epoch": 8.179573804573804, "percentage": 40.9, "elapsed_time": "0:45:49", "remaining_time": "1:06:13", "throughput": 1030.87, "total_tokens": 2834400} {"current_steps": 31480, "total_steps": 76960, "loss": 0.239, "lr": 3.681141064144607e-05, "epoch": 8.180873180873181, "percentage": 40.9, "elapsed_time": "0:45:49", "remaining_time": "1:06:12", "throughput": 1030.88, "total_tokens": 2834864} {"current_steps": 31485, "total_steps": 76960, "loss": 0.1539, "lr": 3.6806413414125016e-05, "epoch": 8.182172557172557, "percentage": 40.91, "elapsed_time": "0:45:50", "remaining_time": "1:06:12", "throughput": 1030.87, "total_tokens": 2835280} {"current_steps": 31490, "total_steps": 76960, "loss": 0.4372, "lr": 3.680141557958881e-05, "epoch": 8.183471933471933, "percentage": 40.92, "elapsed_time": "0:45:50", "remaining_time": "1:06:11", "throughput": 1030.89, "total_tokens": 2835760} {"current_steps": 31495, "total_steps": 76960, "loss": 0.2209, "lr": 3.67964171380945e-05, "epoch": 8.18477130977131, "percentage": 40.92, "elapsed_time": "0:45:51", "remaining_time": "1:06:11", "throughput": 1030.9, "total_tokens": 2836208} {"current_steps": 31500, "total_steps": 76960, "loss": 0.2741, "lr": 3.679141808989914e-05, "epoch": 8.186070686070686, "percentage": 40.93, "elapsed_time": "0:45:51", "remaining_time": "1:06:11", "throughput": 1030.91, "total_tokens": 2836672} {"current_steps": 31505, "total_steps": 76960, "loss": 0.1873, "lr": 3.6786418435259854e-05, "epoch": 8.187370062370062, "percentage": 40.94, "elapsed_time": "0:45:52", "remaining_time": "1:06:10", "throughput": 1030.92, "total_tokens": 2837136} {"current_steps": 31510, "total_steps": 76960, "loss": 0.2673, "lr": 3.678141817443377e-05, "epoch": 8.18866943866944, "percentage": 40.94, "elapsed_time": "0:45:52", "remaining_time": "1:06:10", "throughput": 1030.94, "total_tokens": 2837616} {"current_steps": 31515, "total_steps": 76960, "loss": 0.2358, "lr": 3.677641730767807e-05, "epoch": 8.189968814968815, "percentage": 40.95, "elapsed_time": "0:45:52", "remaining_time": "1:06:09", "throughput": 1030.96, "total_tokens": 2838096} {"current_steps": 31520, "total_steps": 76960, "loss": 0.2045, "lr": 3.6771415835249946e-05, "epoch": 8.191268191268192, "percentage": 40.96, "elapsed_time": "0:45:53", "remaining_time": "1:06:09", "throughput": 1030.97, "total_tokens": 2838544} {"current_steps": 31525, "total_steps": 76960, "loss": 0.2844, "lr": 3.676641375740662e-05, "epoch": 8.192567567567568, "percentage": 40.96, "elapsed_time": "0:45:53", "remaining_time": "1:06:08", "throughput": 1030.97, "total_tokens": 2838976} {"current_steps": 31530, "total_steps": 76960, "loss": 0.2399, "lr": 3.676141107440536e-05, "epoch": 8.193866943866944, "percentage": 40.97, "elapsed_time": "0:45:54", "remaining_time": "1:06:08", "throughput": 1030.98, "total_tokens": 2839424} {"current_steps": 31535, "total_steps": 76960, "loss": 0.3093, "lr": 3.675640778650346e-05, "epoch": 8.19516632016632, "percentage": 40.98, "elapsed_time": "0:45:54", "remaining_time": "1:06:07", "throughput": 1030.99, "total_tokens": 2839888} {"current_steps": 31540, "total_steps": 76960, "loss": 0.3333, "lr": 3.6751403893958244e-05, "epoch": 8.196465696465696, "percentage": 40.98, "elapsed_time": "0:45:54", "remaining_time": "1:06:07", "throughput": 1031.01, "total_tokens": 2840368} {"current_steps": 31545, "total_steps": 76960, "loss": 0.1932, "lr": 3.674639939702707e-05, "epoch": 8.197765072765073, "percentage": 40.99, "elapsed_time": "0:45:55", "remaining_time": "1:06:06", "throughput": 1031.01, "total_tokens": 2840800} {"current_steps": 31550, "total_steps": 76960, "loss": 0.3253, "lr": 3.6741394295967315e-05, "epoch": 8.19906444906445, "percentage": 41.0, "elapsed_time": "0:45:55", "remaining_time": "1:06:06", "throughput": 1031.0, "total_tokens": 2841200} {"current_steps": 31555, "total_steps": 76960, "loss": 0.2708, "lr": 3.6736388591036406e-05, "epoch": 8.200363825363825, "percentage": 41.0, "elapsed_time": "0:45:56", "remaining_time": "1:06:05", "throughput": 1031.0, "total_tokens": 2841648} {"current_steps": 31560, "total_steps": 76960, "loss": 0.2167, "lr": 3.6731382282491786e-05, "epoch": 8.201663201663202, "percentage": 41.01, "elapsed_time": "0:45:56", "remaining_time": "1:06:05", "throughput": 1031.0, "total_tokens": 2842064} {"current_steps": 31565, "total_steps": 76960, "loss": 0.3524, "lr": 3.672637537059093e-05, "epoch": 8.202962577962579, "percentage": 41.01, "elapsed_time": "0:45:57", "remaining_time": "1:06:05", "throughput": 1031.0, "total_tokens": 2842496} {"current_steps": 31570, "total_steps": 76960, "loss": 0.2168, "lr": 3.6721367855591355e-05, "epoch": 8.204261954261954, "percentage": 41.02, "elapsed_time": "0:45:57", "remaining_time": "1:06:04", "throughput": 1031.0, "total_tokens": 2842928} {"current_steps": 31575, "total_steps": 76960, "loss": 0.2771, "lr": 3.67163597377506e-05, "epoch": 8.20556133056133, "percentage": 41.03, "elapsed_time": "0:45:57", "remaining_time": "1:06:04", "throughput": 1031.01, "total_tokens": 2843392} {"current_steps": 31580, "total_steps": 76960, "loss": 0.2057, "lr": 3.671135101732624e-05, "epoch": 8.206860706860708, "percentage": 41.03, "elapsed_time": "0:45:58", "remaining_time": "1:06:03", "throughput": 1031.02, "total_tokens": 2843840} {"current_steps": 31585, "total_steps": 76960, "loss": 0.1983, "lr": 3.670634169457587e-05, "epoch": 8.208160083160083, "percentage": 41.04, "elapsed_time": "0:45:58", "remaining_time": "1:06:03", "throughput": 1031.03, "total_tokens": 2844304} {"current_steps": 31590, "total_steps": 76960, "loss": 0.0758, "lr": 3.6701331769757134e-05, "epoch": 8.20945945945946, "percentage": 41.05, "elapsed_time": "0:45:59", "remaining_time": "1:06:02", "throughput": 1031.05, "total_tokens": 2844768} {"current_steps": 31595, "total_steps": 76960, "loss": 0.272, "lr": 3.6696321243127696e-05, "epoch": 8.210758835758837, "percentage": 41.05, "elapsed_time": "0:45:59", "remaining_time": "1:06:02", "throughput": 1031.05, "total_tokens": 2845200} {"current_steps": 31600, "total_steps": 76960, "loss": 0.339, "lr": 3.6691310114945244e-05, "epoch": 8.212058212058212, "percentage": 41.06, "elapsed_time": "0:45:59", "remaining_time": "1:06:01", "throughput": 1031.05, "total_tokens": 2845632} {"current_steps": 31605, "total_steps": 76960, "loss": 0.1742, "lr": 3.668629838546751e-05, "epoch": 8.213357588357589, "percentage": 41.07, "elapsed_time": "0:46:00", "remaining_time": "1:06:01", "throughput": 1031.06, "total_tokens": 2846096} {"current_steps": 31610, "total_steps": 76960, "loss": 0.3459, "lr": 3.668128605495226e-05, "epoch": 8.214656964656964, "percentage": 41.07, "elapsed_time": "0:46:00", "remaining_time": "1:06:00", "throughput": 1031.07, "total_tokens": 2846544} {"current_steps": 31615, "total_steps": 76960, "loss": 0.378, "lr": 3.6676273123657275e-05, "epoch": 8.21595634095634, "percentage": 41.08, "elapsed_time": "0:46:01", "remaining_time": "1:06:00", "throughput": 1031.07, "total_tokens": 2846976} {"current_steps": 31620, "total_steps": 76960, "loss": 0.238, "lr": 3.667125959184037e-05, "epoch": 8.217255717255718, "percentage": 41.09, "elapsed_time": "0:46:01", "remaining_time": "1:05:59", "throughput": 1031.07, "total_tokens": 2847424} {"current_steps": 31625, "total_steps": 76960, "loss": 0.1678, "lr": 3.666624545975941e-05, "epoch": 8.218555093555093, "percentage": 41.09, "elapsed_time": "0:46:02", "remaining_time": "1:05:59", "throughput": 1031.07, "total_tokens": 2847856} {"current_steps": 31630, "total_steps": 76960, "loss": 0.4297, "lr": 3.666123072767226e-05, "epoch": 8.21985446985447, "percentage": 41.1, "elapsed_time": "0:46:02", "remaining_time": "1:05:58", "throughput": 1031.09, "total_tokens": 2848336} {"current_steps": 31635, "total_steps": 76960, "loss": 0.1623, "lr": 3.665621539583684e-05, "epoch": 8.221153846153847, "percentage": 41.11, "elapsed_time": "0:46:02", "remaining_time": "1:05:58", "throughput": 1031.1, "total_tokens": 2848784} {"current_steps": 31640, "total_steps": 76960, "loss": 0.223, "lr": 3.6651199464511096e-05, "epoch": 8.222453222453222, "percentage": 41.11, "elapsed_time": "0:46:03", "remaining_time": "1:05:58", "throughput": 1031.09, "total_tokens": 2849200} {"current_steps": 31645, "total_steps": 76960, "loss": 0.2031, "lr": 3.6646182933953e-05, "epoch": 8.223752598752599, "percentage": 41.12, "elapsed_time": "0:46:03", "remaining_time": "1:05:57", "throughput": 1031.09, "total_tokens": 2849632} {"current_steps": 31650, "total_steps": 76960, "loss": 0.1613, "lr": 3.6641165804420565e-05, "epoch": 8.225051975051976, "percentage": 41.13, "elapsed_time": "0:46:04", "remaining_time": "1:05:57", "throughput": 1031.12, "total_tokens": 2850144} {"current_steps": 31655, "total_steps": 76960, "loss": 0.1919, "lr": 3.66361480761718e-05, "epoch": 8.22635135135135, "percentage": 41.13, "elapsed_time": "0:46:04", "remaining_time": "1:05:56", "throughput": 1031.14, "total_tokens": 2850624} {"current_steps": 31660, "total_steps": 76960, "loss": 0.1984, "lr": 3.66311297494648e-05, "epoch": 8.227650727650728, "percentage": 41.14, "elapsed_time": "0:46:04", "remaining_time": "1:05:56", "throughput": 1031.16, "total_tokens": 2851104} {"current_steps": 31665, "total_steps": 76960, "loss": 0.221, "lr": 3.662611082455766e-05, "epoch": 8.228950103950105, "percentage": 41.14, "elapsed_time": "0:46:05", "remaining_time": "1:05:55", "throughput": 1031.17, "total_tokens": 2851552} {"current_steps": 31670, "total_steps": 76960, "loss": 0.23, "lr": 3.662109130170849e-05, "epoch": 8.23024948024948, "percentage": 41.15, "elapsed_time": "0:46:05", "remaining_time": "1:05:55", "throughput": 1031.17, "total_tokens": 2852000} {"current_steps": 31675, "total_steps": 76960, "loss": 0.1514, "lr": 3.6616071181175466e-05, "epoch": 8.231548856548857, "percentage": 41.16, "elapsed_time": "0:46:06", "remaining_time": "1:05:54", "throughput": 1031.17, "total_tokens": 2852432} {"current_steps": 31680, "total_steps": 76960, "loss": 0.2656, "lr": 3.661105046321677e-05, "epoch": 8.232848232848234, "percentage": 41.16, "elapsed_time": "0:46:06", "remaining_time": "1:05:54", "throughput": 1031.18, "total_tokens": 2852864} {"current_steps": 31685, "total_steps": 76960, "loss": 0.1965, "lr": 3.660602914809062e-05, "epoch": 8.234147609147609, "percentage": 41.17, "elapsed_time": "0:46:07", "remaining_time": "1:05:53", "throughput": 1031.18, "total_tokens": 2853296} {"current_steps": 31690, "total_steps": 76960, "loss": 0.125, "lr": 3.660100723605527e-05, "epoch": 8.235446985446986, "percentage": 41.18, "elapsed_time": "0:46:07", "remaining_time": "1:05:53", "throughput": 1031.18, "total_tokens": 2853744} {"current_steps": 31695, "total_steps": 76960, "loss": 0.2188, "lr": 3.659598472736901e-05, "epoch": 8.236746361746361, "percentage": 41.18, "elapsed_time": "0:46:07", "remaining_time": "1:05:52", "throughput": 1031.19, "total_tokens": 2854176} {"current_steps": 31700, "total_steps": 76960, "loss": 0.3954, "lr": 3.6590961622290145e-05, "epoch": 8.238045738045738, "percentage": 41.19, "elapsed_time": "0:46:08", "remaining_time": "1:05:52", "throughput": 1031.19, "total_tokens": 2854624} {"current_steps": 31705, "total_steps": 76960, "loss": 0.2672, "lr": 3.658593792107701e-05, "epoch": 8.239345114345115, "percentage": 41.2, "elapsed_time": "0:46:08", "remaining_time": "1:05:51", "throughput": 1031.2, "total_tokens": 2855088} {"current_steps": 31710, "total_steps": 76960, "loss": 0.1997, "lr": 3.6580913623987986e-05, "epoch": 8.24064449064449, "percentage": 41.2, "elapsed_time": "0:46:09", "remaining_time": "1:05:51", "throughput": 1031.21, "total_tokens": 2855536} {"current_steps": 31715, "total_steps": 76960, "loss": 0.3016, "lr": 3.657588873128148e-05, "epoch": 8.241943866943867, "percentage": 41.21, "elapsed_time": "0:46:09", "remaining_time": "1:05:51", "throughput": 1031.22, "total_tokens": 2856000} {"current_steps": 31720, "total_steps": 76960, "loss": 0.2415, "lr": 3.657086324321593e-05, "epoch": 8.243243243243244, "percentage": 41.22, "elapsed_time": "0:46:09", "remaining_time": "1:05:50", "throughput": 1031.23, "total_tokens": 2856448} {"current_steps": 31725, "total_steps": 76960, "loss": 0.2775, "lr": 3.65658371600498e-05, "epoch": 8.244542619542619, "percentage": 41.22, "elapsed_time": "0:46:10", "remaining_time": "1:05:50", "throughput": 1031.24, "total_tokens": 2856896} {"current_steps": 31730, "total_steps": 76960, "loss": 0.2018, "lr": 3.656081048204157e-05, "epoch": 8.245841995841996, "percentage": 41.23, "elapsed_time": "0:46:10", "remaining_time": "1:05:49", "throughput": 1031.24, "total_tokens": 2857344} {"current_steps": 31735, "total_steps": 76960, "loss": 0.2542, "lr": 3.655578320944979e-05, "epoch": 8.247141372141373, "percentage": 41.24, "elapsed_time": "0:46:11", "remaining_time": "1:05:49", "throughput": 1031.24, "total_tokens": 2857776} {"current_steps": 31740, "total_steps": 76960, "loss": 0.2062, "lr": 3.6550755342533e-05, "epoch": 8.248440748440748, "percentage": 41.24, "elapsed_time": "0:46:11", "remaining_time": "1:05:48", "throughput": 1031.25, "total_tokens": 2858208} {"current_steps": 31745, "total_steps": 76960, "loss": 0.1935, "lr": 3.654572688154979e-05, "epoch": 8.249740124740125, "percentage": 41.25, "elapsed_time": "0:46:12", "remaining_time": "1:05:48", "throughput": 1031.25, "total_tokens": 2858640} {"current_steps": 31750, "total_steps": 76960, "loss": 0.2438, "lr": 3.65406978267588e-05, "epoch": 8.2510395010395, "percentage": 41.26, "elapsed_time": "0:46:12", "remaining_time": "1:05:47", "throughput": 1031.25, "total_tokens": 2859088} {"current_steps": 31755, "total_steps": 76960, "loss": 0.2649, "lr": 3.6535668178418656e-05, "epoch": 8.252338877338877, "percentage": 41.26, "elapsed_time": "0:46:12", "remaining_time": "1:05:47", "throughput": 1031.27, "total_tokens": 2859552} {"current_steps": 31760, "total_steps": 76960, "loss": 0.2378, "lr": 3.653063793678804e-05, "epoch": 8.253638253638254, "percentage": 41.27, "elapsed_time": "0:46:13", "remaining_time": "1:05:46", "throughput": 1031.27, "total_tokens": 2859984} {"current_steps": 31765, "total_steps": 76960, "loss": 0.2228, "lr": 3.652560710212567e-05, "epoch": 8.25493762993763, "percentage": 41.27, "elapsed_time": "0:46:13", "remaining_time": "1:05:46", "throughput": 1031.27, "total_tokens": 2860416} {"current_steps": 31770, "total_steps": 76960, "loss": 0.2431, "lr": 3.652057567469029e-05, "epoch": 8.256237006237006, "percentage": 41.28, "elapsed_time": "0:46:14", "remaining_time": "1:05:45", "throughput": 1031.28, "total_tokens": 2860880} {"current_steps": 31775, "total_steps": 76960, "loss": 0.1579, "lr": 3.651554365474066e-05, "epoch": 8.257536382536383, "percentage": 41.29, "elapsed_time": "0:46:14", "remaining_time": "1:05:45", "throughput": 1031.28, "total_tokens": 2861312} {"current_steps": 31780, "total_steps": 76960, "loss": 0.1935, "lr": 3.651051104253558e-05, "epoch": 8.258835758835758, "percentage": 41.29, "elapsed_time": "0:46:14", "remaining_time": "1:05:44", "throughput": 1031.28, "total_tokens": 2861728} {"current_steps": 31785, "total_steps": 76960, "loss": 0.2496, "lr": 3.65054778383339e-05, "epoch": 8.260135135135135, "percentage": 41.3, "elapsed_time": "0:46:15", "remaining_time": "1:05:44", "throughput": 1031.28, "total_tokens": 2862176} {"current_steps": 31790, "total_steps": 76960, "loss": 0.2246, "lr": 3.650044404239447e-05, "epoch": 8.261434511434512, "percentage": 41.31, "elapsed_time": "0:46:15", "remaining_time": "1:05:44", "throughput": 1031.28, "total_tokens": 2862592} {"current_steps": 31795, "total_steps": 76960, "loss": 0.1442, "lr": 3.6495409654976176e-05, "epoch": 8.262733887733887, "percentage": 41.31, "elapsed_time": "0:46:16", "remaining_time": "1:05:43", "throughput": 1031.27, "total_tokens": 2863008} {"current_steps": 31800, "total_steps": 76960, "loss": 0.2138, "lr": 3.649037467633795e-05, "epoch": 8.264033264033264, "percentage": 41.32, "elapsed_time": "0:46:16", "remaining_time": "1:05:43", "throughput": 1031.28, "total_tokens": 2863472} {"current_steps": 31805, "total_steps": 76960, "loss": 0.4613, "lr": 3.648533910673874e-05, "epoch": 8.265332640332641, "percentage": 41.33, "elapsed_time": "0:46:17", "remaining_time": "1:05:42", "throughput": 1031.29, "total_tokens": 2863920} {"current_steps": 31810, "total_steps": 76960, "loss": 0.2662, "lr": 3.6480302946437545e-05, "epoch": 8.266632016632016, "percentage": 41.33, "elapsed_time": "0:46:17", "remaining_time": "1:05:42", "throughput": 1031.3, "total_tokens": 2864368} {"current_steps": 31815, "total_steps": 76960, "loss": 0.3665, "lr": 3.647526619569336e-05, "epoch": 8.267931392931393, "percentage": 41.34, "elapsed_time": "0:46:17", "remaining_time": "1:05:41", "throughput": 1031.31, "total_tokens": 2864848} {"current_steps": 31820, "total_steps": 76960, "loss": 0.3262, "lr": 3.6470228854765245e-05, "epoch": 8.26923076923077, "percentage": 41.35, "elapsed_time": "0:46:18", "remaining_time": "1:05:41", "throughput": 1031.33, "total_tokens": 2865312} {"current_steps": 31825, "total_steps": 76960, "loss": 0.272, "lr": 3.646519092391227e-05, "epoch": 8.270530145530145, "percentage": 41.35, "elapsed_time": "0:46:18", "remaining_time": "1:05:40", "throughput": 1031.32, "total_tokens": 2865728} {"current_steps": 31830, "total_steps": 76960, "loss": 0.2755, "lr": 3.646015240339355e-05, "epoch": 8.271829521829522, "percentage": 41.36, "elapsed_time": "0:46:19", "remaining_time": "1:05:40", "throughput": 1031.33, "total_tokens": 2866176} {"current_steps": 31835, "total_steps": 76960, "loss": 0.3076, "lr": 3.6455113293468197e-05, "epoch": 8.273128898128897, "percentage": 41.37, "elapsed_time": "0:46:19", "remaining_time": "1:05:39", "throughput": 1031.32, "total_tokens": 2866592} {"current_steps": 31840, "total_steps": 76960, "loss": 0.2815, "lr": 3.6450073594395394e-05, "epoch": 8.274428274428274, "percentage": 41.37, "elapsed_time": "0:46:19", "remaining_time": "1:05:39", "throughput": 1031.32, "total_tokens": 2867024} {"current_steps": 31845, "total_steps": 76960, "loss": 0.2479, "lr": 3.644503330643434e-05, "epoch": 8.275727650727651, "percentage": 41.38, "elapsed_time": "0:46:20", "remaining_time": "1:05:38", "throughput": 1031.34, "total_tokens": 2867488} {"current_steps": 31850, "total_steps": 76960, "loss": 0.3007, "lr": 3.643999242984426e-05, "epoch": 8.277027027027026, "percentage": 41.39, "elapsed_time": "0:46:20", "remaining_time": "1:05:38", "throughput": 1031.34, "total_tokens": 2867920} {"current_steps": 31855, "total_steps": 76960, "loss": 1.0154, "lr": 3.64349509648844e-05, "epoch": 8.278326403326403, "percentage": 41.39, "elapsed_time": "0:46:21", "remaining_time": "1:05:38", "throughput": 1031.33, "total_tokens": 2868336} {"current_steps": 31860, "total_steps": 76960, "loss": 0.2425, "lr": 3.642990891181405e-05, "epoch": 8.27962577962578, "percentage": 41.4, "elapsed_time": "0:46:21", "remaining_time": "1:05:37", "throughput": 1031.34, "total_tokens": 2868784} {"current_steps": 31865, "total_steps": 76960, "loss": 0.2744, "lr": 3.6424866270892546e-05, "epoch": 8.280925155925155, "percentage": 41.4, "elapsed_time": "0:46:22", "remaining_time": "1:05:37", "throughput": 1031.33, "total_tokens": 2869200} {"current_steps": 31870, "total_steps": 76960, "loss": 0.1977, "lr": 3.641982304237921e-05, "epoch": 8.282224532224532, "percentage": 41.41, "elapsed_time": "0:46:22", "remaining_time": "1:05:36", "throughput": 1031.34, "total_tokens": 2869648} {"current_steps": 31875, "total_steps": 76960, "loss": 0.1718, "lr": 3.6414779226533444e-05, "epoch": 8.28352390852391, "percentage": 41.42, "elapsed_time": "0:46:22", "remaining_time": "1:05:36", "throughput": 1031.34, "total_tokens": 2870080} {"current_steps": 31880, "total_steps": 76960, "loss": 0.3307, "lr": 3.640973482361464e-05, "epoch": 8.284823284823284, "percentage": 41.42, "elapsed_time": "0:46:23", "remaining_time": "1:05:35", "throughput": 1031.35, "total_tokens": 2870528} {"current_steps": 31885, "total_steps": 76960, "loss": 0.1224, "lr": 3.640468983388224e-05, "epoch": 8.286122661122661, "percentage": 41.43, "elapsed_time": "0:46:23", "remaining_time": "1:05:35", "throughput": 1031.36, "total_tokens": 2870976} {"current_steps": 31890, "total_steps": 76960, "loss": 0.1116, "lr": 3.6399644257595726e-05, "epoch": 8.287422037422038, "percentage": 41.44, "elapsed_time": "0:46:24", "remaining_time": "1:05:34", "throughput": 1031.37, "total_tokens": 2871440} {"current_steps": 31895, "total_steps": 76960, "loss": 0.2891, "lr": 3.639459809501458e-05, "epoch": 8.288721413721413, "percentage": 41.44, "elapsed_time": "0:46:24", "remaining_time": "1:05:34", "throughput": 1031.38, "total_tokens": 2871904} {"current_steps": 31900, "total_steps": 76960, "loss": 0.2081, "lr": 3.638955134639833e-05, "epoch": 8.29002079002079, "percentage": 41.45, "elapsed_time": "0:46:24", "remaining_time": "1:05:33", "throughput": 1031.39, "total_tokens": 2872368} {"current_steps": 31905, "total_steps": 76960, "loss": 0.2693, "lr": 3.6384504012006544e-05, "epoch": 8.291320166320165, "percentage": 41.46, "elapsed_time": "0:46:25", "remaining_time": "1:05:33", "throughput": 1031.4, "total_tokens": 2872816} {"current_steps": 31910, "total_steps": 76960, "loss": 0.2746, "lr": 3.6379456092098806e-05, "epoch": 8.292619542619542, "percentage": 41.46, "elapsed_time": "0:46:25", "remaining_time": "1:05:32", "throughput": 1031.4, "total_tokens": 2873248} {"current_steps": 31915, "total_steps": 76960, "loss": 0.1638, "lr": 3.6374407586934744e-05, "epoch": 8.29391891891892, "percentage": 41.47, "elapsed_time": "0:46:26", "remaining_time": "1:05:32", "throughput": 1031.42, "total_tokens": 2873744} {"current_steps": 31920, "total_steps": 76960, "loss": 0.313, "lr": 3.6369358496774e-05, "epoch": 8.295218295218294, "percentage": 41.48, "elapsed_time": "0:46:26", "remaining_time": "1:05:31", "throughput": 1031.43, "total_tokens": 2874192} {"current_steps": 31925, "total_steps": 76960, "loss": 0.1966, "lr": 3.636430882187625e-05, "epoch": 8.296517671517671, "percentage": 41.48, "elapsed_time": "0:46:27", "remaining_time": "1:05:31", "throughput": 1031.43, "total_tokens": 2874608} {"current_steps": 31930, "total_steps": 76960, "loss": 0.2669, "lr": 3.635925856250121e-05, "epoch": 8.297817047817048, "percentage": 41.49, "elapsed_time": "0:46:27", "remaining_time": "1:05:31", "throughput": 1031.42, "total_tokens": 2875024} {"current_steps": 31935, "total_steps": 76960, "loss": 0.2286, "lr": 3.635420771890862e-05, "epoch": 8.299116424116423, "percentage": 41.5, "elapsed_time": "0:46:27", "remaining_time": "1:05:30", "throughput": 1031.41, "total_tokens": 2875424} {"current_steps": 31940, "total_steps": 76960, "loss": 0.2681, "lr": 3.6349156291358253e-05, "epoch": 8.3004158004158, "percentage": 41.5, "elapsed_time": "0:46:28", "remaining_time": "1:05:30", "throughput": 1031.41, "total_tokens": 2875856} {"current_steps": 31945, "total_steps": 76960, "loss": 0.1624, "lr": 3.63441042801099e-05, "epoch": 8.301715176715177, "percentage": 41.51, "elapsed_time": "0:46:28", "remaining_time": "1:05:29", "throughput": 1031.42, "total_tokens": 2876320} {"current_steps": 31950, "total_steps": 76960, "loss": 0.2429, "lr": 3.633905168542339e-05, "epoch": 8.303014553014552, "percentage": 41.52, "elapsed_time": "0:46:29", "remaining_time": "1:05:29", "throughput": 1031.43, "total_tokens": 2876784} {"current_steps": 31955, "total_steps": 76960, "loss": 0.1463, "lr": 3.63339985075586e-05, "epoch": 8.30431392931393, "percentage": 41.52, "elapsed_time": "0:46:29", "remaining_time": "1:05:28", "throughput": 1031.44, "total_tokens": 2877216} {"current_steps": 31960, "total_steps": 76960, "loss": 0.1517, "lr": 3.632894474677539e-05, "epoch": 8.305613305613306, "percentage": 41.53, "elapsed_time": "0:46:29", "remaining_time": "1:05:28", "throughput": 1031.45, "total_tokens": 2877680} {"current_steps": 31965, "total_steps": 76960, "loss": 0.3477, "lr": 3.6323890403333704e-05, "epoch": 8.306912681912682, "percentage": 41.53, "elapsed_time": "0:46:30", "remaining_time": "1:05:27", "throughput": 1031.44, "total_tokens": 2878096} {"current_steps": 31970, "total_steps": 76960, "loss": 0.1906, "lr": 3.631883547749348e-05, "epoch": 8.308212058212058, "percentage": 41.54, "elapsed_time": "0:46:30", "remaining_time": "1:05:27", "throughput": 1031.45, "total_tokens": 2878544} {"current_steps": 31975, "total_steps": 76960, "loss": 0.3236, "lr": 3.631377996951472e-05, "epoch": 8.309511434511435, "percentage": 41.55, "elapsed_time": "0:46:31", "remaining_time": "1:05:26", "throughput": 1031.45, "total_tokens": 2878992} {"current_steps": 31980, "total_steps": 76960, "loss": 0.3782, "lr": 3.63087238796574e-05, "epoch": 8.31081081081081, "percentage": 41.55, "elapsed_time": "0:46:31", "remaining_time": "1:05:26", "throughput": 1031.45, "total_tokens": 2879424} {"current_steps": 31985, "total_steps": 76960, "loss": 0.2427, "lr": 3.6303667208181575e-05, "epoch": 8.312110187110187, "percentage": 41.56, "elapsed_time": "0:46:32", "remaining_time": "1:05:25", "throughput": 1031.47, "total_tokens": 2879904} {"current_steps": 31990, "total_steps": 76960, "loss": 0.2405, "lr": 3.6298609955347316e-05, "epoch": 8.313409563409563, "percentage": 41.57, "elapsed_time": "0:46:32", "remaining_time": "1:05:25", "throughput": 1031.47, "total_tokens": 2880336} {"current_steps": 31995, "total_steps": 76960, "loss": 0.2892, "lr": 3.629355212141472e-05, "epoch": 8.31470893970894, "percentage": 41.57, "elapsed_time": "0:46:32", "remaining_time": "1:05:25", "throughput": 1031.49, "total_tokens": 2880816} {"current_steps": 32000, "total_steps": 76960, "loss": 0.216, "lr": 3.628849370664392e-05, "epoch": 8.316008316008316, "percentage": 41.58, "elapsed_time": "0:46:33", "remaining_time": "1:05:24", "throughput": 1031.53, "total_tokens": 2881344} {"current_steps": 32005, "total_steps": 76960, "loss": 0.2652, "lr": 3.6283434711295076e-05, "epoch": 8.317307692307692, "percentage": 41.59, "elapsed_time": "0:46:33", "remaining_time": "1:05:24", "throughput": 1031.54, "total_tokens": 2881824} {"current_steps": 32010, "total_steps": 76960, "loss": 0.1481, "lr": 3.627837513562837e-05, "epoch": 8.318607068607069, "percentage": 41.59, "elapsed_time": "0:46:34", "remaining_time": "1:05:23", "throughput": 1031.55, "total_tokens": 2882256} {"current_steps": 32015, "total_steps": 76960, "loss": 0.1888, "lr": 3.6273314979904026e-05, "epoch": 8.319906444906445, "percentage": 41.6, "elapsed_time": "0:46:34", "remaining_time": "1:05:23", "throughput": 1031.56, "total_tokens": 2882736} {"current_steps": 32020, "total_steps": 76960, "loss": 0.4016, "lr": 3.6268254244382294e-05, "epoch": 8.32120582120582, "percentage": 41.61, "elapsed_time": "0:46:34", "remaining_time": "1:05:22", "throughput": 1031.56, "total_tokens": 2883168} {"current_steps": 32025, "total_steps": 76960, "loss": 0.1287, "lr": 3.6263192929323445e-05, "epoch": 8.322505197505198, "percentage": 41.61, "elapsed_time": "0:46:35", "remaining_time": "1:05:22", "throughput": 1031.58, "total_tokens": 2883632} {"current_steps": 32030, "total_steps": 76960, "loss": 0.491, "lr": 3.625813103498779e-05, "epoch": 8.323804573804575, "percentage": 41.62, "elapsed_time": "0:46:35", "remaining_time": "1:05:21", "throughput": 1031.58, "total_tokens": 2884080} {"current_steps": 32035, "total_steps": 76960, "loss": 0.2089, "lr": 3.625306856163567e-05, "epoch": 8.32510395010395, "percentage": 41.63, "elapsed_time": "0:46:36", "remaining_time": "1:05:21", "throughput": 1031.59, "total_tokens": 2884528} {"current_steps": 32040, "total_steps": 76960, "loss": 0.2596, "lr": 3.624800550952746e-05, "epoch": 8.326403326403327, "percentage": 41.63, "elapsed_time": "0:46:36", "remaining_time": "1:05:20", "throughput": 1031.6, "total_tokens": 2884976} {"current_steps": 32045, "total_steps": 76960, "loss": 0.2757, "lr": 3.6242941878923545e-05, "epoch": 8.327702702702704, "percentage": 41.64, "elapsed_time": "0:46:37", "remaining_time": "1:05:20", "throughput": 1031.61, "total_tokens": 2885440} {"current_steps": 32050, "total_steps": 76960, "loss": 0.3415, "lr": 3.623787767008435e-05, "epoch": 8.329002079002079, "percentage": 41.65, "elapsed_time": "0:46:37", "remaining_time": "1:05:19", "throughput": 1031.6, "total_tokens": 2885840} {"current_steps": 32055, "total_steps": 76960, "loss": 0.2825, "lr": 3.623281288327034e-05, "epoch": 8.330301455301456, "percentage": 41.65, "elapsed_time": "0:46:37", "remaining_time": "1:05:19", "throughput": 1031.6, "total_tokens": 2886272} {"current_steps": 32060, "total_steps": 76960, "loss": 0.2237, "lr": 3.6227747518742005e-05, "epoch": 8.33160083160083, "percentage": 41.66, "elapsed_time": "0:46:38", "remaining_time": "1:05:18", "throughput": 1031.59, "total_tokens": 2886688} {"current_steps": 32065, "total_steps": 76960, "loss": 0.1244, "lr": 3.622268157675986e-05, "epoch": 8.332900207900208, "percentage": 41.66, "elapsed_time": "0:46:38", "remaining_time": "1:05:18", "throughput": 1031.6, "total_tokens": 2887136} {"current_steps": 32070, "total_steps": 76960, "loss": 0.4242, "lr": 3.6217615057584435e-05, "epoch": 8.334199584199585, "percentage": 41.67, "elapsed_time": "0:46:39", "remaining_time": "1:05:18", "throughput": 1031.61, "total_tokens": 2887584} {"current_steps": 32075, "total_steps": 76960, "loss": 0.3004, "lr": 3.6212547961476336e-05, "epoch": 8.33549896049896, "percentage": 41.68, "elapsed_time": "0:46:39", "remaining_time": "1:05:17", "throughput": 1031.62, "total_tokens": 2888048} {"current_steps": 32080, "total_steps": 76960, "loss": 0.208, "lr": 3.6207480288696144e-05, "epoch": 8.336798336798337, "percentage": 41.68, "elapsed_time": "0:46:39", "remaining_time": "1:05:17", "throughput": 1031.63, "total_tokens": 2888512} {"current_steps": 32085, "total_steps": 76960, "loss": 0.2, "lr": 3.62024120395045e-05, "epoch": 8.338097713097714, "percentage": 41.69, "elapsed_time": "0:46:40", "remaining_time": "1:05:16", "throughput": 1031.64, "total_tokens": 2888976} {"current_steps": 32090, "total_steps": 76960, "loss": 0.219, "lr": 3.619734321416208e-05, "epoch": 8.339397089397089, "percentage": 41.7, "elapsed_time": "0:46:40", "remaining_time": "1:05:16", "throughput": 1031.64, "total_tokens": 2889392} {"current_steps": 32095, "total_steps": 76960, "loss": 0.2007, "lr": 3.619227381292956e-05, "epoch": 8.340696465696466, "percentage": 41.7, "elapsed_time": "0:46:41", "remaining_time": "1:05:15", "throughput": 1031.63, "total_tokens": 2889808} {"current_steps": 32100, "total_steps": 76960, "loss": 0.1694, "lr": 3.618720383606768e-05, "epoch": 8.341995841995843, "percentage": 41.71, "elapsed_time": "0:46:41", "remaining_time": "1:05:15", "throughput": 1031.65, "total_tokens": 2890272} {"current_steps": 32105, "total_steps": 76960, "loss": 0.4272, "lr": 3.618213328383718e-05, "epoch": 8.343295218295218, "percentage": 41.72, "elapsed_time": "0:46:42", "remaining_time": "1:05:14", "throughput": 1031.65, "total_tokens": 2890720} {"current_steps": 32110, "total_steps": 76960, "loss": 0.1941, "lr": 3.617706215649886e-05, "epoch": 8.344594594594595, "percentage": 41.72, "elapsed_time": "0:46:42", "remaining_time": "1:05:14", "throughput": 1031.64, "total_tokens": 2891120} {"current_steps": 32115, "total_steps": 76960, "loss": 0.2607, "lr": 3.617199045431352e-05, "epoch": 8.345893970893972, "percentage": 41.73, "elapsed_time": "0:46:42", "remaining_time": "1:05:13", "throughput": 1031.65, "total_tokens": 2891584} {"current_steps": 32120, "total_steps": 76960, "loss": 0.4167, "lr": 3.6166918177542006e-05, "epoch": 8.347193347193347, "percentage": 41.74, "elapsed_time": "0:46:43", "remaining_time": "1:05:13", "throughput": 1031.66, "total_tokens": 2892016} {"current_steps": 32125, "total_steps": 76960, "loss": 0.3372, "lr": 3.616184532644519e-05, "epoch": 8.348492723492724, "percentage": 41.74, "elapsed_time": "0:46:43", "remaining_time": "1:05:12", "throughput": 1031.66, "total_tokens": 2892448} {"current_steps": 32130, "total_steps": 76960, "loss": 0.2393, "lr": 3.615677190128398e-05, "epoch": 8.3497920997921, "percentage": 41.75, "elapsed_time": "0:46:44", "remaining_time": "1:05:12", "throughput": 1031.67, "total_tokens": 2892912} {"current_steps": 32135, "total_steps": 76960, "loss": 0.3679, "lr": 3.6151697902319296e-05, "epoch": 8.351091476091476, "percentage": 41.76, "elapsed_time": "0:46:44", "remaining_time": "1:05:12", "throughput": 1031.67, "total_tokens": 2893360} {"current_steps": 32140, "total_steps": 76960, "loss": 0.1925, "lr": 3.61466233298121e-05, "epoch": 8.352390852390853, "percentage": 41.76, "elapsed_time": "0:46:44", "remaining_time": "1:05:11", "throughput": 1031.69, "total_tokens": 2893824} {"current_steps": 32145, "total_steps": 76960, "loss": 0.2963, "lr": 3.614154818402339e-05, "epoch": 8.353690228690228, "percentage": 41.77, "elapsed_time": "0:46:45", "remaining_time": "1:05:11", "throughput": 1031.68, "total_tokens": 2894256} {"current_steps": 32150, "total_steps": 76960, "loss": 0.2443, "lr": 3.613647246521419e-05, "epoch": 8.354989604989605, "percentage": 41.77, "elapsed_time": "0:46:45", "remaining_time": "1:05:10", "throughput": 1031.69, "total_tokens": 2894704} {"current_steps": 32155, "total_steps": 76960, "loss": 0.263, "lr": 3.613139617364553e-05, "epoch": 8.356288981288982, "percentage": 41.78, "elapsed_time": "0:46:46", "remaining_time": "1:05:10", "throughput": 1031.7, "total_tokens": 2895152} {"current_steps": 32160, "total_steps": 76960, "loss": 0.261, "lr": 3.61263193095785e-05, "epoch": 8.357588357588357, "percentage": 41.79, "elapsed_time": "0:46:46", "remaining_time": "1:05:09", "throughput": 1031.7, "total_tokens": 2895600} {"current_steps": 32165, "total_steps": 76960, "loss": 0.2956, "lr": 3.6121241873274205e-05, "epoch": 8.358887733887734, "percentage": 41.79, "elapsed_time": "0:46:47", "remaining_time": "1:05:09", "throughput": 1031.7, "total_tokens": 2896016} {"current_steps": 32170, "total_steps": 76960, "loss": 0.2454, "lr": 3.611616386499379e-05, "epoch": 8.36018711018711, "percentage": 41.8, "elapsed_time": "0:46:47", "remaining_time": "1:05:08", "throughput": 1031.71, "total_tokens": 2896480} {"current_steps": 32175, "total_steps": 76960, "loss": 0.2239, "lr": 3.611108528499841e-05, "epoch": 8.361486486486486, "percentage": 41.81, "elapsed_time": "0:46:47", "remaining_time": "1:05:08", "throughput": 1031.71, "total_tokens": 2896912} {"current_steps": 32180, "total_steps": 76960, "loss": 0.2882, "lr": 3.610600613354927e-05, "epoch": 8.362785862785863, "percentage": 41.81, "elapsed_time": "0:46:48", "remaining_time": "1:05:07", "throughput": 1031.71, "total_tokens": 2897344} {"current_steps": 32185, "total_steps": 76960, "loss": 0.2493, "lr": 3.6100926410907605e-05, "epoch": 8.36408523908524, "percentage": 41.82, "elapsed_time": "0:46:48", "remaining_time": "1:05:07", "throughput": 1031.72, "total_tokens": 2897792} {"current_steps": 32190, "total_steps": 76960, "loss": 0.2733, "lr": 3.6095846117334656e-05, "epoch": 8.365384615384615, "percentage": 41.83, "elapsed_time": "0:46:49", "remaining_time": "1:05:06", "throughput": 1031.72, "total_tokens": 2898224} {"current_steps": 32195, "total_steps": 76960, "loss": 0.1856, "lr": 3.60907652530917e-05, "epoch": 8.366683991683992, "percentage": 41.83, "elapsed_time": "0:46:49", "remaining_time": "1:05:06", "throughput": 1031.74, "total_tokens": 2898704} {"current_steps": 32200, "total_steps": 76960, "loss": 0.2137, "lr": 3.6085683818440055e-05, "epoch": 8.367983367983369, "percentage": 41.84, "elapsed_time": "0:46:49", "remaining_time": "1:05:06", "throughput": 1031.74, "total_tokens": 2899136} {"current_steps": 32205, "total_steps": 76960, "loss": 0.3366, "lr": 3.6080601813641076e-05, "epoch": 8.369282744282744, "percentage": 41.85, "elapsed_time": "0:46:50", "remaining_time": "1:05:05", "throughput": 1031.74, "total_tokens": 2899568} {"current_steps": 32210, "total_steps": 76960, "loss": 0.2295, "lr": 3.6075519238956135e-05, "epoch": 8.370582120582121, "percentage": 41.85, "elapsed_time": "0:46:50", "remaining_time": "1:05:05", "throughput": 1031.74, "total_tokens": 2900000} {"current_steps": 32215, "total_steps": 76960, "loss": 0.3033, "lr": 3.6070436094646626e-05, "epoch": 8.371881496881496, "percentage": 41.86, "elapsed_time": "0:46:51", "remaining_time": "1:05:04", "throughput": 1031.74, "total_tokens": 2900432} {"current_steps": 32220, "total_steps": 76960, "loss": 0.0683, "lr": 3.6065352380973984e-05, "epoch": 8.373180873180873, "percentage": 41.87, "elapsed_time": "0:46:51", "remaining_time": "1:05:04", "throughput": 1031.76, "total_tokens": 2900912} {"current_steps": 32225, "total_steps": 76960, "loss": 0.4462, "lr": 3.606026809819966e-05, "epoch": 8.37448024948025, "percentage": 41.87, "elapsed_time": "0:46:52", "remaining_time": "1:05:03", "throughput": 1031.77, "total_tokens": 2901376} {"current_steps": 32230, "total_steps": 76960, "loss": 0.3098, "lr": 3.605518324658514e-05, "epoch": 8.375779625779625, "percentage": 41.88, "elapsed_time": "0:46:52", "remaining_time": "1:05:03", "throughput": 1031.77, "total_tokens": 2901808} {"current_steps": 32235, "total_steps": 76960, "loss": 0.1601, "lr": 3.605009782639197e-05, "epoch": 8.377079002079002, "percentage": 41.89, "elapsed_time": "0:46:52", "remaining_time": "1:05:02", "throughput": 1031.78, "total_tokens": 2902272} {"current_steps": 32240, "total_steps": 76960, "loss": 0.2732, "lr": 3.604501183788168e-05, "epoch": 8.378378378378379, "percentage": 41.89, "elapsed_time": "0:46:53", "remaining_time": "1:05:02", "throughput": 1031.79, "total_tokens": 2902720} {"current_steps": 32245, "total_steps": 76960, "loss": 0.3126, "lr": 3.603992528131584e-05, "epoch": 8.379677754677754, "percentage": 41.9, "elapsed_time": "0:46:53", "remaining_time": "1:05:01", "throughput": 1031.8, "total_tokens": 2903184} {"current_steps": 32250, "total_steps": 76960, "loss": 0.3305, "lr": 3.6034838156956066e-05, "epoch": 8.380977130977131, "percentage": 41.9, "elapsed_time": "0:46:54", "remaining_time": "1:05:01", "throughput": 1031.82, "total_tokens": 2903664} {"current_steps": 32255, "total_steps": 76960, "loss": 0.2514, "lr": 3.6029750465064e-05, "epoch": 8.382276507276508, "percentage": 41.91, "elapsed_time": "0:46:54", "remaining_time": "1:05:00", "throughput": 1031.82, "total_tokens": 2904096} {"current_steps": 32260, "total_steps": 76960, "loss": 0.2067, "lr": 3.602466220590129e-05, "epoch": 8.383575883575883, "percentage": 41.92, "elapsed_time": "0:46:54", "remaining_time": "1:05:00", "throughput": 1031.83, "total_tokens": 2904544} {"current_steps": 32265, "total_steps": 76960, "loss": 0.1976, "lr": 3.6019573379729643e-05, "epoch": 8.38487525987526, "percentage": 41.92, "elapsed_time": "0:46:55", "remaining_time": "1:04:59", "throughput": 1031.82, "total_tokens": 2904960} {"current_steps": 32270, "total_steps": 76960, "loss": 0.247, "lr": 3.6014483986810784e-05, "epoch": 8.386174636174637, "percentage": 41.93, "elapsed_time": "0:46:55", "remaining_time": "1:04:59", "throughput": 1031.85, "total_tokens": 2905456} {"current_steps": 32275, "total_steps": 76960, "loss": 0.3075, "lr": 3.6009394027406454e-05, "epoch": 8.387474012474012, "percentage": 41.94, "elapsed_time": "0:46:56", "remaining_time": "1:04:59", "throughput": 1031.84, "total_tokens": 2905872} {"current_steps": 32280, "total_steps": 76960, "loss": 0.2124, "lr": 3.600430350177845e-05, "epoch": 8.388773388773389, "percentage": 41.94, "elapsed_time": "0:46:56", "remaining_time": "1:04:58", "throughput": 1031.85, "total_tokens": 2906320} {"current_steps": 32285, "total_steps": 76960, "loss": 0.2933, "lr": 3.599921241018856e-05, "epoch": 8.390072765072764, "percentage": 41.95, "elapsed_time": "0:46:57", "remaining_time": "1:04:58", "throughput": 1031.86, "total_tokens": 2906784} {"current_steps": 32290, "total_steps": 76960, "loss": 0.3141, "lr": 3.599412075289864e-05, "epoch": 8.391372141372141, "percentage": 41.96, "elapsed_time": "0:46:57", "remaining_time": "1:04:57", "throughput": 1031.87, "total_tokens": 2907248} {"current_steps": 32295, "total_steps": 76960, "loss": 0.2955, "lr": 3.598902853017057e-05, "epoch": 8.392671517671518, "percentage": 41.96, "elapsed_time": "0:46:57", "remaining_time": "1:04:57", "throughput": 1031.89, "total_tokens": 2907712} {"current_steps": 32300, "total_steps": 76960, "loss": 0.1886, "lr": 3.598393574226621e-05, "epoch": 8.393970893970893, "percentage": 41.97, "elapsed_time": "0:46:58", "remaining_time": "1:04:56", "throughput": 1031.89, "total_tokens": 2908160} {"current_steps": 32305, "total_steps": 76960, "loss": 0.3305, "lr": 3.597884238944752e-05, "epoch": 8.39527027027027, "percentage": 41.98, "elapsed_time": "0:46:58", "remaining_time": "1:04:56", "throughput": 1031.89, "total_tokens": 2908576} {"current_steps": 32310, "total_steps": 76960, "loss": 0.189, "lr": 3.597374847197646e-05, "epoch": 8.396569646569647, "percentage": 41.98, "elapsed_time": "0:46:59", "remaining_time": "1:04:55", "throughput": 1031.89, "total_tokens": 2909008} {"current_steps": 32315, "total_steps": 76960, "loss": 0.2898, "lr": 3.5968653990114984e-05, "epoch": 8.397869022869022, "percentage": 41.99, "elapsed_time": "0:46:59", "remaining_time": "1:04:55", "throughput": 1031.89, "total_tokens": 2909440} {"current_steps": 32320, "total_steps": 76960, "loss": 0.1832, "lr": 3.596355894412512e-05, "epoch": 8.3991683991684, "percentage": 42.0, "elapsed_time": "0:46:59", "remaining_time": "1:04:54", "throughput": 1031.89, "total_tokens": 2909888} {"current_steps": 32325, "total_steps": 76960, "loss": 0.1977, "lr": 3.5958463334268925e-05, "epoch": 8.400467775467776, "percentage": 42.0, "elapsed_time": "0:47:00", "remaining_time": "1:04:54", "throughput": 1031.9, "total_tokens": 2910336} {"current_steps": 32330, "total_steps": 76960, "loss": 0.3642, "lr": 3.595336716080846e-05, "epoch": 8.401767151767151, "percentage": 42.01, "elapsed_time": "0:47:00", "remaining_time": "1:04:53", "throughput": 1031.9, "total_tokens": 2910752} {"current_steps": 32335, "total_steps": 76960, "loss": 0.2849, "lr": 3.594827042400583e-05, "epoch": 8.403066528066528, "percentage": 42.02, "elapsed_time": "0:47:01", "remaining_time": "1:04:53", "throughput": 1031.9, "total_tokens": 2911184} {"current_steps": 32340, "total_steps": 76960, "loss": 0.2681, "lr": 3.5943173124123156e-05, "epoch": 8.404365904365905, "percentage": 42.02, "elapsed_time": "0:47:01", "remaining_time": "1:04:53", "throughput": 1031.9, "total_tokens": 2911616} {"current_steps": 32345, "total_steps": 76960, "loss": 0.2443, "lr": 3.593807526142261e-05, "epoch": 8.40566528066528, "percentage": 42.03, "elapsed_time": "0:47:02", "remaining_time": "1:04:52", "throughput": 1031.89, "total_tokens": 2912032} {"current_steps": 32350, "total_steps": 76960, "loss": 0.2774, "lr": 3.5932976836166366e-05, "epoch": 8.406964656964657, "percentage": 42.03, "elapsed_time": "0:47:02", "remaining_time": "1:04:52", "throughput": 1031.9, "total_tokens": 2912480} {"current_steps": 32355, "total_steps": 76960, "loss": 0.307, "lr": 3.592787784861665e-05, "epoch": 8.408264033264032, "percentage": 42.04, "elapsed_time": "0:47:02", "remaining_time": "1:04:51", "throughput": 1031.9, "total_tokens": 2912912} {"current_steps": 32360, "total_steps": 76960, "loss": 0.2043, "lr": 3.5922778299035706e-05, "epoch": 8.40956340956341, "percentage": 42.05, "elapsed_time": "0:47:03", "remaining_time": "1:04:51", "throughput": 1031.91, "total_tokens": 2913360} {"current_steps": 32365, "total_steps": 76960, "loss": 0.2183, "lr": 3.5917678187685814e-05, "epoch": 8.410862785862786, "percentage": 42.05, "elapsed_time": "0:47:03", "remaining_time": "1:04:50", "throughput": 1031.92, "total_tokens": 2913824} {"current_steps": 32370, "total_steps": 76960, "loss": 0.2207, "lr": 3.5912577514829264e-05, "epoch": 8.412162162162161, "percentage": 42.06, "elapsed_time": "0:47:04", "remaining_time": "1:04:50", "throughput": 1031.92, "total_tokens": 2914272} {"current_steps": 32375, "total_steps": 76960, "loss": 0.1971, "lr": 3.5907476280728405e-05, "epoch": 8.413461538461538, "percentage": 42.07, "elapsed_time": "0:47:04", "remaining_time": "1:04:49", "throughput": 1031.94, "total_tokens": 2914736} {"current_steps": 32380, "total_steps": 76960, "loss": 0.225, "lr": 3.590237448564558e-05, "epoch": 8.414760914760915, "percentage": 42.07, "elapsed_time": "0:47:04", "remaining_time": "1:04:49", "throughput": 1031.95, "total_tokens": 2915200} {"current_steps": 32385, "total_steps": 76960, "loss": 0.1667, "lr": 3.5897272129843194e-05, "epoch": 8.41606029106029, "percentage": 42.08, "elapsed_time": "0:47:05", "remaining_time": "1:04:48", "throughput": 1031.96, "total_tokens": 2915664} {"current_steps": 32390, "total_steps": 76960, "loss": 0.2851, "lr": 3.589216921358366e-05, "epoch": 8.417359667359667, "percentage": 42.09, "elapsed_time": "0:47:05", "remaining_time": "1:04:48", "throughput": 1031.97, "total_tokens": 2916128} {"current_steps": 32395, "total_steps": 76960, "loss": 0.3149, "lr": 3.588706573712942e-05, "epoch": 8.418659043659044, "percentage": 42.09, "elapsed_time": "0:47:06", "remaining_time": "1:04:47", "throughput": 1031.97, "total_tokens": 2916560} {"current_steps": 32400, "total_steps": 76960, "loss": 0.195, "lr": 3.588196170074297e-05, "epoch": 8.41995841995842, "percentage": 42.1, "elapsed_time": "0:47:06", "remaining_time": "1:04:47", "throughput": 1031.99, "total_tokens": 2917024} {"current_steps": 32405, "total_steps": 76960, "loss": 0.3219, "lr": 3.58768571046868e-05, "epoch": 8.421257796257796, "percentage": 42.11, "elapsed_time": "0:47:07", "remaining_time": "1:04:47", "throughput": 1032.0, "total_tokens": 2917488} {"current_steps": 32410, "total_steps": 76960, "loss": 0.2439, "lr": 3.5871751949223444e-05, "epoch": 8.422557172557173, "percentage": 42.11, "elapsed_time": "0:47:07", "remaining_time": "1:04:46", "throughput": 1032.01, "total_tokens": 2917968} {"current_steps": 32415, "total_steps": 76960, "loss": 0.2796, "lr": 3.5866646234615474e-05, "epoch": 8.423856548856548, "percentage": 42.12, "elapsed_time": "0:47:07", "remaining_time": "1:04:46", "throughput": 1032.02, "total_tokens": 2918416} {"current_steps": 32420, "total_steps": 76960, "loss": 0.1685, "lr": 3.5861539961125475e-05, "epoch": 8.425155925155925, "percentage": 42.13, "elapsed_time": "0:47:08", "remaining_time": "1:04:45", "throughput": 1032.04, "total_tokens": 2918896} {"current_steps": 32425, "total_steps": 76960, "loss": 0.263, "lr": 3.585643312901606e-05, "epoch": 8.426455301455302, "percentage": 42.13, "elapsed_time": "0:47:08", "remaining_time": "1:04:45", "throughput": 1032.06, "total_tokens": 2919376} {"current_steps": 32430, "total_steps": 76960, "loss": 0.208, "lr": 3.585132573854989e-05, "epoch": 8.427754677754677, "percentage": 42.14, "elapsed_time": "0:47:09", "remaining_time": "1:04:44", "throughput": 1032.08, "total_tokens": 2919872} {"current_steps": 32435, "total_steps": 76960, "loss": 0.3197, "lr": 3.5846217789989644e-05, "epoch": 8.429054054054054, "percentage": 42.15, "elapsed_time": "0:47:09", "remaining_time": "1:04:44", "throughput": 1032.09, "total_tokens": 2920336} {"current_steps": 32440, "total_steps": 76960, "loss": 0.0991, "lr": 3.584110928359803e-05, "epoch": 8.43035343035343, "percentage": 42.15, "elapsed_time": "0:47:09", "remaining_time": "1:04:43", "throughput": 1032.09, "total_tokens": 2920768} {"current_steps": 32445, "total_steps": 76960, "loss": 0.1445, "lr": 3.5836000219637765e-05, "epoch": 8.431652806652806, "percentage": 42.16, "elapsed_time": "0:47:10", "remaining_time": "1:04:43", "throughput": 1032.11, "total_tokens": 2921248} {"current_steps": 32450, "total_steps": 76960, "loss": 0.3298, "lr": 3.5830890598371635e-05, "epoch": 8.432952182952183, "percentage": 42.16, "elapsed_time": "0:47:10", "remaining_time": "1:04:42", "throughput": 1032.12, "total_tokens": 2921712} {"current_steps": 32455, "total_steps": 76960, "loss": 0.3311, "lr": 3.582578042006242e-05, "epoch": 8.434251559251559, "percentage": 42.17, "elapsed_time": "0:47:11", "remaining_time": "1:04:42", "throughput": 1032.13, "total_tokens": 2922160} {"current_steps": 32460, "total_steps": 76960, "loss": 0.2522, "lr": 3.5820669684972955e-05, "epoch": 8.435550935550935, "percentage": 42.18, "elapsed_time": "0:47:11", "remaining_time": "1:04:41", "throughput": 1032.13, "total_tokens": 2922592} {"current_steps": 32465, "total_steps": 76960, "loss": 0.1873, "lr": 3.581555839336606e-05, "epoch": 8.436850311850312, "percentage": 42.18, "elapsed_time": "0:47:12", "remaining_time": "1:04:41", "throughput": 1032.13, "total_tokens": 2923024} {"current_steps": 32470, "total_steps": 76960, "loss": 0.2537, "lr": 3.581044654550465e-05, "epoch": 8.438149688149688, "percentage": 42.19, "elapsed_time": "0:47:12", "remaining_time": "1:04:40", "throughput": 1032.15, "total_tokens": 2923504} {"current_steps": 32475, "total_steps": 76960, "loss": 0.1746, "lr": 3.580533414165162e-05, "epoch": 8.439449064449065, "percentage": 42.2, "elapsed_time": "0:47:12", "remaining_time": "1:04:40", "throughput": 1032.17, "total_tokens": 2924000} {"current_steps": 32480, "total_steps": 76960, "loss": 0.2246, "lr": 3.580022118206989e-05, "epoch": 8.440748440748441, "percentage": 42.2, "elapsed_time": "0:47:13", "remaining_time": "1:04:40", "throughput": 1032.18, "total_tokens": 2924448} {"current_steps": 32485, "total_steps": 76960, "loss": 0.3321, "lr": 3.579510766702244e-05, "epoch": 8.442047817047817, "percentage": 42.21, "elapsed_time": "0:47:13", "remaining_time": "1:04:39", "throughput": 1032.17, "total_tokens": 2924864} {"current_steps": 32490, "total_steps": 76960, "loss": 0.281, "lr": 3.578999359677226e-05, "epoch": 8.443347193347194, "percentage": 42.22, "elapsed_time": "0:47:14", "remaining_time": "1:04:39", "throughput": 1032.19, "total_tokens": 2925344} {"current_steps": 32495, "total_steps": 76960, "loss": 0.2212, "lr": 3.578487897158236e-05, "epoch": 8.44464656964657, "percentage": 42.22, "elapsed_time": "0:47:14", "remaining_time": "1:04:38", "throughput": 1032.2, "total_tokens": 2925808} {"current_steps": 32500, "total_steps": 76960, "loss": 0.2228, "lr": 3.577976379171581e-05, "epoch": 8.445945945945946, "percentage": 42.23, "elapsed_time": "0:47:14", "remaining_time": "1:04:38", "throughput": 1032.2, "total_tokens": 2926240} {"current_steps": 32505, "total_steps": 76960, "loss": 0.1674, "lr": 3.577464805743569e-05, "epoch": 8.447245322245323, "percentage": 42.24, "elapsed_time": "0:47:15", "remaining_time": "1:04:37", "throughput": 1032.21, "total_tokens": 2926704} {"current_steps": 32510, "total_steps": 76960, "loss": 0.1445, "lr": 3.576953176900509e-05, "epoch": 8.448544698544698, "percentage": 42.24, "elapsed_time": "0:47:15", "remaining_time": "1:04:37", "throughput": 1032.22, "total_tokens": 2927152} {"current_steps": 32515, "total_steps": 76960, "loss": 0.2095, "lr": 3.5764414926687144e-05, "epoch": 8.449844074844075, "percentage": 42.25, "elapsed_time": "0:47:16", "remaining_time": "1:04:36", "throughput": 1032.22, "total_tokens": 2927584} {"current_steps": 32520, "total_steps": 76960, "loss": 0.2283, "lr": 3.575929753074503e-05, "epoch": 8.451143451143452, "percentage": 42.26, "elapsed_time": "0:47:16", "remaining_time": "1:04:36", "throughput": 1032.23, "total_tokens": 2928048} {"current_steps": 32525, "total_steps": 76960, "loss": 0.1309, "lr": 3.575417958144194e-05, "epoch": 8.452442827442827, "percentage": 42.26, "elapsed_time": "0:47:17", "remaining_time": "1:04:35", "throughput": 1032.23, "total_tokens": 2928480} {"current_steps": 32530, "total_steps": 76960, "loss": 0.2603, "lr": 3.574906107904108e-05, "epoch": 8.453742203742204, "percentage": 42.27, "elapsed_time": "0:47:17", "remaining_time": "1:04:35", "throughput": 1032.25, "total_tokens": 2928944} {"current_steps": 32535, "total_steps": 76960, "loss": 0.3835, "lr": 3.5743942023805715e-05, "epoch": 8.45504158004158, "percentage": 42.28, "elapsed_time": "0:47:17", "remaining_time": "1:04:34", "throughput": 1032.26, "total_tokens": 2929408} {"current_steps": 32540, "total_steps": 76960, "loss": 0.3444, "lr": 3.573882241599912e-05, "epoch": 8.456340956340956, "percentage": 42.28, "elapsed_time": "0:47:18", "remaining_time": "1:04:34", "throughput": 1032.26, "total_tokens": 2929840} {"current_steps": 32545, "total_steps": 76960, "loss": 0.2371, "lr": 3.57337022558846e-05, "epoch": 8.457640332640333, "percentage": 42.29, "elapsed_time": "0:47:18", "remaining_time": "1:04:34", "throughput": 1032.28, "total_tokens": 2930320} {"current_steps": 32550, "total_steps": 76960, "loss": 0.1964, "lr": 3.572858154372548e-05, "epoch": 8.45893970893971, "percentage": 42.29, "elapsed_time": "0:47:19", "remaining_time": "1:04:33", "throughput": 1032.27, "total_tokens": 2930736} {"current_steps": 32555, "total_steps": 76960, "loss": 0.2842, "lr": 3.5723460279785135e-05, "epoch": 8.460239085239085, "percentage": 42.3, "elapsed_time": "0:47:19", "remaining_time": "1:04:33", "throughput": 1032.27, "total_tokens": 2931152} {"current_steps": 32560, "total_steps": 76960, "loss": 0.2431, "lr": 3.571833846432696e-05, "epoch": 8.461538461538462, "percentage": 42.31, "elapsed_time": "0:47:19", "remaining_time": "1:04:32", "throughput": 1032.26, "total_tokens": 2931568} {"current_steps": 32565, "total_steps": 76960, "loss": 0.2107, "lr": 3.571321609761435e-05, "epoch": 8.462837837837839, "percentage": 42.31, "elapsed_time": "0:47:20", "remaining_time": "1:04:32", "throughput": 1032.27, "total_tokens": 2932032} {"current_steps": 32570, "total_steps": 76960, "loss": 0.3211, "lr": 3.5708093179910786e-05, "epoch": 8.464137214137214, "percentage": 42.32, "elapsed_time": "0:47:20", "remaining_time": "1:04:31", "throughput": 1032.28, "total_tokens": 2932480} {"current_steps": 32575, "total_steps": 76960, "loss": 0.1944, "lr": 3.5702969711479726e-05, "epoch": 8.46543659043659, "percentage": 42.33, "elapsed_time": "0:47:21", "remaining_time": "1:04:31", "throughput": 1032.29, "total_tokens": 2932928} {"current_steps": 32580, "total_steps": 76960, "loss": 0.2449, "lr": 3.569784569258469e-05, "epoch": 8.466735966735968, "percentage": 42.33, "elapsed_time": "0:47:21", "remaining_time": "1:04:30", "throughput": 1032.31, "total_tokens": 2933408} {"current_steps": 32585, "total_steps": 76960, "loss": 0.3029, "lr": 3.569272112348918e-05, "epoch": 8.468035343035343, "percentage": 42.34, "elapsed_time": "0:47:22", "remaining_time": "1:04:30", "throughput": 1032.32, "total_tokens": 2933872} {"current_steps": 32590, "total_steps": 76960, "loss": 0.3456, "lr": 3.5687596004456785e-05, "epoch": 8.46933471933472, "percentage": 42.35, "elapsed_time": "0:47:22", "remaining_time": "1:04:29", "throughput": 1032.34, "total_tokens": 2934352} {"current_steps": 32595, "total_steps": 76960, "loss": 0.2634, "lr": 3.568247033575109e-05, "epoch": 8.470634095634095, "percentage": 42.35, "elapsed_time": "0:47:22", "remaining_time": "1:04:29", "throughput": 1032.34, "total_tokens": 2934800} {"current_steps": 32600, "total_steps": 76960, "loss": 0.1746, "lr": 3.567734411763571e-05, "epoch": 8.471933471933472, "percentage": 42.36, "elapsed_time": "0:47:23", "remaining_time": "1:04:28", "throughput": 1032.35, "total_tokens": 2935248} {"current_steps": 32605, "total_steps": 76960, "loss": 0.2499, "lr": 3.5672217350374284e-05, "epoch": 8.473232848232849, "percentage": 42.37, "elapsed_time": "0:47:23", "remaining_time": "1:04:28", "throughput": 1032.36, "total_tokens": 2935712} {"current_steps": 32610, "total_steps": 76960, "loss": 0.2708, "lr": 3.566709003423051e-05, "epoch": 8.474532224532224, "percentage": 42.37, "elapsed_time": "0:47:24", "remaining_time": "1:04:28", "throughput": 1032.37, "total_tokens": 2936160} {"current_steps": 32615, "total_steps": 76960, "loss": 0.1017, "lr": 3.5661962169468065e-05, "epoch": 8.4758316008316, "percentage": 42.38, "elapsed_time": "0:47:24", "remaining_time": "1:04:27", "throughput": 1032.37, "total_tokens": 2936608} {"current_steps": 32620, "total_steps": 76960, "loss": 0.1773, "lr": 3.565683375635068e-05, "epoch": 8.477130977130978, "percentage": 42.39, "elapsed_time": "0:47:24", "remaining_time": "1:04:27", "throughput": 1032.37, "total_tokens": 2937024} {"current_steps": 32625, "total_steps": 76960, "loss": 0.1742, "lr": 3.565170479514214e-05, "epoch": 8.478430353430353, "percentage": 42.39, "elapsed_time": "0:47:25", "remaining_time": "1:04:26", "throughput": 1032.37, "total_tokens": 2937456} {"current_steps": 32630, "total_steps": 76960, "loss": 0.2354, "lr": 3.564657528610621e-05, "epoch": 8.47972972972973, "percentage": 42.4, "elapsed_time": "0:47:25", "remaining_time": "1:04:26", "throughput": 1032.37, "total_tokens": 2937904} {"current_steps": 32635, "total_steps": 76960, "loss": 0.4172, "lr": 3.564144522950671e-05, "epoch": 8.481029106029107, "percentage": 42.41, "elapsed_time": "0:47:26", "remaining_time": "1:04:25", "throughput": 1032.38, "total_tokens": 2938352} {"current_steps": 32640, "total_steps": 76960, "loss": 0.391, "lr": 3.563631462560749e-05, "epoch": 8.482328482328482, "percentage": 42.41, "elapsed_time": "0:47:26", "remaining_time": "1:04:25", "throughput": 1032.38, "total_tokens": 2938784} {"current_steps": 32645, "total_steps": 76960, "loss": 0.2023, "lr": 3.563118347467241e-05, "epoch": 8.483627858627859, "percentage": 42.42, "elapsed_time": "0:47:27", "remaining_time": "1:04:24", "throughput": 1032.39, "total_tokens": 2939232} {"current_steps": 32650, "total_steps": 76960, "loss": 0.2019, "lr": 3.562605177696539e-05, "epoch": 8.484927234927236, "percentage": 42.42, "elapsed_time": "0:47:27", "remaining_time": "1:04:24", "throughput": 1032.39, "total_tokens": 2939664} {"current_steps": 32655, "total_steps": 76960, "loss": 0.3767, "lr": 3.562091953275034e-05, "epoch": 8.486226611226611, "percentage": 42.43, "elapsed_time": "0:47:27", "remaining_time": "1:04:23", "throughput": 1032.4, "total_tokens": 2940128} {"current_steps": 32660, "total_steps": 76960, "loss": 0.2211, "lr": 3.561578674229122e-05, "epoch": 8.487525987525988, "percentage": 42.44, "elapsed_time": "0:47:28", "remaining_time": "1:04:23", "throughput": 1032.41, "total_tokens": 2940592} {"current_steps": 32665, "total_steps": 76960, "loss": 0.1841, "lr": 3.5610653405852014e-05, "epoch": 8.488825363825363, "percentage": 42.44, "elapsed_time": "0:47:28", "remaining_time": "1:04:22", "throughput": 1032.42, "total_tokens": 2941040} {"current_steps": 32670, "total_steps": 76960, "loss": 0.1933, "lr": 3.560551952369674e-05, "epoch": 8.49012474012474, "percentage": 42.45, "elapsed_time": "0:47:29", "remaining_time": "1:04:22", "throughput": 1032.42, "total_tokens": 2941472} {"current_steps": 32675, "total_steps": 76960, "loss": 0.2298, "lr": 3.560038509608944e-05, "epoch": 8.491424116424117, "percentage": 42.46, "elapsed_time": "0:47:29", "remaining_time": "1:04:22", "throughput": 1032.42, "total_tokens": 2941904} {"current_steps": 32680, "total_steps": 76960, "loss": 0.2311, "lr": 3.5595250123294175e-05, "epoch": 8.492723492723492, "percentage": 42.46, "elapsed_time": "0:47:29", "remaining_time": "1:04:21", "throughput": 1032.43, "total_tokens": 2942368} {"current_steps": 32685, "total_steps": 76960, "loss": 0.2691, "lr": 3.559011460557504e-05, "epoch": 8.494022869022869, "percentage": 42.47, "elapsed_time": "0:47:30", "remaining_time": "1:04:21", "throughput": 1032.45, "total_tokens": 2942848} {"current_steps": 32690, "total_steps": 76960, "loss": 0.3877, "lr": 3.558497854319617e-05, "epoch": 8.495322245322246, "percentage": 42.48, "elapsed_time": "0:47:30", "remaining_time": "1:04:20", "throughput": 1032.45, "total_tokens": 2943280} {"current_steps": 32695, "total_steps": 76960, "loss": 0.2746, "lr": 3.5579841936421696e-05, "epoch": 8.496621621621621, "percentage": 42.48, "elapsed_time": "0:47:31", "remaining_time": "1:04:20", "throughput": 1032.45, "total_tokens": 2943712} {"current_steps": 32700, "total_steps": 76960, "loss": 0.2175, "lr": 3.557470478551583e-05, "epoch": 8.497920997920998, "percentage": 42.49, "elapsed_time": "0:47:31", "remaining_time": "1:04:19", "throughput": 1032.46, "total_tokens": 2944176} {"current_steps": 32705, "total_steps": 76960, "loss": 0.2041, "lr": 3.5569567090742764e-05, "epoch": 8.499220374220375, "percentage": 42.5, "elapsed_time": "0:47:32", "remaining_time": "1:04:19", "throughput": 1032.47, "total_tokens": 2944624} {"current_steps": 32710, "total_steps": 76960, "loss": 0.2476, "lr": 3.5564428852366725e-05, "epoch": 8.50051975051975, "percentage": 42.5, "elapsed_time": "0:47:32", "remaining_time": "1:04:18", "throughput": 1032.47, "total_tokens": 2945056} {"current_steps": 32715, "total_steps": 76960, "loss": 0.2907, "lr": 3.5559290070652e-05, "epoch": 8.501819126819127, "percentage": 42.51, "elapsed_time": "0:47:32", "remaining_time": "1:04:18", "throughput": 1032.48, "total_tokens": 2945520} {"current_steps": 32720, "total_steps": 76960, "loss": 0.2997, "lr": 3.555415074586286e-05, "epoch": 8.503118503118504, "percentage": 42.52, "elapsed_time": "0:47:33", "remaining_time": "1:04:17", "throughput": 1032.47, "total_tokens": 2945936} {"current_steps": 32725, "total_steps": 76960, "loss": 0.3031, "lr": 3.554901087826364e-05, "epoch": 8.504417879417879, "percentage": 42.52, "elapsed_time": "0:47:33", "remaining_time": "1:04:17", "throughput": 1032.49, "total_tokens": 2946416} {"current_steps": 32730, "total_steps": 76960, "loss": 0.3091, "lr": 3.5543870468118676e-05, "epoch": 8.505717255717256, "percentage": 42.53, "elapsed_time": "0:47:34", "remaining_time": "1:04:16", "throughput": 1032.48, "total_tokens": 2946832} {"current_steps": 32735, "total_steps": 76960, "loss": 0.2117, "lr": 3.553872951569236e-05, "epoch": 8.507016632016633, "percentage": 42.54, "elapsed_time": "0:47:34", "remaining_time": "1:04:16", "throughput": 1032.5, "total_tokens": 2947296} {"current_steps": 32740, "total_steps": 76960, "loss": 0.292, "lr": 3.5533588021249084e-05, "epoch": 8.508316008316008, "percentage": 42.54, "elapsed_time": "0:47:34", "remaining_time": "1:04:16", "throughput": 1032.51, "total_tokens": 2947776} {"current_steps": 32745, "total_steps": 76960, "loss": 0.3174, "lr": 3.552844598505328e-05, "epoch": 8.509615384615385, "percentage": 42.55, "elapsed_time": "0:47:35", "remaining_time": "1:04:15", "throughput": 1032.51, "total_tokens": 2948208} {"current_steps": 32750, "total_steps": 76960, "loss": 0.3275, "lr": 3.552330340736942e-05, "epoch": 8.51091476091476, "percentage": 42.55, "elapsed_time": "0:47:35", "remaining_time": "1:04:15", "throughput": 1032.53, "total_tokens": 2948688} {"current_steps": 32755, "total_steps": 76960, "loss": 0.2771, "lr": 3.5518160288461975e-05, "epoch": 8.512214137214137, "percentage": 42.56, "elapsed_time": "0:47:36", "remaining_time": "1:04:14", "throughput": 1032.54, "total_tokens": 2949136} {"current_steps": 32760, "total_steps": 76960, "loss": 0.2649, "lr": 3.551301662859548e-05, "epoch": 8.513513513513514, "percentage": 42.57, "elapsed_time": "0:47:36", "remaining_time": "1:04:14", "throughput": 1032.54, "total_tokens": 2949568} {"current_steps": 32765, "total_steps": 76960, "loss": 0.209, "lr": 3.550787242803444e-05, "epoch": 8.51481288981289, "percentage": 42.57, "elapsed_time": "0:47:37", "remaining_time": "1:04:13", "throughput": 1032.55, "total_tokens": 2950016} {"current_steps": 32770, "total_steps": 76960, "loss": 0.2242, "lr": 3.5502727687043476e-05, "epoch": 8.516112266112266, "percentage": 42.58, "elapsed_time": "0:47:37", "remaining_time": "1:04:13", "throughput": 1032.55, "total_tokens": 2950464} {"current_steps": 32775, "total_steps": 76960, "loss": 0.2847, "lr": 3.549758240588716e-05, "epoch": 8.517411642411643, "percentage": 42.59, "elapsed_time": "0:47:37", "remaining_time": "1:04:12", "throughput": 1032.55, "total_tokens": 2950896} {"current_steps": 32780, "total_steps": 76960, "loss": 0.4007, "lr": 3.549243658483012e-05, "epoch": 8.518711018711018, "percentage": 42.59, "elapsed_time": "0:47:38", "remaining_time": "1:04:12", "throughput": 1032.57, "total_tokens": 2951376} {"current_steps": 32785, "total_steps": 76960, "loss": 0.2221, "lr": 3.548729022413701e-05, "epoch": 8.520010395010395, "percentage": 42.6, "elapsed_time": "0:47:38", "remaining_time": "1:04:11", "throughput": 1032.57, "total_tokens": 2951808} {"current_steps": 32790, "total_steps": 76960, "loss": 0.27, "lr": 3.5482143324072517e-05, "epoch": 8.521309771309772, "percentage": 42.61, "elapsed_time": "0:47:39", "remaining_time": "1:04:11", "throughput": 1032.59, "total_tokens": 2952304} {"current_steps": 32795, "total_steps": 76960, "loss": 0.2443, "lr": 3.5476995884901357e-05, "epoch": 8.522609147609147, "percentage": 42.61, "elapsed_time": "0:47:39", "remaining_time": "1:04:10", "throughput": 1032.61, "total_tokens": 2952784} {"current_steps": 32800, "total_steps": 76960, "loss": 0.2538, "lr": 3.547184790688825e-05, "epoch": 8.523908523908524, "percentage": 42.62, "elapsed_time": "0:47:39", "remaining_time": "1:04:10", "throughput": 1032.61, "total_tokens": 2953216} {"current_steps": 32805, "total_steps": 76960, "loss": 0.2239, "lr": 3.546669939029798e-05, "epoch": 8.5252079002079, "percentage": 42.63, "elapsed_time": "0:47:40", "remaining_time": "1:04:10", "throughput": 1032.61, "total_tokens": 2953648} {"current_steps": 32810, "total_steps": 76960, "loss": 0.2432, "lr": 3.546155033539533e-05, "epoch": 8.526507276507276, "percentage": 42.63, "elapsed_time": "0:47:40", "remaining_time": "1:04:09", "throughput": 1032.63, "total_tokens": 2954112} {"current_steps": 32815, "total_steps": 76960, "loss": 0.2063, "lr": 3.5456400742445115e-05, "epoch": 8.527806652806653, "percentage": 42.64, "elapsed_time": "0:47:41", "remaining_time": "1:04:09", "throughput": 1032.64, "total_tokens": 2954576} {"current_steps": 32820, "total_steps": 76960, "loss": 0.2027, "lr": 3.545125061171219e-05, "epoch": 8.529106029106028, "percentage": 42.65, "elapsed_time": "0:47:41", "remaining_time": "1:04:08", "throughput": 1032.64, "total_tokens": 2955008} {"current_steps": 32825, "total_steps": 76960, "loss": 0.1319, "lr": 3.5446099943461445e-05, "epoch": 8.530405405405405, "percentage": 42.65, "elapsed_time": "0:47:42", "remaining_time": "1:04:08", "throughput": 1032.64, "total_tokens": 2955440} {"current_steps": 32830, "total_steps": 76960, "loss": 0.2558, "lr": 3.5440948737957756e-05, "epoch": 8.531704781704782, "percentage": 42.66, "elapsed_time": "0:47:42", "remaining_time": "1:04:07", "throughput": 1032.66, "total_tokens": 2955920} {"current_steps": 32835, "total_steps": 76960, "loss": 0.1402, "lr": 3.543579699546607e-05, "epoch": 8.533004158004157, "percentage": 42.67, "elapsed_time": "0:47:42", "remaining_time": "1:04:07", "throughput": 1032.67, "total_tokens": 2956384} {"current_steps": 32840, "total_steps": 76960, "loss": 0.334, "lr": 3.543064471625136e-05, "epoch": 8.534303534303534, "percentage": 42.67, "elapsed_time": "0:47:43", "remaining_time": "1:04:06", "throughput": 1032.69, "total_tokens": 2956880} {"current_steps": 32845, "total_steps": 76960, "loss": 0.299, "lr": 3.5425491900578586e-05, "epoch": 8.535602910602911, "percentage": 42.68, "elapsed_time": "0:47:43", "remaining_time": "1:04:06", "throughput": 1032.7, "total_tokens": 2957344} {"current_steps": 32850, "total_steps": 76960, "loss": 0.2207, "lr": 3.542033854871278e-05, "epoch": 8.536902286902286, "percentage": 42.68, "elapsed_time": "0:47:44", "remaining_time": "1:04:05", "throughput": 1032.72, "total_tokens": 2957808} {"current_steps": 32855, "total_steps": 76960, "loss": 0.2366, "lr": 3.5415184660918974e-05, "epoch": 8.538201663201663, "percentage": 42.69, "elapsed_time": "0:47:44", "remaining_time": "1:04:05", "throughput": 1032.73, "total_tokens": 2958288} {"current_steps": 32860, "total_steps": 76960, "loss": 0.2289, "lr": 3.541003023746225e-05, "epoch": 8.53950103950104, "percentage": 42.7, "elapsed_time": "0:47:44", "remaining_time": "1:04:04", "throughput": 1032.74, "total_tokens": 2958736} {"current_steps": 32865, "total_steps": 76960, "loss": 0.3541, "lr": 3.540487527860769e-05, "epoch": 8.540800415800415, "percentage": 42.7, "elapsed_time": "0:47:45", "remaining_time": "1:04:04", "throughput": 1032.74, "total_tokens": 2959184} {"current_steps": 32870, "total_steps": 76960, "loss": 0.3567, "lr": 3.539971978462043e-05, "epoch": 8.542099792099792, "percentage": 42.71, "elapsed_time": "0:47:45", "remaining_time": "1:04:03", "throughput": 1032.76, "total_tokens": 2959664} {"current_steps": 32875, "total_steps": 76960, "loss": 0.1929, "lr": 3.5394563755765615e-05, "epoch": 8.54339916839917, "percentage": 42.72, "elapsed_time": "0:47:46", "remaining_time": "1:04:03", "throughput": 1032.77, "total_tokens": 2960112} {"current_steps": 32880, "total_steps": 76960, "loss": 0.2084, "lr": 3.538940719230842e-05, "epoch": 8.544698544698544, "percentage": 42.72, "elapsed_time": "0:47:46", "remaining_time": "1:04:03", "throughput": 1032.77, "total_tokens": 2960544} {"current_steps": 32885, "total_steps": 76960, "loss": 0.2758, "lr": 3.5384250094514073e-05, "epoch": 8.545997920997921, "percentage": 42.73, "elapsed_time": "0:47:47", "remaining_time": "1:04:02", "throughput": 1032.79, "total_tokens": 2961024} {"current_steps": 32890, "total_steps": 76960, "loss": 0.1438, "lr": 3.5379092462647776e-05, "epoch": 8.547297297297296, "percentage": 42.74, "elapsed_time": "0:47:47", "remaining_time": "1:04:02", "throughput": 1032.79, "total_tokens": 2961456} {"current_steps": 32895, "total_steps": 76960, "loss": 0.2783, "lr": 3.5373934296974816e-05, "epoch": 8.548596673596673, "percentage": 42.74, "elapsed_time": "0:47:47", "remaining_time": "1:04:01", "throughput": 1032.8, "total_tokens": 2961920} {"current_steps": 32900, "total_steps": 76960, "loss": 0.1792, "lr": 3.536877559776048e-05, "epoch": 8.54989604989605, "percentage": 42.75, "elapsed_time": "0:47:48", "remaining_time": "1:04:01", "throughput": 1032.8, "total_tokens": 2962368} {"current_steps": 32905, "total_steps": 76960, "loss": 0.3963, "lr": 3.5363616365270075e-05, "epoch": 8.551195426195425, "percentage": 42.76, "elapsed_time": "0:47:48", "remaining_time": "1:04:00", "throughput": 1032.81, "total_tokens": 2962816} {"current_steps": 32910, "total_steps": 76960, "loss": 0.1941, "lr": 3.535845659976895e-05, "epoch": 8.552494802494802, "percentage": 42.76, "elapsed_time": "0:47:49", "remaining_time": "1:04:00", "throughput": 1032.83, "total_tokens": 2963296} {"current_steps": 32915, "total_steps": 76960, "loss": 0.171, "lr": 3.5353296301522474e-05, "epoch": 8.55379417879418, "percentage": 42.77, "elapsed_time": "0:47:49", "remaining_time": "1:03:59", "throughput": 1032.83, "total_tokens": 2963728} {"current_steps": 32920, "total_steps": 76960, "loss": 0.3484, "lr": 3.5348135470796054e-05, "epoch": 8.555093555093555, "percentage": 42.78, "elapsed_time": "0:47:49", "remaining_time": "1:03:59", "throughput": 1032.84, "total_tokens": 2964192} {"current_steps": 32925, "total_steps": 76960, "loss": 0.1588, "lr": 3.534297410785512e-05, "epoch": 8.556392931392931, "percentage": 42.78, "elapsed_time": "0:47:50", "remaining_time": "1:03:58", "throughput": 1032.84, "total_tokens": 2964624} {"current_steps": 32930, "total_steps": 76960, "loss": 0.1695, "lr": 3.53378122129651e-05, "epoch": 8.557692307692308, "percentage": 42.79, "elapsed_time": "0:47:50", "remaining_time": "1:03:58", "throughput": 1032.85, "total_tokens": 2965072} {"current_steps": 32935, "total_steps": 76960, "loss": 0.251, "lr": 3.533264978639151e-05, "epoch": 8.558991683991684, "percentage": 42.79, "elapsed_time": "0:47:51", "remaining_time": "1:03:57", "throughput": 1032.85, "total_tokens": 2965504} {"current_steps": 32940, "total_steps": 76960, "loss": 0.2903, "lr": 3.5327486828399834e-05, "epoch": 8.56029106029106, "percentage": 42.8, "elapsed_time": "0:47:51", "remaining_time": "1:03:57", "throughput": 1032.86, "total_tokens": 2965968} {"current_steps": 32945, "total_steps": 76960, "loss": 0.2861, "lr": 3.53223233392556e-05, "epoch": 8.561590436590437, "percentage": 42.81, "elapsed_time": "0:47:52", "remaining_time": "1:03:57", "throughput": 1032.85, "total_tokens": 2966368} {"current_steps": 32950, "total_steps": 76960, "loss": 0.1914, "lr": 3.5317159319224406e-05, "epoch": 8.562889812889813, "percentage": 42.81, "elapsed_time": "0:47:52", "remaining_time": "1:03:56", "throughput": 1032.85, "total_tokens": 2966800} {"current_steps": 32955, "total_steps": 76960, "loss": 0.2015, "lr": 3.531199476857182e-05, "epoch": 8.56418918918919, "percentage": 42.82, "elapsed_time": "0:47:52", "remaining_time": "1:03:56", "throughput": 1032.85, "total_tokens": 2967248} {"current_steps": 32960, "total_steps": 76960, "loss": 0.3231, "lr": 3.5306829687563455e-05, "epoch": 8.565488565488565, "percentage": 42.83, "elapsed_time": "0:47:53", "remaining_time": "1:03:55", "throughput": 1032.86, "total_tokens": 2967696} {"current_steps": 32965, "total_steps": 76960, "loss": 0.0675, "lr": 3.530166407646497e-05, "epoch": 8.566787941787942, "percentage": 42.83, "elapsed_time": "0:47:53", "remaining_time": "1:03:55", "throughput": 1032.86, "total_tokens": 2968128} {"current_steps": 32970, "total_steps": 76960, "loss": 0.4535, "lr": 3.529649793554203e-05, "epoch": 8.568087318087318, "percentage": 42.84, "elapsed_time": "0:47:54", "remaining_time": "1:03:54", "throughput": 1032.87, "total_tokens": 2968592} {"current_steps": 32975, "total_steps": 76960, "loss": 0.3292, "lr": 3.5291331265060336e-05, "epoch": 8.569386694386694, "percentage": 42.85, "elapsed_time": "0:47:54", "remaining_time": "1:03:54", "throughput": 1032.88, "total_tokens": 2969040} {"current_steps": 32980, "total_steps": 76960, "loss": 0.1968, "lr": 3.528616406528561e-05, "epoch": 8.57068607068607, "percentage": 42.85, "elapsed_time": "0:47:54", "remaining_time": "1:03:53", "throughput": 1032.88, "total_tokens": 2969488} {"current_steps": 32985, "total_steps": 76960, "loss": 0.1601, "lr": 3.5280996336483614e-05, "epoch": 8.571985446985448, "percentage": 42.86, "elapsed_time": "0:47:55", "remaining_time": "1:03:53", "throughput": 1032.87, "total_tokens": 2969888} {"current_steps": 32990, "total_steps": 76960, "loss": 0.2289, "lr": 3.527582807892013e-05, "epoch": 8.573284823284823, "percentage": 42.87, "elapsed_time": "0:47:55", "remaining_time": "1:03:52", "throughput": 1032.87, "total_tokens": 2970320} {"current_steps": 32995, "total_steps": 76960, "loss": 0.1475, "lr": 3.527065929286095e-05, "epoch": 8.5745841995842, "percentage": 42.87, "elapsed_time": "0:47:56", "remaining_time": "1:03:52", "throughput": 1032.87, "total_tokens": 2970736} {"current_steps": 33000, "total_steps": 76960, "loss": 0.1391, "lr": 3.526548997857193e-05, "epoch": 8.575883575883577, "percentage": 42.88, "elapsed_time": "0:47:56", "remaining_time": "1:03:52", "throughput": 1032.87, "total_tokens": 2971168} {"current_steps": 33005, "total_steps": 76960, "loss": 0.2448, "lr": 3.526032013631893e-05, "epoch": 8.577182952182952, "percentage": 42.89, "elapsed_time": "0:47:57", "remaining_time": "1:03:51", "throughput": 1032.87, "total_tokens": 2971600} {"current_steps": 33010, "total_steps": 76960, "loss": 0.3825, "lr": 3.5255149766367826e-05, "epoch": 8.578482328482329, "percentage": 42.89, "elapsed_time": "0:47:57", "remaining_time": "1:03:51", "throughput": 1032.89, "total_tokens": 2972080} {"current_steps": 33015, "total_steps": 76960, "loss": 0.1906, "lr": 3.524997886898454e-05, "epoch": 8.579781704781706, "percentage": 42.9, "elapsed_time": "0:47:57", "remaining_time": "1:03:50", "throughput": 1032.89, "total_tokens": 2972512} {"current_steps": 33020, "total_steps": 76960, "loss": 0.3335, "lr": 3.524480744443503e-05, "epoch": 8.58108108108108, "percentage": 42.91, "elapsed_time": "0:47:58", "remaining_time": "1:03:50", "throughput": 1032.9, "total_tokens": 2972976} {"current_steps": 33025, "total_steps": 76960, "loss": 0.2594, "lr": 3.523963549298525e-05, "epoch": 8.582380457380458, "percentage": 42.91, "elapsed_time": "0:47:58", "remaining_time": "1:03:49", "throughput": 1032.91, "total_tokens": 2973440} {"current_steps": 33030, "total_steps": 76960, "loss": 0.3066, "lr": 3.52344630149012e-05, "epoch": 8.583679833679835, "percentage": 42.92, "elapsed_time": "0:47:59", "remaining_time": "1:03:49", "throughput": 1032.93, "total_tokens": 2973920} {"current_steps": 33035, "total_steps": 76960, "loss": 0.3126, "lr": 3.5229290010448915e-05, "epoch": 8.58497920997921, "percentage": 42.92, "elapsed_time": "0:47:59", "remaining_time": "1:03:48", "throughput": 1032.96, "total_tokens": 2974432} {"current_steps": 33040, "total_steps": 76960, "loss": 0.1539, "lr": 3.5224116479894456e-05, "epoch": 8.586278586278587, "percentage": 42.93, "elapsed_time": "0:47:59", "remaining_time": "1:03:48", "throughput": 1032.95, "total_tokens": 2974848} {"current_steps": 33045, "total_steps": 76960, "loss": 0.1887, "lr": 3.5218942423503874e-05, "epoch": 8.587577962577962, "percentage": 42.94, "elapsed_time": "0:48:00", "remaining_time": "1:03:47", "throughput": 1032.96, "total_tokens": 2975296} {"current_steps": 33050, "total_steps": 76960, "loss": 0.3525, "lr": 3.521376784154331e-05, "epoch": 8.588877338877339, "percentage": 42.94, "elapsed_time": "0:48:00", "remaining_time": "1:03:47", "throughput": 1032.96, "total_tokens": 2975744} {"current_steps": 33055, "total_steps": 76960, "loss": 0.3172, "lr": 3.5208592734278854e-05, "epoch": 8.590176715176716, "percentage": 42.95, "elapsed_time": "0:48:01", "remaining_time": "1:03:46", "throughput": 1032.96, "total_tokens": 2976160} {"current_steps": 33060, "total_steps": 76960, "loss": 0.3732, "lr": 3.520341710197671e-05, "epoch": 8.59147609147609, "percentage": 42.96, "elapsed_time": "0:48:01", "remaining_time": "1:03:46", "throughput": 1032.96, "total_tokens": 2976608} {"current_steps": 33065, "total_steps": 76960, "loss": 0.3121, "lr": 3.519824094490305e-05, "epoch": 8.592775467775468, "percentage": 42.96, "elapsed_time": "0:48:02", "remaining_time": "1:03:46", "throughput": 1032.98, "total_tokens": 2977088} {"current_steps": 33070, "total_steps": 76960, "loss": 0.2463, "lr": 3.519306426332408e-05, "epoch": 8.594074844074845, "percentage": 42.97, "elapsed_time": "0:48:02", "remaining_time": "1:03:45", "throughput": 1032.99, "total_tokens": 2977536} {"current_steps": 33075, "total_steps": 76960, "loss": 0.1347, "lr": 3.518788705750605e-05, "epoch": 8.59537422037422, "percentage": 42.98, "elapsed_time": "0:48:02", "remaining_time": "1:03:45", "throughput": 1033.01, "total_tokens": 2978032} {"current_steps": 33080, "total_steps": 76960, "loss": 0.2441, "lr": 3.518270932771523e-05, "epoch": 8.596673596673597, "percentage": 42.98, "elapsed_time": "0:48:03", "remaining_time": "1:03:44", "throughput": 1033.02, "total_tokens": 2978480} {"current_steps": 33085, "total_steps": 76960, "loss": 0.1463, "lr": 3.5177531074217906e-05, "epoch": 8.597972972972974, "percentage": 42.99, "elapsed_time": "0:48:03", "remaining_time": "1:03:44", "throughput": 1033.02, "total_tokens": 2978928} {"current_steps": 33090, "total_steps": 76960, "loss": 0.1373, "lr": 3.517235229728041e-05, "epoch": 8.599272349272349, "percentage": 43.0, "elapsed_time": "0:48:04", "remaining_time": "1:03:43", "throughput": 1033.03, "total_tokens": 2979376} {"current_steps": 33095, "total_steps": 76960, "loss": 0.2081, "lr": 3.516717299716909e-05, "epoch": 8.600571725571726, "percentage": 43.0, "elapsed_time": "0:48:04", "remaining_time": "1:03:43", "throughput": 1033.03, "total_tokens": 2979808} {"current_steps": 33100, "total_steps": 76960, "loss": 0.415, "lr": 3.516199317415032e-05, "epoch": 8.601871101871101, "percentage": 43.01, "elapsed_time": "0:48:04", "remaining_time": "1:03:42", "throughput": 1033.07, "total_tokens": 2980368} {"current_steps": 33105, "total_steps": 76960, "loss": 0.2776, "lr": 3.51568128284905e-05, "epoch": 8.603170478170478, "percentage": 43.02, "elapsed_time": "0:48:05", "remaining_time": "1:03:42", "throughput": 1033.08, "total_tokens": 2980816} {"current_steps": 33110, "total_steps": 76960, "loss": 0.311, "lr": 3.515163196045607e-05, "epoch": 8.604469854469855, "percentage": 43.02, "elapsed_time": "0:48:05", "remaining_time": "1:03:41", "throughput": 1033.1, "total_tokens": 2981296} {"current_steps": 33115, "total_steps": 76960, "loss": 0.2188, "lr": 3.514645057031348e-05, "epoch": 8.60576923076923, "percentage": 43.03, "elapsed_time": "0:48:06", "remaining_time": "1:03:41", "throughput": 1033.11, "total_tokens": 2981776} {"current_steps": 33120, "total_steps": 76960, "loss": 0.1473, "lr": 3.514126865832922e-05, "epoch": 8.607068607068607, "percentage": 43.04, "elapsed_time": "0:48:06", "remaining_time": "1:03:40", "throughput": 1033.11, "total_tokens": 2982208} {"current_steps": 33125, "total_steps": 76960, "loss": 0.2037, "lr": 3.513608622476979e-05, "epoch": 8.608367983367984, "percentage": 43.04, "elapsed_time": "0:48:07", "remaining_time": "1:03:40", "throughput": 1033.1, "total_tokens": 2982624} {"current_steps": 33130, "total_steps": 76960, "loss": 0.3504, "lr": 3.513090326990174e-05, "epoch": 8.609667359667359, "percentage": 43.05, "elapsed_time": "0:48:07", "remaining_time": "1:03:40", "throughput": 1033.12, "total_tokens": 2983104} {"current_steps": 33135, "total_steps": 76960, "loss": 0.1554, "lr": 3.512571979399162e-05, "epoch": 8.610966735966736, "percentage": 43.05, "elapsed_time": "0:48:07", "remaining_time": "1:03:39", "throughput": 1033.12, "total_tokens": 2983552} {"current_steps": 33140, "total_steps": 76960, "loss": 0.2025, "lr": 3.5120535797306034e-05, "epoch": 8.612266112266113, "percentage": 43.06, "elapsed_time": "0:48:08", "remaining_time": "1:03:39", "throughput": 1033.11, "total_tokens": 2983952} {"current_steps": 33145, "total_steps": 76960, "loss": 0.2741, "lr": 3.511535128011159e-05, "epoch": 8.613565488565488, "percentage": 43.07, "elapsed_time": "0:48:08", "remaining_time": "1:03:38", "throughput": 1033.12, "total_tokens": 2984400} {"current_steps": 33150, "total_steps": 76960, "loss": 0.1546, "lr": 3.511016624267495e-05, "epoch": 8.614864864864865, "percentage": 43.07, "elapsed_time": "0:48:09", "remaining_time": "1:03:38", "throughput": 1033.12, "total_tokens": 2984848} {"current_steps": 33155, "total_steps": 76960, "loss": 0.2867, "lr": 3.510498068526276e-05, "epoch": 8.616164241164242, "percentage": 43.08, "elapsed_time": "0:48:09", "remaining_time": "1:03:37", "throughput": 1033.14, "total_tokens": 2985328} {"current_steps": 33160, "total_steps": 76960, "loss": 0.37, "lr": 3.5099794608141734e-05, "epoch": 8.617463617463617, "percentage": 43.09, "elapsed_time": "0:48:09", "remaining_time": "1:03:37", "throughput": 1033.14, "total_tokens": 2985760} {"current_steps": 33165, "total_steps": 76960, "loss": 0.2175, "lr": 3.50946080115786e-05, "epoch": 8.618762993762994, "percentage": 43.09, "elapsed_time": "0:48:10", "remaining_time": "1:03:36", "throughput": 1033.14, "total_tokens": 2986192} {"current_steps": 33170, "total_steps": 76960, "loss": 0.3713, "lr": 3.5089420895840095e-05, "epoch": 8.62006237006237, "percentage": 43.1, "elapsed_time": "0:48:10", "remaining_time": "1:03:36", "throughput": 1033.15, "total_tokens": 2986656} {"current_steps": 33175, "total_steps": 76960, "loss": 0.2159, "lr": 3.508423326119301e-05, "epoch": 8.621361746361746, "percentage": 43.11, "elapsed_time": "0:48:11", "remaining_time": "1:03:35", "throughput": 1033.16, "total_tokens": 2987104} {"current_steps": 33180, "total_steps": 76960, "loss": 0.1579, "lr": 3.507904510790414e-05, "epoch": 8.622661122661123, "percentage": 43.11, "elapsed_time": "0:48:11", "remaining_time": "1:03:35", "throughput": 1033.17, "total_tokens": 2987568} {"current_steps": 33185, "total_steps": 76960, "loss": 0.2475, "lr": 3.5073856436240334e-05, "epoch": 8.6239604989605, "percentage": 43.12, "elapsed_time": "0:48:12", "remaining_time": "1:03:34", "throughput": 1033.17, "total_tokens": 2988000} {"current_steps": 33190, "total_steps": 76960, "loss": 0.1781, "lr": 3.5068667246468436e-05, "epoch": 8.625259875259875, "percentage": 43.13, "elapsed_time": "0:48:12", "remaining_time": "1:03:34", "throughput": 1033.17, "total_tokens": 2988432} {"current_steps": 33195, "total_steps": 76960, "loss": 0.1973, "lr": 3.506347753885533e-05, "epoch": 8.626559251559252, "percentage": 43.13, "elapsed_time": "0:48:12", "remaining_time": "1:03:34", "throughput": 1033.19, "total_tokens": 2988928} {"current_steps": 33200, "total_steps": 76960, "loss": 0.2451, "lr": 3.5058287313667936e-05, "epoch": 8.627858627858627, "percentage": 43.14, "elapsed_time": "0:48:13", "remaining_time": "1:03:33", "throughput": 1033.19, "total_tokens": 2989360} {"current_steps": 33205, "total_steps": 76960, "loss": 0.201, "lr": 3.505309657117319e-05, "epoch": 8.629158004158004, "percentage": 43.15, "elapsed_time": "0:48:13", "remaining_time": "1:03:33", "throughput": 1033.2, "total_tokens": 2989808} {"current_steps": 33210, "total_steps": 76960, "loss": 0.4358, "lr": 3.5047905311638045e-05, "epoch": 8.630457380457381, "percentage": 43.15, "elapsed_time": "0:48:14", "remaining_time": "1:03:32", "throughput": 1033.19, "total_tokens": 2990224} {"current_steps": 33215, "total_steps": 76960, "loss": 0.2059, "lr": 3.504271353532951e-05, "epoch": 8.631756756756756, "percentage": 43.16, "elapsed_time": "0:48:14", "remaining_time": "1:03:32", "throughput": 1033.21, "total_tokens": 2990688} {"current_steps": 33220, "total_steps": 76960, "loss": 0.1105, "lr": 3.5037521242514595e-05, "epoch": 8.633056133056133, "percentage": 43.17, "elapsed_time": "0:48:14", "remaining_time": "1:03:31", "throughput": 1033.21, "total_tokens": 2991136} {"current_steps": 33225, "total_steps": 76960, "loss": 0.3632, "lr": 3.5032328433460346e-05, "epoch": 8.63435550935551, "percentage": 43.17, "elapsed_time": "0:48:15", "remaining_time": "1:03:31", "throughput": 1033.22, "total_tokens": 2991584} {"current_steps": 33230, "total_steps": 76960, "loss": 0.1821, "lr": 3.502713510843383e-05, "epoch": 8.635654885654885, "percentage": 43.18, "elapsed_time": "0:48:15", "remaining_time": "1:03:30", "throughput": 1033.23, "total_tokens": 2992064} {"current_steps": 33235, "total_steps": 76960, "loss": 0.2978, "lr": 3.5021941267702144e-05, "epoch": 8.636954261954262, "percentage": 43.18, "elapsed_time": "0:48:16", "remaining_time": "1:03:30", "throughput": 1033.24, "total_tokens": 2992512} {"current_steps": 33240, "total_steps": 76960, "loss": 0.2888, "lr": 3.5016746911532425e-05, "epoch": 8.638253638253639, "percentage": 43.19, "elapsed_time": "0:48:16", "remaining_time": "1:03:29", "throughput": 1033.23, "total_tokens": 2992928} {"current_steps": 33245, "total_steps": 76960, "loss": 0.2261, "lr": 3.5011552040191806e-05, "epoch": 8.639553014553014, "percentage": 43.2, "elapsed_time": "0:48:17", "remaining_time": "1:03:29", "throughput": 1033.23, "total_tokens": 2993344} {"current_steps": 33250, "total_steps": 76960, "loss": 0.225, "lr": 3.500635665394748e-05, "epoch": 8.640852390852391, "percentage": 43.2, "elapsed_time": "0:48:17", "remaining_time": "1:03:29", "throughput": 1033.24, "total_tokens": 2993808} {"current_steps": 33255, "total_steps": 76960, "loss": 0.2024, "lr": 3.500116075306664e-05, "epoch": 8.642151767151766, "percentage": 43.21, "elapsed_time": "0:48:17", "remaining_time": "1:03:28", "throughput": 1033.25, "total_tokens": 2994272} {"current_steps": 33260, "total_steps": 76960, "loss": 0.2396, "lr": 3.499596433781653e-05, "epoch": 8.643451143451143, "percentage": 43.22, "elapsed_time": "0:48:18", "remaining_time": "1:03:28", "throughput": 1033.26, "total_tokens": 2994720} {"current_steps": 33265, "total_steps": 76960, "loss": 0.3091, "lr": 3.499076740846438e-05, "epoch": 8.64475051975052, "percentage": 43.22, "elapsed_time": "0:48:18", "remaining_time": "1:03:27", "throughput": 1033.25, "total_tokens": 2995136} {"current_steps": 33270, "total_steps": 76960, "loss": 0.2088, "lr": 3.49855699652775e-05, "epoch": 8.646049896049895, "percentage": 43.23, "elapsed_time": "0:48:19", "remaining_time": "1:03:27", "throughput": 1033.25, "total_tokens": 2995552} {"current_steps": 33275, "total_steps": 76960, "loss": 0.2058, "lr": 3.498037200852319e-05, "epoch": 8.647349272349272, "percentage": 43.24, "elapsed_time": "0:48:19", "remaining_time": "1:03:26", "throughput": 1033.25, "total_tokens": 2995984} {"current_steps": 33280, "total_steps": 76960, "loss": 0.2684, "lr": 3.497517353846878e-05, "epoch": 8.64864864864865, "percentage": 43.24, "elapsed_time": "0:48:19", "remaining_time": "1:03:26", "throughput": 1033.26, "total_tokens": 2996448} {"current_steps": 33285, "total_steps": 76960, "loss": 0.2535, "lr": 3.4969974555381636e-05, "epoch": 8.649948024948024, "percentage": 43.25, "elapsed_time": "0:48:20", "remaining_time": "1:03:25", "throughput": 1033.26, "total_tokens": 2996880} {"current_steps": 33290, "total_steps": 76960, "loss": 0.2114, "lr": 3.496477505952915e-05, "epoch": 8.651247401247401, "percentage": 43.26, "elapsed_time": "0:48:20", "remaining_time": "1:03:25", "throughput": 1033.27, "total_tokens": 2997344} {"current_steps": 33295, "total_steps": 76960, "loss": 0.2633, "lr": 3.4959575051178735e-05, "epoch": 8.652546777546778, "percentage": 43.26, "elapsed_time": "0:48:21", "remaining_time": "1:03:24", "throughput": 1033.27, "total_tokens": 2997776} {"current_steps": 33300, "total_steps": 76960, "loss": 0.2021, "lr": 3.495437453059783e-05, "epoch": 8.653846153846153, "percentage": 43.27, "elapsed_time": "0:48:21", "remaining_time": "1:03:24", "throughput": 1033.29, "total_tokens": 2998256} {"current_steps": 33305, "total_steps": 76960, "loss": 0.1729, "lr": 3.49491734980539e-05, "epoch": 8.65514553014553, "percentage": 43.28, "elapsed_time": "0:48:22", "remaining_time": "1:03:23", "throughput": 1033.31, "total_tokens": 2998752} {"current_steps": 33310, "total_steps": 76960, "loss": 0.2679, "lr": 3.494397195381446e-05, "epoch": 8.656444906444907, "percentage": 43.28, "elapsed_time": "0:48:22", "remaining_time": "1:03:23", "throughput": 1033.31, "total_tokens": 2999168} {"current_steps": 33315, "total_steps": 76960, "loss": 0.2252, "lr": 3.493876989814701e-05, "epoch": 8.657744282744282, "percentage": 43.29, "elapsed_time": "0:48:22", "remaining_time": "1:03:23", "throughput": 1033.33, "total_tokens": 2999664} {"current_steps": 33320, "total_steps": 76960, "loss": 0.2536, "lr": 3.493356733131909e-05, "epoch": 8.65904365904366, "percentage": 43.3, "elapsed_time": "0:48:23", "remaining_time": "1:03:22", "throughput": 1033.33, "total_tokens": 3000096} {"current_steps": 33325, "total_steps": 76960, "loss": 0.2133, "lr": 3.49283642535983e-05, "epoch": 8.660343035343036, "percentage": 43.3, "elapsed_time": "0:48:23", "remaining_time": "1:03:22", "throughput": 1033.33, "total_tokens": 3000528} {"current_steps": 33330, "total_steps": 76960, "loss": 0.3526, "lr": 3.492316066525221e-05, "epoch": 8.661642411642411, "percentage": 43.31, "elapsed_time": "0:48:24", "remaining_time": "1:03:21", "throughput": 1033.34, "total_tokens": 3000976} {"current_steps": 33335, "total_steps": 76960, "loss": 0.4226, "lr": 3.491795656654846e-05, "epoch": 8.662941787941788, "percentage": 43.31, "elapsed_time": "0:48:24", "remaining_time": "1:03:21", "throughput": 1033.34, "total_tokens": 3001424} {"current_steps": 33340, "total_steps": 76960, "loss": 0.4316, "lr": 3.491275195775471e-05, "epoch": 8.664241164241163, "percentage": 43.32, "elapsed_time": "0:48:24", "remaining_time": "1:03:20", "throughput": 1033.36, "total_tokens": 3001888} {"current_steps": 33345, "total_steps": 76960, "loss": 0.2726, "lr": 3.490754683913863e-05, "epoch": 8.66554054054054, "percentage": 43.33, "elapsed_time": "0:48:25", "remaining_time": "1:03:20", "throughput": 1033.36, "total_tokens": 3002336} {"current_steps": 33350, "total_steps": 76960, "loss": 0.1849, "lr": 3.490234121096791e-05, "epoch": 8.666839916839917, "percentage": 43.33, "elapsed_time": "0:48:25", "remaining_time": "1:03:19", "throughput": 1033.36, "total_tokens": 3002768} {"current_steps": 33355, "total_steps": 76960, "loss": 0.2026, "lr": 3.48971350735103e-05, "epoch": 8.668139293139292, "percentage": 43.34, "elapsed_time": "0:48:26", "remaining_time": "1:03:19", "throughput": 1033.37, "total_tokens": 3003232} {"current_steps": 33360, "total_steps": 76960, "loss": 0.1597, "lr": 3.489192842703355e-05, "epoch": 8.66943866943867, "percentage": 43.35, "elapsed_time": "0:48:26", "remaining_time": "1:03:18", "throughput": 1033.38, "total_tokens": 3003696} {"current_steps": 33365, "total_steps": 76960, "loss": 0.2506, "lr": 3.488672127180544e-05, "epoch": 8.670738045738046, "percentage": 43.35, "elapsed_time": "0:48:27", "remaining_time": "1:03:18", "throughput": 1033.4, "total_tokens": 3004176} {"current_steps": 33370, "total_steps": 76960, "loss": 0.2994, "lr": 3.48815136080938e-05, "epoch": 8.672037422037421, "percentage": 43.36, "elapsed_time": "0:48:27", "remaining_time": "1:03:17", "throughput": 1033.4, "total_tokens": 3004608} {"current_steps": 33375, "total_steps": 76960, "loss": 0.4168, "lr": 3.487630543616642e-05, "epoch": 8.673336798336798, "percentage": 43.37, "elapsed_time": "0:48:27", "remaining_time": "1:03:17", "throughput": 1033.41, "total_tokens": 3005056} {"current_steps": 33380, "total_steps": 76960, "loss": 0.2267, "lr": 3.4871096756291203e-05, "epoch": 8.674636174636175, "percentage": 43.37, "elapsed_time": "0:48:28", "remaining_time": "1:03:17", "throughput": 1033.41, "total_tokens": 3005504} {"current_steps": 33385, "total_steps": 76960, "loss": 0.1837, "lr": 3.486588756873602e-05, "epoch": 8.67593555093555, "percentage": 43.38, "elapsed_time": "0:48:28", "remaining_time": "1:03:16", "throughput": 1033.41, "total_tokens": 3005920} {"current_steps": 33390, "total_steps": 76960, "loss": 0.2002, "lr": 3.486067787376879e-05, "epoch": 8.677234927234927, "percentage": 43.39, "elapsed_time": "0:48:29", "remaining_time": "1:03:16", "throughput": 1033.41, "total_tokens": 3006368} {"current_steps": 33395, "total_steps": 76960, "loss": 0.2035, "lr": 3.485546767165745e-05, "epoch": 8.678534303534304, "percentage": 43.39, "elapsed_time": "0:48:29", "remaining_time": "1:03:15", "throughput": 1033.42, "total_tokens": 3006816} {"current_steps": 33400, "total_steps": 76960, "loss": 0.3396, "lr": 3.485025696266996e-05, "epoch": 8.67983367983368, "percentage": 43.4, "elapsed_time": "0:48:29", "remaining_time": "1:03:15", "throughput": 1033.42, "total_tokens": 3007232} {"current_steps": 33405, "total_steps": 76960, "loss": 0.2455, "lr": 3.484504574707431e-05, "epoch": 8.681133056133056, "percentage": 43.41, "elapsed_time": "0:48:30", "remaining_time": "1:03:14", "throughput": 1033.43, "total_tokens": 3007696} {"current_steps": 33410, "total_steps": 76960, "loss": 0.3672, "lr": 3.4839834025138526e-05, "epoch": 8.682432432432432, "percentage": 43.41, "elapsed_time": "0:48:30", "remaining_time": "1:03:14", "throughput": 1033.42, "total_tokens": 3008112} {"current_steps": 33415, "total_steps": 76960, "loss": 0.1494, "lr": 3.483462179713066e-05, "epoch": 8.683731808731808, "percentage": 43.42, "elapsed_time": "0:48:31", "remaining_time": "1:03:13", "throughput": 1033.44, "total_tokens": 3008592} {"current_steps": 33420, "total_steps": 76960, "loss": 0.1828, "lr": 3.482940906331877e-05, "epoch": 8.685031185031185, "percentage": 43.43, "elapsed_time": "0:48:31", "remaining_time": "1:03:13", "throughput": 1033.44, "total_tokens": 3009040} {"current_steps": 33425, "total_steps": 76960, "loss": 0.1932, "lr": 3.482419582397095e-05, "epoch": 8.68633056133056, "percentage": 43.43, "elapsed_time": "0:48:32", "remaining_time": "1:03:12", "throughput": 1033.46, "total_tokens": 3009504} {"current_steps": 33430, "total_steps": 76960, "loss": 0.2567, "lr": 3.481898207935532e-05, "epoch": 8.687629937629938, "percentage": 43.44, "elapsed_time": "0:48:32", "remaining_time": "1:03:12", "throughput": 1033.46, "total_tokens": 3009936} {"current_steps": 33435, "total_steps": 76960, "loss": 0.4462, "lr": 3.481376782974004e-05, "epoch": 8.688929313929314, "percentage": 43.44, "elapsed_time": "0:48:32", "remaining_time": "1:03:11", "throughput": 1033.46, "total_tokens": 3010384} {"current_steps": 33440, "total_steps": 76960, "loss": 0.2232, "lr": 3.480855307539328e-05, "epoch": 8.69022869022869, "percentage": 43.45, "elapsed_time": "0:48:33", "remaining_time": "1:03:11", "throughput": 1033.47, "total_tokens": 3010848} {"current_steps": 33445, "total_steps": 76960, "loss": 0.3312, "lr": 3.4803337816583225e-05, "epoch": 8.691528066528067, "percentage": 43.46, "elapsed_time": "0:48:33", "remaining_time": "1:03:11", "throughput": 1033.47, "total_tokens": 3011280} {"current_steps": 33450, "total_steps": 76960, "loss": 0.292, "lr": 3.479812205357813e-05, "epoch": 8.692827442827443, "percentage": 43.46, "elapsed_time": "0:48:34", "remaining_time": "1:03:10", "throughput": 1033.47, "total_tokens": 3011712} {"current_steps": 33455, "total_steps": 76960, "loss": 0.2665, "lr": 3.479290578664622e-05, "epoch": 8.694126819126819, "percentage": 43.47, "elapsed_time": "0:48:34", "remaining_time": "1:03:10", "throughput": 1033.48, "total_tokens": 3012144} {"current_steps": 33460, "total_steps": 76960, "loss": 0.2412, "lr": 3.478768901605578e-05, "epoch": 8.695426195426196, "percentage": 43.48, "elapsed_time": "0:48:34", "remaining_time": "1:03:09", "throughput": 1033.49, "total_tokens": 3012608} {"current_steps": 33465, "total_steps": 76960, "loss": 0.2253, "lr": 3.478247174207513e-05, "epoch": 8.696725571725572, "percentage": 43.48, "elapsed_time": "0:48:35", "remaining_time": "1:03:09", "throughput": 1033.5, "total_tokens": 3013088} {"current_steps": 33470, "total_steps": 76960, "loss": 0.1825, "lr": 3.477725396497257e-05, "epoch": 8.698024948024948, "percentage": 43.49, "elapsed_time": "0:48:35", "remaining_time": "1:03:08", "throughput": 1033.51, "total_tokens": 3013536} {"current_steps": 33475, "total_steps": 76960, "loss": 0.169, "lr": 3.477203568501648e-05, "epoch": 8.699324324324325, "percentage": 43.5, "elapsed_time": "0:48:36", "remaining_time": "1:03:08", "throughput": 1033.51, "total_tokens": 3013984} {"current_steps": 33480, "total_steps": 76960, "loss": 0.2311, "lr": 3.476681690247522e-05, "epoch": 8.700623700623701, "percentage": 43.5, "elapsed_time": "0:48:36", "remaining_time": "1:03:07", "throughput": 1033.54, "total_tokens": 3014496} {"current_steps": 33485, "total_steps": 76960, "loss": 0.2474, "lr": 3.476159761761722e-05, "epoch": 8.701923076923077, "percentage": 43.51, "elapsed_time": "0:48:37", "remaining_time": "1:03:07", "throughput": 1033.55, "total_tokens": 3014960} {"current_steps": 33490, "total_steps": 76960, "loss": 0.4243, "lr": 3.4756377830710895e-05, "epoch": 8.703222453222454, "percentage": 43.52, "elapsed_time": "0:48:37", "remaining_time": "1:03:06", "throughput": 1033.57, "total_tokens": 3015424} {"current_steps": 33495, "total_steps": 76960, "loss": 0.3634, "lr": 3.4751157542024714e-05, "epoch": 8.704521829521829, "percentage": 43.52, "elapsed_time": "0:48:37", "remaining_time": "1:03:06", "throughput": 1033.56, "total_tokens": 3015840} {"current_steps": 33500, "total_steps": 76960, "loss": 0.1328, "lr": 3.474593675182715e-05, "epoch": 8.705821205821206, "percentage": 43.53, "elapsed_time": "0:48:38", "remaining_time": "1:03:05", "throughput": 1033.58, "total_tokens": 3016320} {"current_steps": 33505, "total_steps": 76960, "loss": 0.291, "lr": 3.474071546038673e-05, "epoch": 8.707120582120583, "percentage": 43.54, "elapsed_time": "0:48:38", "remaining_time": "1:03:05", "throughput": 1033.59, "total_tokens": 3016784} {"current_steps": 33510, "total_steps": 76960, "loss": 0.3183, "lr": 3.473549366797197e-05, "epoch": 8.708419958419958, "percentage": 43.54, "elapsed_time": "0:48:39", "remaining_time": "1:03:05", "throughput": 1033.59, "total_tokens": 3017216} {"current_steps": 33515, "total_steps": 76960, "loss": 0.2793, "lr": 3.473027137485146e-05, "epoch": 8.709719334719335, "percentage": 43.55, "elapsed_time": "0:48:39", "remaining_time": "1:03:04", "throughput": 1033.59, "total_tokens": 3017648} {"current_steps": 33520, "total_steps": 76960, "loss": 0.2173, "lr": 3.472504858129375e-05, "epoch": 8.711018711018712, "percentage": 43.56, "elapsed_time": "0:48:39", "remaining_time": "1:03:04", "throughput": 1033.6, "total_tokens": 3018096} {"current_steps": 33525, "total_steps": 76960, "loss": 0.27, "lr": 3.471982528756749e-05, "epoch": 8.712318087318087, "percentage": 43.56, "elapsed_time": "0:48:40", "remaining_time": "1:03:03", "throughput": 1033.6, "total_tokens": 3018544} {"current_steps": 33530, "total_steps": 76960, "loss": 0.153, "lr": 3.4714601493941304e-05, "epoch": 8.713617463617464, "percentage": 43.57, "elapsed_time": "0:48:40", "remaining_time": "1:03:03", "throughput": 1033.59, "total_tokens": 3018944} {"current_steps": 33535, "total_steps": 76960, "loss": 0.3602, "lr": 3.470937720068384e-05, "epoch": 8.71491683991684, "percentage": 43.57, "elapsed_time": "0:48:41", "remaining_time": "1:03:02", "throughput": 1033.59, "total_tokens": 3019376} {"current_steps": 33540, "total_steps": 76960, "loss": 0.2855, "lr": 3.470415240806381e-05, "epoch": 8.716216216216216, "percentage": 43.58, "elapsed_time": "0:48:41", "remaining_time": "1:03:02", "throughput": 1033.6, "total_tokens": 3019840} {"current_steps": 33545, "total_steps": 76960, "loss": 0.1746, "lr": 3.4698927116349924e-05, "epoch": 8.717515592515593, "percentage": 43.59, "elapsed_time": "0:48:42", "remaining_time": "1:03:01", "throughput": 1033.6, "total_tokens": 3020272} {"current_steps": 33550, "total_steps": 76960, "loss": 0.1622, "lr": 3.4693701325810924e-05, "epoch": 8.71881496881497, "percentage": 43.59, "elapsed_time": "0:48:42", "remaining_time": "1:03:01", "throughput": 1033.6, "total_tokens": 3020704} {"current_steps": 33555, "total_steps": 76960, "loss": 0.3737, "lr": 3.4688475036715575e-05, "epoch": 8.720114345114345, "percentage": 43.6, "elapsed_time": "0:48:42", "remaining_time": "1:03:00", "throughput": 1033.6, "total_tokens": 3021120} {"current_steps": 33560, "total_steps": 76960, "loss": 0.3818, "lr": 3.4683248249332664e-05, "epoch": 8.721413721413722, "percentage": 43.61, "elapsed_time": "0:48:43", "remaining_time": "1:03:00", "throughput": 1033.6, "total_tokens": 3021552} {"current_steps": 33565, "total_steps": 76960, "loss": 0.2963, "lr": 3.467802096393103e-05, "epoch": 8.722713097713097, "percentage": 43.61, "elapsed_time": "0:48:43", "remaining_time": "1:03:00", "throughput": 1033.61, "total_tokens": 3022000} {"current_steps": 33570, "total_steps": 76960, "loss": 0.2321, "lr": 3.46727931807795e-05, "epoch": 8.724012474012474, "percentage": 43.62, "elapsed_time": "0:48:44", "remaining_time": "1:02:59", "throughput": 1033.62, "total_tokens": 3022464} {"current_steps": 33575, "total_steps": 76960, "loss": 0.2488, "lr": 3.4667564900146956e-05, "epoch": 8.72531185031185, "percentage": 43.63, "elapsed_time": "0:48:44", "remaining_time": "1:02:59", "throughput": 1033.63, "total_tokens": 3022928} {"current_steps": 33580, "total_steps": 76960, "loss": 0.205, "lr": 3.4662336122302274e-05, "epoch": 8.726611226611226, "percentage": 43.63, "elapsed_time": "0:48:44", "remaining_time": "1:02:58", "throughput": 1033.62, "total_tokens": 3023344} {"current_steps": 33585, "total_steps": 76960, "loss": 0.2259, "lr": 3.46571068475144e-05, "epoch": 8.727910602910603, "percentage": 43.64, "elapsed_time": "0:48:45", "remaining_time": "1:02:58", "throughput": 1033.63, "total_tokens": 3023792} {"current_steps": 33590, "total_steps": 76960, "loss": 0.1998, "lr": 3.465187707605226e-05, "epoch": 8.72920997920998, "percentage": 43.65, "elapsed_time": "0:48:45", "remaining_time": "1:02:57", "throughput": 1033.63, "total_tokens": 3024240} {"current_steps": 33595, "total_steps": 76960, "loss": 0.2245, "lr": 3.464664680818483e-05, "epoch": 8.730509355509355, "percentage": 43.65, "elapsed_time": "0:48:46", "remaining_time": "1:02:57", "throughput": 1033.66, "total_tokens": 3024736} {"current_steps": 33600, "total_steps": 76960, "loss": 0.1148, "lr": 3.464141604418112e-05, "epoch": 8.731808731808732, "percentage": 43.66, "elapsed_time": "0:48:46", "remaining_time": "1:02:56", "throughput": 1033.65, "total_tokens": 3025152} {"current_steps": 33605, "total_steps": 76960, "loss": 0.2338, "lr": 3.463618478431014e-05, "epoch": 8.733108108108109, "percentage": 43.67, "elapsed_time": "0:48:47", "remaining_time": "1:02:56", "throughput": 1033.65, "total_tokens": 3025584} {"current_steps": 33610, "total_steps": 76960, "loss": 0.1387, "lr": 3.463095302884094e-05, "epoch": 8.734407484407484, "percentage": 43.67, "elapsed_time": "0:48:47", "remaining_time": "1:02:55", "throughput": 1033.65, "total_tokens": 3026000} {"current_steps": 33615, "total_steps": 76960, "loss": 0.2663, "lr": 3.4625720778042606e-05, "epoch": 8.73570686070686, "percentage": 43.68, "elapsed_time": "0:48:47", "remaining_time": "1:02:55", "throughput": 1033.65, "total_tokens": 3026448} {"current_steps": 33620, "total_steps": 76960, "loss": 0.3308, "lr": 3.462048803218423e-05, "epoch": 8.737006237006238, "percentage": 43.69, "elapsed_time": "0:48:48", "remaining_time": "1:02:54", "throughput": 1033.66, "total_tokens": 3026912} {"current_steps": 33625, "total_steps": 76960, "loss": 0.3827, "lr": 3.461525479153493e-05, "epoch": 8.738305613305613, "percentage": 43.69, "elapsed_time": "0:48:48", "remaining_time": "1:02:54", "throughput": 1033.69, "total_tokens": 3027408} {"current_steps": 33630, "total_steps": 76960, "loss": 0.2918, "lr": 3.461002105636387e-05, "epoch": 8.73960498960499, "percentage": 43.7, "elapsed_time": "0:48:49", "remaining_time": "1:02:54", "throughput": 1033.69, "total_tokens": 3027840} {"current_steps": 33635, "total_steps": 76960, "loss": 0.1991, "lr": 3.4604786826940214e-05, "epoch": 8.740904365904367, "percentage": 43.7, "elapsed_time": "0:48:49", "remaining_time": "1:02:53", "throughput": 1033.7, "total_tokens": 3028304} {"current_steps": 33640, "total_steps": 76960, "loss": 0.1593, "lr": 3.4599552103533164e-05, "epoch": 8.742203742203742, "percentage": 43.71, "elapsed_time": "0:48:49", "remaining_time": "1:02:53", "throughput": 1033.69, "total_tokens": 3028720} {"current_steps": 33645, "total_steps": 76960, "loss": 0.3003, "lr": 3.459431688641196e-05, "epoch": 8.743503118503119, "percentage": 43.72, "elapsed_time": "0:48:50", "remaining_time": "1:02:52", "throughput": 1033.7, "total_tokens": 3029184} {"current_steps": 33650, "total_steps": 76960, "loss": 0.1583, "lr": 3.458908117584584e-05, "epoch": 8.744802494802494, "percentage": 43.72, "elapsed_time": "0:48:50", "remaining_time": "1:02:52", "throughput": 1033.72, "total_tokens": 3029648} {"current_steps": 33655, "total_steps": 76960, "loss": 0.299, "lr": 3.45838449721041e-05, "epoch": 8.746101871101871, "percentage": 43.73, "elapsed_time": "0:48:51", "remaining_time": "1:02:51", "throughput": 1033.73, "total_tokens": 3030112} {"current_steps": 33660, "total_steps": 76960, "loss": 0.3283, "lr": 3.457860827545601e-05, "epoch": 8.747401247401248, "percentage": 43.74, "elapsed_time": "0:48:51", "remaining_time": "1:02:51", "throughput": 1033.74, "total_tokens": 3030592} {"current_steps": 33665, "total_steps": 76960, "loss": 0.2203, "lr": 3.4573371086170936e-05, "epoch": 8.748700623700623, "percentage": 43.74, "elapsed_time": "0:48:52", "remaining_time": "1:02:50", "throughput": 1033.77, "total_tokens": 3031088} {"current_steps": 33670, "total_steps": 76960, "loss": 0.3237, "lr": 3.456813340451821e-05, "epoch": 8.75, "percentage": 43.75, "elapsed_time": "0:48:52", "remaining_time": "1:02:50", "throughput": 1033.76, "total_tokens": 3031504} {"current_steps": 33675, "total_steps": 76960, "loss": 0.2265, "lr": 3.456289523076721e-05, "epoch": 8.751299376299377, "percentage": 43.76, "elapsed_time": "0:48:52", "remaining_time": "1:02:49", "throughput": 1033.78, "total_tokens": 3031984} {"current_steps": 33680, "total_steps": 76960, "loss": 0.2409, "lr": 3.4557656565187344e-05, "epoch": 8.752598752598752, "percentage": 43.76, "elapsed_time": "0:48:53", "remaining_time": "1:02:49", "throughput": 1033.78, "total_tokens": 3032416} {"current_steps": 33685, "total_steps": 76960, "loss": 0.2309, "lr": 3.455241740804805e-05, "epoch": 8.753898128898129, "percentage": 43.77, "elapsed_time": "0:48:53", "remaining_time": "1:02:48", "throughput": 1033.79, "total_tokens": 3032864} {"current_steps": 33690, "total_steps": 76960, "loss": 0.2447, "lr": 3.454717775961878e-05, "epoch": 8.755197505197506, "percentage": 43.78, "elapsed_time": "0:48:54", "remaining_time": "1:02:48", "throughput": 1033.78, "total_tokens": 3033264} {"current_steps": 33695, "total_steps": 76960, "loss": 0.2089, "lr": 3.4541937620169e-05, "epoch": 8.756496881496881, "percentage": 43.78, "elapsed_time": "0:48:54", "remaining_time": "1:02:48", "throughput": 1033.78, "total_tokens": 3033712} {"current_steps": 33700, "total_steps": 76960, "loss": 0.2445, "lr": 3.4536696989968226e-05, "epoch": 8.757796257796258, "percentage": 43.79, "elapsed_time": "0:48:54", "remaining_time": "1:02:47", "throughput": 1033.8, "total_tokens": 3034192} {"current_steps": 33705, "total_steps": 76960, "loss": 0.2819, "lr": 3.453145586928599e-05, "epoch": 8.759095634095633, "percentage": 43.8, "elapsed_time": "0:48:55", "remaining_time": "1:02:47", "throughput": 1033.8, "total_tokens": 3034624} {"current_steps": 33710, "total_steps": 76960, "loss": 0.2454, "lr": 3.4526214258391846e-05, "epoch": 8.76039501039501, "percentage": 43.8, "elapsed_time": "0:48:55", "remaining_time": "1:02:46", "throughput": 1033.8, "total_tokens": 3035056} {"current_steps": 33715, "total_steps": 76960, "loss": 0.228, "lr": 3.452097215755537e-05, "epoch": 8.761694386694387, "percentage": 43.81, "elapsed_time": "0:48:56", "remaining_time": "1:02:46", "throughput": 1033.81, "total_tokens": 3035520} {"current_steps": 33720, "total_steps": 76960, "loss": 0.2622, "lr": 3.451572956704619e-05, "epoch": 8.762993762993762, "percentage": 43.81, "elapsed_time": "0:48:56", "remaining_time": "1:02:45", "throughput": 1033.82, "total_tokens": 3035968} {"current_steps": 33725, "total_steps": 76960, "loss": 0.3223, "lr": 3.4510486487133916e-05, "epoch": 8.76429313929314, "percentage": 43.82, "elapsed_time": "0:48:57", "remaining_time": "1:02:45", "throughput": 1033.84, "total_tokens": 3036464} {"current_steps": 33730, "total_steps": 76960, "loss": 0.2832, "lr": 3.45052429180882e-05, "epoch": 8.765592515592516, "percentage": 43.83, "elapsed_time": "0:48:57", "remaining_time": "1:02:44", "throughput": 1033.86, "total_tokens": 3036944} {"current_steps": 33735, "total_steps": 76960, "loss": 0.3494, "lr": 3.4499998860178736e-05, "epoch": 8.766891891891891, "percentage": 43.83, "elapsed_time": "0:48:57", "remaining_time": "1:02:44", "throughput": 1033.88, "total_tokens": 3037440} {"current_steps": 33740, "total_steps": 76960, "loss": 0.2598, "lr": 3.4494754313675235e-05, "epoch": 8.768191268191268, "percentage": 43.84, "elapsed_time": "0:48:58", "remaining_time": "1:02:43", "throughput": 1033.88, "total_tokens": 3037888} {"current_steps": 33745, "total_steps": 76960, "loss": 0.2954, "lr": 3.4489509278847414e-05, "epoch": 8.769490644490645, "percentage": 43.85, "elapsed_time": "0:48:58", "remaining_time": "1:02:43", "throughput": 1033.88, "total_tokens": 3038304} {"current_steps": 33750, "total_steps": 76960, "loss": 0.2138, "lr": 3.448426375596504e-05, "epoch": 8.77079002079002, "percentage": 43.85, "elapsed_time": "0:48:59", "remaining_time": "1:02:42", "throughput": 1033.89, "total_tokens": 3038752} {"current_steps": 33755, "total_steps": 76960, "loss": 0.3135, "lr": 3.447901774529789e-05, "epoch": 8.772089397089397, "percentage": 43.86, "elapsed_time": "0:48:59", "remaining_time": "1:02:42", "throughput": 1033.89, "total_tokens": 3039184} {"current_steps": 33760, "total_steps": 76960, "loss": 0.2304, "lr": 3.447377124711578e-05, "epoch": 8.773388773388774, "percentage": 43.87, "elapsed_time": "0:48:59", "remaining_time": "1:02:42", "throughput": 1033.89, "total_tokens": 3039632} {"current_steps": 33765, "total_steps": 76960, "loss": 0.3288, "lr": 3.446852426168854e-05, "epoch": 8.77468814968815, "percentage": 43.87, "elapsed_time": "0:49:00", "remaining_time": "1:02:41", "throughput": 1033.89, "total_tokens": 3040064} {"current_steps": 33770, "total_steps": 76960, "loss": 0.2504, "lr": 3.446327678928602e-05, "epoch": 8.775987525987526, "percentage": 43.88, "elapsed_time": "0:49:00", "remaining_time": "1:02:41", "throughput": 1033.89, "total_tokens": 3040496} {"current_steps": 33775, "total_steps": 76960, "loss": 0.248, "lr": 3.4458028830178114e-05, "epoch": 8.777286902286903, "percentage": 43.89, "elapsed_time": "0:49:01", "remaining_time": "1:02:40", "throughput": 1033.89, "total_tokens": 3040912} {"current_steps": 33780, "total_steps": 76960, "loss": 0.2463, "lr": 3.4452780384634716e-05, "epoch": 8.778586278586278, "percentage": 43.89, "elapsed_time": "0:49:01", "remaining_time": "1:02:40", "throughput": 1033.9, "total_tokens": 3041376} {"current_steps": 33785, "total_steps": 76960, "loss": 0.2554, "lr": 3.4447531452925766e-05, "epoch": 8.779885654885655, "percentage": 43.9, "elapsed_time": "0:49:02", "remaining_time": "1:02:39", "throughput": 1033.89, "total_tokens": 3041776} {"current_steps": 33790, "total_steps": 76960, "loss": 0.227, "lr": 3.4442282035321224e-05, "epoch": 8.78118503118503, "percentage": 43.91, "elapsed_time": "0:49:02", "remaining_time": "1:02:39", "throughput": 1033.9, "total_tokens": 3042240} {"current_steps": 33795, "total_steps": 76960, "loss": 0.2311, "lr": 3.443703213209107e-05, "epoch": 8.782484407484407, "percentage": 43.91, "elapsed_time": "0:49:02", "remaining_time": "1:02:38", "throughput": 1033.91, "total_tokens": 3042704} {"current_steps": 33800, "total_steps": 76960, "loss": 0.3009, "lr": 3.4431781743505314e-05, "epoch": 8.783783783783784, "percentage": 43.92, "elapsed_time": "0:49:03", "remaining_time": "1:02:38", "throughput": 1033.94, "total_tokens": 3043216} {"current_steps": 33805, "total_steps": 76960, "loss": 0.2873, "lr": 3.442653086983398e-05, "epoch": 8.78508316008316, "percentage": 43.93, "elapsed_time": "0:49:03", "remaining_time": "1:02:37", "throughput": 1033.94, "total_tokens": 3043648} {"current_steps": 33810, "total_steps": 76960, "loss": 0.3175, "lr": 3.442127951134714e-05, "epoch": 8.786382536382536, "percentage": 43.93, "elapsed_time": "0:49:04", "remaining_time": "1:02:37", "throughput": 1033.96, "total_tokens": 3044144} {"current_steps": 33815, "total_steps": 76960, "loss": 0.2812, "lr": 3.4416027668314854e-05, "epoch": 8.787681912681913, "percentage": 43.94, "elapsed_time": "0:49:04", "remaining_time": "1:02:37", "throughput": 1033.97, "total_tokens": 3044592} {"current_steps": 33820, "total_steps": 76960, "loss": 0.2374, "lr": 3.441077534100725e-05, "epoch": 8.788981288981288, "percentage": 43.94, "elapsed_time": "0:49:04", "remaining_time": "1:02:36", "throughput": 1033.97, "total_tokens": 3045040} {"current_steps": 33825, "total_steps": 76960, "loss": 0.2253, "lr": 3.4405522529694454e-05, "epoch": 8.790280665280665, "percentage": 43.95, "elapsed_time": "0:49:05", "remaining_time": "1:02:36", "throughput": 1033.97, "total_tokens": 3045472} {"current_steps": 33830, "total_steps": 76960, "loss": 0.3245, "lr": 3.440026923464662e-05, "epoch": 8.791580041580042, "percentage": 43.96, "elapsed_time": "0:49:05", "remaining_time": "1:02:35", "throughput": 1033.99, "total_tokens": 3045936} {"current_steps": 33835, "total_steps": 76960, "loss": 0.2927, "lr": 3.4395015456133937e-05, "epoch": 8.792879417879417, "percentage": 43.96, "elapsed_time": "0:49:06", "remaining_time": "1:02:35", "throughput": 1033.99, "total_tokens": 3046384} {"current_steps": 33840, "total_steps": 76960, "loss": 0.3357, "lr": 3.43897611944266e-05, "epoch": 8.794178794178794, "percentage": 43.97, "elapsed_time": "0:49:06", "remaining_time": "1:02:34", "throughput": 1033.99, "total_tokens": 3046816} {"current_steps": 33845, "total_steps": 76960, "loss": 0.2725, "lr": 3.4384506449794857e-05, "epoch": 8.795478170478171, "percentage": 43.98, "elapsed_time": "0:49:07", "remaining_time": "1:02:34", "throughput": 1034.01, "total_tokens": 3047280} {"current_steps": 33850, "total_steps": 76960, "loss": 0.2786, "lr": 3.437925122250896e-05, "epoch": 8.796777546777546, "percentage": 43.98, "elapsed_time": "0:49:07", "remaining_time": "1:02:33", "throughput": 1034.02, "total_tokens": 3047744} {"current_steps": 33855, "total_steps": 76960, "loss": 0.2652, "lr": 3.437399551283917e-05, "epoch": 8.798076923076923, "percentage": 43.99, "elapsed_time": "0:49:07", "remaining_time": "1:02:33", "throughput": 1034.04, "total_tokens": 3048240} {"current_steps": 33860, "total_steps": 76960, "loss": 0.3142, "lr": 3.436873932105581e-05, "epoch": 8.799376299376299, "percentage": 44.0, "elapsed_time": "0:49:08", "remaining_time": "1:02:32", "throughput": 1034.05, "total_tokens": 3048720} {"current_steps": 33865, "total_steps": 76960, "loss": 0.2436, "lr": 3.436348264742922e-05, "epoch": 8.800675675675675, "percentage": 44.0, "elapsed_time": "0:49:08", "remaining_time": "1:02:32", "throughput": 1034.06, "total_tokens": 3049184} {"current_steps": 33870, "total_steps": 76960, "loss": 0.303, "lr": 3.4358225492229746e-05, "epoch": 8.801975051975052, "percentage": 44.01, "elapsed_time": "0:49:09", "remaining_time": "1:02:31", "throughput": 1034.07, "total_tokens": 3049648} {"current_steps": 33875, "total_steps": 76960, "loss": 0.2664, "lr": 3.435296785572776e-05, "epoch": 8.803274428274428, "percentage": 44.02, "elapsed_time": "0:49:09", "remaining_time": "1:02:31", "throughput": 1034.09, "total_tokens": 3050128} {"current_steps": 33880, "total_steps": 76960, "loss": 0.237, "lr": 3.434770973819368e-05, "epoch": 8.804573804573804, "percentage": 44.02, "elapsed_time": "0:49:09", "remaining_time": "1:02:31", "throughput": 1034.11, "total_tokens": 3050608} {"current_steps": 33885, "total_steps": 76960, "loss": 0.2293, "lr": 3.434245113989793e-05, "epoch": 8.805873180873181, "percentage": 44.03, "elapsed_time": "0:49:10", "remaining_time": "1:02:30", "throughput": 1034.12, "total_tokens": 3051088} {"current_steps": 33890, "total_steps": 76960, "loss": 0.2466, "lr": 3.4337192061110966e-05, "epoch": 8.807172557172557, "percentage": 44.04, "elapsed_time": "0:49:10", "remaining_time": "1:02:30", "throughput": 1034.13, "total_tokens": 3051536} {"current_steps": 33895, "total_steps": 76960, "loss": 0.2682, "lr": 3.433193250210327e-05, "epoch": 8.808471933471933, "percentage": 44.04, "elapsed_time": "0:49:11", "remaining_time": "1:02:29", "throughput": 1034.14, "total_tokens": 3051984} {"current_steps": 33900, "total_steps": 76960, "loss": 0.3506, "lr": 3.4326672463145345e-05, "epoch": 8.80977130977131, "percentage": 44.05, "elapsed_time": "0:49:11", "remaining_time": "1:02:29", "throughput": 1034.14, "total_tokens": 3052432} {"current_steps": 33905, "total_steps": 76960, "loss": 0.2344, "lr": 3.432141194450772e-05, "epoch": 8.811070686070686, "percentage": 44.06, "elapsed_time": "0:49:12", "remaining_time": "1:02:28", "throughput": 1034.13, "total_tokens": 3052832} {"current_steps": 33910, "total_steps": 76960, "loss": 0.1343, "lr": 3.4316150946460946e-05, "epoch": 8.812370062370062, "percentage": 44.06, "elapsed_time": "0:49:12", "remaining_time": "1:02:28", "throughput": 1034.13, "total_tokens": 3053264} {"current_steps": 33915, "total_steps": 76960, "loss": 0.3319, "lr": 3.43108894692756e-05, "epoch": 8.81366943866944, "percentage": 44.07, "elapsed_time": "0:49:12", "remaining_time": "1:02:27", "throughput": 1034.14, "total_tokens": 3053728} {"current_steps": 33920, "total_steps": 76960, "loss": 0.2104, "lr": 3.430562751322229e-05, "epoch": 8.814968814968815, "percentage": 44.07, "elapsed_time": "0:49:13", "remaining_time": "1:02:27", "throughput": 1034.15, "total_tokens": 3054192} {"current_steps": 33925, "total_steps": 76960, "loss": 0.2003, "lr": 3.430036507857164e-05, "epoch": 8.816268191268192, "percentage": 44.08, "elapsed_time": "0:49:13", "remaining_time": "1:02:26", "throughput": 1034.17, "total_tokens": 3054688} {"current_steps": 33930, "total_steps": 76960, "loss": 0.2271, "lr": 3.429510216559429e-05, "epoch": 8.817567567567568, "percentage": 44.09, "elapsed_time": "0:49:14", "remaining_time": "1:02:26", "throughput": 1034.19, "total_tokens": 3055152} {"current_steps": 33935, "total_steps": 76960, "loss": 0.2581, "lr": 3.428983877456095e-05, "epoch": 8.818866943866944, "percentage": 44.09, "elapsed_time": "0:49:14", "remaining_time": "1:02:26", "throughput": 1034.19, "total_tokens": 3055584} {"current_steps": 33940, "total_steps": 76960, "loss": 0.2079, "lr": 3.4284574905742294e-05, "epoch": 8.82016632016632, "percentage": 44.1, "elapsed_time": "0:49:14", "remaining_time": "1:02:25", "throughput": 1034.2, "total_tokens": 3056048} {"current_steps": 33945, "total_steps": 76960, "loss": 0.3189, "lr": 3.427931055940905e-05, "epoch": 8.821465696465696, "percentage": 44.11, "elapsed_time": "0:49:15", "remaining_time": "1:02:25", "throughput": 1034.21, "total_tokens": 3056512} {"current_steps": 33950, "total_steps": 76960, "loss": 0.4208, "lr": 3.427404573583197e-05, "epoch": 8.822765072765073, "percentage": 44.11, "elapsed_time": "0:49:15", "remaining_time": "1:02:24", "throughput": 1034.21, "total_tokens": 3056960} {"current_steps": 33955, "total_steps": 76960, "loss": 0.1929, "lr": 3.426878043528185e-05, "epoch": 8.82406444906445, "percentage": 44.12, "elapsed_time": "0:49:16", "remaining_time": "1:02:24", "throughput": 1034.21, "total_tokens": 3057392} {"current_steps": 33960, "total_steps": 76960, "loss": 0.208, "lr": 3.426351465802945e-05, "epoch": 8.825363825363825, "percentage": 44.13, "elapsed_time": "0:49:16", "remaining_time": "1:02:23", "throughput": 1034.23, "total_tokens": 3057856} {"current_steps": 33965, "total_steps": 76960, "loss": 0.2923, "lr": 3.425824840434562e-05, "epoch": 8.826663201663202, "percentage": 44.13, "elapsed_time": "0:49:17", "remaining_time": "1:02:23", "throughput": 1034.23, "total_tokens": 3058304} {"current_steps": 33970, "total_steps": 76960, "loss": 0.1987, "lr": 3.425298167450121e-05, "epoch": 8.827962577962579, "percentage": 44.14, "elapsed_time": "0:49:17", "remaining_time": "1:02:22", "throughput": 1034.25, "total_tokens": 3058784} {"current_steps": 33975, "total_steps": 76960, "loss": 0.1985, "lr": 3.424771446876709e-05, "epoch": 8.829261954261954, "percentage": 44.15, "elapsed_time": "0:49:17", "remaining_time": "1:02:22", "throughput": 1034.25, "total_tokens": 3059232} {"current_steps": 33980, "total_steps": 76960, "loss": 0.1837, "lr": 3.424244678741414e-05, "epoch": 8.83056133056133, "percentage": 44.15, "elapsed_time": "0:49:18", "remaining_time": "1:02:21", "throughput": 1034.27, "total_tokens": 3059696} {"current_steps": 33985, "total_steps": 76960, "loss": 0.3177, "lr": 3.4237178630713314e-05, "epoch": 8.831860706860708, "percentage": 44.16, "elapsed_time": "0:49:18", "remaining_time": "1:02:21", "throughput": 1034.28, "total_tokens": 3060160} {"current_steps": 33990, "total_steps": 76960, "loss": 0.2768, "lr": 3.423190999893553e-05, "epoch": 8.833160083160083, "percentage": 44.17, "elapsed_time": "0:49:19", "remaining_time": "1:02:20", "throughput": 1034.29, "total_tokens": 3060624} {"current_steps": 33995, "total_steps": 76960, "loss": 0.209, "lr": 3.4226640892351776e-05, "epoch": 8.83445945945946, "percentage": 44.17, "elapsed_time": "0:49:19", "remaining_time": "1:02:20", "throughput": 1034.29, "total_tokens": 3061072} {"current_steps": 34000, "total_steps": 76960, "loss": 0.3137, "lr": 3.422137131123303e-05, "epoch": 8.835758835758837, "percentage": 44.18, "elapsed_time": "0:49:19", "remaining_time": "1:02:20", "throughput": 1034.31, "total_tokens": 3061552} {"current_steps": 34005, "total_steps": 76960, "loss": 0.2284, "lr": 3.421610125585032e-05, "epoch": 8.837058212058212, "percentage": 44.19, "elapsed_time": "0:49:20", "remaining_time": "1:02:19", "throughput": 1034.32, "total_tokens": 3062000} {"current_steps": 34010, "total_steps": 76960, "loss": 0.2182, "lr": 3.421083072647471e-05, "epoch": 8.838357588357589, "percentage": 44.19, "elapsed_time": "0:49:20", "remaining_time": "1:02:19", "throughput": 1034.33, "total_tokens": 3062464} {"current_steps": 34015, "total_steps": 76960, "loss": 0.2076, "lr": 3.4205559723377234e-05, "epoch": 8.839656964656964, "percentage": 44.2, "elapsed_time": "0:49:21", "remaining_time": "1:02:18", "throughput": 1034.33, "total_tokens": 3062896} {"current_steps": 34020, "total_steps": 76960, "loss": 0.332, "lr": 3.4200288246829005e-05, "epoch": 8.84095634095634, "percentage": 44.2, "elapsed_time": "0:49:21", "remaining_time": "1:02:18", "throughput": 1034.33, "total_tokens": 3063328} {"current_steps": 34025, "total_steps": 76960, "loss": 0.19, "lr": 3.4195016297101134e-05, "epoch": 8.842255717255718, "percentage": 44.21, "elapsed_time": "0:49:22", "remaining_time": "1:02:17", "throughput": 1034.33, "total_tokens": 3063760} {"current_steps": 34030, "total_steps": 76960, "loss": 0.2349, "lr": 3.4189743874464766e-05, "epoch": 8.843555093555093, "percentage": 44.22, "elapsed_time": "0:49:22", "remaining_time": "1:02:17", "throughput": 1034.33, "total_tokens": 3064192} {"current_steps": 34035, "total_steps": 76960, "loss": 0.2533, "lr": 3.4184470979191076e-05, "epoch": 8.84485446985447, "percentage": 44.22, "elapsed_time": "0:49:22", "remaining_time": "1:02:16", "throughput": 1034.33, "total_tokens": 3064640} {"current_steps": 34040, "total_steps": 76960, "loss": 0.3097, "lr": 3.4179197611551227e-05, "epoch": 8.846153846153847, "percentage": 44.23, "elapsed_time": "0:49:23", "remaining_time": "1:02:16", "throughput": 1034.33, "total_tokens": 3065072} {"current_steps": 34045, "total_steps": 76960, "loss": 0.2361, "lr": 3.417392377181646e-05, "epoch": 8.847453222453222, "percentage": 44.24, "elapsed_time": "0:49:23", "remaining_time": "1:02:15", "throughput": 1034.32, "total_tokens": 3065472} {"current_steps": 34050, "total_steps": 76960, "loss": 0.2379, "lr": 3.416864946025801e-05, "epoch": 8.848752598752599, "percentage": 44.24, "elapsed_time": "0:49:24", "remaining_time": "1:02:15", "throughput": 1034.32, "total_tokens": 3065888} {"current_steps": 34055, "total_steps": 76960, "loss": 0.2687, "lr": 3.4163374677147114e-05, "epoch": 8.850051975051976, "percentage": 44.25, "elapsed_time": "0:49:24", "remaining_time": "1:02:14", "throughput": 1034.32, "total_tokens": 3066336} {"current_steps": 34060, "total_steps": 76960, "loss": 0.2803, "lr": 3.415809942275509e-05, "epoch": 8.85135135135135, "percentage": 44.26, "elapsed_time": "0:49:24", "remaining_time": "1:02:14", "throughput": 1034.33, "total_tokens": 3066784} {"current_steps": 34065, "total_steps": 76960, "loss": 0.2721, "lr": 3.415282369735324e-05, "epoch": 8.852650727650728, "percentage": 44.26, "elapsed_time": "0:49:25", "remaining_time": "1:02:14", "throughput": 1034.34, "total_tokens": 3067248} {"current_steps": 34070, "total_steps": 76960, "loss": 0.2295, "lr": 3.414754750121289e-05, "epoch": 8.853950103950105, "percentage": 44.27, "elapsed_time": "0:49:25", "remaining_time": "1:02:13", "throughput": 1034.35, "total_tokens": 3067712} {"current_steps": 34075, "total_steps": 76960, "loss": 0.2612, "lr": 3.414227083460541e-05, "epoch": 8.85524948024948, "percentage": 44.28, "elapsed_time": "0:49:26", "remaining_time": "1:02:13", "throughput": 1034.36, "total_tokens": 3068160} {"current_steps": 34080, "total_steps": 76960, "loss": 0.3209, "lr": 3.4136993697802184e-05, "epoch": 8.856548856548857, "percentage": 44.28, "elapsed_time": "0:49:26", "remaining_time": "1:02:12", "throughput": 1034.36, "total_tokens": 3068608} {"current_steps": 34085, "total_steps": 76960, "loss": 0.2452, "lr": 3.4131716091074617e-05, "epoch": 8.857848232848234, "percentage": 44.29, "elapsed_time": "0:49:27", "remaining_time": "1:02:12", "throughput": 1034.36, "total_tokens": 3069040} {"current_steps": 34090, "total_steps": 76960, "loss": 0.2514, "lr": 3.4126438014694134e-05, "epoch": 8.859147609147609, "percentage": 44.3, "elapsed_time": "0:49:27", "remaining_time": "1:02:11", "throughput": 1034.39, "total_tokens": 3069536} {"current_steps": 34095, "total_steps": 76960, "loss": 0.2495, "lr": 3.412115946893221e-05, "epoch": 8.860446985446986, "percentage": 44.3, "elapsed_time": "0:49:27", "remaining_time": "1:02:11", "throughput": 1034.39, "total_tokens": 3069968} {"current_steps": 34100, "total_steps": 76960, "loss": 0.238, "lr": 3.4115880454060314e-05, "epoch": 8.861746361746361, "percentage": 44.31, "elapsed_time": "0:49:28", "remaining_time": "1:02:10", "throughput": 1034.39, "total_tokens": 3070400} {"current_steps": 34105, "total_steps": 76960, "loss": 0.2417, "lr": 3.411060097034995e-05, "epoch": 8.863045738045738, "percentage": 44.32, "elapsed_time": "0:49:28", "remaining_time": "1:02:10", "throughput": 1034.43, "total_tokens": 3070960} {"current_steps": 34110, "total_steps": 76960, "loss": 0.196, "lr": 3.4105321018072645e-05, "epoch": 8.864345114345115, "percentage": 44.32, "elapsed_time": "0:49:29", "remaining_time": "1:02:09", "throughput": 1034.44, "total_tokens": 3071424} {"current_steps": 34115, "total_steps": 76960, "loss": 0.1411, "lr": 3.410004059749996e-05, "epoch": 8.86564449064449, "percentage": 44.33, "elapsed_time": "0:49:29", "remaining_time": "1:02:09", "throughput": 1034.45, "total_tokens": 3071888} {"current_steps": 34120, "total_steps": 76960, "loss": 0.2146, "lr": 3.409475970890347e-05, "epoch": 8.866943866943867, "percentage": 44.33, "elapsed_time": "0:49:29", "remaining_time": "1:02:09", "throughput": 1034.45, "total_tokens": 3072304} {"current_steps": 34125, "total_steps": 76960, "loss": 0.2956, "lr": 3.408947835255476e-05, "epoch": 8.868243243243244, "percentage": 44.34, "elapsed_time": "0:49:30", "remaining_time": "1:02:08", "throughput": 1034.45, "total_tokens": 3072752} {"current_steps": 34130, "total_steps": 76960, "loss": 0.3847, "lr": 3.4084196528725484e-05, "epoch": 8.869542619542619, "percentage": 44.35, "elapsed_time": "0:49:30", "remaining_time": "1:02:08", "throughput": 1034.47, "total_tokens": 3073232} {"current_steps": 34135, "total_steps": 76960, "loss": 0.2325, "lr": 3.407891423768727e-05, "epoch": 8.870841995841996, "percentage": 44.35, "elapsed_time": "0:49:31", "remaining_time": "1:02:07", "throughput": 1034.48, "total_tokens": 3073680} {"current_steps": 34140, "total_steps": 76960, "loss": 0.256, "lr": 3.407363147971181e-05, "epoch": 8.872141372141373, "percentage": 44.36, "elapsed_time": "0:49:31", "remaining_time": "1:02:07", "throughput": 1034.48, "total_tokens": 3074128} {"current_steps": 34145, "total_steps": 76960, "loss": 0.3326, "lr": 3.4068348255070763e-05, "epoch": 8.873440748440748, "percentage": 44.37, "elapsed_time": "0:49:32", "remaining_time": "1:02:06", "throughput": 1034.48, "total_tokens": 3074544} {"current_steps": 34150, "total_steps": 76960, "loss": 0.2235, "lr": 3.4063064564035896e-05, "epoch": 8.874740124740125, "percentage": 44.37, "elapsed_time": "0:49:32", "remaining_time": "1:02:06", "throughput": 1034.48, "total_tokens": 3074976} {"current_steps": 34155, "total_steps": 76960, "loss": 0.241, "lr": 3.4057780406878934e-05, "epoch": 8.8760395010395, "percentage": 44.38, "elapsed_time": "0:49:32", "remaining_time": "1:02:05", "throughput": 1034.5, "total_tokens": 3075472} {"current_steps": 34160, "total_steps": 76960, "loss": 0.2757, "lr": 3.405249578387164e-05, "epoch": 8.877338877338877, "percentage": 44.39, "elapsed_time": "0:49:33", "remaining_time": "1:02:05", "throughput": 1034.51, "total_tokens": 3075920} {"current_steps": 34165, "total_steps": 76960, "loss": 0.1408, "lr": 3.404721069528581e-05, "epoch": 8.878638253638254, "percentage": 44.39, "elapsed_time": "0:49:33", "remaining_time": "1:02:04", "throughput": 1034.51, "total_tokens": 3076352} {"current_steps": 34170, "total_steps": 76960, "loss": 0.1663, "lr": 3.4041925141393284e-05, "epoch": 8.87993762993763, "percentage": 44.4, "elapsed_time": "0:49:34", "remaining_time": "1:02:04", "throughput": 1034.52, "total_tokens": 3076816} {"current_steps": 34175, "total_steps": 76960, "loss": 0.301, "lr": 3.403663912246587e-05, "epoch": 8.881237006237006, "percentage": 44.41, "elapsed_time": "0:49:34", "remaining_time": "1:02:03", "throughput": 1034.53, "total_tokens": 3077264} {"current_steps": 34180, "total_steps": 76960, "loss": 0.2572, "lr": 3.403135263877545e-05, "epoch": 8.882536382536383, "percentage": 44.41, "elapsed_time": "0:49:34", "remaining_time": "1:02:03", "throughput": 1034.54, "total_tokens": 3077744} {"current_steps": 34185, "total_steps": 76960, "loss": 0.2733, "lr": 3.402606569059392e-05, "epoch": 8.883835758835758, "percentage": 44.42, "elapsed_time": "0:49:35", "remaining_time": "1:02:03", "throughput": 1034.55, "total_tokens": 3078208} {"current_steps": 34190, "total_steps": 76960, "loss": 0.1797, "lr": 3.402077827819317e-05, "epoch": 8.885135135135135, "percentage": 44.43, "elapsed_time": "0:49:35", "remaining_time": "1:02:02", "throughput": 1034.56, "total_tokens": 3078672} {"current_steps": 34195, "total_steps": 76960, "loss": 0.285, "lr": 3.401549040184515e-05, "epoch": 8.886434511434512, "percentage": 44.43, "elapsed_time": "0:49:36", "remaining_time": "1:02:02", "throughput": 1034.58, "total_tokens": 3079152} {"current_steps": 34200, "total_steps": 76960, "loss": 0.1599, "lr": 3.4010202061821825e-05, "epoch": 8.887733887733887, "percentage": 44.44, "elapsed_time": "0:49:36", "remaining_time": "1:02:01", "throughput": 1034.58, "total_tokens": 3079600} {"current_steps": 34205, "total_steps": 76960, "loss": 0.279, "lr": 3.400491325839518e-05, "epoch": 8.889033264033264, "percentage": 44.45, "elapsed_time": "0:49:37", "remaining_time": "1:02:01", "throughput": 1034.58, "total_tokens": 3080032} {"current_steps": 34210, "total_steps": 76960, "loss": 0.2802, "lr": 3.399962399183721e-05, "epoch": 8.890332640332641, "percentage": 44.45, "elapsed_time": "0:49:37", "remaining_time": "1:02:00", "throughput": 1034.6, "total_tokens": 3080512} {"current_steps": 34215, "total_steps": 76960, "loss": 0.2297, "lr": 3.3994334262419955e-05, "epoch": 8.891632016632016, "percentage": 44.46, "elapsed_time": "0:49:37", "remaining_time": "1:02:00", "throughput": 1034.61, "total_tokens": 3080976} {"current_steps": 34220, "total_steps": 76960, "loss": 0.2362, "lr": 3.398904407041548e-05, "epoch": 8.892931392931393, "percentage": 44.46, "elapsed_time": "0:49:38", "remaining_time": "1:01:59", "throughput": 1034.62, "total_tokens": 3081424} {"current_steps": 34225, "total_steps": 76960, "loss": 0.3216, "lr": 3.3983753416095845e-05, "epoch": 8.89423076923077, "percentage": 44.47, "elapsed_time": "0:49:38", "remaining_time": "1:01:59", "throughput": 1034.61, "total_tokens": 3081840} {"current_steps": 34230, "total_steps": 76960, "loss": 0.2703, "lr": 3.397846229973317e-05, "epoch": 8.895530145530145, "percentage": 44.48, "elapsed_time": "0:49:39", "remaining_time": "1:01:58", "throughput": 1034.62, "total_tokens": 3082288} {"current_steps": 34235, "total_steps": 76960, "loss": 0.1291, "lr": 3.3973170721599565e-05, "epoch": 8.896829521829522, "percentage": 44.48, "elapsed_time": "0:49:39", "remaining_time": "1:01:58", "throughput": 1034.63, "total_tokens": 3082752} {"current_steps": 34240, "total_steps": 76960, "loss": 0.2346, "lr": 3.3967878681967216e-05, "epoch": 8.898128898128899, "percentage": 44.49, "elapsed_time": "0:49:39", "remaining_time": "1:01:58", "throughput": 1034.63, "total_tokens": 3083200} {"current_steps": 34245, "total_steps": 76960, "loss": 0.235, "lr": 3.3962586181108256e-05, "epoch": 8.899428274428274, "percentage": 44.5, "elapsed_time": "0:49:40", "remaining_time": "1:01:57", "throughput": 1034.63, "total_tokens": 3083616} {"current_steps": 34250, "total_steps": 76960, "loss": 0.1407, "lr": 3.39572932192949e-05, "epoch": 8.900727650727651, "percentage": 44.5, "elapsed_time": "0:49:40", "remaining_time": "1:01:57", "throughput": 1034.64, "total_tokens": 3084080} {"current_steps": 34255, "total_steps": 76960, "loss": 0.2926, "lr": 3.395199979679938e-05, "epoch": 8.902027027027026, "percentage": 44.51, "elapsed_time": "0:49:41", "remaining_time": "1:01:56", "throughput": 1034.64, "total_tokens": 3084512} {"current_steps": 34260, "total_steps": 76960, "loss": 0.2778, "lr": 3.3946705913893925e-05, "epoch": 8.903326403326403, "percentage": 44.52, "elapsed_time": "0:49:41", "remaining_time": "1:01:56", "throughput": 1034.65, "total_tokens": 3084960} {"current_steps": 34265, "total_steps": 76960, "loss": 0.1359, "lr": 3.394141157085082e-05, "epoch": 8.90462577962578, "percentage": 44.52, "elapsed_time": "0:49:42", "remaining_time": "1:01:55", "throughput": 1034.66, "total_tokens": 3085440} {"current_steps": 34270, "total_steps": 76960, "loss": 0.1873, "lr": 3.3936116767942336e-05, "epoch": 8.905925155925155, "percentage": 44.53, "elapsed_time": "0:49:42", "remaining_time": "1:01:55", "throughput": 1034.67, "total_tokens": 3085888} {"current_steps": 34275, "total_steps": 76960, "loss": 0.5049, "lr": 3.3930821505440824e-05, "epoch": 8.907224532224532, "percentage": 44.54, "elapsed_time": "0:49:42", "remaining_time": "1:01:54", "throughput": 1034.68, "total_tokens": 3086352} {"current_steps": 34280, "total_steps": 76960, "loss": 0.2228, "lr": 3.392552578361859e-05, "epoch": 8.90852390852391, "percentage": 44.54, "elapsed_time": "0:49:43", "remaining_time": "1:01:54", "throughput": 1034.68, "total_tokens": 3086784} {"current_steps": 34285, "total_steps": 76960, "loss": 0.368, "lr": 3.392022960274802e-05, "epoch": 8.909823284823284, "percentage": 44.55, "elapsed_time": "0:49:43", "remaining_time": "1:01:53", "throughput": 1034.69, "total_tokens": 3087248} {"current_steps": 34290, "total_steps": 76960, "loss": 0.2525, "lr": 3.391493296310149e-05, "epoch": 8.911122661122661, "percentage": 44.56, "elapsed_time": "0:49:44", "remaining_time": "1:01:53", "throughput": 1034.71, "total_tokens": 3087728} {"current_steps": 34295, "total_steps": 76960, "loss": 0.2742, "lr": 3.390963586495142e-05, "epoch": 8.912422037422038, "percentage": 44.56, "elapsed_time": "0:49:44", "remaining_time": "1:01:52", "throughput": 1034.71, "total_tokens": 3088160} {"current_steps": 34300, "total_steps": 76960, "loss": 0.2623, "lr": 3.3904338308570244e-05, "epoch": 8.913721413721413, "percentage": 44.57, "elapsed_time": "0:49:44", "remaining_time": "1:01:52", "throughput": 1034.71, "total_tokens": 3088608} {"current_steps": 34305, "total_steps": 76960, "loss": 0.238, "lr": 3.389904029423041e-05, "epoch": 8.91502079002079, "percentage": 44.58, "elapsed_time": "0:49:45", "remaining_time": "1:01:52", "throughput": 1034.72, "total_tokens": 3089056} {"current_steps": 34310, "total_steps": 76960, "loss": 0.2828, "lr": 3.3893741822204415e-05, "epoch": 8.916320166320165, "percentage": 44.58, "elapsed_time": "0:49:45", "remaining_time": "1:01:51", "throughput": 1034.73, "total_tokens": 3089520} {"current_steps": 34315, "total_steps": 76960, "loss": 0.1916, "lr": 3.388844289276475e-05, "epoch": 8.917619542619542, "percentage": 44.59, "elapsed_time": "0:49:46", "remaining_time": "1:01:51", "throughput": 1034.72, "total_tokens": 3089920} {"current_steps": 34320, "total_steps": 76960, "loss": 0.2245, "lr": 3.3883143506183954e-05, "epoch": 8.91891891891892, "percentage": 44.59, "elapsed_time": "0:49:46", "remaining_time": "1:01:50", "throughput": 1034.73, "total_tokens": 3090368} {"current_steps": 34325, "total_steps": 76960, "loss": 0.2263, "lr": 3.387784366273458e-05, "epoch": 8.920218295218294, "percentage": 44.6, "elapsed_time": "0:49:47", "remaining_time": "1:01:50", "throughput": 1034.76, "total_tokens": 3090880} {"current_steps": 34330, "total_steps": 76960, "loss": 0.209, "lr": 3.387254336268919e-05, "epoch": 8.921517671517671, "percentage": 44.61, "elapsed_time": "0:49:47", "remaining_time": "1:01:49", "throughput": 1034.77, "total_tokens": 3091344} {"current_steps": 34335, "total_steps": 76960, "loss": 0.1897, "lr": 3.38672426063204e-05, "epoch": 8.922817047817048, "percentage": 44.61, "elapsed_time": "0:49:47", "remaining_time": "1:01:49", "throughput": 1034.78, "total_tokens": 3091824} {"current_steps": 34340, "total_steps": 76960, "loss": 0.3096, "lr": 3.386194139390082e-05, "epoch": 8.924116424116423, "percentage": 44.62, "elapsed_time": "0:49:48", "remaining_time": "1:01:48", "throughput": 1034.78, "total_tokens": 3092240} {"current_steps": 34345, "total_steps": 76960, "loss": 0.2906, "lr": 3.385663972570311e-05, "epoch": 8.9254158004158, "percentage": 44.63, "elapsed_time": "0:49:48", "remaining_time": "1:01:48", "throughput": 1034.78, "total_tokens": 3092672} {"current_steps": 34350, "total_steps": 76960, "loss": 0.1862, "lr": 3.3851337601999936e-05, "epoch": 8.926715176715177, "percentage": 44.63, "elapsed_time": "0:49:49", "remaining_time": "1:01:47", "throughput": 1034.79, "total_tokens": 3093136} {"current_steps": 34355, "total_steps": 76960, "loss": 0.2498, "lr": 3.384603502306398e-05, "epoch": 8.928014553014552, "percentage": 44.64, "elapsed_time": "0:49:49", "remaining_time": "1:01:47", "throughput": 1034.8, "total_tokens": 3093600} {"current_steps": 34360, "total_steps": 76960, "loss": 0.334, "lr": 3.3840731989167963e-05, "epoch": 8.92931392931393, "percentage": 44.65, "elapsed_time": "0:49:49", "remaining_time": "1:01:47", "throughput": 1034.8, "total_tokens": 3094016} {"current_steps": 34365, "total_steps": 76960, "loss": 0.2514, "lr": 3.3835428500584635e-05, "epoch": 8.930613305613306, "percentage": 44.65, "elapsed_time": "0:49:50", "remaining_time": "1:01:46", "throughput": 1034.8, "total_tokens": 3094464} {"current_steps": 34370, "total_steps": 76960, "loss": 0.287, "lr": 3.383012455758676e-05, "epoch": 8.931912681912682, "percentage": 44.66, "elapsed_time": "0:49:50", "remaining_time": "1:01:46", "throughput": 1034.81, "total_tokens": 3094912} {"current_steps": 34375, "total_steps": 76960, "loss": 0.2526, "lr": 3.382482016044711e-05, "epoch": 8.933212058212058, "percentage": 44.67, "elapsed_time": "0:49:51", "remaining_time": "1:01:45", "throughput": 1034.82, "total_tokens": 3095376} {"current_steps": 34380, "total_steps": 76960, "loss": 0.2514, "lr": 3.381951530943851e-05, "epoch": 8.934511434511435, "percentage": 44.67, "elapsed_time": "0:49:51", "remaining_time": "1:01:45", "throughput": 1034.81, "total_tokens": 3095792} {"current_steps": 34385, "total_steps": 76960, "loss": 0.2374, "lr": 3.381421000483378e-05, "epoch": 8.93581081081081, "percentage": 44.68, "elapsed_time": "0:49:52", "remaining_time": "1:01:44", "throughput": 1034.81, "total_tokens": 3096224} {"current_steps": 34390, "total_steps": 76960, "loss": 0.294, "lr": 3.380890424690579e-05, "epoch": 8.937110187110187, "percentage": 44.69, "elapsed_time": "0:49:52", "remaining_time": "1:01:44", "throughput": 1034.83, "total_tokens": 3096704} {"current_steps": 34395, "total_steps": 76960, "loss": 0.2324, "lr": 3.380359803592741e-05, "epoch": 8.938409563409563, "percentage": 44.69, "elapsed_time": "0:49:52", "remaining_time": "1:01:43", "throughput": 1034.84, "total_tokens": 3097168} {"current_steps": 34400, "total_steps": 76960, "loss": 0.2684, "lr": 3.3798291372171545e-05, "epoch": 8.93970893970894, "percentage": 44.7, "elapsed_time": "0:49:53", "remaining_time": "1:01:43", "throughput": 1034.86, "total_tokens": 3097664} {"current_steps": 34405, "total_steps": 76960, "loss": 0.2741, "lr": 3.379298425591113e-05, "epoch": 8.941008316008316, "percentage": 44.71, "elapsed_time": "0:49:53", "remaining_time": "1:01:42", "throughput": 1034.89, "total_tokens": 3098160} {"current_steps": 34410, "total_steps": 76960, "loss": 0.2157, "lr": 3.378767668741911e-05, "epoch": 8.942307692307692, "percentage": 44.71, "elapsed_time": "0:49:54", "remaining_time": "1:01:42", "throughput": 1034.9, "total_tokens": 3098640} {"current_steps": 34415, "total_steps": 76960, "loss": 0.2105, "lr": 3.378236866696846e-05, "epoch": 8.943607068607069, "percentage": 44.72, "elapsed_time": "0:49:54", "remaining_time": "1:01:41", "throughput": 1034.91, "total_tokens": 3099104} {"current_steps": 34420, "total_steps": 76960, "loss": 0.3027, "lr": 3.377706019483216e-05, "epoch": 8.944906444906445, "percentage": 44.72, "elapsed_time": "0:49:54", "remaining_time": "1:01:41", "throughput": 1034.91, "total_tokens": 3099536} {"current_steps": 34425, "total_steps": 76960, "loss": 0.194, "lr": 3.377175127128327e-05, "epoch": 8.94620582120582, "percentage": 44.73, "elapsed_time": "0:49:55", "remaining_time": "1:01:41", "throughput": 1034.93, "total_tokens": 3100016} {"current_steps": 34430, "total_steps": 76960, "loss": 0.14, "lr": 3.3766441896594784e-05, "epoch": 8.947505197505198, "percentage": 44.74, "elapsed_time": "0:49:55", "remaining_time": "1:01:40", "throughput": 1034.92, "total_tokens": 3100416} {"current_steps": 34435, "total_steps": 76960, "loss": 0.1997, "lr": 3.3761132071039805e-05, "epoch": 8.948804573804575, "percentage": 44.74, "elapsed_time": "0:49:56", "remaining_time": "1:01:40", "throughput": 1034.92, "total_tokens": 3100848} {"current_steps": 34440, "total_steps": 76960, "loss": 0.2649, "lr": 3.3755821794891405e-05, "epoch": 8.95010395010395, "percentage": 44.75, "elapsed_time": "0:49:56", "remaining_time": "1:01:39", "throughput": 1034.93, "total_tokens": 3101312} {"current_steps": 34445, "total_steps": 76960, "loss": 0.3192, "lr": 3.37505110684227e-05, "epoch": 8.951403326403327, "percentage": 44.76, "elapsed_time": "0:49:57", "remaining_time": "1:01:39", "throughput": 1034.95, "total_tokens": 3101808} {"current_steps": 34450, "total_steps": 76960, "loss": 0.3036, "lr": 3.374519989190683e-05, "epoch": 8.952702702702704, "percentage": 44.76, "elapsed_time": "0:49:57", "remaining_time": "1:01:38", "throughput": 1034.95, "total_tokens": 3102240} {"current_steps": 34455, "total_steps": 76960, "loss": 0.1876, "lr": 3.373988826561695e-05, "epoch": 8.954002079002079, "percentage": 44.77, "elapsed_time": "0:49:57", "remaining_time": "1:01:38", "throughput": 1034.95, "total_tokens": 3102672} {"current_steps": 34460, "total_steps": 76960, "loss": 0.2207, "lr": 3.373457618982624e-05, "epoch": 8.955301455301456, "percentage": 44.78, "elapsed_time": "0:49:58", "remaining_time": "1:01:37", "throughput": 1034.95, "total_tokens": 3103088} {"current_steps": 34465, "total_steps": 76960, "loss": 0.19, "lr": 3.37292636648079e-05, "epoch": 8.95660083160083, "percentage": 44.78, "elapsed_time": "0:49:58", "remaining_time": "1:01:37", "throughput": 1034.95, "total_tokens": 3103536} {"current_steps": 34470, "total_steps": 76960, "loss": 0.3318, "lr": 3.3723950690835173e-05, "epoch": 8.957900207900208, "percentage": 44.79, "elapsed_time": "0:49:59", "remaining_time": "1:01:36", "throughput": 1034.95, "total_tokens": 3103968} {"current_steps": 34475, "total_steps": 76960, "loss": 0.2874, "lr": 3.371863726818131e-05, "epoch": 8.959199584199585, "percentage": 44.8, "elapsed_time": "0:49:59", "remaining_time": "1:01:36", "throughput": 1034.96, "total_tokens": 3104416} {"current_steps": 34480, "total_steps": 76960, "loss": 0.2369, "lr": 3.371332339711957e-05, "epoch": 8.96049896049896, "percentage": 44.8, "elapsed_time": "0:49:59", "remaining_time": "1:01:36", "throughput": 1034.97, "total_tokens": 3104896} {"current_steps": 34485, "total_steps": 76960, "loss": 0.3035, "lr": 3.370800907792325e-05, "epoch": 8.961798336798337, "percentage": 44.81, "elapsed_time": "0:50:00", "remaining_time": "1:01:35", "throughput": 1034.98, "total_tokens": 3105344} {"current_steps": 34490, "total_steps": 76960, "loss": 0.2694, "lr": 3.3702694310865695e-05, "epoch": 8.963097713097714, "percentage": 44.82, "elapsed_time": "0:50:00", "remaining_time": "1:01:35", "throughput": 1034.98, "total_tokens": 3105776} {"current_steps": 34495, "total_steps": 76960, "loss": 0.2271, "lr": 3.369737909622023e-05, "epoch": 8.964397089397089, "percentage": 44.82, "elapsed_time": "0:50:01", "remaining_time": "1:01:34", "throughput": 1034.97, "total_tokens": 3106192} {"current_steps": 34500, "total_steps": 76960, "loss": 0.2638, "lr": 3.369206343426023e-05, "epoch": 8.965696465696466, "percentage": 44.83, "elapsed_time": "0:50:01", "remaining_time": "1:01:34", "throughput": 1034.98, "total_tokens": 3106640} {"current_steps": 34505, "total_steps": 76960, "loss": 0.2567, "lr": 3.3686747325259065e-05, "epoch": 8.966995841995843, "percentage": 44.83, "elapsed_time": "0:50:02", "remaining_time": "1:01:33", "throughput": 1034.98, "total_tokens": 3107072} {"current_steps": 34510, "total_steps": 76960, "loss": 0.225, "lr": 3.368143076949017e-05, "epoch": 8.968295218295218, "percentage": 44.84, "elapsed_time": "0:50:02", "remaining_time": "1:01:33", "throughput": 1034.99, "total_tokens": 3107520} {"current_steps": 34515, "total_steps": 76960, "loss": 0.2755, "lr": 3.367611376722698e-05, "epoch": 8.969594594594595, "percentage": 44.85, "elapsed_time": "0:50:02", "remaining_time": "1:01:32", "throughput": 1034.98, "total_tokens": 3107936} {"current_steps": 34520, "total_steps": 76960, "loss": 0.2713, "lr": 3.367079631874293e-05, "epoch": 8.970893970893972, "percentage": 44.85, "elapsed_time": "0:50:03", "remaining_time": "1:01:32", "throughput": 1034.99, "total_tokens": 3108384} {"current_steps": 34525, "total_steps": 76960, "loss": 0.2001, "lr": 3.3665478424311524e-05, "epoch": 8.972193347193347, "percentage": 44.86, "elapsed_time": "0:50:03", "remaining_time": "1:01:31", "throughput": 1035.01, "total_tokens": 3108880} {"current_steps": 34530, "total_steps": 76960, "loss": 0.2674, "lr": 3.366016008420626e-05, "epoch": 8.973492723492724, "percentage": 44.87, "elapsed_time": "0:50:04", "remaining_time": "1:01:31", "throughput": 1035.01, "total_tokens": 3109312} {"current_steps": 34535, "total_steps": 76960, "loss": 0.2842, "lr": 3.365484129870067e-05, "epoch": 8.9747920997921, "percentage": 44.87, "elapsed_time": "0:50:04", "remaining_time": "1:01:30", "throughput": 1035.01, "total_tokens": 3109744} {"current_steps": 34540, "total_steps": 76960, "loss": 0.1781, "lr": 3.364952206806828e-05, "epoch": 8.976091476091476, "percentage": 44.88, "elapsed_time": "0:50:04", "remaining_time": "1:01:30", "throughput": 1035.01, "total_tokens": 3110192} {"current_steps": 34545, "total_steps": 76960, "loss": 0.2689, "lr": 3.36442023925827e-05, "epoch": 8.977390852390853, "percentage": 44.89, "elapsed_time": "0:50:05", "remaining_time": "1:01:30", "throughput": 1035.02, "total_tokens": 3110640} {"current_steps": 34550, "total_steps": 76960, "loss": 0.2427, "lr": 3.3638882272517514e-05, "epoch": 8.978690228690228, "percentage": 44.89, "elapsed_time": "0:50:05", "remaining_time": "1:01:29", "throughput": 1035.03, "total_tokens": 3111104} {"current_steps": 34555, "total_steps": 76960, "loss": 0.2398, "lr": 3.363356170814632e-05, "epoch": 8.979989604989605, "percentage": 44.9, "elapsed_time": "0:50:06", "remaining_time": "1:01:29", "throughput": 1035.03, "total_tokens": 3111536} {"current_steps": 34560, "total_steps": 76960, "loss": 0.2827, "lr": 3.362824069974279e-05, "epoch": 8.981288981288982, "percentage": 44.91, "elapsed_time": "0:50:06", "remaining_time": "1:01:28", "throughput": 1035.04, "total_tokens": 3112000} {"current_steps": 34565, "total_steps": 76960, "loss": 0.363, "lr": 3.362291924758056e-05, "epoch": 8.982588357588357, "percentage": 44.91, "elapsed_time": "0:50:07", "remaining_time": "1:01:28", "throughput": 1035.06, "total_tokens": 3112480} {"current_steps": 34570, "total_steps": 76960, "loss": 0.1685, "lr": 3.361759735193334e-05, "epoch": 8.983887733887734, "percentage": 44.92, "elapsed_time": "0:50:07", "remaining_time": "1:01:27", "throughput": 1035.07, "total_tokens": 3112944} {"current_steps": 34575, "total_steps": 76960, "loss": 0.2839, "lr": 3.361227501307483e-05, "epoch": 8.98518711018711, "percentage": 44.93, "elapsed_time": "0:50:07", "remaining_time": "1:01:27", "throughput": 1035.09, "total_tokens": 3113440} {"current_steps": 34580, "total_steps": 76960, "loss": 0.2651, "lr": 3.360695223127876e-05, "epoch": 8.986486486486486, "percentage": 44.93, "elapsed_time": "0:50:08", "remaining_time": "1:01:26", "throughput": 1035.08, "total_tokens": 3113840} {"current_steps": 34585, "total_steps": 76960, "loss": 0.204, "lr": 3.360162900681889e-05, "epoch": 8.987785862785863, "percentage": 44.94, "elapsed_time": "0:50:08", "remaining_time": "1:01:26", "throughput": 1035.08, "total_tokens": 3114256} {"current_steps": 34590, "total_steps": 76960, "loss": 0.2103, "lr": 3.3596305339968995e-05, "epoch": 8.98908523908524, "percentage": 44.95, "elapsed_time": "0:50:09", "remaining_time": "1:01:25", "throughput": 1035.09, "total_tokens": 3114720} {"current_steps": 34595, "total_steps": 76960, "loss": 0.3394, "lr": 3.359098123100289e-05, "epoch": 8.990384615384615, "percentage": 44.95, "elapsed_time": "0:50:09", "remaining_time": "1:01:25", "throughput": 1035.09, "total_tokens": 3115168} {"current_steps": 34600, "total_steps": 76960, "loss": 0.3014, "lr": 3.358565668019439e-05, "epoch": 8.991683991683992, "percentage": 44.96, "elapsed_time": "0:50:09", "remaining_time": "1:01:25", "throughput": 1035.1, "total_tokens": 3115632} {"current_steps": 34605, "total_steps": 76960, "loss": 0.2181, "lr": 3.3580331687817336e-05, "epoch": 8.992983367983367, "percentage": 44.96, "elapsed_time": "0:50:10", "remaining_time": "1:01:24", "throughput": 1035.12, "total_tokens": 3116096} {"current_steps": 34610, "total_steps": 76960, "loss": 0.1196, "lr": 3.3575006254145594e-05, "epoch": 8.994282744282744, "percentage": 44.97, "elapsed_time": "0:50:10", "remaining_time": "1:01:24", "throughput": 1035.12, "total_tokens": 3116544} {"current_steps": 34615, "total_steps": 76960, "loss": 0.3679, "lr": 3.356968037945307e-05, "epoch": 8.995582120582121, "percentage": 44.98, "elapsed_time": "0:50:11", "remaining_time": "1:01:23", "throughput": 1035.13, "total_tokens": 3116992} {"current_steps": 34620, "total_steps": 76960, "loss": 0.1787, "lr": 3.3564354064013676e-05, "epoch": 8.996881496881496, "percentage": 44.98, "elapsed_time": "0:50:11", "remaining_time": "1:01:23", "throughput": 1035.13, "total_tokens": 3117440} {"current_steps": 34625, "total_steps": 76960, "loss": 0.2627, "lr": 3.3559027308101345e-05, "epoch": 8.998180873180873, "percentage": 44.99, "elapsed_time": "0:50:12", "remaining_time": "1:01:22", "throughput": 1035.14, "total_tokens": 3117904} {"current_steps": 34630, "total_steps": 76960, "loss": 0.2726, "lr": 3.355370011199003e-05, "epoch": 8.99948024948025, "percentage": 45.0, "elapsed_time": "0:50:12", "remaining_time": "1:01:22", "throughput": 1035.15, "total_tokens": 3118336} {"current_steps": 34632, "total_steps": 76960, "eval_loss": 0.23929104208946228, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "0:50:25", "remaining_time": "1:01:38", "throughput": 1030.61, "total_tokens": 3118472} {"current_steps": 34635, "total_steps": 76960, "loss": 0.1063, "lr": 3.354837247595374e-05, "epoch": 9.000779625779625, "percentage": 45.0, "elapsed_time": "0:50:27", "remaining_time": "1:01:39", "throughput": 1030.08, "total_tokens": 3118728} {"current_steps": 34640, "total_steps": 76960, "loss": 0.2619, "lr": 3.354304440026646e-05, "epoch": 9.002079002079002, "percentage": 45.01, "elapsed_time": "0:50:28", "remaining_time": "1:01:39", "throughput": 1030.08, "total_tokens": 3119176} {"current_steps": 34645, "total_steps": 76960, "loss": 0.1186, "lr": 3.35377158852022e-05, "epoch": 9.003378378378379, "percentage": 45.02, "elapsed_time": "0:50:28", "remaining_time": "1:01:39", "throughput": 1030.07, "total_tokens": 3119608} {"current_steps": 34650, "total_steps": 76960, "loss": 0.2756, "lr": 3.3532386931035054e-05, "epoch": 9.004677754677754, "percentage": 45.02, "elapsed_time": "0:50:28", "remaining_time": "1:01:38", "throughput": 1030.06, "total_tokens": 3120024} {"current_steps": 34655, "total_steps": 76960, "loss": 0.3529, "lr": 3.3527057538039064e-05, "epoch": 9.005977130977131, "percentage": 45.03, "elapsed_time": "0:50:29", "remaining_time": "1:01:38", "throughput": 1030.08, "total_tokens": 3120504} {"current_steps": 34660, "total_steps": 76960, "loss": 0.2532, "lr": 3.3521727706488336e-05, "epoch": 9.007276507276508, "percentage": 45.04, "elapsed_time": "0:50:29", "remaining_time": "1:01:37", "throughput": 1030.08, "total_tokens": 3120952} {"current_steps": 34665, "total_steps": 76960, "loss": 0.2729, "lr": 3.3516397436656985e-05, "epoch": 9.008575883575883, "percentage": 45.04, "elapsed_time": "0:50:30", "remaining_time": "1:01:37", "throughput": 1030.09, "total_tokens": 3121432} {"current_steps": 34670, "total_steps": 76960, "loss": 0.3095, "lr": 3.351106672881915e-05, "epoch": 9.00987525987526, "percentage": 45.05, "elapsed_time": "0:50:30", "remaining_time": "1:01:36", "throughput": 1030.09, "total_tokens": 3121848} {"current_steps": 34675, "total_steps": 76960, "loss": 0.2072, "lr": 3.350573558324901e-05, "epoch": 9.011174636174637, "percentage": 45.06, "elapsed_time": "0:50:31", "remaining_time": "1:01:36", "throughput": 1030.1, "total_tokens": 3122328} {"current_steps": 34680, "total_steps": 76960, "loss": 0.202, "lr": 3.350040400022072e-05, "epoch": 9.012474012474012, "percentage": 45.06, "elapsed_time": "0:50:31", "remaining_time": "1:01:35", "throughput": 1030.12, "total_tokens": 3122824} {"current_steps": 34685, "total_steps": 76960, "loss": 0.27, "lr": 3.349507198000853e-05, "epoch": 9.013773388773389, "percentage": 45.07, "elapsed_time": "0:50:31", "remaining_time": "1:01:35", "throughput": 1030.12, "total_tokens": 3123240} {"current_steps": 34690, "total_steps": 76960, "loss": 0.1725, "lr": 3.348973952288664e-05, "epoch": 9.015072765072764, "percentage": 45.08, "elapsed_time": "0:50:32", "remaining_time": "1:01:34", "throughput": 1030.12, "total_tokens": 3123688} {"current_steps": 34695, "total_steps": 76960, "loss": 0.3098, "lr": 3.3484406629129314e-05, "epoch": 9.016372141372141, "percentage": 45.08, "elapsed_time": "0:50:32", "remaining_time": "1:01:34", "throughput": 1030.14, "total_tokens": 3124168} {"current_steps": 34700, "total_steps": 76960, "loss": 0.1326, "lr": 3.347907329901082e-05, "epoch": 9.017671517671518, "percentage": 45.09, "elapsed_time": "0:50:33", "remaining_time": "1:01:34", "throughput": 1030.14, "total_tokens": 3124600} {"current_steps": 34705, "total_steps": 76960, "loss": 0.2719, "lr": 3.3473739532805467e-05, "epoch": 9.018970893970893, "percentage": 45.09, "elapsed_time": "0:50:33", "remaining_time": "1:01:33", "throughput": 1030.16, "total_tokens": 3125080} {"current_steps": 34710, "total_steps": 76960, "loss": 0.1898, "lr": 3.346840533078757e-05, "epoch": 9.02027027027027, "percentage": 45.1, "elapsed_time": "0:50:34", "remaining_time": "1:01:33", "throughput": 1030.15, "total_tokens": 3125496} {"current_steps": 34715, "total_steps": 76960, "loss": 0.1818, "lr": 3.346307069323146e-05, "epoch": 9.021569646569647, "percentage": 45.11, "elapsed_time": "0:50:34", "remaining_time": "1:01:32", "throughput": 1030.16, "total_tokens": 3125944} {"current_steps": 34720, "total_steps": 76960, "loss": 0.2621, "lr": 3.345773562041153e-05, "epoch": 9.022869022869022, "percentage": 45.11, "elapsed_time": "0:50:34", "remaining_time": "1:01:32", "throughput": 1030.17, "total_tokens": 3126424} {"current_steps": 34725, "total_steps": 76960, "loss": 0.279, "lr": 3.345240011260215e-05, "epoch": 9.0241683991684, "percentage": 45.12, "elapsed_time": "0:50:35", "remaining_time": "1:01:31", "throughput": 1030.17, "total_tokens": 3126856} {"current_steps": 34730, "total_steps": 76960, "loss": 0.1191, "lr": 3.344706417007773e-05, "epoch": 9.025467775467776, "percentage": 45.13, "elapsed_time": "0:50:35", "remaining_time": "1:01:31", "throughput": 1030.18, "total_tokens": 3127304} {"current_steps": 34735, "total_steps": 76960, "loss": 0.2707, "lr": 3.344172779311271e-05, "epoch": 9.026767151767151, "percentage": 45.13, "elapsed_time": "0:50:36", "remaining_time": "1:01:30", "throughput": 1030.18, "total_tokens": 3127752} {"current_steps": 34740, "total_steps": 76960, "loss": 0.1693, "lr": 3.3436390981981535e-05, "epoch": 9.028066528066528, "percentage": 45.14, "elapsed_time": "0:50:36", "remaining_time": "1:01:30", "throughput": 1030.19, "total_tokens": 3128200} {"current_steps": 34745, "total_steps": 76960, "loss": 0.3109, "lr": 3.3431053736958695e-05, "epoch": 9.029365904365905, "percentage": 45.15, "elapsed_time": "0:50:36", "remaining_time": "1:01:29", "throughput": 1030.21, "total_tokens": 3128680} {"current_steps": 34750, "total_steps": 76960, "loss": 0.2023, "lr": 3.3425716058318684e-05, "epoch": 9.03066528066528, "percentage": 45.15, "elapsed_time": "0:50:37", "remaining_time": "1:01:29", "throughput": 1030.21, "total_tokens": 3129128} {"current_steps": 34755, "total_steps": 76960, "loss": 0.1206, "lr": 3.342037794633602e-05, "epoch": 9.031964656964657, "percentage": 45.16, "elapsed_time": "0:50:37", "remaining_time": "1:01:28", "throughput": 1030.23, "total_tokens": 3129608} {"current_steps": 34760, "total_steps": 76960, "loss": 0.4991, "lr": 3.3415039401285245e-05, "epoch": 9.033264033264032, "percentage": 45.17, "elapsed_time": "0:50:38", "remaining_time": "1:01:28", "throughput": 1030.24, "total_tokens": 3130072} {"current_steps": 34765, "total_steps": 76960, "loss": 0.1476, "lr": 3.3409700423440945e-05, "epoch": 9.03456340956341, "percentage": 45.17, "elapsed_time": "0:50:38", "remaining_time": "1:01:28", "throughput": 1030.25, "total_tokens": 3130520} {"current_steps": 34770, "total_steps": 76960, "loss": 0.1538, "lr": 3.340436101307768e-05, "epoch": 9.035862785862786, "percentage": 45.18, "elapsed_time": "0:50:39", "remaining_time": "1:01:27", "throughput": 1030.25, "total_tokens": 3130968} {"current_steps": 34775, "total_steps": 76960, "loss": 0.2328, "lr": 3.3399021170470084e-05, "epoch": 9.037162162162161, "percentage": 45.19, "elapsed_time": "0:50:39", "remaining_time": "1:01:27", "throughput": 1030.26, "total_tokens": 3131416} {"current_steps": 34780, "total_steps": 76960, "loss": 0.299, "lr": 3.339368089589278e-05, "epoch": 9.038461538461538, "percentage": 45.19, "elapsed_time": "0:50:39", "remaining_time": "1:01:26", "throughput": 1030.27, "total_tokens": 3131880} {"current_steps": 34785, "total_steps": 76960, "loss": 0.3727, "lr": 3.3388340189620424e-05, "epoch": 9.039760914760915, "percentage": 45.2, "elapsed_time": "0:50:40", "remaining_time": "1:01:26", "throughput": 1030.28, "total_tokens": 3132344} {"current_steps": 34790, "total_steps": 76960, "loss": 0.3141, "lr": 3.338299905192769e-05, "epoch": 9.04106029106029, "percentage": 45.21, "elapsed_time": "0:50:40", "remaining_time": "1:01:25", "throughput": 1030.29, "total_tokens": 3132808} {"current_steps": 34795, "total_steps": 76960, "loss": 0.2026, "lr": 3.337765748308929e-05, "epoch": 9.042359667359667, "percentage": 45.21, "elapsed_time": "0:50:41", "remaining_time": "1:01:25", "throughput": 1030.31, "total_tokens": 3133304} {"current_steps": 34800, "total_steps": 76960, "loss": 0.2535, "lr": 3.337231548337994e-05, "epoch": 9.043659043659044, "percentage": 45.22, "elapsed_time": "0:50:41", "remaining_time": "1:01:24", "throughput": 1030.34, "total_tokens": 3133816} {"current_steps": 34805, "total_steps": 76960, "loss": 0.2787, "lr": 3.336697305307437e-05, "epoch": 9.04495841995842, "percentage": 45.22, "elapsed_time": "0:50:41", "remaining_time": "1:01:24", "throughput": 1030.35, "total_tokens": 3134264} {"current_steps": 34810, "total_steps": 76960, "loss": 0.1796, "lr": 3.336163019244737e-05, "epoch": 9.046257796257796, "percentage": 45.23, "elapsed_time": "0:50:42", "remaining_time": "1:01:23", "throughput": 1030.36, "total_tokens": 3134728} {"current_steps": 34815, "total_steps": 76960, "loss": 0.2481, "lr": 3.335628690177371e-05, "epoch": 9.047557172557173, "percentage": 45.24, "elapsed_time": "0:50:42", "remaining_time": "1:01:23", "throughput": 1030.36, "total_tokens": 3135160} {"current_steps": 34820, "total_steps": 76960, "loss": 0.4127, "lr": 3.335094318132822e-05, "epoch": 9.048856548856548, "percentage": 45.24, "elapsed_time": "0:50:43", "remaining_time": "1:01:22", "throughput": 1030.36, "total_tokens": 3135576} {"current_steps": 34825, "total_steps": 76960, "loss": 0.2175, "lr": 3.3345599031385713e-05, "epoch": 9.050155925155925, "percentage": 45.25, "elapsed_time": "0:50:43", "remaining_time": "1:01:22", "throughput": 1030.36, "total_tokens": 3136008} {"current_steps": 34830, "total_steps": 76960, "loss": 0.2316, "lr": 3.3340254452221056e-05, "epoch": 9.051455301455302, "percentage": 45.26, "elapsed_time": "0:50:44", "remaining_time": "1:01:22", "throughput": 1030.36, "total_tokens": 3136440} {"current_steps": 34835, "total_steps": 76960, "loss": 0.1441, "lr": 3.333490944410912e-05, "epoch": 9.052754677754677, "percentage": 45.26, "elapsed_time": "0:50:44", "remaining_time": "1:01:21", "throughput": 1030.37, "total_tokens": 3136904} {"current_steps": 34840, "total_steps": 76960, "loss": 0.3239, "lr": 3.33295640073248e-05, "epoch": 9.054054054054054, "percentage": 45.27, "elapsed_time": "0:50:44", "remaining_time": "1:01:21", "throughput": 1030.37, "total_tokens": 3137336} {"current_steps": 34845, "total_steps": 76960, "loss": 0.3103, "lr": 3.332421814214302e-05, "epoch": 9.05535343035343, "percentage": 45.28, "elapsed_time": "0:50:45", "remaining_time": "1:01:20", "throughput": 1030.39, "total_tokens": 3137816} {"current_steps": 34850, "total_steps": 76960, "loss": 0.1823, "lr": 3.331887184883873e-05, "epoch": 9.056652806652806, "percentage": 45.28, "elapsed_time": "0:50:45", "remaining_time": "1:01:20", "throughput": 1030.38, "total_tokens": 3138248} {"current_steps": 34855, "total_steps": 76960, "loss": 0.1687, "lr": 3.33135251276869e-05, "epoch": 9.057952182952183, "percentage": 45.29, "elapsed_time": "0:50:46", "remaining_time": "1:01:19", "throughput": 1030.39, "total_tokens": 3138712} {"current_steps": 34860, "total_steps": 76960, "loss": 0.1434, "lr": 3.330817797896249e-05, "epoch": 9.059251559251559, "percentage": 45.3, "elapsed_time": "0:50:46", "remaining_time": "1:01:19", "throughput": 1030.42, "total_tokens": 3139224} {"current_steps": 34865, "total_steps": 76960, "loss": 0.1971, "lr": 3.330283040294053e-05, "epoch": 9.060550935550935, "percentage": 45.3, "elapsed_time": "0:50:46", "remaining_time": "1:01:18", "throughput": 1030.42, "total_tokens": 3139656} {"current_steps": 34870, "total_steps": 76960, "loss": 0.1467, "lr": 3.3297482399896054e-05, "epoch": 9.061850311850312, "percentage": 45.31, "elapsed_time": "0:50:47", "remaining_time": "1:01:18", "throughput": 1030.42, "total_tokens": 3140088} {"current_steps": 34875, "total_steps": 76960, "loss": 0.2684, "lr": 3.32921339701041e-05, "epoch": 9.063149688149688, "percentage": 45.32, "elapsed_time": "0:50:47", "remaining_time": "1:01:17", "throughput": 1030.44, "total_tokens": 3140552} {"current_steps": 34880, "total_steps": 76960, "loss": 0.2569, "lr": 3.328678511383975e-05, "epoch": 9.064449064449065, "percentage": 45.32, "elapsed_time": "0:50:48", "remaining_time": "1:01:17", "throughput": 1030.44, "total_tokens": 3140984} {"current_steps": 34885, "total_steps": 76960, "loss": 0.3164, "lr": 3.328143583137811e-05, "epoch": 9.065748440748441, "percentage": 45.33, "elapsed_time": "0:50:48", "remaining_time": "1:01:16", "throughput": 1030.44, "total_tokens": 3141416} {"current_steps": 34890, "total_steps": 76960, "loss": 0.3881, "lr": 3.3276086122994286e-05, "epoch": 9.067047817047817, "percentage": 45.34, "elapsed_time": "0:50:49", "remaining_time": "1:01:16", "throughput": 1030.44, "total_tokens": 3141864} {"current_steps": 34895, "total_steps": 76960, "loss": 0.1986, "lr": 3.327073598896342e-05, "epoch": 9.068347193347194, "percentage": 45.34, "elapsed_time": "0:50:49", "remaining_time": "1:01:16", "throughput": 1030.46, "total_tokens": 3142328} {"current_steps": 34900, "total_steps": 76960, "loss": 0.2923, "lr": 3.326538542956069e-05, "epoch": 9.06964656964657, "percentage": 45.35, "elapsed_time": "0:50:49", "remaining_time": "1:01:15", "throughput": 1030.45, "total_tokens": 3142728} {"current_steps": 34905, "total_steps": 76960, "loss": 0.1242, "lr": 3.326003444506126e-05, "epoch": 9.070945945945946, "percentage": 45.35, "elapsed_time": "0:50:50", "remaining_time": "1:01:15", "throughput": 1030.44, "total_tokens": 3143144} {"current_steps": 34910, "total_steps": 76960, "loss": 0.3322, "lr": 3.3254683035740344e-05, "epoch": 9.072245322245323, "percentage": 45.36, "elapsed_time": "0:50:50", "remaining_time": "1:01:14", "throughput": 1030.45, "total_tokens": 3143592} {"current_steps": 34915, "total_steps": 76960, "loss": 0.4556, "lr": 3.3249331201873164e-05, "epoch": 9.073544698544698, "percentage": 45.37, "elapsed_time": "0:50:51", "remaining_time": "1:01:14", "throughput": 1030.45, "total_tokens": 3144040} {"current_steps": 34920, "total_steps": 76960, "loss": 0.2898, "lr": 3.324397894373498e-05, "epoch": 9.074844074844075, "percentage": 45.37, "elapsed_time": "0:50:51", "remaining_time": "1:01:13", "throughput": 1030.45, "total_tokens": 3144472} {"current_steps": 34925, "total_steps": 76960, "loss": 0.1688, "lr": 3.3238626261601066e-05, "epoch": 9.076143451143452, "percentage": 45.38, "elapsed_time": "0:50:51", "remaining_time": "1:01:13", "throughput": 1030.46, "total_tokens": 3144920} {"current_steps": 34930, "total_steps": 76960, "loss": 0.1357, "lr": 3.32332731557467e-05, "epoch": 9.077442827442827, "percentage": 45.39, "elapsed_time": "0:50:52", "remaining_time": "1:01:12", "throughput": 1030.47, "total_tokens": 3145368} {"current_steps": 34935, "total_steps": 76960, "loss": 0.2182, "lr": 3.322791962644721e-05, "epoch": 9.078742203742204, "percentage": 45.39, "elapsed_time": "0:50:52", "remaining_time": "1:01:12", "throughput": 1030.47, "total_tokens": 3145800} {"current_steps": 34940, "total_steps": 76960, "loss": 0.3742, "lr": 3.3222565673977936e-05, "epoch": 9.08004158004158, "percentage": 45.4, "elapsed_time": "0:50:53", "remaining_time": "1:01:11", "throughput": 1030.48, "total_tokens": 3146280} {"current_steps": 34945, "total_steps": 76960, "loss": 0.2008, "lr": 3.321721129861422e-05, "epoch": 9.081340956340956, "percentage": 45.41, "elapsed_time": "0:50:53", "remaining_time": "1:01:11", "throughput": 1030.48, "total_tokens": 3146696} {"current_steps": 34950, "total_steps": 76960, "loss": 0.3613, "lr": 3.3211856500631464e-05, "epoch": 9.082640332640333, "percentage": 45.41, "elapsed_time": "0:50:54", "remaining_time": "1:01:10", "throughput": 1030.48, "total_tokens": 3147128} {"current_steps": 34955, "total_steps": 76960, "loss": 0.152, "lr": 3.320650128030505e-05, "epoch": 9.08393970893971, "percentage": 45.42, "elapsed_time": "0:50:54", "remaining_time": "1:01:10", "throughput": 1030.5, "total_tokens": 3147608} {"current_steps": 34960, "total_steps": 76960, "loss": 0.3899, "lr": 3.3201145637910426e-05, "epoch": 9.085239085239085, "percentage": 45.43, "elapsed_time": "0:50:54", "remaining_time": "1:01:10", "throughput": 1030.49, "total_tokens": 3148024} {"current_steps": 34965, "total_steps": 76960, "loss": 0.2391, "lr": 3.319578957372301e-05, "epoch": 9.086538461538462, "percentage": 45.43, "elapsed_time": "0:50:55", "remaining_time": "1:01:09", "throughput": 1030.49, "total_tokens": 3148440} {"current_steps": 34970, "total_steps": 76960, "loss": 0.1492, "lr": 3.3190433088018294e-05, "epoch": 9.087837837837839, "percentage": 45.44, "elapsed_time": "0:50:55", "remaining_time": "1:01:09", "throughput": 1030.5, "total_tokens": 3148888} {"current_steps": 34975, "total_steps": 76960, "loss": 0.2092, "lr": 3.318507618107175e-05, "epoch": 9.089137214137214, "percentage": 45.45, "elapsed_time": "0:50:56", "remaining_time": "1:01:08", "throughput": 1030.5, "total_tokens": 3149320} {"current_steps": 34980, "total_steps": 76960, "loss": 0.321, "lr": 3.3179718853158906e-05, "epoch": 9.09043659043659, "percentage": 45.45, "elapsed_time": "0:50:56", "remaining_time": "1:01:08", "throughput": 1030.52, "total_tokens": 3149816} {"current_steps": 34985, "total_steps": 76960, "loss": 0.191, "lr": 3.3174361104555266e-05, "epoch": 9.091735966735968, "percentage": 45.46, "elapsed_time": "0:50:56", "remaining_time": "1:01:07", "throughput": 1030.52, "total_tokens": 3150248} {"current_steps": 34990, "total_steps": 76960, "loss": 0.3779, "lr": 3.316900293553642e-05, "epoch": 9.093035343035343, "percentage": 45.47, "elapsed_time": "0:50:57", "remaining_time": "1:01:07", "throughput": 1030.53, "total_tokens": 3150696} {"current_steps": 34995, "total_steps": 76960, "loss": 0.5418, "lr": 3.316364434637791e-05, "epoch": 9.09433471933472, "percentage": 45.47, "elapsed_time": "0:50:57", "remaining_time": "1:01:06", "throughput": 1030.53, "total_tokens": 3151144} {"current_steps": 35000, "total_steps": 76960, "loss": 0.1739, "lr": 3.315828533735536e-05, "epoch": 9.095634095634095, "percentage": 45.48, "elapsed_time": "0:50:58", "remaining_time": "1:01:06", "throughput": 1030.54, "total_tokens": 3151592} {"current_steps": 35005, "total_steps": 76960, "loss": 0.2573, "lr": 3.315292590874437e-05, "epoch": 9.096933471933472, "percentage": 45.48, "elapsed_time": "0:50:58", "remaining_time": "1:01:05", "throughput": 1030.56, "total_tokens": 3152088} {"current_steps": 35010, "total_steps": 76960, "loss": 0.3507, "lr": 3.314756606082059e-05, "epoch": 9.098232848232849, "percentage": 45.49, "elapsed_time": "0:50:59", "remaining_time": "1:01:05", "throughput": 1030.58, "total_tokens": 3152584} {"current_steps": 35015, "total_steps": 76960, "loss": 0.2811, "lr": 3.3142205793859684e-05, "epoch": 9.099532224532224, "percentage": 45.5, "elapsed_time": "0:50:59", "remaining_time": "1:01:04", "throughput": 1030.58, "total_tokens": 3153016} {"current_steps": 35020, "total_steps": 76960, "loss": 0.2433, "lr": 3.3136845108137336e-05, "epoch": 9.1008316008316, "percentage": 45.5, "elapsed_time": "0:50:59", "remaining_time": "1:01:04", "throughput": 1030.57, "total_tokens": 3153448} {"current_steps": 35025, "total_steps": 76960, "loss": 0.2874, "lr": 3.3131484003929246e-05, "epoch": 9.102130977130978, "percentage": 45.51, "elapsed_time": "0:51:00", "remaining_time": "1:01:04", "throughput": 1030.59, "total_tokens": 3153928} {"current_steps": 35030, "total_steps": 76960, "loss": 0.2348, "lr": 3.312612248151115e-05, "epoch": 9.103430353430353, "percentage": 45.52, "elapsed_time": "0:51:00", "remaining_time": "1:01:03", "throughput": 1030.61, "total_tokens": 3154440} {"current_steps": 35035, "total_steps": 76960, "loss": 0.3187, "lr": 3.312076054115877e-05, "epoch": 9.10472972972973, "percentage": 45.52, "elapsed_time": "0:51:01", "remaining_time": "1:01:03", "throughput": 1030.63, "total_tokens": 3154904} {"current_steps": 35040, "total_steps": 76960, "loss": 0.2384, "lr": 3.31153981831479e-05, "epoch": 9.106029106029107, "percentage": 45.53, "elapsed_time": "0:51:01", "remaining_time": "1:01:02", "throughput": 1030.64, "total_tokens": 3155368} {"current_steps": 35045, "total_steps": 76960, "loss": 0.2546, "lr": 3.311003540775434e-05, "epoch": 9.107328482328482, "percentage": 45.54, "elapsed_time": "0:51:01", "remaining_time": "1:01:02", "throughput": 1030.63, "total_tokens": 3155768} {"current_steps": 35050, "total_steps": 76960, "loss": 0.2377, "lr": 3.310467221525387e-05, "epoch": 9.108627858627859, "percentage": 45.54, "elapsed_time": "0:51:02", "remaining_time": "1:01:01", "throughput": 1030.64, "total_tokens": 3156248} {"current_steps": 35055, "total_steps": 76960, "loss": 0.162, "lr": 3.3099308605922354e-05, "epoch": 9.109927234927236, "percentage": 45.55, "elapsed_time": "0:51:02", "remaining_time": "1:01:01", "throughput": 1030.66, "total_tokens": 3156728} {"current_steps": 35060, "total_steps": 76960, "loss": 0.1805, "lr": 3.309394458003563e-05, "epoch": 9.111226611226611, "percentage": 45.56, "elapsed_time": "0:51:03", "remaining_time": "1:01:00", "throughput": 1030.66, "total_tokens": 3157160} {"current_steps": 35065, "total_steps": 76960, "loss": 0.1759, "lr": 3.3088580137869587e-05, "epoch": 9.112525987525988, "percentage": 45.56, "elapsed_time": "0:51:03", "remaining_time": "1:01:00", "throughput": 1030.67, "total_tokens": 3157608} {"current_steps": 35070, "total_steps": 76960, "loss": 0.2374, "lr": 3.3083215279700115e-05, "epoch": 9.113825363825363, "percentage": 45.57, "elapsed_time": "0:51:04", "remaining_time": "1:00:59", "throughput": 1030.67, "total_tokens": 3158056} {"current_steps": 35075, "total_steps": 76960, "loss": 0.3479, "lr": 3.307785000580313e-05, "epoch": 9.11512474012474, "percentage": 45.58, "elapsed_time": "0:51:04", "remaining_time": "1:00:59", "throughput": 1030.68, "total_tokens": 3158504} {"current_steps": 35080, "total_steps": 76960, "loss": 0.3631, "lr": 3.307248431645458e-05, "epoch": 9.116424116424117, "percentage": 45.58, "elapsed_time": "0:51:04", "remaining_time": "1:00:59", "throughput": 1030.68, "total_tokens": 3158936} {"current_steps": 35085, "total_steps": 76960, "loss": 0.3272, "lr": 3.306711821193044e-05, "epoch": 9.117723492723492, "percentage": 45.59, "elapsed_time": "0:51:05", "remaining_time": "1:00:58", "throughput": 1030.69, "total_tokens": 3159400} {"current_steps": 35090, "total_steps": 76960, "loss": 0.301, "lr": 3.306175169250667e-05, "epoch": 9.119022869022869, "percentage": 45.6, "elapsed_time": "0:51:05", "remaining_time": "1:00:58", "throughput": 1030.7, "total_tokens": 3159864} {"current_steps": 35095, "total_steps": 76960, "loss": 0.1742, "lr": 3.305638475845929e-05, "epoch": 9.120322245322246, "percentage": 45.6, "elapsed_time": "0:51:06", "remaining_time": "1:00:57", "throughput": 1030.71, "total_tokens": 3160312} {"current_steps": 35100, "total_steps": 76960, "loss": 0.2981, "lr": 3.305101741006432e-05, "epoch": 9.121621621621621, "percentage": 45.61, "elapsed_time": "0:51:06", "remaining_time": "1:00:57", "throughput": 1030.71, "total_tokens": 3160760} {"current_steps": 35105, "total_steps": 76960, "loss": 0.1895, "lr": 3.3045649647597815e-05, "epoch": 9.122920997920998, "percentage": 45.61, "elapsed_time": "0:51:06", "remaining_time": "1:00:56", "throughput": 1030.71, "total_tokens": 3161192} {"current_steps": 35110, "total_steps": 76960, "loss": 0.2115, "lr": 3.304028147133583e-05, "epoch": 9.124220374220375, "percentage": 45.62, "elapsed_time": "0:51:07", "remaining_time": "1:00:56", "throughput": 1030.71, "total_tokens": 3161608} {"current_steps": 35115, "total_steps": 76960, "loss": 0.2405, "lr": 3.303491288155448e-05, "epoch": 9.12551975051975, "percentage": 45.63, "elapsed_time": "0:51:07", "remaining_time": "1:00:55", "throughput": 1030.71, "total_tokens": 3162040} {"current_steps": 35120, "total_steps": 76960, "loss": 0.1273, "lr": 3.3029543878529844e-05, "epoch": 9.126819126819127, "percentage": 45.63, "elapsed_time": "0:51:08", "remaining_time": "1:00:55", "throughput": 1030.71, "total_tokens": 3162472} {"current_steps": 35125, "total_steps": 76960, "loss": 0.1713, "lr": 3.3024174462538086e-05, "epoch": 9.128118503118504, "percentage": 45.64, "elapsed_time": "0:51:08", "remaining_time": "1:00:54", "throughput": 1030.71, "total_tokens": 3162904} {"current_steps": 35130, "total_steps": 76960, "loss": 0.2984, "lr": 3.301880463385534e-05, "epoch": 9.129417879417879, "percentage": 45.65, "elapsed_time": "0:51:09", "remaining_time": "1:00:54", "throughput": 1030.7, "total_tokens": 3163304} {"current_steps": 35135, "total_steps": 76960, "loss": 0.3292, "lr": 3.301343439275779e-05, "epoch": 9.130717255717256, "percentage": 45.65, "elapsed_time": "0:51:09", "remaining_time": "1:00:53", "throughput": 1030.71, "total_tokens": 3163768} {"current_steps": 35140, "total_steps": 76960, "loss": 0.2473, "lr": 3.3008063739521636e-05, "epoch": 9.132016632016631, "percentage": 45.66, "elapsed_time": "0:51:09", "remaining_time": "1:00:53", "throughput": 1030.71, "total_tokens": 3164200} {"current_steps": 35145, "total_steps": 76960, "loss": 0.3123, "lr": 3.300269267442309e-05, "epoch": 9.133316008316008, "percentage": 45.67, "elapsed_time": "0:51:10", "remaining_time": "1:00:53", "throughput": 1030.72, "total_tokens": 3164664} {"current_steps": 35150, "total_steps": 76960, "loss": 0.2167, "lr": 3.2997321197738385e-05, "epoch": 9.134615384615385, "percentage": 45.67, "elapsed_time": "0:51:10", "remaining_time": "1:00:52", "throughput": 1030.72, "total_tokens": 3165096} {"current_steps": 35155, "total_steps": 76960, "loss": 0.334, "lr": 3.299194930974379e-05, "epoch": 9.13591476091476, "percentage": 45.68, "elapsed_time": "0:51:11", "remaining_time": "1:00:52", "throughput": 1030.74, "total_tokens": 3165560} {"current_steps": 35160, "total_steps": 76960, "loss": 0.2273, "lr": 3.2986577010715594e-05, "epoch": 9.137214137214137, "percentage": 45.69, "elapsed_time": "0:51:11", "remaining_time": "1:00:51", "throughput": 1030.73, "total_tokens": 3165960} {"current_steps": 35165, "total_steps": 76960, "loss": 0.1935, "lr": 3.298120430093008e-05, "epoch": 9.138513513513514, "percentage": 45.69, "elapsed_time": "0:51:12", "remaining_time": "1:00:51", "throughput": 1030.73, "total_tokens": 3166392} {"current_steps": 35170, "total_steps": 76960, "loss": 0.0798, "lr": 3.2975831180663585e-05, "epoch": 9.13981288981289, "percentage": 45.7, "elapsed_time": "0:51:12", "remaining_time": "1:00:50", "throughput": 1030.73, "total_tokens": 3166824} {"current_steps": 35175, "total_steps": 76960, "loss": 0.2241, "lr": 3.2970457650192446e-05, "epoch": 9.141112266112266, "percentage": 45.71, "elapsed_time": "0:51:12", "remaining_time": "1:00:50", "throughput": 1030.73, "total_tokens": 3167256} {"current_steps": 35180, "total_steps": 76960, "loss": 0.3341, "lr": 3.296508370979303e-05, "epoch": 9.142411642411643, "percentage": 45.71, "elapsed_time": "0:51:13", "remaining_time": "1:00:49", "throughput": 1030.73, "total_tokens": 3167688} {"current_steps": 35185, "total_steps": 76960, "loss": 0.3731, "lr": 3.2959709359741744e-05, "epoch": 9.143711018711018, "percentage": 45.72, "elapsed_time": "0:51:13", "remaining_time": "1:00:49", "throughput": 1030.73, "total_tokens": 3168136} {"current_steps": 35190, "total_steps": 76960, "loss": 0.1114, "lr": 3.295433460031497e-05, "epoch": 9.145010395010395, "percentage": 45.73, "elapsed_time": "0:51:14", "remaining_time": "1:00:48", "throughput": 1030.74, "total_tokens": 3168568} {"current_steps": 35195, "total_steps": 76960, "loss": 0.1697, "lr": 3.294895943178914e-05, "epoch": 9.146309771309772, "percentage": 45.73, "elapsed_time": "0:51:14", "remaining_time": "1:00:48", "throughput": 1030.74, "total_tokens": 3169016} {"current_steps": 35200, "total_steps": 76960, "loss": 0.3354, "lr": 3.294358385444071e-05, "epoch": 9.147609147609147, "percentage": 45.74, "elapsed_time": "0:51:14", "remaining_time": "1:00:47", "throughput": 1030.75, "total_tokens": 3169464} {"current_steps": 35205, "total_steps": 76960, "loss": 0.1498, "lr": 3.293820786854616e-05, "epoch": 9.148908523908524, "percentage": 45.74, "elapsed_time": "0:51:15", "remaining_time": "1:00:47", "throughput": 1030.75, "total_tokens": 3169896} {"current_steps": 35210, "total_steps": 76960, "loss": 0.4818, "lr": 3.293283147438197e-05, "epoch": 9.1502079002079, "percentage": 45.75, "elapsed_time": "0:51:15", "remaining_time": "1:00:47", "throughput": 1030.76, "total_tokens": 3170376} {"current_steps": 35215, "total_steps": 76960, "loss": 0.3624, "lr": 3.292745467222465e-05, "epoch": 9.151507276507276, "percentage": 45.76, "elapsed_time": "0:51:16", "remaining_time": "1:00:46", "throughput": 1030.75, "total_tokens": 3170792} {"current_steps": 35220, "total_steps": 76960, "loss": 0.2375, "lr": 3.292207746235075e-05, "epoch": 9.152806652806653, "percentage": 45.76, "elapsed_time": "0:51:16", "remaining_time": "1:00:46", "throughput": 1030.75, "total_tokens": 3171208} {"current_steps": 35225, "total_steps": 76960, "loss": 0.1887, "lr": 3.2916699845036816e-05, "epoch": 9.154106029106028, "percentage": 45.77, "elapsed_time": "0:51:17", "remaining_time": "1:00:45", "throughput": 1030.76, "total_tokens": 3171688} {"current_steps": 35230, "total_steps": 76960, "loss": 0.1676, "lr": 3.291132182055942e-05, "epoch": 9.155405405405405, "percentage": 45.78, "elapsed_time": "0:51:17", "remaining_time": "1:00:45", "throughput": 1030.78, "total_tokens": 3172168} {"current_steps": 35235, "total_steps": 76960, "loss": 0.5021, "lr": 3.2905943389195156e-05, "epoch": 9.156704781704782, "percentage": 45.78, "elapsed_time": "0:51:17", "remaining_time": "1:00:44", "throughput": 1030.77, "total_tokens": 3172568} {"current_steps": 35240, "total_steps": 76960, "loss": 0.0671, "lr": 3.290056455122066e-05, "epoch": 9.158004158004157, "percentage": 45.79, "elapsed_time": "0:51:18", "remaining_time": "1:00:44", "throughput": 1030.77, "total_tokens": 3173000} {"current_steps": 35245, "total_steps": 76960, "loss": 0.2635, "lr": 3.289518530691255e-05, "epoch": 9.159303534303534, "percentage": 45.8, "elapsed_time": "0:51:18", "remaining_time": "1:00:43", "throughput": 1030.78, "total_tokens": 3173464} {"current_steps": 35250, "total_steps": 76960, "loss": 0.4138, "lr": 3.28898056565475e-05, "epoch": 9.160602910602911, "percentage": 45.8, "elapsed_time": "0:51:19", "remaining_time": "1:00:43", "throughput": 1030.79, "total_tokens": 3173912} {"current_steps": 35255, "total_steps": 76960, "loss": 0.1787, "lr": 3.288442560040218e-05, "epoch": 9.161902286902286, "percentage": 45.81, "elapsed_time": "0:51:19", "remaining_time": "1:00:42", "throughput": 1030.78, "total_tokens": 3174328} {"current_steps": 35260, "total_steps": 76960, "loss": 0.2162, "lr": 3.2879045138753305e-05, "epoch": 9.163201663201663, "percentage": 45.82, "elapsed_time": "0:51:19", "remaining_time": "1:00:42", "throughput": 1030.78, "total_tokens": 3174744} {"current_steps": 35265, "total_steps": 76960, "loss": 0.2681, "lr": 3.2873664271877584e-05, "epoch": 9.16450103950104, "percentage": 45.82, "elapsed_time": "0:51:20", "remaining_time": "1:00:42", "throughput": 1030.78, "total_tokens": 3175176} {"current_steps": 35270, "total_steps": 76960, "loss": 0.2742, "lr": 3.286828300005177e-05, "epoch": 9.165800415800415, "percentage": 45.83, "elapsed_time": "0:51:20", "remaining_time": "1:00:41", "throughput": 1030.79, "total_tokens": 3175640} {"current_steps": 35275, "total_steps": 76960, "loss": 0.3989, "lr": 3.2862901323552616e-05, "epoch": 9.167099792099792, "percentage": 45.84, "elapsed_time": "0:51:21", "remaining_time": "1:00:41", "throughput": 1030.8, "total_tokens": 3176104} {"current_steps": 35280, "total_steps": 76960, "loss": 0.3374, "lr": 3.2857519242656915e-05, "epoch": 9.16839916839917, "percentage": 45.84, "elapsed_time": "0:51:21", "remaining_time": "1:00:40", "throughput": 1030.8, "total_tokens": 3176552} {"current_steps": 35285, "total_steps": 76960, "loss": 0.1753, "lr": 3.285213675764147e-05, "epoch": 9.169698544698544, "percentage": 45.85, "elapsed_time": "0:51:22", "remaining_time": "1:00:40", "throughput": 1030.81, "total_tokens": 3177016} {"current_steps": 35290, "total_steps": 76960, "loss": 0.2626, "lr": 3.284675386878311e-05, "epoch": 9.170997920997921, "percentage": 45.85, "elapsed_time": "0:51:22", "remaining_time": "1:00:39", "throughput": 1030.81, "total_tokens": 3177432} {"current_steps": 35295, "total_steps": 76960, "loss": 0.2282, "lr": 3.284137057635868e-05, "epoch": 9.172297297297296, "percentage": 45.86, "elapsed_time": "0:51:22", "remaining_time": "1:00:39", "throughput": 1030.82, "total_tokens": 3177880} {"current_steps": 35300, "total_steps": 76960, "loss": 0.1083, "lr": 3.283598688064505e-05, "epoch": 9.173596673596673, "percentage": 45.87, "elapsed_time": "0:51:23", "remaining_time": "1:00:38", "throughput": 1030.83, "total_tokens": 3178344} {"current_steps": 35305, "total_steps": 76960, "loss": 0.5059, "lr": 3.28306027819191e-05, "epoch": 9.17489604989605, "percentage": 45.87, "elapsed_time": "0:51:23", "remaining_time": "1:00:38", "throughput": 1030.82, "total_tokens": 3178744} {"current_steps": 35310, "total_steps": 76960, "loss": 0.4788, "lr": 3.2825218280457747e-05, "epoch": 9.176195426195425, "percentage": 45.88, "elapsed_time": "0:51:24", "remaining_time": "1:00:37", "throughput": 1030.83, "total_tokens": 3179224} {"current_steps": 35315, "total_steps": 76960, "loss": 0.3085, "lr": 3.281983337653793e-05, "epoch": 9.177494802494802, "percentage": 45.89, "elapsed_time": "0:51:24", "remaining_time": "1:00:37", "throughput": 1030.84, "total_tokens": 3179672} {"current_steps": 35320, "total_steps": 76960, "loss": 0.3312, "lr": 3.281444807043658e-05, "epoch": 9.17879417879418, "percentage": 45.89, "elapsed_time": "0:51:24", "remaining_time": "1:00:36", "throughput": 1030.84, "total_tokens": 3180120} {"current_steps": 35325, "total_steps": 76960, "loss": 0.2615, "lr": 3.280906236243067e-05, "epoch": 9.180093555093555, "percentage": 45.9, "elapsed_time": "0:51:25", "remaining_time": "1:00:36", "throughput": 1030.84, "total_tokens": 3180552} {"current_steps": 35330, "total_steps": 76960, "loss": 0.189, "lr": 3.280367625279722e-05, "epoch": 9.181392931392931, "percentage": 45.91, "elapsed_time": "0:51:25", "remaining_time": "1:00:36", "throughput": 1030.85, "total_tokens": 3181000} {"current_steps": 35335, "total_steps": 76960, "loss": 0.3065, "lr": 3.279828974181322e-05, "epoch": 9.182692307692308, "percentage": 45.91, "elapsed_time": "0:51:26", "remaining_time": "1:00:35", "throughput": 1030.85, "total_tokens": 3181432} {"current_steps": 35340, "total_steps": 76960, "loss": 0.222, "lr": 3.27929028297557e-05, "epoch": 9.183991683991684, "percentage": 45.92, "elapsed_time": "0:51:26", "remaining_time": "1:00:35", "throughput": 1030.86, "total_tokens": 3181880} {"current_steps": 35345, "total_steps": 76960, "loss": 0.1852, "lr": 3.278751551690172e-05, "epoch": 9.18529106029106, "percentage": 45.93, "elapsed_time": "0:51:27", "remaining_time": "1:00:34", "throughput": 1030.87, "total_tokens": 3182344} {"current_steps": 35350, "total_steps": 76960, "loss": 0.1799, "lr": 3.278212780352836e-05, "epoch": 9.186590436590437, "percentage": 45.93, "elapsed_time": "0:51:27", "remaining_time": "1:00:34", "throughput": 1030.88, "total_tokens": 3182808} {"current_steps": 35355, "total_steps": 76960, "loss": 0.6107, "lr": 3.2776739689912714e-05, "epoch": 9.187889812889813, "percentage": 45.94, "elapsed_time": "0:51:27", "remaining_time": "1:00:33", "throughput": 1030.87, "total_tokens": 3183224} {"current_steps": 35360, "total_steps": 76960, "loss": 0.2627, "lr": 3.277135117633188e-05, "epoch": 9.18918918918919, "percentage": 45.95, "elapsed_time": "0:51:28", "remaining_time": "1:00:33", "throughput": 1030.86, "total_tokens": 3183624} {"current_steps": 35365, "total_steps": 76960, "loss": 0.3498, "lr": 3.2765962263063016e-05, "epoch": 9.190488565488565, "percentage": 45.95, "elapsed_time": "0:51:28", "remaining_time": "1:00:32", "throughput": 1030.86, "total_tokens": 3184024} {"current_steps": 35370, "total_steps": 76960, "loss": 0.2465, "lr": 3.2760572950383275e-05, "epoch": 9.191787941787942, "percentage": 45.96, "elapsed_time": "0:51:29", "remaining_time": "1:00:32", "throughput": 1030.87, "total_tokens": 3184488} {"current_steps": 35375, "total_steps": 76960, "loss": 0.3813, "lr": 3.275518323856983e-05, "epoch": 9.193087318087318, "percentage": 45.97, "elapsed_time": "0:51:29", "remaining_time": "1:00:31", "throughput": 1030.88, "total_tokens": 3184952} {"current_steps": 35380, "total_steps": 76960, "loss": 0.3073, "lr": 3.274979312789988e-05, "epoch": 9.194386694386694, "percentage": 45.97, "elapsed_time": "0:51:29", "remaining_time": "1:00:31", "throughput": 1030.89, "total_tokens": 3185432} {"current_steps": 35385, "total_steps": 76960, "loss": 0.2182, "lr": 3.274440261865064e-05, "epoch": 9.19568607068607, "percentage": 45.98, "elapsed_time": "0:51:30", "remaining_time": "1:00:31", "throughput": 1030.9, "total_tokens": 3185880} {"current_steps": 35390, "total_steps": 76960, "loss": 0.2585, "lr": 3.273901171109936e-05, "epoch": 9.196985446985448, "percentage": 45.98, "elapsed_time": "0:51:30", "remaining_time": "1:00:30", "throughput": 1030.9, "total_tokens": 3186328} {"current_steps": 35395, "total_steps": 76960, "loss": 0.2058, "lr": 3.2733620405523294e-05, "epoch": 9.198284823284823, "percentage": 45.99, "elapsed_time": "0:51:31", "remaining_time": "1:00:30", "throughput": 1030.91, "total_tokens": 3186792} {"current_steps": 35400, "total_steps": 76960, "loss": 0.3299, "lr": 3.272822870219971e-05, "epoch": 9.1995841995842, "percentage": 46.0, "elapsed_time": "0:51:31", "remaining_time": "1:00:29", "throughput": 1030.92, "total_tokens": 3187240} {"current_steps": 35405, "total_steps": 76960, "loss": 0.2864, "lr": 3.2722836601405925e-05, "epoch": 9.200883575883577, "percentage": 46.0, "elapsed_time": "0:51:32", "remaining_time": "1:00:29", "throughput": 1030.92, "total_tokens": 3187656} {"current_steps": 35410, "total_steps": 76960, "loss": 0.2294, "lr": 3.271744410341925e-05, "epoch": 9.202182952182952, "percentage": 46.01, "elapsed_time": "0:51:32", "remaining_time": "1:00:28", "throughput": 1030.92, "total_tokens": 3188104} {"current_steps": 35415, "total_steps": 76960, "loss": 0.2707, "lr": 3.2712051208517035e-05, "epoch": 9.203482328482329, "percentage": 46.02, "elapsed_time": "0:51:32", "remaining_time": "1:00:28", "throughput": 1030.92, "total_tokens": 3188536} {"current_steps": 35420, "total_steps": 76960, "loss": 0.2239, "lr": 3.270665791697664e-05, "epoch": 9.204781704781706, "percentage": 46.02, "elapsed_time": "0:51:33", "remaining_time": "1:00:27", "throughput": 1030.94, "total_tokens": 3189032} {"current_steps": 35425, "total_steps": 76960, "loss": 0.0839, "lr": 3.270126422907544e-05, "epoch": 9.20608108108108, "percentage": 46.03, "elapsed_time": "0:51:33", "remaining_time": "1:00:27", "throughput": 1030.95, "total_tokens": 3189480} {"current_steps": 35430, "total_steps": 76960, "loss": 0.2598, "lr": 3.269587014509084e-05, "epoch": 9.207380457380458, "percentage": 46.04, "elapsed_time": "0:51:34", "remaining_time": "1:00:26", "throughput": 1030.95, "total_tokens": 3189912} {"current_steps": 35435, "total_steps": 76960, "loss": 0.0246, "lr": 3.2690475665300266e-05, "epoch": 9.208679833679835, "percentage": 46.04, "elapsed_time": "0:51:34", "remaining_time": "1:00:26", "throughput": 1030.96, "total_tokens": 3190376} {"current_steps": 35440, "total_steps": 76960, "loss": 0.64, "lr": 3.268508078998116e-05, "epoch": 9.20997920997921, "percentage": 46.05, "elapsed_time": "0:51:34", "remaining_time": "1:00:25", "throughput": 1030.95, "total_tokens": 3190792} {"current_steps": 35445, "total_steps": 76960, "loss": 0.2281, "lr": 3.267968551941099e-05, "epoch": 9.211278586278587, "percentage": 46.06, "elapsed_time": "0:51:35", "remaining_time": "1:00:25", "throughput": 1030.96, "total_tokens": 3191240} {"current_steps": 35450, "total_steps": 76960, "loss": 0.1485, "lr": 3.2674289853867226e-05, "epoch": 9.212577962577962, "percentage": 46.06, "elapsed_time": "0:51:35", "remaining_time": "1:00:25", "throughput": 1030.96, "total_tokens": 3191688} {"current_steps": 35455, "total_steps": 76960, "loss": 0.3901, "lr": 3.266889379362739e-05, "epoch": 9.213877338877339, "percentage": 46.07, "elapsed_time": "0:51:36", "remaining_time": "1:00:24", "throughput": 1030.95, "total_tokens": 3192088} {"current_steps": 35460, "total_steps": 76960, "loss": 0.2055, "lr": 3.2663497338968994e-05, "epoch": 9.215176715176716, "percentage": 46.08, "elapsed_time": "0:51:36", "remaining_time": "1:00:24", "throughput": 1030.96, "total_tokens": 3192552} {"current_steps": 35465, "total_steps": 76960, "loss": 0.2938, "lr": 3.265810049016959e-05, "epoch": 9.21647609147609, "percentage": 46.08, "elapsed_time": "0:51:37", "remaining_time": "1:00:23", "throughput": 1030.98, "total_tokens": 3193032} {"current_steps": 35470, "total_steps": 76960, "loss": 0.3009, "lr": 3.2652703247506735e-05, "epoch": 9.217775467775468, "percentage": 46.09, "elapsed_time": "0:51:37", "remaining_time": "1:00:23", "throughput": 1031.0, "total_tokens": 3193512} {"current_steps": 35475, "total_steps": 76960, "loss": 0.3756, "lr": 3.264730561125802e-05, "epoch": 9.219074844074845, "percentage": 46.1, "elapsed_time": "0:51:37", "remaining_time": "1:00:22", "throughput": 1031.01, "total_tokens": 3193992} {"current_steps": 35480, "total_steps": 76960, "loss": 0.4139, "lr": 3.264190758170106e-05, "epoch": 9.22037422037422, "percentage": 46.1, "elapsed_time": "0:51:38", "remaining_time": "1:00:22", "throughput": 1031.01, "total_tokens": 3194424} {"current_steps": 35485, "total_steps": 76960, "loss": 0.2821, "lr": 3.263650915911346e-05, "epoch": 9.221673596673597, "percentage": 46.11, "elapsed_time": "0:51:38", "remaining_time": "1:00:21", "throughput": 1031.03, "total_tokens": 3194888} {"current_steps": 35490, "total_steps": 76960, "loss": 0.1707, "lr": 3.263111034377288e-05, "epoch": 9.222972972972974, "percentage": 46.11, "elapsed_time": "0:51:39", "remaining_time": "1:00:21", "throughput": 1031.03, "total_tokens": 3195320} {"current_steps": 35495, "total_steps": 76960, "loss": 0.2332, "lr": 3.2625711135956986e-05, "epoch": 9.224272349272349, "percentage": 46.12, "elapsed_time": "0:51:39", "remaining_time": "1:00:20", "throughput": 1031.03, "total_tokens": 3195768} {"current_steps": 35500, "total_steps": 76960, "loss": 0.304, "lr": 3.262031153594347e-05, "epoch": 9.225571725571726, "percentage": 46.13, "elapsed_time": "0:51:40", "remaining_time": "1:00:20", "throughput": 1031.04, "total_tokens": 3196248} {"current_steps": 35505, "total_steps": 76960, "loss": 0.125, "lr": 3.261491154401001e-05, "epoch": 9.226871101871103, "percentage": 46.13, "elapsed_time": "0:51:40", "remaining_time": "1:00:20", "throughput": 1031.05, "total_tokens": 3196728} {"current_steps": 35510, "total_steps": 76960, "loss": 0.2112, "lr": 3.2609511160434366e-05, "epoch": 9.228170478170478, "percentage": 46.14, "elapsed_time": "0:51:40", "remaining_time": "1:00:19", "throughput": 1031.04, "total_tokens": 3197128} {"current_steps": 35515, "total_steps": 76960, "loss": 0.1351, "lr": 3.260411038549427e-05, "epoch": 9.229469854469855, "percentage": 46.15, "elapsed_time": "0:51:41", "remaining_time": "1:00:19", "throughput": 1031.05, "total_tokens": 3197608} {"current_steps": 35520, "total_steps": 76960, "loss": 0.3349, "lr": 3.2598709219467485e-05, "epoch": 9.23076923076923, "percentage": 46.15, "elapsed_time": "0:51:41", "remaining_time": "1:00:18", "throughput": 1031.05, "total_tokens": 3198040} {"current_steps": 35525, "total_steps": 76960, "loss": 0.4356, "lr": 3.259330766263181e-05, "epoch": 9.232068607068607, "percentage": 46.16, "elapsed_time": "0:51:42", "remaining_time": "1:00:18", "throughput": 1031.07, "total_tokens": 3198520} {"current_steps": 35530, "total_steps": 76960, "loss": 0.2473, "lr": 3.2587905715265047e-05, "epoch": 9.233367983367984, "percentage": 46.17, "elapsed_time": "0:51:42", "remaining_time": "1:00:17", "throughput": 1031.07, "total_tokens": 3198968} {"current_steps": 35535, "total_steps": 76960, "loss": 0.1712, "lr": 3.258250337764502e-05, "epoch": 9.234667359667359, "percentage": 46.17, "elapsed_time": "0:51:42", "remaining_time": "1:00:17", "throughput": 1031.08, "total_tokens": 3199432} {"current_steps": 35540, "total_steps": 76960, "loss": 0.239, "lr": 3.257710065004958e-05, "epoch": 9.235966735966736, "percentage": 46.18, "elapsed_time": "0:51:43", "remaining_time": "1:00:16", "throughput": 1031.08, "total_tokens": 3199848} {"current_steps": 35545, "total_steps": 76960, "loss": 0.2571, "lr": 3.2571697532756595e-05, "epoch": 9.237266112266113, "percentage": 46.19, "elapsed_time": "0:51:43", "remaining_time": "1:00:16", "throughput": 1031.08, "total_tokens": 3200296} {"current_steps": 35550, "total_steps": 76960, "loss": 0.2275, "lr": 3.2566294026043956e-05, "epoch": 9.238565488565488, "percentage": 46.19, "elapsed_time": "0:51:44", "remaining_time": "1:00:15", "throughput": 1031.1, "total_tokens": 3200776} {"current_steps": 35555, "total_steps": 76960, "loss": 0.3728, "lr": 3.2560890130189555e-05, "epoch": 9.239864864864865, "percentage": 46.2, "elapsed_time": "0:51:44", "remaining_time": "1:00:15", "throughput": 1031.12, "total_tokens": 3201272} {"current_steps": 35560, "total_steps": 76960, "loss": 0.2251, "lr": 3.255548584547133e-05, "epoch": 9.241164241164242, "percentage": 46.21, "elapsed_time": "0:51:45", "remaining_time": "1:00:15", "throughput": 1031.12, "total_tokens": 3201704} {"current_steps": 35565, "total_steps": 76960, "loss": 0.2701, "lr": 3.255008117216723e-05, "epoch": 9.242463617463617, "percentage": 46.21, "elapsed_time": "0:51:45", "remaining_time": "1:00:14", "throughput": 1031.12, "total_tokens": 3202152} {"current_steps": 35570, "total_steps": 76960, "loss": 0.2543, "lr": 3.2544676110555236e-05, "epoch": 9.243762993762994, "percentage": 46.22, "elapsed_time": "0:51:45", "remaining_time": "1:00:14", "throughput": 1031.13, "total_tokens": 3202616} {"current_steps": 35575, "total_steps": 76960, "loss": 0.274, "lr": 3.25392706609133e-05, "epoch": 9.24506237006237, "percentage": 46.23, "elapsed_time": "0:51:46", "remaining_time": "1:00:13", "throughput": 1031.13, "total_tokens": 3203064} {"current_steps": 35580, "total_steps": 76960, "loss": 0.3378, "lr": 3.253386482351946e-05, "epoch": 9.246361746361746, "percentage": 46.23, "elapsed_time": "0:51:46", "remaining_time": "1:00:13", "throughput": 1031.14, "total_tokens": 3203528} {"current_steps": 35585, "total_steps": 76960, "loss": 0.3488, "lr": 3.2528458598651734e-05, "epoch": 9.247661122661123, "percentage": 46.24, "elapsed_time": "0:51:47", "remaining_time": "1:00:12", "throughput": 1031.14, "total_tokens": 3203960} {"current_steps": 35590, "total_steps": 76960, "loss": 0.4088, "lr": 3.252305198658817e-05, "epoch": 9.248960498960498, "percentage": 46.24, "elapsed_time": "0:51:47", "remaining_time": "1:00:12", "throughput": 1031.15, "total_tokens": 3204408} {"current_steps": 35595, "total_steps": 76960, "loss": 0.1941, "lr": 3.251764498760683e-05, "epoch": 9.250259875259875, "percentage": 46.25, "elapsed_time": "0:51:48", "remaining_time": "1:00:11", "throughput": 1031.16, "total_tokens": 3204872} {"current_steps": 35600, "total_steps": 76960, "loss": 0.1526, "lr": 3.2512237601985805e-05, "epoch": 9.251559251559252, "percentage": 46.26, "elapsed_time": "0:51:48", "remaining_time": "1:00:11", "throughput": 1031.17, "total_tokens": 3205352} {"current_steps": 35605, "total_steps": 76960, "loss": 0.0844, "lr": 3.2506829830003205e-05, "epoch": 9.252858627858627, "percentage": 46.26, "elapsed_time": "0:51:48", "remaining_time": "1:00:10", "throughput": 1031.18, "total_tokens": 3205800} {"current_steps": 35610, "total_steps": 76960, "loss": 0.348, "lr": 3.2501421671937154e-05, "epoch": 9.254158004158004, "percentage": 46.27, "elapsed_time": "0:51:49", "remaining_time": "1:00:10", "throughput": 1031.18, "total_tokens": 3206248} {"current_steps": 35615, "total_steps": 76960, "loss": 0.497, "lr": 3.24960131280658e-05, "epoch": 9.255457380457381, "percentage": 46.28, "elapsed_time": "0:51:49", "remaining_time": "1:00:10", "throughput": 1031.19, "total_tokens": 3206712} {"current_steps": 35620, "total_steps": 76960, "loss": 0.4857, "lr": 3.249060419866731e-05, "epoch": 9.256756756756756, "percentage": 46.28, "elapsed_time": "0:51:50", "remaining_time": "1:00:09", "throughput": 1031.2, "total_tokens": 3207160} {"current_steps": 35625, "total_steps": 76960, "loss": 0.3511, "lr": 3.248519488401986e-05, "epoch": 9.258056133056133, "percentage": 46.29, "elapsed_time": "0:51:50", "remaining_time": "1:00:09", "throughput": 1031.2, "total_tokens": 3207608} {"current_steps": 35630, "total_steps": 76960, "loss": 0.2565, "lr": 3.2479785184401674e-05, "epoch": 9.25935550935551, "percentage": 46.3, "elapsed_time": "0:51:50", "remaining_time": "1:00:08", "throughput": 1031.21, "total_tokens": 3208072} {"current_steps": 35635, "total_steps": 76960, "loss": 0.1187, "lr": 3.247437510009096e-05, "epoch": 9.260654885654885, "percentage": 46.3, "elapsed_time": "0:51:51", "remaining_time": "1:00:08", "throughput": 1031.23, "total_tokens": 3208552} {"current_steps": 35640, "total_steps": 76960, "loss": 0.1533, "lr": 3.2468964631365984e-05, "epoch": 9.261954261954262, "percentage": 46.31, "elapsed_time": "0:51:51", "remaining_time": "1:00:07", "throughput": 1031.23, "total_tokens": 3209000} {"current_steps": 35645, "total_steps": 76960, "loss": 0.2082, "lr": 3.2463553778505e-05, "epoch": 9.263253638253639, "percentage": 46.32, "elapsed_time": "0:51:52", "remaining_time": "1:00:07", "throughput": 1031.24, "total_tokens": 3209448} {"current_steps": 35650, "total_steps": 76960, "loss": 0.2323, "lr": 3.245814254178628e-05, "epoch": 9.264553014553014, "percentage": 46.32, "elapsed_time": "0:51:52", "remaining_time": "1:00:06", "throughput": 1031.24, "total_tokens": 3209880} {"current_steps": 35655, "total_steps": 76960, "loss": 0.0476, "lr": 3.245273092148816e-05, "epoch": 9.265852390852391, "percentage": 46.33, "elapsed_time": "0:51:53", "remaining_time": "1:00:06", "throughput": 1031.25, "total_tokens": 3210344} {"current_steps": 35660, "total_steps": 76960, "loss": 0.1835, "lr": 3.244731891788893e-05, "epoch": 9.267151767151766, "percentage": 46.34, "elapsed_time": "0:51:53", "remaining_time": "1:00:05", "throughput": 1031.26, "total_tokens": 3210824} {"current_steps": 35665, "total_steps": 76960, "loss": 0.2945, "lr": 3.244190653126696e-05, "epoch": 9.268451143451143, "percentage": 46.34, "elapsed_time": "0:51:53", "remaining_time": "1:00:05", "throughput": 1031.26, "total_tokens": 3211256} {"current_steps": 35670, "total_steps": 76960, "loss": 0.4035, "lr": 3.2436493761900614e-05, "epoch": 9.26975051975052, "percentage": 46.35, "elapsed_time": "0:51:54", "remaining_time": "1:00:05", "throughput": 1031.26, "total_tokens": 3211688} {"current_steps": 35675, "total_steps": 76960, "loss": 0.3925, "lr": 3.2431080610068264e-05, "epoch": 9.271049896049895, "percentage": 46.36, "elapsed_time": "0:51:54", "remaining_time": "1:00:04", "throughput": 1031.27, "total_tokens": 3212152} {"current_steps": 35680, "total_steps": 76960, "loss": 0.2322, "lr": 3.242566707604832e-05, "epoch": 9.272349272349272, "percentage": 46.36, "elapsed_time": "0:51:55", "remaining_time": "1:00:04", "throughput": 1031.27, "total_tokens": 3212600} {"current_steps": 35685, "total_steps": 76960, "loss": 0.1497, "lr": 3.242025316011921e-05, "epoch": 9.27364864864865, "percentage": 46.37, "elapsed_time": "0:51:55", "remaining_time": "1:00:03", "throughput": 1031.27, "total_tokens": 3213048} {"current_steps": 35690, "total_steps": 76960, "loss": 0.1229, "lr": 3.241483886255936e-05, "epoch": 9.274948024948024, "percentage": 46.37, "elapsed_time": "0:51:56", "remaining_time": "1:00:03", "throughput": 1031.27, "total_tokens": 3213480} {"current_steps": 35695, "total_steps": 76960, "loss": 0.2368, "lr": 3.240942418364724e-05, "epoch": 9.276247401247401, "percentage": 46.38, "elapsed_time": "0:51:56", "remaining_time": "1:00:02", "throughput": 1031.28, "total_tokens": 3213928} {"current_steps": 35700, "total_steps": 76960, "loss": 0.3349, "lr": 3.2404009123661336e-05, "epoch": 9.277546777546778, "percentage": 46.39, "elapsed_time": "0:51:56", "remaining_time": "1:00:02", "throughput": 1031.27, "total_tokens": 3214360} {"current_steps": 35705, "total_steps": 76960, "loss": 0.1315, "lr": 3.239859368288015e-05, "epoch": 9.278846153846153, "percentage": 46.39, "elapsed_time": "0:51:57", "remaining_time": "1:00:01", "throughput": 1031.27, "total_tokens": 3214792} {"current_steps": 35710, "total_steps": 76960, "loss": 0.4049, "lr": 3.2393177861582206e-05, "epoch": 9.28014553014553, "percentage": 46.4, "elapsed_time": "0:51:57", "remaining_time": "1:00:01", "throughput": 1031.28, "total_tokens": 3215256} {"current_steps": 35715, "total_steps": 76960, "loss": 0.3886, "lr": 3.238776166004604e-05, "epoch": 9.281444906444907, "percentage": 46.41, "elapsed_time": "0:51:58", "remaining_time": "1:00:00", "throughput": 1031.28, "total_tokens": 3215704} {"current_steps": 35720, "total_steps": 76960, "loss": 0.238, "lr": 3.238234507855021e-05, "epoch": 9.282744282744282, "percentage": 46.41, "elapsed_time": "0:51:58", "remaining_time": "1:00:00", "throughput": 1031.29, "total_tokens": 3216168} {"current_steps": 35725, "total_steps": 76960, "loss": 0.2246, "lr": 3.23769281173733e-05, "epoch": 9.28404365904366, "percentage": 46.42, "elapsed_time": "0:51:58", "remaining_time": "1:00:00", "throughput": 1031.3, "total_tokens": 3216632} {"current_steps": 35730, "total_steps": 76960, "loss": 0.2066, "lr": 3.237151077679391e-05, "epoch": 9.285343035343036, "percentage": 46.43, "elapsed_time": "0:51:59", "remaining_time": "0:59:59", "throughput": 1031.3, "total_tokens": 3217064} {"current_steps": 35735, "total_steps": 76960, "loss": 0.4044, "lr": 3.236609305709066e-05, "epoch": 9.286642411642411, "percentage": 46.43, "elapsed_time": "0:51:59", "remaining_time": "0:59:59", "throughput": 1031.31, "total_tokens": 3217512} {"current_steps": 35740, "total_steps": 76960, "loss": 0.2474, "lr": 3.2360674958542184e-05, "epoch": 9.287941787941788, "percentage": 46.44, "elapsed_time": "0:52:00", "remaining_time": "0:59:58", "throughput": 1031.3, "total_tokens": 3217944} {"current_steps": 35745, "total_steps": 76960, "loss": 0.1718, "lr": 3.2355256481427145e-05, "epoch": 9.289241164241163, "percentage": 46.45, "elapsed_time": "0:52:00", "remaining_time": "0:59:58", "throughput": 1031.3, "total_tokens": 3218360} {"current_steps": 35750, "total_steps": 76960, "loss": 0.2947, "lr": 3.234983762602422e-05, "epoch": 9.29054054054054, "percentage": 46.45, "elapsed_time": "0:52:01", "remaining_time": "0:59:57", "throughput": 1031.29, "total_tokens": 3218792} {"current_steps": 35755, "total_steps": 76960, "loss": 0.1855, "lr": 3.234441839261209e-05, "epoch": 9.291839916839917, "percentage": 46.46, "elapsed_time": "0:52:01", "remaining_time": "0:59:57", "throughput": 1031.31, "total_tokens": 3219288} {"current_steps": 35760, "total_steps": 76960, "loss": 0.2916, "lr": 3.2338998781469485e-05, "epoch": 9.293139293139292, "percentage": 46.47, "elapsed_time": "0:52:01", "remaining_time": "0:59:56", "throughput": 1031.31, "total_tokens": 3219720} {"current_steps": 35765, "total_steps": 76960, "loss": 0.3353, "lr": 3.233357879287515e-05, "epoch": 9.29443866943867, "percentage": 46.47, "elapsed_time": "0:52:02", "remaining_time": "0:59:56", "throughput": 1031.3, "total_tokens": 3220136} {"current_steps": 35770, "total_steps": 76960, "loss": 0.2623, "lr": 3.232815842710784e-05, "epoch": 9.295738045738046, "percentage": 46.48, "elapsed_time": "0:52:02", "remaining_time": "0:59:56", "throughput": 1031.31, "total_tokens": 3220600} {"current_steps": 35775, "total_steps": 76960, "loss": 0.3206, "lr": 3.2322737684446304e-05, "epoch": 9.297037422037421, "percentage": 46.49, "elapsed_time": "0:52:03", "remaining_time": "0:59:55", "throughput": 1031.33, "total_tokens": 3221096} {"current_steps": 35780, "total_steps": 76960, "loss": 0.2772, "lr": 3.231731656516936e-05, "epoch": 9.298336798336798, "percentage": 46.49, "elapsed_time": "0:52:03", "remaining_time": "0:59:55", "throughput": 1031.33, "total_tokens": 3221528} {"current_steps": 35785, "total_steps": 76960, "loss": 0.2243, "lr": 3.231189506955581e-05, "epoch": 9.299636174636175, "percentage": 46.5, "elapsed_time": "0:52:04", "remaining_time": "0:59:54", "throughput": 1031.34, "total_tokens": 3221992} {"current_steps": 35790, "total_steps": 76960, "loss": 0.2537, "lr": 3.2306473197884494e-05, "epoch": 9.30093555093555, "percentage": 46.5, "elapsed_time": "0:52:04", "remaining_time": "0:59:54", "throughput": 1031.35, "total_tokens": 3222440} {"current_steps": 35795, "total_steps": 76960, "loss": 0.2586, "lr": 3.2301050950434255e-05, "epoch": 9.302234927234927, "percentage": 46.51, "elapsed_time": "0:52:04", "remaining_time": "0:59:53", "throughput": 1031.35, "total_tokens": 3222888} {"current_steps": 35800, "total_steps": 76960, "loss": 0.2961, "lr": 3.229562832748398e-05, "epoch": 9.303534303534304, "percentage": 46.52, "elapsed_time": "0:52:05", "remaining_time": "0:59:53", "throughput": 1031.37, "total_tokens": 3223384} {"current_steps": 35805, "total_steps": 76960, "loss": 0.4133, "lr": 3.2290205329312544e-05, "epoch": 9.30483367983368, "percentage": 46.52, "elapsed_time": "0:52:05", "remaining_time": "0:59:52", "throughput": 1031.38, "total_tokens": 3223832} {"current_steps": 35810, "total_steps": 76960, "loss": 0.2805, "lr": 3.2284781956198866e-05, "epoch": 9.306133056133056, "percentage": 46.53, "elapsed_time": "0:52:06", "remaining_time": "0:59:52", "throughput": 1031.39, "total_tokens": 3224280} {"current_steps": 35815, "total_steps": 76960, "loss": 0.2649, "lr": 3.2279358208421875e-05, "epoch": 9.307432432432432, "percentage": 46.54, "elapsed_time": "0:52:06", "remaining_time": "0:59:51", "throughput": 1031.4, "total_tokens": 3224760} {"current_steps": 35820, "total_steps": 76960, "loss": 0.2326, "lr": 3.227393408626051e-05, "epoch": 9.308731808731808, "percentage": 46.54, "elapsed_time": "0:52:06", "remaining_time": "0:59:51", "throughput": 1031.41, "total_tokens": 3225224} {"current_steps": 35825, "total_steps": 76960, "loss": 0.2409, "lr": 3.226850958999375e-05, "epoch": 9.310031185031185, "percentage": 46.55, "elapsed_time": "0:52:07", "remaining_time": "0:59:50", "throughput": 1031.42, "total_tokens": 3225672} {"current_steps": 35830, "total_steps": 76960, "loss": 0.2121, "lr": 3.226308471990057e-05, "epoch": 9.31133056133056, "percentage": 46.56, "elapsed_time": "0:52:07", "remaining_time": "0:59:50", "throughput": 1031.41, "total_tokens": 3226072} {"current_steps": 35835, "total_steps": 76960, "loss": 0.2121, "lr": 3.225765947625999e-05, "epoch": 9.312629937629938, "percentage": 46.56, "elapsed_time": "0:52:08", "remaining_time": "0:59:50", "throughput": 1031.41, "total_tokens": 3226504} {"current_steps": 35840, "total_steps": 76960, "loss": 0.3858, "lr": 3.225223385935102e-05, "epoch": 9.313929313929314, "percentage": 46.57, "elapsed_time": "0:52:08", "remaining_time": "0:59:49", "throughput": 1031.41, "total_tokens": 3226936} {"current_steps": 35845, "total_steps": 76960, "loss": 0.3443, "lr": 3.224680786945272e-05, "epoch": 9.31522869022869, "percentage": 46.58, "elapsed_time": "0:52:09", "remaining_time": "0:59:49", "throughput": 1031.41, "total_tokens": 3227352} {"current_steps": 35850, "total_steps": 76960, "loss": 0.2428, "lr": 3.224138150684415e-05, "epoch": 9.316528066528067, "percentage": 46.58, "elapsed_time": "0:52:09", "remaining_time": "0:59:48", "throughput": 1031.41, "total_tokens": 3227800} {"current_steps": 35855, "total_steps": 76960, "loss": 0.2053, "lr": 3.223595477180439e-05, "epoch": 9.317827442827443, "percentage": 46.59, "elapsed_time": "0:52:09", "remaining_time": "0:59:48", "throughput": 1031.42, "total_tokens": 3228232} {"current_steps": 35860, "total_steps": 76960, "loss": 0.2853, "lr": 3.223052766461254e-05, "epoch": 9.319126819126819, "percentage": 46.6, "elapsed_time": "0:52:10", "remaining_time": "0:59:47", "throughput": 1031.42, "total_tokens": 3228680} {"current_steps": 35865, "total_steps": 76960, "loss": 0.2462, "lr": 3.222510018554773e-05, "epoch": 9.320426195426196, "percentage": 46.6, "elapsed_time": "0:52:10", "remaining_time": "0:59:47", "throughput": 1031.42, "total_tokens": 3229112} {"current_steps": 35870, "total_steps": 76960, "loss": 0.3442, "lr": 3.221967233488909e-05, "epoch": 9.321725571725572, "percentage": 46.61, "elapsed_time": "0:52:11", "remaining_time": "0:59:46", "throughput": 1031.43, "total_tokens": 3229576} {"current_steps": 35875, "total_steps": 76960, "loss": 0.2694, "lr": 3.2214244112915795e-05, "epoch": 9.323024948024948, "percentage": 46.62, "elapsed_time": "0:52:11", "remaining_time": "0:59:46", "throughput": 1031.45, "total_tokens": 3230040} {"current_steps": 35880, "total_steps": 76960, "loss": 0.2007, "lr": 3.2208815519907e-05, "epoch": 9.324324324324325, "percentage": 46.62, "elapsed_time": "0:52:11", "remaining_time": "0:59:45", "throughput": 1031.44, "total_tokens": 3230440} {"current_steps": 35885, "total_steps": 76960, "loss": 0.2847, "lr": 3.220338655614192e-05, "epoch": 9.325623700623701, "percentage": 46.63, "elapsed_time": "0:52:12", "remaining_time": "0:59:45", "throughput": 1031.44, "total_tokens": 3230888} {"current_steps": 35890, "total_steps": 76960, "loss": 0.2736, "lr": 3.2197957221899764e-05, "epoch": 9.326923076923077, "percentage": 46.63, "elapsed_time": "0:52:12", "remaining_time": "0:59:44", "throughput": 1031.45, "total_tokens": 3231336} {"current_steps": 35895, "total_steps": 76960, "loss": 0.3321, "lr": 3.2192527517459774e-05, "epoch": 9.328222453222454, "percentage": 46.64, "elapsed_time": "0:52:13", "remaining_time": "0:59:44", "throughput": 1031.44, "total_tokens": 3231752} {"current_steps": 35900, "total_steps": 76960, "loss": 0.2147, "lr": 3.21870974431012e-05, "epoch": 9.329521829521829, "percentage": 46.65, "elapsed_time": "0:52:13", "remaining_time": "0:59:44", "throughput": 1031.45, "total_tokens": 3232216} {"current_steps": 35905, "total_steps": 76960, "loss": 0.1637, "lr": 3.2181666999103324e-05, "epoch": 9.330821205821206, "percentage": 46.65, "elapsed_time": "0:52:14", "remaining_time": "0:59:43", "throughput": 1031.47, "total_tokens": 3232696} {"current_steps": 35910, "total_steps": 76960, "loss": 0.1834, "lr": 3.217623618574543e-05, "epoch": 9.332120582120583, "percentage": 46.66, "elapsed_time": "0:52:14", "remaining_time": "0:59:43", "throughput": 1031.48, "total_tokens": 3233144} {"current_steps": 35915, "total_steps": 76960, "loss": 0.2755, "lr": 3.2170805003306824e-05, "epoch": 9.333419958419958, "percentage": 46.67, "elapsed_time": "0:52:14", "remaining_time": "0:59:42", "throughput": 1031.48, "total_tokens": 3233576} {"current_steps": 35920, "total_steps": 76960, "loss": 0.2804, "lr": 3.216537345206686e-05, "epoch": 9.334719334719335, "percentage": 46.67, "elapsed_time": "0:52:15", "remaining_time": "0:59:42", "throughput": 1031.48, "total_tokens": 3234024} {"current_steps": 35925, "total_steps": 76960, "loss": 0.2182, "lr": 3.215994153230487e-05, "epoch": 9.336018711018712, "percentage": 46.68, "elapsed_time": "0:52:15", "remaining_time": "0:59:41", "throughput": 1031.48, "total_tokens": 3234456} {"current_steps": 35930, "total_steps": 76960, "loss": 0.2402, "lr": 3.215450924430022e-05, "epoch": 9.337318087318087, "percentage": 46.69, "elapsed_time": "0:52:16", "remaining_time": "0:59:41", "throughput": 1031.48, "total_tokens": 3234888} {"current_steps": 35935, "total_steps": 76960, "loss": 0.2089, "lr": 3.214907658833231e-05, "epoch": 9.338617463617464, "percentage": 46.69, "elapsed_time": "0:52:16", "remaining_time": "0:59:40", "throughput": 1031.5, "total_tokens": 3235352} {"current_steps": 35940, "total_steps": 76960, "loss": 0.2632, "lr": 3.214364356468054e-05, "epoch": 9.33991683991684, "percentage": 46.7, "elapsed_time": "0:52:16", "remaining_time": "0:59:40", "throughput": 1031.53, "total_tokens": 3235880} {"current_steps": 35945, "total_steps": 76960, "loss": 0.2866, "lr": 3.213821017362434e-05, "epoch": 9.341216216216216, "percentage": 46.71, "elapsed_time": "0:52:17", "remaining_time": "0:59:39", "throughput": 1031.55, "total_tokens": 3236360} {"current_steps": 35950, "total_steps": 76960, "loss": 0.2758, "lr": 3.2132776415443145e-05, "epoch": 9.342515592515593, "percentage": 46.71, "elapsed_time": "0:52:17", "remaining_time": "0:59:39", "throughput": 1031.56, "total_tokens": 3236824} {"current_steps": 35955, "total_steps": 76960, "loss": 0.254, "lr": 3.212734229041643e-05, "epoch": 9.34381496881497, "percentage": 46.72, "elapsed_time": "0:52:18", "remaining_time": "0:59:38", "throughput": 1031.57, "total_tokens": 3237288} {"current_steps": 35960, "total_steps": 76960, "loss": 0.2508, "lr": 3.212190779882367e-05, "epoch": 9.345114345114345, "percentage": 46.73, "elapsed_time": "0:52:18", "remaining_time": "0:59:38", "throughput": 1031.58, "total_tokens": 3237768} {"current_steps": 35965, "total_steps": 76960, "loss": 0.2009, "lr": 3.211647294094437e-05, "epoch": 9.346413721413722, "percentage": 46.73, "elapsed_time": "0:52:19", "remaining_time": "0:59:38", "throughput": 1031.59, "total_tokens": 3238200} {"current_steps": 35970, "total_steps": 76960, "loss": 0.2919, "lr": 3.2111037717058045e-05, "epoch": 9.347713097713097, "percentage": 46.74, "elapsed_time": "0:52:19", "remaining_time": "0:59:37", "throughput": 1031.59, "total_tokens": 3238648} {"current_steps": 35975, "total_steps": 76960, "loss": 0.2132, "lr": 3.210560212744424e-05, "epoch": 9.349012474012474, "percentage": 46.75, "elapsed_time": "0:52:19", "remaining_time": "0:59:37", "throughput": 1031.59, "total_tokens": 3239080} {"current_steps": 35980, "total_steps": 76960, "loss": 0.3762, "lr": 3.210016617238251e-05, "epoch": 9.35031185031185, "percentage": 46.75, "elapsed_time": "0:52:20", "remaining_time": "0:59:36", "throughput": 1031.6, "total_tokens": 3239528} {"current_steps": 35985, "total_steps": 76960, "loss": 0.2607, "lr": 3.209472985215243e-05, "epoch": 9.351611226611226, "percentage": 46.76, "elapsed_time": "0:52:20", "remaining_time": "0:59:36", "throughput": 1031.6, "total_tokens": 3239960} {"current_steps": 35990, "total_steps": 76960, "loss": 0.2625, "lr": 3.208929316703359e-05, "epoch": 9.352910602910603, "percentage": 46.76, "elapsed_time": "0:52:21", "remaining_time": "0:59:35", "throughput": 1031.61, "total_tokens": 3240424} {"current_steps": 35995, "total_steps": 76960, "loss": 0.2355, "lr": 3.208385611730561e-05, "epoch": 9.35420997920998, "percentage": 46.77, "elapsed_time": "0:52:21", "remaining_time": "0:59:35", "throughput": 1031.62, "total_tokens": 3240872} {"current_steps": 36000, "total_steps": 76960, "loss": 0.2937, "lr": 3.2078418703248126e-05, "epoch": 9.355509355509355, "percentage": 46.78, "elapsed_time": "0:52:21", "remaining_time": "0:59:34", "throughput": 1031.62, "total_tokens": 3241320} {"current_steps": 36005, "total_steps": 76960, "loss": 0.2529, "lr": 3.207298092514079e-05, "epoch": 9.356808731808732, "percentage": 46.78, "elapsed_time": "0:52:22", "remaining_time": "0:59:34", "throughput": 1031.64, "total_tokens": 3241784} {"current_steps": 36010, "total_steps": 76960, "loss": 0.2582, "lr": 3.206754278326326e-05, "epoch": 9.358108108108109, "percentage": 46.79, "elapsed_time": "0:52:22", "remaining_time": "0:59:33", "throughput": 1031.63, "total_tokens": 3242200} {"current_steps": 36015, "total_steps": 76960, "loss": 0.2231, "lr": 3.206210427789524e-05, "epoch": 9.359407484407484, "percentage": 46.8, "elapsed_time": "0:52:23", "remaining_time": "0:59:33", "throughput": 1031.64, "total_tokens": 3242648} {"current_steps": 36020, "total_steps": 76960, "loss": 0.241, "lr": 3.2056665409316426e-05, "epoch": 9.36070686070686, "percentage": 46.8, "elapsed_time": "0:52:23", "remaining_time": "0:59:33", "throughput": 1031.65, "total_tokens": 3243128} {"current_steps": 36025, "total_steps": 76960, "loss": 0.1512, "lr": 3.205122617780655e-05, "epoch": 9.362006237006238, "percentage": 46.81, "elapsed_time": "0:52:24", "remaining_time": "0:59:32", "throughput": 1031.65, "total_tokens": 3243560} {"current_steps": 36030, "total_steps": 76960, "loss": 0.3254, "lr": 3.2045786583645354e-05, "epoch": 9.363305613305613, "percentage": 46.82, "elapsed_time": "0:52:24", "remaining_time": "0:59:32", "throughput": 1031.67, "total_tokens": 3244040} {"current_steps": 36035, "total_steps": 76960, "loss": 0.2349, "lr": 3.2040346627112604e-05, "epoch": 9.36460498960499, "percentage": 46.82, "elapsed_time": "0:52:24", "remaining_time": "0:59:31", "throughput": 1031.68, "total_tokens": 3244488} {"current_steps": 36040, "total_steps": 76960, "loss": 0.2924, "lr": 3.2034906308488075e-05, "epoch": 9.365904365904367, "percentage": 46.83, "elapsed_time": "0:52:25", "remaining_time": "0:59:31", "throughput": 1031.69, "total_tokens": 3244952} {"current_steps": 36045, "total_steps": 76960, "loss": 0.2958, "lr": 3.2029465628051586e-05, "epoch": 9.367203742203742, "percentage": 46.84, "elapsed_time": "0:52:25", "remaining_time": "0:59:30", "throughput": 1031.7, "total_tokens": 3245416} {"current_steps": 36050, "total_steps": 76960, "loss": 0.3053, "lr": 3.202402458608294e-05, "epoch": 9.368503118503119, "percentage": 46.84, "elapsed_time": "0:52:26", "remaining_time": "0:59:30", "throughput": 1031.71, "total_tokens": 3245864} {"current_steps": 36055, "total_steps": 76960, "loss": 0.2138, "lr": 3.201858318286198e-05, "epoch": 9.369802494802494, "percentage": 46.85, "elapsed_time": "0:52:26", "remaining_time": "0:59:29", "throughput": 1031.72, "total_tokens": 3246328} {"current_steps": 36060, "total_steps": 76960, "loss": 0.2985, "lr": 3.201314141866856e-05, "epoch": 9.371101871101871, "percentage": 46.86, "elapsed_time": "0:52:26", "remaining_time": "0:59:29", "throughput": 1031.73, "total_tokens": 3246792} {"current_steps": 36065, "total_steps": 76960, "loss": 0.2591, "lr": 3.2007699293782555e-05, "epoch": 9.372401247401248, "percentage": 46.86, "elapsed_time": "0:52:27", "remaining_time": "0:59:28", "throughput": 1031.72, "total_tokens": 3247208} {"current_steps": 36070, "total_steps": 76960, "loss": 0.3324, "lr": 3.2002256808483864e-05, "epoch": 9.373700623700623, "percentage": 46.87, "elapsed_time": "0:52:27", "remaining_time": "0:59:28", "throughput": 1031.73, "total_tokens": 3247640} {"current_steps": 36075, "total_steps": 76960, "loss": 0.2576, "lr": 3.19968139630524e-05, "epoch": 9.375, "percentage": 46.88, "elapsed_time": "0:52:28", "remaining_time": "0:59:27", "throughput": 1031.73, "total_tokens": 3248088} {"current_steps": 36080, "total_steps": 76960, "loss": 0.3878, "lr": 3.199137075776809e-05, "epoch": 9.376299376299377, "percentage": 46.88, "elapsed_time": "0:52:28", "remaining_time": "0:59:27", "throughput": 1031.74, "total_tokens": 3248536} {"current_steps": 36085, "total_steps": 76960, "loss": 0.3054, "lr": 3.1985927192910875e-05, "epoch": 9.377598752598752, "percentage": 46.89, "elapsed_time": "0:52:29", "remaining_time": "0:59:27", "throughput": 1031.75, "total_tokens": 3249000} {"current_steps": 36090, "total_steps": 76960, "loss": 0.2501, "lr": 3.198048326876074e-05, "epoch": 9.378898128898129, "percentage": 46.89, "elapsed_time": "0:52:29", "remaining_time": "0:59:26", "throughput": 1031.74, "total_tokens": 3249416} {"current_steps": 36095, "total_steps": 76960, "loss": 0.2325, "lr": 3.197503898559765e-05, "epoch": 9.380197505197506, "percentage": 46.9, "elapsed_time": "0:52:29", "remaining_time": "0:59:26", "throughput": 1031.74, "total_tokens": 3249832} {"current_steps": 36100, "total_steps": 76960, "loss": 0.2182, "lr": 3.1969594343701626e-05, "epoch": 9.381496881496881, "percentage": 46.91, "elapsed_time": "0:52:30", "remaining_time": "0:59:25", "throughput": 1031.75, "total_tokens": 3250296} {"current_steps": 36105, "total_steps": 76960, "loss": 0.1887, "lr": 3.196414934335269e-05, "epoch": 9.382796257796258, "percentage": 46.91, "elapsed_time": "0:52:30", "remaining_time": "0:59:25", "throughput": 1031.75, "total_tokens": 3250728} {"current_steps": 36110, "total_steps": 76960, "loss": 0.1439, "lr": 3.195870398483089e-05, "epoch": 9.384095634095633, "percentage": 46.92, "elapsed_time": "0:52:31", "remaining_time": "0:59:24", "throughput": 1031.76, "total_tokens": 3251192} {"current_steps": 36115, "total_steps": 76960, "loss": 0.2245, "lr": 3.195325826841625e-05, "epoch": 9.38539501039501, "percentage": 46.93, "elapsed_time": "0:52:31", "remaining_time": "0:59:24", "throughput": 1031.77, "total_tokens": 3251656} {"current_steps": 36120, "total_steps": 76960, "loss": 0.3066, "lr": 3.194781219438889e-05, "epoch": 9.386694386694387, "percentage": 46.93, "elapsed_time": "0:52:31", "remaining_time": "0:59:23", "throughput": 1031.77, "total_tokens": 3252088} {"current_steps": 36125, "total_steps": 76960, "loss": 0.2847, "lr": 3.19423657630289e-05, "epoch": 9.387993762993762, "percentage": 46.94, "elapsed_time": "0:52:32", "remaining_time": "0:59:23", "throughput": 1031.78, "total_tokens": 3252520} {"current_steps": 36130, "total_steps": 76960, "loss": 0.2166, "lr": 3.193691897461638e-05, "epoch": 9.38929313929314, "percentage": 46.95, "elapsed_time": "0:52:32", "remaining_time": "0:59:22", "throughput": 1031.79, "total_tokens": 3253000} {"current_steps": 36135, "total_steps": 76960, "loss": 0.3136, "lr": 3.193147182943147e-05, "epoch": 9.390592515592516, "percentage": 46.95, "elapsed_time": "0:52:33", "remaining_time": "0:59:22", "throughput": 1031.8, "total_tokens": 3253448} {"current_steps": 36140, "total_steps": 76960, "loss": 0.2194, "lr": 3.192602432775433e-05, "epoch": 9.391891891891891, "percentage": 46.96, "elapsed_time": "0:52:33", "remaining_time": "0:59:21", "throughput": 1031.81, "total_tokens": 3253912} {"current_steps": 36145, "total_steps": 76960, "loss": 0.147, "lr": 3.1920576469865115e-05, "epoch": 9.393191268191268, "percentage": 46.97, "elapsed_time": "0:52:34", "remaining_time": "0:59:21", "throughput": 1031.82, "total_tokens": 3254376} {"current_steps": 36150, "total_steps": 76960, "loss": 0.3602, "lr": 3.191512825604402e-05, "epoch": 9.394490644490645, "percentage": 46.97, "elapsed_time": "0:52:34", "remaining_time": "0:59:21", "throughput": 1031.82, "total_tokens": 3254808} {"current_steps": 36155, "total_steps": 76960, "loss": 0.1802, "lr": 3.1909679686571256e-05, "epoch": 9.39579002079002, "percentage": 46.98, "elapsed_time": "0:52:34", "remaining_time": "0:59:20", "throughput": 1031.82, "total_tokens": 3255224} {"current_steps": 36160, "total_steps": 76960, "loss": 0.2066, "lr": 3.190423076172705e-05, "epoch": 9.397089397089397, "percentage": 46.99, "elapsed_time": "0:52:35", "remaining_time": "0:59:20", "throughput": 1031.81, "total_tokens": 3255640} {"current_steps": 36165, "total_steps": 76960, "loss": 0.3515, "lr": 3.1898781481791624e-05, "epoch": 9.398388773388774, "percentage": 46.99, "elapsed_time": "0:52:35", "remaining_time": "0:59:19", "throughput": 1031.82, "total_tokens": 3256072} {"current_steps": 36170, "total_steps": 76960, "loss": 0.2128, "lr": 3.1893331847045266e-05, "epoch": 9.39968814968815, "percentage": 47.0, "elapsed_time": "0:52:36", "remaining_time": "0:59:19", "throughput": 1031.82, "total_tokens": 3256520} {"current_steps": 36175, "total_steps": 76960, "loss": 0.2126, "lr": 3.188788185776825e-05, "epoch": 9.400987525987526, "percentage": 47.0, "elapsed_time": "0:52:36", "remaining_time": "0:59:18", "throughput": 1031.84, "total_tokens": 3257000} {"current_steps": 36180, "total_steps": 76960, "loss": 0.1577, "lr": 3.188243151424087e-05, "epoch": 9.402286902286903, "percentage": 47.01, "elapsed_time": "0:52:36", "remaining_time": "0:59:18", "throughput": 1031.84, "total_tokens": 3257432} {"current_steps": 36185, "total_steps": 76960, "loss": 0.2243, "lr": 3.1876980816743434e-05, "epoch": 9.403586278586278, "percentage": 47.02, "elapsed_time": "0:52:37", "remaining_time": "0:59:17", "throughput": 1031.85, "total_tokens": 3257880} {"current_steps": 36190, "total_steps": 76960, "loss": 0.1987, "lr": 3.187152976555629e-05, "epoch": 9.404885654885655, "percentage": 47.02, "elapsed_time": "0:52:37", "remaining_time": "0:59:17", "throughput": 1031.86, "total_tokens": 3258360} {"current_steps": 36195, "total_steps": 76960, "loss": 0.1366, "lr": 3.186607836095979e-05, "epoch": 9.40618503118503, "percentage": 47.03, "elapsed_time": "0:52:38", "remaining_time": "0:59:16", "throughput": 1031.87, "total_tokens": 3258808} {"current_steps": 36200, "total_steps": 76960, "loss": 0.3708, "lr": 3.18606266032343e-05, "epoch": 9.407484407484407, "percentage": 47.04, "elapsed_time": "0:52:38", "remaining_time": "0:59:16", "throughput": 1031.86, "total_tokens": 3259224} {"current_steps": 36205, "total_steps": 76960, "loss": 0.2594, "lr": 3.185517449266021e-05, "epoch": 9.408783783783784, "percentage": 47.04, "elapsed_time": "0:52:38", "remaining_time": "0:59:15", "throughput": 1031.89, "total_tokens": 3259720} {"current_steps": 36210, "total_steps": 76960, "loss": 0.3773, "lr": 3.1849722029517934e-05, "epoch": 9.41008316008316, "percentage": 47.05, "elapsed_time": "0:52:39", "remaining_time": "0:59:15", "throughput": 1031.91, "total_tokens": 3260216} {"current_steps": 36215, "total_steps": 76960, "loss": 0.1867, "lr": 3.184426921408789e-05, "epoch": 9.411382536382536, "percentage": 47.06, "elapsed_time": "0:52:39", "remaining_time": "0:59:15", "throughput": 1031.9, "total_tokens": 3260632} {"current_steps": 36220, "total_steps": 76960, "loss": 0.5733, "lr": 3.1838816046650503e-05, "epoch": 9.412681912681913, "percentage": 47.06, "elapsed_time": "0:52:40", "remaining_time": "0:59:14", "throughput": 1031.91, "total_tokens": 3261096} {"current_steps": 36225, "total_steps": 76960, "loss": 0.2472, "lr": 3.183336252748627e-05, "epoch": 9.413981288981288, "percentage": 47.07, "elapsed_time": "0:52:40", "remaining_time": "0:59:14", "throughput": 1031.91, "total_tokens": 3261528} {"current_steps": 36230, "total_steps": 76960, "loss": 0.1574, "lr": 3.182790865687565e-05, "epoch": 9.415280665280665, "percentage": 47.08, "elapsed_time": "0:52:41", "remaining_time": "0:59:13", "throughput": 1031.92, "total_tokens": 3261976} {"current_steps": 36235, "total_steps": 76960, "loss": 0.1959, "lr": 3.182245443509915e-05, "epoch": 9.416580041580042, "percentage": 47.08, "elapsed_time": "0:52:41", "remaining_time": "0:59:13", "throughput": 1031.92, "total_tokens": 3262408} {"current_steps": 36240, "total_steps": 76960, "loss": 0.1665, "lr": 3.181699986243728e-05, "epoch": 9.417879417879417, "percentage": 47.09, "elapsed_time": "0:52:41", "remaining_time": "0:59:12", "throughput": 1031.94, "total_tokens": 3262888} {"current_steps": 36245, "total_steps": 76960, "loss": 0.1618, "lr": 3.1811544939170575e-05, "epoch": 9.419178794178794, "percentage": 47.1, "elapsed_time": "0:52:42", "remaining_time": "0:59:12", "throughput": 1031.94, "total_tokens": 3263336} {"current_steps": 36250, "total_steps": 76960, "loss": 0.352, "lr": 3.180608966557959e-05, "epoch": 9.420478170478171, "percentage": 47.1, "elapsed_time": "0:52:42", "remaining_time": "0:59:11", "throughput": 1031.95, "total_tokens": 3263784} {"current_steps": 36255, "total_steps": 76960, "loss": 0.3175, "lr": 3.180063404194489e-05, "epoch": 9.421777546777546, "percentage": 47.11, "elapsed_time": "0:52:43", "remaining_time": "0:59:11", "throughput": 1031.96, "total_tokens": 3264248} {"current_steps": 36260, "total_steps": 76960, "loss": 0.2018, "lr": 3.179517806854705e-05, "epoch": 9.423076923076923, "percentage": 47.12, "elapsed_time": "0:52:43", "remaining_time": "0:59:10", "throughput": 1031.98, "total_tokens": 3264744} {"current_steps": 36265, "total_steps": 76960, "loss": 0.1351, "lr": 3.1789721745666714e-05, "epoch": 9.424376299376299, "percentage": 47.12, "elapsed_time": "0:52:43", "remaining_time": "0:59:10", "throughput": 1031.99, "total_tokens": 3265208} {"current_steps": 36270, "total_steps": 76960, "loss": 0.3245, "lr": 3.178426507358448e-05, "epoch": 9.425675675675675, "percentage": 47.13, "elapsed_time": "0:52:44", "remaining_time": "0:59:10", "throughput": 1032.01, "total_tokens": 3265672} {"current_steps": 36275, "total_steps": 76960, "loss": 0.1446, "lr": 3.177880805258098e-05, "epoch": 9.426975051975052, "percentage": 47.13, "elapsed_time": "0:52:44", "remaining_time": "0:59:09", "throughput": 1032.02, "total_tokens": 3266136} {"current_steps": 36280, "total_steps": 76960, "loss": 0.339, "lr": 3.1773350682936895e-05, "epoch": 9.428274428274428, "percentage": 47.14, "elapsed_time": "0:52:45", "remaining_time": "0:59:09", "throughput": 1032.04, "total_tokens": 3266632} {"current_steps": 36285, "total_steps": 76960, "loss": 0.3722, "lr": 3.17678929649329e-05, "epoch": 9.429573804573804, "percentage": 47.15, "elapsed_time": "0:52:45", "remaining_time": "0:59:08", "throughput": 1032.05, "total_tokens": 3267096} {"current_steps": 36290, "total_steps": 76960, "loss": 0.294, "lr": 3.176243489884967e-05, "epoch": 9.430873180873181, "percentage": 47.15, "elapsed_time": "0:52:46", "remaining_time": "0:59:08", "throughput": 1032.04, "total_tokens": 3267512} {"current_steps": 36295, "total_steps": 76960, "loss": 0.2046, "lr": 3.1756976484967944e-05, "epoch": 9.432172557172557, "percentage": 47.16, "elapsed_time": "0:52:46", "remaining_time": "0:59:07", "throughput": 1032.06, "total_tokens": 3267976} {"current_steps": 36300, "total_steps": 76960, "loss": 0.3806, "lr": 3.1751517723568445e-05, "epoch": 9.433471933471933, "percentage": 47.17, "elapsed_time": "0:52:46", "remaining_time": "0:59:07", "throughput": 1032.05, "total_tokens": 3268392} {"current_steps": 36305, "total_steps": 76960, "loss": 0.1291, "lr": 3.1746058614931916e-05, "epoch": 9.43477130977131, "percentage": 47.17, "elapsed_time": "0:52:47", "remaining_time": "0:59:06", "throughput": 1032.06, "total_tokens": 3268840} {"current_steps": 36310, "total_steps": 76960, "loss": 0.3829, "lr": 3.1740599159339125e-05, "epoch": 9.436070686070686, "percentage": 47.18, "elapsed_time": "0:52:47", "remaining_time": "0:59:06", "throughput": 1032.06, "total_tokens": 3269272} {"current_steps": 36315, "total_steps": 76960, "loss": 0.2365, "lr": 3.1735139357070866e-05, "epoch": 9.437370062370062, "percentage": 47.19, "elapsed_time": "0:52:48", "remaining_time": "0:59:05", "throughput": 1032.06, "total_tokens": 3269704} {"current_steps": 36320, "total_steps": 76960, "loss": 0.2414, "lr": 3.1729679208407935e-05, "epoch": 9.43866943866944, "percentage": 47.19, "elapsed_time": "0:52:48", "remaining_time": "0:59:05", "throughput": 1032.06, "total_tokens": 3270136} {"current_steps": 36325, "total_steps": 76960, "loss": 0.2439, "lr": 3.172421871363116e-05, "epoch": 9.439968814968815, "percentage": 47.2, "elapsed_time": "0:52:48", "remaining_time": "0:59:04", "throughput": 1032.06, "total_tokens": 3270568} {"current_steps": 36330, "total_steps": 76960, "loss": 0.242, "lr": 3.171875787302136e-05, "epoch": 9.441268191268192, "percentage": 47.21, "elapsed_time": "0:52:49", "remaining_time": "0:59:04", "throughput": 1032.06, "total_tokens": 3271000} {"current_steps": 36335, "total_steps": 76960, "loss": 0.1468, "lr": 3.1713296686859426e-05, "epoch": 9.442567567567568, "percentage": 47.21, "elapsed_time": "0:52:49", "remaining_time": "0:59:04", "throughput": 1032.07, "total_tokens": 3271448} {"current_steps": 36340, "total_steps": 76960, "loss": 0.1715, "lr": 3.17078351554262e-05, "epoch": 9.443866943866944, "percentage": 47.22, "elapsed_time": "0:52:50", "remaining_time": "0:59:03", "throughput": 1032.06, "total_tokens": 3271864} {"current_steps": 36345, "total_steps": 76960, "loss": 0.2007, "lr": 3.170237327900258e-05, "epoch": 9.44516632016632, "percentage": 47.23, "elapsed_time": "0:52:50", "remaining_time": "0:59:03", "throughput": 1032.07, "total_tokens": 3272312} {"current_steps": 36350, "total_steps": 76960, "loss": 0.2447, "lr": 3.169691105786948e-05, "epoch": 9.446465696465696, "percentage": 47.23, "elapsed_time": "0:52:51", "remaining_time": "0:59:02", "throughput": 1032.08, "total_tokens": 3272776} {"current_steps": 36355, "total_steps": 76960, "loss": 0.3352, "lr": 3.169144849230783e-05, "epoch": 9.447765072765073, "percentage": 47.24, "elapsed_time": "0:52:51", "remaining_time": "0:59:02", "throughput": 1032.08, "total_tokens": 3273192} {"current_steps": 36360, "total_steps": 76960, "loss": 0.4896, "lr": 3.168598558259858e-05, "epoch": 9.44906444906445, "percentage": 47.25, "elapsed_time": "0:52:51", "remaining_time": "0:59:01", "throughput": 1032.08, "total_tokens": 3273624} {"current_steps": 36365, "total_steps": 76960, "loss": 0.2854, "lr": 3.168052232902268e-05, "epoch": 9.450363825363825, "percentage": 47.25, "elapsed_time": "0:52:52", "remaining_time": "0:59:01", "throughput": 1032.09, "total_tokens": 3274088} {"current_steps": 36370, "total_steps": 76960, "loss": 0.2029, "lr": 3.1675058731861115e-05, "epoch": 9.451663201663202, "percentage": 47.26, "elapsed_time": "0:52:52", "remaining_time": "0:59:00", "throughput": 1032.1, "total_tokens": 3274536} {"current_steps": 36375, "total_steps": 76960, "loss": 0.0658, "lr": 3.1669594791394886e-05, "epoch": 9.452962577962579, "percentage": 47.26, "elapsed_time": "0:52:53", "remaining_time": "0:59:00", "throughput": 1032.1, "total_tokens": 3274968} {"current_steps": 36380, "total_steps": 76960, "loss": 0.4697, "lr": 3.1664130507905e-05, "epoch": 9.454261954261954, "percentage": 47.27, "elapsed_time": "0:52:53", "remaining_time": "0:58:59", "throughput": 1032.11, "total_tokens": 3275448} {"current_steps": 36385, "total_steps": 76960, "loss": 0.3298, "lr": 3.16586658816725e-05, "epoch": 9.45556133056133, "percentage": 47.28, "elapsed_time": "0:52:53", "remaining_time": "0:58:59", "throughput": 1032.12, "total_tokens": 3275896} {"current_steps": 36390, "total_steps": 76960, "loss": 0.0566, "lr": 3.165320091297843e-05, "epoch": 9.456860706860708, "percentage": 47.28, "elapsed_time": "0:52:54", "remaining_time": "0:58:58", "throughput": 1032.13, "total_tokens": 3276360} {"current_steps": 36395, "total_steps": 76960, "loss": 0.3846, "lr": 3.164773560210387e-05, "epoch": 9.458160083160083, "percentage": 47.29, "elapsed_time": "0:52:54", "remaining_time": "0:58:58", "throughput": 1032.15, "total_tokens": 3276840} {"current_steps": 36400, "total_steps": 76960, "loss": 0.2992, "lr": 3.16422699493299e-05, "epoch": 9.45945945945946, "percentage": 47.3, "elapsed_time": "0:52:55", "remaining_time": "0:58:58", "throughput": 1032.15, "total_tokens": 3277288} {"current_steps": 36405, "total_steps": 76960, "loss": 0.2587, "lr": 3.1636803954937616e-05, "epoch": 9.460758835758837, "percentage": 47.3, "elapsed_time": "0:52:55", "remaining_time": "0:58:57", "throughput": 1032.17, "total_tokens": 3277768} {"current_steps": 36410, "total_steps": 76960, "loss": 0.3271, "lr": 3.163133761920815e-05, "epoch": 9.462058212058212, "percentage": 47.31, "elapsed_time": "0:52:56", "remaining_time": "0:58:57", "throughput": 1032.18, "total_tokens": 3278216} {"current_steps": 36415, "total_steps": 76960, "loss": 0.1593, "lr": 3.162587094242263e-05, "epoch": 9.463357588357589, "percentage": 47.32, "elapsed_time": "0:52:56", "remaining_time": "0:58:56", "throughput": 1032.19, "total_tokens": 3278696} {"current_steps": 36420, "total_steps": 76960, "loss": 0.2401, "lr": 3.162040392486222e-05, "epoch": 9.464656964656964, "percentage": 47.32, "elapsed_time": "0:52:56", "remaining_time": "0:58:56", "throughput": 1032.22, "total_tokens": 3279224} {"current_steps": 36425, "total_steps": 76960, "loss": 0.3008, "lr": 3.1614936566808095e-05, "epoch": 9.46595634095634, "percentage": 47.33, "elapsed_time": "0:52:57", "remaining_time": "0:58:55", "throughput": 1032.23, "total_tokens": 3279688} {"current_steps": 36430, "total_steps": 76960, "loss": 0.1755, "lr": 3.160946886854145e-05, "epoch": 9.467255717255718, "percentage": 47.34, "elapsed_time": "0:52:57", "remaining_time": "0:58:55", "throughput": 1032.25, "total_tokens": 3280152} {"current_steps": 36435, "total_steps": 76960, "loss": 0.2685, "lr": 3.1604000830343475e-05, "epoch": 9.468555093555093, "percentage": 47.34, "elapsed_time": "0:52:58", "remaining_time": "0:58:54", "throughput": 1032.25, "total_tokens": 3280600} {"current_steps": 36440, "total_steps": 76960, "loss": 0.2191, "lr": 3.159853245249542e-05, "epoch": 9.46985446985447, "percentage": 47.35, "elapsed_time": "0:52:58", "remaining_time": "0:58:54", "throughput": 1032.25, "total_tokens": 3281032} {"current_steps": 36445, "total_steps": 76960, "loss": 0.2861, "lr": 3.1593063735278517e-05, "epoch": 9.471153846153847, "percentage": 47.36, "elapsed_time": "0:52:58", "remaining_time": "0:58:53", "throughput": 1032.26, "total_tokens": 3281496} {"current_steps": 36450, "total_steps": 76960, "loss": 0.4201, "lr": 3.1587594678974034e-05, "epoch": 9.472453222453222, "percentage": 47.36, "elapsed_time": "0:52:59", "remaining_time": "0:58:53", "throughput": 1032.27, "total_tokens": 3281960} {"current_steps": 36455, "total_steps": 76960, "loss": 0.107, "lr": 3.158212528386323e-05, "epoch": 9.473752598752599, "percentage": 47.37, "elapsed_time": "0:52:59", "remaining_time": "0:58:53", "throughput": 1032.29, "total_tokens": 3282440} {"current_steps": 36460, "total_steps": 76960, "loss": 0.3268, "lr": 3.157665555022742e-05, "epoch": 9.475051975051976, "percentage": 47.38, "elapsed_time": "0:53:00", "remaining_time": "0:58:52", "throughput": 1032.29, "total_tokens": 3282888} {"current_steps": 36465, "total_steps": 76960, "loss": 0.1803, "lr": 3.157118547834793e-05, "epoch": 9.47635135135135, "percentage": 47.38, "elapsed_time": "0:53:00", "remaining_time": "0:58:52", "throughput": 1032.31, "total_tokens": 3283352} {"current_steps": 36470, "total_steps": 76960, "loss": 0.1746, "lr": 3.1565715068506056e-05, "epoch": 9.477650727650728, "percentage": 47.39, "elapsed_time": "0:53:01", "remaining_time": "0:58:51", "throughput": 1032.32, "total_tokens": 3283832} {"current_steps": 36475, "total_steps": 76960, "loss": 0.2609, "lr": 3.156024432098317e-05, "epoch": 9.478950103950105, "percentage": 47.39, "elapsed_time": "0:53:01", "remaining_time": "0:58:51", "throughput": 1032.34, "total_tokens": 3284312} {"current_steps": 36480, "total_steps": 76960, "loss": 0.3212, "lr": 3.155477323606064e-05, "epoch": 9.48024948024948, "percentage": 47.4, "elapsed_time": "0:53:01", "remaining_time": "0:58:50", "throughput": 1032.35, "total_tokens": 3284792} {"current_steps": 36485, "total_steps": 76960, "loss": 0.2747, "lr": 3.154930181401984e-05, "epoch": 9.481548856548857, "percentage": 47.41, "elapsed_time": "0:53:02", "remaining_time": "0:58:50", "throughput": 1032.35, "total_tokens": 3285224} {"current_steps": 36490, "total_steps": 76960, "loss": 0.1858, "lr": 3.154383005514216e-05, "epoch": 9.482848232848234, "percentage": 47.41, "elapsed_time": "0:53:02", "remaining_time": "0:58:49", "throughput": 1032.36, "total_tokens": 3285688} {"current_steps": 36495, "total_steps": 76960, "loss": 0.2886, "lr": 3.153835795970904e-05, "epoch": 9.484147609147609, "percentage": 47.42, "elapsed_time": "0:53:03", "remaining_time": "0:58:49", "throughput": 1032.39, "total_tokens": 3286184} {"current_steps": 36500, "total_steps": 76960, "loss": 0.2239, "lr": 3.153288552800191e-05, "epoch": 9.485446985446986, "percentage": 47.43, "elapsed_time": "0:53:03", "remaining_time": "0:58:48", "throughput": 1032.39, "total_tokens": 3286648} {"current_steps": 36505, "total_steps": 76960, "loss": 0.1884, "lr": 3.152741276030221e-05, "epoch": 9.486746361746361, "percentage": 47.43, "elapsed_time": "0:53:03", "remaining_time": "0:58:48", "throughput": 1032.43, "total_tokens": 3287192} {"current_steps": 36510, "total_steps": 76960, "loss": 0.1701, "lr": 3.152193965689142e-05, "epoch": 9.488045738045738, "percentage": 47.44, "elapsed_time": "0:53:04", "remaining_time": "0:58:47", "throughput": 1032.43, "total_tokens": 3287608} {"current_steps": 36515, "total_steps": 76960, "loss": 0.2048, "lr": 3.151646621805102e-05, "epoch": 9.489345114345115, "percentage": 47.45, "elapsed_time": "0:53:04", "remaining_time": "0:58:47", "throughput": 1032.44, "total_tokens": 3288088} {"current_steps": 36520, "total_steps": 76960, "loss": 0.2002, "lr": 3.151099244406253e-05, "epoch": 9.49064449064449, "percentage": 47.45, "elapsed_time": "0:53:05", "remaining_time": "0:58:47", "throughput": 1032.45, "total_tokens": 3288552} {"current_steps": 36525, "total_steps": 76960, "loss": 0.3024, "lr": 3.150551833520745e-05, "epoch": 9.491943866943867, "percentage": 47.46, "elapsed_time": "0:53:05", "remaining_time": "0:58:46", "throughput": 1032.45, "total_tokens": 3288984} {"current_steps": 36530, "total_steps": 76960, "loss": 0.4403, "lr": 3.1500043891767336e-05, "epoch": 9.493243243243244, "percentage": 47.47, "elapsed_time": "0:53:06", "remaining_time": "0:58:46", "throughput": 1032.47, "total_tokens": 3289464} {"current_steps": 36535, "total_steps": 76960, "loss": 0.2507, "lr": 3.149456911402373e-05, "epoch": 9.494542619542619, "percentage": 47.47, "elapsed_time": "0:53:06", "remaining_time": "0:58:45", "throughput": 1032.48, "total_tokens": 3289928} {"current_steps": 36540, "total_steps": 76960, "loss": 0.3218, "lr": 3.148909400225821e-05, "epoch": 9.495841995841996, "percentage": 47.48, "elapsed_time": "0:53:06", "remaining_time": "0:58:45", "throughput": 1032.48, "total_tokens": 3290344} {"current_steps": 36545, "total_steps": 76960, "loss": 0.2607, "lr": 3.148361855675237e-05, "epoch": 9.497141372141373, "percentage": 47.49, "elapsed_time": "0:53:07", "remaining_time": "0:58:44", "throughput": 1032.48, "total_tokens": 3290776} {"current_steps": 36550, "total_steps": 76960, "loss": 0.1686, "lr": 3.147814277778782e-05, "epoch": 9.498440748440748, "percentage": 47.49, "elapsed_time": "0:53:07", "remaining_time": "0:58:44", "throughput": 1032.47, "total_tokens": 3291192} {"current_steps": 36555, "total_steps": 76960, "loss": 0.1637, "lr": 3.1472666665646176e-05, "epoch": 9.499740124740125, "percentage": 47.5, "elapsed_time": "0:53:08", "remaining_time": "0:58:43", "throughput": 1032.48, "total_tokens": 3291640} {"current_steps": 36560, "total_steps": 76960, "loss": 0.3068, "lr": 3.146719022060908e-05, "epoch": 9.5010395010395, "percentage": 47.51, "elapsed_time": "0:53:08", "remaining_time": "0:58:43", "throughput": 1032.48, "total_tokens": 3292072} {"current_steps": 36565, "total_steps": 76960, "loss": 0.236, "lr": 3.1461713442958204e-05, "epoch": 9.502338877338877, "percentage": 47.51, "elapsed_time": "0:53:08", "remaining_time": "0:58:42", "throughput": 1032.49, "total_tokens": 3292536} {"current_steps": 36570, "total_steps": 76960, "loss": 0.1439, "lr": 3.145623633297521e-05, "epoch": 9.503638253638254, "percentage": 47.52, "elapsed_time": "0:53:09", "remaining_time": "0:58:42", "throughput": 1032.5, "total_tokens": 3293000} {"current_steps": 36575, "total_steps": 76960, "loss": 0.2995, "lr": 3.145075889094179e-05, "epoch": 9.50493762993763, "percentage": 47.52, "elapsed_time": "0:53:09", "remaining_time": "0:58:42", "throughput": 1032.52, "total_tokens": 3293480} {"current_steps": 36580, "total_steps": 76960, "loss": 0.2648, "lr": 3.1445281117139666e-05, "epoch": 9.506237006237006, "percentage": 47.53, "elapsed_time": "0:53:10", "remaining_time": "0:58:41", "throughput": 1032.51, "total_tokens": 3293896} {"current_steps": 36585, "total_steps": 76960, "loss": 0.1966, "lr": 3.143980301185055e-05, "epoch": 9.507536382536383, "percentage": 47.54, "elapsed_time": "0:53:10", "remaining_time": "0:58:41", "throughput": 1032.51, "total_tokens": 3294328} {"current_steps": 36590, "total_steps": 76960, "loss": 0.209, "lr": 3.1434324575356214e-05, "epoch": 9.508835758835758, "percentage": 47.54, "elapsed_time": "0:53:11", "remaining_time": "0:58:40", "throughput": 1032.54, "total_tokens": 3294824} {"current_steps": 36595, "total_steps": 76960, "loss": 0.2678, "lr": 3.142884580793838e-05, "epoch": 9.510135135135135, "percentage": 47.55, "elapsed_time": "0:53:11", "remaining_time": "0:58:40", "throughput": 1032.54, "total_tokens": 3295272} {"current_steps": 36600, "total_steps": 76960, "loss": 0.1968, "lr": 3.142336670987886e-05, "epoch": 9.511434511434512, "percentage": 47.56, "elapsed_time": "0:53:11", "remaining_time": "0:58:39", "throughput": 1032.56, "total_tokens": 3295768} {"current_steps": 36605, "total_steps": 76960, "loss": 0.3298, "lr": 3.141788728145943e-05, "epoch": 9.512733887733887, "percentage": 47.56, "elapsed_time": "0:53:12", "remaining_time": "0:58:39", "throughput": 1032.56, "total_tokens": 3296200} {"current_steps": 36610, "total_steps": 76960, "loss": 0.1299, "lr": 3.1412407522961906e-05, "epoch": 9.514033264033264, "percentage": 47.57, "elapsed_time": "0:53:12", "remaining_time": "0:58:38", "throughput": 1032.57, "total_tokens": 3296648} {"current_steps": 36615, "total_steps": 76960, "loss": 0.4051, "lr": 3.140692743466812e-05, "epoch": 9.515332640332641, "percentage": 47.58, "elapsed_time": "0:53:13", "remaining_time": "0:58:38", "throughput": 1032.58, "total_tokens": 3297112} {"current_steps": 36620, "total_steps": 76960, "loss": 0.2751, "lr": 3.140144701685992e-05, "epoch": 9.516632016632016, "percentage": 47.58, "elapsed_time": "0:53:13", "remaining_time": "0:58:37", "throughput": 1032.58, "total_tokens": 3297528} {"current_steps": 36625, "total_steps": 76960, "loss": 0.2357, "lr": 3.139596626981916e-05, "epoch": 9.517931392931393, "percentage": 47.59, "elapsed_time": "0:53:13", "remaining_time": "0:58:37", "throughput": 1032.57, "total_tokens": 3297944} {"current_steps": 36630, "total_steps": 76960, "loss": 0.2549, "lr": 3.139048519382773e-05, "epoch": 9.51923076923077, "percentage": 47.6, "elapsed_time": "0:53:14", "remaining_time": "0:58:36", "throughput": 1032.56, "total_tokens": 3298344} {"current_steps": 36635, "total_steps": 76960, "loss": 0.3878, "lr": 3.138500378916752e-05, "epoch": 9.520530145530145, "percentage": 47.6, "elapsed_time": "0:53:14", "remaining_time": "0:58:36", "throughput": 1032.57, "total_tokens": 3298792} {"current_steps": 36640, "total_steps": 76960, "loss": 0.1672, "lr": 3.137952205612045e-05, "epoch": 9.521829521829522, "percentage": 47.61, "elapsed_time": "0:53:15", "remaining_time": "0:58:36", "throughput": 1032.56, "total_tokens": 3299208} {"current_steps": 36645, "total_steps": 76960, "loss": 0.2718, "lr": 3.137403999496845e-05, "epoch": 9.523128898128899, "percentage": 47.62, "elapsed_time": "0:53:15", "remaining_time": "0:58:35", "throughput": 1032.56, "total_tokens": 3299624} {"current_steps": 36650, "total_steps": 76960, "loss": 0.2741, "lr": 3.1368557605993465e-05, "epoch": 9.524428274428274, "percentage": 47.62, "elapsed_time": "0:53:16", "remaining_time": "0:58:35", "throughput": 1032.56, "total_tokens": 3300056} {"current_steps": 36655, "total_steps": 76960, "loss": 0.1479, "lr": 3.1363074889477463e-05, "epoch": 9.525727650727651, "percentage": 47.63, "elapsed_time": "0:53:16", "remaining_time": "0:58:34", "throughput": 1032.57, "total_tokens": 3300536} {"current_steps": 36660, "total_steps": 76960, "loss": 0.2031, "lr": 3.135759184570242e-05, "epoch": 9.527027027027026, "percentage": 47.64, "elapsed_time": "0:53:16", "remaining_time": "0:58:34", "throughput": 1032.57, "total_tokens": 3300968} {"current_steps": 36665, "total_steps": 76960, "loss": 0.1656, "lr": 3.1352108474950336e-05, "epoch": 9.528326403326403, "percentage": 47.64, "elapsed_time": "0:53:17", "remaining_time": "0:58:33", "throughput": 1032.58, "total_tokens": 3301400} {"current_steps": 36670, "total_steps": 76960, "loss": 0.1835, "lr": 3.134662477750323e-05, "epoch": 9.52962577962578, "percentage": 47.65, "elapsed_time": "0:53:17", "remaining_time": "0:58:33", "throughput": 1032.59, "total_tokens": 3301880} {"current_steps": 36675, "total_steps": 76960, "loss": 0.1322, "lr": 3.1341140753643126e-05, "epoch": 9.530925155925155, "percentage": 47.65, "elapsed_time": "0:53:18", "remaining_time": "0:58:32", "throughput": 1032.6, "total_tokens": 3302344} {"current_steps": 36680, "total_steps": 76960, "loss": 0.3465, "lr": 3.133565640365208e-05, "epoch": 9.532224532224532, "percentage": 47.66, "elapsed_time": "0:53:18", "remaining_time": "0:58:32", "throughput": 1032.61, "total_tokens": 3302776} {"current_steps": 36685, "total_steps": 76960, "loss": 0.2331, "lr": 3.133017172781215e-05, "epoch": 9.53352390852391, "percentage": 47.67, "elapsed_time": "0:53:18", "remaining_time": "0:58:31", "throughput": 1032.61, "total_tokens": 3303208} {"current_steps": 36690, "total_steps": 76960, "loss": 0.2521, "lr": 3.132468672640543e-05, "epoch": 9.534823284823284, "percentage": 47.67, "elapsed_time": "0:53:19", "remaining_time": "0:58:31", "throughput": 1032.62, "total_tokens": 3303672} {"current_steps": 36695, "total_steps": 76960, "loss": 0.1309, "lr": 3.131920139971401e-05, "epoch": 9.536122661122661, "percentage": 47.68, "elapsed_time": "0:53:19", "remaining_time": "0:58:31", "throughput": 1032.61, "total_tokens": 3304088} {"current_steps": 36700, "total_steps": 76960, "loss": 0.3014, "lr": 3.131371574802e-05, "epoch": 9.537422037422038, "percentage": 47.69, "elapsed_time": "0:53:20", "remaining_time": "0:58:30", "throughput": 1032.63, "total_tokens": 3304568} {"current_steps": 36705, "total_steps": 76960, "loss": 0.4003, "lr": 3.130822977160554e-05, "epoch": 9.538721413721413, "percentage": 47.69, "elapsed_time": "0:53:20", "remaining_time": "0:58:30", "throughput": 1032.64, "total_tokens": 3305032} {"current_steps": 36710, "total_steps": 76960, "loss": 0.2481, "lr": 3.130274347075279e-05, "epoch": 9.54002079002079, "percentage": 47.7, "elapsed_time": "0:53:20", "remaining_time": "0:58:29", "throughput": 1032.64, "total_tokens": 3305464} {"current_steps": 36715, "total_steps": 76960, "loss": 0.3236, "lr": 3.12972568457439e-05, "epoch": 9.541320166320165, "percentage": 47.71, "elapsed_time": "0:53:21", "remaining_time": "0:58:29", "throughput": 1032.66, "total_tokens": 3305944} {"current_steps": 36720, "total_steps": 76960, "loss": 0.4657, "lr": 3.1291769896861056e-05, "epoch": 9.542619542619542, "percentage": 47.71, "elapsed_time": "0:53:21", "remaining_time": "0:58:28", "throughput": 1032.66, "total_tokens": 3306376} {"current_steps": 36725, "total_steps": 76960, "loss": 0.3627, "lr": 3.128628262438645e-05, "epoch": 9.54391891891892, "percentage": 47.72, "elapsed_time": "0:53:22", "remaining_time": "0:58:28", "throughput": 1032.68, "total_tokens": 3306872} {"current_steps": 36730, "total_steps": 76960, "loss": 0.1804, "lr": 3.128079502860232e-05, "epoch": 9.545218295218294, "percentage": 47.73, "elapsed_time": "0:53:22", "remaining_time": "0:58:27", "throughput": 1032.69, "total_tokens": 3307336} {"current_steps": 36735, "total_steps": 76960, "loss": 0.2224, "lr": 3.1275307109790873e-05, "epoch": 9.546517671517671, "percentage": 47.73, "elapsed_time": "0:53:23", "remaining_time": "0:58:27", "throughput": 1032.71, "total_tokens": 3307816} {"current_steps": 36740, "total_steps": 76960, "loss": 0.2493, "lr": 3.126981886823437e-05, "epoch": 9.547817047817048, "percentage": 47.74, "elapsed_time": "0:53:23", "remaining_time": "0:58:26", "throughput": 1032.73, "total_tokens": 3308328} {"current_steps": 36745, "total_steps": 76960, "loss": 0.2886, "lr": 3.1264330304215075e-05, "epoch": 9.549116424116423, "percentage": 47.75, "elapsed_time": "0:53:23", "remaining_time": "0:58:26", "throughput": 1032.74, "total_tokens": 3308776} {"current_steps": 36750, "total_steps": 76960, "loss": 0.3341, "lr": 3.125884141801527e-05, "epoch": 9.5504158004158, "percentage": 47.75, "elapsed_time": "0:53:24", "remaining_time": "0:58:25", "throughput": 1032.74, "total_tokens": 3309208} {"current_steps": 36755, "total_steps": 76960, "loss": 0.3148, "lr": 3.125335220991726e-05, "epoch": 9.551715176715177, "percentage": 47.76, "elapsed_time": "0:53:24", "remaining_time": "0:58:25", "throughput": 1032.76, "total_tokens": 3309688} {"current_steps": 36760, "total_steps": 76960, "loss": 0.1841, "lr": 3.124786268020334e-05, "epoch": 9.553014553014552, "percentage": 47.77, "elapsed_time": "0:53:25", "remaining_time": "0:58:25", "throughput": 1032.76, "total_tokens": 3310120} {"current_steps": 36765, "total_steps": 76960, "loss": 0.2758, "lr": 3.124237282915587e-05, "epoch": 9.55431392931393, "percentage": 47.77, "elapsed_time": "0:53:25", "remaining_time": "0:58:24", "throughput": 1032.75, "total_tokens": 3310536} {"current_steps": 36770, "total_steps": 76960, "loss": 0.3817, "lr": 3.123688265705718e-05, "epoch": 9.555613305613306, "percentage": 47.78, "elapsed_time": "0:53:25", "remaining_time": "0:58:24", "throughput": 1032.75, "total_tokens": 3310952} {"current_steps": 36775, "total_steps": 76960, "loss": 0.1712, "lr": 3.123139216418964e-05, "epoch": 9.556912681912682, "percentage": 47.78, "elapsed_time": "0:53:26", "remaining_time": "0:58:23", "throughput": 1032.76, "total_tokens": 3311416} {"current_steps": 36780, "total_steps": 76960, "loss": 0.2378, "lr": 3.122590135083563e-05, "epoch": 9.558212058212058, "percentage": 47.79, "elapsed_time": "0:53:26", "remaining_time": "0:58:23", "throughput": 1032.75, "total_tokens": 3311832} {"current_steps": 36785, "total_steps": 76960, "loss": 0.1968, "lr": 3.122041021727755e-05, "epoch": 9.559511434511435, "percentage": 47.8, "elapsed_time": "0:53:27", "remaining_time": "0:58:22", "throughput": 1032.75, "total_tokens": 3312248} {"current_steps": 36790, "total_steps": 76960, "loss": 0.332, "lr": 3.1214918763797805e-05, "epoch": 9.56081081081081, "percentage": 47.8, "elapsed_time": "0:53:27", "remaining_time": "0:58:22", "throughput": 1032.76, "total_tokens": 3312696} {"current_steps": 36795, "total_steps": 76960, "loss": 0.2511, "lr": 3.120942699067884e-05, "epoch": 9.562110187110187, "percentage": 47.81, "elapsed_time": "0:53:28", "remaining_time": "0:58:21", "throughput": 1032.75, "total_tokens": 3313112} {"current_steps": 36800, "total_steps": 76960, "loss": 0.1666, "lr": 3.1203934898203096e-05, "epoch": 9.563409563409563, "percentage": 47.82, "elapsed_time": "0:53:28", "remaining_time": "0:58:21", "throughput": 1032.75, "total_tokens": 3313528} {"current_steps": 36805, "total_steps": 76960, "loss": 0.2699, "lr": 3.119844248665303e-05, "epoch": 9.56470893970894, "percentage": 47.82, "elapsed_time": "0:53:28", "remaining_time": "0:58:20", "throughput": 1032.75, "total_tokens": 3313976} {"current_steps": 36810, "total_steps": 76960, "loss": 0.211, "lr": 3.119294975631113e-05, "epoch": 9.566008316008316, "percentage": 47.83, "elapsed_time": "0:53:29", "remaining_time": "0:58:20", "throughput": 1032.75, "total_tokens": 3314408} {"current_steps": 36815, "total_steps": 76960, "loss": 0.2555, "lr": 3.118745670745989e-05, "epoch": 9.567307692307692, "percentage": 47.84, "elapsed_time": "0:53:29", "remaining_time": "0:58:20", "throughput": 1032.76, "total_tokens": 3314872} {"current_steps": 36820, "total_steps": 76960, "loss": 0.3422, "lr": 3.118196334038182e-05, "epoch": 9.568607068607069, "percentage": 47.84, "elapsed_time": "0:53:30", "remaining_time": "0:58:19", "throughput": 1032.78, "total_tokens": 3315336} {"current_steps": 36825, "total_steps": 76960, "loss": 0.2176, "lr": 3.1176469655359465e-05, "epoch": 9.569906444906445, "percentage": 47.85, "elapsed_time": "0:53:30", "remaining_time": "0:58:19", "throughput": 1032.77, "total_tokens": 3315768} {"current_steps": 36830, "total_steps": 76960, "loss": 0.2411, "lr": 3.1170975652675344e-05, "epoch": 9.57120582120582, "percentage": 47.86, "elapsed_time": "0:53:30", "remaining_time": "0:58:18", "throughput": 1032.77, "total_tokens": 3316168} {"current_steps": 36835, "total_steps": 76960, "loss": 0.1279, "lr": 3.116548133261204e-05, "epoch": 9.572505197505198, "percentage": 47.86, "elapsed_time": "0:53:31", "remaining_time": "0:58:18", "throughput": 1032.78, "total_tokens": 3316648} {"current_steps": 36840, "total_steps": 76960, "loss": 0.2405, "lr": 3.115998669545212e-05, "epoch": 9.573804573804575, "percentage": 47.87, "elapsed_time": "0:53:31", "remaining_time": "0:58:17", "throughput": 1032.78, "total_tokens": 3317064} {"current_steps": 36845, "total_steps": 76960, "loss": 0.1445, "lr": 3.115449174147818e-05, "epoch": 9.57510395010395, "percentage": 47.88, "elapsed_time": "0:53:32", "remaining_time": "0:58:17", "throughput": 1032.78, "total_tokens": 3317496} {"current_steps": 36850, "total_steps": 76960, "loss": 0.3215, "lr": 3.1148996470972835e-05, "epoch": 9.576403326403327, "percentage": 47.88, "elapsed_time": "0:53:32", "remaining_time": "0:58:16", "throughput": 1032.79, "total_tokens": 3317960} {"current_steps": 36855, "total_steps": 76960, "loss": 0.1755, "lr": 3.1143500884218714e-05, "epoch": 9.577702702702704, "percentage": 47.89, "elapsed_time": "0:53:33", "remaining_time": "0:58:16", "throughput": 1032.78, "total_tokens": 3318376} {"current_steps": 36860, "total_steps": 76960, "loss": 0.1731, "lr": 3.113800498149846e-05, "epoch": 9.579002079002079, "percentage": 47.9, "elapsed_time": "0:53:33", "remaining_time": "0:58:15", "throughput": 1032.79, "total_tokens": 3318808} {"current_steps": 36865, "total_steps": 76960, "loss": 0.2602, "lr": 3.1132508763094715e-05, "epoch": 9.580301455301456, "percentage": 47.9, "elapsed_time": "0:53:33", "remaining_time": "0:58:15", "throughput": 1032.79, "total_tokens": 3319256} {"current_steps": 36870, "total_steps": 76960, "loss": 0.2167, "lr": 3.1127012229290174e-05, "epoch": 9.58160083160083, "percentage": 47.91, "elapsed_time": "0:53:34", "remaining_time": "0:58:15", "throughput": 1032.81, "total_tokens": 3319752} {"current_steps": 36875, "total_steps": 76960, "loss": 0.1152, "lr": 3.112151538036753e-05, "epoch": 9.582900207900208, "percentage": 47.91, "elapsed_time": "0:53:34", "remaining_time": "0:58:14", "throughput": 1032.82, "total_tokens": 3320200} {"current_steps": 36880, "total_steps": 76960, "loss": 0.1682, "lr": 3.111601821660948e-05, "epoch": 9.584199584199585, "percentage": 47.92, "elapsed_time": "0:53:35", "remaining_time": "0:58:14", "throughput": 1032.83, "total_tokens": 3320680} {"current_steps": 36885, "total_steps": 76960, "loss": 0.3915, "lr": 3.1110520738298746e-05, "epoch": 9.58549896049896, "percentage": 47.93, "elapsed_time": "0:53:35", "remaining_time": "0:58:13", "throughput": 1032.83, "total_tokens": 3321096} {"current_steps": 36890, "total_steps": 76960, "loss": 0.4104, "lr": 3.1105022945718074e-05, "epoch": 9.586798336798337, "percentage": 47.93, "elapsed_time": "0:53:35", "remaining_time": "0:58:13", "throughput": 1032.83, "total_tokens": 3321528} {"current_steps": 36895, "total_steps": 76960, "loss": 0.1223, "lr": 3.109952483915024e-05, "epoch": 9.588097713097714, "percentage": 47.94, "elapsed_time": "0:53:36", "remaining_time": "0:58:12", "throughput": 1032.84, "total_tokens": 3322008} {"current_steps": 36900, "total_steps": 76960, "loss": 0.2884, "lr": 3.109402641887798e-05, "epoch": 9.589397089397089, "percentage": 47.95, "elapsed_time": "0:53:36", "remaining_time": "0:58:12", "throughput": 1032.85, "total_tokens": 3322472} {"current_steps": 36905, "total_steps": 76960, "loss": 0.2376, "lr": 3.1088527685184114e-05, "epoch": 9.590696465696466, "percentage": 47.95, "elapsed_time": "0:53:37", "remaining_time": "0:58:11", "throughput": 1032.85, "total_tokens": 3322904} {"current_steps": 36910, "total_steps": 76960, "loss": 0.3491, "lr": 3.108302863835143e-05, "epoch": 9.591995841995843, "percentage": 47.96, "elapsed_time": "0:53:37", "remaining_time": "0:58:11", "throughput": 1032.88, "total_tokens": 3323400} {"current_steps": 36915, "total_steps": 76960, "loss": 0.2787, "lr": 3.107752927866276e-05, "epoch": 9.593295218295218, "percentage": 47.97, "elapsed_time": "0:53:38", "remaining_time": "0:58:10", "throughput": 1032.88, "total_tokens": 3323848} {"current_steps": 36920, "total_steps": 76960, "loss": 0.1214, "lr": 3.107202960640093e-05, "epoch": 9.594594594594595, "percentage": 47.97, "elapsed_time": "0:53:38", "remaining_time": "0:58:10", "throughput": 1032.89, "total_tokens": 3324296} {"current_steps": 36925, "total_steps": 76960, "loss": 0.2491, "lr": 3.106652962184881e-05, "epoch": 9.595893970893972, "percentage": 47.98, "elapsed_time": "0:53:38", "remaining_time": "0:58:09", "throughput": 1032.9, "total_tokens": 3324760} {"current_steps": 36930, "total_steps": 76960, "loss": 0.1827, "lr": 3.106102932528925e-05, "epoch": 9.597193347193347, "percentage": 47.99, "elapsed_time": "0:53:39", "remaining_time": "0:58:09", "throughput": 1032.9, "total_tokens": 3325208} {"current_steps": 36935, "total_steps": 76960, "loss": 0.262, "lr": 3.105552871700515e-05, "epoch": 9.598492723492724, "percentage": 47.99, "elapsed_time": "0:53:39", "remaining_time": "0:58:09", "throughput": 1032.91, "total_tokens": 3325672} {"current_steps": 36940, "total_steps": 76960, "loss": 0.2347, "lr": 3.1050027797279394e-05, "epoch": 9.5997920997921, "percentage": 48.0, "elapsed_time": "0:53:40", "remaining_time": "0:58:08", "throughput": 1032.91, "total_tokens": 3326104} {"current_steps": 36945, "total_steps": 76960, "loss": 0.217, "lr": 3.104452656639492e-05, "epoch": 9.601091476091476, "percentage": 48.01, "elapsed_time": "0:53:40", "remaining_time": "0:58:08", "throughput": 1032.93, "total_tokens": 3326568} {"current_steps": 36950, "total_steps": 76960, "loss": 0.1967, "lr": 3.103902502463465e-05, "epoch": 9.602390852390853, "percentage": 48.01, "elapsed_time": "0:53:40", "remaining_time": "0:58:07", "throughput": 1032.94, "total_tokens": 3327032} {"current_steps": 36955, "total_steps": 76960, "loss": 0.1684, "lr": 3.1033523172281544e-05, "epoch": 9.603690228690228, "percentage": 48.02, "elapsed_time": "0:53:41", "remaining_time": "0:58:07", "throughput": 1032.95, "total_tokens": 3327512} {"current_steps": 36960, "total_steps": 76960, "loss": 0.369, "lr": 3.102802100961856e-05, "epoch": 9.604989604989605, "percentage": 48.02, "elapsed_time": "0:53:41", "remaining_time": "0:58:06", "throughput": 1032.96, "total_tokens": 3327960} {"current_steps": 36965, "total_steps": 76960, "loss": 0.3809, "lr": 3.102251853692867e-05, "epoch": 9.606288981288982, "percentage": 48.03, "elapsed_time": "0:53:42", "remaining_time": "0:58:06", "throughput": 1032.96, "total_tokens": 3328392} {"current_steps": 36970, "total_steps": 76960, "loss": 0.1779, "lr": 3.101701575449489e-05, "epoch": 9.607588357588357, "percentage": 48.04, "elapsed_time": "0:53:42", "remaining_time": "0:58:05", "throughput": 1032.97, "total_tokens": 3328856} {"current_steps": 36975, "total_steps": 76960, "loss": 0.5735, "lr": 3.1011512662600216e-05, "epoch": 9.608887733887734, "percentage": 48.04, "elapsed_time": "0:53:43", "remaining_time": "0:58:05", "throughput": 1032.97, "total_tokens": 3329272} {"current_steps": 36980, "total_steps": 76960, "loss": 0.2105, "lr": 3.100600926152769e-05, "epoch": 9.61018711018711, "percentage": 48.05, "elapsed_time": "0:53:43", "remaining_time": "0:58:04", "throughput": 1032.98, "total_tokens": 3329736} {"current_steps": 36985, "total_steps": 76960, "loss": 0.3217, "lr": 3.100050555156035e-05, "epoch": 9.611486486486486, "percentage": 48.06, "elapsed_time": "0:53:43", "remaining_time": "0:58:04", "throughput": 1032.98, "total_tokens": 3330184} {"current_steps": 36990, "total_steps": 76960, "loss": 0.1906, "lr": 3.099500153298127e-05, "epoch": 9.612785862785863, "percentage": 48.06, "elapsed_time": "0:53:44", "remaining_time": "0:58:04", "throughput": 1032.98, "total_tokens": 3330600} {"current_steps": 36995, "total_steps": 76960, "loss": 0.1746, "lr": 3.098949720607351e-05, "epoch": 9.61408523908524, "percentage": 48.07, "elapsed_time": "0:53:44", "remaining_time": "0:58:03", "throughput": 1032.98, "total_tokens": 3331032} {"current_steps": 37000, "total_steps": 76960, "loss": 0.3543, "lr": 3.0983992571120176e-05, "epoch": 9.615384615384615, "percentage": 48.08, "elapsed_time": "0:53:45", "remaining_time": "0:58:03", "throughput": 1032.98, "total_tokens": 3331480} {"current_steps": 37005, "total_steps": 76960, "loss": 0.3817, "lr": 3.0978487628404365e-05, "epoch": 9.616683991683992, "percentage": 48.08, "elapsed_time": "0:53:45", "remaining_time": "0:58:02", "throughput": 1032.99, "total_tokens": 3331944} {"current_steps": 37010, "total_steps": 76960, "loss": 0.2814, "lr": 3.0972982378209204e-05, "epoch": 9.617983367983367, "percentage": 48.09, "elapsed_time": "0:53:45", "remaining_time": "0:58:02", "throughput": 1033.0, "total_tokens": 3332392} {"current_steps": 37015, "total_steps": 76960, "loss": 0.2314, "lr": 3.096747682081784e-05, "epoch": 9.619282744282744, "percentage": 48.1, "elapsed_time": "0:53:46", "remaining_time": "0:58:01", "throughput": 1033.0, "total_tokens": 3332824} {"current_steps": 37020, "total_steps": 76960, "loss": 0.2426, "lr": 3.096197095651342e-05, "epoch": 9.620582120582121, "percentage": 48.1, "elapsed_time": "0:53:46", "remaining_time": "0:58:01", "throughput": 1033.0, "total_tokens": 3333256} {"current_steps": 37025, "total_steps": 76960, "loss": 0.3373, "lr": 3.0956464785579124e-05, "epoch": 9.621881496881496, "percentage": 48.11, "elapsed_time": "0:53:47", "remaining_time": "0:58:00", "throughput": 1033.01, "total_tokens": 3333720} {"current_steps": 37030, "total_steps": 76960, "loss": 0.2972, "lr": 3.095095830829814e-05, "epoch": 9.623180873180873, "percentage": 48.12, "elapsed_time": "0:53:47", "remaining_time": "0:58:00", "throughput": 1033.02, "total_tokens": 3334168} {"current_steps": 37035, "total_steps": 76960, "loss": 0.2793, "lr": 3.0945451524953666e-05, "epoch": 9.62448024948025, "percentage": 48.12, "elapsed_time": "0:53:48", "remaining_time": "0:57:59", "throughput": 1033.03, "total_tokens": 3334648} {"current_steps": 37040, "total_steps": 76960, "loss": 0.204, "lr": 3.093994443582893e-05, "epoch": 9.625779625779625, "percentage": 48.13, "elapsed_time": "0:53:48", "remaining_time": "0:57:59", "throughput": 1033.04, "total_tokens": 3335112} {"current_steps": 37045, "total_steps": 76960, "loss": 0.189, "lr": 3.093443704120715e-05, "epoch": 9.627079002079002, "percentage": 48.14, "elapsed_time": "0:53:48", "remaining_time": "0:57:59", "throughput": 1033.07, "total_tokens": 3335624} {"current_steps": 37050, "total_steps": 76960, "loss": 0.1574, "lr": 3.092892934137159e-05, "epoch": 9.628378378378379, "percentage": 48.14, "elapsed_time": "0:53:49", "remaining_time": "0:57:58", "throughput": 1033.08, "total_tokens": 3336088} {"current_steps": 37055, "total_steps": 76960, "loss": 0.3259, "lr": 3.092342133660553e-05, "epoch": 9.629677754677754, "percentage": 48.15, "elapsed_time": "0:53:49", "remaining_time": "0:57:58", "throughput": 1033.09, "total_tokens": 3336568} {"current_steps": 37060, "total_steps": 76960, "loss": 0.1388, "lr": 3.091791302719221e-05, "epoch": 9.630977130977131, "percentage": 48.15, "elapsed_time": "0:53:50", "remaining_time": "0:57:57", "throughput": 1033.1, "total_tokens": 3337016} {"current_steps": 37065, "total_steps": 76960, "loss": 0.2245, "lr": 3.0912404413414965e-05, "epoch": 9.632276507276508, "percentage": 48.16, "elapsed_time": "0:53:50", "remaining_time": "0:57:57", "throughput": 1033.12, "total_tokens": 3337496} {"current_steps": 37070, "total_steps": 76960, "loss": 0.3225, "lr": 3.0906895495557094e-05, "epoch": 9.633575883575883, "percentage": 48.17, "elapsed_time": "0:53:50", "remaining_time": "0:57:56", "throughput": 1033.12, "total_tokens": 3337944} {"current_steps": 37075, "total_steps": 76960, "loss": 0.2784, "lr": 3.090138627390193e-05, "epoch": 9.63487525987526, "percentage": 48.17, "elapsed_time": "0:53:51", "remaining_time": "0:57:56", "throughput": 1033.12, "total_tokens": 3338360} {"current_steps": 37080, "total_steps": 76960, "loss": 0.2032, "lr": 3.0895876748732806e-05, "epoch": 9.636174636174637, "percentage": 48.18, "elapsed_time": "0:53:51", "remaining_time": "0:57:55", "throughput": 1033.12, "total_tokens": 3338808} {"current_steps": 37085, "total_steps": 76960, "loss": 0.2054, "lr": 3.08903669203331e-05, "epoch": 9.637474012474012, "percentage": 48.19, "elapsed_time": "0:53:52", "remaining_time": "0:57:55", "throughput": 1033.12, "total_tokens": 3339240} {"current_steps": 37090, "total_steps": 76960, "loss": 0.4125, "lr": 3.088485678898618e-05, "epoch": 9.638773388773389, "percentage": 48.19, "elapsed_time": "0:53:52", "remaining_time": "0:57:54", "throughput": 1033.13, "total_tokens": 3339704} {"current_steps": 37095, "total_steps": 76960, "loss": 0.1495, "lr": 3.0879346354975435e-05, "epoch": 9.640072765072766, "percentage": 48.2, "elapsed_time": "0:53:53", "remaining_time": "0:57:54", "throughput": 1033.14, "total_tokens": 3340152} {"current_steps": 37100, "total_steps": 76960, "loss": 0.2473, "lr": 3.087383561858427e-05, "epoch": 9.641372141372141, "percentage": 48.21, "elapsed_time": "0:53:53", "remaining_time": "0:57:53", "throughput": 1033.15, "total_tokens": 3340616} {"current_steps": 37105, "total_steps": 76960, "loss": 0.328, "lr": 3.0868324580096114e-05, "epoch": 9.642671517671518, "percentage": 48.21, "elapsed_time": "0:53:53", "remaining_time": "0:57:53", "throughput": 1033.16, "total_tokens": 3341064} {"current_steps": 37110, "total_steps": 76960, "loss": 0.1113, "lr": 3.0862813239794405e-05, "epoch": 9.643970893970893, "percentage": 48.22, "elapsed_time": "0:53:54", "remaining_time": "0:57:53", "throughput": 1033.16, "total_tokens": 3341512} {"current_steps": 37115, "total_steps": 76960, "loss": 0.1217, "lr": 3.085730159796259e-05, "epoch": 9.64527027027027, "percentage": 48.23, "elapsed_time": "0:53:54", "remaining_time": "0:57:52", "throughput": 1033.16, "total_tokens": 3341944} {"current_steps": 37120, "total_steps": 76960, "loss": 0.432, "lr": 3.0851789654884145e-05, "epoch": 9.646569646569647, "percentage": 48.23, "elapsed_time": "0:53:55", "remaining_time": "0:57:52", "throughput": 1033.16, "total_tokens": 3342376} {"current_steps": 37125, "total_steps": 76960, "loss": 0.2573, "lr": 3.084627741084255e-05, "epoch": 9.647869022869022, "percentage": 48.24, "elapsed_time": "0:53:55", "remaining_time": "0:57:51", "throughput": 1033.17, "total_tokens": 3342824} {"current_steps": 37130, "total_steps": 76960, "loss": 0.2022, "lr": 3.084076486612131e-05, "epoch": 9.6491683991684, "percentage": 48.25, "elapsed_time": "0:53:55", "remaining_time": "0:57:51", "throughput": 1033.18, "total_tokens": 3343272} {"current_steps": 37135, "total_steps": 76960, "loss": 0.2279, "lr": 3.0835252021003925e-05, "epoch": 9.650467775467776, "percentage": 48.25, "elapsed_time": "0:53:56", "remaining_time": "0:57:50", "throughput": 1033.18, "total_tokens": 3343720} {"current_steps": 37140, "total_steps": 76960, "loss": 0.2028, "lr": 3.0829738875773945e-05, "epoch": 9.651767151767151, "percentage": 48.26, "elapsed_time": "0:53:56", "remaining_time": "0:57:50", "throughput": 1033.18, "total_tokens": 3344152} {"current_steps": 37145, "total_steps": 76960, "loss": 0.0736, "lr": 3.082422543071491e-05, "epoch": 9.653066528066528, "percentage": 48.27, "elapsed_time": "0:53:57", "remaining_time": "0:57:49", "throughput": 1033.18, "total_tokens": 3344584} {"current_steps": 37150, "total_steps": 76960, "loss": 0.1644, "lr": 3.081871168611037e-05, "epoch": 9.654365904365905, "percentage": 48.27, "elapsed_time": "0:53:57", "remaining_time": "0:57:49", "throughput": 1033.19, "total_tokens": 3345032} {"current_steps": 37155, "total_steps": 76960, "loss": 0.341, "lr": 3.0813197642243925e-05, "epoch": 9.65566528066528, "percentage": 48.28, "elapsed_time": "0:53:58", "remaining_time": "0:57:48", "throughput": 1033.18, "total_tokens": 3345448} {"current_steps": 37160, "total_steps": 76960, "loss": 0.1664, "lr": 3.080768329939916e-05, "epoch": 9.656964656964657, "percentage": 48.28, "elapsed_time": "0:53:58", "remaining_time": "0:57:48", "throughput": 1033.18, "total_tokens": 3345880} {"current_steps": 37165, "total_steps": 76960, "loss": 0.3199, "lr": 3.0802168657859665e-05, "epoch": 9.658264033264032, "percentage": 48.29, "elapsed_time": "0:53:58", "remaining_time": "0:57:48", "throughput": 1033.19, "total_tokens": 3346328} {"current_steps": 37170, "total_steps": 76960, "loss": 0.2305, "lr": 3.079665371790908e-05, "epoch": 9.65956340956341, "percentage": 48.3, "elapsed_time": "0:53:59", "remaining_time": "0:57:47", "throughput": 1033.2, "total_tokens": 3346776} {"current_steps": 37175, "total_steps": 76960, "loss": 0.032, "lr": 3.079113847983104e-05, "epoch": 9.660862785862786, "percentage": 48.3, "elapsed_time": "0:53:59", "remaining_time": "0:57:47", "throughput": 1033.2, "total_tokens": 3347224} {"current_steps": 37180, "total_steps": 76960, "loss": 0.5952, "lr": 3.0785622943909195e-05, "epoch": 9.662162162162161, "percentage": 48.31, "elapsed_time": "0:54:00", "remaining_time": "0:57:46", "throughput": 1033.22, "total_tokens": 3347704} {"current_steps": 37185, "total_steps": 76960, "loss": 0.1978, "lr": 3.078010711042723e-05, "epoch": 9.663461538461538, "percentage": 48.32, "elapsed_time": "0:54:00", "remaining_time": "0:57:46", "throughput": 1033.22, "total_tokens": 3348136} {"current_steps": 37190, "total_steps": 76960, "loss": 0.2466, "lr": 3.0774590979668814e-05, "epoch": 9.664760914760915, "percentage": 48.32, "elapsed_time": "0:54:00", "remaining_time": "0:57:45", "throughput": 1033.22, "total_tokens": 3348584} {"current_steps": 37195, "total_steps": 76960, "loss": 0.2306, "lr": 3.076907455191765e-05, "epoch": 9.66606029106029, "percentage": 48.33, "elapsed_time": "0:54:01", "remaining_time": "0:57:45", "throughput": 1033.22, "total_tokens": 3349016} {"current_steps": 37200, "total_steps": 76960, "loss": 0.3745, "lr": 3.0763557827457454e-05, "epoch": 9.667359667359667, "percentage": 48.34, "elapsed_time": "0:54:01", "remaining_time": "0:57:44", "throughput": 1033.23, "total_tokens": 3349464} {"current_steps": 37205, "total_steps": 76960, "loss": 0.0829, "lr": 3.0758040806571954e-05, "epoch": 9.668659043659044, "percentage": 48.34, "elapsed_time": "0:54:02", "remaining_time": "0:57:44", "throughput": 1033.22, "total_tokens": 3349880} {"current_steps": 37210, "total_steps": 76960, "loss": 0.3773, "lr": 3.07525234895449e-05, "epoch": 9.66995841995842, "percentage": 48.35, "elapsed_time": "0:54:02", "remaining_time": "0:57:43", "throughput": 1033.23, "total_tokens": 3350344} {"current_steps": 37215, "total_steps": 76960, "loss": 0.3629, "lr": 3.074700587666005e-05, "epoch": 9.671257796257796, "percentage": 48.36, "elapsed_time": "0:54:02", "remaining_time": "0:57:43", "throughput": 1033.25, "total_tokens": 3350824} {"current_steps": 37220, "total_steps": 76960, "loss": 0.2716, "lr": 3.074148796820119e-05, "epoch": 9.672557172557173, "percentage": 48.36, "elapsed_time": "0:54:03", "remaining_time": "0:57:43", "throughput": 1033.26, "total_tokens": 3351304} {"current_steps": 37225, "total_steps": 76960, "loss": 0.2819, "lr": 3.073596976445209e-05, "epoch": 9.673856548856548, "percentage": 48.37, "elapsed_time": "0:54:03", "remaining_time": "0:57:42", "throughput": 1033.28, "total_tokens": 3351784} {"current_steps": 37230, "total_steps": 76960, "loss": 0.2193, "lr": 3.0730451265696576e-05, "epoch": 9.675155925155925, "percentage": 48.38, "elapsed_time": "0:54:04", "remaining_time": "0:57:42", "throughput": 1033.29, "total_tokens": 3352248} {"current_steps": 37235, "total_steps": 76960, "loss": 0.3061, "lr": 3.072493247221846e-05, "epoch": 9.676455301455302, "percentage": 48.38, "elapsed_time": "0:54:04", "remaining_time": "0:57:41", "throughput": 1033.31, "total_tokens": 3352744} {"current_steps": 37240, "total_steps": 76960, "loss": 0.211, "lr": 3.0719413384301584e-05, "epoch": 9.677754677754677, "percentage": 48.39, "elapsed_time": "0:54:05", "remaining_time": "0:57:41", "throughput": 1033.31, "total_tokens": 3353176} {"current_steps": 37245, "total_steps": 76960, "loss": 0.3551, "lr": 3.071389400222979e-05, "epoch": 9.679054054054054, "percentage": 48.4, "elapsed_time": "0:54:05", "remaining_time": "0:57:40", "throughput": 1033.31, "total_tokens": 3353608} {"current_steps": 37250, "total_steps": 76960, "loss": 0.2512, "lr": 3.0708374326286965e-05, "epoch": 9.68035343035343, "percentage": 48.4, "elapsed_time": "0:54:05", "remaining_time": "0:57:40", "throughput": 1033.34, "total_tokens": 3354120} {"current_steps": 37255, "total_steps": 76960, "loss": 0.2125, "lr": 3.070285435675698e-05, "epoch": 9.681652806652806, "percentage": 48.41, "elapsed_time": "0:54:06", "remaining_time": "0:57:39", "throughput": 1033.35, "total_tokens": 3354600} {"current_steps": 37260, "total_steps": 76960, "loss": 0.2794, "lr": 3.069733409392371e-05, "epoch": 9.682952182952183, "percentage": 48.41, "elapsed_time": "0:54:06", "remaining_time": "0:57:39", "throughput": 1033.37, "total_tokens": 3355080} {"current_steps": 37265, "total_steps": 76960, "loss": 0.2915, "lr": 3.0691813538071105e-05, "epoch": 9.684251559251559, "percentage": 48.42, "elapsed_time": "0:54:07", "remaining_time": "0:57:38", "throughput": 1033.39, "total_tokens": 3355576} {"current_steps": 37270, "total_steps": 76960, "loss": 0.2994, "lr": 3.0686292689483074e-05, "epoch": 9.685550935550935, "percentage": 48.43, "elapsed_time": "0:54:07", "remaining_time": "0:57:38", "throughput": 1033.4, "total_tokens": 3356024} {"current_steps": 37275, "total_steps": 76960, "loss": 0.2852, "lr": 3.068077154844356e-05, "epoch": 9.686850311850312, "percentage": 48.43, "elapsed_time": "0:54:07", "remaining_time": "0:57:37", "throughput": 1033.4, "total_tokens": 3356472} {"current_steps": 37280, "total_steps": 76960, "loss": 0.285, "lr": 3.0675250115236526e-05, "epoch": 9.688149688149688, "percentage": 48.44, "elapsed_time": "0:54:08", "remaining_time": "0:57:37", "throughput": 1033.4, "total_tokens": 3356904} {"current_steps": 37285, "total_steps": 76960, "loss": 0.2637, "lr": 3.066972839014594e-05, "epoch": 9.689449064449065, "percentage": 48.45, "elapsed_time": "0:54:08", "remaining_time": "0:57:37", "throughput": 1033.41, "total_tokens": 3357352} {"current_steps": 37290, "total_steps": 76960, "loss": 0.1943, "lr": 3.066420637345579e-05, "epoch": 9.690748440748441, "percentage": 48.45, "elapsed_time": "0:54:09", "remaining_time": "0:57:36", "throughput": 1033.42, "total_tokens": 3357816} {"current_steps": 37295, "total_steps": 76960, "loss": 0.2175, "lr": 3.0658684065450075e-05, "epoch": 9.692047817047817, "percentage": 48.46, "elapsed_time": "0:54:09", "remaining_time": "0:57:36", "throughput": 1033.42, "total_tokens": 3358248} {"current_steps": 37300, "total_steps": 76960, "loss": 0.2174, "lr": 3.0653161466412824e-05, "epoch": 9.693347193347194, "percentage": 48.47, "elapsed_time": "0:54:10", "remaining_time": "0:57:35", "throughput": 1033.43, "total_tokens": 3358728} {"current_steps": 37305, "total_steps": 76960, "loss": 0.1501, "lr": 3.064763857662806e-05, "epoch": 9.69464656964657, "percentage": 48.47, "elapsed_time": "0:54:10", "remaining_time": "0:57:35", "throughput": 1033.45, "total_tokens": 3359208} {"current_steps": 37310, "total_steps": 76960, "loss": 0.4031, "lr": 3.0642115396379825e-05, "epoch": 9.695945945945946, "percentage": 48.48, "elapsed_time": "0:54:10", "remaining_time": "0:57:34", "throughput": 1033.46, "total_tokens": 3359672} {"current_steps": 37315, "total_steps": 76960, "loss": 0.2064, "lr": 3.06365919259522e-05, "epoch": 9.697245322245323, "percentage": 48.49, "elapsed_time": "0:54:11", "remaining_time": "0:57:34", "throughput": 1033.47, "total_tokens": 3360120} {"current_steps": 37320, "total_steps": 76960, "loss": 0.3701, "lr": 3.063106816562925e-05, "epoch": 9.698544698544698, "percentage": 48.49, "elapsed_time": "0:54:11", "remaining_time": "0:57:33", "throughput": 1033.48, "total_tokens": 3360584} {"current_steps": 37325, "total_steps": 76960, "loss": 0.2239, "lr": 3.062554411569506e-05, "epoch": 9.699844074844075, "percentage": 48.5, "elapsed_time": "0:54:12", "remaining_time": "0:57:33", "throughput": 1033.48, "total_tokens": 3361032} {"current_steps": 37330, "total_steps": 76960, "loss": 0.1783, "lr": 3.062001977643375e-05, "epoch": 9.701143451143452, "percentage": 48.51, "elapsed_time": "0:54:12", "remaining_time": "0:57:32", "throughput": 1033.5, "total_tokens": 3361512} {"current_steps": 37335, "total_steps": 76960, "loss": 0.1476, "lr": 3.0614495148129436e-05, "epoch": 9.702442827442827, "percentage": 48.51, "elapsed_time": "0:54:12", "remaining_time": "0:57:32", "throughput": 1033.49, "total_tokens": 3361928} {"current_steps": 37340, "total_steps": 76960, "loss": 0.311, "lr": 3.060897023106627e-05, "epoch": 9.703742203742204, "percentage": 48.52, "elapsed_time": "0:54:13", "remaining_time": "0:57:32", "throughput": 1033.49, "total_tokens": 3362360} {"current_steps": 37345, "total_steps": 76960, "loss": 0.3419, "lr": 3.0603445025528376e-05, "epoch": 9.70504158004158, "percentage": 48.53, "elapsed_time": "0:54:13", "remaining_time": "0:57:31", "throughput": 1033.51, "total_tokens": 3362840} {"current_steps": 37350, "total_steps": 76960, "loss": 0.2342, "lr": 3.059791953179993e-05, "epoch": 9.706340956340956, "percentage": 48.53, "elapsed_time": "0:54:14", "remaining_time": "0:57:31", "throughput": 1033.51, "total_tokens": 3363272} {"current_steps": 37355, "total_steps": 76960, "loss": 0.219, "lr": 3.059239375016513e-05, "epoch": 9.707640332640333, "percentage": 48.54, "elapsed_time": "0:54:14", "remaining_time": "0:57:30", "throughput": 1033.52, "total_tokens": 3363736} {"current_steps": 37360, "total_steps": 76960, "loss": 0.2899, "lr": 3.058686768090816e-05, "epoch": 9.70893970893971, "percentage": 48.54, "elapsed_time": "0:54:15", "remaining_time": "0:57:30", "throughput": 1033.54, "total_tokens": 3364216} {"current_steps": 37365, "total_steps": 76960, "loss": 0.3003, "lr": 3.058134132431324e-05, "epoch": 9.710239085239085, "percentage": 48.55, "elapsed_time": "0:54:15", "remaining_time": "0:57:29", "throughput": 1033.55, "total_tokens": 3364680} {"current_steps": 37370, "total_steps": 76960, "loss": 0.3201, "lr": 3.0575814680664575e-05, "epoch": 9.711538461538462, "percentage": 48.56, "elapsed_time": "0:54:15", "remaining_time": "0:57:29", "throughput": 1033.55, "total_tokens": 3365112} {"current_steps": 37375, "total_steps": 76960, "loss": 0.1254, "lr": 3.057028775024642e-05, "epoch": 9.712837837837839, "percentage": 48.56, "elapsed_time": "0:54:16", "remaining_time": "0:57:28", "throughput": 1033.57, "total_tokens": 3365608} {"current_steps": 37380, "total_steps": 76960, "loss": 0.2815, "lr": 3.056476053334304e-05, "epoch": 9.714137214137214, "percentage": 48.57, "elapsed_time": "0:54:16", "remaining_time": "0:57:28", "throughput": 1033.59, "total_tokens": 3366104} {"current_steps": 37385, "total_steps": 76960, "loss": 0.2358, "lr": 3.0559233030238684e-05, "epoch": 9.71543659043659, "percentage": 48.58, "elapsed_time": "0:54:17", "remaining_time": "0:57:27", "throughput": 1033.59, "total_tokens": 3366536} {"current_steps": 37390, "total_steps": 76960, "loss": 0.4322, "lr": 3.055370524121765e-05, "epoch": 9.716735966735968, "percentage": 48.58, "elapsed_time": "0:54:17", "remaining_time": "0:57:27", "throughput": 1033.59, "total_tokens": 3366968} {"current_steps": 37395, "total_steps": 76960, "loss": 0.2036, "lr": 3.0548177166564235e-05, "epoch": 9.718035343035343, "percentage": 48.59, "elapsed_time": "0:54:17", "remaining_time": "0:57:27", "throughput": 1033.59, "total_tokens": 3367416} {"current_steps": 37400, "total_steps": 76960, "loss": 0.186, "lr": 3.054264880656275e-05, "epoch": 9.71933471933472, "percentage": 48.6, "elapsed_time": "0:54:18", "remaining_time": "0:57:26", "throughput": 1033.61, "total_tokens": 3367896} {"current_steps": 37405, "total_steps": 76960, "loss": 0.2842, "lr": 3.053712016149752e-05, "epoch": 9.720634095634095, "percentage": 48.6, "elapsed_time": "0:54:18", "remaining_time": "0:57:26", "throughput": 1033.63, "total_tokens": 3368392} {"current_steps": 37410, "total_steps": 76960, "loss": 0.2105, "lr": 3.05315912316529e-05, "epoch": 9.721933471933472, "percentage": 48.61, "elapsed_time": "0:54:19", "remaining_time": "0:57:25", "throughput": 1033.63, "total_tokens": 3368824} {"current_steps": 37415, "total_steps": 76960, "loss": 0.221, "lr": 3.0526062017313254e-05, "epoch": 9.723232848232849, "percentage": 48.62, "elapsed_time": "0:54:19", "remaining_time": "0:57:25", "throughput": 1033.63, "total_tokens": 3369240} {"current_steps": 37420, "total_steps": 76960, "loss": 0.2212, "lr": 3.0520532518762924e-05, "epoch": 9.724532224532224, "percentage": 48.62, "elapsed_time": "0:54:20", "remaining_time": "0:57:24", "throughput": 1033.65, "total_tokens": 3369736} {"current_steps": 37425, "total_steps": 76960, "loss": 0.4427, "lr": 3.051500273628633e-05, "epoch": 9.7258316008316, "percentage": 48.63, "elapsed_time": "0:54:20", "remaining_time": "0:57:24", "throughput": 1033.64, "total_tokens": 3370152} {"current_steps": 37430, "total_steps": 76960, "loss": 0.3586, "lr": 3.0509472670167853e-05, "epoch": 9.727130977130978, "percentage": 48.64, "elapsed_time": "0:54:20", "remaining_time": "0:57:23", "throughput": 1033.65, "total_tokens": 3370600} {"current_steps": 37435, "total_steps": 76960, "loss": 0.1805, "lr": 3.0503942320691925e-05, "epoch": 9.728430353430353, "percentage": 48.64, "elapsed_time": "0:54:21", "remaining_time": "0:57:23", "throughput": 1033.65, "total_tokens": 3371032} {"current_steps": 37440, "total_steps": 76960, "loss": 0.289, "lr": 3.0498411688142962e-05, "epoch": 9.72972972972973, "percentage": 48.65, "elapsed_time": "0:54:21", "remaining_time": "0:57:22", "throughput": 1033.66, "total_tokens": 3371480} {"current_steps": 37445, "total_steps": 76960, "loss": 0.2564, "lr": 3.0492880772805433e-05, "epoch": 9.731029106029107, "percentage": 48.66, "elapsed_time": "0:54:22", "remaining_time": "0:57:22", "throughput": 1033.66, "total_tokens": 3371928} {"current_steps": 37450, "total_steps": 76960, "loss": 0.1469, "lr": 3.0487349574963775e-05, "epoch": 9.732328482328482, "percentage": 48.66, "elapsed_time": "0:54:22", "remaining_time": "0:57:21", "throughput": 1033.67, "total_tokens": 3372376} {"current_steps": 37455, "total_steps": 76960, "loss": 0.3782, "lr": 3.048181809490246e-05, "epoch": 9.733627858627859, "percentage": 48.67, "elapsed_time": "0:54:22", "remaining_time": "0:57:21", "throughput": 1033.67, "total_tokens": 3372824} {"current_steps": 37460, "total_steps": 76960, "loss": 0.2883, "lr": 3.0476286332906e-05, "epoch": 9.734927234927234, "percentage": 48.67, "elapsed_time": "0:54:23", "remaining_time": "0:57:21", "throughput": 1033.68, "total_tokens": 3373272} {"current_steps": 37465, "total_steps": 76960, "loss": 0.1808, "lr": 3.0470754289258886e-05, "epoch": 9.736226611226611, "percentage": 48.68, "elapsed_time": "0:54:23", "remaining_time": "0:57:20", "throughput": 1033.7, "total_tokens": 3373752} {"current_steps": 37470, "total_steps": 76960, "loss": 0.2591, "lr": 3.0465221964245633e-05, "epoch": 9.737525987525988, "percentage": 48.69, "elapsed_time": "0:54:24", "remaining_time": "0:57:20", "throughput": 1033.71, "total_tokens": 3374232} {"current_steps": 37475, "total_steps": 76960, "loss": 0.2322, "lr": 3.0459689358150774e-05, "epoch": 9.738825363825363, "percentage": 48.69, "elapsed_time": "0:54:24", "remaining_time": "0:57:19", "throughput": 1033.73, "total_tokens": 3374712} {"current_steps": 37480, "total_steps": 76960, "loss": 0.3549, "lr": 3.0454156471258866e-05, "epoch": 9.74012474012474, "percentage": 48.7, "elapsed_time": "0:54:25", "remaining_time": "0:57:19", "throughput": 1033.74, "total_tokens": 3375176} {"current_steps": 37485, "total_steps": 76960, "loss": 0.1565, "lr": 3.0448623303854464e-05, "epoch": 9.741424116424117, "percentage": 48.71, "elapsed_time": "0:54:25", "remaining_time": "0:57:18", "throughput": 1033.74, "total_tokens": 3375624} {"current_steps": 37490, "total_steps": 76960, "loss": 0.3211, "lr": 3.0443089856222147e-05, "epoch": 9.742723492723492, "percentage": 48.71, "elapsed_time": "0:54:25", "remaining_time": "0:57:18", "throughput": 1033.74, "total_tokens": 3376056} {"current_steps": 37495, "total_steps": 76960, "loss": 0.3382, "lr": 3.0437556128646494e-05, "epoch": 9.744022869022869, "percentage": 48.72, "elapsed_time": "0:54:26", "remaining_time": "0:57:17", "throughput": 1033.75, "total_tokens": 3376520} {"current_steps": 37500, "total_steps": 76960, "loss": 0.2204, "lr": 3.043202212141213e-05, "epoch": 9.745322245322246, "percentage": 48.73, "elapsed_time": "0:54:26", "remaining_time": "0:57:17", "throughput": 1033.76, "total_tokens": 3376984} {"current_steps": 37505, "total_steps": 76960, "loss": 0.2192, "lr": 3.0426487834803657e-05, "epoch": 9.746621621621621, "percentage": 48.73, "elapsed_time": "0:54:27", "remaining_time": "0:57:16", "throughput": 1033.77, "total_tokens": 3377432} {"current_steps": 37510, "total_steps": 76960, "loss": 0.2156, "lr": 3.0420953269105722e-05, "epoch": 9.747920997920998, "percentage": 48.74, "elapsed_time": "0:54:27", "remaining_time": "0:57:16", "throughput": 1033.78, "total_tokens": 3377880} {"current_steps": 37515, "total_steps": 76960, "loss": 0.2015, "lr": 3.0415418424602966e-05, "epoch": 9.749220374220375, "percentage": 48.75, "elapsed_time": "0:54:27", "remaining_time": "0:57:16", "throughput": 1033.78, "total_tokens": 3378328} {"current_steps": 37520, "total_steps": 76960, "loss": 0.323, "lr": 3.0409883301580045e-05, "epoch": 9.75051975051975, "percentage": 48.75, "elapsed_time": "0:54:28", "remaining_time": "0:57:15", "throughput": 1033.8, "total_tokens": 3378824} {"current_steps": 37525, "total_steps": 76960, "loss": 0.2411, "lr": 3.0404347900321638e-05, "epoch": 9.751819126819127, "percentage": 48.76, "elapsed_time": "0:54:28", "remaining_time": "0:57:15", "throughput": 1033.81, "total_tokens": 3379272} {"current_steps": 37530, "total_steps": 76960, "loss": 0.1529, "lr": 3.039881222111245e-05, "epoch": 9.753118503118504, "percentage": 48.77, "elapsed_time": "0:54:29", "remaining_time": "0:57:14", "throughput": 1033.81, "total_tokens": 3379720} {"current_steps": 37535, "total_steps": 76960, "loss": 0.2491, "lr": 3.0393276264237176e-05, "epoch": 9.754417879417879, "percentage": 48.77, "elapsed_time": "0:54:29", "remaining_time": "0:57:14", "throughput": 1033.81, "total_tokens": 3380152} {"current_steps": 37540, "total_steps": 76960, "loss": 0.3186, "lr": 3.0387740029980538e-05, "epoch": 9.755717255717256, "percentage": 48.78, "elapsed_time": "0:54:30", "remaining_time": "0:57:13", "throughput": 1033.81, "total_tokens": 3380584} {"current_steps": 37545, "total_steps": 76960, "loss": 0.1451, "lr": 3.0382203518627262e-05, "epoch": 9.757016632016633, "percentage": 48.79, "elapsed_time": "0:54:30", "remaining_time": "0:57:13", "throughput": 1033.82, "total_tokens": 3381032} {"current_steps": 37550, "total_steps": 76960, "loss": 0.1672, "lr": 3.03766667304621e-05, "epoch": 9.758316008316008, "percentage": 48.79, "elapsed_time": "0:54:30", "remaining_time": "0:57:12", "throughput": 1033.82, "total_tokens": 3381480} {"current_steps": 37555, "total_steps": 76960, "loss": 0.1291, "lr": 3.0371129665769825e-05, "epoch": 9.759615384615385, "percentage": 48.8, "elapsed_time": "0:54:31", "remaining_time": "0:57:12", "throughput": 1033.82, "total_tokens": 3381912} {"current_steps": 37560, "total_steps": 76960, "loss": 0.1868, "lr": 3.03655923248352e-05, "epoch": 9.76091476091476, "percentage": 48.8, "elapsed_time": "0:54:31", "remaining_time": "0:57:11", "throughput": 1033.82, "total_tokens": 3382328} {"current_steps": 37565, "total_steps": 76960, "loss": 0.2718, "lr": 3.036005470794302e-05, "epoch": 9.762214137214137, "percentage": 48.81, "elapsed_time": "0:54:32", "remaining_time": "0:57:11", "throughput": 1033.84, "total_tokens": 3382808} {"current_steps": 37570, "total_steps": 76960, "loss": 0.3694, "lr": 3.0354516815378085e-05, "epoch": 9.763513513513514, "percentage": 48.82, "elapsed_time": "0:54:32", "remaining_time": "0:57:11", "throughput": 1033.84, "total_tokens": 3383240} {"current_steps": 37575, "total_steps": 76960, "loss": 0.0994, "lr": 3.0348978647425236e-05, "epoch": 9.76481288981289, "percentage": 48.82, "elapsed_time": "0:54:32", "remaining_time": "0:57:10", "throughput": 1033.84, "total_tokens": 3383688} {"current_steps": 37580, "total_steps": 76960, "loss": 0.3298, "lr": 3.0343440204369278e-05, "epoch": 9.766112266112266, "percentage": 48.83, "elapsed_time": "0:54:33", "remaining_time": "0:57:10", "throughput": 1033.85, "total_tokens": 3384136} {"current_steps": 37585, "total_steps": 76960, "loss": 0.2777, "lr": 3.0337901486495073e-05, "epoch": 9.767411642411643, "percentage": 48.84, "elapsed_time": "0:54:33", "remaining_time": "0:57:09", "throughput": 1033.85, "total_tokens": 3384568} {"current_steps": 37590, "total_steps": 76960, "loss": 0.2714, "lr": 3.0332362494087485e-05, "epoch": 9.768711018711018, "percentage": 48.84, "elapsed_time": "0:54:34", "remaining_time": "0:57:09", "throughput": 1033.85, "total_tokens": 3385016} {"current_steps": 37595, "total_steps": 76960, "loss": 0.1923, "lr": 3.0326823227431377e-05, "epoch": 9.770010395010395, "percentage": 48.85, "elapsed_time": "0:54:34", "remaining_time": "0:57:08", "throughput": 1033.86, "total_tokens": 3385464} {"current_steps": 37600, "total_steps": 76960, "loss": 0.2087, "lr": 3.0321283686811648e-05, "epoch": 9.771309771309772, "percentage": 48.86, "elapsed_time": "0:54:35", "remaining_time": "0:57:08", "throughput": 1033.86, "total_tokens": 3385896} {"current_steps": 37605, "total_steps": 76960, "loss": 0.2804, "lr": 3.0315743872513202e-05, "epoch": 9.772609147609147, "percentage": 48.86, "elapsed_time": "0:54:35", "remaining_time": "0:57:07", "throughput": 1033.86, "total_tokens": 3386328} {"current_steps": 37610, "total_steps": 76960, "loss": 0.2725, "lr": 3.0310203784820957e-05, "epoch": 9.773908523908524, "percentage": 48.87, "elapsed_time": "0:54:35", "remaining_time": "0:57:07", "throughput": 1033.86, "total_tokens": 3386760} {"current_steps": 37615, "total_steps": 76960, "loss": 0.2569, "lr": 3.0304663424019842e-05, "epoch": 9.7752079002079, "percentage": 48.88, "elapsed_time": "0:54:36", "remaining_time": "0:57:06", "throughput": 1033.86, "total_tokens": 3387176} {"current_steps": 37620, "total_steps": 76960, "loss": 0.2479, "lr": 3.0299122790394794e-05, "epoch": 9.776507276507276, "percentage": 48.88, "elapsed_time": "0:54:36", "remaining_time": "0:57:06", "throughput": 1033.88, "total_tokens": 3387672} {"current_steps": 37625, "total_steps": 76960, "loss": 0.2351, "lr": 3.0293581884230798e-05, "epoch": 9.777806652806653, "percentage": 48.89, "elapsed_time": "0:54:37", "remaining_time": "0:57:06", "throughput": 1033.88, "total_tokens": 3388120} {"current_steps": 37630, "total_steps": 76960, "loss": 0.2434, "lr": 3.028804070581281e-05, "epoch": 9.779106029106028, "percentage": 48.9, "elapsed_time": "0:54:37", "remaining_time": "0:57:05", "throughput": 1033.89, "total_tokens": 3388584} {"current_steps": 37635, "total_steps": 76960, "loss": 0.2992, "lr": 3.028249925542582e-05, "epoch": 9.780405405405405, "percentage": 48.9, "elapsed_time": "0:54:37", "remaining_time": "0:57:05", "throughput": 1033.9, "total_tokens": 3389032} {"current_steps": 37640, "total_steps": 76960, "loss": 0.2942, "lr": 3.027695753335483e-05, "epoch": 9.781704781704782, "percentage": 48.91, "elapsed_time": "0:54:38", "remaining_time": "0:57:04", "throughput": 1033.9, "total_tokens": 3389464} {"current_steps": 37645, "total_steps": 76960, "loss": 0.2591, "lr": 3.027141553988487e-05, "epoch": 9.783004158004157, "percentage": 48.92, "elapsed_time": "0:54:38", "remaining_time": "0:57:04", "throughput": 1033.9, "total_tokens": 3389896} {"current_steps": 37650, "total_steps": 76960, "loss": 0.283, "lr": 3.0265873275300945e-05, "epoch": 9.784303534303534, "percentage": 48.92, "elapsed_time": "0:54:39", "remaining_time": "0:57:03", "throughput": 1033.91, "total_tokens": 3390344} {"current_steps": 37655, "total_steps": 76960, "loss": 0.1955, "lr": 3.026033073988811e-05, "epoch": 9.785602910602911, "percentage": 48.93, "elapsed_time": "0:54:39", "remaining_time": "0:57:03", "throughput": 1033.91, "total_tokens": 3390792} {"current_steps": 37660, "total_steps": 76960, "loss": 0.1737, "lr": 3.0254787933931434e-05, "epoch": 9.786902286902286, "percentage": 48.93, "elapsed_time": "0:54:39", "remaining_time": "0:57:02", "throughput": 1033.92, "total_tokens": 3391256} {"current_steps": 37665, "total_steps": 76960, "loss": 0.2396, "lr": 3.0249244857715976e-05, "epoch": 9.788201663201663, "percentage": 48.94, "elapsed_time": "0:54:40", "remaining_time": "0:57:02", "throughput": 1033.93, "total_tokens": 3391704} {"current_steps": 37670, "total_steps": 76960, "loss": 0.3317, "lr": 3.024370151152682e-05, "epoch": 9.78950103950104, "percentage": 48.95, "elapsed_time": "0:54:40", "remaining_time": "0:57:01", "throughput": 1033.94, "total_tokens": 3392184} {"current_steps": 37675, "total_steps": 76960, "loss": 0.2657, "lr": 3.0238157895649078e-05, "epoch": 9.790800415800415, "percentage": 48.95, "elapsed_time": "0:54:41", "remaining_time": "0:57:01", "throughput": 1033.95, "total_tokens": 3392648} {"current_steps": 37680, "total_steps": 76960, "loss": 0.336, "lr": 3.0232614010367854e-05, "epoch": 9.792099792099792, "percentage": 48.96, "elapsed_time": "0:54:41", "remaining_time": "0:57:00", "throughput": 1033.97, "total_tokens": 3393128} {"current_steps": 37685, "total_steps": 76960, "loss": 0.2461, "lr": 3.0227069855968283e-05, "epoch": 9.79339916839917, "percentage": 48.97, "elapsed_time": "0:54:42", "remaining_time": "0:57:00", "throughput": 1033.98, "total_tokens": 3393576} {"current_steps": 37690, "total_steps": 76960, "loss": 0.2706, "lr": 3.0221525432735492e-05, "epoch": 9.794698544698544, "percentage": 48.97, "elapsed_time": "0:54:42", "remaining_time": "0:57:00", "throughput": 1033.99, "total_tokens": 3394056} {"current_steps": 37695, "total_steps": 76960, "loss": 0.1992, "lr": 3.0215980740954653e-05, "epoch": 9.795997920997921, "percentage": 48.98, "elapsed_time": "0:54:42", "remaining_time": "0:56:59", "throughput": 1034.0, "total_tokens": 3394520} {"current_steps": 37700, "total_steps": 76960, "loss": 0.2755, "lr": 3.0210435780910923e-05, "epoch": 9.797297297297296, "percentage": 48.99, "elapsed_time": "0:54:43", "remaining_time": "0:56:59", "throughput": 1034.01, "total_tokens": 3394984} {"current_steps": 37705, "total_steps": 76960, "loss": 0.1582, "lr": 3.0204890552889486e-05, "epoch": 9.798596673596673, "percentage": 48.99, "elapsed_time": "0:54:43", "remaining_time": "0:56:58", "throughput": 1034.02, "total_tokens": 3395432} {"current_steps": 37710, "total_steps": 76960, "loss": 0.1954, "lr": 3.0199345057175544e-05, "epoch": 9.79989604989605, "percentage": 49.0, "elapsed_time": "0:54:44", "remaining_time": "0:56:58", "throughput": 1034.02, "total_tokens": 3395880} {"current_steps": 37715, "total_steps": 76960, "loss": 0.3951, "lr": 3.0193799294054304e-05, "epoch": 9.801195426195425, "percentage": 49.01, "elapsed_time": "0:54:44", "remaining_time": "0:56:57", "throughput": 1034.03, "total_tokens": 3396344} {"current_steps": 37720, "total_steps": 76960, "loss": 0.2062, "lr": 3.0188253263810995e-05, "epoch": 9.802494802494802, "percentage": 49.01, "elapsed_time": "0:54:44", "remaining_time": "0:56:57", "throughput": 1034.03, "total_tokens": 3396760} {"current_steps": 37725, "total_steps": 76960, "loss": 0.2684, "lr": 3.0182706966730834e-05, "epoch": 9.80379417879418, "percentage": 49.02, "elapsed_time": "0:54:45", "remaining_time": "0:56:56", "throughput": 1034.04, "total_tokens": 3397240} {"current_steps": 37730, "total_steps": 76960, "loss": 0.2467, "lr": 3.0177160403099104e-05, "epoch": 9.805093555093555, "percentage": 49.03, "elapsed_time": "0:54:45", "remaining_time": "0:56:56", "throughput": 1034.05, "total_tokens": 3397688} {"current_steps": 37735, "total_steps": 76960, "loss": 0.2642, "lr": 3.0171613573201046e-05, "epoch": 9.806392931392931, "percentage": 49.03, "elapsed_time": "0:54:46", "remaining_time": "0:56:55", "throughput": 1034.04, "total_tokens": 3398104} {"current_steps": 37740, "total_steps": 76960, "loss": 0.3097, "lr": 3.0166066477321947e-05, "epoch": 9.807692307692308, "percentage": 49.04, "elapsed_time": "0:54:46", "remaining_time": "0:56:55", "throughput": 1034.06, "total_tokens": 3398568} {"current_steps": 37745, "total_steps": 76960, "loss": 0.1936, "lr": 3.01605191157471e-05, "epoch": 9.808991683991684, "percentage": 49.04, "elapsed_time": "0:54:47", "remaining_time": "0:56:55", "throughput": 1034.07, "total_tokens": 3399032} {"current_steps": 37750, "total_steps": 76960, "loss": 0.2449, "lr": 3.0154971488761808e-05, "epoch": 9.81029106029106, "percentage": 49.05, "elapsed_time": "0:54:47", "remaining_time": "0:56:54", "throughput": 1034.06, "total_tokens": 3399448} {"current_steps": 37755, "total_steps": 76960, "loss": 0.1058, "lr": 3.01494235966514e-05, "epoch": 9.811590436590437, "percentage": 49.06, "elapsed_time": "0:54:47", "remaining_time": "0:56:54", "throughput": 1034.06, "total_tokens": 3399880} {"current_steps": 37760, "total_steps": 76960, "loss": 0.2106, "lr": 3.0143875439701192e-05, "epoch": 9.812889812889813, "percentage": 49.06, "elapsed_time": "0:54:48", "remaining_time": "0:56:53", "throughput": 1034.09, "total_tokens": 3400392} {"current_steps": 37765, "total_steps": 76960, "loss": 0.1654, "lr": 3.013832701819655e-05, "epoch": 9.81418918918919, "percentage": 49.07, "elapsed_time": "0:54:48", "remaining_time": "0:56:53", "throughput": 1034.09, "total_tokens": 3400840} {"current_steps": 37770, "total_steps": 76960, "loss": 0.202, "lr": 3.0132778332422824e-05, "epoch": 9.815488565488565, "percentage": 49.08, "elapsed_time": "0:54:49", "remaining_time": "0:56:52", "throughput": 1034.09, "total_tokens": 3401272} {"current_steps": 37775, "total_steps": 76960, "loss": 0.3976, "lr": 3.012722938266539e-05, "epoch": 9.816787941787942, "percentage": 49.08, "elapsed_time": "0:54:49", "remaining_time": "0:56:52", "throughput": 1034.1, "total_tokens": 3401720} {"current_steps": 37780, "total_steps": 76960, "loss": 0.1205, "lr": 3.0121680169209636e-05, "epoch": 9.818087318087318, "percentage": 49.09, "elapsed_time": "0:54:49", "remaining_time": "0:56:51", "throughput": 1034.11, "total_tokens": 3402184} {"current_steps": 37785, "total_steps": 76960, "loss": 0.2166, "lr": 3.011613069234097e-05, "epoch": 9.819386694386694, "percentage": 49.1, "elapsed_time": "0:54:50", "remaining_time": "0:56:51", "throughput": 1034.12, "total_tokens": 3402632} {"current_steps": 37790, "total_steps": 76960, "loss": 0.3163, "lr": 3.0110580952344792e-05, "epoch": 9.82068607068607, "percentage": 49.1, "elapsed_time": "0:54:50", "remaining_time": "0:56:50", "throughput": 1034.12, "total_tokens": 3403080} {"current_steps": 37795, "total_steps": 76960, "loss": 0.3527, "lr": 3.0105030949506542e-05, "epoch": 9.821985446985448, "percentage": 49.11, "elapsed_time": "0:54:51", "remaining_time": "0:56:50", "throughput": 1034.13, "total_tokens": 3403528} {"current_steps": 37800, "total_steps": 76960, "loss": 0.1796, "lr": 3.009948068411166e-05, "epoch": 9.823284823284823, "percentage": 49.12, "elapsed_time": "0:54:51", "remaining_time": "0:56:50", "throughput": 1034.13, "total_tokens": 3403976} {"current_steps": 37805, "total_steps": 76960, "loss": 0.2053, "lr": 3.0093930156445595e-05, "epoch": 9.8245841995842, "percentage": 49.12, "elapsed_time": "0:54:52", "remaining_time": "0:56:49", "throughput": 1034.14, "total_tokens": 3404424} {"current_steps": 37810, "total_steps": 76960, "loss": 0.1597, "lr": 3.008837936679383e-05, "epoch": 9.825883575883577, "percentage": 49.13, "elapsed_time": "0:54:52", "remaining_time": "0:56:49", "throughput": 1034.13, "total_tokens": 3404840} {"current_steps": 37815, "total_steps": 76960, "loss": 0.1834, "lr": 3.0082828315441825e-05, "epoch": 9.827182952182952, "percentage": 49.14, "elapsed_time": "0:54:52", "remaining_time": "0:56:48", "throughput": 1034.13, "total_tokens": 3405256} {"current_steps": 37820, "total_steps": 76960, "loss": 0.2084, "lr": 3.0077277002675097e-05, "epoch": 9.828482328482329, "percentage": 49.14, "elapsed_time": "0:54:53", "remaining_time": "0:56:48", "throughput": 1034.13, "total_tokens": 3405704} {"current_steps": 37825, "total_steps": 76960, "loss": 0.2575, "lr": 3.007172542877915e-05, "epoch": 9.829781704781706, "percentage": 49.15, "elapsed_time": "0:54:53", "remaining_time": "0:56:47", "throughput": 1034.13, "total_tokens": 3406120} {"current_steps": 37830, "total_steps": 76960, "loss": 0.1805, "lr": 3.006617359403951e-05, "epoch": 9.83108108108108, "percentage": 49.16, "elapsed_time": "0:54:54", "remaining_time": "0:56:47", "throughput": 1034.15, "total_tokens": 3406616} {"current_steps": 37835, "total_steps": 76960, "loss": 0.2793, "lr": 3.0060621498741692e-05, "epoch": 9.832380457380458, "percentage": 49.16, "elapsed_time": "0:54:54", "remaining_time": "0:56:46", "throughput": 1034.16, "total_tokens": 3407064} {"current_steps": 37840, "total_steps": 76960, "loss": 0.3373, "lr": 3.0055069143171284e-05, "epoch": 9.833679833679835, "percentage": 49.17, "elapsed_time": "0:54:54", "remaining_time": "0:56:46", "throughput": 1034.16, "total_tokens": 3407512} {"current_steps": 37845, "total_steps": 76960, "loss": 0.4188, "lr": 3.0049516527613812e-05, "epoch": 9.83497920997921, "percentage": 49.17, "elapsed_time": "0:54:55", "remaining_time": "0:56:45", "throughput": 1034.17, "total_tokens": 3407960} {"current_steps": 37850, "total_steps": 76960, "loss": 0.3683, "lr": 3.0043963652354863e-05, "epoch": 9.836278586278587, "percentage": 49.18, "elapsed_time": "0:54:55", "remaining_time": "0:56:45", "throughput": 1034.18, "total_tokens": 3408424} {"current_steps": 37855, "total_steps": 76960, "loss": 0.3014, "lr": 3.0038410517680036e-05, "epoch": 9.837577962577962, "percentage": 49.19, "elapsed_time": "0:54:56", "remaining_time": "0:56:45", "throughput": 1034.19, "total_tokens": 3408904} {"current_steps": 37860, "total_steps": 76960, "loss": 0.2481, "lr": 3.003285712387493e-05, "epoch": 9.838877338877339, "percentage": 49.19, "elapsed_time": "0:54:56", "remaining_time": "0:56:44", "throughput": 1034.2, "total_tokens": 3409352} {"current_steps": 37865, "total_steps": 76960, "loss": 0.2084, "lr": 3.002730347122516e-05, "epoch": 9.840176715176716, "percentage": 49.2, "elapsed_time": "0:54:57", "remaining_time": "0:56:44", "throughput": 1034.21, "total_tokens": 3409816} {"current_steps": 37870, "total_steps": 76960, "loss": 0.235, "lr": 3.002174956001635e-05, "epoch": 9.84147609147609, "percentage": 49.21, "elapsed_time": "0:54:57", "remaining_time": "0:56:43", "throughput": 1034.22, "total_tokens": 3410296} {"current_steps": 37875, "total_steps": 76960, "loss": 0.1737, "lr": 3.001619539053415e-05, "epoch": 9.842775467775468, "percentage": 49.21, "elapsed_time": "0:54:57", "remaining_time": "0:56:43", "throughput": 1034.22, "total_tokens": 3410712} {"current_steps": 37880, "total_steps": 76960, "loss": 0.2913, "lr": 3.001064096306422e-05, "epoch": 9.844074844074845, "percentage": 49.22, "elapsed_time": "0:54:58", "remaining_time": "0:56:42", "throughput": 1034.23, "total_tokens": 3411176} {"current_steps": 37885, "total_steps": 76960, "loss": 0.2334, "lr": 3.0005086277892218e-05, "epoch": 9.84537422037422, "percentage": 49.23, "elapsed_time": "0:54:58", "remaining_time": "0:56:42", "throughput": 1034.24, "total_tokens": 3411624} {"current_steps": 37890, "total_steps": 76960, "loss": 0.184, "lr": 2.9999531335303838e-05, "epoch": 9.846673596673597, "percentage": 49.23, "elapsed_time": "0:54:59", "remaining_time": "0:56:41", "throughput": 1034.25, "total_tokens": 3412088} {"current_steps": 37895, "total_steps": 76960, "loss": 0.1877, "lr": 2.9993976135584766e-05, "epoch": 9.847972972972974, "percentage": 49.24, "elapsed_time": "0:54:59", "remaining_time": "0:56:41", "throughput": 1034.26, "total_tokens": 3412568} {"current_steps": 37900, "total_steps": 76960, "loss": 0.363, "lr": 2.9988420679020724e-05, "epoch": 9.849272349272349, "percentage": 49.25, "elapsed_time": "0:54:59", "remaining_time": "0:56:40", "throughput": 1034.27, "total_tokens": 3413016} {"current_steps": 37905, "total_steps": 76960, "loss": 0.5248, "lr": 2.998286496589742e-05, "epoch": 9.850571725571726, "percentage": 49.25, "elapsed_time": "0:55:00", "remaining_time": "0:56:40", "throughput": 1034.27, "total_tokens": 3413480} {"current_steps": 37910, "total_steps": 76960, "loss": 0.3151, "lr": 2.99773089965006e-05, "epoch": 9.851871101871101, "percentage": 49.26, "elapsed_time": "0:55:00", "remaining_time": "0:56:40", "throughput": 1034.28, "total_tokens": 3413928} {"current_steps": 37915, "total_steps": 76960, "loss": 0.3341, "lr": 2.9971752771116012e-05, "epoch": 9.853170478170478, "percentage": 49.27, "elapsed_time": "0:55:01", "remaining_time": "0:56:39", "throughput": 1034.3, "total_tokens": 3414408} {"current_steps": 37920, "total_steps": 76960, "loss": 0.144, "lr": 2.9966196290029408e-05, "epoch": 9.854469854469855, "percentage": 49.27, "elapsed_time": "0:55:01", "remaining_time": "0:56:39", "throughput": 1034.29, "total_tokens": 3414824} {"current_steps": 37925, "total_steps": 76960, "loss": 0.3059, "lr": 2.9960639553526577e-05, "epoch": 9.85576923076923, "percentage": 49.28, "elapsed_time": "0:55:02", "remaining_time": "0:56:38", "throughput": 1034.29, "total_tokens": 3415240} {"current_steps": 37930, "total_steps": 76960, "loss": 0.1483, "lr": 2.99550825618933e-05, "epoch": 9.857068607068607, "percentage": 49.29, "elapsed_time": "0:55:02", "remaining_time": "0:56:38", "throughput": 1034.3, "total_tokens": 3415720} {"current_steps": 37935, "total_steps": 76960, "loss": 0.2197, "lr": 2.9949525315415378e-05, "epoch": 9.858367983367984, "percentage": 49.29, "elapsed_time": "0:55:02", "remaining_time": "0:56:37", "throughput": 1034.3, "total_tokens": 3416136} {"current_steps": 37940, "total_steps": 76960, "loss": 0.1062, "lr": 2.994396781437862e-05, "epoch": 9.859667359667359, "percentage": 49.3, "elapsed_time": "0:55:03", "remaining_time": "0:56:37", "throughput": 1034.29, "total_tokens": 3416552} {"current_steps": 37945, "total_steps": 76960, "loss": 0.3636, "lr": 2.9938410059068868e-05, "epoch": 9.860966735966736, "percentage": 49.3, "elapsed_time": "0:55:03", "remaining_time": "0:56:36", "throughput": 1034.29, "total_tokens": 3416984} {"current_steps": 37950, "total_steps": 76960, "loss": 0.2412, "lr": 2.9932852049771952e-05, "epoch": 9.862266112266113, "percentage": 49.31, "elapsed_time": "0:55:04", "remaining_time": "0:56:36", "throughput": 1034.3, "total_tokens": 3417448} {"current_steps": 37955, "total_steps": 76960, "loss": 0.1393, "lr": 2.992729378677373e-05, "epoch": 9.863565488565488, "percentage": 49.32, "elapsed_time": "0:55:04", "remaining_time": "0:56:35", "throughput": 1034.3, "total_tokens": 3417864} {"current_steps": 37960, "total_steps": 76960, "loss": 0.3535, "lr": 2.9921735270360063e-05, "epoch": 9.864864864864865, "percentage": 49.32, "elapsed_time": "0:55:04", "remaining_time": "0:56:35", "throughput": 1034.29, "total_tokens": 3418280} {"current_steps": 37965, "total_steps": 76960, "loss": 0.0752, "lr": 2.991617650081684e-05, "epoch": 9.866164241164242, "percentage": 49.33, "elapsed_time": "0:55:05", "remaining_time": "0:56:35", "throughput": 1034.3, "total_tokens": 3418744} {"current_steps": 37970, "total_steps": 76960, "loss": 0.2995, "lr": 2.9910617478429953e-05, "epoch": 9.867463617463617, "percentage": 49.34, "elapsed_time": "0:55:05", "remaining_time": "0:56:34", "throughput": 1034.31, "total_tokens": 3419208} {"current_steps": 37975, "total_steps": 76960, "loss": 0.235, "lr": 2.9905058203485298e-05, "epoch": 9.868762993762994, "percentage": 49.34, "elapsed_time": "0:55:06", "remaining_time": "0:56:34", "throughput": 1034.31, "total_tokens": 3419624} {"current_steps": 37980, "total_steps": 76960, "loss": 0.3209, "lr": 2.98994986762688e-05, "epoch": 9.87006237006237, "percentage": 49.35, "elapsed_time": "0:55:06", "remaining_time": "0:56:33", "throughput": 1034.33, "total_tokens": 3420104} {"current_steps": 37985, "total_steps": 76960, "loss": 0.4078, "lr": 2.9893938897066393e-05, "epoch": 9.871361746361746, "percentage": 49.36, "elapsed_time": "0:55:07", "remaining_time": "0:56:33", "throughput": 1034.33, "total_tokens": 3420536} {"current_steps": 37990, "total_steps": 76960, "loss": 0.2825, "lr": 2.988837886616402e-05, "epoch": 9.872661122661123, "percentage": 49.36, "elapsed_time": "0:55:07", "remaining_time": "0:56:32", "throughput": 1034.34, "total_tokens": 3421016} {"current_steps": 37995, "total_steps": 76960, "loss": 0.2549, "lr": 2.9882818583847634e-05, "epoch": 9.8739604989605, "percentage": 49.37, "elapsed_time": "0:55:07", "remaining_time": "0:56:32", "throughput": 1034.34, "total_tokens": 3421448} {"current_steps": 38000, "total_steps": 76960, "loss": 0.181, "lr": 2.9877258050403212e-05, "epoch": 9.875259875259875, "percentage": 49.38, "elapsed_time": "0:55:08", "remaining_time": "0:56:31", "throughput": 1034.34, "total_tokens": 3421880} {"current_steps": 38005, "total_steps": 76960, "loss": 0.1557, "lr": 2.987169726611673e-05, "epoch": 9.876559251559252, "percentage": 49.38, "elapsed_time": "0:55:08", "remaining_time": "0:56:31", "throughput": 1034.35, "total_tokens": 3422344} {"current_steps": 38010, "total_steps": 76960, "loss": 0.3406, "lr": 2.9866136231274195e-05, "epoch": 9.877858627858627, "percentage": 49.39, "elapsed_time": "0:55:09", "remaining_time": "0:56:30", "throughput": 1034.36, "total_tokens": 3422792} {"current_steps": 38015, "total_steps": 76960, "loss": 0.2787, "lr": 2.9860574946161612e-05, "epoch": 9.879158004158004, "percentage": 49.4, "elapsed_time": "0:55:09", "remaining_time": "0:56:30", "throughput": 1034.37, "total_tokens": 3423272} {"current_steps": 38020, "total_steps": 76960, "loss": 0.411, "lr": 2.9855013411065e-05, "epoch": 9.880457380457381, "percentage": 49.4, "elapsed_time": "0:55:09", "remaining_time": "0:56:30", "throughput": 1034.38, "total_tokens": 3423720} {"current_steps": 38025, "total_steps": 76960, "loss": 0.2035, "lr": 2.9849451626270397e-05, "epoch": 9.881756756756756, "percentage": 49.41, "elapsed_time": "0:55:10", "remaining_time": "0:56:29", "throughput": 1034.39, "total_tokens": 3424200} {"current_steps": 38030, "total_steps": 76960, "loss": 0.2532, "lr": 2.984388959206385e-05, "epoch": 9.883056133056133, "percentage": 49.42, "elapsed_time": "0:55:10", "remaining_time": "0:56:29", "throughput": 1034.39, "total_tokens": 3424616} {"current_steps": 38035, "total_steps": 76960, "loss": 0.204, "lr": 2.983832730873143e-05, "epoch": 9.88435550935551, "percentage": 49.42, "elapsed_time": "0:55:11", "remaining_time": "0:56:28", "throughput": 1034.4, "total_tokens": 3425080} {"current_steps": 38040, "total_steps": 76960, "loss": 0.2396, "lr": 2.983276477655919e-05, "epoch": 9.885654885654885, "percentage": 49.43, "elapsed_time": "0:55:11", "remaining_time": "0:56:28", "throughput": 1034.41, "total_tokens": 3425528} {"current_steps": 38045, "total_steps": 76960, "loss": 0.1927, "lr": 2.9827201995833225e-05, "epoch": 9.886954261954262, "percentage": 49.43, "elapsed_time": "0:55:12", "remaining_time": "0:56:27", "throughput": 1034.43, "total_tokens": 3426024} {"current_steps": 38050, "total_steps": 76960, "loss": 0.2923, "lr": 2.982163896683964e-05, "epoch": 9.888253638253639, "percentage": 49.44, "elapsed_time": "0:55:12", "remaining_time": "0:56:27", "throughput": 1034.44, "total_tokens": 3426504} {"current_steps": 38055, "total_steps": 76960, "loss": 0.2642, "lr": 2.9816075689864543e-05, "epoch": 9.889553014553014, "percentage": 49.45, "elapsed_time": "0:55:12", "remaining_time": "0:56:26", "throughput": 1034.45, "total_tokens": 3426952} {"current_steps": 38060, "total_steps": 76960, "loss": 0.2213, "lr": 2.981051216519406e-05, "epoch": 9.890852390852391, "percentage": 49.45, "elapsed_time": "0:55:13", "remaining_time": "0:56:26", "throughput": 1034.46, "total_tokens": 3427432} {"current_steps": 38065, "total_steps": 76960, "loss": 0.1189, "lr": 2.9804948393114324e-05, "epoch": 9.892151767151766, "percentage": 49.46, "elapsed_time": "0:55:13", "remaining_time": "0:56:25", "throughput": 1034.47, "total_tokens": 3427880} {"current_steps": 38070, "total_steps": 76960, "loss": 0.2317, "lr": 2.9799384373911488e-05, "epoch": 9.893451143451143, "percentage": 49.47, "elapsed_time": "0:55:14", "remaining_time": "0:56:25", "throughput": 1034.48, "total_tokens": 3428360} {"current_steps": 38075, "total_steps": 76960, "loss": 0.2724, "lr": 2.9793820107871717e-05, "epoch": 9.89475051975052, "percentage": 49.47, "elapsed_time": "0:55:14", "remaining_time": "0:56:25", "throughput": 1034.51, "total_tokens": 3428872} {"current_steps": 38080, "total_steps": 76960, "loss": 0.366, "lr": 2.978825559528119e-05, "epoch": 9.896049896049895, "percentage": 49.48, "elapsed_time": "0:55:14", "remaining_time": "0:56:24", "throughput": 1034.52, "total_tokens": 3429336} {"current_steps": 38085, "total_steps": 76960, "loss": 0.2364, "lr": 2.978269083642608e-05, "epoch": 9.897349272349272, "percentage": 49.49, "elapsed_time": "0:55:15", "remaining_time": "0:56:24", "throughput": 1034.52, "total_tokens": 3429784} {"current_steps": 38090, "total_steps": 76960, "loss": 0.1803, "lr": 2.9777125831592602e-05, "epoch": 9.89864864864865, "percentage": 49.49, "elapsed_time": "0:55:15", "remaining_time": "0:56:23", "throughput": 1034.53, "total_tokens": 3430248} {"current_steps": 38095, "total_steps": 76960, "loss": 0.3355, "lr": 2.9771560581066972e-05, "epoch": 9.899948024948024, "percentage": 49.5, "elapsed_time": "0:55:16", "remaining_time": "0:56:23", "throughput": 1034.54, "total_tokens": 3430696} {"current_steps": 38100, "total_steps": 76960, "loss": 0.2204, "lr": 2.9765995085135402e-05, "epoch": 9.901247401247401, "percentage": 49.51, "elapsed_time": "0:55:16", "remaining_time": "0:56:22", "throughput": 1034.54, "total_tokens": 3431144} {"current_steps": 38105, "total_steps": 76960, "loss": 0.0886, "lr": 2.976042934408414e-05, "epoch": 9.902546777546778, "percentage": 49.51, "elapsed_time": "0:55:16", "remaining_time": "0:56:22", "throughput": 1034.55, "total_tokens": 3431608} {"current_steps": 38110, "total_steps": 76960, "loss": 0.0756, "lr": 2.9754863358199436e-05, "epoch": 9.903846153846153, "percentage": 49.52, "elapsed_time": "0:55:17", "remaining_time": "0:56:21", "throughput": 1034.56, "total_tokens": 3432056} {"current_steps": 38115, "total_steps": 76960, "loss": 0.3342, "lr": 2.974929712776755e-05, "epoch": 9.90514553014553, "percentage": 49.53, "elapsed_time": "0:55:17", "remaining_time": "0:56:21", "throughput": 1034.56, "total_tokens": 3432504} {"current_steps": 38120, "total_steps": 76960, "loss": 0.299, "lr": 2.9743730653074766e-05, "epoch": 9.906444906444907, "percentage": 49.53, "elapsed_time": "0:55:18", "remaining_time": "0:56:20", "throughput": 1034.57, "total_tokens": 3432968} {"current_steps": 38125, "total_steps": 76960, "loss": 0.3878, "lr": 2.9738163934407365e-05, "epoch": 9.907744282744282, "percentage": 49.54, "elapsed_time": "0:55:18", "remaining_time": "0:56:20", "throughput": 1034.57, "total_tokens": 3433384} {"current_steps": 38130, "total_steps": 76960, "loss": 0.1679, "lr": 2.9732596972051656e-05, "epoch": 9.90904365904366, "percentage": 49.55, "elapsed_time": "0:55:19", "remaining_time": "0:56:20", "throughput": 1034.59, "total_tokens": 3433864} {"current_steps": 38135, "total_steps": 76960, "loss": 0.135, "lr": 2.9727029766293944e-05, "epoch": 9.910343035343036, "percentage": 49.55, "elapsed_time": "0:55:19", "remaining_time": "0:56:19", "throughput": 1034.6, "total_tokens": 3434328} {"current_steps": 38140, "total_steps": 76960, "loss": 0.1331, "lr": 2.9721462317420572e-05, "epoch": 9.911642411642411, "percentage": 49.56, "elapsed_time": "0:55:19", "remaining_time": "0:56:19", "throughput": 1034.6, "total_tokens": 3434760} {"current_steps": 38145, "total_steps": 76960, "loss": 0.2672, "lr": 2.9715894625717866e-05, "epoch": 9.912941787941788, "percentage": 49.56, "elapsed_time": "0:55:20", "remaining_time": "0:56:18", "throughput": 1034.61, "total_tokens": 3435240} {"current_steps": 38150, "total_steps": 76960, "loss": 0.2735, "lr": 2.971032669147218e-05, "epoch": 9.914241164241163, "percentage": 49.57, "elapsed_time": "0:55:20", "remaining_time": "0:56:18", "throughput": 1034.62, "total_tokens": 3435704} {"current_steps": 38155, "total_steps": 76960, "loss": 0.2285, "lr": 2.9704758514969878e-05, "epoch": 9.91554054054054, "percentage": 49.58, "elapsed_time": "0:55:21", "remaining_time": "0:56:17", "throughput": 1034.62, "total_tokens": 3436136} {"current_steps": 38160, "total_steps": 76960, "loss": 0.3618, "lr": 2.9699190096497335e-05, "epoch": 9.916839916839917, "percentage": 49.58, "elapsed_time": "0:55:21", "remaining_time": "0:56:17", "throughput": 1034.63, "total_tokens": 3436600} {"current_steps": 38165, "total_steps": 76960, "loss": 0.312, "lr": 2.9693621436340956e-05, "epoch": 9.918139293139292, "percentage": 49.59, "elapsed_time": "0:55:21", "remaining_time": "0:56:16", "throughput": 1034.64, "total_tokens": 3437064} {"current_steps": 38170, "total_steps": 76960, "loss": 0.273, "lr": 2.9688052534787113e-05, "epoch": 9.91943866943867, "percentage": 49.6, "elapsed_time": "0:55:22", "remaining_time": "0:56:16", "throughput": 1034.65, "total_tokens": 3437528} {"current_steps": 38175, "total_steps": 76960, "loss": 0.202, "lr": 2.9682483392122247e-05, "epoch": 9.920738045738046, "percentage": 49.6, "elapsed_time": "0:55:22", "remaining_time": "0:56:15", "throughput": 1034.65, "total_tokens": 3437960} {"current_steps": 38180, "total_steps": 76960, "loss": 0.3273, "lr": 2.9676914008632772e-05, "epoch": 9.922037422037421, "percentage": 49.61, "elapsed_time": "0:55:23", "remaining_time": "0:56:15", "throughput": 1034.65, "total_tokens": 3438392} {"current_steps": 38185, "total_steps": 76960, "loss": 0.1455, "lr": 2.9671344384605127e-05, "epoch": 9.923336798336798, "percentage": 49.62, "elapsed_time": "0:55:23", "remaining_time": "0:56:15", "throughput": 1034.67, "total_tokens": 3438872} {"current_steps": 38190, "total_steps": 76960, "loss": 0.2081, "lr": 2.9665774520325755e-05, "epoch": 9.924636174636175, "percentage": 49.62, "elapsed_time": "0:55:24", "remaining_time": "0:56:14", "throughput": 1034.67, "total_tokens": 3439304} {"current_steps": 38195, "total_steps": 76960, "loss": 0.2402, "lr": 2.966020441608114e-05, "epoch": 9.92593555093555, "percentage": 49.63, "elapsed_time": "0:55:24", "remaining_time": "0:56:14", "throughput": 1034.68, "total_tokens": 3439768} {"current_steps": 38200, "total_steps": 76960, "loss": 0.2338, "lr": 2.9654634072157743e-05, "epoch": 9.927234927234927, "percentage": 49.64, "elapsed_time": "0:55:24", "remaining_time": "0:56:13", "throughput": 1034.69, "total_tokens": 3440232} {"current_steps": 38205, "total_steps": 76960, "loss": 0.2246, "lr": 2.964906348884206e-05, "epoch": 9.928534303534304, "percentage": 49.64, "elapsed_time": "0:55:25", "remaining_time": "0:56:13", "throughput": 1034.7, "total_tokens": 3440696} {"current_steps": 38210, "total_steps": 76960, "loss": 0.2716, "lr": 2.964349266642058e-05, "epoch": 9.92983367983368, "percentage": 49.65, "elapsed_time": "0:55:25", "remaining_time": "0:56:12", "throughput": 1034.7, "total_tokens": 3441128} {"current_steps": 38215, "total_steps": 76960, "loss": 0.2615, "lr": 2.963792160517983e-05, "epoch": 9.931133056133056, "percentage": 49.66, "elapsed_time": "0:55:26", "remaining_time": "0:56:12", "throughput": 1034.7, "total_tokens": 3441560} {"current_steps": 38220, "total_steps": 76960, "loss": 0.3005, "lr": 2.9632350305406326e-05, "epoch": 9.932432432432432, "percentage": 49.66, "elapsed_time": "0:55:26", "remaining_time": "0:56:11", "throughput": 1034.7, "total_tokens": 3441992} {"current_steps": 38225, "total_steps": 76960, "loss": 0.2116, "lr": 2.9626778767386604e-05, "epoch": 9.933731808731808, "percentage": 49.67, "elapsed_time": "0:55:26", "remaining_time": "0:56:11", "throughput": 1034.7, "total_tokens": 3442424} {"current_steps": 38230, "total_steps": 76960, "loss": 0.2601, "lr": 2.9621206991407223e-05, "epoch": 9.935031185031185, "percentage": 49.68, "elapsed_time": "0:55:27", "remaining_time": "0:56:10", "throughput": 1034.71, "total_tokens": 3442888} {"current_steps": 38235, "total_steps": 76960, "loss": 0.2337, "lr": 2.9615634977754737e-05, "epoch": 9.93633056133056, "percentage": 49.68, "elapsed_time": "0:55:27", "remaining_time": "0:56:10", "throughput": 1034.72, "total_tokens": 3443336} {"current_steps": 38240, "total_steps": 76960, "loss": 0.2236, "lr": 2.961006272671572e-05, "epoch": 9.937629937629938, "percentage": 49.69, "elapsed_time": "0:55:28", "remaining_time": "0:56:10", "throughput": 1034.73, "total_tokens": 3443800} {"current_steps": 38245, "total_steps": 76960, "loss": 0.2574, "lr": 2.9604490238576754e-05, "epoch": 9.938929313929314, "percentage": 49.69, "elapsed_time": "0:55:28", "remaining_time": "0:56:09", "throughput": 1034.73, "total_tokens": 3444248} {"current_steps": 38250, "total_steps": 76960, "loss": 0.3165, "lr": 2.9598917513624447e-05, "epoch": 9.94022869022869, "percentage": 49.7, "elapsed_time": "0:55:29", "remaining_time": "0:56:09", "throughput": 1034.74, "total_tokens": 3444712} {"current_steps": 38255, "total_steps": 76960, "loss": 0.1821, "lr": 2.9593344552145407e-05, "epoch": 9.941528066528067, "percentage": 49.71, "elapsed_time": "0:55:29", "remaining_time": "0:56:08", "throughput": 1034.74, "total_tokens": 3445144} {"current_steps": 38260, "total_steps": 76960, "loss": 0.2182, "lr": 2.958777135442625e-05, "epoch": 9.942827442827443, "percentage": 49.71, "elapsed_time": "0:55:29", "remaining_time": "0:56:08", "throughput": 1034.75, "total_tokens": 3445592} {"current_steps": 38265, "total_steps": 76960, "loss": 0.2423, "lr": 2.9582197920753628e-05, "epoch": 9.944126819126819, "percentage": 49.72, "elapsed_time": "0:55:30", "remaining_time": "0:56:07", "throughput": 1034.75, "total_tokens": 3446024} {"current_steps": 38270, "total_steps": 76960, "loss": 0.2653, "lr": 2.957662425141417e-05, "epoch": 9.945426195426196, "percentage": 49.73, "elapsed_time": "0:55:30", "remaining_time": "0:56:07", "throughput": 1034.75, "total_tokens": 3446472} {"current_steps": 38275, "total_steps": 76960, "loss": 0.1284, "lr": 2.9571050346694545e-05, "epoch": 9.946725571725572, "percentage": 49.73, "elapsed_time": "0:55:31", "remaining_time": "0:56:06", "throughput": 1034.76, "total_tokens": 3446936} {"current_steps": 38280, "total_steps": 76960, "loss": 0.3078, "lr": 2.9565476206881415e-05, "epoch": 9.948024948024948, "percentage": 49.74, "elapsed_time": "0:55:31", "remaining_time": "0:56:06", "throughput": 1034.76, "total_tokens": 3447352} {"current_steps": 38285, "total_steps": 76960, "loss": 0.3958, "lr": 2.9559901832261473e-05, "epoch": 9.949324324324325, "percentage": 49.75, "elapsed_time": "0:55:31", "remaining_time": "0:56:05", "throughput": 1034.75, "total_tokens": 3447768} {"current_steps": 38290, "total_steps": 76960, "loss": 0.4009, "lr": 2.9554327223121414e-05, "epoch": 9.950623700623701, "percentage": 49.75, "elapsed_time": "0:55:32", "remaining_time": "0:56:05", "throughput": 1034.76, "total_tokens": 3448216} {"current_steps": 38295, "total_steps": 76960, "loss": 0.2293, "lr": 2.9548752379747936e-05, "epoch": 9.951923076923077, "percentage": 49.76, "elapsed_time": "0:55:32", "remaining_time": "0:56:05", "throughput": 1034.77, "total_tokens": 3448680} {"current_steps": 38300, "total_steps": 76960, "loss": 0.2291, "lr": 2.954317730242777e-05, "epoch": 9.953222453222454, "percentage": 49.77, "elapsed_time": "0:55:33", "remaining_time": "0:56:04", "throughput": 1034.78, "total_tokens": 3449144} {"current_steps": 38305, "total_steps": 76960, "loss": 0.2674, "lr": 2.953760199144764e-05, "epoch": 9.954521829521829, "percentage": 49.77, "elapsed_time": "0:55:33", "remaining_time": "0:56:04", "throughput": 1034.78, "total_tokens": 3449592} {"current_steps": 38310, "total_steps": 76960, "loss": 0.3856, "lr": 2.9532026447094292e-05, "epoch": 9.955821205821206, "percentage": 49.78, "elapsed_time": "0:55:34", "remaining_time": "0:56:03", "throughput": 1034.78, "total_tokens": 3450008} {"current_steps": 38315, "total_steps": 76960, "loss": 0.2377, "lr": 2.9526450669654476e-05, "epoch": 9.957120582120583, "percentage": 49.79, "elapsed_time": "0:55:34", "remaining_time": "0:56:03", "throughput": 1034.79, "total_tokens": 3450456} {"current_steps": 38320, "total_steps": 76960, "loss": 0.2384, "lr": 2.9520874659414973e-05, "epoch": 9.958419958419958, "percentage": 49.79, "elapsed_time": "0:55:34", "remaining_time": "0:56:02", "throughput": 1034.8, "total_tokens": 3450936} {"current_steps": 38325, "total_steps": 76960, "loss": 0.2532, "lr": 2.951529841666255e-05, "epoch": 9.959719334719335, "percentage": 49.8, "elapsed_time": "0:55:35", "remaining_time": "0:56:02", "throughput": 1034.81, "total_tokens": 3451400} {"current_steps": 38330, "total_steps": 76960, "loss": 0.2306, "lr": 2.9509721941684004e-05, "epoch": 9.961018711018712, "percentage": 49.81, "elapsed_time": "0:55:35", "remaining_time": "0:56:01", "throughput": 1034.81, "total_tokens": 3451816} {"current_steps": 38335, "total_steps": 76960, "loss": 0.1648, "lr": 2.9504145234766133e-05, "epoch": 9.962318087318087, "percentage": 49.81, "elapsed_time": "0:55:36", "remaining_time": "0:56:01", "throughput": 1034.8, "total_tokens": 3452232} {"current_steps": 38340, "total_steps": 76960, "loss": 0.2252, "lr": 2.9498568296195768e-05, "epoch": 9.963617463617464, "percentage": 49.82, "elapsed_time": "0:55:36", "remaining_time": "0:56:00", "throughput": 1034.81, "total_tokens": 3452696} {"current_steps": 38345, "total_steps": 76960, "loss": 0.1926, "lr": 2.9492991126259716e-05, "epoch": 9.96491683991684, "percentage": 49.82, "elapsed_time": "0:55:36", "remaining_time": "0:56:00", "throughput": 1034.82, "total_tokens": 3453160} {"current_steps": 38350, "total_steps": 76960, "loss": 0.2011, "lr": 2.948741372524483e-05, "epoch": 9.966216216216216, "percentage": 49.83, "elapsed_time": "0:55:37", "remaining_time": "0:55:59", "throughput": 1034.83, "total_tokens": 3453624} {"current_steps": 38355, "total_steps": 76960, "loss": 0.2649, "lr": 2.9481836093437954e-05, "epoch": 9.967515592515593, "percentage": 49.84, "elapsed_time": "0:55:37", "remaining_time": "0:55:59", "throughput": 1034.84, "total_tokens": 3454072} {"current_steps": 38360, "total_steps": 76960, "loss": 0.2576, "lr": 2.947625823112596e-05, "epoch": 9.96881496881497, "percentage": 49.84, "elapsed_time": "0:55:38", "remaining_time": "0:55:59", "throughput": 1034.84, "total_tokens": 3454520} {"current_steps": 38365, "total_steps": 76960, "loss": 0.2109, "lr": 2.947068013859571e-05, "epoch": 9.970114345114345, "percentage": 49.85, "elapsed_time": "0:55:38", "remaining_time": "0:55:58", "throughput": 1034.85, "total_tokens": 3454968} {"current_steps": 38370, "total_steps": 76960, "loss": 0.3539, "lr": 2.9465101816134093e-05, "epoch": 9.971413721413722, "percentage": 49.86, "elapsed_time": "0:55:39", "remaining_time": "0:55:58", "throughput": 1034.86, "total_tokens": 3455448} {"current_steps": 38375, "total_steps": 76960, "loss": 0.1477, "lr": 2.9459523264028018e-05, "epoch": 9.972713097713097, "percentage": 49.86, "elapsed_time": "0:55:39", "remaining_time": "0:55:57", "throughput": 1034.87, "total_tokens": 3455912} {"current_steps": 38380, "total_steps": 76960, "loss": 0.2734, "lr": 2.9453944482564387e-05, "epoch": 9.974012474012474, "percentage": 49.87, "elapsed_time": "0:55:39", "remaining_time": "0:55:57", "throughput": 1034.88, "total_tokens": 3456344} {"current_steps": 38385, "total_steps": 76960, "loss": 0.3045, "lr": 2.9448365472030115e-05, "epoch": 9.97531185031185, "percentage": 49.88, "elapsed_time": "0:55:40", "remaining_time": "0:55:56", "throughput": 1034.88, "total_tokens": 3456792} {"current_steps": 38390, "total_steps": 76960, "loss": 0.1828, "lr": 2.9442786232712155e-05, "epoch": 9.976611226611226, "percentage": 49.88, "elapsed_time": "0:55:40", "remaining_time": "0:55:56", "throughput": 1034.9, "total_tokens": 3457272} {"current_steps": 38395, "total_steps": 76960, "loss": 0.4493, "lr": 2.943720676489744e-05, "epoch": 9.977910602910603, "percentage": 49.89, "elapsed_time": "0:55:41", "remaining_time": "0:55:55", "throughput": 1034.89, "total_tokens": 3457688} {"current_steps": 38400, "total_steps": 76960, "loss": 0.068, "lr": 2.9431627068872932e-05, "epoch": 9.97920997920998, "percentage": 49.9, "elapsed_time": "0:55:41", "remaining_time": "0:55:55", "throughput": 1034.89, "total_tokens": 3458136} {"current_steps": 38405, "total_steps": 76960, "loss": 0.1763, "lr": 2.942604714492559e-05, "epoch": 9.980509355509355, "percentage": 49.9, "elapsed_time": "0:55:41", "remaining_time": "0:55:55", "throughput": 1034.91, "total_tokens": 3458616} {"current_steps": 38410, "total_steps": 76960, "loss": 0.3073, "lr": 2.942046699334241e-05, "epoch": 9.981808731808732, "percentage": 49.91, "elapsed_time": "0:55:42", "remaining_time": "0:55:54", "throughput": 1034.91, "total_tokens": 3459048} {"current_steps": 38415, "total_steps": 76960, "loss": 0.227, "lr": 2.9414886614410375e-05, "epoch": 9.983108108108109, "percentage": 49.92, "elapsed_time": "0:55:42", "remaining_time": "0:55:54", "throughput": 1034.92, "total_tokens": 3459496} {"current_steps": 38420, "total_steps": 76960, "loss": 0.3067, "lr": 2.940930600841649e-05, "epoch": 9.984407484407484, "percentage": 49.92, "elapsed_time": "0:55:43", "remaining_time": "0:55:53", "throughput": 1034.92, "total_tokens": 3459944} {"current_steps": 38425, "total_steps": 76960, "loss": 0.2731, "lr": 2.940372517564777e-05, "epoch": 9.98570686070686, "percentage": 49.93, "elapsed_time": "0:55:43", "remaining_time": "0:55:53", "throughput": 1034.92, "total_tokens": 3460360} {"current_steps": 38430, "total_steps": 76960, "loss": 0.2099, "lr": 2.9398144116391257e-05, "epoch": 9.987006237006238, "percentage": 49.94, "elapsed_time": "0:55:44", "remaining_time": "0:55:52", "throughput": 1034.93, "total_tokens": 3460824} {"current_steps": 38435, "total_steps": 76960, "loss": 0.2205, "lr": 2.9392562830933968e-05, "epoch": 9.988305613305613, "percentage": 49.94, "elapsed_time": "0:55:44", "remaining_time": "0:55:52", "throughput": 1034.92, "total_tokens": 3461240} {"current_steps": 38440, "total_steps": 76960, "loss": 0.123, "lr": 2.9386981319562962e-05, "epoch": 9.98960498960499, "percentage": 49.95, "elapsed_time": "0:55:44", "remaining_time": "0:55:51", "throughput": 1034.93, "total_tokens": 3461704} {"current_steps": 38445, "total_steps": 76960, "loss": 0.2333, "lr": 2.9381399582565304e-05, "epoch": 9.990904365904367, "percentage": 49.95, "elapsed_time": "0:55:45", "remaining_time": "0:55:51", "throughput": 1034.94, "total_tokens": 3462168} {"current_steps": 38450, "total_steps": 76960, "loss": 0.3525, "lr": 2.9375817620228075e-05, "epoch": 9.992203742203742, "percentage": 49.96, "elapsed_time": "0:55:45", "remaining_time": "0:55:50", "throughput": 1034.95, "total_tokens": 3462616} {"current_steps": 38455, "total_steps": 76960, "loss": 0.1294, "lr": 2.9370235432838343e-05, "epoch": 9.993503118503119, "percentage": 49.97, "elapsed_time": "0:55:46", "remaining_time": "0:55:50", "throughput": 1034.95, "total_tokens": 3463048} {"current_steps": 38460, "total_steps": 76960, "loss": 0.3018, "lr": 2.9364653020683218e-05, "epoch": 9.994802494802494, "percentage": 49.97, "elapsed_time": "0:55:46", "remaining_time": "0:55:50", "throughput": 1034.95, "total_tokens": 3463496} {"current_steps": 38465, "total_steps": 76960, "loss": 0.2559, "lr": 2.935907038404981e-05, "epoch": 9.996101871101871, "percentage": 49.98, "elapsed_time": "0:55:46", "remaining_time": "0:55:49", "throughput": 1034.95, "total_tokens": 3463928} {"current_steps": 38470, "total_steps": 76960, "loss": 0.3323, "lr": 2.9353487523225232e-05, "epoch": 9.997401247401248, "percentage": 49.99, "elapsed_time": "0:55:47", "remaining_time": "0:55:49", "throughput": 1034.98, "total_tokens": 3464440} {"current_steps": 38475, "total_steps": 76960, "loss": 0.3676, "lr": 2.9347904438496622e-05, "epoch": 9.998700623700623, "percentage": 49.99, "elapsed_time": "0:55:47", "remaining_time": "0:55:48", "throughput": 1034.98, "total_tokens": 3464888} {"current_steps": 38480, "total_steps": 76960, "loss": 0.2241, "lr": 2.9342321130151118e-05, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:55:48", "remaining_time": "0:55:48", "throughput": 1034.95, "total_tokens": 3465288} {"current_steps": 38480, "total_steps": 76960, "eval_loss": 0.24384894967079163, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:56:01", "remaining_time": "0:56:01", "throughput": 1030.9, "total_tokens": 3465288} {"current_steps": 38485, "total_steps": 76960, "loss": 0.2165, "lr": 2.9336737598475877e-05, "epoch": 10.001299376299377, "percentage": 50.01, "elapsed_time": "0:56:03", "remaining_time": "0:56:02", "throughput": 1030.42, "total_tokens": 3465720} {"current_steps": 38490, "total_steps": 76960, "loss": 0.1407, "lr": 2.933115384375807e-05, "epoch": 10.002598752598752, "percentage": 50.01, "elapsed_time": "0:56:03", "remaining_time": "0:56:02", "throughput": 1030.42, "total_tokens": 3466184} {"current_steps": 38495, "total_steps": 76960, "loss": 0.21, "lr": 2.9325569866284876e-05, "epoch": 10.003898128898129, "percentage": 50.02, "elapsed_time": "0:56:04", "remaining_time": "0:56:01", "throughput": 1030.41, "total_tokens": 3466584} {"current_steps": 38500, "total_steps": 76960, "loss": 0.2344, "lr": 2.931998566634347e-05, "epoch": 10.005197505197506, "percentage": 50.03, "elapsed_time": "0:56:04", "remaining_time": "0:56:01", "throughput": 1030.42, "total_tokens": 3467048} {"current_steps": 38505, "total_steps": 76960, "loss": 0.1138, "lr": 2.9314401244221064e-05, "epoch": 10.006496881496881, "percentage": 50.03, "elapsed_time": "0:56:05", "remaining_time": "0:56:00", "throughput": 1030.43, "total_tokens": 3467512} {"current_steps": 38510, "total_steps": 76960, "loss": 0.1573, "lr": 2.9308816600204863e-05, "epoch": 10.007796257796258, "percentage": 50.04, "elapsed_time": "0:56:05", "remaining_time": "0:56:00", "throughput": 1030.42, "total_tokens": 3467928} {"current_steps": 38515, "total_steps": 76960, "loss": 0.2319, "lr": 2.9303231734582102e-05, "epoch": 10.009095634095635, "percentage": 50.05, "elapsed_time": "0:56:05", "remaining_time": "0:55:59", "throughput": 1030.42, "total_tokens": 3468376} {"current_steps": 38520, "total_steps": 76960, "loss": 0.1063, "lr": 2.929764664764001e-05, "epoch": 10.01039501039501, "percentage": 50.05, "elapsed_time": "0:56:06", "remaining_time": "0:55:59", "throughput": 1030.43, "total_tokens": 3468856} {"current_steps": 38525, "total_steps": 76960, "loss": 0.2589, "lr": 2.9292061339665833e-05, "epoch": 10.011694386694387, "percentage": 50.06, "elapsed_time": "0:56:06", "remaining_time": "0:55:58", "throughput": 1030.44, "total_tokens": 3469304} {"current_steps": 38530, "total_steps": 76960, "loss": 0.1841, "lr": 2.9286475810946823e-05, "epoch": 10.012993762993762, "percentage": 50.06, "elapsed_time": "0:56:07", "remaining_time": "0:55:58", "throughput": 1030.45, "total_tokens": 3469768} {"current_steps": 38535, "total_steps": 76960, "loss": 0.2239, "lr": 2.928089006177026e-05, "epoch": 10.01429313929314, "percentage": 50.07, "elapsed_time": "0:56:07", "remaining_time": "0:55:58", "throughput": 1030.45, "total_tokens": 3470200} {"current_steps": 38540, "total_steps": 76960, "loss": 0.757, "lr": 2.9275304092423422e-05, "epoch": 10.015592515592516, "percentage": 50.08, "elapsed_time": "0:56:08", "remaining_time": "0:55:57", "throughput": 1030.47, "total_tokens": 3470680} {"current_steps": 38545, "total_steps": 76960, "loss": 0.1647, "lr": 2.92697179031936e-05, "epoch": 10.016891891891891, "percentage": 50.08, "elapsed_time": "0:56:08", "remaining_time": "0:55:57", "throughput": 1030.47, "total_tokens": 3471128} {"current_steps": 38550, "total_steps": 76960, "loss": 0.3117, "lr": 2.9264131494368084e-05, "epoch": 10.018191268191268, "percentage": 50.09, "elapsed_time": "0:56:08", "remaining_time": "0:55:56", "throughput": 1030.49, "total_tokens": 3471608} {"current_steps": 38555, "total_steps": 76960, "loss": 0.2158, "lr": 2.9258544866234207e-05, "epoch": 10.019490644490645, "percentage": 50.1, "elapsed_time": "0:56:09", "remaining_time": "0:55:56", "throughput": 1030.49, "total_tokens": 3472040} {"current_steps": 38560, "total_steps": 76960, "loss": 0.2544, "lr": 2.9252958019079296e-05, "epoch": 10.02079002079002, "percentage": 50.1, "elapsed_time": "0:56:09", "remaining_time": "0:55:55", "throughput": 1030.5, "total_tokens": 3472520} {"current_steps": 38565, "total_steps": 76960, "loss": 0.1834, "lr": 2.924737095319066e-05, "epoch": 10.022089397089397, "percentage": 50.11, "elapsed_time": "0:56:10", "remaining_time": "0:55:55", "throughput": 1030.52, "total_tokens": 3473000} {"current_steps": 38570, "total_steps": 76960, "loss": 0.1977, "lr": 2.9241783668855683e-05, "epoch": 10.023388773388774, "percentage": 50.12, "elapsed_time": "0:56:10", "remaining_time": "0:55:54", "throughput": 1030.53, "total_tokens": 3473464} {"current_steps": 38575, "total_steps": 76960, "loss": 0.2948, "lr": 2.9236196166361694e-05, "epoch": 10.02468814968815, "percentage": 50.12, "elapsed_time": "0:56:10", "remaining_time": "0:55:54", "throughput": 1030.52, "total_tokens": 3473880} {"current_steps": 38580, "total_steps": 76960, "loss": 0.2866, "lr": 2.9230608445996087e-05, "epoch": 10.025987525987526, "percentage": 50.13, "elapsed_time": "0:56:11", "remaining_time": "0:55:53", "throughput": 1030.53, "total_tokens": 3474328} {"current_steps": 38585, "total_steps": 76960, "loss": 0.1842, "lr": 2.9225020508046232e-05, "epoch": 10.027286902286903, "percentage": 50.14, "elapsed_time": "0:56:11", "remaining_time": "0:55:53", "throughput": 1030.53, "total_tokens": 3474776} {"current_steps": 38590, "total_steps": 76960, "loss": 0.3096, "lr": 2.921943235279952e-05, "epoch": 10.028586278586278, "percentage": 50.14, "elapsed_time": "0:56:12", "remaining_time": "0:55:53", "throughput": 1030.54, "total_tokens": 3475240} {"current_steps": 38595, "total_steps": 76960, "loss": 0.267, "lr": 2.9213843980543364e-05, "epoch": 10.029885654885655, "percentage": 50.15, "elapsed_time": "0:56:12", "remaining_time": "0:55:52", "throughput": 1030.55, "total_tokens": 3475688} {"current_steps": 38600, "total_steps": 76960, "loss": 0.1712, "lr": 2.920825539156517e-05, "epoch": 10.03118503118503, "percentage": 50.16, "elapsed_time": "0:56:13", "remaining_time": "0:55:52", "throughput": 1030.56, "total_tokens": 3476168} {"current_steps": 38605, "total_steps": 76960, "loss": 0.6621, "lr": 2.920266658615237e-05, "epoch": 10.032484407484407, "percentage": 50.16, "elapsed_time": "0:56:13", "remaining_time": "0:55:51", "throughput": 1030.58, "total_tokens": 3476648} {"current_steps": 38610, "total_steps": 76960, "loss": 0.1687, "lr": 2.9197077564592402e-05, "epoch": 10.033783783783784, "percentage": 50.17, "elapsed_time": "0:56:13", "remaining_time": "0:55:51", "throughput": 1030.59, "total_tokens": 3477112} {"current_steps": 38615, "total_steps": 76960, "loss": 0.394, "lr": 2.9191488327172717e-05, "epoch": 10.03508316008316, "percentage": 50.18, "elapsed_time": "0:56:14", "remaining_time": "0:55:50", "throughput": 1030.59, "total_tokens": 3477544} {"current_steps": 38620, "total_steps": 76960, "loss": 0.2154, "lr": 2.9185898874180762e-05, "epoch": 10.036382536382536, "percentage": 50.18, "elapsed_time": "0:56:14", "remaining_time": "0:55:50", "throughput": 1030.61, "total_tokens": 3478040} {"current_steps": 38625, "total_steps": 76960, "loss": 0.0735, "lr": 2.9180309205904027e-05, "epoch": 10.037681912681913, "percentage": 50.19, "elapsed_time": "0:56:15", "remaining_time": "0:55:49", "throughput": 1030.61, "total_tokens": 3478488} {"current_steps": 38630, "total_steps": 76960, "loss": 0.0539, "lr": 2.9174719322629983e-05, "epoch": 10.038981288981288, "percentage": 50.19, "elapsed_time": "0:56:15", "remaining_time": "0:55:49", "throughput": 1030.61, "total_tokens": 3478936} {"current_steps": 38635, "total_steps": 76960, "loss": 0.2715, "lr": 2.916912922464612e-05, "epoch": 10.040280665280665, "percentage": 50.2, "elapsed_time": "0:56:16", "remaining_time": "0:55:48", "throughput": 1030.62, "total_tokens": 3479384} {"current_steps": 38640, "total_steps": 76960, "loss": 0.3067, "lr": 2.9163538912239946e-05, "epoch": 10.041580041580042, "percentage": 50.21, "elapsed_time": "0:56:16", "remaining_time": "0:55:48", "throughput": 1030.63, "total_tokens": 3479848} {"current_steps": 38645, "total_steps": 76960, "loss": 0.0168, "lr": 2.915794838569898e-05, "epoch": 10.042879417879417, "percentage": 50.21, "elapsed_time": "0:56:16", "remaining_time": "0:55:48", "throughput": 1030.63, "total_tokens": 3480280} {"current_steps": 38650, "total_steps": 76960, "loss": 0.3123, "lr": 2.9152357645310748e-05, "epoch": 10.044178794178794, "percentage": 50.22, "elapsed_time": "0:56:17", "remaining_time": "0:55:47", "throughput": 1030.64, "total_tokens": 3480728} {"current_steps": 38655, "total_steps": 76960, "loss": 0.3997, "lr": 2.914676669136277e-05, "epoch": 10.045478170478171, "percentage": 50.23, "elapsed_time": "0:56:17", "remaining_time": "0:55:47", "throughput": 1030.64, "total_tokens": 3481176} {"current_steps": 38660, "total_steps": 76960, "loss": 0.4297, "lr": 2.9141175524142615e-05, "epoch": 10.046777546777546, "percentage": 50.23, "elapsed_time": "0:56:18", "remaining_time": "0:55:46", "throughput": 1030.65, "total_tokens": 3481640} {"current_steps": 38665, "total_steps": 76960, "loss": 0.5424, "lr": 2.913558414393784e-05, "epoch": 10.048076923076923, "percentage": 50.24, "elapsed_time": "0:56:18", "remaining_time": "0:55:46", "throughput": 1030.66, "total_tokens": 3482088} {"current_steps": 38670, "total_steps": 76960, "loss": 0.5064, "lr": 2.9129992551036005e-05, "epoch": 10.049376299376299, "percentage": 50.25, "elapsed_time": "0:56:18", "remaining_time": "0:55:45", "throughput": 1030.66, "total_tokens": 3482536} {"current_steps": 38675, "total_steps": 76960, "loss": 0.1421, "lr": 2.9124400745724695e-05, "epoch": 10.050675675675675, "percentage": 50.25, "elapsed_time": "0:56:19", "remaining_time": "0:55:45", "throughput": 1030.68, "total_tokens": 3483000} {"current_steps": 38680, "total_steps": 76960, "loss": 0.0863, "lr": 2.9118808728291503e-05, "epoch": 10.051975051975052, "percentage": 50.26, "elapsed_time": "0:56:19", "remaining_time": "0:55:44", "throughput": 1030.68, "total_tokens": 3483432} {"current_steps": 38685, "total_steps": 76960, "loss": 0.3174, "lr": 2.9113216499024038e-05, "epoch": 10.053274428274428, "percentage": 50.27, "elapsed_time": "0:56:20", "remaining_time": "0:55:44", "throughput": 1030.69, "total_tokens": 3483896} {"current_steps": 38690, "total_steps": 76960, "loss": 0.2795, "lr": 2.9107624058209905e-05, "epoch": 10.054573804573804, "percentage": 50.27, "elapsed_time": "0:56:20", "remaining_time": "0:55:43", "throughput": 1030.68, "total_tokens": 3484312} {"current_steps": 38695, "total_steps": 76960, "loss": 0.2371, "lr": 2.9102031406136725e-05, "epoch": 10.055873180873181, "percentage": 50.28, "elapsed_time": "0:56:20", "remaining_time": "0:55:43", "throughput": 1030.69, "total_tokens": 3484760} {"current_steps": 38700, "total_steps": 76960, "loss": 0.2246, "lr": 2.9096438543092147e-05, "epoch": 10.057172557172557, "percentage": 50.29, "elapsed_time": "0:56:21", "remaining_time": "0:55:42", "throughput": 1030.7, "total_tokens": 3485224} {"current_steps": 38705, "total_steps": 76960, "loss": 0.2368, "lr": 2.9090845469363805e-05, "epoch": 10.058471933471933, "percentage": 50.29, "elapsed_time": "0:56:21", "remaining_time": "0:55:42", "throughput": 1030.71, "total_tokens": 3485688} {"current_steps": 38710, "total_steps": 76960, "loss": 0.3788, "lr": 2.908525218523936e-05, "epoch": 10.05977130977131, "percentage": 50.3, "elapsed_time": "0:56:22", "remaining_time": "0:55:42", "throughput": 1030.71, "total_tokens": 3486120} {"current_steps": 38715, "total_steps": 76960, "loss": 0.2267, "lr": 2.9079658691006484e-05, "epoch": 10.061070686070686, "percentage": 50.31, "elapsed_time": "0:56:22", "remaining_time": "0:55:41", "throughput": 1030.71, "total_tokens": 3486552} {"current_steps": 38720, "total_steps": 76960, "loss": 0.1398, "lr": 2.9074064986952848e-05, "epoch": 10.062370062370062, "percentage": 50.31, "elapsed_time": "0:56:23", "remaining_time": "0:55:41", "throughput": 1030.72, "total_tokens": 3486984} {"current_steps": 38725, "total_steps": 76960, "loss": 0.428, "lr": 2.9068471073366154e-05, "epoch": 10.06366943866944, "percentage": 50.32, "elapsed_time": "0:56:23", "remaining_time": "0:55:40", "throughput": 1030.72, "total_tokens": 3487432} {"current_steps": 38730, "total_steps": 76960, "loss": 0.2657, "lr": 2.9062876950534085e-05, "epoch": 10.064968814968815, "percentage": 50.32, "elapsed_time": "0:56:23", "remaining_time": "0:55:40", "throughput": 1030.72, "total_tokens": 3487864} {"current_steps": 38735, "total_steps": 76960, "loss": 0.1494, "lr": 2.9057282618744362e-05, "epoch": 10.066268191268192, "percentage": 50.33, "elapsed_time": "0:56:24", "remaining_time": "0:55:39", "throughput": 1030.72, "total_tokens": 3488280} {"current_steps": 38740, "total_steps": 76960, "loss": 0.2277, "lr": 2.9051688078284715e-05, "epoch": 10.067567567567568, "percentage": 50.34, "elapsed_time": "0:56:24", "remaining_time": "0:55:39", "throughput": 1030.74, "total_tokens": 3488776} {"current_steps": 38745, "total_steps": 76960, "loss": 0.2531, "lr": 2.9046093329442857e-05, "epoch": 10.068866943866944, "percentage": 50.34, "elapsed_time": "0:56:25", "remaining_time": "0:55:38", "throughput": 1030.75, "total_tokens": 3489256} {"current_steps": 38750, "total_steps": 76960, "loss": 0.2793, "lr": 2.9040498372506552e-05, "epoch": 10.07016632016632, "percentage": 50.35, "elapsed_time": "0:56:25", "remaining_time": "0:55:38", "throughput": 1030.75, "total_tokens": 3489688} {"current_steps": 38755, "total_steps": 76960, "loss": 0.2266, "lr": 2.903490320776355e-05, "epoch": 10.071465696465696, "percentage": 50.36, "elapsed_time": "0:56:25", "remaining_time": "0:55:37", "throughput": 1030.75, "total_tokens": 3490120} {"current_steps": 38760, "total_steps": 76960, "loss": 0.4326, "lr": 2.9029307835501596e-05, "epoch": 10.072765072765073, "percentage": 50.36, "elapsed_time": "0:56:26", "remaining_time": "0:55:37", "throughput": 1030.77, "total_tokens": 3490600} {"current_steps": 38765, "total_steps": 76960, "loss": 0.1091, "lr": 2.9023712256008486e-05, "epoch": 10.07406444906445, "percentage": 50.37, "elapsed_time": "0:56:26", "remaining_time": "0:55:37", "throughput": 1030.77, "total_tokens": 3491016} {"current_steps": 38770, "total_steps": 76960, "loss": 0.2965, "lr": 2.9018116469572e-05, "epoch": 10.075363825363825, "percentage": 50.38, "elapsed_time": "0:56:27", "remaining_time": "0:55:36", "throughput": 1030.77, "total_tokens": 3491448} {"current_steps": 38775, "total_steps": 76960, "loss": 0.2266, "lr": 2.901252047647993e-05, "epoch": 10.076663201663202, "percentage": 50.38, "elapsed_time": "0:56:27", "remaining_time": "0:55:36", "throughput": 1030.77, "total_tokens": 3491880} {"current_steps": 38780, "total_steps": 76960, "loss": 0.1183, "lr": 2.9006924277020086e-05, "epoch": 10.077962577962579, "percentage": 50.39, "elapsed_time": "0:56:28", "remaining_time": "0:55:35", "throughput": 1030.76, "total_tokens": 3492296} {"current_steps": 38785, "total_steps": 76960, "loss": 0.5898, "lr": 2.9001327871480294e-05, "epoch": 10.079261954261954, "percentage": 50.4, "elapsed_time": "0:56:28", "remaining_time": "0:55:35", "throughput": 1030.76, "total_tokens": 3492728} {"current_steps": 38790, "total_steps": 76960, "loss": 0.2492, "lr": 2.8995731260148374e-05, "epoch": 10.08056133056133, "percentage": 50.4, "elapsed_time": "0:56:28", "remaining_time": "0:55:34", "throughput": 1030.76, "total_tokens": 3493192} {"current_steps": 38795, "total_steps": 76960, "loss": 0.1389, "lr": 2.8990134443312167e-05, "epoch": 10.081860706860708, "percentage": 50.41, "elapsed_time": "0:56:29", "remaining_time": "0:55:34", "throughput": 1030.76, "total_tokens": 3493624} {"current_steps": 38800, "total_steps": 76960, "loss": 0.3654, "lr": 2.898453742125951e-05, "epoch": 10.083160083160083, "percentage": 50.42, "elapsed_time": "0:56:29", "remaining_time": "0:55:33", "throughput": 1030.77, "total_tokens": 3494072} {"current_steps": 38805, "total_steps": 76960, "loss": 0.3031, "lr": 2.8978940194278293e-05, "epoch": 10.08445945945946, "percentage": 50.42, "elapsed_time": "0:56:30", "remaining_time": "0:55:33", "throughput": 1030.77, "total_tokens": 3494504} {"current_steps": 38810, "total_steps": 76960, "loss": 0.1416, "lr": 2.8973342762656357e-05, "epoch": 10.085758835758837, "percentage": 50.43, "elapsed_time": "0:56:30", "remaining_time": "0:55:32", "throughput": 1030.76, "total_tokens": 3494920} {"current_steps": 38815, "total_steps": 76960, "loss": 0.3022, "lr": 2.8967745126681604e-05, "epoch": 10.087058212058212, "percentage": 50.44, "elapsed_time": "0:56:31", "remaining_time": "0:55:32", "throughput": 1030.77, "total_tokens": 3495352} {"current_steps": 38820, "total_steps": 76960, "loss": 0.1893, "lr": 2.8962147286641916e-05, "epoch": 10.088357588357589, "percentage": 50.44, "elapsed_time": "0:56:31", "remaining_time": "0:55:32", "throughput": 1030.78, "total_tokens": 3495816} {"current_steps": 38825, "total_steps": 76960, "loss": 0.1924, "lr": 2.8956549242825197e-05, "epoch": 10.089656964656964, "percentage": 50.45, "elapsed_time": "0:56:31", "remaining_time": "0:55:31", "throughput": 1030.77, "total_tokens": 3496216} {"current_steps": 38830, "total_steps": 76960, "loss": 0.2172, "lr": 2.895095099551936e-05, "epoch": 10.09095634095634, "percentage": 50.45, "elapsed_time": "0:56:32", "remaining_time": "0:55:31", "throughput": 1030.77, "total_tokens": 3496648} {"current_steps": 38835, "total_steps": 76960, "loss": 0.3009, "lr": 2.8945352545012316e-05, "epoch": 10.092255717255718, "percentage": 50.46, "elapsed_time": "0:56:32", "remaining_time": "0:55:30", "throughput": 1030.78, "total_tokens": 3497112} {"current_steps": 38840, "total_steps": 76960, "loss": 0.1539, "lr": 2.8939753891592025e-05, "epoch": 10.093555093555093, "percentage": 50.47, "elapsed_time": "0:56:33", "remaining_time": "0:55:30", "throughput": 1030.79, "total_tokens": 3497592} {"current_steps": 38845, "total_steps": 76960, "loss": 0.2389, "lr": 2.893415503554641e-05, "epoch": 10.09485446985447, "percentage": 50.47, "elapsed_time": "0:56:33", "remaining_time": "0:55:29", "throughput": 1030.79, "total_tokens": 3498024} {"current_steps": 38850, "total_steps": 76960, "loss": 0.0362, "lr": 2.8928555977163435e-05, "epoch": 10.096153846153847, "percentage": 50.48, "elapsed_time": "0:56:33", "remaining_time": "0:55:29", "throughput": 1030.8, "total_tokens": 3498472} {"current_steps": 38855, "total_steps": 76960, "loss": 0.2588, "lr": 2.8922956716731054e-05, "epoch": 10.097453222453222, "percentage": 50.49, "elapsed_time": "0:56:34", "remaining_time": "0:55:28", "throughput": 1030.8, "total_tokens": 3498920} {"current_steps": 38860, "total_steps": 76960, "loss": 0.674, "lr": 2.8917357254537257e-05, "epoch": 10.098752598752599, "percentage": 50.49, "elapsed_time": "0:56:34", "remaining_time": "0:55:28", "throughput": 1030.82, "total_tokens": 3499400} {"current_steps": 38865, "total_steps": 76960, "loss": 0.7279, "lr": 2.8911757590870027e-05, "epoch": 10.100051975051976, "percentage": 50.5, "elapsed_time": "0:56:35", "remaining_time": "0:55:27", "throughput": 1030.83, "total_tokens": 3499880} {"current_steps": 38870, "total_steps": 76960, "loss": 0.256, "lr": 2.8906157726017347e-05, "epoch": 10.10135135135135, "percentage": 50.51, "elapsed_time": "0:56:35", "remaining_time": "0:55:27", "throughput": 1030.84, "total_tokens": 3500328} {"current_steps": 38875, "total_steps": 76960, "loss": 0.419, "lr": 2.8900557660267236e-05, "epoch": 10.102650727650728, "percentage": 50.51, "elapsed_time": "0:56:36", "remaining_time": "0:55:27", "throughput": 1030.85, "total_tokens": 3500776} {"current_steps": 38880, "total_steps": 76960, "loss": 0.2422, "lr": 2.8894957393907708e-05, "epoch": 10.103950103950105, "percentage": 50.52, "elapsed_time": "0:56:36", "remaining_time": "0:55:26", "throughput": 1030.86, "total_tokens": 3501240} {"current_steps": 38885, "total_steps": 76960, "loss": 0.2793, "lr": 2.888935692722679e-05, "epoch": 10.10524948024948, "percentage": 50.53, "elapsed_time": "0:56:36", "remaining_time": "0:55:26", "throughput": 1030.87, "total_tokens": 3501720} {"current_steps": 38890, "total_steps": 76960, "loss": 0.2503, "lr": 2.8883756260512517e-05, "epoch": 10.106548856548857, "percentage": 50.53, "elapsed_time": "0:56:37", "remaining_time": "0:55:25", "throughput": 1030.87, "total_tokens": 3502152} {"current_steps": 38895, "total_steps": 76960, "loss": 0.3922, "lr": 2.8878155394052942e-05, "epoch": 10.107848232848232, "percentage": 50.54, "elapsed_time": "0:56:37", "remaining_time": "0:55:25", "throughput": 1030.88, "total_tokens": 3502616} {"current_steps": 38900, "total_steps": 76960, "loss": 0.1469, "lr": 2.887255432813612e-05, "epoch": 10.109147609147609, "percentage": 50.55, "elapsed_time": "0:56:38", "remaining_time": "0:55:24", "throughput": 1030.88, "total_tokens": 3503048} {"current_steps": 38905, "total_steps": 76960, "loss": 0.2343, "lr": 2.8866953063050105e-05, "epoch": 10.110446985446986, "percentage": 50.55, "elapsed_time": "0:56:38", "remaining_time": "0:55:24", "throughput": 1030.89, "total_tokens": 3503496} {"current_steps": 38910, "total_steps": 76960, "loss": 0.2713, "lr": 2.8861351599083002e-05, "epoch": 10.111746361746361, "percentage": 50.56, "elapsed_time": "0:56:38", "remaining_time": "0:55:23", "throughput": 1030.88, "total_tokens": 3503912} {"current_steps": 38915, "total_steps": 76960, "loss": 0.2763, "lr": 2.8855749936522886e-05, "epoch": 10.113045738045738, "percentage": 50.57, "elapsed_time": "0:56:39", "remaining_time": "0:55:23", "throughput": 1030.88, "total_tokens": 3504344} {"current_steps": 38920, "total_steps": 76960, "loss": 0.1937, "lr": 2.885014807565785e-05, "epoch": 10.114345114345115, "percentage": 50.57, "elapsed_time": "0:56:39", "remaining_time": "0:55:22", "throughput": 1030.89, "total_tokens": 3504792} {"current_steps": 38925, "total_steps": 76960, "loss": 0.2236, "lr": 2.8844546016776013e-05, "epoch": 10.11564449064449, "percentage": 50.58, "elapsed_time": "0:56:40", "remaining_time": "0:55:22", "throughput": 1030.89, "total_tokens": 3505208} {"current_steps": 38930, "total_steps": 76960, "loss": 0.2786, "lr": 2.8838943760165487e-05, "epoch": 10.116943866943867, "percentage": 50.58, "elapsed_time": "0:56:40", "remaining_time": "0:55:21", "throughput": 1030.88, "total_tokens": 3505624} {"current_steps": 38935, "total_steps": 76960, "loss": 0.2886, "lr": 2.8833341306114413e-05, "epoch": 10.118243243243244, "percentage": 50.59, "elapsed_time": "0:56:41", "remaining_time": "0:55:21", "throughput": 1030.89, "total_tokens": 3506072} {"current_steps": 38940, "total_steps": 76960, "loss": 0.1938, "lr": 2.882773865491092e-05, "epoch": 10.119542619542619, "percentage": 50.6, "elapsed_time": "0:56:41", "remaining_time": "0:55:21", "throughput": 1030.89, "total_tokens": 3506520} {"current_steps": 38945, "total_steps": 76960, "loss": 0.1562, "lr": 2.8822135806843154e-05, "epoch": 10.120841995841996, "percentage": 50.6, "elapsed_time": "0:56:41", "remaining_time": "0:55:20", "throughput": 1030.91, "total_tokens": 3507016} {"current_steps": 38950, "total_steps": 76960, "loss": 0.1806, "lr": 2.8816532762199293e-05, "epoch": 10.122141372141373, "percentage": 50.61, "elapsed_time": "0:56:42", "remaining_time": "0:55:20", "throughput": 1030.91, "total_tokens": 3507448} {"current_steps": 38955, "total_steps": 76960, "loss": 0.1629, "lr": 2.881092952126749e-05, "epoch": 10.123440748440748, "percentage": 50.62, "elapsed_time": "0:56:42", "remaining_time": "0:55:19", "throughput": 1030.92, "total_tokens": 3507896} {"current_steps": 38960, "total_steps": 76960, "loss": 0.3098, "lr": 2.880532608433592e-05, "epoch": 10.124740124740125, "percentage": 50.62, "elapsed_time": "0:56:43", "remaining_time": "0:55:19", "throughput": 1030.93, "total_tokens": 3508360} {"current_steps": 38965, "total_steps": 76960, "loss": 0.1569, "lr": 2.8799722451692796e-05, "epoch": 10.126039501039502, "percentage": 50.63, "elapsed_time": "0:56:43", "remaining_time": "0:55:18", "throughput": 1030.92, "total_tokens": 3508760} {"current_steps": 38970, "total_steps": 76960, "loss": 0.2004, "lr": 2.8794118623626305e-05, "epoch": 10.127338877338877, "percentage": 50.64, "elapsed_time": "0:56:43", "remaining_time": "0:55:18", "throughput": 1030.92, "total_tokens": 3509192} {"current_steps": 38975, "total_steps": 76960, "loss": 0.3336, "lr": 2.8788514600424653e-05, "epoch": 10.128638253638254, "percentage": 50.64, "elapsed_time": "0:56:44", "remaining_time": "0:55:17", "throughput": 1030.93, "total_tokens": 3509640} {"current_steps": 38980, "total_steps": 76960, "loss": 0.2322, "lr": 2.878291038237606e-05, "epoch": 10.12993762993763, "percentage": 50.65, "elapsed_time": "0:56:44", "remaining_time": "0:55:17", "throughput": 1030.94, "total_tokens": 3510104} {"current_steps": 38985, "total_steps": 76960, "loss": 0.3139, "lr": 2.877730596976877e-05, "epoch": 10.131237006237006, "percentage": 50.66, "elapsed_time": "0:56:45", "remaining_time": "0:55:16", "throughput": 1030.94, "total_tokens": 3510536} {"current_steps": 38990, "total_steps": 76960, "loss": 0.2753, "lr": 2.8771701362891012e-05, "epoch": 10.132536382536383, "percentage": 50.66, "elapsed_time": "0:56:45", "remaining_time": "0:55:16", "throughput": 1030.95, "total_tokens": 3511000} {"current_steps": 38995, "total_steps": 76960, "loss": 0.1751, "lr": 2.8766096562031038e-05, "epoch": 10.133835758835758, "percentage": 50.67, "elapsed_time": "0:56:46", "remaining_time": "0:55:16", "throughput": 1030.96, "total_tokens": 3511480} {"current_steps": 39000, "total_steps": 76960, "loss": 0.2057, "lr": 2.876049156747711e-05, "epoch": 10.135135135135135, "percentage": 50.68, "elapsed_time": "0:56:46", "remaining_time": "0:55:15", "throughput": 1030.98, "total_tokens": 3511960} {"current_steps": 39005, "total_steps": 76960, "loss": 0.2433, "lr": 2.87548863795175e-05, "epoch": 10.136434511434512, "percentage": 50.68, "elapsed_time": "0:56:46", "remaining_time": "0:55:15", "throughput": 1030.98, "total_tokens": 3512408} {"current_steps": 39010, "total_steps": 76960, "loss": 0.3036, "lr": 2.8749280998440488e-05, "epoch": 10.137733887733887, "percentage": 50.69, "elapsed_time": "0:56:47", "remaining_time": "0:55:14", "throughput": 1030.99, "total_tokens": 3512872} {"current_steps": 39015, "total_steps": 76960, "loss": 0.3333, "lr": 2.8743675424534355e-05, "epoch": 10.139033264033264, "percentage": 50.7, "elapsed_time": "0:56:47", "remaining_time": "0:55:14", "throughput": 1031.0, "total_tokens": 3513304} {"current_steps": 39020, "total_steps": 76960, "loss": 0.2705, "lr": 2.8738069658087412e-05, "epoch": 10.140332640332641, "percentage": 50.7, "elapsed_time": "0:56:48", "remaining_time": "0:55:13", "throughput": 1031.01, "total_tokens": 3513784} {"current_steps": 39025, "total_steps": 76960, "loss": 0.2501, "lr": 2.8732463699387968e-05, "epoch": 10.141632016632016, "percentage": 50.71, "elapsed_time": "0:56:48", "remaining_time": "0:55:13", "throughput": 1031.02, "total_tokens": 3514248} {"current_steps": 39030, "total_steps": 76960, "loss": 0.1976, "lr": 2.8726857548724328e-05, "epoch": 10.142931392931393, "percentage": 50.71, "elapsed_time": "0:56:48", "remaining_time": "0:55:12", "throughput": 1031.03, "total_tokens": 3514696} {"current_steps": 39035, "total_steps": 76960, "loss": 0.2814, "lr": 2.872125120638484e-05, "epoch": 10.14423076923077, "percentage": 50.72, "elapsed_time": "0:56:49", "remaining_time": "0:55:12", "throughput": 1031.03, "total_tokens": 3515128} {"current_steps": 39040, "total_steps": 76960, "loss": 0.247, "lr": 2.8715644672657842e-05, "epoch": 10.145530145530145, "percentage": 50.73, "elapsed_time": "0:56:49", "remaining_time": "0:55:11", "throughput": 1031.03, "total_tokens": 3515576} {"current_steps": 39045, "total_steps": 76960, "loss": 0.1809, "lr": 2.8710037947831676e-05, "epoch": 10.146829521829522, "percentage": 50.73, "elapsed_time": "0:56:50", "remaining_time": "0:55:11", "throughput": 1031.05, "total_tokens": 3516056} {"current_steps": 39050, "total_steps": 76960, "loss": 0.1508, "lr": 2.8704431032194696e-05, "epoch": 10.148128898128897, "percentage": 50.74, "elapsed_time": "0:56:50", "remaining_time": "0:55:11", "throughput": 1031.05, "total_tokens": 3516504} {"current_steps": 39055, "total_steps": 76960, "loss": 0.1774, "lr": 2.8698823926035283e-05, "epoch": 10.149428274428274, "percentage": 50.75, "elapsed_time": "0:56:51", "remaining_time": "0:55:10", "throughput": 1031.06, "total_tokens": 3516952} {"current_steps": 39060, "total_steps": 76960, "loss": 0.1349, "lr": 2.8693216629641818e-05, "epoch": 10.150727650727651, "percentage": 50.75, "elapsed_time": "0:56:51", "remaining_time": "0:55:10", "throughput": 1031.06, "total_tokens": 3517384} {"current_steps": 39065, "total_steps": 76960, "loss": 0.4605, "lr": 2.8687609143302678e-05, "epoch": 10.152027027027026, "percentage": 50.76, "elapsed_time": "0:56:51", "remaining_time": "0:55:09", "throughput": 1031.06, "total_tokens": 3517816} {"current_steps": 39070, "total_steps": 76960, "loss": 0.3347, "lr": 2.8682001467306265e-05, "epoch": 10.153326403326403, "percentage": 50.77, "elapsed_time": "0:56:52", "remaining_time": "0:55:09", "throughput": 1031.06, "total_tokens": 3518248} {"current_steps": 39075, "total_steps": 76960, "loss": 0.367, "lr": 2.867639360194099e-05, "epoch": 10.15462577962578, "percentage": 50.77, "elapsed_time": "0:56:52", "remaining_time": "0:55:08", "throughput": 1031.08, "total_tokens": 3518728} {"current_steps": 39080, "total_steps": 76960, "loss": 0.2229, "lr": 2.8670785547495272e-05, "epoch": 10.155925155925155, "percentage": 50.78, "elapsed_time": "0:56:53", "remaining_time": "0:55:08", "throughput": 1031.08, "total_tokens": 3519176} {"current_steps": 39085, "total_steps": 76960, "loss": 0.3029, "lr": 2.866517730425753e-05, "epoch": 10.157224532224532, "percentage": 50.79, "elapsed_time": "0:56:53", "remaining_time": "0:55:07", "throughput": 1031.09, "total_tokens": 3519640} {"current_steps": 39090, "total_steps": 76960, "loss": 0.2489, "lr": 2.8659568872516213e-05, "epoch": 10.15852390852391, "percentage": 50.79, "elapsed_time": "0:56:53", "remaining_time": "0:55:07", "throughput": 1031.1, "total_tokens": 3520088} {"current_steps": 39095, "total_steps": 76960, "loss": 0.3241, "lr": 2.8653960252559757e-05, "epoch": 10.159823284823284, "percentage": 50.8, "elapsed_time": "0:56:54", "remaining_time": "0:55:06", "throughput": 1031.11, "total_tokens": 3520552} {"current_steps": 39100, "total_steps": 76960, "loss": 0.1969, "lr": 2.864835144467663e-05, "epoch": 10.161122661122661, "percentage": 50.81, "elapsed_time": "0:56:54", "remaining_time": "0:55:06", "throughput": 1031.12, "total_tokens": 3521032} {"current_steps": 39105, "total_steps": 76960, "loss": 0.2345, "lr": 2.8642742449155284e-05, "epoch": 10.162422037422038, "percentage": 50.81, "elapsed_time": "0:56:55", "remaining_time": "0:55:06", "throughput": 1031.12, "total_tokens": 3521464} {"current_steps": 39110, "total_steps": 76960, "loss": 0.2167, "lr": 2.8637133266284215e-05, "epoch": 10.163721413721413, "percentage": 50.82, "elapsed_time": "0:56:55", "remaining_time": "0:55:05", "throughput": 1031.12, "total_tokens": 3521896} {"current_steps": 39115, "total_steps": 76960, "loss": 0.1625, "lr": 2.8631523896351893e-05, "epoch": 10.16502079002079, "percentage": 50.83, "elapsed_time": "0:56:56", "remaining_time": "0:55:05", "throughput": 1031.13, "total_tokens": 3522328} {"current_steps": 39120, "total_steps": 76960, "loss": 0.2997, "lr": 2.862591433964681e-05, "epoch": 10.166320166320165, "percentage": 50.83, "elapsed_time": "0:56:56", "remaining_time": "0:55:04", "throughput": 1031.13, "total_tokens": 3522760} {"current_steps": 39125, "total_steps": 76960, "loss": 0.2016, "lr": 2.8620304596457486e-05, "epoch": 10.167619542619542, "percentage": 50.84, "elapsed_time": "0:56:56", "remaining_time": "0:55:04", "throughput": 1031.12, "total_tokens": 3523160} {"current_steps": 39130, "total_steps": 76960, "loss": 0.2732, "lr": 2.8614694667072428e-05, "epoch": 10.16891891891892, "percentage": 50.84, "elapsed_time": "0:56:57", "remaining_time": "0:55:03", "throughput": 1031.12, "total_tokens": 3523592} {"current_steps": 39135, "total_steps": 76960, "loss": 0.201, "lr": 2.860908455178016e-05, "epoch": 10.170218295218294, "percentage": 50.85, "elapsed_time": "0:56:57", "remaining_time": "0:55:03", "throughput": 1031.14, "total_tokens": 3524088} {"current_steps": 39140, "total_steps": 76960, "loss": 0.2047, "lr": 2.860347425086921e-05, "epoch": 10.171517671517671, "percentage": 50.86, "elapsed_time": "0:56:58", "remaining_time": "0:55:02", "throughput": 1031.14, "total_tokens": 3524536} {"current_steps": 39145, "total_steps": 76960, "loss": 0.0527, "lr": 2.8597863764628136e-05, "epoch": 10.172817047817048, "percentage": 50.86, "elapsed_time": "0:56:58", "remaining_time": "0:55:02", "throughput": 1031.15, "total_tokens": 3525000} {"current_steps": 39150, "total_steps": 76960, "loss": 0.418, "lr": 2.859225309334548e-05, "epoch": 10.174116424116423, "percentage": 50.87, "elapsed_time": "0:56:58", "remaining_time": "0:55:01", "throughput": 1031.18, "total_tokens": 3525512} {"current_steps": 39155, "total_steps": 76960, "loss": 0.095, "lr": 2.8586642237309792e-05, "epoch": 10.1754158004158, "percentage": 50.88, "elapsed_time": "0:56:59", "remaining_time": "0:55:01", "throughput": 1031.18, "total_tokens": 3525944} {"current_steps": 39160, "total_steps": 76960, "loss": 0.4244, "lr": 2.8581031196809665e-05, "epoch": 10.176715176715177, "percentage": 50.88, "elapsed_time": "0:56:59", "remaining_time": "0:55:00", "throughput": 1031.18, "total_tokens": 3526376} {"current_steps": 39165, "total_steps": 76960, "loss": 0.239, "lr": 2.8575419972133675e-05, "epoch": 10.178014553014552, "percentage": 50.89, "elapsed_time": "0:57:00", "remaining_time": "0:55:00", "throughput": 1031.19, "total_tokens": 3526840} {"current_steps": 39170, "total_steps": 76960, "loss": 0.1474, "lr": 2.856980856357041e-05, "epoch": 10.17931392931393, "percentage": 50.9, "elapsed_time": "0:57:00", "remaining_time": "0:55:00", "throughput": 1031.2, "total_tokens": 3527320} {"current_steps": 39175, "total_steps": 76960, "loss": 0.1772, "lr": 2.8564196971408462e-05, "epoch": 10.180613305613306, "percentage": 50.9, "elapsed_time": "0:57:01", "remaining_time": "0:54:59", "throughput": 1031.21, "total_tokens": 3527768} {"current_steps": 39180, "total_steps": 76960, "loss": 0.3278, "lr": 2.855858519593646e-05, "epoch": 10.181912681912682, "percentage": 50.91, "elapsed_time": "0:57:01", "remaining_time": "0:54:59", "throughput": 1031.21, "total_tokens": 3528184} {"current_steps": 39185, "total_steps": 76960, "loss": 0.2968, "lr": 2.855297323744301e-05, "epoch": 10.183212058212058, "percentage": 50.92, "elapsed_time": "0:57:01", "remaining_time": "0:54:58", "throughput": 1031.21, "total_tokens": 3528632} {"current_steps": 39190, "total_steps": 76960, "loss": 0.2263, "lr": 2.854736109621674e-05, "epoch": 10.184511434511435, "percentage": 50.92, "elapsed_time": "0:57:02", "remaining_time": "0:54:58", "throughput": 1031.22, "total_tokens": 3529096} {"current_steps": 39195, "total_steps": 76960, "loss": 0.5098, "lr": 2.8541748772546286e-05, "epoch": 10.18581081081081, "percentage": 50.93, "elapsed_time": "0:57:02", "remaining_time": "0:54:57", "throughput": 1031.23, "total_tokens": 3529560} {"current_steps": 39200, "total_steps": 76960, "loss": 0.4346, "lr": 2.85361362667203e-05, "epoch": 10.187110187110187, "percentage": 50.94, "elapsed_time": "0:57:03", "remaining_time": "0:54:57", "throughput": 1031.25, "total_tokens": 3530040} {"current_steps": 39205, "total_steps": 76960, "loss": 0.1866, "lr": 2.853052357902744e-05, "epoch": 10.188409563409563, "percentage": 50.94, "elapsed_time": "0:57:03", "remaining_time": "0:54:56", "throughput": 1031.25, "total_tokens": 3530472} {"current_steps": 39210, "total_steps": 76960, "loss": 0.2097, "lr": 2.852491070975637e-05, "epoch": 10.18970893970894, "percentage": 50.95, "elapsed_time": "0:57:03", "remaining_time": "0:54:56", "throughput": 1031.25, "total_tokens": 3530904} {"current_steps": 39215, "total_steps": 76960, "loss": 0.2676, "lr": 2.8519297659195766e-05, "epoch": 10.191008316008316, "percentage": 50.96, "elapsed_time": "0:57:04", "remaining_time": "0:54:55", "throughput": 1031.25, "total_tokens": 3531352} {"current_steps": 39220, "total_steps": 76960, "loss": 0.278, "lr": 2.851368442763431e-05, "epoch": 10.192307692307692, "percentage": 50.96, "elapsed_time": "0:57:04", "remaining_time": "0:54:55", "throughput": 1031.25, "total_tokens": 3531784} {"current_steps": 39225, "total_steps": 76960, "loss": 0.2704, "lr": 2.8508071015360698e-05, "epoch": 10.193607068607069, "percentage": 50.97, "elapsed_time": "0:57:05", "remaining_time": "0:54:55", "throughput": 1031.27, "total_tokens": 3532248} {"current_steps": 39230, "total_steps": 76960, "loss": 0.2413, "lr": 2.850245742266363e-05, "epoch": 10.194906444906445, "percentage": 50.97, "elapsed_time": "0:57:05", "remaining_time": "0:54:54", "throughput": 1031.27, "total_tokens": 3532680} {"current_steps": 39235, "total_steps": 76960, "loss": 0.1997, "lr": 2.849684364983182e-05, "epoch": 10.19620582120582, "percentage": 50.98, "elapsed_time": "0:57:05", "remaining_time": "0:54:54", "throughput": 1031.26, "total_tokens": 3533096} {"current_steps": 39240, "total_steps": 76960, "loss": 0.1731, "lr": 2.8491229697153993e-05, "epoch": 10.197505197505198, "percentage": 50.99, "elapsed_time": "0:57:06", "remaining_time": "0:54:53", "throughput": 1031.27, "total_tokens": 3533560} {"current_steps": 39245, "total_steps": 76960, "loss": 0.3423, "lr": 2.8485615564918878e-05, "epoch": 10.198804573804575, "percentage": 50.99, "elapsed_time": "0:57:06", "remaining_time": "0:54:53", "throughput": 1031.27, "total_tokens": 3533992} {"current_steps": 39250, "total_steps": 76960, "loss": 0.2049, "lr": 2.8480001253415213e-05, "epoch": 10.20010395010395, "percentage": 51.0, "elapsed_time": "0:57:07", "remaining_time": "0:54:52", "throughput": 1031.28, "total_tokens": 3534440} {"current_steps": 39255, "total_steps": 76960, "loss": 0.2779, "lr": 2.847438676293175e-05, "epoch": 10.201403326403327, "percentage": 51.01, "elapsed_time": "0:57:07", "remaining_time": "0:54:52", "throughput": 1031.29, "total_tokens": 3534904} {"current_steps": 39260, "total_steps": 76960, "loss": 0.3055, "lr": 2.8468772093757244e-05, "epoch": 10.202702702702704, "percentage": 51.01, "elapsed_time": "0:57:08", "remaining_time": "0:54:51", "throughput": 1031.31, "total_tokens": 3535384} {"current_steps": 39265, "total_steps": 76960, "loss": 0.2449, "lr": 2.8463157246180468e-05, "epoch": 10.204002079002079, "percentage": 51.02, "elapsed_time": "0:57:08", "remaining_time": "0:54:51", "throughput": 1031.31, "total_tokens": 3535832} {"current_steps": 39270, "total_steps": 76960, "loss": 0.5463, "lr": 2.8457542220490196e-05, "epoch": 10.205301455301456, "percentage": 51.03, "elapsed_time": "0:57:08", "remaining_time": "0:54:50", "throughput": 1031.32, "total_tokens": 3536280} {"current_steps": 39275, "total_steps": 76960, "loss": 0.2014, "lr": 2.8451927016975216e-05, "epoch": 10.20660083160083, "percentage": 51.03, "elapsed_time": "0:57:09", "remaining_time": "0:54:50", "throughput": 1031.32, "total_tokens": 3536728} {"current_steps": 39280, "total_steps": 76960, "loss": 0.3352, "lr": 2.8446311635924326e-05, "epoch": 10.207900207900208, "percentage": 51.04, "elapsed_time": "0:57:09", "remaining_time": "0:54:50", "throughput": 1031.32, "total_tokens": 3537160} {"current_steps": 39285, "total_steps": 76960, "loss": 0.2238, "lr": 2.8440696077626324e-05, "epoch": 10.209199584199585, "percentage": 51.05, "elapsed_time": "0:57:10", "remaining_time": "0:54:49", "throughput": 1031.32, "total_tokens": 3537576} {"current_steps": 39290, "total_steps": 76960, "loss": 0.1897, "lr": 2.8435080342370023e-05, "epoch": 10.21049896049896, "percentage": 51.05, "elapsed_time": "0:57:10", "remaining_time": "0:54:49", "throughput": 1031.33, "total_tokens": 3538024} {"current_steps": 39295, "total_steps": 76960, "loss": 0.1935, "lr": 2.8429464430444252e-05, "epoch": 10.211798336798337, "percentage": 51.06, "elapsed_time": "0:57:10", "remaining_time": "0:54:48", "throughput": 1031.32, "total_tokens": 3538440} {"current_steps": 39300, "total_steps": 76960, "loss": 0.2668, "lr": 2.8423848342137832e-05, "epoch": 10.213097713097714, "percentage": 51.07, "elapsed_time": "0:57:11", "remaining_time": "0:54:48", "throughput": 1031.33, "total_tokens": 3538888} {"current_steps": 39305, "total_steps": 76960, "loss": 0.1806, "lr": 2.841823207773962e-05, "epoch": 10.214397089397089, "percentage": 51.07, "elapsed_time": "0:57:11", "remaining_time": "0:54:47", "throughput": 1031.33, "total_tokens": 3539320} {"current_steps": 39310, "total_steps": 76960, "loss": 0.212, "lr": 2.8412615637538454e-05, "epoch": 10.215696465696466, "percentage": 51.08, "elapsed_time": "0:57:12", "remaining_time": "0:54:47", "throughput": 1031.32, "total_tokens": 3539736} {"current_steps": 39315, "total_steps": 76960, "loss": 0.2607, "lr": 2.8406999021823196e-05, "epoch": 10.216995841995843, "percentage": 51.08, "elapsed_time": "0:57:12", "remaining_time": "0:54:46", "throughput": 1031.34, "total_tokens": 3540216} {"current_steps": 39320, "total_steps": 76960, "loss": 0.1371, "lr": 2.8401382230882712e-05, "epoch": 10.218295218295218, "percentage": 51.09, "elapsed_time": "0:57:13", "remaining_time": "0:54:46", "throughput": 1031.36, "total_tokens": 3540712} {"current_steps": 39325, "total_steps": 76960, "loss": 0.3028, "lr": 2.839576526500588e-05, "epoch": 10.219594594594595, "percentage": 51.1, "elapsed_time": "0:57:13", "remaining_time": "0:54:45", "throughput": 1031.38, "total_tokens": 3541208} {"current_steps": 39330, "total_steps": 76960, "loss": 0.3479, "lr": 2.839014812448159e-05, "epoch": 10.220893970893972, "percentage": 51.1, "elapsed_time": "0:57:13", "remaining_time": "0:54:45", "throughput": 1031.38, "total_tokens": 3541624} {"current_steps": 39335, "total_steps": 76960, "loss": 0.2144, "lr": 2.838453080959873e-05, "epoch": 10.222193347193347, "percentage": 51.11, "elapsed_time": "0:57:14", "remaining_time": "0:54:45", "throughput": 1031.37, "total_tokens": 3542040} {"current_steps": 39340, "total_steps": 76960, "loss": 0.1739, "lr": 2.8378913320646212e-05, "epoch": 10.223492723492724, "percentage": 51.12, "elapsed_time": "0:57:14", "remaining_time": "0:54:44", "throughput": 1031.37, "total_tokens": 3542472} {"current_steps": 39345, "total_steps": 76960, "loss": 0.395, "lr": 2.8373295657912945e-05, "epoch": 10.2247920997921, "percentage": 51.12, "elapsed_time": "0:57:15", "remaining_time": "0:54:44", "throughput": 1031.37, "total_tokens": 3542888} {"current_steps": 39350, "total_steps": 76960, "loss": 0.1257, "lr": 2.8367677821687848e-05, "epoch": 10.226091476091476, "percentage": 51.13, "elapsed_time": "0:57:15", "remaining_time": "0:54:43", "throughput": 1031.38, "total_tokens": 3543352} {"current_steps": 39355, "total_steps": 76960, "loss": 0.2089, "lr": 2.836205981225985e-05, "epoch": 10.227390852390853, "percentage": 51.14, "elapsed_time": "0:57:15", "remaining_time": "0:54:43", "throughput": 1031.39, "total_tokens": 3543832} {"current_steps": 39360, "total_steps": 76960, "loss": 0.2467, "lr": 2.8356441629917902e-05, "epoch": 10.228690228690228, "percentage": 51.14, "elapsed_time": "0:57:16", "remaining_time": "0:54:42", "throughput": 1031.4, "total_tokens": 3544296} {"current_steps": 39365, "total_steps": 76960, "loss": 0.4605, "lr": 2.8350823274950943e-05, "epoch": 10.229989604989605, "percentage": 51.15, "elapsed_time": "0:57:16", "remaining_time": "0:54:42", "throughput": 1031.41, "total_tokens": 3544760} {"current_steps": 39370, "total_steps": 76960, "loss": 0.3573, "lr": 2.8345204747647924e-05, "epoch": 10.231288981288982, "percentage": 51.16, "elapsed_time": "0:57:17", "remaining_time": "0:54:41", "throughput": 1031.42, "total_tokens": 3545208} {"current_steps": 39375, "total_steps": 76960, "loss": 0.3286, "lr": 2.833958604829783e-05, "epoch": 10.232588357588357, "percentage": 51.16, "elapsed_time": "0:57:17", "remaining_time": "0:54:41", "throughput": 1031.43, "total_tokens": 3545672} {"current_steps": 39380, "total_steps": 76960, "loss": 0.162, "lr": 2.833396717718962e-05, "epoch": 10.233887733887734, "percentage": 51.17, "elapsed_time": "0:57:18", "remaining_time": "0:54:40", "throughput": 1031.42, "total_tokens": 3546088} {"current_steps": 39385, "total_steps": 76960, "loss": 0.095, "lr": 2.8328348134612288e-05, "epoch": 10.23518711018711, "percentage": 51.18, "elapsed_time": "0:57:18", "remaining_time": "0:54:40", "throughput": 1031.43, "total_tokens": 3546536} {"current_steps": 39390, "total_steps": 76960, "loss": 0.3781, "lr": 2.8322728920854812e-05, "epoch": 10.236486486486486, "percentage": 51.18, "elapsed_time": "0:57:18", "remaining_time": "0:54:39", "throughput": 1031.42, "total_tokens": 3546936} {"current_steps": 39395, "total_steps": 76960, "loss": 0.2674, "lr": 2.8317109536206216e-05, "epoch": 10.237785862785863, "percentage": 51.19, "elapsed_time": "0:57:19", "remaining_time": "0:54:39", "throughput": 1031.42, "total_tokens": 3547368} {"current_steps": 39400, "total_steps": 76960, "loss": 0.3478, "lr": 2.831148998095549e-05, "epoch": 10.23908523908524, "percentage": 51.2, "elapsed_time": "0:57:19", "remaining_time": "0:54:39", "throughput": 1031.43, "total_tokens": 3547832} {"current_steps": 39405, "total_steps": 76960, "loss": 0.2315, "lr": 2.830587025539167e-05, "epoch": 10.240384615384615, "percentage": 51.2, "elapsed_time": "0:57:20", "remaining_time": "0:54:38", "throughput": 1031.44, "total_tokens": 3548296} {"current_steps": 39410, "total_steps": 76960, "loss": 0.2108, "lr": 2.830025035980377e-05, "epoch": 10.241683991683992, "percentage": 51.21, "elapsed_time": "0:57:20", "remaining_time": "0:54:38", "throughput": 1031.45, "total_tokens": 3548760} {"current_steps": 39415, "total_steps": 76960, "loss": 0.1448, "lr": 2.8294630294480834e-05, "epoch": 10.242983367983369, "percentage": 51.21, "elapsed_time": "0:57:20", "remaining_time": "0:54:37", "throughput": 1031.46, "total_tokens": 3549224} {"current_steps": 39420, "total_steps": 76960, "loss": 0.2665, "lr": 2.8289010059711906e-05, "epoch": 10.244282744282744, "percentage": 51.22, "elapsed_time": "0:57:21", "remaining_time": "0:54:37", "throughput": 1031.48, "total_tokens": 3549704} {"current_steps": 39425, "total_steps": 76960, "loss": 0.4418, "lr": 2.828338965578603e-05, "epoch": 10.245582120582121, "percentage": 51.23, "elapsed_time": "0:57:21", "remaining_time": "0:54:36", "throughput": 1031.49, "total_tokens": 3550184} {"current_steps": 39430, "total_steps": 76960, "loss": 0.2807, "lr": 2.827776908299229e-05, "epoch": 10.246881496881496, "percentage": 51.23, "elapsed_time": "0:57:22", "remaining_time": "0:54:36", "throughput": 1031.5, "total_tokens": 3550648} {"current_steps": 39435, "total_steps": 76960, "loss": 0.2721, "lr": 2.8272148341619742e-05, "epoch": 10.248180873180873, "percentage": 51.24, "elapsed_time": "0:57:22", "remaining_time": "0:54:35", "throughput": 1031.51, "total_tokens": 3551080} {"current_steps": 39440, "total_steps": 76960, "loss": 0.1847, "lr": 2.8266527431957467e-05, "epoch": 10.24948024948025, "percentage": 51.25, "elapsed_time": "0:57:23", "remaining_time": "0:54:35", "throughput": 1031.51, "total_tokens": 3551512} {"current_steps": 39445, "total_steps": 76960, "loss": 0.2463, "lr": 2.826090635429455e-05, "epoch": 10.250779625779625, "percentage": 51.25, "elapsed_time": "0:57:23", "remaining_time": "0:54:34", "throughput": 1031.51, "total_tokens": 3551960} {"current_steps": 39450, "total_steps": 76960, "loss": 0.2303, "lr": 2.8255285108920105e-05, "epoch": 10.252079002079002, "percentage": 51.26, "elapsed_time": "0:57:23", "remaining_time": "0:54:34", "throughput": 1031.52, "total_tokens": 3552408} {"current_steps": 39455, "total_steps": 76960, "loss": 0.1747, "lr": 2.8249663696123223e-05, "epoch": 10.253378378378379, "percentage": 51.27, "elapsed_time": "0:57:24", "remaining_time": "0:54:34", "throughput": 1031.54, "total_tokens": 3552904} {"current_steps": 39460, "total_steps": 76960, "loss": 0.3975, "lr": 2.8244042116193033e-05, "epoch": 10.254677754677754, "percentage": 51.27, "elapsed_time": "0:57:24", "remaining_time": "0:54:33", "throughput": 1031.55, "total_tokens": 3553368} {"current_steps": 39465, "total_steps": 76960, "loss": 0.4026, "lr": 2.8238420369418633e-05, "epoch": 10.255977130977131, "percentage": 51.28, "elapsed_time": "0:57:25", "remaining_time": "0:54:33", "throughput": 1031.55, "total_tokens": 3553816} {"current_steps": 39470, "total_steps": 76960, "loss": 0.2417, "lr": 2.8232798456089183e-05, "epoch": 10.257276507276508, "percentage": 51.29, "elapsed_time": "0:57:25", "remaining_time": "0:54:32", "throughput": 1031.55, "total_tokens": 3554232} {"current_steps": 39475, "total_steps": 76960, "loss": 0.1253, "lr": 2.822717637649381e-05, "epoch": 10.258575883575883, "percentage": 51.29, "elapsed_time": "0:57:25", "remaining_time": "0:54:32", "throughput": 1031.56, "total_tokens": 3554696} {"current_steps": 39480, "total_steps": 76960, "loss": 0.4742, "lr": 2.8221554130921656e-05, "epoch": 10.25987525987526, "percentage": 51.3, "elapsed_time": "0:57:26", "remaining_time": "0:54:31", "throughput": 1031.55, "total_tokens": 3555112} {"current_steps": 39485, "total_steps": 76960, "loss": 0.2709, "lr": 2.8215931719661893e-05, "epoch": 10.261174636174637, "percentage": 51.31, "elapsed_time": "0:57:26", "remaining_time": "0:54:31", "throughput": 1031.57, "total_tokens": 3555608} {"current_steps": 39490, "total_steps": 76960, "loss": 0.2814, "lr": 2.8210309143003676e-05, "epoch": 10.262474012474012, "percentage": 51.31, "elapsed_time": "0:57:27", "remaining_time": "0:54:30", "throughput": 1031.57, "total_tokens": 3556024} {"current_steps": 39495, "total_steps": 76960, "loss": 0.1956, "lr": 2.820468640123618e-05, "epoch": 10.263773388773389, "percentage": 51.32, "elapsed_time": "0:57:27", "remaining_time": "0:54:30", "throughput": 1031.58, "total_tokens": 3556488} {"current_steps": 39500, "total_steps": 76960, "loss": 0.2862, "lr": 2.8199063494648598e-05, "epoch": 10.265072765072764, "percentage": 51.33, "elapsed_time": "0:57:28", "remaining_time": "0:54:29", "throughput": 1031.59, "total_tokens": 3556952} {"current_steps": 39505, "total_steps": 76960, "loss": 0.3389, "lr": 2.8193440423530114e-05, "epoch": 10.266372141372141, "percentage": 51.33, "elapsed_time": "0:57:28", "remaining_time": "0:54:29", "throughput": 1031.59, "total_tokens": 3557384} {"current_steps": 39510, "total_steps": 76960, "loss": 0.2847, "lr": 2.8187817188169936e-05, "epoch": 10.267671517671518, "percentage": 51.34, "elapsed_time": "0:57:28", "remaining_time": "0:54:29", "throughput": 1031.61, "total_tokens": 3557864} {"current_steps": 39515, "total_steps": 76960, "loss": 0.1952, "lr": 2.8182193788857254e-05, "epoch": 10.268970893970893, "percentage": 51.34, "elapsed_time": "0:57:29", "remaining_time": "0:54:28", "throughput": 1031.6, "total_tokens": 3558280} {"current_steps": 39520, "total_steps": 76960, "loss": 0.1357, "lr": 2.81765702258813e-05, "epoch": 10.27027027027027, "percentage": 51.35, "elapsed_time": "0:57:29", "remaining_time": "0:54:28", "throughput": 1031.6, "total_tokens": 3558696} {"current_steps": 39525, "total_steps": 76960, "loss": 0.2726, "lr": 2.8170946499531298e-05, "epoch": 10.271569646569647, "percentage": 51.36, "elapsed_time": "0:57:30", "remaining_time": "0:54:27", "throughput": 1031.6, "total_tokens": 3559144} {"current_steps": 39530, "total_steps": 76960, "loss": 0.3162, "lr": 2.8165322610096483e-05, "epoch": 10.272869022869022, "percentage": 51.36, "elapsed_time": "0:57:30", "remaining_time": "0:54:27", "throughput": 1031.61, "total_tokens": 3559592} {"current_steps": 39535, "total_steps": 76960, "loss": 0.2209, "lr": 2.8159698557866082e-05, "epoch": 10.2741683991684, "percentage": 51.37, "elapsed_time": "0:57:30", "remaining_time": "0:54:26", "throughput": 1031.61, "total_tokens": 3560024} {"current_steps": 39540, "total_steps": 76960, "loss": 0.1535, "lr": 2.8154074343129372e-05, "epoch": 10.275467775467776, "percentage": 51.38, "elapsed_time": "0:57:31", "remaining_time": "0:54:26", "throughput": 1031.61, "total_tokens": 3560472} {"current_steps": 39545, "total_steps": 76960, "loss": 0.0933, "lr": 2.814844996617559e-05, "epoch": 10.276767151767151, "percentage": 51.38, "elapsed_time": "0:57:31", "remaining_time": "0:54:25", "throughput": 1031.62, "total_tokens": 3560936} {"current_steps": 39550, "total_steps": 76960, "loss": 0.2588, "lr": 2.8142825427294e-05, "epoch": 10.278066528066528, "percentage": 51.39, "elapsed_time": "0:57:32", "remaining_time": "0:54:25", "throughput": 1031.62, "total_tokens": 3561368} {"current_steps": 39555, "total_steps": 76960, "loss": 0.3568, "lr": 2.81372007267739e-05, "epoch": 10.279365904365905, "percentage": 51.4, "elapsed_time": "0:57:32", "remaining_time": "0:54:24", "throughput": 1031.64, "total_tokens": 3561864} {"current_steps": 39560, "total_steps": 76960, "loss": 0.1463, "lr": 2.813157586490455e-05, "epoch": 10.28066528066528, "percentage": 51.4, "elapsed_time": "0:57:33", "remaining_time": "0:54:24", "throughput": 1031.64, "total_tokens": 3562264} {"current_steps": 39565, "total_steps": 76960, "loss": 0.2231, "lr": 2.8125950841975264e-05, "epoch": 10.281964656964657, "percentage": 51.41, "elapsed_time": "0:57:33", "remaining_time": "0:54:24", "throughput": 1031.65, "total_tokens": 3562728} {"current_steps": 39570, "total_steps": 76960, "loss": 0.1259, "lr": 2.8120325658275322e-05, "epoch": 10.283264033264032, "percentage": 51.42, "elapsed_time": "0:57:33", "remaining_time": "0:54:23", "throughput": 1031.66, "total_tokens": 3563208} {"current_steps": 39575, "total_steps": 76960, "loss": 0.2413, "lr": 2.8114700314094044e-05, "epoch": 10.28456340956341, "percentage": 51.42, "elapsed_time": "0:57:34", "remaining_time": "0:54:23", "throughput": 1031.66, "total_tokens": 3563640} {"current_steps": 39580, "total_steps": 76960, "loss": 0.2477, "lr": 2.8109074809720747e-05, "epoch": 10.285862785862786, "percentage": 51.43, "elapsed_time": "0:57:34", "remaining_time": "0:54:22", "throughput": 1031.67, "total_tokens": 3564088} {"current_steps": 39585, "total_steps": 76960, "loss": 0.5329, "lr": 2.810344914544475e-05, "epoch": 10.287162162162161, "percentage": 51.44, "elapsed_time": "0:57:35", "remaining_time": "0:54:22", "throughput": 1031.7, "total_tokens": 3564616} {"current_steps": 39590, "total_steps": 76960, "loss": 0.1872, "lr": 2.8097823321555388e-05, "epoch": 10.288461538461538, "percentage": 51.44, "elapsed_time": "0:57:35", "remaining_time": "0:54:21", "throughput": 1031.69, "total_tokens": 3565032} {"current_steps": 39595, "total_steps": 76960, "loss": 0.4076, "lr": 2.809219733834201e-05, "epoch": 10.289760914760915, "percentage": 51.45, "elapsed_time": "0:57:35", "remaining_time": "0:54:21", "throughput": 1031.69, "total_tokens": 3565464} {"current_steps": 39600, "total_steps": 76960, "loss": 0.1119, "lr": 2.808657119609396e-05, "epoch": 10.29106029106029, "percentage": 51.46, "elapsed_time": "0:57:36", "remaining_time": "0:54:20", "throughput": 1031.69, "total_tokens": 3565880} {"current_steps": 39605, "total_steps": 76960, "loss": 0.1403, "lr": 2.808094489510059e-05, "epoch": 10.292359667359667, "percentage": 51.46, "elapsed_time": "0:57:36", "remaining_time": "0:54:20", "throughput": 1031.69, "total_tokens": 3566312} {"current_steps": 39610, "total_steps": 76960, "loss": 0.1919, "lr": 2.8075318435651282e-05, "epoch": 10.293659043659044, "percentage": 51.47, "elapsed_time": "0:57:37", "remaining_time": "0:54:19", "throughput": 1031.69, "total_tokens": 3566760} {"current_steps": 39615, "total_steps": 76960, "loss": 0.3694, "lr": 2.8069691818035393e-05, "epoch": 10.29495841995842, "percentage": 51.47, "elapsed_time": "0:57:37", "remaining_time": "0:54:19", "throughput": 1031.7, "total_tokens": 3567192} {"current_steps": 39620, "total_steps": 76960, "loss": 0.3224, "lr": 2.806406504254231e-05, "epoch": 10.296257796257796, "percentage": 51.48, "elapsed_time": "0:57:38", "remaining_time": "0:54:19", "throughput": 1031.7, "total_tokens": 3567624} {"current_steps": 39625, "total_steps": 76960, "loss": 0.4509, "lr": 2.8058438109461434e-05, "epoch": 10.297557172557173, "percentage": 51.49, "elapsed_time": "0:57:38", "remaining_time": "0:54:18", "throughput": 1031.7, "total_tokens": 3568072} {"current_steps": 39630, "total_steps": 76960, "loss": 0.4073, "lr": 2.8052811019082155e-05, "epoch": 10.298856548856548, "percentage": 51.49, "elapsed_time": "0:57:38", "remaining_time": "0:54:18", "throughput": 1031.71, "total_tokens": 3568520} {"current_steps": 39635, "total_steps": 76960, "loss": 0.248, "lr": 2.8047183771693874e-05, "epoch": 10.300155925155925, "percentage": 51.5, "elapsed_time": "0:57:39", "remaining_time": "0:54:17", "throughput": 1031.71, "total_tokens": 3568952} {"current_steps": 39640, "total_steps": 76960, "loss": 0.3275, "lr": 2.804155636758601e-05, "epoch": 10.301455301455302, "percentage": 51.51, "elapsed_time": "0:57:39", "remaining_time": "0:54:17", "throughput": 1031.71, "total_tokens": 3569400} {"current_steps": 39645, "total_steps": 76960, "loss": 0.244, "lr": 2.8035928807047995e-05, "epoch": 10.302754677754677, "percentage": 51.51, "elapsed_time": "0:57:40", "remaining_time": "0:54:16", "throughput": 1031.73, "total_tokens": 3569880} {"current_steps": 39650, "total_steps": 76960, "loss": 0.1873, "lr": 2.8030301090369248e-05, "epoch": 10.304054054054054, "percentage": 51.52, "elapsed_time": "0:57:40", "remaining_time": "0:54:16", "throughput": 1031.73, "total_tokens": 3570328} {"current_steps": 39655, "total_steps": 76960, "loss": 0.1547, "lr": 2.8024673217839214e-05, "epoch": 10.30535343035343, "percentage": 51.53, "elapsed_time": "0:57:40", "remaining_time": "0:54:15", "throughput": 1031.74, "total_tokens": 3570792} {"current_steps": 39660, "total_steps": 76960, "loss": 0.1861, "lr": 2.801904518974734e-05, "epoch": 10.306652806652806, "percentage": 51.53, "elapsed_time": "0:57:41", "remaining_time": "0:54:15", "throughput": 1031.76, "total_tokens": 3571288} {"current_steps": 39665, "total_steps": 76960, "loss": 0.1585, "lr": 2.8013417006383076e-05, "epoch": 10.307952182952183, "percentage": 51.54, "elapsed_time": "0:57:41", "remaining_time": "0:54:14", "throughput": 1031.76, "total_tokens": 3571704} {"current_steps": 39670, "total_steps": 76960, "loss": 0.0934, "lr": 2.8007788668035895e-05, "epoch": 10.309251559251559, "percentage": 51.55, "elapsed_time": "0:57:42", "remaining_time": "0:54:14", "throughput": 1031.76, "total_tokens": 3572136} {"current_steps": 39675, "total_steps": 76960, "loss": 0.0434, "lr": 2.800216017499525e-05, "epoch": 10.310550935550935, "percentage": 51.55, "elapsed_time": "0:57:42", "remaining_time": "0:54:14", "throughput": 1031.76, "total_tokens": 3572552} {"current_steps": 39680, "total_steps": 76960, "loss": 0.2061, "lr": 2.799653152755064e-05, "epoch": 10.311850311850312, "percentage": 51.56, "elapsed_time": "0:57:43", "remaining_time": "0:54:13", "throughput": 1031.77, "total_tokens": 3573016} {"current_steps": 39685, "total_steps": 76960, "loss": 0.3471, "lr": 2.799090272599154e-05, "epoch": 10.313149688149688, "percentage": 51.57, "elapsed_time": "0:57:43", "remaining_time": "0:54:13", "throughput": 1031.77, "total_tokens": 3573448} {"current_steps": 39690, "total_steps": 76960, "loss": 0.0359, "lr": 2.7985273770607445e-05, "epoch": 10.314449064449065, "percentage": 51.57, "elapsed_time": "0:57:43", "remaining_time": "0:54:12", "throughput": 1031.77, "total_tokens": 3573880} {"current_steps": 39695, "total_steps": 76960, "loss": 0.3702, "lr": 2.797964466168786e-05, "epoch": 10.315748440748441, "percentage": 51.58, "elapsed_time": "0:57:44", "remaining_time": "0:54:12", "throughput": 1031.77, "total_tokens": 3574312} {"current_steps": 39700, "total_steps": 76960, "loss": 0.3257, "lr": 2.7974015399522298e-05, "epoch": 10.317047817047817, "percentage": 51.59, "elapsed_time": "0:57:44", "remaining_time": "0:54:11", "throughput": 1031.79, "total_tokens": 3574808} {"current_steps": 39705, "total_steps": 76960, "loss": 0.2037, "lr": 2.796838598440027e-05, "epoch": 10.318347193347194, "percentage": 51.59, "elapsed_time": "0:57:45", "remaining_time": "0:54:11", "throughput": 1031.8, "total_tokens": 3575288} {"current_steps": 39710, "total_steps": 76960, "loss": 0.495, "lr": 2.7962756416611314e-05, "epoch": 10.31964656964657, "percentage": 51.6, "elapsed_time": "0:57:45", "remaining_time": "0:54:10", "throughput": 1031.81, "total_tokens": 3575752} {"current_steps": 39715, "total_steps": 76960, "loss": 0.2457, "lr": 2.7957126696444948e-05, "epoch": 10.320945945945946, "percentage": 51.6, "elapsed_time": "0:57:45", "remaining_time": "0:54:10", "throughput": 1031.81, "total_tokens": 3576184} {"current_steps": 39720, "total_steps": 76960, "loss": 0.3993, "lr": 2.7951496824190726e-05, "epoch": 10.322245322245323, "percentage": 51.61, "elapsed_time": "0:57:46", "remaining_time": "0:54:09", "throughput": 1031.81, "total_tokens": 3576600} {"current_steps": 39725, "total_steps": 76960, "loss": 0.051, "lr": 2.7945866800138195e-05, "epoch": 10.323544698544698, "percentage": 51.62, "elapsed_time": "0:57:46", "remaining_time": "0:54:09", "throughput": 1031.81, "total_tokens": 3577048} {"current_steps": 39730, "total_steps": 76960, "loss": 0.2209, "lr": 2.7940236624576904e-05, "epoch": 10.324844074844075, "percentage": 51.62, "elapsed_time": "0:57:47", "remaining_time": "0:54:08", "throughput": 1031.82, "total_tokens": 3577480} {"current_steps": 39735, "total_steps": 76960, "loss": 0.3574, "lr": 2.793460629779644e-05, "epoch": 10.326143451143452, "percentage": 51.63, "elapsed_time": "0:57:47", "remaining_time": "0:54:08", "throughput": 1031.82, "total_tokens": 3577928} {"current_steps": 39740, "total_steps": 76960, "loss": 0.249, "lr": 2.7928975820086357e-05, "epoch": 10.327442827442827, "percentage": 51.64, "elapsed_time": "0:57:47", "remaining_time": "0:54:08", "throughput": 1031.84, "total_tokens": 3578408} {"current_steps": 39745, "total_steps": 76960, "loss": 0.3179, "lr": 2.792334519173624e-05, "epoch": 10.328742203742204, "percentage": 51.64, "elapsed_time": "0:57:48", "remaining_time": "0:54:07", "throughput": 1031.85, "total_tokens": 3578872} {"current_steps": 39750, "total_steps": 76960, "loss": 0.2688, "lr": 2.7917714413035678e-05, "epoch": 10.33004158004158, "percentage": 51.65, "elapsed_time": "0:57:48", "remaining_time": "0:54:07", "throughput": 1031.84, "total_tokens": 3579288} {"current_steps": 39755, "total_steps": 76960, "loss": 0.1247, "lr": 2.7912083484274266e-05, "epoch": 10.331340956340956, "percentage": 51.66, "elapsed_time": "0:57:49", "remaining_time": "0:54:06", "throughput": 1031.85, "total_tokens": 3579752} {"current_steps": 39760, "total_steps": 76960, "loss": 0.2025, "lr": 2.790645240574162e-05, "epoch": 10.332640332640333, "percentage": 51.66, "elapsed_time": "0:57:49", "remaining_time": "0:54:06", "throughput": 1031.86, "total_tokens": 3580200} {"current_steps": 39765, "total_steps": 76960, "loss": 0.1956, "lr": 2.7900821177727326e-05, "epoch": 10.33393970893971, "percentage": 51.67, "elapsed_time": "0:57:50", "remaining_time": "0:54:05", "throughput": 1031.85, "total_tokens": 3580616} {"current_steps": 39770, "total_steps": 76960, "loss": 0.468, "lr": 2.7895189800521033e-05, "epoch": 10.335239085239085, "percentage": 51.68, "elapsed_time": "0:57:50", "remaining_time": "0:54:05", "throughput": 1031.87, "total_tokens": 3581080} {"current_steps": 39775, "total_steps": 76960, "loss": 0.5375, "lr": 2.788955827441235e-05, "epoch": 10.336538461538462, "percentage": 51.68, "elapsed_time": "0:57:50", "remaining_time": "0:54:04", "throughput": 1031.88, "total_tokens": 3581576} {"current_steps": 39780, "total_steps": 76960, "loss": 0.1865, "lr": 2.7883926599690914e-05, "epoch": 10.337837837837839, "percentage": 51.69, "elapsed_time": "0:57:51", "remaining_time": "0:54:04", "throughput": 1031.89, "total_tokens": 3582040} {"current_steps": 39785, "total_steps": 76960, "loss": 0.1346, "lr": 2.787829477664637e-05, "epoch": 10.339137214137214, "percentage": 51.7, "elapsed_time": "0:57:51", "remaining_time": "0:54:03", "throughput": 1031.9, "total_tokens": 3582504} {"current_steps": 39790, "total_steps": 76960, "loss": 0.4431, "lr": 2.787266280556837e-05, "epoch": 10.34043659043659, "percentage": 51.7, "elapsed_time": "0:57:52", "remaining_time": "0:54:03", "throughput": 1031.92, "total_tokens": 3582968} {"current_steps": 39795, "total_steps": 76960, "loss": 0.2755, "lr": 2.786703068674657e-05, "epoch": 10.341735966735968, "percentage": 51.71, "elapsed_time": "0:57:52", "remaining_time": "0:54:03", "throughput": 1031.92, "total_tokens": 3583400} {"current_steps": 39800, "total_steps": 76960, "loss": 0.2536, "lr": 2.7861398420470636e-05, "epoch": 10.343035343035343, "percentage": 51.72, "elapsed_time": "0:57:52", "remaining_time": "0:54:02", "throughput": 1031.93, "total_tokens": 3583880} {"current_steps": 39805, "total_steps": 76960, "loss": 0.234, "lr": 2.7855766007030237e-05, "epoch": 10.34433471933472, "percentage": 51.72, "elapsed_time": "0:57:53", "remaining_time": "0:54:02", "throughput": 1031.94, "total_tokens": 3584328} {"current_steps": 39810, "total_steps": 76960, "loss": 0.2327, "lr": 2.785013344671506e-05, "epoch": 10.345634095634095, "percentage": 51.73, "elapsed_time": "0:57:53", "remaining_time": "0:54:01", "throughput": 1031.93, "total_tokens": 3584744} {"current_steps": 39815, "total_steps": 76960, "loss": 0.2289, "lr": 2.7844500739814782e-05, "epoch": 10.346933471933472, "percentage": 51.73, "elapsed_time": "0:57:54", "remaining_time": "0:54:01", "throughput": 1031.93, "total_tokens": 3585176} {"current_steps": 39820, "total_steps": 76960, "loss": 0.2086, "lr": 2.783886788661911e-05, "epoch": 10.348232848232849, "percentage": 51.74, "elapsed_time": "0:57:54", "remaining_time": "0:54:00", "throughput": 1031.94, "total_tokens": 3585640} {"current_steps": 39825, "total_steps": 76960, "loss": 0.1787, "lr": 2.7833234887417743e-05, "epoch": 10.349532224532224, "percentage": 51.75, "elapsed_time": "0:57:55", "remaining_time": "0:54:00", "throughput": 1031.94, "total_tokens": 3586056} {"current_steps": 39830, "total_steps": 76960, "loss": 0.181, "lr": 2.7827601742500388e-05, "epoch": 10.3508316008316, "percentage": 51.75, "elapsed_time": "0:57:55", "remaining_time": "0:53:59", "throughput": 1031.94, "total_tokens": 3586488} {"current_steps": 39835, "total_steps": 76960, "loss": 0.0938, "lr": 2.7821968452156766e-05, "epoch": 10.352130977130978, "percentage": 51.76, "elapsed_time": "0:57:55", "remaining_time": "0:53:59", "throughput": 1031.95, "total_tokens": 3586952} {"current_steps": 39840, "total_steps": 76960, "loss": 0.3264, "lr": 2.7816335016676604e-05, "epoch": 10.353430353430353, "percentage": 51.77, "elapsed_time": "0:57:56", "remaining_time": "0:53:58", "throughput": 1031.96, "total_tokens": 3587416} {"current_steps": 39845, "total_steps": 76960, "loss": 0.1922, "lr": 2.7810701436349633e-05, "epoch": 10.35472972972973, "percentage": 51.77, "elapsed_time": "0:57:56", "remaining_time": "0:53:58", "throughput": 1031.97, "total_tokens": 3587864} {"current_steps": 39850, "total_steps": 76960, "loss": 0.2619, "lr": 2.7805067711465594e-05, "epoch": 10.356029106029107, "percentage": 51.78, "elapsed_time": "0:57:57", "remaining_time": "0:53:58", "throughput": 1031.98, "total_tokens": 3588344} {"current_steps": 39855, "total_steps": 76960, "loss": 0.2888, "lr": 2.7799433842314232e-05, "epoch": 10.357328482328482, "percentage": 51.79, "elapsed_time": "0:57:57", "remaining_time": "0:53:57", "throughput": 1031.99, "total_tokens": 3588792} {"current_steps": 39860, "total_steps": 76960, "loss": 0.3589, "lr": 2.7793799829185315e-05, "epoch": 10.358627858627859, "percentage": 51.79, "elapsed_time": "0:57:57", "remaining_time": "0:53:57", "throughput": 1031.98, "total_tokens": 3589208} {"current_steps": 39865, "total_steps": 76960, "loss": 0.2332, "lr": 2.7788165672368594e-05, "epoch": 10.359927234927236, "percentage": 51.8, "elapsed_time": "0:57:58", "remaining_time": "0:53:56", "throughput": 1031.98, "total_tokens": 3589624} {"current_steps": 39870, "total_steps": 76960, "loss": 0.0928, "lr": 2.778253137215383e-05, "epoch": 10.361226611226611, "percentage": 51.81, "elapsed_time": "0:57:58", "remaining_time": "0:53:56", "throughput": 1031.98, "total_tokens": 3590040} {"current_steps": 39875, "total_steps": 76960, "loss": 0.2141, "lr": 2.777689692883082e-05, "epoch": 10.362525987525988, "percentage": 51.81, "elapsed_time": "0:57:59", "remaining_time": "0:53:55", "throughput": 1031.98, "total_tokens": 3590472} {"current_steps": 39880, "total_steps": 76960, "loss": 0.1483, "lr": 2.7771262342689343e-05, "epoch": 10.363825363825363, "percentage": 51.82, "elapsed_time": "0:57:59", "remaining_time": "0:53:55", "throughput": 1031.98, "total_tokens": 3590904} {"current_steps": 39885, "total_steps": 76960, "loss": 0.0655, "lr": 2.7765627614019185e-05, "epoch": 10.36512474012474, "percentage": 51.83, "elapsed_time": "0:58:00", "remaining_time": "0:53:54", "throughput": 1031.98, "total_tokens": 3591336} {"current_steps": 39890, "total_steps": 76960, "loss": 0.3238, "lr": 2.7759992743110143e-05, "epoch": 10.366424116424117, "percentage": 51.83, "elapsed_time": "0:58:00", "remaining_time": "0:53:54", "throughput": 1031.97, "total_tokens": 3591752} {"current_steps": 39895, "total_steps": 76960, "loss": 0.2151, "lr": 2.7754357730252032e-05, "epoch": 10.367723492723492, "percentage": 51.84, "elapsed_time": "0:58:00", "remaining_time": "0:53:53", "throughput": 1031.98, "total_tokens": 3592216} {"current_steps": 39900, "total_steps": 76960, "loss": 0.2267, "lr": 2.7748722575734672e-05, "epoch": 10.369022869022869, "percentage": 51.85, "elapsed_time": "0:58:01", "remaining_time": "0:53:53", "throughput": 1031.98, "total_tokens": 3592632} {"current_steps": 39905, "total_steps": 76960, "loss": 0.4921, "lr": 2.7743087279847868e-05, "epoch": 10.370322245322246, "percentage": 51.85, "elapsed_time": "0:58:01", "remaining_time": "0:53:53", "throughput": 1031.99, "total_tokens": 3593096} {"current_steps": 39910, "total_steps": 76960, "loss": 0.1285, "lr": 2.7737451842881455e-05, "epoch": 10.371621621621621, "percentage": 51.86, "elapsed_time": "0:58:02", "remaining_time": "0:53:52", "throughput": 1031.99, "total_tokens": 3593544} {"current_steps": 39915, "total_steps": 76960, "loss": 0.2072, "lr": 2.7731816265125278e-05, "epoch": 10.372920997920998, "percentage": 51.86, "elapsed_time": "0:58:02", "remaining_time": "0:53:52", "throughput": 1032.0, "total_tokens": 3594008} {"current_steps": 39920, "total_steps": 76960, "loss": 0.2496, "lr": 2.7726180546869175e-05, "epoch": 10.374220374220375, "percentage": 51.87, "elapsed_time": "0:58:02", "remaining_time": "0:53:51", "throughput": 1032.01, "total_tokens": 3594472} {"current_steps": 39925, "total_steps": 76960, "loss": 0.3191, "lr": 2.772054468840299e-05, "epoch": 10.37551975051975, "percentage": 51.88, "elapsed_time": "0:58:03", "remaining_time": "0:53:51", "throughput": 1032.03, "total_tokens": 3594936} {"current_steps": 39930, "total_steps": 76960, "loss": 0.1985, "lr": 2.7714908690016583e-05, "epoch": 10.376819126819127, "percentage": 51.88, "elapsed_time": "0:58:03", "remaining_time": "0:53:50", "throughput": 1032.03, "total_tokens": 3595384} {"current_steps": 39935, "total_steps": 76960, "loss": 0.1316, "lr": 2.7709272551999828e-05, "epoch": 10.378118503118504, "percentage": 51.89, "elapsed_time": "0:58:04", "remaining_time": "0:53:50", "throughput": 1032.04, "total_tokens": 3595832} {"current_steps": 39940, "total_steps": 76960, "loss": 0.308, "lr": 2.770363627464258e-05, "epoch": 10.379417879417879, "percentage": 51.9, "elapsed_time": "0:58:04", "remaining_time": "0:53:49", "throughput": 1032.05, "total_tokens": 3596296} {"current_steps": 39945, "total_steps": 76960, "loss": 0.4267, "lr": 2.769799985823473e-05, "epoch": 10.380717255717256, "percentage": 51.9, "elapsed_time": "0:58:05", "remaining_time": "0:53:49", "throughput": 1032.06, "total_tokens": 3596776} {"current_steps": 39950, "total_steps": 76960, "loss": 0.2882, "lr": 2.7692363303066164e-05, "epoch": 10.382016632016631, "percentage": 51.91, "elapsed_time": "0:58:05", "remaining_time": "0:53:48", "throughput": 1032.07, "total_tokens": 3597224} {"current_steps": 39955, "total_steps": 76960, "loss": 0.3162, "lr": 2.7686726609426777e-05, "epoch": 10.383316008316008, "percentage": 51.92, "elapsed_time": "0:58:05", "remaining_time": "0:53:48", "throughput": 1032.07, "total_tokens": 3597672} {"current_steps": 39960, "total_steps": 76960, "loss": 0.3499, "lr": 2.7681089777606463e-05, "epoch": 10.384615384615385, "percentage": 51.92, "elapsed_time": "0:58:06", "remaining_time": "0:53:48", "throughput": 1032.09, "total_tokens": 3598152} {"current_steps": 39965, "total_steps": 76960, "loss": 0.2609, "lr": 2.767545280789513e-05, "epoch": 10.38591476091476, "percentage": 51.93, "elapsed_time": "0:58:06", "remaining_time": "0:53:47", "throughput": 1032.1, "total_tokens": 3598632} {"current_steps": 39970, "total_steps": 76960, "loss": 0.2317, "lr": 2.7669815700582697e-05, "epoch": 10.387214137214137, "percentage": 51.94, "elapsed_time": "0:58:07", "remaining_time": "0:53:47", "throughput": 1032.11, "total_tokens": 3599096} {"current_steps": 39975, "total_steps": 76960, "loss": 0.2412, "lr": 2.7664178455959087e-05, "epoch": 10.388513513513514, "percentage": 51.94, "elapsed_time": "0:58:07", "remaining_time": "0:53:46", "throughput": 1032.13, "total_tokens": 3599608} {"current_steps": 39980, "total_steps": 76960, "loss": 0.2779, "lr": 2.765854107431422e-05, "epoch": 10.38981288981289, "percentage": 51.95, "elapsed_time": "0:58:07", "remaining_time": "0:53:46", "throughput": 1032.14, "total_tokens": 3600040} {"current_steps": 39985, "total_steps": 76960, "loss": 0.2435, "lr": 2.765290355593805e-05, "epoch": 10.391112266112266, "percentage": 51.96, "elapsed_time": "0:58:08", "remaining_time": "0:53:45", "throughput": 1032.14, "total_tokens": 3600472} {"current_steps": 39990, "total_steps": 76960, "loss": 0.1922, "lr": 2.76472659011205e-05, "epoch": 10.392411642411643, "percentage": 51.96, "elapsed_time": "0:58:08", "remaining_time": "0:53:45", "throughput": 1032.14, "total_tokens": 3600920} {"current_steps": 39995, "total_steps": 76960, "loss": 0.3053, "lr": 2.764162811015153e-05, "epoch": 10.393711018711018, "percentage": 51.97, "elapsed_time": "0:58:09", "remaining_time": "0:53:44", "throughput": 1032.14, "total_tokens": 3601352} {"current_steps": 40000, "total_steps": 76960, "loss": 0.2197, "lr": 2.7635990183321098e-05, "epoch": 10.395010395010395, "percentage": 51.98, "elapsed_time": "0:58:09", "remaining_time": "0:53:44", "throughput": 1032.14, "total_tokens": 3601784} {"current_steps": 40005, "total_steps": 76960, "loss": 0.1517, "lr": 2.7630352120919162e-05, "epoch": 10.396309771309772, "percentage": 51.98, "elapsed_time": "0:58:10", "remaining_time": "0:53:43", "throughput": 1032.14, "total_tokens": 3602216} {"current_steps": 40010, "total_steps": 76960, "loss": 0.4249, "lr": 2.76247139232357e-05, "epoch": 10.397609147609147, "percentage": 51.99, "elapsed_time": "0:58:10", "remaining_time": "0:53:43", "throughput": 1032.15, "total_tokens": 3602664} {"current_steps": 40015, "total_steps": 76960, "loss": 0.1676, "lr": 2.7619075590560678e-05, "epoch": 10.398908523908524, "percentage": 51.99, "elapsed_time": "0:58:10", "remaining_time": "0:53:43", "throughput": 1032.16, "total_tokens": 3603128} {"current_steps": 40020, "total_steps": 76960, "loss": 0.3328, "lr": 2.7613437123184093e-05, "epoch": 10.4002079002079, "percentage": 52.0, "elapsed_time": "0:58:11", "remaining_time": "0:53:42", "throughput": 1032.16, "total_tokens": 3603576} {"current_steps": 40025, "total_steps": 76960, "loss": 0.2133, "lr": 2.7607798521395933e-05, "epoch": 10.401507276507276, "percentage": 52.01, "elapsed_time": "0:58:11", "remaining_time": "0:53:42", "throughput": 1032.17, "total_tokens": 3604024} {"current_steps": 40030, "total_steps": 76960, "loss": 0.349, "lr": 2.7602159785486198e-05, "epoch": 10.402806652806653, "percentage": 52.01, "elapsed_time": "0:58:12", "remaining_time": "0:53:41", "throughput": 1032.17, "total_tokens": 3604456} {"current_steps": 40035, "total_steps": 76960, "loss": 0.2853, "lr": 2.759652091574489e-05, "epoch": 10.404106029106028, "percentage": 52.02, "elapsed_time": "0:58:12", "remaining_time": "0:53:41", "throughput": 1032.18, "total_tokens": 3604904} {"current_steps": 40040, "total_steps": 76960, "loss": 0.4079, "lr": 2.7590881912462026e-05, "epoch": 10.405405405405405, "percentage": 52.03, "elapsed_time": "0:58:12", "remaining_time": "0:53:40", "throughput": 1032.19, "total_tokens": 3605384} {"current_steps": 40045, "total_steps": 76960, "loss": 0.5392, "lr": 2.7585242775927618e-05, "epoch": 10.406704781704782, "percentage": 52.03, "elapsed_time": "0:58:13", "remaining_time": "0:53:40", "throughput": 1032.21, "total_tokens": 3605880} {"current_steps": 40050, "total_steps": 76960, "loss": 0.355, "lr": 2.75796035064317e-05, "epoch": 10.408004158004157, "percentage": 52.04, "elapsed_time": "0:58:13", "remaining_time": "0:53:39", "throughput": 1032.22, "total_tokens": 3606344} {"current_steps": 40055, "total_steps": 76960, "loss": 0.2069, "lr": 2.75739641042643e-05, "epoch": 10.409303534303534, "percentage": 52.05, "elapsed_time": "0:58:14", "remaining_time": "0:53:39", "throughput": 1032.22, "total_tokens": 3606792} {"current_steps": 40060, "total_steps": 76960, "loss": 0.245, "lr": 2.7568324569715465e-05, "epoch": 10.410602910602911, "percentage": 52.05, "elapsed_time": "0:58:14", "remaining_time": "0:53:38", "throughput": 1032.23, "total_tokens": 3607224} {"current_steps": 40065, "total_steps": 76960, "loss": 0.2731, "lr": 2.7562684903075238e-05, "epoch": 10.411902286902286, "percentage": 52.06, "elapsed_time": "0:58:15", "remaining_time": "0:53:38", "throughput": 1032.23, "total_tokens": 3607672} {"current_steps": 40070, "total_steps": 76960, "loss": 0.3246, "lr": 2.7557045104633662e-05, "epoch": 10.413201663201663, "percentage": 52.07, "elapsed_time": "0:58:15", "remaining_time": "0:53:38", "throughput": 1032.23, "total_tokens": 3608104} {"current_steps": 40075, "total_steps": 76960, "loss": 0.3532, "lr": 2.7551405174680812e-05, "epoch": 10.41450103950104, "percentage": 52.07, "elapsed_time": "0:58:15", "remaining_time": "0:53:37", "throughput": 1032.24, "total_tokens": 3608552} {"current_steps": 40080, "total_steps": 76960, "loss": 0.2949, "lr": 2.7545765113506746e-05, "epoch": 10.415800415800415, "percentage": 52.08, "elapsed_time": "0:58:16", "remaining_time": "0:53:37", "throughput": 1032.24, "total_tokens": 3609000} {"current_steps": 40085, "total_steps": 76960, "loss": 0.2684, "lr": 2.7540124921401545e-05, "epoch": 10.417099792099792, "percentage": 52.09, "elapsed_time": "0:58:16", "remaining_time": "0:53:36", "throughput": 1032.25, "total_tokens": 3609464} {"current_steps": 40090, "total_steps": 76960, "loss": 0.3102, "lr": 2.7534484598655275e-05, "epoch": 10.41839916839917, "percentage": 52.09, "elapsed_time": "0:58:17", "remaining_time": "0:53:36", "throughput": 1032.26, "total_tokens": 3609912} {"current_steps": 40095, "total_steps": 76960, "loss": 0.3197, "lr": 2.7528844145558048e-05, "epoch": 10.419698544698544, "percentage": 52.1, "elapsed_time": "0:58:17", "remaining_time": "0:53:35", "throughput": 1032.27, "total_tokens": 3610376} {"current_steps": 40100, "total_steps": 76960, "loss": 0.2525, "lr": 2.7523203562399935e-05, "epoch": 10.420997920997921, "percentage": 52.1, "elapsed_time": "0:58:17", "remaining_time": "0:53:35", "throughput": 1032.28, "total_tokens": 3610856} {"current_steps": 40105, "total_steps": 76960, "loss": 0.1719, "lr": 2.7517562849471045e-05, "epoch": 10.422297297297296, "percentage": 52.11, "elapsed_time": "0:58:18", "remaining_time": "0:53:34", "throughput": 1032.3, "total_tokens": 3611336} {"current_steps": 40110, "total_steps": 76960, "loss": 0.2542, "lr": 2.7511922007061487e-05, "epoch": 10.423596673596673, "percentage": 52.12, "elapsed_time": "0:58:18", "remaining_time": "0:53:34", "throughput": 1032.31, "total_tokens": 3611800} {"current_steps": 40115, "total_steps": 76960, "loss": 0.1974, "lr": 2.750628103546138e-05, "epoch": 10.42489604989605, "percentage": 52.12, "elapsed_time": "0:58:19", "remaining_time": "0:53:33", "throughput": 1032.31, "total_tokens": 3612232} {"current_steps": 40120, "total_steps": 76960, "loss": 0.1648, "lr": 2.750063993496083e-05, "epoch": 10.426195426195425, "percentage": 52.13, "elapsed_time": "0:58:19", "remaining_time": "0:53:33", "throughput": 1032.32, "total_tokens": 3612712} {"current_steps": 40125, "total_steps": 76960, "loss": 0.0634, "lr": 2.7494998705849968e-05, "epoch": 10.427494802494802, "percentage": 52.14, "elapsed_time": "0:58:20", "remaining_time": "0:53:33", "throughput": 1032.32, "total_tokens": 3613144} {"current_steps": 40130, "total_steps": 76960, "loss": 0.1855, "lr": 2.748935734841895e-05, "epoch": 10.42879417879418, "percentage": 52.14, "elapsed_time": "0:58:20", "remaining_time": "0:53:32", "throughput": 1032.32, "total_tokens": 3613576} {"current_steps": 40135, "total_steps": 76960, "loss": 0.1173, "lr": 2.7483715862957882e-05, "epoch": 10.430093555093555, "percentage": 52.15, "elapsed_time": "0:58:20", "remaining_time": "0:53:32", "throughput": 1032.32, "total_tokens": 3614008} {"current_steps": 40140, "total_steps": 76960, "loss": 0.283, "lr": 2.747807424975693e-05, "epoch": 10.431392931392931, "percentage": 52.16, "elapsed_time": "0:58:21", "remaining_time": "0:53:31", "throughput": 1032.31, "total_tokens": 3614408} {"current_steps": 40145, "total_steps": 76960, "loss": 0.2391, "lr": 2.7472432509106248e-05, "epoch": 10.432692307692308, "percentage": 52.16, "elapsed_time": "0:58:21", "remaining_time": "0:53:31", "throughput": 1032.31, "total_tokens": 3614840} {"current_steps": 40150, "total_steps": 76960, "loss": 0.577, "lr": 2.7466790641295992e-05, "epoch": 10.433991683991684, "percentage": 52.17, "elapsed_time": "0:58:22", "remaining_time": "0:53:30", "throughput": 1032.33, "total_tokens": 3615320} {"current_steps": 40155, "total_steps": 76960, "loss": 0.2798, "lr": 2.746114864661633e-05, "epoch": 10.43529106029106, "percentage": 52.18, "elapsed_time": "0:58:22", "remaining_time": "0:53:30", "throughput": 1032.35, "total_tokens": 3615816} {"current_steps": 40160, "total_steps": 76960, "loss": 0.2722, "lr": 2.745550652535743e-05, "epoch": 10.436590436590437, "percentage": 52.18, "elapsed_time": "0:58:22", "remaining_time": "0:53:29", "throughput": 1032.34, "total_tokens": 3616216} {"current_steps": 40165, "total_steps": 76960, "loss": 0.3677, "lr": 2.7449864277809484e-05, "epoch": 10.437889812889813, "percentage": 52.19, "elapsed_time": "0:58:23", "remaining_time": "0:53:29", "throughput": 1032.35, "total_tokens": 3616680} {"current_steps": 40170, "total_steps": 76960, "loss": 0.0475, "lr": 2.744422190426267e-05, "epoch": 10.43918918918919, "percentage": 52.2, "elapsed_time": "0:58:23", "remaining_time": "0:53:28", "throughput": 1032.36, "total_tokens": 3617144} {"current_steps": 40175, "total_steps": 76960, "loss": 0.2816, "lr": 2.7438579405007182e-05, "epoch": 10.440488565488565, "percentage": 52.2, "elapsed_time": "0:58:24", "remaining_time": "0:53:28", "throughput": 1032.37, "total_tokens": 3617592} {"current_steps": 40180, "total_steps": 76960, "loss": 0.3022, "lr": 2.7432936780333214e-05, "epoch": 10.441787941787942, "percentage": 52.21, "elapsed_time": "0:58:24", "remaining_time": "0:53:28", "throughput": 1032.37, "total_tokens": 3618024} {"current_steps": 40185, "total_steps": 76960, "loss": 0.2083, "lr": 2.7427294030530975e-05, "epoch": 10.443087318087318, "percentage": 52.22, "elapsed_time": "0:58:25", "remaining_time": "0:53:27", "throughput": 1032.38, "total_tokens": 3618488} {"current_steps": 40190, "total_steps": 76960, "loss": 0.3186, "lr": 2.7421651155890686e-05, "epoch": 10.444386694386694, "percentage": 52.22, "elapsed_time": "0:58:25", "remaining_time": "0:53:27", "throughput": 1032.39, "total_tokens": 3618952} {"current_steps": 40195, "total_steps": 76960, "loss": 0.2679, "lr": 2.7416008156702554e-05, "epoch": 10.44568607068607, "percentage": 52.23, "elapsed_time": "0:58:25", "remaining_time": "0:53:26", "throughput": 1032.4, "total_tokens": 3619432} {"current_steps": 40200, "total_steps": 76960, "loss": 0.2762, "lr": 2.7410365033256806e-05, "epoch": 10.446985446985448, "percentage": 52.23, "elapsed_time": "0:58:26", "remaining_time": "0:53:26", "throughput": 1032.41, "total_tokens": 3619880} {"current_steps": 40205, "total_steps": 76960, "loss": 0.0446, "lr": 2.740472178584368e-05, "epoch": 10.448284823284823, "percentage": 52.24, "elapsed_time": "0:58:26", "remaining_time": "0:53:25", "throughput": 1032.41, "total_tokens": 3620312} {"current_steps": 40210, "total_steps": 76960, "loss": 0.1833, "lr": 2.7399078414753403e-05, "epoch": 10.4495841995842, "percentage": 52.25, "elapsed_time": "0:58:27", "remaining_time": "0:53:25", "throughput": 1032.42, "total_tokens": 3620792} {"current_steps": 40215, "total_steps": 76960, "loss": 0.434, "lr": 2.7393434920276222e-05, "epoch": 10.450883575883577, "percentage": 52.25, "elapsed_time": "0:58:27", "remaining_time": "0:53:24", "throughput": 1032.44, "total_tokens": 3621272} {"current_steps": 40220, "total_steps": 76960, "loss": 0.1287, "lr": 2.7387791302702397e-05, "epoch": 10.452182952182952, "percentage": 52.26, "elapsed_time": "0:58:27", "remaining_time": "0:53:24", "throughput": 1032.44, "total_tokens": 3621704} {"current_steps": 40225, "total_steps": 76960, "loss": 0.2505, "lr": 2.7382147562322174e-05, "epoch": 10.453482328482329, "percentage": 52.27, "elapsed_time": "0:58:28", "remaining_time": "0:53:23", "throughput": 1032.43, "total_tokens": 3622120} {"current_steps": 40230, "total_steps": 76960, "loss": 0.3978, "lr": 2.7376503699425814e-05, "epoch": 10.454781704781706, "percentage": 52.27, "elapsed_time": "0:58:28", "remaining_time": "0:53:23", "throughput": 1032.44, "total_tokens": 3622568} {"current_steps": 40235, "total_steps": 76960, "loss": 0.3312, "lr": 2.7370859714303603e-05, "epoch": 10.45608108108108, "percentage": 52.28, "elapsed_time": "0:58:29", "remaining_time": "0:53:23", "throughput": 1032.44, "total_tokens": 3623016} {"current_steps": 40240, "total_steps": 76960, "loss": 0.2838, "lr": 2.73652156072458e-05, "epoch": 10.457380457380458, "percentage": 52.29, "elapsed_time": "0:58:29", "remaining_time": "0:53:22", "throughput": 1032.44, "total_tokens": 3623432} {"current_steps": 40245, "total_steps": 76960, "loss": 0.1528, "lr": 2.7359571378542692e-05, "epoch": 10.458679833679835, "percentage": 52.29, "elapsed_time": "0:58:29", "remaining_time": "0:53:22", "throughput": 1032.44, "total_tokens": 3623848} {"current_steps": 40250, "total_steps": 76960, "loss": 0.3402, "lr": 2.735392702848456e-05, "epoch": 10.45997920997921, "percentage": 52.3, "elapsed_time": "0:58:30", "remaining_time": "0:53:21", "throughput": 1032.44, "total_tokens": 3624280} {"current_steps": 40255, "total_steps": 76960, "loss": 0.2808, "lr": 2.7348282557361714e-05, "epoch": 10.461278586278587, "percentage": 52.31, "elapsed_time": "0:58:30", "remaining_time": "0:53:21", "throughput": 1032.45, "total_tokens": 3624760} {"current_steps": 40260, "total_steps": 76960, "loss": 0.2138, "lr": 2.7342637965464453e-05, "epoch": 10.462577962577962, "percentage": 52.31, "elapsed_time": "0:58:31", "remaining_time": "0:53:20", "throughput": 1032.46, "total_tokens": 3625208} {"current_steps": 40265, "total_steps": 76960, "loss": 0.3023, "lr": 2.7336993253083064e-05, "epoch": 10.463877338877339, "percentage": 52.32, "elapsed_time": "0:58:31", "remaining_time": "0:53:20", "throughput": 1032.46, "total_tokens": 3625656} {"current_steps": 40270, "total_steps": 76960, "loss": 0.1717, "lr": 2.733134842050788e-05, "epoch": 10.465176715176716, "percentage": 52.33, "elapsed_time": "0:58:32", "remaining_time": "0:53:19", "throughput": 1032.47, "total_tokens": 3626136} {"current_steps": 40275, "total_steps": 76960, "loss": 0.3753, "lr": 2.7325703468029207e-05, "epoch": 10.46647609147609, "percentage": 52.33, "elapsed_time": "0:58:32", "remaining_time": "0:53:19", "throughput": 1032.48, "total_tokens": 3626568} {"current_steps": 40280, "total_steps": 76960, "loss": 0.2788, "lr": 2.732005839593738e-05, "epoch": 10.467775467775468, "percentage": 52.34, "elapsed_time": "0:58:32", "remaining_time": "0:53:18", "throughput": 1032.48, "total_tokens": 3627000} {"current_steps": 40285, "total_steps": 76960, "loss": 0.3395, "lr": 2.7314413204522725e-05, "epoch": 10.469074844074845, "percentage": 52.35, "elapsed_time": "0:58:33", "remaining_time": "0:53:18", "throughput": 1032.49, "total_tokens": 3627464} {"current_steps": 40290, "total_steps": 76960, "loss": 0.2258, "lr": 2.7308767894075583e-05, "epoch": 10.47037422037422, "percentage": 52.35, "elapsed_time": "0:58:33", "remaining_time": "0:53:18", "throughput": 1032.49, "total_tokens": 3627896} {"current_steps": 40295, "total_steps": 76960, "loss": 0.2142, "lr": 2.7303122464886298e-05, "epoch": 10.471673596673597, "percentage": 52.36, "elapsed_time": "0:58:34", "remaining_time": "0:53:17", "throughput": 1032.48, "total_tokens": 3628312} {"current_steps": 40300, "total_steps": 76960, "loss": 0.2094, "lr": 2.7297476917245214e-05, "epoch": 10.472972972972974, "percentage": 52.36, "elapsed_time": "0:58:34", "remaining_time": "0:53:17", "throughput": 1032.49, "total_tokens": 3628776} {"current_steps": 40305, "total_steps": 76960, "loss": 0.2018, "lr": 2.729183125144269e-05, "epoch": 10.474272349272349, "percentage": 52.37, "elapsed_time": "0:58:34", "remaining_time": "0:53:16", "throughput": 1032.5, "total_tokens": 3629224} {"current_steps": 40310, "total_steps": 76960, "loss": 0.224, "lr": 2.728618546776909e-05, "epoch": 10.475571725571726, "percentage": 52.38, "elapsed_time": "0:58:35", "remaining_time": "0:53:16", "throughput": 1032.52, "total_tokens": 3629720} {"current_steps": 40315, "total_steps": 76960, "loss": 0.2602, "lr": 2.7280539566514786e-05, "epoch": 10.476871101871103, "percentage": 52.38, "elapsed_time": "0:58:35", "remaining_time": "0:53:15", "throughput": 1032.53, "total_tokens": 3630200} {"current_steps": 40320, "total_steps": 76960, "loss": 0.2072, "lr": 2.7274893547970143e-05, "epoch": 10.478170478170478, "percentage": 52.39, "elapsed_time": "0:58:36", "remaining_time": "0:53:15", "throughput": 1032.55, "total_tokens": 3630680} {"current_steps": 40325, "total_steps": 76960, "loss": 0.082, "lr": 2.7269247412425548e-05, "epoch": 10.479469854469855, "percentage": 52.4, "elapsed_time": "0:58:36", "remaining_time": "0:53:14", "throughput": 1032.54, "total_tokens": 3631096} {"current_steps": 40330, "total_steps": 76960, "loss": 0.1127, "lr": 2.7263601160171376e-05, "epoch": 10.48076923076923, "percentage": 52.4, "elapsed_time": "0:58:37", "remaining_time": "0:53:14", "throughput": 1032.54, "total_tokens": 3631512} {"current_steps": 40335, "total_steps": 76960, "loss": 0.224, "lr": 2.7257954791498035e-05, "epoch": 10.482068607068607, "percentage": 52.41, "elapsed_time": "0:58:37", "remaining_time": "0:53:13", "throughput": 1032.54, "total_tokens": 3631960} {"current_steps": 40340, "total_steps": 76960, "loss": 0.2597, "lr": 2.725230830669591e-05, "epoch": 10.483367983367984, "percentage": 52.42, "elapsed_time": "0:58:37", "remaining_time": "0:53:13", "throughput": 1032.55, "total_tokens": 3632408} {"current_steps": 40345, "total_steps": 76960, "loss": 0.123, "lr": 2.7246661706055414e-05, "epoch": 10.484667359667359, "percentage": 52.42, "elapsed_time": "0:58:38", "remaining_time": "0:53:13", "throughput": 1032.55, "total_tokens": 3632840} {"current_steps": 40350, "total_steps": 76960, "loss": 0.2615, "lr": 2.724101498986695e-05, "epoch": 10.485966735966736, "percentage": 52.43, "elapsed_time": "0:58:38", "remaining_time": "0:53:12", "throughput": 1032.57, "total_tokens": 3633336} {"current_steps": 40355, "total_steps": 76960, "loss": 0.1473, "lr": 2.7235368158420944e-05, "epoch": 10.487266112266113, "percentage": 52.44, "elapsed_time": "0:58:39", "remaining_time": "0:53:12", "throughput": 1032.56, "total_tokens": 3633752} {"current_steps": 40360, "total_steps": 76960, "loss": 0.2258, "lr": 2.722972121200781e-05, "epoch": 10.488565488565488, "percentage": 52.44, "elapsed_time": "0:58:39", "remaining_time": "0:53:11", "throughput": 1032.59, "total_tokens": 3634264} {"current_steps": 40365, "total_steps": 76960, "loss": 0.2693, "lr": 2.722407415091798e-05, "epoch": 10.489864864864865, "percentage": 52.45, "elapsed_time": "0:58:39", "remaining_time": "0:53:11", "throughput": 1032.59, "total_tokens": 3634696} {"current_steps": 40370, "total_steps": 76960, "loss": 0.1165, "lr": 2.721842697544188e-05, "epoch": 10.491164241164242, "percentage": 52.46, "elapsed_time": "0:58:40", "remaining_time": "0:53:10", "throughput": 1032.59, "total_tokens": 3635128} {"current_steps": 40375, "total_steps": 76960, "loss": 0.4143, "lr": 2.7212779685869954e-05, "epoch": 10.492463617463617, "percentage": 52.46, "elapsed_time": "0:58:40", "remaining_time": "0:53:10", "throughput": 1032.59, "total_tokens": 3635560} {"current_steps": 40380, "total_steps": 76960, "loss": 0.3102, "lr": 2.7207132282492654e-05, "epoch": 10.493762993762994, "percentage": 52.47, "elapsed_time": "0:58:41", "remaining_time": "0:53:09", "throughput": 1032.6, "total_tokens": 3636008} {"current_steps": 40385, "total_steps": 76960, "loss": 0.259, "lr": 2.7201484765600426e-05, "epoch": 10.49506237006237, "percentage": 52.48, "elapsed_time": "0:58:41", "remaining_time": "0:53:09", "throughput": 1032.61, "total_tokens": 3636472} {"current_steps": 40390, "total_steps": 76960, "loss": 0.3151, "lr": 2.7195837135483726e-05, "epoch": 10.496361746361746, "percentage": 52.48, "elapsed_time": "0:58:42", "remaining_time": "0:53:08", "throughput": 1032.61, "total_tokens": 3636904} {"current_steps": 40395, "total_steps": 76960, "loss": 0.1473, "lr": 2.719018939243302e-05, "epoch": 10.497661122661123, "percentage": 52.49, "elapsed_time": "0:58:42", "remaining_time": "0:53:08", "throughput": 1032.62, "total_tokens": 3637368} {"current_steps": 40400, "total_steps": 76960, "loss": 0.2228, "lr": 2.7184541536738774e-05, "epoch": 10.4989604989605, "percentage": 52.49, "elapsed_time": "0:58:42", "remaining_time": "0:53:08", "throughput": 1032.64, "total_tokens": 3637864} {"current_steps": 40405, "total_steps": 76960, "loss": 0.3947, "lr": 2.717889356869146e-05, "epoch": 10.500259875259875, "percentage": 52.5, "elapsed_time": "0:58:43", "remaining_time": "0:53:07", "throughput": 1032.66, "total_tokens": 3638376} {"current_steps": 40410, "total_steps": 76960, "loss": 0.1808, "lr": 2.7173245488581563e-05, "epoch": 10.501559251559252, "percentage": 52.51, "elapsed_time": "0:58:43", "remaining_time": "0:53:07", "throughput": 1032.66, "total_tokens": 3638808} {"current_steps": 40415, "total_steps": 76960, "loss": 0.3146, "lr": 2.7167597296699564e-05, "epoch": 10.502858627858627, "percentage": 52.51, "elapsed_time": "0:58:44", "remaining_time": "0:53:06", "throughput": 1032.66, "total_tokens": 3639224} {"current_steps": 40420, "total_steps": 76960, "loss": 0.1709, "lr": 2.7161948993335967e-05, "epoch": 10.504158004158004, "percentage": 52.52, "elapsed_time": "0:58:44", "remaining_time": "0:53:06", "throughput": 1032.67, "total_tokens": 3639704} {"current_steps": 40425, "total_steps": 76960, "loss": 0.1664, "lr": 2.715630057878126e-05, "epoch": 10.505457380457381, "percentage": 52.53, "elapsed_time": "0:58:44", "remaining_time": "0:53:05", "throughput": 1032.67, "total_tokens": 3640152} {"current_steps": 40430, "total_steps": 76960, "loss": 0.1819, "lr": 2.715065205332594e-05, "epoch": 10.506756756756756, "percentage": 52.53, "elapsed_time": "0:58:45", "remaining_time": "0:53:05", "throughput": 1032.69, "total_tokens": 3640632} {"current_steps": 40435, "total_steps": 76960, "loss": 0.1764, "lr": 2.714500341726054e-05, "epoch": 10.508056133056133, "percentage": 52.54, "elapsed_time": "0:58:45", "remaining_time": "0:53:04", "throughput": 1032.7, "total_tokens": 3641112} {"current_steps": 40440, "total_steps": 76960, "loss": 0.2399, "lr": 2.713935467087555e-05, "epoch": 10.50935550935551, "percentage": 52.55, "elapsed_time": "0:58:46", "remaining_time": "0:53:04", "throughput": 1032.7, "total_tokens": 3641528} {"current_steps": 40445, "total_steps": 76960, "loss": 0.3204, "lr": 2.7133705814461503e-05, "epoch": 10.510654885654885, "percentage": 52.55, "elapsed_time": "0:58:46", "remaining_time": "0:53:03", "throughput": 1032.7, "total_tokens": 3641976} {"current_steps": 40450, "total_steps": 76960, "loss": 0.235, "lr": 2.7128056848308913e-05, "epoch": 10.511954261954262, "percentage": 52.56, "elapsed_time": "0:58:47", "remaining_time": "0:53:03", "throughput": 1032.72, "total_tokens": 3642456} {"current_steps": 40455, "total_steps": 76960, "loss": 0.3597, "lr": 2.712240777270833e-05, "epoch": 10.513253638253639, "percentage": 52.57, "elapsed_time": "0:58:47", "remaining_time": "0:53:03", "throughput": 1032.72, "total_tokens": 3642904} {"current_steps": 40460, "total_steps": 76960, "loss": 0.2797, "lr": 2.711675858795028e-05, "epoch": 10.514553014553014, "percentage": 52.57, "elapsed_time": "0:58:47", "remaining_time": "0:53:02", "throughput": 1032.72, "total_tokens": 3643336} {"current_steps": 40465, "total_steps": 76960, "loss": 0.2541, "lr": 2.7111109294325297e-05, "epoch": 10.515852390852391, "percentage": 52.58, "elapsed_time": "0:58:48", "remaining_time": "0:53:02", "throughput": 1032.72, "total_tokens": 3643768} {"current_steps": 40470, "total_steps": 76960, "loss": 0.075, "lr": 2.710545989212395e-05, "epoch": 10.517151767151766, "percentage": 52.59, "elapsed_time": "0:58:48", "remaining_time": "0:53:01", "throughput": 1032.74, "total_tokens": 3644264} {"current_steps": 40475, "total_steps": 76960, "loss": 0.338, "lr": 2.7099810381636788e-05, "epoch": 10.518451143451143, "percentage": 52.59, "elapsed_time": "0:58:49", "remaining_time": "0:53:01", "throughput": 1032.74, "total_tokens": 3644680} {"current_steps": 40480, "total_steps": 76960, "loss": 0.3043, "lr": 2.7094160763154354e-05, "epoch": 10.51975051975052, "percentage": 52.6, "elapsed_time": "0:58:49", "remaining_time": "0:53:00", "throughput": 1032.75, "total_tokens": 3645160} {"current_steps": 40485, "total_steps": 76960, "loss": 0.2052, "lr": 2.7088511036967235e-05, "epoch": 10.521049896049895, "percentage": 52.61, "elapsed_time": "0:58:49", "remaining_time": "0:53:00", "throughput": 1032.75, "total_tokens": 3645592} {"current_steps": 40490, "total_steps": 76960, "loss": 0.2031, "lr": 2.7082861203365988e-05, "epoch": 10.522349272349272, "percentage": 52.61, "elapsed_time": "0:58:50", "remaining_time": "0:52:59", "throughput": 1032.77, "total_tokens": 3646072} {"current_steps": 40495, "total_steps": 76960, "loss": 0.2252, "lr": 2.7077211262641196e-05, "epoch": 10.52364864864865, "percentage": 52.62, "elapsed_time": "0:58:50", "remaining_time": "0:52:59", "throughput": 1032.78, "total_tokens": 3646536} {"current_steps": 40500, "total_steps": 76960, "loss": 0.1557, "lr": 2.707156121508343e-05, "epoch": 10.524948024948024, "percentage": 52.62, "elapsed_time": "0:58:51", "remaining_time": "0:52:58", "throughput": 1032.79, "total_tokens": 3647016} {"current_steps": 40505, "total_steps": 76960, "loss": 0.3606, "lr": 2.7065911060983297e-05, "epoch": 10.526247401247401, "percentage": 52.63, "elapsed_time": "0:58:51", "remaining_time": "0:52:58", "throughput": 1032.81, "total_tokens": 3647496} {"current_steps": 40510, "total_steps": 76960, "loss": 0.195, "lr": 2.706026080063137e-05, "epoch": 10.527546777546778, "percentage": 52.64, "elapsed_time": "0:58:52", "remaining_time": "0:52:58", "throughput": 1032.81, "total_tokens": 3647928} {"current_steps": 40515, "total_steps": 76960, "loss": 0.2217, "lr": 2.7054610434318262e-05, "epoch": 10.528846153846153, "percentage": 52.64, "elapsed_time": "0:58:52", "remaining_time": "0:52:57", "throughput": 1032.82, "total_tokens": 3648408} {"current_steps": 40520, "total_steps": 76960, "loss": 0.1743, "lr": 2.7048959962334568e-05, "epoch": 10.53014553014553, "percentage": 52.65, "elapsed_time": "0:58:52", "remaining_time": "0:52:57", "throughput": 1032.83, "total_tokens": 3648856} {"current_steps": 40525, "total_steps": 76960, "loss": 0.1204, "lr": 2.7043309384970905e-05, "epoch": 10.531444906444907, "percentage": 52.66, "elapsed_time": "0:58:53", "remaining_time": "0:52:56", "throughput": 1032.84, "total_tokens": 3649336} {"current_steps": 40530, "total_steps": 76960, "loss": 0.237, "lr": 2.7037658702517883e-05, "epoch": 10.532744282744282, "percentage": 52.66, "elapsed_time": "0:58:53", "remaining_time": "0:52:56", "throughput": 1032.85, "total_tokens": 3649800} {"current_steps": 40535, "total_steps": 76960, "loss": 0.1738, "lr": 2.703200791526611e-05, "epoch": 10.53404365904366, "percentage": 52.67, "elapsed_time": "0:58:54", "remaining_time": "0:52:55", "throughput": 1032.85, "total_tokens": 3650232} {"current_steps": 40540, "total_steps": 76960, "loss": 0.4854, "lr": 2.7026357023506233e-05, "epoch": 10.535343035343036, "percentage": 52.68, "elapsed_time": "0:58:54", "remaining_time": "0:52:55", "throughput": 1032.85, "total_tokens": 3650664} {"current_steps": 40545, "total_steps": 76960, "loss": 0.2885, "lr": 2.702070602752887e-05, "epoch": 10.536642411642411, "percentage": 52.68, "elapsed_time": "0:58:54", "remaining_time": "0:52:54", "throughput": 1032.85, "total_tokens": 3651096} {"current_steps": 40550, "total_steps": 76960, "loss": 0.149, "lr": 2.7015054927624662e-05, "epoch": 10.537941787941788, "percentage": 52.69, "elapsed_time": "0:58:55", "remaining_time": "0:52:54", "throughput": 1032.85, "total_tokens": 3651528} {"current_steps": 40555, "total_steps": 76960, "loss": 0.1958, "lr": 2.7009403724084235e-05, "epoch": 10.539241164241163, "percentage": 52.7, "elapsed_time": "0:58:55", "remaining_time": "0:52:53", "throughput": 1032.86, "total_tokens": 3651992} {"current_steps": 40560, "total_steps": 76960, "loss": 0.5054, "lr": 2.7003752417198264e-05, "epoch": 10.54054054054054, "percentage": 52.7, "elapsed_time": "0:58:56", "remaining_time": "0:52:53", "throughput": 1032.88, "total_tokens": 3652472} {"current_steps": 40565, "total_steps": 76960, "loss": 0.2722, "lr": 2.6998101007257383e-05, "epoch": 10.541839916839917, "percentage": 52.71, "elapsed_time": "0:58:56", "remaining_time": "0:52:53", "throughput": 1032.88, "total_tokens": 3652904} {"current_steps": 40570, "total_steps": 76960, "loss": 0.1384, "lr": 2.699244949455225e-05, "epoch": 10.543139293139292, "percentage": 52.72, "elapsed_time": "0:58:57", "remaining_time": "0:52:52", "throughput": 1032.88, "total_tokens": 3653336} {"current_steps": 40575, "total_steps": 76960, "loss": 0.2026, "lr": 2.698679787937353e-05, "epoch": 10.54443866943867, "percentage": 52.72, "elapsed_time": "0:58:57", "remaining_time": "0:52:52", "throughput": 1032.89, "total_tokens": 3653800} {"current_steps": 40580, "total_steps": 76960, "loss": 0.1962, "lr": 2.6981146162011894e-05, "epoch": 10.545738045738046, "percentage": 52.73, "elapsed_time": "0:58:57", "remaining_time": "0:52:51", "throughput": 1032.89, "total_tokens": 3654248} {"current_steps": 40585, "total_steps": 76960, "loss": 0.1799, "lr": 2.6975494342758025e-05, "epoch": 10.547037422037421, "percentage": 52.74, "elapsed_time": "0:58:58", "remaining_time": "0:52:51", "throughput": 1032.89, "total_tokens": 3654680} {"current_steps": 40590, "total_steps": 76960, "loss": 0.2132, "lr": 2.696984242190257e-05, "epoch": 10.548336798336798, "percentage": 52.74, "elapsed_time": "0:58:58", "remaining_time": "0:52:50", "throughput": 1032.9, "total_tokens": 3655144} {"current_steps": 40595, "total_steps": 76960, "loss": 0.3562, "lr": 2.6964190399736238e-05, "epoch": 10.549636174636175, "percentage": 52.75, "elapsed_time": "0:58:59", "remaining_time": "0:52:50", "throughput": 1032.91, "total_tokens": 3655608} {"current_steps": 40600, "total_steps": 76960, "loss": 0.3391, "lr": 2.695853827654971e-05, "epoch": 10.55093555093555, "percentage": 52.75, "elapsed_time": "0:58:59", "remaining_time": "0:52:49", "throughput": 1032.91, "total_tokens": 3656024} {"current_steps": 40605, "total_steps": 76960, "loss": 0.58, "lr": 2.695288605263368e-05, "epoch": 10.552234927234927, "percentage": 52.76, "elapsed_time": "0:58:59", "remaining_time": "0:52:49", "throughput": 1032.92, "total_tokens": 3656488} {"current_steps": 40610, "total_steps": 76960, "loss": 0.3303, "lr": 2.6947233728278852e-05, "epoch": 10.553534303534304, "percentage": 52.77, "elapsed_time": "0:59:00", "remaining_time": "0:52:48", "throughput": 1032.91, "total_tokens": 3656904} {"current_steps": 40615, "total_steps": 76960, "loss": 0.4617, "lr": 2.694158130377593e-05, "epoch": 10.55483367983368, "percentage": 52.77, "elapsed_time": "0:59:00", "remaining_time": "0:52:48", "throughput": 1032.91, "total_tokens": 3657336} {"current_steps": 40620, "total_steps": 76960, "loss": 0.3564, "lr": 2.6935928779415626e-05, "epoch": 10.556133056133056, "percentage": 52.78, "elapsed_time": "0:59:01", "remaining_time": "0:52:48", "throughput": 1032.92, "total_tokens": 3657800} {"current_steps": 40625, "total_steps": 76960, "loss": 0.3424, "lr": 2.693027615548864e-05, "epoch": 10.557432432432432, "percentage": 52.79, "elapsed_time": "0:59:01", "remaining_time": "0:52:47", "throughput": 1032.93, "total_tokens": 3658264} {"current_steps": 40630, "total_steps": 76960, "loss": 0.3312, "lr": 2.6924623432285707e-05, "epoch": 10.558731808731808, "percentage": 52.79, "elapsed_time": "0:59:02", "remaining_time": "0:52:47", "throughput": 1032.94, "total_tokens": 3658712} {"current_steps": 40635, "total_steps": 76960, "loss": 0.2136, "lr": 2.6918970610097543e-05, "epoch": 10.560031185031185, "percentage": 52.8, "elapsed_time": "0:59:02", "remaining_time": "0:52:46", "throughput": 1032.95, "total_tokens": 3659176} {"current_steps": 40640, "total_steps": 76960, "loss": 0.2753, "lr": 2.691331768921489e-05, "epoch": 10.56133056133056, "percentage": 52.81, "elapsed_time": "0:59:02", "remaining_time": "0:52:46", "throughput": 1032.95, "total_tokens": 3659608} {"current_steps": 40645, "total_steps": 76960, "loss": 0.2391, "lr": 2.6907664669928463e-05, "epoch": 10.562629937629938, "percentage": 52.81, "elapsed_time": "0:59:03", "remaining_time": "0:52:45", "throughput": 1032.94, "total_tokens": 3660024} {"current_steps": 40650, "total_steps": 76960, "loss": 0.2633, "lr": 2.690201155252903e-05, "epoch": 10.563929313929314, "percentage": 52.82, "elapsed_time": "0:59:03", "remaining_time": "0:52:45", "throughput": 1032.96, "total_tokens": 3660520} {"current_steps": 40655, "total_steps": 76960, "loss": 0.2373, "lr": 2.689635833730731e-05, "epoch": 10.56522869022869, "percentage": 52.83, "elapsed_time": "0:59:04", "remaining_time": "0:52:44", "throughput": 1032.96, "total_tokens": 3660952} {"current_steps": 40660, "total_steps": 76960, "loss": 0.1764, "lr": 2.689070502455406e-05, "epoch": 10.566528066528067, "percentage": 52.83, "elapsed_time": "0:59:04", "remaining_time": "0:52:44", "throughput": 1032.96, "total_tokens": 3661384} {"current_steps": 40665, "total_steps": 76960, "loss": 0.3138, "lr": 2.6885051614560042e-05, "epoch": 10.567827442827443, "percentage": 52.84, "elapsed_time": "0:59:04", "remaining_time": "0:52:44", "throughput": 1032.96, "total_tokens": 3661800} {"current_steps": 40670, "total_steps": 76960, "loss": 0.4197, "lr": 2.6879398107616017e-05, "epoch": 10.569126819126819, "percentage": 52.85, "elapsed_time": "0:59:05", "remaining_time": "0:52:43", "throughput": 1032.96, "total_tokens": 3662232} {"current_steps": 40675, "total_steps": 76960, "loss": 0.2777, "lr": 2.6873744504012742e-05, "epoch": 10.570426195426196, "percentage": 52.85, "elapsed_time": "0:59:05", "remaining_time": "0:52:43", "throughput": 1032.98, "total_tokens": 3662712} {"current_steps": 40680, "total_steps": 76960, "loss": 0.2755, "lr": 2.6868090804040998e-05, "epoch": 10.571725571725572, "percentage": 52.86, "elapsed_time": "0:59:06", "remaining_time": "0:52:42", "throughput": 1032.98, "total_tokens": 3663144} {"current_steps": 40685, "total_steps": 76960, "loss": 0.2467, "lr": 2.686243700799155e-05, "epoch": 10.573024948024948, "percentage": 52.87, "elapsed_time": "0:59:06", "remaining_time": "0:52:42", "throughput": 1032.98, "total_tokens": 3663592} {"current_steps": 40690, "total_steps": 76960, "loss": 0.1522, "lr": 2.6856783116155183e-05, "epoch": 10.574324324324325, "percentage": 52.87, "elapsed_time": "0:59:07", "remaining_time": "0:52:41", "throughput": 1032.99, "total_tokens": 3664040} {"current_steps": 40695, "total_steps": 76960, "loss": 0.244, "lr": 2.6851129128822677e-05, "epoch": 10.575623700623701, "percentage": 52.88, "elapsed_time": "0:59:07", "remaining_time": "0:52:41", "throughput": 1032.98, "total_tokens": 3664456} {"current_steps": 40700, "total_steps": 76960, "loss": 0.1941, "lr": 2.684547504628483e-05, "epoch": 10.576923076923077, "percentage": 52.88, "elapsed_time": "0:59:07", "remaining_time": "0:52:40", "throughput": 1032.98, "total_tokens": 3664888} {"current_steps": 40705, "total_steps": 76960, "loss": 0.2017, "lr": 2.6839820868832433e-05, "epoch": 10.578222453222454, "percentage": 52.89, "elapsed_time": "0:59:08", "remaining_time": "0:52:40", "throughput": 1032.98, "total_tokens": 3665320} {"current_steps": 40710, "total_steps": 76960, "loss": 0.2896, "lr": 2.683416659675629e-05, "epoch": 10.579521829521829, "percentage": 52.9, "elapsed_time": "0:59:08", "remaining_time": "0:52:39", "throughput": 1032.99, "total_tokens": 3665784} {"current_steps": 40715, "total_steps": 76960, "loss": 0.3017, "lr": 2.6828512230347197e-05, "epoch": 10.580821205821206, "percentage": 52.9, "elapsed_time": "0:59:09", "remaining_time": "0:52:39", "throughput": 1032.99, "total_tokens": 3666216} {"current_steps": 40720, "total_steps": 76960, "loss": 0.3085, "lr": 2.682285776989597e-05, "epoch": 10.582120582120583, "percentage": 52.91, "elapsed_time": "0:59:09", "remaining_time": "0:52:39", "throughput": 1033.02, "total_tokens": 3666728} {"current_steps": 40725, "total_steps": 76960, "loss": 0.354, "lr": 2.681720321569342e-05, "epoch": 10.583419958419958, "percentage": 52.92, "elapsed_time": "0:59:09", "remaining_time": "0:52:38", "throughput": 1033.02, "total_tokens": 3667176} {"current_steps": 40730, "total_steps": 76960, "loss": 0.3543, "lr": 2.6811548568030364e-05, "epoch": 10.584719334719335, "percentage": 52.92, "elapsed_time": "0:59:10", "remaining_time": "0:52:38", "throughput": 1033.03, "total_tokens": 3667640} {"current_steps": 40735, "total_steps": 76960, "loss": 0.2519, "lr": 2.6805893827197632e-05, "epoch": 10.586018711018712, "percentage": 52.93, "elapsed_time": "0:59:10", "remaining_time": "0:52:37", "throughput": 1033.04, "total_tokens": 3668104} {"current_steps": 40740, "total_steps": 76960, "loss": 0.2869, "lr": 2.680023899348605e-05, "epoch": 10.587318087318087, "percentage": 52.94, "elapsed_time": "0:59:11", "remaining_time": "0:52:37", "throughput": 1033.06, "total_tokens": 3668584} {"current_steps": 40745, "total_steps": 76960, "loss": 0.2221, "lr": 2.6794584067186456e-05, "epoch": 10.588617463617464, "percentage": 52.94, "elapsed_time": "0:59:11", "remaining_time": "0:52:36", "throughput": 1033.06, "total_tokens": 3669016} {"current_steps": 40750, "total_steps": 76960, "loss": 0.2584, "lr": 2.6788929048589672e-05, "epoch": 10.58991683991684, "percentage": 52.95, "elapsed_time": "0:59:12", "remaining_time": "0:52:36", "throughput": 1033.07, "total_tokens": 3669480} {"current_steps": 40755, "total_steps": 76960, "loss": 0.1872, "lr": 2.6783273937986563e-05, "epoch": 10.591216216216216, "percentage": 52.96, "elapsed_time": "0:59:12", "remaining_time": "0:52:35", "throughput": 1033.07, "total_tokens": 3669928} {"current_steps": 40760, "total_steps": 76960, "loss": 0.1528, "lr": 2.677761873566797e-05, "epoch": 10.592515592515593, "percentage": 52.96, "elapsed_time": "0:59:12", "remaining_time": "0:52:35", "throughput": 1033.08, "total_tokens": 3670392} {"current_steps": 40765, "total_steps": 76960, "loss": 0.2749, "lr": 2.6771963441924735e-05, "epoch": 10.59381496881497, "percentage": 52.97, "elapsed_time": "0:59:13", "remaining_time": "0:52:34", "throughput": 1033.09, "total_tokens": 3670856} {"current_steps": 40770, "total_steps": 76960, "loss": 0.3316, "lr": 2.6766308057047723e-05, "epoch": 10.595114345114345, "percentage": 52.98, "elapsed_time": "0:59:13", "remaining_time": "0:52:34", "throughput": 1033.1, "total_tokens": 3671336} {"current_steps": 40775, "total_steps": 76960, "loss": 0.3921, "lr": 2.67606525813278e-05, "epoch": 10.596413721413722, "percentage": 52.98, "elapsed_time": "0:59:14", "remaining_time": "0:52:34", "throughput": 1033.11, "total_tokens": 3671784} {"current_steps": 40780, "total_steps": 76960, "loss": 0.2873, "lr": 2.6754997015055827e-05, "epoch": 10.597713097713097, "percentage": 52.99, "elapsed_time": "0:59:14", "remaining_time": "0:52:33", "throughput": 1033.11, "total_tokens": 3672216} {"current_steps": 40785, "total_steps": 76960, "loss": 0.1295, "lr": 2.6749341358522674e-05, "epoch": 10.599012474012474, "percentage": 53.0, "elapsed_time": "0:59:14", "remaining_time": "0:52:33", "throughput": 1033.12, "total_tokens": 3672696} {"current_steps": 40790, "total_steps": 76960, "loss": 0.279, "lr": 2.6743685612019216e-05, "epoch": 10.60031185031185, "percentage": 53.0, "elapsed_time": "0:59:15", "remaining_time": "0:52:32", "throughput": 1033.12, "total_tokens": 3673112} {"current_steps": 40795, "total_steps": 76960, "loss": 0.3699, "lr": 2.673802977583634e-05, "epoch": 10.601611226611226, "percentage": 53.01, "elapsed_time": "0:59:15", "remaining_time": "0:52:32", "throughput": 1033.13, "total_tokens": 3673592} {"current_steps": 40800, "total_steps": 76960, "loss": 0.2096, "lr": 2.673237385026493e-05, "epoch": 10.602910602910603, "percentage": 53.01, "elapsed_time": "0:59:16", "remaining_time": "0:52:31", "throughput": 1033.13, "total_tokens": 3674024} {"current_steps": 40805, "total_steps": 76960, "loss": 0.1733, "lr": 2.672671783559586e-05, "epoch": 10.60420997920998, "percentage": 53.02, "elapsed_time": "0:59:16", "remaining_time": "0:52:31", "throughput": 1033.15, "total_tokens": 3674504} {"current_steps": 40810, "total_steps": 76960, "loss": 0.1608, "lr": 2.672106173212005e-05, "epoch": 10.605509355509355, "percentage": 53.03, "elapsed_time": "0:59:17", "remaining_time": "0:52:30", "throughput": 1033.16, "total_tokens": 3674968} {"current_steps": 40815, "total_steps": 76960, "loss": 0.2907, "lr": 2.6715405540128386e-05, "epoch": 10.606808731808732, "percentage": 53.03, "elapsed_time": "0:59:17", "remaining_time": "0:52:30", "throughput": 1033.15, "total_tokens": 3675384} {"current_steps": 40820, "total_steps": 76960, "loss": 0.3663, "lr": 2.6709749259911765e-05, "epoch": 10.608108108108109, "percentage": 53.04, "elapsed_time": "0:59:17", "remaining_time": "0:52:29", "throughput": 1033.15, "total_tokens": 3675816} {"current_steps": 40825, "total_steps": 76960, "loss": 0.4187, "lr": 2.67040928917611e-05, "epoch": 10.609407484407484, "percentage": 53.05, "elapsed_time": "0:59:18", "remaining_time": "0:52:29", "throughput": 1033.16, "total_tokens": 3676280} {"current_steps": 40830, "total_steps": 76960, "loss": 0.3244, "lr": 2.6698436435967313e-05, "epoch": 10.61070686070686, "percentage": 53.05, "elapsed_time": "0:59:18", "remaining_time": "0:52:29", "throughput": 1033.16, "total_tokens": 3676712} {"current_steps": 40835, "total_steps": 76960, "loss": 0.1941, "lr": 2.6692779892821308e-05, "epoch": 10.612006237006238, "percentage": 53.06, "elapsed_time": "0:59:19", "remaining_time": "0:52:28", "throughput": 1033.17, "total_tokens": 3677160} {"current_steps": 40840, "total_steps": 76960, "loss": 0.2865, "lr": 2.6687123262614007e-05, "epoch": 10.613305613305613, "percentage": 53.07, "elapsed_time": "0:59:19", "remaining_time": "0:52:28", "throughput": 1033.18, "total_tokens": 3677640} {"current_steps": 40845, "total_steps": 76960, "loss": 0.2472, "lr": 2.6681466545636353e-05, "epoch": 10.61460498960499, "percentage": 53.07, "elapsed_time": "0:59:19", "remaining_time": "0:52:27", "throughput": 1033.19, "total_tokens": 3678088} {"current_steps": 40850, "total_steps": 76960, "loss": 0.3439, "lr": 2.6675809742179255e-05, "epoch": 10.615904365904367, "percentage": 53.08, "elapsed_time": "0:59:20", "remaining_time": "0:52:27", "throughput": 1033.19, "total_tokens": 3678520} {"current_steps": 40855, "total_steps": 76960, "loss": 0.3742, "lr": 2.6670152852533653e-05, "epoch": 10.617203742203742, "percentage": 53.09, "elapsed_time": "0:59:20", "remaining_time": "0:52:26", "throughput": 1033.2, "total_tokens": 3678984} {"current_steps": 40860, "total_steps": 76960, "loss": 0.3302, "lr": 2.666449587699049e-05, "epoch": 10.618503118503119, "percentage": 53.09, "elapsed_time": "0:59:21", "remaining_time": "0:52:26", "throughput": 1033.21, "total_tokens": 3679448} {"current_steps": 40865, "total_steps": 76960, "loss": 0.2538, "lr": 2.665883881584072e-05, "epoch": 10.619802494802494, "percentage": 53.1, "elapsed_time": "0:59:21", "remaining_time": "0:52:25", "throughput": 1033.21, "total_tokens": 3679896} {"current_steps": 40870, "total_steps": 76960, "loss": 0.1979, "lr": 2.665318166937527e-05, "epoch": 10.621101871101871, "percentage": 53.11, "elapsed_time": "0:59:22", "remaining_time": "0:52:25", "throughput": 1033.22, "total_tokens": 3680328} {"current_steps": 40875, "total_steps": 76960, "loss": 0.1496, "lr": 2.66475244378851e-05, "epoch": 10.622401247401248, "percentage": 53.11, "elapsed_time": "0:59:22", "remaining_time": "0:52:24", "throughput": 1033.22, "total_tokens": 3680776} {"current_steps": 40880, "total_steps": 76960, "loss": 0.2246, "lr": 2.6641867121661178e-05, "epoch": 10.623700623700623, "percentage": 53.12, "elapsed_time": "0:59:22", "remaining_time": "0:52:24", "throughput": 1033.23, "total_tokens": 3681240} {"current_steps": 40885, "total_steps": 76960, "loss": 0.196, "lr": 2.6636209720994454e-05, "epoch": 10.625, "percentage": 53.12, "elapsed_time": "0:59:23", "remaining_time": "0:52:24", "throughput": 1033.23, "total_tokens": 3681672} {"current_steps": 40890, "total_steps": 76960, "loss": 0.1787, "lr": 2.6630552236175897e-05, "epoch": 10.626299376299377, "percentage": 53.13, "elapsed_time": "0:59:23", "remaining_time": "0:52:23", "throughput": 1033.25, "total_tokens": 3682168} {"current_steps": 40895, "total_steps": 76960, "loss": 0.1191, "lr": 2.6624894667496474e-05, "epoch": 10.627598752598752, "percentage": 53.14, "elapsed_time": "0:59:24", "remaining_time": "0:52:23", "throughput": 1033.26, "total_tokens": 3682616} {"current_steps": 40900, "total_steps": 76960, "loss": 0.2493, "lr": 2.661923701524716e-05, "epoch": 10.628898128898129, "percentage": 53.14, "elapsed_time": "0:59:24", "remaining_time": "0:52:22", "throughput": 1033.27, "total_tokens": 3683112} {"current_steps": 40905, "total_steps": 76960, "loss": 0.485, "lr": 2.661357927971894e-05, "epoch": 10.630197505197506, "percentage": 53.15, "elapsed_time": "0:59:24", "remaining_time": "0:52:22", "throughput": 1033.28, "total_tokens": 3683560} {"current_steps": 40910, "total_steps": 76960, "loss": 0.5456, "lr": 2.660792146120279e-05, "epoch": 10.631496881496881, "percentage": 53.16, "elapsed_time": "0:59:25", "remaining_time": "0:52:21", "throughput": 1033.29, "total_tokens": 3684024} {"current_steps": 40915, "total_steps": 76960, "loss": 0.0745, "lr": 2.6602263559989697e-05, "epoch": 10.632796257796258, "percentage": 53.16, "elapsed_time": "0:59:25", "remaining_time": "0:52:21", "throughput": 1033.29, "total_tokens": 3684472} {"current_steps": 40920, "total_steps": 76960, "loss": 0.3342, "lr": 2.659660557637066e-05, "epoch": 10.634095634095633, "percentage": 53.17, "elapsed_time": "0:59:26", "remaining_time": "0:52:20", "throughput": 1033.31, "total_tokens": 3684952} {"current_steps": 40925, "total_steps": 76960, "loss": 0.255, "lr": 2.659094751063666e-05, "epoch": 10.63539501039501, "percentage": 53.18, "elapsed_time": "0:59:26", "remaining_time": "0:52:20", "throughput": 1033.31, "total_tokens": 3685400} {"current_steps": 40930, "total_steps": 76960, "loss": 0.3075, "lr": 2.658528936307871e-05, "epoch": 10.636694386694387, "percentage": 53.18, "elapsed_time": "0:59:26", "remaining_time": "0:52:19", "throughput": 1033.32, "total_tokens": 3685848} {"current_steps": 40935, "total_steps": 76960, "loss": 0.3329, "lr": 2.6579631133987802e-05, "epoch": 10.637993762993762, "percentage": 53.19, "elapsed_time": "0:59:27", "remaining_time": "0:52:19", "throughput": 1033.33, "total_tokens": 3686312} {"current_steps": 40940, "total_steps": 76960, "loss": 0.1973, "lr": 2.6573972823654957e-05, "epoch": 10.63929313929314, "percentage": 53.2, "elapsed_time": "0:59:27", "remaining_time": "0:52:19", "throughput": 1033.34, "total_tokens": 3686776} {"current_steps": 40945, "total_steps": 76960, "loss": 0.2118, "lr": 2.6568314432371183e-05, "epoch": 10.640592515592516, "percentage": 53.2, "elapsed_time": "0:59:28", "remaining_time": "0:52:18", "throughput": 1033.35, "total_tokens": 3687240} {"current_steps": 40950, "total_steps": 76960, "loss": 0.2161, "lr": 2.656265596042749e-05, "epoch": 10.641891891891891, "percentage": 53.21, "elapsed_time": "0:59:28", "remaining_time": "0:52:18", "throughput": 1033.36, "total_tokens": 3687720} {"current_steps": 40955, "total_steps": 76960, "loss": 0.2375, "lr": 2.655699740811491e-05, "epoch": 10.643191268191268, "percentage": 53.22, "elapsed_time": "0:59:29", "remaining_time": "0:52:17", "throughput": 1033.37, "total_tokens": 3688168} {"current_steps": 40960, "total_steps": 76960, "loss": 0.2506, "lr": 2.655133877572446e-05, "epoch": 10.644490644490645, "percentage": 53.22, "elapsed_time": "0:59:29", "remaining_time": "0:52:17", "throughput": 1033.37, "total_tokens": 3688584} {"current_steps": 40965, "total_steps": 76960, "loss": 0.1825, "lr": 2.6545680063547164e-05, "epoch": 10.64579002079002, "percentage": 53.23, "elapsed_time": "0:59:29", "remaining_time": "0:52:16", "throughput": 1033.37, "total_tokens": 3689032} {"current_steps": 40970, "total_steps": 76960, "loss": 0.345, "lr": 2.6540021271874067e-05, "epoch": 10.647089397089397, "percentage": 53.24, "elapsed_time": "0:59:30", "remaining_time": "0:52:16", "throughput": 1033.37, "total_tokens": 3689464} {"current_steps": 40975, "total_steps": 76960, "loss": 0.2134, "lr": 2.65343624009962e-05, "epoch": 10.648388773388774, "percentage": 53.24, "elapsed_time": "0:59:30", "remaining_time": "0:52:15", "throughput": 1033.38, "total_tokens": 3689928} {"current_steps": 40980, "total_steps": 76960, "loss": 0.1074, "lr": 2.6528703451204606e-05, "epoch": 10.64968814968815, "percentage": 53.25, "elapsed_time": "0:59:31", "remaining_time": "0:52:15", "throughput": 1033.39, "total_tokens": 3690376} {"current_steps": 40985, "total_steps": 76960, "loss": 0.1011, "lr": 2.6523044422790326e-05, "epoch": 10.650987525987526, "percentage": 53.25, "elapsed_time": "0:59:31", "remaining_time": "0:52:14", "throughput": 1033.4, "total_tokens": 3690856} {"current_steps": 40990, "total_steps": 76960, "loss": 0.4082, "lr": 2.6517385316044412e-05, "epoch": 10.652286902286903, "percentage": 53.26, "elapsed_time": "0:59:31", "remaining_time": "0:52:14", "throughput": 1033.39, "total_tokens": 3691272} {"current_steps": 40995, "total_steps": 76960, "loss": 0.3788, "lr": 2.651172613125792e-05, "epoch": 10.653586278586278, "percentage": 53.27, "elapsed_time": "0:59:32", "remaining_time": "0:52:14", "throughput": 1033.4, "total_tokens": 3691720} {"current_steps": 41000, "total_steps": 76960, "loss": 0.1997, "lr": 2.6506066868721897e-05, "epoch": 10.654885654885655, "percentage": 53.27, "elapsed_time": "0:59:32", "remaining_time": "0:52:13", "throughput": 1033.41, "total_tokens": 3692184} {"current_steps": 41005, "total_steps": 76960, "loss": 0.1067, "lr": 2.6500407528727422e-05, "epoch": 10.65618503118503, "percentage": 53.28, "elapsed_time": "0:59:33", "remaining_time": "0:52:13", "throughput": 1033.41, "total_tokens": 3692632} {"current_steps": 41010, "total_steps": 76960, "loss": 0.5089, "lr": 2.6494748111565542e-05, "epoch": 10.657484407484407, "percentage": 53.29, "elapsed_time": "0:59:33", "remaining_time": "0:52:12", "throughput": 1033.43, "total_tokens": 3693112} {"current_steps": 41015, "total_steps": 76960, "loss": 0.1548, "lr": 2.648908861752734e-05, "epoch": 10.658783783783784, "percentage": 53.29, "elapsed_time": "0:59:34", "remaining_time": "0:52:12", "throughput": 1033.43, "total_tokens": 3693544} {"current_steps": 41020, "total_steps": 76960, "loss": 0.3495, "lr": 2.648342904690388e-05, "epoch": 10.66008316008316, "percentage": 53.3, "elapsed_time": "0:59:34", "remaining_time": "0:52:11", "throughput": 1033.43, "total_tokens": 3693976} {"current_steps": 41025, "total_steps": 76960, "loss": 0.2784, "lr": 2.6477769399986245e-05, "epoch": 10.661382536382536, "percentage": 53.31, "elapsed_time": "0:59:34", "remaining_time": "0:52:11", "throughput": 1033.43, "total_tokens": 3694408} {"current_steps": 41030, "total_steps": 76960, "loss": 0.2061, "lr": 2.6472109677065515e-05, "epoch": 10.662681912681913, "percentage": 53.31, "elapsed_time": "0:59:35", "remaining_time": "0:52:10", "throughput": 1033.45, "total_tokens": 3694888} {"current_steps": 41035, "total_steps": 76960, "loss": 0.3434, "lr": 2.6466449878432776e-05, "epoch": 10.663981288981288, "percentage": 53.32, "elapsed_time": "0:59:35", "remaining_time": "0:52:10", "throughput": 1033.45, "total_tokens": 3695320} {"current_steps": 41040, "total_steps": 76960, "loss": 0.1755, "lr": 2.6460790004379105e-05, "epoch": 10.665280665280665, "percentage": 53.33, "elapsed_time": "0:59:36", "remaining_time": "0:52:09", "throughput": 1033.46, "total_tokens": 3695800} {"current_steps": 41045, "total_steps": 76960, "loss": 0.1522, "lr": 2.6455130055195613e-05, "epoch": 10.666580041580042, "percentage": 53.33, "elapsed_time": "0:59:36", "remaining_time": "0:52:09", "throughput": 1033.47, "total_tokens": 3696280} {"current_steps": 41050, "total_steps": 76960, "loss": 0.2549, "lr": 2.644947003117339e-05, "epoch": 10.667879417879417, "percentage": 53.34, "elapsed_time": "0:59:36", "remaining_time": "0:52:09", "throughput": 1033.47, "total_tokens": 3696696} {"current_steps": 41055, "total_steps": 76960, "loss": 0.2144, "lr": 2.6443809932603526e-05, "epoch": 10.669178794178794, "percentage": 53.35, "elapsed_time": "0:59:37", "remaining_time": "0:52:08", "throughput": 1033.48, "total_tokens": 3697160} {"current_steps": 41060, "total_steps": 76960, "loss": 0.3069, "lr": 2.6438149759777137e-05, "epoch": 10.670478170478171, "percentage": 53.35, "elapsed_time": "0:59:37", "remaining_time": "0:52:08", "throughput": 1033.49, "total_tokens": 3697640} {"current_steps": 41065, "total_steps": 76960, "loss": 0.2258, "lr": 2.6432489512985326e-05, "epoch": 10.671777546777546, "percentage": 53.36, "elapsed_time": "0:59:38", "remaining_time": "0:52:07", "throughput": 1033.5, "total_tokens": 3698104} {"current_steps": 41070, "total_steps": 76960, "loss": 0.3082, "lr": 2.6426829192519213e-05, "epoch": 10.673076923076923, "percentage": 53.37, "elapsed_time": "0:59:38", "remaining_time": "0:52:07", "throughput": 1033.51, "total_tokens": 3698552} {"current_steps": 41075, "total_steps": 76960, "loss": 0.3958, "lr": 2.64211687986699e-05, "epoch": 10.674376299376299, "percentage": 53.37, "elapsed_time": "0:59:39", "remaining_time": "0:52:06", "throughput": 1033.52, "total_tokens": 3699016} {"current_steps": 41080, "total_steps": 76960, "loss": 0.2199, "lr": 2.6415508331728517e-05, "epoch": 10.675675675675675, "percentage": 53.38, "elapsed_time": "0:59:39", "remaining_time": "0:52:06", "throughput": 1033.52, "total_tokens": 3699448} {"current_steps": 41085, "total_steps": 76960, "loss": 0.3287, "lr": 2.6409847791986188e-05, "epoch": 10.676975051975052, "percentage": 53.38, "elapsed_time": "0:59:39", "remaining_time": "0:52:05", "throughput": 1033.52, "total_tokens": 3699864} {"current_steps": 41090, "total_steps": 76960, "loss": 0.1422, "lr": 2.640418717973403e-05, "epoch": 10.678274428274428, "percentage": 53.39, "elapsed_time": "0:59:40", "remaining_time": "0:52:05", "throughput": 1033.52, "total_tokens": 3700296} {"current_steps": 41095, "total_steps": 76960, "loss": 0.3029, "lr": 2.6398526495263182e-05, "epoch": 10.679573804573804, "percentage": 53.4, "elapsed_time": "0:59:40", "remaining_time": "0:52:05", "throughput": 1033.52, "total_tokens": 3700744} {"current_steps": 41100, "total_steps": 76960, "loss": 0.1805, "lr": 2.639286573886478e-05, "epoch": 10.680873180873181, "percentage": 53.4, "elapsed_time": "0:59:41", "remaining_time": "0:52:04", "throughput": 1033.53, "total_tokens": 3701192} {"current_steps": 41105, "total_steps": 76960, "loss": 0.2094, "lr": 2.6387204910829956e-05, "epoch": 10.682172557172557, "percentage": 53.41, "elapsed_time": "0:59:41", "remaining_time": "0:52:04", "throughput": 1033.54, "total_tokens": 3701672} {"current_steps": 41110, "total_steps": 76960, "loss": 0.1966, "lr": 2.6381544011449854e-05, "epoch": 10.683471933471933, "percentage": 53.42, "elapsed_time": "0:59:41", "remaining_time": "0:52:03", "throughput": 1033.56, "total_tokens": 3702152} {"current_steps": 41115, "total_steps": 76960, "loss": 0.275, "lr": 2.637588304101562e-05, "epoch": 10.68477130977131, "percentage": 53.42, "elapsed_time": "0:59:42", "remaining_time": "0:52:03", "throughput": 1033.56, "total_tokens": 3702600} {"current_steps": 41120, "total_steps": 76960, "loss": 0.2625, "lr": 2.6370221999818407e-05, "epoch": 10.686070686070686, "percentage": 53.43, "elapsed_time": "0:59:42", "remaining_time": "0:52:02", "throughput": 1033.56, "total_tokens": 3703016} {"current_steps": 41125, "total_steps": 76960, "loss": 0.441, "lr": 2.6364560888149352e-05, "epoch": 10.687370062370062, "percentage": 53.44, "elapsed_time": "0:59:43", "remaining_time": "0:52:02", "throughput": 1033.55, "total_tokens": 3703432} {"current_steps": 41130, "total_steps": 76960, "loss": 0.2316, "lr": 2.6358899706299633e-05, "epoch": 10.68866943866944, "percentage": 53.44, "elapsed_time": "0:59:43", "remaining_time": "0:52:01", "throughput": 1033.55, "total_tokens": 3703864} {"current_steps": 41135, "total_steps": 76960, "loss": 0.3121, "lr": 2.6353238454560398e-05, "epoch": 10.689968814968815, "percentage": 53.45, "elapsed_time": "0:59:44", "remaining_time": "0:52:01", "throughput": 1033.56, "total_tokens": 3704312} {"current_steps": 41140, "total_steps": 76960, "loss": 0.2273, "lr": 2.634757713322281e-05, "epoch": 10.691268191268192, "percentage": 53.46, "elapsed_time": "0:59:44", "remaining_time": "0:52:00", "throughput": 1033.56, "total_tokens": 3704760} {"current_steps": 41145, "total_steps": 76960, "loss": 0.1195, "lr": 2.6341915742578037e-05, "epoch": 10.692567567567568, "percentage": 53.46, "elapsed_time": "0:59:44", "remaining_time": "0:52:00", "throughput": 1033.56, "total_tokens": 3705192} {"current_steps": 41150, "total_steps": 76960, "loss": 0.131, "lr": 2.633625428291726e-05, "epoch": 10.693866943866944, "percentage": 53.47, "elapsed_time": "0:59:45", "remaining_time": "0:52:00", "throughput": 1033.56, "total_tokens": 3705624} {"current_steps": 41155, "total_steps": 76960, "loss": 0.138, "lr": 2.633059275453164e-05, "epoch": 10.69516632016632, "percentage": 53.48, "elapsed_time": "0:59:45", "remaining_time": "0:51:59", "throughput": 1033.57, "total_tokens": 3706072} {"current_steps": 41160, "total_steps": 76960, "loss": 0.4057, "lr": 2.6324931157712362e-05, "epoch": 10.696465696465696, "percentage": 53.48, "elapsed_time": "0:59:46", "remaining_time": "0:51:59", "throughput": 1033.58, "total_tokens": 3706536} {"current_steps": 41165, "total_steps": 76960, "loss": 0.3112, "lr": 2.6319269492750598e-05, "epoch": 10.697765072765073, "percentage": 53.49, "elapsed_time": "0:59:46", "remaining_time": "0:51:58", "throughput": 1033.58, "total_tokens": 3706968} {"current_steps": 41170, "total_steps": 76960, "loss": 0.4447, "lr": 2.6313607759937548e-05, "epoch": 10.69906444906445, "percentage": 53.5, "elapsed_time": "0:59:46", "remaining_time": "0:51:58", "throughput": 1033.58, "total_tokens": 3707416} {"current_steps": 41175, "total_steps": 76960, "loss": 0.3515, "lr": 2.6307945959564394e-05, "epoch": 10.700363825363825, "percentage": 53.5, "elapsed_time": "0:59:47", "remaining_time": "0:51:57", "throughput": 1033.59, "total_tokens": 3707880} {"current_steps": 41180, "total_steps": 76960, "loss": 0.1655, "lr": 2.630228409192232e-05, "epoch": 10.701663201663202, "percentage": 53.51, "elapsed_time": "0:59:47", "remaining_time": "0:51:57", "throughput": 1033.6, "total_tokens": 3708328} {"current_steps": 41185, "total_steps": 76960, "loss": 0.3803, "lr": 2.629662215730253e-05, "epoch": 10.702962577962579, "percentage": 53.51, "elapsed_time": "0:59:48", "remaining_time": "0:51:56", "throughput": 1033.61, "total_tokens": 3708792} {"current_steps": 41190, "total_steps": 76960, "loss": 0.2894, "lr": 2.6290960155996218e-05, "epoch": 10.704261954261954, "percentage": 53.52, "elapsed_time": "0:59:48", "remaining_time": "0:51:56", "throughput": 1033.61, "total_tokens": 3709240} {"current_steps": 41195, "total_steps": 76960, "loss": 0.1067, "lr": 2.628529808829459e-05, "epoch": 10.70556133056133, "percentage": 53.53, "elapsed_time": "0:59:49", "remaining_time": "0:51:55", "throughput": 1033.62, "total_tokens": 3709688} {"current_steps": 41200, "total_steps": 76960, "loss": 0.2556, "lr": 2.6279635954488845e-05, "epoch": 10.706860706860708, "percentage": 53.53, "elapsed_time": "0:59:49", "remaining_time": "0:51:55", "throughput": 1033.62, "total_tokens": 3710136} {"current_steps": 41205, "total_steps": 76960, "loss": 0.141, "lr": 2.627397375487021e-05, "epoch": 10.708160083160083, "percentage": 53.54, "elapsed_time": "0:59:49", "remaining_time": "0:51:55", "throughput": 1033.64, "total_tokens": 3710648} {"current_steps": 41210, "total_steps": 76960, "loss": 0.1675, "lr": 2.626831148972987e-05, "epoch": 10.70945945945946, "percentage": 53.55, "elapsed_time": "0:59:50", "remaining_time": "0:51:54", "throughput": 1033.65, "total_tokens": 3711112} {"current_steps": 41215, "total_steps": 76960, "loss": 0.3446, "lr": 2.6262649159359053e-05, "epoch": 10.710758835758837, "percentage": 53.55, "elapsed_time": "0:59:50", "remaining_time": "0:51:54", "throughput": 1033.66, "total_tokens": 3711576} {"current_steps": 41220, "total_steps": 76960, "loss": 0.3743, "lr": 2.6256986764048992e-05, "epoch": 10.712058212058212, "percentage": 53.56, "elapsed_time": "0:59:51", "remaining_time": "0:51:53", "throughput": 1033.67, "total_tokens": 3712040} {"current_steps": 41225, "total_steps": 76960, "loss": 0.3958, "lr": 2.6251324304090892e-05, "epoch": 10.713357588357589, "percentage": 53.57, "elapsed_time": "0:59:51", "remaining_time": "0:51:53", "throughput": 1033.69, "total_tokens": 3712520} {"current_steps": 41230, "total_steps": 76960, "loss": 0.1549, "lr": 2.624566177977599e-05, "epoch": 10.714656964656964, "percentage": 53.57, "elapsed_time": "0:59:51", "remaining_time": "0:51:52", "throughput": 1033.7, "total_tokens": 3712984} {"current_steps": 41235, "total_steps": 76960, "loss": 0.183, "lr": 2.6239999191395494e-05, "epoch": 10.71595634095634, "percentage": 53.58, "elapsed_time": "0:59:52", "remaining_time": "0:51:52", "throughput": 1033.71, "total_tokens": 3713448} {"current_steps": 41240, "total_steps": 76960, "loss": 0.1459, "lr": 2.623433653924067e-05, "epoch": 10.717255717255718, "percentage": 53.59, "elapsed_time": "0:59:52", "remaining_time": "0:51:51", "throughput": 1033.71, "total_tokens": 3713896} {"current_steps": 41245, "total_steps": 76960, "loss": 0.1841, "lr": 2.6228673823602723e-05, "epoch": 10.718555093555093, "percentage": 53.59, "elapsed_time": "0:59:53", "remaining_time": "0:51:51", "throughput": 1033.72, "total_tokens": 3714360} {"current_steps": 41250, "total_steps": 76960, "loss": 0.3198, "lr": 2.6223011044772904e-05, "epoch": 10.71985446985447, "percentage": 53.6, "elapsed_time": "0:59:53", "remaining_time": "0:51:50", "throughput": 1033.74, "total_tokens": 3714856} {"current_steps": 41255, "total_steps": 76960, "loss": 0.346, "lr": 2.621734820304246e-05, "epoch": 10.721153846153847, "percentage": 53.61, "elapsed_time": "0:59:54", "remaining_time": "0:51:50", "throughput": 1033.75, "total_tokens": 3715320} {"current_steps": 41260, "total_steps": 76960, "loss": 0.333, "lr": 2.6211685298702632e-05, "epoch": 10.722453222453222, "percentage": 53.61, "elapsed_time": "0:59:54", "remaining_time": "0:51:50", "throughput": 1033.76, "total_tokens": 3715768} {"current_steps": 41265, "total_steps": 76960, "loss": 0.3361, "lr": 2.6206022332044667e-05, "epoch": 10.723752598752599, "percentage": 53.62, "elapsed_time": "0:59:54", "remaining_time": "0:51:49", "throughput": 1033.76, "total_tokens": 3716232} {"current_steps": 41270, "total_steps": 76960, "loss": 0.119, "lr": 2.620035930335981e-05, "epoch": 10.725051975051976, "percentage": 53.63, "elapsed_time": "0:59:55", "remaining_time": "0:51:49", "throughput": 1033.77, "total_tokens": 3716664} {"current_steps": 41275, "total_steps": 76960, "loss": 0.351, "lr": 2.619469621293933e-05, "epoch": 10.72635135135135, "percentage": 53.63, "elapsed_time": "0:59:55", "remaining_time": "0:51:48", "throughput": 1033.77, "total_tokens": 3717112} {"current_steps": 41280, "total_steps": 76960, "loss": 0.3359, "lr": 2.618903306107448e-05, "epoch": 10.727650727650728, "percentage": 53.64, "elapsed_time": "0:59:56", "remaining_time": "0:51:48", "throughput": 1033.77, "total_tokens": 3717544} {"current_steps": 41285, "total_steps": 76960, "loss": 0.2227, "lr": 2.618336984805652e-05, "epoch": 10.728950103950105, "percentage": 53.64, "elapsed_time": "0:59:56", "remaining_time": "0:51:47", "throughput": 1033.78, "total_tokens": 3718008} {"current_steps": 41290, "total_steps": 76960, "loss": 0.1621, "lr": 2.6177706574176714e-05, "epoch": 10.73024948024948, "percentage": 53.65, "elapsed_time": "0:59:56", "remaining_time": "0:51:47", "throughput": 1033.79, "total_tokens": 3718456} {"current_steps": 41295, "total_steps": 76960, "loss": 0.3098, "lr": 2.617204323972633e-05, "epoch": 10.731548856548857, "percentage": 53.66, "elapsed_time": "0:59:57", "remaining_time": "0:51:46", "throughput": 1033.8, "total_tokens": 3718920} {"current_steps": 41300, "total_steps": 76960, "loss": 0.261, "lr": 2.6166379844996643e-05, "epoch": 10.732848232848234, "percentage": 53.66, "elapsed_time": "0:59:57", "remaining_time": "0:51:46", "throughput": 1033.79, "total_tokens": 3719320} {"current_steps": 41305, "total_steps": 76960, "loss": 0.1724, "lr": 2.6160716390278923e-05, "epoch": 10.734147609147609, "percentage": 53.67, "elapsed_time": "0:59:58", "remaining_time": "0:51:45", "throughput": 1033.78, "total_tokens": 3719720} {"current_steps": 41310, "total_steps": 76960, "loss": 0.4872, "lr": 2.6155052875864443e-05, "epoch": 10.735446985446986, "percentage": 53.68, "elapsed_time": "0:59:58", "remaining_time": "0:51:45", "throughput": 1033.8, "total_tokens": 3720216} {"current_steps": 41315, "total_steps": 76960, "loss": 0.4024, "lr": 2.6149389302044492e-05, "epoch": 10.736746361746361, "percentage": 53.68, "elapsed_time": "0:59:59", "remaining_time": "0:51:45", "throughput": 1033.8, "total_tokens": 3720664} {"current_steps": 41320, "total_steps": 76960, "loss": 0.1117, "lr": 2.6143725669110343e-05, "epoch": 10.738045738045738, "percentage": 53.69, "elapsed_time": "0:59:59", "remaining_time": "0:51:44", "throughput": 1033.81, "total_tokens": 3721128} {"current_steps": 41325, "total_steps": 76960, "loss": 0.3085, "lr": 2.6138061977353286e-05, "epoch": 10.739345114345115, "percentage": 53.7, "elapsed_time": "0:59:59", "remaining_time": "0:51:44", "throughput": 1033.81, "total_tokens": 3721560} {"current_steps": 41330, "total_steps": 76960, "loss": 0.2591, "lr": 2.6132398227064615e-05, "epoch": 10.74064449064449, "percentage": 53.7, "elapsed_time": "1:00:00", "remaining_time": "0:51:43", "throughput": 1033.82, "total_tokens": 3722024} {"current_steps": 41335, "total_steps": 76960, "loss": 0.4276, "lr": 2.6126734418535613e-05, "epoch": 10.741943866943867, "percentage": 53.71, "elapsed_time": "1:00:00", "remaining_time": "0:51:43", "throughput": 1033.82, "total_tokens": 3722456} {"current_steps": 41340, "total_steps": 76960, "loss": 0.2532, "lr": 2.612107055205758e-05, "epoch": 10.743243243243244, "percentage": 53.72, "elapsed_time": "1:00:01", "remaining_time": "0:51:42", "throughput": 1033.83, "total_tokens": 3722920} {"current_steps": 41345, "total_steps": 76960, "loss": 0.1553, "lr": 2.6115406627921825e-05, "epoch": 10.744542619542619, "percentage": 53.72, "elapsed_time": "1:00:01", "remaining_time": "0:51:42", "throughput": 1033.83, "total_tokens": 3723336} {"current_steps": 41350, "total_steps": 76960, "loss": 0.3704, "lr": 2.6109742646419628e-05, "epoch": 10.745841995841996, "percentage": 53.73, "elapsed_time": "1:00:01", "remaining_time": "0:51:41", "throughput": 1033.84, "total_tokens": 3723816} {"current_steps": 41355, "total_steps": 76960, "loss": 0.4383, "lr": 2.6104078607842308e-05, "epoch": 10.747141372141373, "percentage": 53.74, "elapsed_time": "1:00:02", "remaining_time": "0:51:41", "throughput": 1033.85, "total_tokens": 3724280} {"current_steps": 41360, "total_steps": 76960, "loss": 0.4236, "lr": 2.6098414512481163e-05, "epoch": 10.748440748440748, "percentage": 53.74, "elapsed_time": "1:00:02", "remaining_time": "0:51:41", "throughput": 1033.85, "total_tokens": 3724712} {"current_steps": 41365, "total_steps": 76960, "loss": 0.2805, "lr": 2.609275036062751e-05, "epoch": 10.749740124740125, "percentage": 53.75, "elapsed_time": "1:00:03", "remaining_time": "0:51:40", "throughput": 1033.85, "total_tokens": 3725160} {"current_steps": 41370, "total_steps": 76960, "loss": 0.1197, "lr": 2.6087086152572665e-05, "epoch": 10.7510395010395, "percentage": 53.76, "elapsed_time": "1:00:03", "remaining_time": "0:51:40", "throughput": 1033.86, "total_tokens": 3725624} {"current_steps": 41375, "total_steps": 76960, "loss": 0.2885, "lr": 2.6081421888607928e-05, "epoch": 10.752338877338877, "percentage": 53.76, "elapsed_time": "1:00:04", "remaining_time": "0:51:39", "throughput": 1033.86, "total_tokens": 3726056} {"current_steps": 41380, "total_steps": 76960, "loss": 0.3565, "lr": 2.6075757569024633e-05, "epoch": 10.753638253638254, "percentage": 53.77, "elapsed_time": "1:00:04", "remaining_time": "0:51:39", "throughput": 1033.87, "total_tokens": 3726504} {"current_steps": 41385, "total_steps": 76960, "loss": 0.1425, "lr": 2.6070093194114094e-05, "epoch": 10.75493762993763, "percentage": 53.77, "elapsed_time": "1:00:04", "remaining_time": "0:51:38", "throughput": 1033.87, "total_tokens": 3726952} {"current_steps": 41390, "total_steps": 76960, "loss": 0.184, "lr": 2.6064428764167637e-05, "epoch": 10.756237006237006, "percentage": 53.78, "elapsed_time": "1:00:05", "remaining_time": "0:51:38", "throughput": 1033.88, "total_tokens": 3727384} {"current_steps": 41395, "total_steps": 76960, "loss": 0.3493, "lr": 2.6058764279476583e-05, "epoch": 10.757536382536383, "percentage": 53.79, "elapsed_time": "1:00:05", "remaining_time": "0:51:37", "throughput": 1033.88, "total_tokens": 3727816} {"current_steps": 41400, "total_steps": 76960, "loss": 0.4299, "lr": 2.6053099740332275e-05, "epoch": 10.758835758835758, "percentage": 53.79, "elapsed_time": "1:00:06", "remaining_time": "0:51:37", "throughput": 1033.89, "total_tokens": 3728280} {"current_steps": 41405, "total_steps": 76960, "loss": 0.1927, "lr": 2.6047435147026034e-05, "epoch": 10.760135135135135, "percentage": 53.8, "elapsed_time": "1:00:06", "remaining_time": "0:51:36", "throughput": 1033.89, "total_tokens": 3728712} {"current_steps": 41410, "total_steps": 76960, "loss": 0.1572, "lr": 2.6041770499849206e-05, "epoch": 10.761434511434512, "percentage": 53.81, "elapsed_time": "1:00:06", "remaining_time": "0:51:36", "throughput": 1033.9, "total_tokens": 3729176} {"current_steps": 41415, "total_steps": 76960, "loss": 0.3107, "lr": 2.6036105799093112e-05, "epoch": 10.762733887733887, "percentage": 53.81, "elapsed_time": "1:00:07", "remaining_time": "0:51:36", "throughput": 1033.9, "total_tokens": 3729624} {"current_steps": 41420, "total_steps": 76960, "loss": 0.2595, "lr": 2.6030441045049115e-05, "epoch": 10.764033264033264, "percentage": 53.82, "elapsed_time": "1:00:07", "remaining_time": "0:51:35", "throughput": 1033.91, "total_tokens": 3730072} {"current_steps": 41425, "total_steps": 76960, "loss": 0.247, "lr": 2.6024776238008543e-05, "epoch": 10.765332640332641, "percentage": 53.83, "elapsed_time": "1:00:08", "remaining_time": "0:51:35", "throughput": 1033.9, "total_tokens": 3730488} {"current_steps": 41430, "total_steps": 76960, "loss": 0.1761, "lr": 2.6019111378262745e-05, "epoch": 10.766632016632016, "percentage": 53.83, "elapsed_time": "1:00:08", "remaining_time": "0:51:34", "throughput": 1033.91, "total_tokens": 3730952} {"current_steps": 41435, "total_steps": 76960, "loss": 0.2613, "lr": 2.601344646610308e-05, "epoch": 10.767931392931393, "percentage": 53.84, "elapsed_time": "1:00:08", "remaining_time": "0:51:34", "throughput": 1033.92, "total_tokens": 3731400} {"current_steps": 41440, "total_steps": 76960, "loss": 0.2952, "lr": 2.600778150182089e-05, "epoch": 10.76923076923077, "percentage": 53.85, "elapsed_time": "1:00:09", "remaining_time": "0:51:33", "throughput": 1033.92, "total_tokens": 3731832} {"current_steps": 41445, "total_steps": 76960, "loss": 0.3554, "lr": 2.600211648570753e-05, "epoch": 10.770530145530145, "percentage": 53.85, "elapsed_time": "1:00:09", "remaining_time": "0:51:33", "throughput": 1033.93, "total_tokens": 3732312} {"current_steps": 41450, "total_steps": 76960, "loss": 0.2953, "lr": 2.599645141805435e-05, "epoch": 10.771829521829522, "percentage": 53.86, "elapsed_time": "1:00:10", "remaining_time": "0:51:32", "throughput": 1033.95, "total_tokens": 3732792} {"current_steps": 41455, "total_steps": 76960, "loss": 0.138, "lr": 2.5990786299152725e-05, "epoch": 10.773128898128899, "percentage": 53.87, "elapsed_time": "1:00:10", "remaining_time": "0:51:32", "throughput": 1033.96, "total_tokens": 3733256} {"current_steps": 41460, "total_steps": 76960, "loss": 0.1615, "lr": 2.5985121129294016e-05, "epoch": 10.774428274428274, "percentage": 53.87, "elapsed_time": "1:00:11", "remaining_time": "0:51:31", "throughput": 1033.96, "total_tokens": 3733704} {"current_steps": 41465, "total_steps": 76960, "loss": 0.3215, "lr": 2.597945590876958e-05, "epoch": 10.775727650727651, "percentage": 53.88, "elapsed_time": "1:00:11", "remaining_time": "0:51:31", "throughput": 1033.97, "total_tokens": 3734152} {"current_steps": 41470, "total_steps": 76960, "loss": 0.2878, "lr": 2.5973790637870786e-05, "epoch": 10.777027027027026, "percentage": 53.89, "elapsed_time": "1:00:11", "remaining_time": "0:51:31", "throughput": 1033.97, "total_tokens": 3734584} {"current_steps": 41475, "total_steps": 76960, "loss": 0.3382, "lr": 2.596812531688901e-05, "epoch": 10.778326403326403, "percentage": 53.89, "elapsed_time": "1:00:12", "remaining_time": "0:51:30", "throughput": 1033.97, "total_tokens": 3735032} {"current_steps": 41480, "total_steps": 76960, "loss": 0.0829, "lr": 2.5962459946115618e-05, "epoch": 10.77962577962578, "percentage": 53.9, "elapsed_time": "1:00:12", "remaining_time": "0:51:30", "throughput": 1033.97, "total_tokens": 3735464} {"current_steps": 41485, "total_steps": 76960, "loss": 0.2142, "lr": 2.5956794525841986e-05, "epoch": 10.780925155925155, "percentage": 53.9, "elapsed_time": "1:00:13", "remaining_time": "0:51:29", "throughput": 1033.98, "total_tokens": 3735912} {"current_steps": 41490, "total_steps": 76960, "loss": 0.4263, "lr": 2.59511290563595e-05, "epoch": 10.782224532224532, "percentage": 53.91, "elapsed_time": "1:00:13", "remaining_time": "0:51:29", "throughput": 1033.98, "total_tokens": 3736344} {"current_steps": 41495, "total_steps": 76960, "loss": 0.2276, "lr": 2.5945463537959542e-05, "epoch": 10.78352390852391, "percentage": 53.92, "elapsed_time": "1:00:13", "remaining_time": "0:51:28", "throughput": 1033.99, "total_tokens": 3736808} {"current_steps": 41500, "total_steps": 76960, "loss": 0.3948, "lr": 2.593979797093348e-05, "epoch": 10.784823284823284, "percentage": 53.92, "elapsed_time": "1:00:14", "remaining_time": "0:51:28", "throughput": 1033.98, "total_tokens": 3737224} {"current_steps": 41505, "total_steps": 76960, "loss": 0.219, "lr": 2.593413235557271e-05, "epoch": 10.786122661122661, "percentage": 53.93, "elapsed_time": "1:00:14", "remaining_time": "0:51:27", "throughput": 1033.99, "total_tokens": 3737688} {"current_steps": 41510, "total_steps": 76960, "loss": 0.1955, "lr": 2.5928466692168617e-05, "epoch": 10.787422037422038, "percentage": 53.94, "elapsed_time": "1:00:15", "remaining_time": "0:51:27", "throughput": 1034.0, "total_tokens": 3738136} {"current_steps": 41515, "total_steps": 76960, "loss": 0.2954, "lr": 2.5922800981012596e-05, "epoch": 10.788721413721413, "percentage": 53.94, "elapsed_time": "1:00:15", "remaining_time": "0:51:26", "throughput": 1034.0, "total_tokens": 3738584} {"current_steps": 41520, "total_steps": 76960, "loss": 0.339, "lr": 2.5917135222396027e-05, "epoch": 10.79002079002079, "percentage": 53.95, "elapsed_time": "1:00:16", "remaining_time": "0:51:26", "throughput": 1034.01, "total_tokens": 3739048} {"current_steps": 41525, "total_steps": 76960, "loss": 0.2856, "lr": 2.5911469416610322e-05, "epoch": 10.791320166320165, "percentage": 53.96, "elapsed_time": "1:00:16", "remaining_time": "0:51:26", "throughput": 1034.02, "total_tokens": 3739496} {"current_steps": 41530, "total_steps": 76960, "loss": 0.3309, "lr": 2.5905803563946872e-05, "epoch": 10.792619542619542, "percentage": 53.96, "elapsed_time": "1:00:16", "remaining_time": "0:51:25", "throughput": 1034.02, "total_tokens": 3739944} {"current_steps": 41535, "total_steps": 76960, "loss": 0.2589, "lr": 2.5900137664697078e-05, "epoch": 10.79391891891892, "percentage": 53.97, "elapsed_time": "1:00:17", "remaining_time": "0:51:25", "throughput": 1034.03, "total_tokens": 3740408} {"current_steps": 41540, "total_steps": 76960, "loss": 0.1597, "lr": 2.5894471719152336e-05, "epoch": 10.795218295218294, "percentage": 53.98, "elapsed_time": "1:00:17", "remaining_time": "0:51:24", "throughput": 1034.04, "total_tokens": 3740872} {"current_steps": 41545, "total_steps": 76960, "loss": 0.1506, "lr": 2.588880572760406e-05, "epoch": 10.796517671517671, "percentage": 53.98, "elapsed_time": "1:00:18", "remaining_time": "0:51:24", "throughput": 1034.06, "total_tokens": 3741384} {"current_steps": 41550, "total_steps": 76960, "loss": 0.1747, "lr": 2.5883139690343656e-05, "epoch": 10.797817047817048, "percentage": 53.99, "elapsed_time": "1:00:18", "remaining_time": "0:51:23", "throughput": 1034.07, "total_tokens": 3741832} {"current_steps": 41555, "total_steps": 76960, "loss": 0.2608, "lr": 2.5877473607662528e-05, "epoch": 10.799116424116423, "percentage": 54.0, "elapsed_time": "1:00:18", "remaining_time": "0:51:23", "throughput": 1034.08, "total_tokens": 3742280} {"current_steps": 41560, "total_steps": 76960, "loss": 0.2188, "lr": 2.5871807479852084e-05, "epoch": 10.8004158004158, "percentage": 54.0, "elapsed_time": "1:00:19", "remaining_time": "0:51:22", "throughput": 1034.08, "total_tokens": 3742728} {"current_steps": 41565, "total_steps": 76960, "loss": 0.426, "lr": 2.586614130720376e-05, "epoch": 10.801715176715177, "percentage": 54.01, "elapsed_time": "1:00:19", "remaining_time": "0:51:22", "throughput": 1034.09, "total_tokens": 3743192} {"current_steps": 41570, "total_steps": 76960, "loss": 0.2403, "lr": 2.5860475090008956e-05, "epoch": 10.803014553014552, "percentage": 54.02, "elapsed_time": "1:00:20", "remaining_time": "0:51:22", "throughput": 1034.09, "total_tokens": 3743640} {"current_steps": 41575, "total_steps": 76960, "loss": 0.2658, "lr": 2.5854808828559085e-05, "epoch": 10.80431392931393, "percentage": 54.02, "elapsed_time": "1:00:20", "remaining_time": "0:51:21", "throughput": 1034.1, "total_tokens": 3744104} {"current_steps": 41580, "total_steps": 76960, "loss": 0.2026, "lr": 2.5849142523145588e-05, "epoch": 10.805613305613306, "percentage": 54.03, "elapsed_time": "1:00:21", "remaining_time": "0:51:21", "throughput": 1034.11, "total_tokens": 3744552} {"current_steps": 41585, "total_steps": 76960, "loss": 0.2938, "lr": 2.5843476174059872e-05, "epoch": 10.806912681912682, "percentage": 54.03, "elapsed_time": "1:00:21", "remaining_time": "0:51:20", "throughput": 1034.12, "total_tokens": 3745000} {"current_steps": 41590, "total_steps": 76960, "loss": 0.2103, "lr": 2.5837809781593357e-05, "epoch": 10.808212058212058, "percentage": 54.04, "elapsed_time": "1:00:21", "remaining_time": "0:51:20", "throughput": 1034.12, "total_tokens": 3745464} {"current_steps": 41595, "total_steps": 76960, "loss": 0.2398, "lr": 2.5832143346037496e-05, "epoch": 10.809511434511435, "percentage": 54.05, "elapsed_time": "1:00:22", "remaining_time": "0:51:19", "throughput": 1034.12, "total_tokens": 3745880} {"current_steps": 41600, "total_steps": 76960, "loss": 0.2341, "lr": 2.5826476867683707e-05, "epoch": 10.81081081081081, "percentage": 54.05, "elapsed_time": "1:00:22", "remaining_time": "0:51:19", "throughput": 1034.12, "total_tokens": 3746312} {"current_steps": 41605, "total_steps": 76960, "loss": 0.1397, "lr": 2.5820810346823416e-05, "epoch": 10.812110187110187, "percentage": 54.06, "elapsed_time": "1:00:23", "remaining_time": "0:51:18", "throughput": 1034.14, "total_tokens": 3746808} {"current_steps": 41610, "total_steps": 76960, "loss": 0.2549, "lr": 2.5815143783748057e-05, "epoch": 10.813409563409563, "percentage": 54.07, "elapsed_time": "1:00:23", "remaining_time": "0:51:18", "throughput": 1034.15, "total_tokens": 3747272} {"current_steps": 41615, "total_steps": 76960, "loss": 0.0944, "lr": 2.580947717874908e-05, "epoch": 10.81470893970894, "percentage": 54.07, "elapsed_time": "1:00:23", "remaining_time": "0:51:17", "throughput": 1034.15, "total_tokens": 3747720} {"current_steps": 41620, "total_steps": 76960, "loss": 0.4094, "lr": 2.5803810532117918e-05, "epoch": 10.816008316008316, "percentage": 54.08, "elapsed_time": "1:00:24", "remaining_time": "0:51:17", "throughput": 1034.16, "total_tokens": 3748152} {"current_steps": 41625, "total_steps": 76960, "loss": 0.128, "lr": 2.5798143844146005e-05, "epoch": 10.817307692307692, "percentage": 54.09, "elapsed_time": "1:00:24", "remaining_time": "0:51:17", "throughput": 1034.16, "total_tokens": 3748616} {"current_steps": 41630, "total_steps": 76960, "loss": 0.3487, "lr": 2.5792477115124793e-05, "epoch": 10.818607068607069, "percentage": 54.09, "elapsed_time": "1:00:25", "remaining_time": "0:51:16", "throughput": 1034.17, "total_tokens": 3749064} {"current_steps": 41635, "total_steps": 76960, "loss": 0.3538, "lr": 2.578681034534572e-05, "epoch": 10.819906444906445, "percentage": 54.1, "elapsed_time": "1:00:25", "remaining_time": "0:51:16", "throughput": 1034.17, "total_tokens": 3749496} {"current_steps": 41640, "total_steps": 76960, "loss": 0.0902, "lr": 2.5781143535100237e-05, "epoch": 10.82120582120582, "percentage": 54.11, "elapsed_time": "1:00:26", "remaining_time": "0:51:15", "throughput": 1034.17, "total_tokens": 3749928} {"current_steps": 41645, "total_steps": 76960, "loss": 0.3034, "lr": 2.5775476684679796e-05, "epoch": 10.822505197505198, "percentage": 54.11, "elapsed_time": "1:00:26", "remaining_time": "0:51:15", "throughput": 1034.19, "total_tokens": 3750424} {"current_steps": 41650, "total_steps": 76960, "loss": 0.2922, "lr": 2.5769809794375843e-05, "epoch": 10.823804573804575, "percentage": 54.12, "elapsed_time": "1:00:26", "remaining_time": "0:51:14", "throughput": 1034.19, "total_tokens": 3750872} {"current_steps": 41655, "total_steps": 76960, "loss": 0.1094, "lr": 2.5764142864479835e-05, "epoch": 10.82510395010395, "percentage": 54.13, "elapsed_time": "1:00:27", "remaining_time": "0:51:14", "throughput": 1034.21, "total_tokens": 3751352} {"current_steps": 41660, "total_steps": 76960, "loss": 0.213, "lr": 2.575847589528323e-05, "epoch": 10.826403326403327, "percentage": 54.13, "elapsed_time": "1:00:27", "remaining_time": "0:51:13", "throughput": 1034.21, "total_tokens": 3751800} {"current_steps": 41665, "total_steps": 76960, "loss": 0.3266, "lr": 2.5752808887077477e-05, "epoch": 10.827702702702704, "percentage": 54.14, "elapsed_time": "1:00:28", "remaining_time": "0:51:13", "throughput": 1034.22, "total_tokens": 3752248} {"current_steps": 41670, "total_steps": 76960, "loss": 0.3373, "lr": 2.574714184015405e-05, "epoch": 10.829002079002079, "percentage": 54.15, "elapsed_time": "1:00:28", "remaining_time": "0:51:12", "throughput": 1034.23, "total_tokens": 3752712} {"current_steps": 41675, "total_steps": 76960, "loss": 0.1192, "lr": 2.57414747548044e-05, "epoch": 10.830301455301456, "percentage": 54.15, "elapsed_time": "1:00:28", "remaining_time": "0:51:12", "throughput": 1034.25, "total_tokens": 3753224} {"current_steps": 41680, "total_steps": 76960, "loss": 0.0735, "lr": 2.5735807631319993e-05, "epoch": 10.83160083160083, "percentage": 54.16, "elapsed_time": "1:00:29", "remaining_time": "0:51:12", "throughput": 1034.25, "total_tokens": 3753656} {"current_steps": 41685, "total_steps": 76960, "loss": 0.3347, "lr": 2.5730140469992286e-05, "epoch": 10.832900207900208, "percentage": 54.16, "elapsed_time": "1:00:29", "remaining_time": "0:51:11", "throughput": 1034.26, "total_tokens": 3754104} {"current_steps": 41690, "total_steps": 76960, "loss": 0.1139, "lr": 2.5724473271112763e-05, "epoch": 10.834199584199585, "percentage": 54.17, "elapsed_time": "1:00:30", "remaining_time": "0:51:11", "throughput": 1034.26, "total_tokens": 3754536} {"current_steps": 41695, "total_steps": 76960, "loss": 0.2673, "lr": 2.571880603497289e-05, "epoch": 10.83549896049896, "percentage": 54.18, "elapsed_time": "1:00:30", "remaining_time": "0:51:10", "throughput": 1034.27, "total_tokens": 3755032} {"current_steps": 41700, "total_steps": 76960, "loss": 0.4192, "lr": 2.5713138761864127e-05, "epoch": 10.836798336798337, "percentage": 54.18, "elapsed_time": "1:00:31", "remaining_time": "0:51:10", "throughput": 1034.26, "total_tokens": 3755432} {"current_steps": 41705, "total_steps": 76960, "loss": 0.34, "lr": 2.570747145207796e-05, "epoch": 10.838097713097714, "percentage": 54.19, "elapsed_time": "1:00:31", "remaining_time": "0:51:09", "throughput": 1034.27, "total_tokens": 3755864} {"current_steps": 41710, "total_steps": 76960, "loss": 0.1838, "lr": 2.5701804105905854e-05, "epoch": 10.839397089397089, "percentage": 54.2, "elapsed_time": "1:00:31", "remaining_time": "0:51:09", "throughput": 1034.27, "total_tokens": 3756312} {"current_steps": 41715, "total_steps": 76960, "loss": 0.4022, "lr": 2.5696136723639286e-05, "epoch": 10.840696465696466, "percentage": 54.2, "elapsed_time": "1:00:32", "remaining_time": "0:51:08", "throughput": 1034.28, "total_tokens": 3756776} {"current_steps": 41720, "total_steps": 76960, "loss": 0.2767, "lr": 2.569046930556974e-05, "epoch": 10.841995841995843, "percentage": 54.21, "elapsed_time": "1:00:32", "remaining_time": "0:51:08", "throughput": 1034.3, "total_tokens": 3757272} {"current_steps": 41725, "total_steps": 76960, "loss": 0.3668, "lr": 2.5684801851988704e-05, "epoch": 10.843295218295218, "percentage": 54.22, "elapsed_time": "1:00:33", "remaining_time": "0:51:07", "throughput": 1034.3, "total_tokens": 3757720} {"current_steps": 41730, "total_steps": 76960, "loss": 0.0457, "lr": 2.5679134363187652e-05, "epoch": 10.844594594594595, "percentage": 54.22, "elapsed_time": "1:00:33", "remaining_time": "0:51:07", "throughput": 1034.31, "total_tokens": 3758168} {"current_steps": 41735, "total_steps": 76960, "loss": 0.214, "lr": 2.567346683945806e-05, "epoch": 10.845893970893972, "percentage": 54.23, "elapsed_time": "1:00:33", "remaining_time": "0:51:07", "throughput": 1034.3, "total_tokens": 3758584} {"current_steps": 41740, "total_steps": 76960, "loss": 0.4529, "lr": 2.5667799281091427e-05, "epoch": 10.847193347193347, "percentage": 54.24, "elapsed_time": "1:00:34", "remaining_time": "0:51:06", "throughput": 1034.31, "total_tokens": 3759048} {"current_steps": 41745, "total_steps": 76960, "loss": 0.284, "lr": 2.5662131688379242e-05, "epoch": 10.848492723492724, "percentage": 54.24, "elapsed_time": "1:00:34", "remaining_time": "0:51:06", "throughput": 1034.31, "total_tokens": 3759480} {"current_steps": 41750, "total_steps": 76960, "loss": 0.3706, "lr": 2.5656464061612982e-05, "epoch": 10.8497920997921, "percentage": 54.25, "elapsed_time": "1:00:35", "remaining_time": "0:51:05", "throughput": 1034.32, "total_tokens": 3759928} {"current_steps": 41755, "total_steps": 76960, "loss": 0.0988, "lr": 2.565079640108415e-05, "epoch": 10.851091476091476, "percentage": 54.26, "elapsed_time": "1:00:35", "remaining_time": "0:51:05", "throughput": 1034.32, "total_tokens": 3760360} {"current_steps": 41760, "total_steps": 76960, "loss": 0.1987, "lr": 2.564512870708424e-05, "epoch": 10.852390852390853, "percentage": 54.26, "elapsed_time": "1:00:36", "remaining_time": "0:51:04", "throughput": 1034.32, "total_tokens": 3760808} {"current_steps": 41765, "total_steps": 76960, "loss": 0.1672, "lr": 2.5639460979904744e-05, "epoch": 10.853690228690228, "percentage": 54.27, "elapsed_time": "1:00:36", "remaining_time": "0:51:04", "throughput": 1034.32, "total_tokens": 3761240} {"current_steps": 41770, "total_steps": 76960, "loss": 0.3027, "lr": 2.5633793219837148e-05, "epoch": 10.854989604989605, "percentage": 54.27, "elapsed_time": "1:00:36", "remaining_time": "0:51:03", "throughput": 1034.32, "total_tokens": 3761656} {"current_steps": 41775, "total_steps": 76960, "loss": 0.3653, "lr": 2.562812542717296e-05, "epoch": 10.856288981288982, "percentage": 54.28, "elapsed_time": "1:00:37", "remaining_time": "0:51:03", "throughput": 1034.32, "total_tokens": 3762088} {"current_steps": 41780, "total_steps": 76960, "loss": 0.4564, "lr": 2.5622457602203688e-05, "epoch": 10.857588357588357, "percentage": 54.29, "elapsed_time": "1:00:37", "remaining_time": "0:51:03", "throughput": 1034.33, "total_tokens": 3762568} {"current_steps": 41785, "total_steps": 76960, "loss": 0.2046, "lr": 2.5616789745220822e-05, "epoch": 10.858887733887734, "percentage": 54.29, "elapsed_time": "1:00:38", "remaining_time": "0:51:02", "throughput": 1034.34, "total_tokens": 3763032} {"current_steps": 41790, "total_steps": 76960, "loss": 0.1347, "lr": 2.5611121856515857e-05, "epoch": 10.86018711018711, "percentage": 54.3, "elapsed_time": "1:00:38", "remaining_time": "0:51:02", "throughput": 1034.36, "total_tokens": 3763512} {"current_steps": 41795, "total_steps": 76960, "loss": 0.3223, "lr": 2.560545393638032e-05, "epoch": 10.861486486486486, "percentage": 54.31, "elapsed_time": "1:00:38", "remaining_time": "0:51:01", "throughput": 1034.36, "total_tokens": 3763944} {"current_steps": 41800, "total_steps": 76960, "loss": 0.1993, "lr": 2.5599785985105705e-05, "epoch": 10.862785862785863, "percentage": 54.31, "elapsed_time": "1:00:39", "remaining_time": "0:51:01", "throughput": 1034.35, "total_tokens": 3764360} {"current_steps": 41805, "total_steps": 76960, "loss": 0.4427, "lr": 2.5594118002983523e-05, "epoch": 10.86408523908524, "percentage": 54.32, "elapsed_time": "1:00:39", "remaining_time": "0:51:00", "throughput": 1034.36, "total_tokens": 3764808} {"current_steps": 41810, "total_steps": 76960, "loss": 0.1512, "lr": 2.5588449990305278e-05, "epoch": 10.865384615384615, "percentage": 54.33, "elapsed_time": "1:00:40", "remaining_time": "0:51:00", "throughput": 1034.37, "total_tokens": 3765272} {"current_steps": 41815, "total_steps": 76960, "loss": 0.327, "lr": 2.5582781947362495e-05, "epoch": 10.866683991683992, "percentage": 54.33, "elapsed_time": "1:00:40", "remaining_time": "0:50:59", "throughput": 1034.37, "total_tokens": 3765720} {"current_steps": 41820, "total_steps": 76960, "loss": 0.0863, "lr": 2.557711387444668e-05, "epoch": 10.867983367983367, "percentage": 54.34, "elapsed_time": "1:00:40", "remaining_time": "0:50:59", "throughput": 1034.37, "total_tokens": 3766152} {"current_steps": 41825, "total_steps": 76960, "loss": 0.3049, "lr": 2.5571445771849327e-05, "epoch": 10.869282744282744, "percentage": 54.35, "elapsed_time": "1:00:41", "remaining_time": "0:50:58", "throughput": 1034.37, "total_tokens": 3766584} {"current_steps": 41830, "total_steps": 76960, "loss": 0.4318, "lr": 2.5565777639861992e-05, "epoch": 10.870582120582121, "percentage": 54.35, "elapsed_time": "1:00:41", "remaining_time": "0:50:58", "throughput": 1034.38, "total_tokens": 3767048} {"current_steps": 41835, "total_steps": 76960, "loss": 0.3951, "lr": 2.5560109478776162e-05, "epoch": 10.871881496881496, "percentage": 54.36, "elapsed_time": "1:00:42", "remaining_time": "0:50:58", "throughput": 1034.39, "total_tokens": 3767512} {"current_steps": 41840, "total_steps": 76960, "loss": 0.2988, "lr": 2.5554441288883364e-05, "epoch": 10.873180873180873, "percentage": 54.37, "elapsed_time": "1:00:42", "remaining_time": "0:50:57", "throughput": 1034.4, "total_tokens": 3767960} {"current_steps": 41845, "total_steps": 76960, "loss": 0.2441, "lr": 2.5548773070475118e-05, "epoch": 10.87448024948025, "percentage": 54.37, "elapsed_time": "1:00:43", "remaining_time": "0:50:57", "throughput": 1034.4, "total_tokens": 3768408} {"current_steps": 41850, "total_steps": 76960, "loss": 0.2792, "lr": 2.554310482384295e-05, "epoch": 10.875779625779625, "percentage": 54.38, "elapsed_time": "1:00:43", "remaining_time": "0:50:56", "throughput": 1034.4, "total_tokens": 3768840} {"current_steps": 41855, "total_steps": 76960, "loss": 0.2469, "lr": 2.553743654927838e-05, "epoch": 10.877079002079002, "percentage": 54.39, "elapsed_time": "1:00:43", "remaining_time": "0:50:56", "throughput": 1034.4, "total_tokens": 3769256} {"current_steps": 41860, "total_steps": 76960, "loss": 0.2301, "lr": 2.553176824707293e-05, "epoch": 10.878378378378379, "percentage": 54.39, "elapsed_time": "1:00:44", "remaining_time": "0:50:55", "throughput": 1034.4, "total_tokens": 3769704} {"current_steps": 41865, "total_steps": 76960, "loss": 0.2384, "lr": 2.552609991751813e-05, "epoch": 10.879677754677754, "percentage": 54.4, "elapsed_time": "1:00:44", "remaining_time": "0:50:55", "throughput": 1034.41, "total_tokens": 3770152} {"current_steps": 41870, "total_steps": 76960, "loss": 0.2332, "lr": 2.552043156090551e-05, "epoch": 10.880977130977131, "percentage": 54.4, "elapsed_time": "1:00:45", "remaining_time": "0:50:54", "throughput": 1034.41, "total_tokens": 3770584} {"current_steps": 41875, "total_steps": 76960, "loss": 0.2061, "lr": 2.55147631775266e-05, "epoch": 10.882276507276508, "percentage": 54.41, "elapsed_time": "1:00:45", "remaining_time": "0:50:54", "throughput": 1034.42, "total_tokens": 3771048} {"current_steps": 41880, "total_steps": 76960, "loss": 0.2677, "lr": 2.550909476767292e-05, "epoch": 10.883575883575883, "percentage": 54.42, "elapsed_time": "1:00:45", "remaining_time": "0:50:53", "throughput": 1034.43, "total_tokens": 3771512} {"current_steps": 41885, "total_steps": 76960, "loss": 0.1554, "lr": 2.550342633163601e-05, "epoch": 10.88487525987526, "percentage": 54.42, "elapsed_time": "1:00:46", "remaining_time": "0:50:53", "throughput": 1034.43, "total_tokens": 3771960} {"current_steps": 41890, "total_steps": 76960, "loss": 0.3303, "lr": 2.54977578697074e-05, "epoch": 10.886174636174637, "percentage": 54.43, "elapsed_time": "1:00:46", "remaining_time": "0:50:53", "throughput": 1034.44, "total_tokens": 3772424} {"current_steps": 41895, "total_steps": 76960, "loss": 0.1856, "lr": 2.549208938217863e-05, "epoch": 10.887474012474012, "percentage": 54.44, "elapsed_time": "1:00:47", "remaining_time": "0:50:52", "throughput": 1034.43, "total_tokens": 3772824} {"current_steps": 41900, "total_steps": 76960, "loss": 0.1617, "lr": 2.5486420869341232e-05, "epoch": 10.888773388773389, "percentage": 54.44, "elapsed_time": "1:00:47", "remaining_time": "0:50:52", "throughput": 1034.44, "total_tokens": 3773288} {"current_steps": 41905, "total_steps": 76960, "loss": 0.3429, "lr": 2.548075233148674e-05, "epoch": 10.890072765072766, "percentage": 54.45, "elapsed_time": "1:00:48", "remaining_time": "0:50:51", "throughput": 1034.45, "total_tokens": 3773752} {"current_steps": 41910, "total_steps": 76960, "loss": 0.0591, "lr": 2.5475083768906694e-05, "epoch": 10.891372141372141, "percentage": 54.46, "elapsed_time": "1:00:48", "remaining_time": "0:50:51", "throughput": 1034.46, "total_tokens": 3774216} {"current_steps": 41915, "total_steps": 76960, "loss": 0.2165, "lr": 2.546941518189263e-05, "epoch": 10.892671517671518, "percentage": 54.46, "elapsed_time": "1:00:48", "remaining_time": "0:50:50", "throughput": 1034.47, "total_tokens": 3774680} {"current_steps": 41920, "total_steps": 76960, "loss": 0.2812, "lr": 2.5463746570736103e-05, "epoch": 10.893970893970893, "percentage": 54.47, "elapsed_time": "1:00:49", "remaining_time": "0:50:50", "throughput": 1034.47, "total_tokens": 3775112} {"current_steps": 41925, "total_steps": 76960, "loss": 0.3399, "lr": 2.545807793572864e-05, "epoch": 10.89527027027027, "percentage": 54.48, "elapsed_time": "1:00:49", "remaining_time": "0:50:49", "throughput": 1034.48, "total_tokens": 3775576} {"current_steps": 41930, "total_steps": 76960, "loss": 0.3745, "lr": 2.5452409277161793e-05, "epoch": 10.896569646569647, "percentage": 54.48, "elapsed_time": "1:00:50", "remaining_time": "0:50:49", "throughput": 1034.49, "total_tokens": 3776056} {"current_steps": 41935, "total_steps": 76960, "loss": 0.3359, "lr": 2.5446740595327096e-05, "epoch": 10.897869022869022, "percentage": 54.49, "elapsed_time": "1:00:50", "remaining_time": "0:50:49", "throughput": 1034.5, "total_tokens": 3776520} {"current_steps": 41940, "total_steps": 76960, "loss": 0.2345, "lr": 2.5441071890516112e-05, "epoch": 10.8991683991684, "percentage": 54.5, "elapsed_time": "1:00:50", "remaining_time": "0:50:48", "throughput": 1034.51, "total_tokens": 3776968} {"current_steps": 41945, "total_steps": 76960, "loss": 0.2344, "lr": 2.5435403163020373e-05, "epoch": 10.900467775467776, "percentage": 54.5, "elapsed_time": "1:00:51", "remaining_time": "0:50:48", "throughput": 1034.51, "total_tokens": 3777416} {"current_steps": 41950, "total_steps": 76960, "loss": 0.2174, "lr": 2.5429734413131427e-05, "epoch": 10.901767151767151, "percentage": 54.51, "elapsed_time": "1:00:51", "remaining_time": "0:50:47", "throughput": 1034.51, "total_tokens": 3777832} {"current_steps": 41955, "total_steps": 76960, "loss": 0.3476, "lr": 2.5424065641140837e-05, "epoch": 10.903066528066528, "percentage": 54.52, "elapsed_time": "1:00:52", "remaining_time": "0:50:47", "throughput": 1034.52, "total_tokens": 3778296} {"current_steps": 41960, "total_steps": 76960, "loss": 0.1599, "lr": 2.541839684734015e-05, "epoch": 10.904365904365905, "percentage": 54.52, "elapsed_time": "1:00:52", "remaining_time": "0:50:46", "throughput": 1034.51, "total_tokens": 3778712} {"current_steps": 41965, "total_steps": 76960, "loss": 0.1531, "lr": 2.54127280320209e-05, "epoch": 10.90566528066528, "percentage": 54.53, "elapsed_time": "1:00:53", "remaining_time": "0:50:46", "throughput": 1034.51, "total_tokens": 3779128} {"current_steps": 41970, "total_steps": 76960, "loss": 0.114, "lr": 2.540705919547466e-05, "epoch": 10.906964656964657, "percentage": 54.53, "elapsed_time": "1:00:53", "remaining_time": "0:50:45", "throughput": 1034.52, "total_tokens": 3779592} {"current_steps": 41975, "total_steps": 76960, "loss": 0.3049, "lr": 2.540139033799297e-05, "epoch": 10.908264033264032, "percentage": 54.54, "elapsed_time": "1:00:53", "remaining_time": "0:50:45", "throughput": 1034.53, "total_tokens": 3780056} {"current_steps": 41980, "total_steps": 76960, "loss": 0.3851, "lr": 2.5395721459867393e-05, "epoch": 10.90956340956341, "percentage": 54.55, "elapsed_time": "1:00:54", "remaining_time": "0:50:44", "throughput": 1034.54, "total_tokens": 3780520} {"current_steps": 41985, "total_steps": 76960, "loss": 0.2167, "lr": 2.5390052561389478e-05, "epoch": 10.910862785862786, "percentage": 54.55, "elapsed_time": "1:00:54", "remaining_time": "0:50:44", "throughput": 1034.54, "total_tokens": 3780952} {"current_steps": 41990, "total_steps": 76960, "loss": 0.22, "lr": 2.538438364285079e-05, "epoch": 10.912162162162161, "percentage": 54.56, "elapsed_time": "1:00:55", "remaining_time": "0:50:44", "throughput": 1034.54, "total_tokens": 3781400} {"current_steps": 41995, "total_steps": 76960, "loss": 0.2285, "lr": 2.5378714704542883e-05, "epoch": 10.913461538461538, "percentage": 54.57, "elapsed_time": "1:00:55", "remaining_time": "0:50:43", "throughput": 1034.56, "total_tokens": 3781880} {"current_steps": 42000, "total_steps": 76960, "loss": 0.2255, "lr": 2.5373045746757313e-05, "epoch": 10.914760914760915, "percentage": 54.57, "elapsed_time": "1:00:55", "remaining_time": "0:50:43", "throughput": 1034.57, "total_tokens": 3782344} {"current_steps": 42005, "total_steps": 76960, "loss": 0.3091, "lr": 2.5367376769785645e-05, "epoch": 10.91606029106029, "percentage": 54.58, "elapsed_time": "1:00:56", "remaining_time": "0:50:42", "throughput": 1034.57, "total_tokens": 3782792} {"current_steps": 42010, "total_steps": 76960, "loss": 0.3292, "lr": 2.5361707773919436e-05, "epoch": 10.917359667359667, "percentage": 54.59, "elapsed_time": "1:00:56", "remaining_time": "0:50:42", "throughput": 1034.57, "total_tokens": 3783224} {"current_steps": 42015, "total_steps": 76960, "loss": 0.0985, "lr": 2.5356038759450252e-05, "epoch": 10.918659043659044, "percentage": 54.59, "elapsed_time": "1:00:57", "remaining_time": "0:50:41", "throughput": 1034.58, "total_tokens": 3783672} {"current_steps": 42020, "total_steps": 76960, "loss": 0.3888, "lr": 2.5350369726669652e-05, "epoch": 10.91995841995842, "percentage": 54.6, "elapsed_time": "1:00:57", "remaining_time": "0:50:41", "throughput": 1034.58, "total_tokens": 3784104} {"current_steps": 42025, "total_steps": 76960, "loss": 0.3665, "lr": 2.5344700675869203e-05, "epoch": 10.921257796257796, "percentage": 54.61, "elapsed_time": "1:00:58", "remaining_time": "0:50:40", "throughput": 1034.59, "total_tokens": 3784584} {"current_steps": 42030, "total_steps": 76960, "loss": 0.1756, "lr": 2.533903160734047e-05, "epoch": 10.922557172557173, "percentage": 54.61, "elapsed_time": "1:00:58", "remaining_time": "0:50:40", "throughput": 1034.6, "total_tokens": 3785048} {"current_steps": 42035, "total_steps": 76960, "loss": 0.159, "lr": 2.5333362521375013e-05, "epoch": 10.923856548856548, "percentage": 54.62, "elapsed_time": "1:00:58", "remaining_time": "0:50:39", "throughput": 1034.61, "total_tokens": 3785496} {"current_steps": 42040, "total_steps": 76960, "loss": 0.1384, "lr": 2.5327693418264397e-05, "epoch": 10.925155925155925, "percentage": 54.63, "elapsed_time": "1:00:59", "remaining_time": "0:50:39", "throughput": 1034.61, "total_tokens": 3785944} {"current_steps": 42045, "total_steps": 76960, "loss": 0.2291, "lr": 2.53220242983002e-05, "epoch": 10.926455301455302, "percentage": 54.63, "elapsed_time": "1:00:59", "remaining_time": "0:50:39", "throughput": 1034.62, "total_tokens": 3786424} {"current_steps": 42050, "total_steps": 76960, "loss": 0.448, "lr": 2.531635516177399e-05, "epoch": 10.927754677754677, "percentage": 54.64, "elapsed_time": "1:01:00", "remaining_time": "0:50:38", "throughput": 1034.63, "total_tokens": 3786872} {"current_steps": 42055, "total_steps": 76960, "loss": 0.165, "lr": 2.5310686008977326e-05, "epoch": 10.929054054054054, "percentage": 54.65, "elapsed_time": "1:01:00", "remaining_time": "0:50:38", "throughput": 1034.63, "total_tokens": 3787320} {"current_steps": 42060, "total_steps": 76960, "loss": 0.0933, "lr": 2.530501684020178e-05, "epoch": 10.93035343035343, "percentage": 54.65, "elapsed_time": "1:01:00", "remaining_time": "0:50:37", "throughput": 1034.64, "total_tokens": 3787768} {"current_steps": 42065, "total_steps": 76960, "loss": 0.2142, "lr": 2.529934765573893e-05, "epoch": 10.931652806652806, "percentage": 54.66, "elapsed_time": "1:01:01", "remaining_time": "0:50:37", "throughput": 1034.63, "total_tokens": 3788184} {"current_steps": 42070, "total_steps": 76960, "loss": 0.2494, "lr": 2.5293678455880343e-05, "epoch": 10.932952182952183, "percentage": 54.66, "elapsed_time": "1:01:01", "remaining_time": "0:50:36", "throughput": 1034.64, "total_tokens": 3788632} {"current_steps": 42075, "total_steps": 76960, "loss": 0.1891, "lr": 2.528800924091758e-05, "epoch": 10.934251559251559, "percentage": 54.67, "elapsed_time": "1:01:02", "remaining_time": "0:50:36", "throughput": 1034.65, "total_tokens": 3789096} {"current_steps": 42080, "total_steps": 76960, "loss": 0.3653, "lr": 2.528234001114224e-05, "epoch": 10.935550935550935, "percentage": 54.68, "elapsed_time": "1:01:02", "remaining_time": "0:50:35", "throughput": 1034.66, "total_tokens": 3789576} {"current_steps": 42085, "total_steps": 76960, "loss": 0.2307, "lr": 2.527667076684588e-05, "epoch": 10.936850311850312, "percentage": 54.68, "elapsed_time": "1:01:03", "remaining_time": "0:50:35", "throughput": 1034.66, "total_tokens": 3790008} {"current_steps": 42090, "total_steps": 76960, "loss": 0.3684, "lr": 2.527100150832008e-05, "epoch": 10.938149688149688, "percentage": 54.69, "elapsed_time": "1:01:03", "remaining_time": "0:50:35", "throughput": 1034.66, "total_tokens": 3790440} {"current_steps": 42095, "total_steps": 76960, "loss": 0.1253, "lr": 2.526533223585641e-05, "epoch": 10.939449064449065, "percentage": 54.7, "elapsed_time": "1:01:03", "remaining_time": "0:50:34", "throughput": 1034.67, "total_tokens": 3790904} {"current_steps": 42100, "total_steps": 76960, "loss": 0.3663, "lr": 2.525966294974645e-05, "epoch": 10.940748440748441, "percentage": 54.7, "elapsed_time": "1:01:04", "remaining_time": "0:50:34", "throughput": 1034.67, "total_tokens": 3791320} {"current_steps": 42105, "total_steps": 76960, "loss": 0.2114, "lr": 2.525399365028177e-05, "epoch": 10.942047817047817, "percentage": 54.71, "elapsed_time": "1:01:04", "remaining_time": "0:50:33", "throughput": 1034.67, "total_tokens": 3791768} {"current_steps": 42110, "total_steps": 76960, "loss": 0.4161, "lr": 2.5248324337753953e-05, "epoch": 10.943347193347194, "percentage": 54.72, "elapsed_time": "1:01:05", "remaining_time": "0:50:33", "throughput": 1034.67, "total_tokens": 3792216} {"current_steps": 42115, "total_steps": 76960, "loss": 0.4144, "lr": 2.524265501245458e-05, "epoch": 10.94464656964657, "percentage": 54.72, "elapsed_time": "1:01:05", "remaining_time": "0:50:32", "throughput": 1034.68, "total_tokens": 3792680} {"current_steps": 42120, "total_steps": 76960, "loss": 0.1516, "lr": 2.523698567467523e-05, "epoch": 10.945945945945946, "percentage": 54.73, "elapsed_time": "1:01:05", "remaining_time": "0:50:32", "throughput": 1034.69, "total_tokens": 3793144} {"current_steps": 42125, "total_steps": 76960, "loss": 0.2897, "lr": 2.5231316324707482e-05, "epoch": 10.947245322245323, "percentage": 54.74, "elapsed_time": "1:01:06", "remaining_time": "0:50:31", "throughput": 1034.7, "total_tokens": 3793592} {"current_steps": 42130, "total_steps": 76960, "loss": 0.0835, "lr": 2.5225646962842904e-05, "epoch": 10.948544698544698, "percentage": 54.74, "elapsed_time": "1:01:06", "remaining_time": "0:50:31", "throughput": 1034.71, "total_tokens": 3794072} {"current_steps": 42135, "total_steps": 76960, "loss": 0.182, "lr": 2.5219977589373093e-05, "epoch": 10.949844074844075, "percentage": 54.75, "elapsed_time": "1:01:07", "remaining_time": "0:50:30", "throughput": 1034.72, "total_tokens": 3794520} {"current_steps": 42140, "total_steps": 76960, "loss": 0.3465, "lr": 2.5214308204589626e-05, "epoch": 10.951143451143452, "percentage": 54.76, "elapsed_time": "1:01:07", "remaining_time": "0:50:30", "throughput": 1034.72, "total_tokens": 3794984} {"current_steps": 42145, "total_steps": 76960, "loss": 0.1122, "lr": 2.520863880878408e-05, "epoch": 10.952442827442827, "percentage": 54.76, "elapsed_time": "1:01:08", "remaining_time": "0:50:30", "throughput": 1034.73, "total_tokens": 3795416} {"current_steps": 42150, "total_steps": 76960, "loss": 0.1384, "lr": 2.5202969402248033e-05, "epoch": 10.953742203742204, "percentage": 54.77, "elapsed_time": "1:01:08", "remaining_time": "0:50:29", "throughput": 1034.73, "total_tokens": 3795880} {"current_steps": 42155, "total_steps": 76960, "loss": 0.2889, "lr": 2.519729998527309e-05, "epoch": 10.95504158004158, "percentage": 54.78, "elapsed_time": "1:01:08", "remaining_time": "0:50:29", "throughput": 1034.74, "total_tokens": 3796344} {"current_steps": 42160, "total_steps": 76960, "loss": 0.332, "lr": 2.5191630558150816e-05, "epoch": 10.956340956340956, "percentage": 54.78, "elapsed_time": "1:01:09", "remaining_time": "0:50:28", "throughput": 1034.74, "total_tokens": 3796760} {"current_steps": 42165, "total_steps": 76960, "loss": 0.3307, "lr": 2.5185961121172785e-05, "epoch": 10.957640332640333, "percentage": 54.79, "elapsed_time": "1:01:09", "remaining_time": "0:50:28", "throughput": 1034.75, "total_tokens": 3797224} {"current_steps": 42170, "total_steps": 76960, "loss": 0.1767, "lr": 2.5180291674630608e-05, "epoch": 10.95893970893971, "percentage": 54.79, "elapsed_time": "1:01:10", "remaining_time": "0:50:27", "throughput": 1034.75, "total_tokens": 3797656} {"current_steps": 42175, "total_steps": 76960, "loss": 0.3708, "lr": 2.5174622218815852e-05, "epoch": 10.960239085239085, "percentage": 54.8, "elapsed_time": "1:01:10", "remaining_time": "0:50:27", "throughput": 1034.75, "total_tokens": 3798104} {"current_steps": 42180, "total_steps": 76960, "loss": 0.34, "lr": 2.5168952754020115e-05, "epoch": 10.961538461538462, "percentage": 54.81, "elapsed_time": "1:01:10", "remaining_time": "0:50:26", "throughput": 1034.74, "total_tokens": 3798504} {"current_steps": 42185, "total_steps": 76960, "loss": 0.29, "lr": 2.5163283280534964e-05, "epoch": 10.962837837837839, "percentage": 54.81, "elapsed_time": "1:01:11", "remaining_time": "0:50:26", "throughput": 1034.75, "total_tokens": 3798968} {"current_steps": 42190, "total_steps": 76960, "loss": 0.3275, "lr": 2.5157613798652008e-05, "epoch": 10.964137214137214, "percentage": 54.82, "elapsed_time": "1:01:11", "remaining_time": "0:50:26", "throughput": 1034.75, "total_tokens": 3799400} {"current_steps": 42195, "total_steps": 76960, "loss": 0.1753, "lr": 2.5151944308662824e-05, "epoch": 10.96543659043659, "percentage": 54.83, "elapsed_time": "1:01:12", "remaining_time": "0:50:25", "throughput": 1034.77, "total_tokens": 3799880} {"current_steps": 42200, "total_steps": 76960, "loss": 0.3419, "lr": 2.5146274810858988e-05, "epoch": 10.966735966735968, "percentage": 54.83, "elapsed_time": "1:01:12", "remaining_time": "0:50:25", "throughput": 1034.78, "total_tokens": 3800344} {"current_steps": 42205, "total_steps": 76960, "loss": 0.1839, "lr": 2.5140605305532104e-05, "epoch": 10.968035343035343, "percentage": 54.84, "elapsed_time": "1:01:13", "remaining_time": "0:50:24", "throughput": 1034.78, "total_tokens": 3800776} {"current_steps": 42210, "total_steps": 76960, "loss": 0.1634, "lr": 2.5134935792973757e-05, "epoch": 10.96933471933472, "percentage": 54.85, "elapsed_time": "1:01:13", "remaining_time": "0:50:24", "throughput": 1034.78, "total_tokens": 3801224} {"current_steps": 42215, "total_steps": 76960, "loss": 0.0569, "lr": 2.512926627347553e-05, "epoch": 10.970634095634095, "percentage": 54.85, "elapsed_time": "1:01:13", "remaining_time": "0:50:23", "throughput": 1034.79, "total_tokens": 3801688} {"current_steps": 42220, "total_steps": 76960, "loss": 0.205, "lr": 2.512359674732902e-05, "epoch": 10.971933471933472, "percentage": 54.86, "elapsed_time": "1:01:14", "remaining_time": "0:50:23", "throughput": 1034.79, "total_tokens": 3802120} {"current_steps": 42225, "total_steps": 76960, "loss": 0.5008, "lr": 2.511792721482581e-05, "epoch": 10.973232848232849, "percentage": 54.87, "elapsed_time": "1:01:14", "remaining_time": "0:50:22", "throughput": 1034.8, "total_tokens": 3802584} {"current_steps": 42230, "total_steps": 76960, "loss": 0.49, "lr": 2.5112257676257484e-05, "epoch": 10.974532224532224, "percentage": 54.87, "elapsed_time": "1:01:15", "remaining_time": "0:50:22", "throughput": 1034.82, "total_tokens": 3803080} {"current_steps": 42235, "total_steps": 76960, "loss": 0.2984, "lr": 2.5106588131915636e-05, "epoch": 10.9758316008316, "percentage": 54.88, "elapsed_time": "1:01:15", "remaining_time": "0:50:21", "throughput": 1034.81, "total_tokens": 3803496} {"current_steps": 42240, "total_steps": 76960, "loss": 0.3165, "lr": 2.5100918582091864e-05, "epoch": 10.977130977130978, "percentage": 54.89, "elapsed_time": "1:01:15", "remaining_time": "0:50:21", "throughput": 1034.81, "total_tokens": 3803928} {"current_steps": 42245, "total_steps": 76960, "loss": 0.1046, "lr": 2.5095249027077757e-05, "epoch": 10.978430353430353, "percentage": 54.89, "elapsed_time": "1:01:16", "remaining_time": "0:50:21", "throughput": 1034.81, "total_tokens": 3804360} {"current_steps": 42250, "total_steps": 76960, "loss": 0.1765, "lr": 2.5089579467164898e-05, "epoch": 10.97972972972973, "percentage": 54.9, "elapsed_time": "1:01:16", "remaining_time": "0:50:20", "throughput": 1034.83, "total_tokens": 3804840} {"current_steps": 42255, "total_steps": 76960, "loss": 0.4251, "lr": 2.5083909902644875e-05, "epoch": 10.981029106029107, "percentage": 54.91, "elapsed_time": "1:01:17", "remaining_time": "0:50:20", "throughput": 1034.83, "total_tokens": 3805272} {"current_steps": 42260, "total_steps": 76960, "loss": 0.2963, "lr": 2.5078240333809287e-05, "epoch": 10.982328482328482, "percentage": 54.91, "elapsed_time": "1:01:17", "remaining_time": "0:50:19", "throughput": 1034.84, "total_tokens": 3805768} {"current_steps": 42265, "total_steps": 76960, "loss": 0.3403, "lr": 2.5072570760949733e-05, "epoch": 10.983627858627859, "percentage": 54.92, "elapsed_time": "1:01:18", "remaining_time": "0:50:19", "throughput": 1034.85, "total_tokens": 3806200} {"current_steps": 42270, "total_steps": 76960, "loss": 0.3338, "lr": 2.506690118435779e-05, "epoch": 10.984927234927234, "percentage": 54.92, "elapsed_time": "1:01:18", "remaining_time": "0:50:18", "throughput": 1034.85, "total_tokens": 3806632} {"current_steps": 42275, "total_steps": 76960, "loss": 0.1923, "lr": 2.5061231604325046e-05, "epoch": 10.986226611226611, "percentage": 54.93, "elapsed_time": "1:01:18", "remaining_time": "0:50:18", "throughput": 1034.84, "total_tokens": 3807048} {"current_steps": 42280, "total_steps": 76960, "loss": 0.1286, "lr": 2.505556202114311e-05, "epoch": 10.987525987525988, "percentage": 54.94, "elapsed_time": "1:01:19", "remaining_time": "0:50:17", "throughput": 1034.85, "total_tokens": 3807512} {"current_steps": 42285, "total_steps": 76960, "loss": 0.1856, "lr": 2.5049892435103573e-05, "epoch": 10.988825363825363, "percentage": 54.94, "elapsed_time": "1:01:19", "remaining_time": "0:50:17", "throughput": 1034.85, "total_tokens": 3807944} {"current_steps": 42290, "total_steps": 76960, "loss": 0.1558, "lr": 2.5044222846498012e-05, "epoch": 10.99012474012474, "percentage": 54.95, "elapsed_time": "1:01:20", "remaining_time": "0:50:17", "throughput": 1034.86, "total_tokens": 3808392} {"current_steps": 42295, "total_steps": 76960, "loss": 0.2328, "lr": 2.5038553255618026e-05, "epoch": 10.991424116424117, "percentage": 54.96, "elapsed_time": "1:01:20", "remaining_time": "0:50:16", "throughput": 1034.87, "total_tokens": 3808872} {"current_steps": 42300, "total_steps": 76960, "loss": 0.2707, "lr": 2.5032883662755213e-05, "epoch": 10.992723492723492, "percentage": 54.96, "elapsed_time": "1:01:20", "remaining_time": "0:50:16", "throughput": 1034.86, "total_tokens": 3809288} {"current_steps": 42305, "total_steps": 76960, "loss": 0.3039, "lr": 2.502721406820116e-05, "epoch": 10.994022869022869, "percentage": 54.97, "elapsed_time": "1:01:21", "remaining_time": "0:50:15", "throughput": 1034.87, "total_tokens": 3809736} {"current_steps": 42310, "total_steps": 76960, "loss": 0.2289, "lr": 2.502154447224746e-05, "epoch": 10.995322245322246, "percentage": 54.98, "elapsed_time": "1:01:21", "remaining_time": "0:50:15", "throughput": 1034.88, "total_tokens": 3810200} {"current_steps": 42315, "total_steps": 76960, "loss": 0.0686, "lr": 2.5015874875185708e-05, "epoch": 10.996621621621621, "percentage": 54.98, "elapsed_time": "1:01:22", "remaining_time": "0:50:14", "throughput": 1034.87, "total_tokens": 3810600} {"current_steps": 42320, "total_steps": 76960, "loss": 0.1823, "lr": 2.5010205277307498e-05, "epoch": 10.997920997920998, "percentage": 54.99, "elapsed_time": "1:01:22", "remaining_time": "0:50:14", "throughput": 1034.87, "total_tokens": 3811032} {"current_steps": 42325, "total_steps": 76960, "loss": 0.2284, "lr": 2.500453567890442e-05, "epoch": 10.999220374220375, "percentage": 55.0, "elapsed_time": "1:01:23", "remaining_time": "0:50:13", "throughput": 1034.88, "total_tokens": 3811480} {"current_steps": 42328, "total_steps": 76960, "eval_loss": 0.2862201929092407, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "1:01:36", "remaining_time": "0:50:24", "throughput": 1031.15, "total_tokens": 3811696} {"current_steps": 42330, "total_steps": 76960, "loss": 0.2435, "lr": 2.4998866080268067e-05, "epoch": 11.00051975051975, "percentage": 55.0, "elapsed_time": "1:01:38", "remaining_time": "0:50:25", "throughput": 1030.7, "total_tokens": 3811904} {"current_steps": 42335, "total_steps": 76960, "loss": 0.3411, "lr": 2.4993196481690038e-05, "epoch": 11.001819126819127, "percentage": 55.01, "elapsed_time": "1:01:38", "remaining_time": "0:50:25", "throughput": 1030.7, "total_tokens": 3812352} {"current_steps": 42340, "total_steps": 76960, "loss": 0.3118, "lr": 2.498752688346191e-05, "epoch": 11.003118503118504, "percentage": 55.02, "elapsed_time": "1:01:39", "remaining_time": "0:50:24", "throughput": 1030.69, "total_tokens": 3812784} {"current_steps": 42345, "total_steps": 76960, "loss": 0.3588, "lr": 2.4981857285875295e-05, "epoch": 11.004417879417879, "percentage": 55.02, "elapsed_time": "1:01:39", "remaining_time": "0:50:24", "throughput": 1030.69, "total_tokens": 3813232} {"current_steps": 42350, "total_steps": 76960, "loss": 0.2678, "lr": 2.4976187689221765e-05, "epoch": 11.005717255717256, "percentage": 55.03, "elapsed_time": "1:01:40", "remaining_time": "0:50:23", "throughput": 1030.7, "total_tokens": 3813696} {"current_steps": 42355, "total_steps": 76960, "loss": 0.2236, "lr": 2.4970518093792944e-05, "epoch": 11.007016632016631, "percentage": 55.04, "elapsed_time": "1:01:40", "remaining_time": "0:50:23", "throughput": 1030.71, "total_tokens": 3814144} {"current_steps": 42360, "total_steps": 76960, "loss": 0.1661, "lr": 2.496484849988039e-05, "epoch": 11.008316008316008, "percentage": 55.04, "elapsed_time": "1:01:40", "remaining_time": "0:50:22", "throughput": 1030.7, "total_tokens": 3814560} {"current_steps": 42365, "total_steps": 76960, "loss": 0.1507, "lr": 2.495917890777572e-05, "epoch": 11.009615384615385, "percentage": 55.05, "elapsed_time": "1:01:41", "remaining_time": "0:50:22", "throughput": 1030.7, "total_tokens": 3815008} {"current_steps": 42370, "total_steps": 76960, "loss": 0.1594, "lr": 2.495350931777051e-05, "epoch": 11.01091476091476, "percentage": 55.05, "elapsed_time": "1:01:41", "remaining_time": "0:50:22", "throughput": 1030.71, "total_tokens": 3815472} {"current_steps": 42375, "total_steps": 76960, "loss": 0.2255, "lr": 2.4947839730156372e-05, "epoch": 11.012214137214137, "percentage": 55.06, "elapsed_time": "1:01:42", "remaining_time": "0:50:21", "throughput": 1030.71, "total_tokens": 3815888} {"current_steps": 42380, "total_steps": 76960, "loss": 0.2564, "lr": 2.4942170145224874e-05, "epoch": 11.013513513513514, "percentage": 55.07, "elapsed_time": "1:01:42", "remaining_time": "0:50:21", "throughput": 1030.71, "total_tokens": 3816336} {"current_steps": 42385, "total_steps": 76960, "loss": 0.2615, "lr": 2.4936500563267627e-05, "epoch": 11.01481288981289, "percentage": 55.07, "elapsed_time": "1:01:43", "remaining_time": "0:50:20", "throughput": 1030.73, "total_tokens": 3816832} {"current_steps": 42390, "total_steps": 76960, "loss": 0.1725, "lr": 2.493083098457622e-05, "epoch": 11.016112266112266, "percentage": 55.08, "elapsed_time": "1:01:43", "remaining_time": "0:50:20", "throughput": 1030.73, "total_tokens": 3817296} {"current_steps": 42395, "total_steps": 76960, "loss": 0.2777, "lr": 2.492516140944224e-05, "epoch": 11.017411642411643, "percentage": 55.09, "elapsed_time": "1:01:43", "remaining_time": "0:50:19", "throughput": 1030.74, "total_tokens": 3817760} {"current_steps": 42400, "total_steps": 76960, "loss": 0.3057, "lr": 2.4919491838157278e-05, "epoch": 11.018711018711018, "percentage": 55.09, "elapsed_time": "1:01:44", "remaining_time": "0:50:19", "throughput": 1030.75, "total_tokens": 3818224} {"current_steps": 42405, "total_steps": 76960, "loss": 0.3606, "lr": 2.4913822271012923e-05, "epoch": 11.020010395010395, "percentage": 55.1, "elapsed_time": "1:01:44", "remaining_time": "0:50:18", "throughput": 1030.76, "total_tokens": 3818688} {"current_steps": 42410, "total_steps": 76960, "loss": 0.1461, "lr": 2.4908152708300784e-05, "epoch": 11.021309771309772, "percentage": 55.11, "elapsed_time": "1:01:45", "remaining_time": "0:50:18", "throughput": 1030.77, "total_tokens": 3819168} {"current_steps": 42415, "total_steps": 76960, "loss": 0.1783, "lr": 2.4902483150312428e-05, "epoch": 11.022609147609147, "percentage": 55.11, "elapsed_time": "1:01:45", "remaining_time": "0:50:18", "throughput": 1030.78, "total_tokens": 3819616} {"current_steps": 42420, "total_steps": 76960, "loss": 0.2611, "lr": 2.489681359733946e-05, "epoch": 11.023908523908524, "percentage": 55.12, "elapsed_time": "1:01:45", "remaining_time": "0:50:17", "throughput": 1030.79, "total_tokens": 3820096} {"current_steps": 42425, "total_steps": 76960, "loss": 0.1447, "lr": 2.4891144049673464e-05, "epoch": 11.025207900207901, "percentage": 55.13, "elapsed_time": "1:01:46", "remaining_time": "0:50:17", "throughput": 1030.8, "total_tokens": 3820544} {"current_steps": 42430, "total_steps": 76960, "loss": 0.2007, "lr": 2.4885474507606045e-05, "epoch": 11.026507276507276, "percentage": 55.13, "elapsed_time": "1:01:46", "remaining_time": "0:50:16", "throughput": 1030.81, "total_tokens": 3821008} {"current_steps": 42435, "total_steps": 76960, "loss": 0.3271, "lr": 2.4879804971428768e-05, "epoch": 11.027806652806653, "percentage": 55.14, "elapsed_time": "1:01:47", "remaining_time": "0:50:16", "throughput": 1030.81, "total_tokens": 3821456} {"current_steps": 42440, "total_steps": 76960, "loss": 0.1985, "lr": 2.487413544143325e-05, "epoch": 11.029106029106028, "percentage": 55.15, "elapsed_time": "1:01:47", "remaining_time": "0:50:15", "throughput": 1030.82, "total_tokens": 3821904} {"current_steps": 42445, "total_steps": 76960, "loss": 0.2054, "lr": 2.4868465917911053e-05, "epoch": 11.030405405405405, "percentage": 55.15, "elapsed_time": "1:01:48", "remaining_time": "0:50:15", "throughput": 1030.82, "total_tokens": 3822352} {"current_steps": 42450, "total_steps": 76960, "loss": 0.2025, "lr": 2.4862796401153792e-05, "epoch": 11.031704781704782, "percentage": 55.16, "elapsed_time": "1:01:48", "remaining_time": "0:50:14", "throughput": 1030.83, "total_tokens": 3822800} {"current_steps": 42455, "total_steps": 76960, "loss": 0.133, "lr": 2.4857126891453046e-05, "epoch": 11.033004158004157, "percentage": 55.17, "elapsed_time": "1:01:48", "remaining_time": "0:50:14", "throughput": 1030.83, "total_tokens": 3823248} {"current_steps": 42460, "total_steps": 76960, "loss": 0.206, "lr": 2.485145738910039e-05, "epoch": 11.034303534303534, "percentage": 55.17, "elapsed_time": "1:01:49", "remaining_time": "0:50:13", "throughput": 1030.84, "total_tokens": 3823728} {"current_steps": 42465, "total_steps": 76960, "loss": 0.1798, "lr": 2.4845787894387425e-05, "epoch": 11.035602910602911, "percentage": 55.18, "elapsed_time": "1:01:49", "remaining_time": "0:50:13", "throughput": 1030.85, "total_tokens": 3824192} {"current_steps": 42470, "total_steps": 76960, "loss": 0.104, "lr": 2.4840118407605734e-05, "epoch": 11.036902286902286, "percentage": 55.18, "elapsed_time": "1:01:50", "remaining_time": "0:50:13", "throughput": 1030.85, "total_tokens": 3824624} {"current_steps": 42475, "total_steps": 76960, "loss": 0.3622, "lr": 2.4834448929046918e-05, "epoch": 11.038201663201663, "percentage": 55.19, "elapsed_time": "1:01:50", "remaining_time": "0:50:12", "throughput": 1030.86, "total_tokens": 3825088} {"current_steps": 42480, "total_steps": 76960, "loss": 0.1412, "lr": 2.482877945900254e-05, "epoch": 11.03950103950104, "percentage": 55.2, "elapsed_time": "1:01:50", "remaining_time": "0:50:12", "throughput": 1030.86, "total_tokens": 3825520} {"current_steps": 42485, "total_steps": 76960, "loss": 0.1585, "lr": 2.4823109997764206e-05, "epoch": 11.040800415800415, "percentage": 55.2, "elapsed_time": "1:01:51", "remaining_time": "0:50:11", "throughput": 1030.86, "total_tokens": 3825952} {"current_steps": 42490, "total_steps": 76960, "loss": 0.0966, "lr": 2.4817440545623486e-05, "epoch": 11.042099792099792, "percentage": 55.21, "elapsed_time": "1:01:51", "remaining_time": "0:50:11", "throughput": 1030.86, "total_tokens": 3826384} {"current_steps": 42495, "total_steps": 76960, "loss": 0.3961, "lr": 2.4811771102871985e-05, "epoch": 11.04339916839917, "percentage": 55.22, "elapsed_time": "1:01:52", "remaining_time": "0:50:10", "throughput": 1030.86, "total_tokens": 3826816} {"current_steps": 42500, "total_steps": 76960, "loss": 0.4114, "lr": 2.4806101669801266e-05, "epoch": 11.044698544698544, "percentage": 55.22, "elapsed_time": "1:01:52", "remaining_time": "0:50:10", "throughput": 1030.87, "total_tokens": 3827264} {"current_steps": 42505, "total_steps": 76960, "loss": 0.4136, "lr": 2.4800432246702928e-05, "epoch": 11.045997920997921, "percentage": 55.23, "elapsed_time": "1:01:53", "remaining_time": "0:50:09", "throughput": 1030.88, "total_tokens": 3827744} {"current_steps": 42510, "total_steps": 76960, "loss": 0.2671, "lr": 2.479476283386855e-05, "epoch": 11.047297297297296, "percentage": 55.24, "elapsed_time": "1:01:53", "remaining_time": "0:50:09", "throughput": 1030.89, "total_tokens": 3828208} {"current_steps": 42515, "total_steps": 76960, "loss": 0.2634, "lr": 2.478909343158972e-05, "epoch": 11.048596673596673, "percentage": 55.24, "elapsed_time": "1:01:53", "remaining_time": "0:50:08", "throughput": 1030.91, "total_tokens": 3828704} {"current_steps": 42520, "total_steps": 76960, "loss": 0.2196, "lr": 2.4783424040158018e-05, "epoch": 11.04989604989605, "percentage": 55.25, "elapsed_time": "1:01:54", "remaining_time": "0:50:08", "throughput": 1030.92, "total_tokens": 3829152} {"current_steps": 42525, "total_steps": 76960, "loss": 0.4359, "lr": 2.4777754659865015e-05, "epoch": 11.051195426195425, "percentage": 55.26, "elapsed_time": "1:01:54", "remaining_time": "0:50:08", "throughput": 1030.92, "total_tokens": 3829584} {"current_steps": 42530, "total_steps": 76960, "loss": 0.3182, "lr": 2.4772085291002318e-05, "epoch": 11.052494802494802, "percentage": 55.26, "elapsed_time": "1:01:55", "remaining_time": "0:50:07", "throughput": 1030.92, "total_tokens": 3830032} {"current_steps": 42535, "total_steps": 76960, "loss": 0.1378, "lr": 2.476641593386148e-05, "epoch": 11.05379417879418, "percentage": 55.27, "elapsed_time": "1:01:55", "remaining_time": "0:50:07", "throughput": 1030.92, "total_tokens": 3830448} {"current_steps": 42540, "total_steps": 76960, "loss": 0.2673, "lr": 2.47607465887341e-05, "epoch": 11.055093555093555, "percentage": 55.28, "elapsed_time": "1:01:55", "remaining_time": "0:50:06", "throughput": 1030.92, "total_tokens": 3830896} {"current_steps": 42545, "total_steps": 76960, "loss": 0.2021, "lr": 2.4755077255911743e-05, "epoch": 11.056392931392931, "percentage": 55.28, "elapsed_time": "1:01:56", "remaining_time": "0:50:06", "throughput": 1030.92, "total_tokens": 3831328} {"current_steps": 42550, "total_steps": 76960, "loss": 0.3015, "lr": 2.4749407935686014e-05, "epoch": 11.057692307692308, "percentage": 55.29, "elapsed_time": "1:01:56", "remaining_time": "0:50:05", "throughput": 1030.92, "total_tokens": 3831776} {"current_steps": 42555, "total_steps": 76960, "loss": 0.132, "lr": 2.4743738628348463e-05, "epoch": 11.058991683991684, "percentage": 55.29, "elapsed_time": "1:01:57", "remaining_time": "0:50:05", "throughput": 1030.93, "total_tokens": 3832240} {"current_steps": 42560, "total_steps": 76960, "loss": 0.2313, "lr": 2.473806933419068e-05, "epoch": 11.06029106029106, "percentage": 55.3, "elapsed_time": "1:01:57", "remaining_time": "0:50:04", "throughput": 1030.93, "total_tokens": 3832672} {"current_steps": 42565, "total_steps": 76960, "loss": 0.0778, "lr": 2.4732400053504243e-05, "epoch": 11.061590436590437, "percentage": 55.31, "elapsed_time": "1:01:58", "remaining_time": "0:50:04", "throughput": 1030.94, "total_tokens": 3833136} {"current_steps": 42570, "total_steps": 76960, "loss": 0.2173, "lr": 2.4726730786580735e-05, "epoch": 11.062889812889813, "percentage": 55.31, "elapsed_time": "1:01:58", "remaining_time": "0:50:03", "throughput": 1030.94, "total_tokens": 3833584} {"current_steps": 42575, "total_steps": 76960, "loss": 0.3106, "lr": 2.4721061533711716e-05, "epoch": 11.06418918918919, "percentage": 55.32, "elapsed_time": "1:01:58", "remaining_time": "0:50:03", "throughput": 1030.96, "total_tokens": 3834064} {"current_steps": 42580, "total_steps": 76960, "loss": 0.057, "lr": 2.4715392295188772e-05, "epoch": 11.065488565488565, "percentage": 55.33, "elapsed_time": "1:01:59", "remaining_time": "0:50:03", "throughput": 1030.97, "total_tokens": 3834528} {"current_steps": 42585, "total_steps": 76960, "loss": 0.2131, "lr": 2.4709723071303485e-05, "epoch": 11.066787941787942, "percentage": 55.33, "elapsed_time": "1:01:59", "remaining_time": "0:50:02", "throughput": 1030.97, "total_tokens": 3834976} {"current_steps": 42590, "total_steps": 76960, "loss": 0.0241, "lr": 2.4704053862347402e-05, "epoch": 11.068087318087318, "percentage": 55.34, "elapsed_time": "1:02:00", "remaining_time": "0:50:02", "throughput": 1030.98, "total_tokens": 3835424} {"current_steps": 42595, "total_steps": 76960, "loss": 0.4571, "lr": 2.469838466861212e-05, "epoch": 11.069386694386694, "percentage": 55.35, "elapsed_time": "1:02:00", "remaining_time": "0:50:01", "throughput": 1030.99, "total_tokens": 3835904} {"current_steps": 42600, "total_steps": 76960, "loss": 0.3894, "lr": 2.4692715490389202e-05, "epoch": 11.07068607068607, "percentage": 55.35, "elapsed_time": "1:02:01", "remaining_time": "0:50:01", "throughput": 1031.0, "total_tokens": 3836384} {"current_steps": 42605, "total_steps": 76960, "loss": 0.366, "lr": 2.4687046327970227e-05, "epoch": 11.071985446985448, "percentage": 55.36, "elapsed_time": "1:02:01", "remaining_time": "0:50:00", "throughput": 1031.01, "total_tokens": 3836832} {"current_steps": 42610, "total_steps": 76960, "loss": 0.2217, "lr": 2.4681377181646752e-05, "epoch": 11.073284823284823, "percentage": 55.37, "elapsed_time": "1:02:01", "remaining_time": "0:50:00", "throughput": 1031.0, "total_tokens": 3837248} {"current_steps": 42615, "total_steps": 76960, "loss": 0.4056, "lr": 2.4675708051710355e-05, "epoch": 11.0745841995842, "percentage": 55.37, "elapsed_time": "1:02:02", "remaining_time": "0:49:59", "throughput": 1031.02, "total_tokens": 3837728} {"current_steps": 42620, "total_steps": 76960, "loss": 0.2957, "lr": 2.46700389384526e-05, "epoch": 11.075883575883577, "percentage": 55.38, "elapsed_time": "1:02:02", "remaining_time": "0:49:59", "throughput": 1031.03, "total_tokens": 3838192} {"current_steps": 42625, "total_steps": 76960, "loss": 0.1769, "lr": 2.4664369842165068e-05, "epoch": 11.077182952182952, "percentage": 55.39, "elapsed_time": "1:02:03", "remaining_time": "0:49:59", "throughput": 1031.04, "total_tokens": 3838672} {"current_steps": 42630, "total_steps": 76960, "loss": 0.1281, "lr": 2.465870076313931e-05, "epoch": 11.078482328482329, "percentage": 55.39, "elapsed_time": "1:02:03", "remaining_time": "0:49:58", "throughput": 1031.05, "total_tokens": 3839120} {"current_steps": 42635, "total_steps": 76960, "loss": 0.5147, "lr": 2.4653031701666902e-05, "epoch": 11.079781704781706, "percentage": 55.4, "elapsed_time": "1:02:03", "remaining_time": "0:49:58", "throughput": 1031.05, "total_tokens": 3839552} {"current_steps": 42640, "total_steps": 76960, "loss": 0.1912, "lr": 2.46473626580394e-05, "epoch": 11.08108108108108, "percentage": 55.41, "elapsed_time": "1:02:04", "remaining_time": "0:49:57", "throughput": 1031.05, "total_tokens": 3839984} {"current_steps": 42645, "total_steps": 76960, "loss": 0.365, "lr": 2.4641693632548385e-05, "epoch": 11.082380457380458, "percentage": 55.41, "elapsed_time": "1:02:04", "remaining_time": "0:49:57", "throughput": 1031.05, "total_tokens": 3840416} {"current_steps": 42650, "total_steps": 76960, "loss": 0.2678, "lr": 2.4636024625485403e-05, "epoch": 11.083679833679835, "percentage": 55.42, "elapsed_time": "1:02:05", "remaining_time": "0:49:56", "throughput": 1031.05, "total_tokens": 3840848} {"current_steps": 42655, "total_steps": 76960, "loss": 0.2857, "lr": 2.463035563714202e-05, "epoch": 11.08497920997921, "percentage": 55.42, "elapsed_time": "1:02:05", "remaining_time": "0:49:56", "throughput": 1031.08, "total_tokens": 3841376} {"current_steps": 42660, "total_steps": 76960, "loss": 0.178, "lr": 2.462468666780981e-05, "epoch": 11.086278586278587, "percentage": 55.43, "elapsed_time": "1:02:06", "remaining_time": "0:49:55", "throughput": 1031.08, "total_tokens": 3841824} {"current_steps": 42665, "total_steps": 76960, "loss": 0.1287, "lr": 2.4619017717780316e-05, "epoch": 11.087577962577962, "percentage": 55.44, "elapsed_time": "1:02:06", "remaining_time": "0:49:55", "throughput": 1031.09, "total_tokens": 3842256} {"current_steps": 42670, "total_steps": 76960, "loss": 0.2201, "lr": 2.461334878734511e-05, "epoch": 11.088877338877339, "percentage": 55.44, "elapsed_time": "1:02:06", "remaining_time": "0:49:54", "throughput": 1031.09, "total_tokens": 3842688} {"current_steps": 42675, "total_steps": 76960, "loss": 0.2011, "lr": 2.4607679876795738e-05, "epoch": 11.090176715176716, "percentage": 55.45, "elapsed_time": "1:02:07", "remaining_time": "0:49:54", "throughput": 1031.09, "total_tokens": 3843120} {"current_steps": 42680, "total_steps": 76960, "loss": 0.2326, "lr": 2.4602010986423782e-05, "epoch": 11.09147609147609, "percentage": 55.46, "elapsed_time": "1:02:07", "remaining_time": "0:49:54", "throughput": 1031.09, "total_tokens": 3843552} {"current_steps": 42685, "total_steps": 76960, "loss": 0.0885, "lr": 2.459634211652076e-05, "epoch": 11.092775467775468, "percentage": 55.46, "elapsed_time": "1:02:08", "remaining_time": "0:49:53", "throughput": 1031.08, "total_tokens": 3843968} {"current_steps": 42690, "total_steps": 76960, "loss": 0.2723, "lr": 2.4590673267378273e-05, "epoch": 11.094074844074845, "percentage": 55.47, "elapsed_time": "1:02:08", "remaining_time": "0:49:53", "throughput": 1031.09, "total_tokens": 3844432} {"current_steps": 42695, "total_steps": 76960, "loss": 0.3865, "lr": 2.4585004439287838e-05, "epoch": 11.09537422037422, "percentage": 55.48, "elapsed_time": "1:02:08", "remaining_time": "0:49:52", "throughput": 1031.1, "total_tokens": 3844880} {"current_steps": 42700, "total_steps": 76960, "loss": 0.3519, "lr": 2.4579335632541026e-05, "epoch": 11.096673596673597, "percentage": 55.48, "elapsed_time": "1:02:09", "remaining_time": "0:49:52", "throughput": 1031.11, "total_tokens": 3845344} {"current_steps": 42705, "total_steps": 76960, "loss": 0.1531, "lr": 2.4573666847429384e-05, "epoch": 11.097972972972974, "percentage": 55.49, "elapsed_time": "1:02:09", "remaining_time": "0:49:51", "throughput": 1031.12, "total_tokens": 3845808} {"current_steps": 42710, "total_steps": 76960, "loss": 0.4157, "lr": 2.456799808424447e-05, "epoch": 11.099272349272349, "percentage": 55.5, "elapsed_time": "1:02:10", "remaining_time": "0:49:51", "throughput": 1031.12, "total_tokens": 3846240} {"current_steps": 42715, "total_steps": 76960, "loss": 0.1966, "lr": 2.4562329343277825e-05, "epoch": 11.100571725571726, "percentage": 55.5, "elapsed_time": "1:02:10", "remaining_time": "0:49:50", "throughput": 1031.12, "total_tokens": 3846672} {"current_steps": 42720, "total_steps": 76960, "loss": 0.1186, "lr": 2.4556660624820998e-05, "epoch": 11.101871101871103, "percentage": 55.51, "elapsed_time": "1:02:10", "remaining_time": "0:49:50", "throughput": 1031.13, "total_tokens": 3847152} {"current_steps": 42725, "total_steps": 76960, "loss": 0.2862, "lr": 2.4550991929165553e-05, "epoch": 11.103170478170478, "percentage": 55.52, "elapsed_time": "1:02:11", "remaining_time": "0:49:49", "throughput": 1031.14, "total_tokens": 3847600} {"current_steps": 42730, "total_steps": 76960, "loss": 0.3622, "lr": 2.4545323256603007e-05, "epoch": 11.104469854469855, "percentage": 55.52, "elapsed_time": "1:02:11", "remaining_time": "0:49:49", "throughput": 1031.13, "total_tokens": 3848016} {"current_steps": 42735, "total_steps": 76960, "loss": 0.2779, "lr": 2.4539654607424927e-05, "epoch": 11.10576923076923, "percentage": 55.53, "elapsed_time": "1:02:12", "remaining_time": "0:49:49", "throughput": 1031.15, "total_tokens": 3848512} {"current_steps": 42740, "total_steps": 76960, "loss": 0.1333, "lr": 2.453398598192285e-05, "epoch": 11.107068607068607, "percentage": 55.54, "elapsed_time": "1:02:12", "remaining_time": "0:49:48", "throughput": 1031.16, "total_tokens": 3848960} {"current_steps": 42745, "total_steps": 76960, "loss": 0.3361, "lr": 2.4528317380388328e-05, "epoch": 11.108367983367984, "percentage": 55.54, "elapsed_time": "1:02:13", "remaining_time": "0:49:48", "throughput": 1031.16, "total_tokens": 3849392} {"current_steps": 42750, "total_steps": 76960, "loss": 0.214, "lr": 2.4522648803112886e-05, "epoch": 11.109667359667359, "percentage": 55.55, "elapsed_time": "1:02:13", "remaining_time": "0:49:47", "throughput": 1031.15, "total_tokens": 3849808} {"current_steps": 42755, "total_steps": 76960, "loss": 0.1335, "lr": 2.4516980250388077e-05, "epoch": 11.110966735966736, "percentage": 55.55, "elapsed_time": "1:02:13", "remaining_time": "0:49:47", "throughput": 1031.17, "total_tokens": 3850304} {"current_steps": 42760, "total_steps": 76960, "loss": 0.1632, "lr": 2.4511311722505433e-05, "epoch": 11.112266112266113, "percentage": 55.56, "elapsed_time": "1:02:14", "remaining_time": "0:49:46", "throughput": 1031.18, "total_tokens": 3850752} {"current_steps": 42765, "total_steps": 76960, "loss": 0.2006, "lr": 2.4505643219756504e-05, "epoch": 11.113565488565488, "percentage": 55.57, "elapsed_time": "1:02:14", "remaining_time": "0:49:46", "throughput": 1031.19, "total_tokens": 3851232} {"current_steps": 42770, "total_steps": 76960, "loss": 0.2363, "lr": 2.449997474243281e-05, "epoch": 11.114864864864865, "percentage": 55.57, "elapsed_time": "1:02:15", "remaining_time": "0:49:45", "throughput": 1031.2, "total_tokens": 3851712} {"current_steps": 42775, "total_steps": 76960, "loss": 0.2854, "lr": 2.44943062908259e-05, "epoch": 11.116164241164242, "percentage": 55.58, "elapsed_time": "1:02:15", "remaining_time": "0:49:45", "throughput": 1031.21, "total_tokens": 3852176} {"current_steps": 42780, "total_steps": 76960, "loss": 0.2267, "lr": 2.4488637865227306e-05, "epoch": 11.117463617463617, "percentage": 55.59, "elapsed_time": "1:02:15", "remaining_time": "0:49:44", "throughput": 1031.22, "total_tokens": 3852624} {"current_steps": 42785, "total_steps": 76960, "loss": 0.498, "lr": 2.4482969465928543e-05, "epoch": 11.118762993762994, "percentage": 55.59, "elapsed_time": "1:02:16", "remaining_time": "0:49:44", "throughput": 1031.22, "total_tokens": 3853056} {"current_steps": 42790, "total_steps": 76960, "loss": 0.2536, "lr": 2.4477301093221163e-05, "epoch": 11.12006237006237, "percentage": 55.6, "elapsed_time": "1:02:16", "remaining_time": "0:49:44", "throughput": 1031.23, "total_tokens": 3853536} {"current_steps": 42795, "total_steps": 76960, "loss": 0.1905, "lr": 2.4471632747396687e-05, "epoch": 11.121361746361746, "percentage": 55.61, "elapsed_time": "1:02:17", "remaining_time": "0:49:43", "throughput": 1031.25, "total_tokens": 3854032} {"current_steps": 42800, "total_steps": 76960, "loss": 0.3209, "lr": 2.4465964428746652e-05, "epoch": 11.122661122661123, "percentage": 55.61, "elapsed_time": "1:02:17", "remaining_time": "0:49:43", "throughput": 1031.25, "total_tokens": 3854480} {"current_steps": 42805, "total_steps": 76960, "loss": 0.2606, "lr": 2.4460296137562565e-05, "epoch": 11.123960498960498, "percentage": 55.62, "elapsed_time": "1:02:18", "remaining_time": "0:49:42", "throughput": 1031.26, "total_tokens": 3854944} {"current_steps": 42810, "total_steps": 76960, "loss": 0.1854, "lr": 2.4454627874135974e-05, "epoch": 11.125259875259875, "percentage": 55.63, "elapsed_time": "1:02:18", "remaining_time": "0:49:42", "throughput": 1031.27, "total_tokens": 3855392} {"current_steps": 42815, "total_steps": 76960, "loss": 0.219, "lr": 2.444895963875839e-05, "epoch": 11.126559251559252, "percentage": 55.63, "elapsed_time": "1:02:18", "remaining_time": "0:49:41", "throughput": 1031.27, "total_tokens": 3855840} {"current_steps": 42820, "total_steps": 76960, "loss": 0.2304, "lr": 2.4443291431721345e-05, "epoch": 11.127858627858627, "percentage": 55.64, "elapsed_time": "1:02:19", "remaining_time": "0:49:41", "throughput": 1031.29, "total_tokens": 3856320} {"current_steps": 42825, "total_steps": 76960, "loss": 0.2346, "lr": 2.443762325331635e-05, "epoch": 11.129158004158004, "percentage": 55.65, "elapsed_time": "1:02:19", "remaining_time": "0:49:40", "throughput": 1031.29, "total_tokens": 3856752} {"current_steps": 42830, "total_steps": 76960, "loss": 0.1257, "lr": 2.4431955103834933e-05, "epoch": 11.130457380457381, "percentage": 55.65, "elapsed_time": "1:02:20", "remaining_time": "0:49:40", "throughput": 1031.3, "total_tokens": 3857216} {"current_steps": 42835, "total_steps": 76960, "loss": 0.232, "lr": 2.4426286983568602e-05, "epoch": 11.131756756756756, "percentage": 55.66, "elapsed_time": "1:02:20", "remaining_time": "0:49:39", "throughput": 1031.31, "total_tokens": 3857680} {"current_steps": 42840, "total_steps": 76960, "loss": 0.1682, "lr": 2.4420618892808895e-05, "epoch": 11.133056133056133, "percentage": 55.67, "elapsed_time": "1:02:20", "remaining_time": "0:49:39", "throughput": 1031.31, "total_tokens": 3858128} {"current_steps": 42845, "total_steps": 76960, "loss": 0.2983, "lr": 2.441495083184731e-05, "epoch": 11.13435550935551, "percentage": 55.67, "elapsed_time": "1:02:21", "remaining_time": "0:49:39", "throughput": 1031.32, "total_tokens": 3858592} {"current_steps": 42850, "total_steps": 76960, "loss": 0.5179, "lr": 2.4409282800975352e-05, "epoch": 11.135654885654885, "percentage": 55.68, "elapsed_time": "1:02:21", "remaining_time": "0:49:38", "throughput": 1031.33, "total_tokens": 3859072} {"current_steps": 42855, "total_steps": 76960, "loss": 0.1484, "lr": 2.4403614800484563e-05, "epoch": 11.136954261954262, "percentage": 55.68, "elapsed_time": "1:02:22", "remaining_time": "0:49:38", "throughput": 1031.34, "total_tokens": 3859520} {"current_steps": 42860, "total_steps": 76960, "loss": 0.1847, "lr": 2.4397946830666422e-05, "epoch": 11.138253638253639, "percentage": 55.69, "elapsed_time": "1:02:22", "remaining_time": "0:49:37", "throughput": 1031.34, "total_tokens": 3859952} {"current_steps": 42865, "total_steps": 76960, "loss": 0.3095, "lr": 2.4392278891812455e-05, "epoch": 11.139553014553014, "percentage": 55.7, "elapsed_time": "1:02:23", "remaining_time": "0:49:37", "throughput": 1031.34, "total_tokens": 3860400} {"current_steps": 42870, "total_steps": 76960, "loss": 0.24, "lr": 2.4386610984214163e-05, "epoch": 11.140852390852391, "percentage": 55.7, "elapsed_time": "1:02:23", "remaining_time": "0:49:36", "throughput": 1031.35, "total_tokens": 3860832} {"current_steps": 42875, "total_steps": 76960, "loss": 0.2309, "lr": 2.438094310816307e-05, "epoch": 11.142151767151766, "percentage": 55.71, "elapsed_time": "1:02:23", "remaining_time": "0:49:36", "throughput": 1031.35, "total_tokens": 3861280} {"current_steps": 42880, "total_steps": 76960, "loss": 0.3674, "lr": 2.4375275263950654e-05, "epoch": 11.143451143451143, "percentage": 55.72, "elapsed_time": "1:02:24", "remaining_time": "0:49:35", "throughput": 1031.36, "total_tokens": 3861760} {"current_steps": 42885, "total_steps": 76960, "loss": 0.3283, "lr": 2.4369607451868435e-05, "epoch": 11.14475051975052, "percentage": 55.72, "elapsed_time": "1:02:24", "remaining_time": "0:49:35", "throughput": 1031.37, "total_tokens": 3862208} {"current_steps": 42890, "total_steps": 76960, "loss": 0.1245, "lr": 2.4363939672207904e-05, "epoch": 11.146049896049895, "percentage": 55.73, "elapsed_time": "1:02:25", "remaining_time": "0:49:34", "throughput": 1031.37, "total_tokens": 3862640} {"current_steps": 42895, "total_steps": 76960, "loss": 0.2912, "lr": 2.4358271925260574e-05, "epoch": 11.147349272349272, "percentage": 55.74, "elapsed_time": "1:02:25", "remaining_time": "0:49:34", "throughput": 1031.37, "total_tokens": 3863072} {"current_steps": 42900, "total_steps": 76960, "loss": 0.17, "lr": 2.4352604211317924e-05, "epoch": 11.14864864864865, "percentage": 55.74, "elapsed_time": "1:02:25", "remaining_time": "0:49:34", "throughput": 1031.37, "total_tokens": 3863488} {"current_steps": 42905, "total_steps": 76960, "loss": 0.111, "lr": 2.4346936530671465e-05, "epoch": 11.149948024948024, "percentage": 55.75, "elapsed_time": "1:02:26", "remaining_time": "0:49:33", "throughput": 1031.38, "total_tokens": 3863952} {"current_steps": 42910, "total_steps": 76960, "loss": 0.2505, "lr": 2.434126888361269e-05, "epoch": 11.151247401247401, "percentage": 55.76, "elapsed_time": "1:02:26", "remaining_time": "0:49:33", "throughput": 1031.37, "total_tokens": 3864368} {"current_steps": 42915, "total_steps": 76960, "loss": 0.1347, "lr": 2.433560127043308e-05, "epoch": 11.152546777546778, "percentage": 55.76, "elapsed_time": "1:02:27", "remaining_time": "0:49:32", "throughput": 1031.37, "total_tokens": 3864784} {"current_steps": 42920, "total_steps": 76960, "loss": 0.1955, "lr": 2.4329933691424137e-05, "epoch": 11.153846153846153, "percentage": 55.77, "elapsed_time": "1:02:27", "remaining_time": "0:49:32", "throughput": 1031.39, "total_tokens": 3865280} {"current_steps": 42925, "total_steps": 76960, "loss": 0.2663, "lr": 2.432426614687734e-05, "epoch": 11.15514553014553, "percentage": 55.78, "elapsed_time": "1:02:28", "remaining_time": "0:49:31", "throughput": 1031.39, "total_tokens": 3865728} {"current_steps": 42930, "total_steps": 76960, "loss": 0.1794, "lr": 2.431859863708419e-05, "epoch": 11.156444906444907, "percentage": 55.78, "elapsed_time": "1:02:28", "remaining_time": "0:49:31", "throughput": 1031.4, "total_tokens": 3866176} {"current_steps": 42935, "total_steps": 76960, "loss": 0.2944, "lr": 2.431293116233616e-05, "epoch": 11.157744282744282, "percentage": 55.79, "elapsed_time": "1:02:28", "remaining_time": "0:49:30", "throughput": 1031.39, "total_tokens": 3866576} {"current_steps": 42940, "total_steps": 76960, "loss": 0.2443, "lr": 2.4307263722924744e-05, "epoch": 11.15904365904366, "percentage": 55.8, "elapsed_time": "1:02:29", "remaining_time": "0:49:30", "throughput": 1031.4, "total_tokens": 3867024} {"current_steps": 42945, "total_steps": 76960, "loss": 0.3265, "lr": 2.430159631914141e-05, "epoch": 11.160343035343036, "percentage": 55.8, "elapsed_time": "1:02:29", "remaining_time": "0:49:30", "throughput": 1031.4, "total_tokens": 3867488} {"current_steps": 42950, "total_steps": 76960, "loss": 0.2353, "lr": 2.4295928951277653e-05, "epoch": 11.161642411642411, "percentage": 55.81, "elapsed_time": "1:02:30", "remaining_time": "0:49:29", "throughput": 1031.42, "total_tokens": 3867968} {"current_steps": 42955, "total_steps": 76960, "loss": 0.5051, "lr": 2.429026161962494e-05, "epoch": 11.162941787941788, "percentage": 55.81, "elapsed_time": "1:02:30", "remaining_time": "0:49:29", "throughput": 1031.43, "total_tokens": 3868432} {"current_steps": 42960, "total_steps": 76960, "loss": 0.357, "lr": 2.4284594324474763e-05, "epoch": 11.164241164241163, "percentage": 55.82, "elapsed_time": "1:02:30", "remaining_time": "0:49:28", "throughput": 1031.44, "total_tokens": 3868896} {"current_steps": 42965, "total_steps": 76960, "loss": 0.1772, "lr": 2.427892706611857e-05, "epoch": 11.16554054054054, "percentage": 55.83, "elapsed_time": "1:02:31", "remaining_time": "0:49:28", "throughput": 1031.44, "total_tokens": 3869344} {"current_steps": 42970, "total_steps": 76960, "loss": 0.4932, "lr": 2.427325984484786e-05, "epoch": 11.166839916839917, "percentage": 55.83, "elapsed_time": "1:02:31", "remaining_time": "0:49:27", "throughput": 1031.44, "total_tokens": 3869760} {"current_steps": 42975, "total_steps": 76960, "loss": 0.1923, "lr": 2.4267592660954096e-05, "epoch": 11.168139293139292, "percentage": 55.84, "elapsed_time": "1:02:32", "remaining_time": "0:49:27", "throughput": 1031.44, "total_tokens": 3870208} {"current_steps": 42980, "total_steps": 76960, "loss": 0.14, "lr": 2.4261925514728733e-05, "epoch": 11.16943866943867, "percentage": 55.85, "elapsed_time": "1:02:32", "remaining_time": "0:49:26", "throughput": 1031.47, "total_tokens": 3870736} {"current_steps": 42985, "total_steps": 76960, "loss": 0.2441, "lr": 2.4256258406463253e-05, "epoch": 11.170738045738046, "percentage": 55.85, "elapsed_time": "1:02:33", "remaining_time": "0:49:26", "throughput": 1031.48, "total_tokens": 3871200} {"current_steps": 42990, "total_steps": 76960, "loss": 0.308, "lr": 2.425059133644911e-05, "epoch": 11.172037422037421, "percentage": 55.86, "elapsed_time": "1:02:33", "remaining_time": "0:49:25", "throughput": 1031.49, "total_tokens": 3871664} {"current_steps": 42995, "total_steps": 76960, "loss": 0.2005, "lr": 2.4244924304977785e-05, "epoch": 11.173336798336798, "percentage": 55.87, "elapsed_time": "1:02:33", "remaining_time": "0:49:25", "throughput": 1031.49, "total_tokens": 3872112} {"current_steps": 43000, "total_steps": 76960, "loss": 0.2289, "lr": 2.4239257312340712e-05, "epoch": 11.174636174636175, "percentage": 55.87, "elapsed_time": "1:02:34", "remaining_time": "0:49:25", "throughput": 1031.5, "total_tokens": 3872576} {"current_steps": 43005, "total_steps": 76960, "loss": 0.2514, "lr": 2.4233590358829374e-05, "epoch": 11.17593555093555, "percentage": 55.88, "elapsed_time": "1:02:34", "remaining_time": "0:49:24", "throughput": 1031.51, "total_tokens": 3873024} {"current_steps": 43010, "total_steps": 76960, "loss": 0.394, "lr": 2.422792344473521e-05, "epoch": 11.177234927234927, "percentage": 55.89, "elapsed_time": "1:02:35", "remaining_time": "0:49:24", "throughput": 1031.51, "total_tokens": 3873472} {"current_steps": 43015, "total_steps": 76960, "loss": 0.2335, "lr": 2.4222256570349692e-05, "epoch": 11.178534303534304, "percentage": 55.89, "elapsed_time": "1:02:35", "remaining_time": "0:49:23", "throughput": 1031.52, "total_tokens": 3873936} {"current_steps": 43020, "total_steps": 76960, "loss": 0.2108, "lr": 2.421658973596426e-05, "epoch": 11.17983367983368, "percentage": 55.9, "elapsed_time": "1:02:35", "remaining_time": "0:49:23", "throughput": 1031.53, "total_tokens": 3874400} {"current_steps": 43025, "total_steps": 76960, "loss": 0.3731, "lr": 2.4210922941870367e-05, "epoch": 11.181133056133056, "percentage": 55.91, "elapsed_time": "1:02:36", "remaining_time": "0:49:22", "throughput": 1031.53, "total_tokens": 3874832} {"current_steps": 43030, "total_steps": 76960, "loss": 0.1921, "lr": 2.420525618835946e-05, "epoch": 11.182432432432432, "percentage": 55.91, "elapsed_time": "1:02:36", "remaining_time": "0:49:22", "throughput": 1031.53, "total_tokens": 3875264} {"current_steps": 43035, "total_steps": 76960, "loss": 0.1286, "lr": 2.4199589475723e-05, "epoch": 11.183731808731808, "percentage": 55.92, "elapsed_time": "1:02:37", "remaining_time": "0:49:21", "throughput": 1031.54, "total_tokens": 3875728} {"current_steps": 43040, "total_steps": 76960, "loss": 0.3959, "lr": 2.4193922804252416e-05, "epoch": 11.185031185031185, "percentage": 55.93, "elapsed_time": "1:02:37", "remaining_time": "0:49:21", "throughput": 1031.55, "total_tokens": 3876192} {"current_steps": 43045, "total_steps": 76960, "loss": 0.0669, "lr": 2.4188256174239146e-05, "epoch": 11.18633056133056, "percentage": 55.93, "elapsed_time": "1:02:38", "remaining_time": "0:49:20", "throughput": 1031.55, "total_tokens": 3876624} {"current_steps": 43050, "total_steps": 76960, "loss": 0.2809, "lr": 2.4182589585974653e-05, "epoch": 11.187629937629938, "percentage": 55.94, "elapsed_time": "1:02:38", "remaining_time": "0:49:20", "throughput": 1031.55, "total_tokens": 3877072} {"current_steps": 43055, "total_steps": 76960, "loss": 0.5073, "lr": 2.4176923039750347e-05, "epoch": 11.188929313929314, "percentage": 55.94, "elapsed_time": "1:02:38", "remaining_time": "0:49:20", "throughput": 1031.55, "total_tokens": 3877488} {"current_steps": 43060, "total_steps": 76960, "loss": 0.3199, "lr": 2.4171256535857684e-05, "epoch": 11.19022869022869, "percentage": 55.95, "elapsed_time": "1:02:39", "remaining_time": "0:49:19", "throughput": 1031.56, "total_tokens": 3877936} {"current_steps": 43065, "total_steps": 76960, "loss": 0.2109, "lr": 2.4165590074588085e-05, "epoch": 11.191528066528067, "percentage": 55.96, "elapsed_time": "1:02:39", "remaining_time": "0:49:19", "throughput": 1031.56, "total_tokens": 3878368} {"current_steps": 43070, "total_steps": 76960, "loss": 0.1987, "lr": 2.4159923656233e-05, "epoch": 11.192827442827443, "percentage": 55.96, "elapsed_time": "1:02:40", "remaining_time": "0:49:18", "throughput": 1031.55, "total_tokens": 3878784} {"current_steps": 43075, "total_steps": 76960, "loss": 0.2036, "lr": 2.4154257281083837e-05, "epoch": 11.194126819126819, "percentage": 55.97, "elapsed_time": "1:02:40", "remaining_time": "0:49:18", "throughput": 1031.57, "total_tokens": 3879264} {"current_steps": 43080, "total_steps": 76960, "loss": 0.3448, "lr": 2.4148590949432035e-05, "epoch": 11.195426195426196, "percentage": 55.98, "elapsed_time": "1:02:40", "remaining_time": "0:49:17", "throughput": 1031.57, "total_tokens": 3879696} {"current_steps": 43085, "total_steps": 76960, "loss": 0.1787, "lr": 2.4142924661569013e-05, "epoch": 11.196725571725572, "percentage": 55.98, "elapsed_time": "1:02:41", "remaining_time": "0:49:17", "throughput": 1031.58, "total_tokens": 3880176} {"current_steps": 43090, "total_steps": 76960, "loss": 0.1988, "lr": 2.4137258417786206e-05, "epoch": 11.198024948024948, "percentage": 55.99, "elapsed_time": "1:02:41", "remaining_time": "0:49:16", "throughput": 1031.59, "total_tokens": 3880640} {"current_steps": 43095, "total_steps": 76960, "loss": 0.2189, "lr": 2.4131592218375017e-05, "epoch": 11.199324324324325, "percentage": 56.0, "elapsed_time": "1:02:42", "remaining_time": "0:49:16", "throughput": 1031.6, "total_tokens": 3881120} {"current_steps": 43100, "total_steps": 76960, "loss": 0.1412, "lr": 2.4125926063626875e-05, "epoch": 11.200623700623701, "percentage": 56.0, "elapsed_time": "1:02:42", "remaining_time": "0:49:15", "throughput": 1031.62, "total_tokens": 3881600} {"current_steps": 43105, "total_steps": 76960, "loss": 0.4343, "lr": 2.41202599538332e-05, "epoch": 11.201923076923077, "percentage": 56.01, "elapsed_time": "1:02:43", "remaining_time": "0:49:15", "throughput": 1031.62, "total_tokens": 3882048} {"current_steps": 43110, "total_steps": 76960, "loss": 0.2712, "lr": 2.4114593889285385e-05, "epoch": 11.203222453222454, "percentage": 56.02, "elapsed_time": "1:02:43", "remaining_time": "0:49:15", "throughput": 1031.63, "total_tokens": 3882512} {"current_steps": 43115, "total_steps": 76960, "loss": 0.3787, "lr": 2.4108927870274863e-05, "epoch": 11.204521829521829, "percentage": 56.02, "elapsed_time": "1:02:43", "remaining_time": "0:49:14", "throughput": 1031.64, "total_tokens": 3882976} {"current_steps": 43120, "total_steps": 76960, "loss": 0.1682, "lr": 2.4103261897093028e-05, "epoch": 11.205821205821206, "percentage": 56.03, "elapsed_time": "1:02:44", "remaining_time": "0:49:14", "throughput": 1031.65, "total_tokens": 3883424} {"current_steps": 43125, "total_steps": 76960, "loss": 0.3169, "lr": 2.4097595970031304e-05, "epoch": 11.207120582120583, "percentage": 56.04, "elapsed_time": "1:02:44", "remaining_time": "0:49:13", "throughput": 1031.65, "total_tokens": 3883856} {"current_steps": 43130, "total_steps": 76960, "loss": 0.2043, "lr": 2.409193008938107e-05, "epoch": 11.208419958419958, "percentage": 56.04, "elapsed_time": "1:02:45", "remaining_time": "0:49:13", "throughput": 1031.64, "total_tokens": 3884272} {"current_steps": 43135, "total_steps": 76960, "loss": 0.2298, "lr": 2.408626425543375e-05, "epoch": 11.209719334719335, "percentage": 56.05, "elapsed_time": "1:02:45", "remaining_time": "0:49:12", "throughput": 1031.65, "total_tokens": 3884720} {"current_steps": 43140, "total_steps": 76960, "loss": 0.1514, "lr": 2.4080598468480732e-05, "epoch": 11.211018711018712, "percentage": 56.06, "elapsed_time": "1:02:45", "remaining_time": "0:49:12", "throughput": 1031.66, "total_tokens": 3885216} {"current_steps": 43145, "total_steps": 76960, "loss": 0.3789, "lr": 2.4074932728813422e-05, "epoch": 11.212318087318087, "percentage": 56.06, "elapsed_time": "1:02:46", "remaining_time": "0:49:11", "throughput": 1031.67, "total_tokens": 3885664} {"current_steps": 43150, "total_steps": 76960, "loss": 0.2918, "lr": 2.40692670367232e-05, "epoch": 11.213617463617464, "percentage": 56.07, "elapsed_time": "1:02:46", "remaining_time": "0:49:11", "throughput": 1031.67, "total_tokens": 3886112} {"current_steps": 43155, "total_steps": 76960, "loss": 0.3597, "lr": 2.406360139250147e-05, "epoch": 11.21491683991684, "percentage": 56.07, "elapsed_time": "1:02:47", "remaining_time": "0:49:11", "throughput": 1031.68, "total_tokens": 3886576} {"current_steps": 43160, "total_steps": 76960, "loss": 0.4732, "lr": 2.4057935796439613e-05, "epoch": 11.216216216216216, "percentage": 56.08, "elapsed_time": "1:02:47", "remaining_time": "0:49:10", "throughput": 1031.68, "total_tokens": 3887008} {"current_steps": 43165, "total_steps": 76960, "loss": 0.257, "lr": 2.405227024882903e-05, "epoch": 11.217515592515593, "percentage": 56.09, "elapsed_time": "1:02:48", "remaining_time": "0:49:10", "throughput": 1031.7, "total_tokens": 3887488} {"current_steps": 43170, "total_steps": 76960, "loss": 0.2873, "lr": 2.4046604749961093e-05, "epoch": 11.21881496881497, "percentage": 56.09, "elapsed_time": "1:02:48", "remaining_time": "0:49:09", "throughput": 1031.71, "total_tokens": 3887952} {"current_steps": 43175, "total_steps": 76960, "loss": 0.0879, "lr": 2.404093930012718e-05, "epoch": 11.220114345114345, "percentage": 56.1, "elapsed_time": "1:02:48", "remaining_time": "0:49:09", "throughput": 1031.71, "total_tokens": 3888400} {"current_steps": 43180, "total_steps": 76960, "loss": 0.3629, "lr": 2.4035273899618683e-05, "epoch": 11.221413721413722, "percentage": 56.11, "elapsed_time": "1:02:49", "remaining_time": "0:49:08", "throughput": 1031.72, "total_tokens": 3888880} {"current_steps": 43185, "total_steps": 76960, "loss": 0.2368, "lr": 2.402960854872697e-05, "epoch": 11.222713097713097, "percentage": 56.11, "elapsed_time": "1:02:49", "remaining_time": "0:49:08", "throughput": 1031.74, "total_tokens": 3889376} {"current_steps": 43190, "total_steps": 76960, "loss": 0.4148, "lr": 2.402394324774343e-05, "epoch": 11.224012474012474, "percentage": 56.12, "elapsed_time": "1:02:50", "remaining_time": "0:49:07", "throughput": 1031.75, "total_tokens": 3889840} {"current_steps": 43195, "total_steps": 76960, "loss": 0.1905, "lr": 2.4018277996959412e-05, "epoch": 11.22531185031185, "percentage": 56.13, "elapsed_time": "1:02:50", "remaining_time": "0:49:07", "throughput": 1031.77, "total_tokens": 3890336} {"current_steps": 43200, "total_steps": 76960, "loss": 0.3359, "lr": 2.4012612796666302e-05, "epoch": 11.226611226611226, "percentage": 56.13, "elapsed_time": "1:02:50", "remaining_time": "0:49:06", "throughput": 1031.77, "total_tokens": 3890784} {"current_steps": 43205, "total_steps": 76960, "loss": 0.2469, "lr": 2.400694764715546e-05, "epoch": 11.227910602910603, "percentage": 56.14, "elapsed_time": "1:02:51", "remaining_time": "0:49:06", "throughput": 1031.77, "total_tokens": 3891200} {"current_steps": 43210, "total_steps": 76960, "loss": 0.1285, "lr": 2.4001282548718258e-05, "epoch": 11.22920997920998, "percentage": 56.15, "elapsed_time": "1:02:51", "remaining_time": "0:49:06", "throughput": 1031.78, "total_tokens": 3891664} {"current_steps": 43215, "total_steps": 76960, "loss": 0.2129, "lr": 2.399561750164604e-05, "epoch": 11.230509355509355, "percentage": 56.15, "elapsed_time": "1:02:52", "remaining_time": "0:49:05", "throughput": 1031.78, "total_tokens": 3892096} {"current_steps": 43220, "total_steps": 76960, "loss": 0.3228, "lr": 2.3989952506230187e-05, "epoch": 11.231808731808732, "percentage": 56.16, "elapsed_time": "1:02:52", "remaining_time": "0:49:05", "throughput": 1031.79, "total_tokens": 3892576} {"current_steps": 43225, "total_steps": 76960, "loss": 0.0257, "lr": 2.3984287562762037e-05, "epoch": 11.233108108108109, "percentage": 56.17, "elapsed_time": "1:02:53", "remaining_time": "0:49:04", "throughput": 1031.79, "total_tokens": 3892976} {"current_steps": 43230, "total_steps": 76960, "loss": 0.2847, "lr": 2.397862267153296e-05, "epoch": 11.234407484407484, "percentage": 56.17, "elapsed_time": "1:02:53", "remaining_time": "0:49:04", "throughput": 1031.79, "total_tokens": 3893408} {"current_steps": 43235, "total_steps": 76960, "loss": 0.1484, "lr": 2.3972957832834295e-05, "epoch": 11.23570686070686, "percentage": 56.18, "elapsed_time": "1:02:53", "remaining_time": "0:49:03", "throughput": 1031.79, "total_tokens": 3893856} {"current_steps": 43240, "total_steps": 76960, "loss": 0.019, "lr": 2.3967293046957383e-05, "epoch": 11.237006237006238, "percentage": 56.19, "elapsed_time": "1:02:54", "remaining_time": "0:49:03", "throughput": 1031.78, "total_tokens": 3894256} {"current_steps": 43245, "total_steps": 76960, "loss": 0.5246, "lr": 2.3961628314193595e-05, "epoch": 11.238305613305613, "percentage": 56.19, "elapsed_time": "1:02:54", "remaining_time": "0:49:02", "throughput": 1031.8, "total_tokens": 3894736} {"current_steps": 43250, "total_steps": 76960, "loss": 0.6324, "lr": 2.3955963634834244e-05, "epoch": 11.23960498960499, "percentage": 56.2, "elapsed_time": "1:02:55", "remaining_time": "0:49:02", "throughput": 1031.8, "total_tokens": 3895168} {"current_steps": 43255, "total_steps": 76960, "loss": 0.1507, "lr": 2.395029900917069e-05, "epoch": 11.240904365904365, "percentage": 56.2, "elapsed_time": "1:02:55", "remaining_time": "0:49:01", "throughput": 1031.8, "total_tokens": 3895632} {"current_steps": 43260, "total_steps": 76960, "loss": 0.3152, "lr": 2.3944634437494256e-05, "epoch": 11.242203742203742, "percentage": 56.21, "elapsed_time": "1:02:55", "remaining_time": "0:49:01", "throughput": 1031.8, "total_tokens": 3896048} {"current_steps": 43265, "total_steps": 76960, "loss": 0.3448, "lr": 2.39389699200963e-05, "epoch": 11.243503118503119, "percentage": 56.22, "elapsed_time": "1:02:56", "remaining_time": "0:49:01", "throughput": 1031.81, "total_tokens": 3896528} {"current_steps": 43270, "total_steps": 76960, "loss": 0.3239, "lr": 2.393330545726812e-05, "epoch": 11.244802494802494, "percentage": 56.22, "elapsed_time": "1:02:56", "remaining_time": "0:49:00", "throughput": 1031.85, "total_tokens": 3897088} {"current_steps": 43275, "total_steps": 76960, "loss": 0.2929, "lr": 2.392764104930107e-05, "epoch": 11.246101871101871, "percentage": 56.23, "elapsed_time": "1:02:57", "remaining_time": "0:49:00", "throughput": 1031.86, "total_tokens": 3897568} {"current_steps": 43280, "total_steps": 76960, "loss": 0.3194, "lr": 2.3921976696486468e-05, "epoch": 11.247401247401248, "percentage": 56.24, "elapsed_time": "1:02:57", "remaining_time": "0:48:59", "throughput": 1031.87, "total_tokens": 3898016} {"current_steps": 43285, "total_steps": 76960, "loss": 0.1486, "lr": 2.3916312399115646e-05, "epoch": 11.248700623700623, "percentage": 56.24, "elapsed_time": "1:02:58", "remaining_time": "0:48:59", "throughput": 1031.88, "total_tokens": 3898480} {"current_steps": 43290, "total_steps": 76960, "loss": 0.1653, "lr": 2.39106481574799e-05, "epoch": 11.25, "percentage": 56.25, "elapsed_time": "1:02:58", "remaining_time": "0:48:58", "throughput": 1031.89, "total_tokens": 3898960} {"current_steps": 43295, "total_steps": 76960, "loss": 0.4652, "lr": 2.3904983971870573e-05, "epoch": 11.251299376299377, "percentage": 56.26, "elapsed_time": "1:02:58", "remaining_time": "0:48:58", "throughput": 1031.89, "total_tokens": 3899392} {"current_steps": 43300, "total_steps": 76960, "loss": 0.3771, "lr": 2.3899319842578972e-05, "epoch": 11.252598752598752, "percentage": 56.26, "elapsed_time": "1:02:59", "remaining_time": "0:48:57", "throughput": 1031.89, "total_tokens": 3899808} {"current_steps": 43305, "total_steps": 76960, "loss": 0.2078, "lr": 2.3893655769896396e-05, "epoch": 11.253898128898129, "percentage": 56.27, "elapsed_time": "1:02:59", "remaining_time": "0:48:57", "throughput": 1031.88, "total_tokens": 3900224} {"current_steps": 43310, "total_steps": 76960, "loss": 0.2824, "lr": 2.3887991754114173e-05, "epoch": 11.255197505197506, "percentage": 56.28, "elapsed_time": "1:03:00", "remaining_time": "0:48:56", "throughput": 1031.88, "total_tokens": 3900656} {"current_steps": 43315, "total_steps": 76960, "loss": 0.0598, "lr": 2.388232779552359e-05, "epoch": 11.256496881496881, "percentage": 56.28, "elapsed_time": "1:03:00", "remaining_time": "0:48:56", "throughput": 1031.88, "total_tokens": 3901072} {"current_steps": 43320, "total_steps": 76960, "loss": 0.4059, "lr": 2.3876663894415974e-05, "epoch": 11.257796257796258, "percentage": 56.29, "elapsed_time": "1:03:00", "remaining_time": "0:48:56", "throughput": 1031.88, "total_tokens": 3901504} {"current_steps": 43325, "total_steps": 76960, "loss": 0.1257, "lr": 2.3871000051082594e-05, "epoch": 11.259095634095633, "percentage": 56.3, "elapsed_time": "1:03:01", "remaining_time": "0:48:55", "throughput": 1031.89, "total_tokens": 3901968} {"current_steps": 43330, "total_steps": 76960, "loss": 0.1468, "lr": 2.3865336265814773e-05, "epoch": 11.26039501039501, "percentage": 56.3, "elapsed_time": "1:03:01", "remaining_time": "0:48:55", "throughput": 1031.89, "total_tokens": 3902416} {"current_steps": 43335, "total_steps": 76960, "loss": 0.1734, "lr": 2.385967253890379e-05, "epoch": 11.261694386694387, "percentage": 56.31, "elapsed_time": "1:03:02", "remaining_time": "0:48:54", "throughput": 1031.89, "total_tokens": 3902848} {"current_steps": 43340, "total_steps": 76960, "loss": 0.3412, "lr": 2.385400887064095e-05, "epoch": 11.262993762993762, "percentage": 56.31, "elapsed_time": "1:03:02", "remaining_time": "0:48:54", "throughput": 1031.9, "total_tokens": 3903296} {"current_steps": 43345, "total_steps": 76960, "loss": 0.5133, "lr": 2.384834526131752e-05, "epoch": 11.26429313929314, "percentage": 56.32, "elapsed_time": "1:03:03", "remaining_time": "0:48:53", "throughput": 1031.9, "total_tokens": 3903728} {"current_steps": 43350, "total_steps": 76960, "loss": 0.2353, "lr": 2.38426817112248e-05, "epoch": 11.265592515592516, "percentage": 56.33, "elapsed_time": "1:03:03", "remaining_time": "0:48:53", "throughput": 1031.9, "total_tokens": 3904176} {"current_steps": 43355, "total_steps": 76960, "loss": 0.2741, "lr": 2.3837018220654066e-05, "epoch": 11.266891891891891, "percentage": 56.33, "elapsed_time": "1:03:03", "remaining_time": "0:48:52", "throughput": 1031.91, "total_tokens": 3904608} {"current_steps": 43360, "total_steps": 76960, "loss": 0.3468, "lr": 2.3831354789896612e-05, "epoch": 11.268191268191268, "percentage": 56.34, "elapsed_time": "1:03:04", "remaining_time": "0:48:52", "throughput": 1031.91, "total_tokens": 3905072} {"current_steps": 43365, "total_steps": 76960, "loss": 0.3102, "lr": 2.3825691419243694e-05, "epoch": 11.269490644490645, "percentage": 56.35, "elapsed_time": "1:03:04", "remaining_time": "0:48:52", "throughput": 1031.92, "total_tokens": 3905504} {"current_steps": 43370, "total_steps": 76960, "loss": 0.3539, "lr": 2.3820028108986586e-05, "epoch": 11.27079002079002, "percentage": 56.35, "elapsed_time": "1:03:05", "remaining_time": "0:48:51", "throughput": 1031.92, "total_tokens": 3905936} {"current_steps": 43375, "total_steps": 76960, "loss": 0.2201, "lr": 2.3814364859416574e-05, "epoch": 11.272089397089397, "percentage": 56.36, "elapsed_time": "1:03:05", "remaining_time": "0:48:51", "throughput": 1031.93, "total_tokens": 3906400} {"current_steps": 43380, "total_steps": 76960, "loss": 0.1596, "lr": 2.38087016708249e-05, "epoch": 11.273388773388774, "percentage": 56.37, "elapsed_time": "1:03:05", "remaining_time": "0:48:50", "throughput": 1031.93, "total_tokens": 3906864} {"current_steps": 43385, "total_steps": 76960, "loss": 0.1179, "lr": 2.3803038543502847e-05, "epoch": 11.27468814968815, "percentage": 56.37, "elapsed_time": "1:03:06", "remaining_time": "0:48:50", "throughput": 1031.94, "total_tokens": 3907328} {"current_steps": 43390, "total_steps": 76960, "loss": 0.1232, "lr": 2.3797375477741665e-05, "epoch": 11.275987525987526, "percentage": 56.38, "elapsed_time": "1:03:06", "remaining_time": "0:48:49", "throughput": 1031.95, "total_tokens": 3907792} {"current_steps": 43395, "total_steps": 76960, "loss": 0.4665, "lr": 2.3791712473832627e-05, "epoch": 11.277286902286903, "percentage": 56.39, "elapsed_time": "1:03:07", "remaining_time": "0:48:49", "throughput": 1031.96, "total_tokens": 3908240} {"current_steps": 43400, "total_steps": 76960, "loss": 0.1959, "lr": 2.3786049532066957e-05, "epoch": 11.278586278586278, "percentage": 56.39, "elapsed_time": "1:03:07", "remaining_time": "0:48:48", "throughput": 1031.97, "total_tokens": 3908720} {"current_steps": 43405, "total_steps": 76960, "loss": 0.411, "lr": 2.3780386652735934e-05, "epoch": 11.279885654885655, "percentage": 56.4, "elapsed_time": "1:03:08", "remaining_time": "0:48:48", "throughput": 1031.98, "total_tokens": 3909168} {"current_steps": 43410, "total_steps": 76960, "loss": 0.1984, "lr": 2.3774723836130787e-05, "epoch": 11.28118503118503, "percentage": 56.41, "elapsed_time": "1:03:08", "remaining_time": "0:48:47", "throughput": 1031.98, "total_tokens": 3909616} {"current_steps": 43415, "total_steps": 76960, "loss": 0.2408, "lr": 2.376906108254277e-05, "epoch": 11.282484407484407, "percentage": 56.41, "elapsed_time": "1:03:08", "remaining_time": "0:48:47", "throughput": 1031.99, "total_tokens": 3910080} {"current_steps": 43420, "total_steps": 76960, "loss": 0.3627, "lr": 2.3763398392263118e-05, "epoch": 11.283783783783784, "percentage": 56.42, "elapsed_time": "1:03:09", "remaining_time": "0:48:47", "throughput": 1032.0, "total_tokens": 3910544} {"current_steps": 43425, "total_steps": 76960, "loss": 0.3566, "lr": 2.3757735765583083e-05, "epoch": 11.28508316008316, "percentage": 56.43, "elapsed_time": "1:03:09", "remaining_time": "0:48:46", "throughput": 1032.0, "total_tokens": 3910992} {"current_steps": 43430, "total_steps": 76960, "loss": 0.2417, "lr": 2.3752073202793882e-05, "epoch": 11.286382536382536, "percentage": 56.43, "elapsed_time": "1:03:10", "remaining_time": "0:48:46", "throughput": 1032.01, "total_tokens": 3911456} {"current_steps": 43435, "total_steps": 76960, "loss": 0.2568, "lr": 2.3746410704186744e-05, "epoch": 11.287681912681913, "percentage": 56.44, "elapsed_time": "1:03:10", "remaining_time": "0:48:45", "throughput": 1032.02, "total_tokens": 3911920} {"current_steps": 43440, "total_steps": 76960, "loss": 0.32, "lr": 2.3740748270052917e-05, "epoch": 11.288981288981288, "percentage": 56.44, "elapsed_time": "1:03:10", "remaining_time": "0:48:45", "throughput": 1032.04, "total_tokens": 3912400} {"current_steps": 43445, "total_steps": 76960, "loss": 0.2718, "lr": 2.3735085900683602e-05, "epoch": 11.290280665280665, "percentage": 56.45, "elapsed_time": "1:03:11", "remaining_time": "0:48:44", "throughput": 1032.03, "total_tokens": 3912816} {"current_steps": 43450, "total_steps": 76960, "loss": 0.2172, "lr": 2.3729423596370036e-05, "epoch": 11.291580041580042, "percentage": 56.46, "elapsed_time": "1:03:11", "remaining_time": "0:48:44", "throughput": 1032.03, "total_tokens": 3913248} {"current_steps": 43455, "total_steps": 76960, "loss": 0.1981, "lr": 2.372376135740343e-05, "epoch": 11.292879417879417, "percentage": 56.46, "elapsed_time": "1:03:12", "remaining_time": "0:48:43", "throughput": 1032.03, "total_tokens": 3913664} {"current_steps": 43460, "total_steps": 76960, "loss": 0.2198, "lr": 2.3718099184075008e-05, "epoch": 11.294178794178794, "percentage": 56.47, "elapsed_time": "1:03:12", "remaining_time": "0:48:43", "throughput": 1032.03, "total_tokens": 3914080} {"current_steps": 43465, "total_steps": 76960, "loss": 0.1558, "lr": 2.371243707667596e-05, "epoch": 11.295478170478171, "percentage": 56.48, "elapsed_time": "1:03:13", "remaining_time": "0:48:42", "throughput": 1032.04, "total_tokens": 3914544} {"current_steps": 43470, "total_steps": 76960, "loss": 0.1419, "lr": 2.3706775035497517e-05, "epoch": 11.296777546777546, "percentage": 56.48, "elapsed_time": "1:03:13", "remaining_time": "0:48:42", "throughput": 1032.04, "total_tokens": 3914976} {"current_steps": 43475, "total_steps": 76960, "loss": 0.2383, "lr": 2.3701113060830865e-05, "epoch": 11.298076923076923, "percentage": 56.49, "elapsed_time": "1:03:13", "remaining_time": "0:48:42", "throughput": 1032.03, "total_tokens": 3915392} {"current_steps": 43480, "total_steps": 76960, "loss": 0.2574, "lr": 2.3695451152967225e-05, "epoch": 11.299376299376299, "percentage": 56.5, "elapsed_time": "1:03:14", "remaining_time": "0:48:41", "throughput": 1032.03, "total_tokens": 3915824} {"current_steps": 43485, "total_steps": 76960, "loss": 0.2452, "lr": 2.3689789312197772e-05, "epoch": 11.300675675675675, "percentage": 56.5, "elapsed_time": "1:03:14", "remaining_time": "0:48:41", "throughput": 1032.05, "total_tokens": 3916304} {"current_steps": 43490, "total_steps": 76960, "loss": 0.4442, "lr": 2.3684127538813714e-05, "epoch": 11.301975051975052, "percentage": 56.51, "elapsed_time": "1:03:15", "remaining_time": "0:48:40", "throughput": 1032.05, "total_tokens": 3916768} {"current_steps": 43495, "total_steps": 76960, "loss": 0.4289, "lr": 2.3678465833106243e-05, "epoch": 11.303274428274428, "percentage": 56.52, "elapsed_time": "1:03:15", "remaining_time": "0:48:40", "throughput": 1032.07, "total_tokens": 3917248} {"current_steps": 43500, "total_steps": 76960, "loss": 0.1429, "lr": 2.367280419536653e-05, "epoch": 11.304573804573804, "percentage": 56.52, "elapsed_time": "1:03:15", "remaining_time": "0:48:39", "throughput": 1032.07, "total_tokens": 3917696} {"current_steps": 43505, "total_steps": 76960, "loss": 0.141, "lr": 2.366714262588577e-05, "epoch": 11.305873180873181, "percentage": 56.53, "elapsed_time": "1:03:16", "remaining_time": "0:48:39", "throughput": 1032.07, "total_tokens": 3918128} {"current_steps": 43510, "total_steps": 76960, "loss": 0.3843, "lr": 2.3661481124955142e-05, "epoch": 11.307172557172557, "percentage": 56.54, "elapsed_time": "1:03:16", "remaining_time": "0:48:38", "throughput": 1032.08, "total_tokens": 3918592} {"current_steps": 43515, "total_steps": 76960, "loss": 0.1915, "lr": 2.3655819692865832e-05, "epoch": 11.308471933471933, "percentage": 56.54, "elapsed_time": "1:03:17", "remaining_time": "0:48:38", "throughput": 1032.09, "total_tokens": 3919040} {"current_steps": 43520, "total_steps": 76960, "loss": 0.1139, "lr": 2.3650158329908993e-05, "epoch": 11.30977130977131, "percentage": 56.55, "elapsed_time": "1:03:17", "remaining_time": "0:48:38", "throughput": 1032.09, "total_tokens": 3919488} {"current_steps": 43525, "total_steps": 76960, "loss": 0.2254, "lr": 2.364449703637581e-05, "epoch": 11.311070686070686, "percentage": 56.56, "elapsed_time": "1:03:18", "remaining_time": "0:48:37", "throughput": 1032.1, "total_tokens": 3919936} {"current_steps": 43530, "total_steps": 76960, "loss": 0.2528, "lr": 2.3638835812557433e-05, "epoch": 11.312370062370062, "percentage": 56.56, "elapsed_time": "1:03:18", "remaining_time": "0:48:37", "throughput": 1032.11, "total_tokens": 3920400} {"current_steps": 43535, "total_steps": 76960, "loss": 0.1358, "lr": 2.363317465874505e-05, "epoch": 11.31366943866944, "percentage": 56.57, "elapsed_time": "1:03:18", "remaining_time": "0:48:36", "throughput": 1032.1, "total_tokens": 3920816} {"current_steps": 43540, "total_steps": 76960, "loss": 0.1104, "lr": 2.362751357522979e-05, "epoch": 11.314968814968815, "percentage": 56.57, "elapsed_time": "1:03:19", "remaining_time": "0:48:36", "throughput": 1032.1, "total_tokens": 3921248} {"current_steps": 43545, "total_steps": 76960, "loss": 0.3113, "lr": 2.362185256230283e-05, "epoch": 11.316268191268192, "percentage": 56.58, "elapsed_time": "1:03:19", "remaining_time": "0:48:35", "throughput": 1032.12, "total_tokens": 3921744} {"current_steps": 43550, "total_steps": 76960, "loss": 0.2788, "lr": 2.3616191620255307e-05, "epoch": 11.317567567567568, "percentage": 56.59, "elapsed_time": "1:03:20", "remaining_time": "0:48:35", "throughput": 1032.12, "total_tokens": 3922192} {"current_steps": 43555, "total_steps": 76960, "loss": 0.2993, "lr": 2.3610530749378386e-05, "epoch": 11.318866943866944, "percentage": 56.59, "elapsed_time": "1:03:20", "remaining_time": "0:48:34", "throughput": 1032.13, "total_tokens": 3922624} {"current_steps": 43560, "total_steps": 76960, "loss": 0.4235, "lr": 2.3604869949963192e-05, "epoch": 11.32016632016632, "percentage": 56.6, "elapsed_time": "1:03:20", "remaining_time": "0:48:34", "throughput": 1032.13, "total_tokens": 3923072} {"current_steps": 43565, "total_steps": 76960, "loss": 0.2605, "lr": 2.3599209222300874e-05, "epoch": 11.321465696465696, "percentage": 56.61, "elapsed_time": "1:03:21", "remaining_time": "0:48:33", "throughput": 1032.14, "total_tokens": 3923552} {"current_steps": 43570, "total_steps": 76960, "loss": 0.2321, "lr": 2.359354856668257e-05, "epoch": 11.322765072765073, "percentage": 56.61, "elapsed_time": "1:03:21", "remaining_time": "0:48:33", "throughput": 1032.15, "total_tokens": 3924000} {"current_steps": 43575, "total_steps": 76960, "loss": 0.1953, "lr": 2.3587887983399407e-05, "epoch": 11.32406444906445, "percentage": 56.62, "elapsed_time": "1:03:22", "remaining_time": "0:48:33", "throughput": 1032.15, "total_tokens": 3924448} {"current_steps": 43580, "total_steps": 76960, "loss": 0.2727, "lr": 2.3582227472742518e-05, "epoch": 11.325363825363825, "percentage": 56.63, "elapsed_time": "1:03:22", "remaining_time": "0:48:32", "throughput": 1032.16, "total_tokens": 3924912} {"current_steps": 43585, "total_steps": 76960, "loss": 0.3947, "lr": 2.3576567035003027e-05, "epoch": 11.326663201663202, "percentage": 56.63, "elapsed_time": "1:03:23", "remaining_time": "0:48:32", "throughput": 1032.16, "total_tokens": 3925344} {"current_steps": 43590, "total_steps": 76960, "loss": 0.4504, "lr": 2.3570906670472068e-05, "epoch": 11.327962577962579, "percentage": 56.64, "elapsed_time": "1:03:23", "remaining_time": "0:48:31", "throughput": 1032.18, "total_tokens": 3925840} {"current_steps": 43595, "total_steps": 76960, "loss": 0.1133, "lr": 2.3565246379440737e-05, "epoch": 11.329261954261954, "percentage": 56.65, "elapsed_time": "1:03:23", "remaining_time": "0:48:31", "throughput": 1032.18, "total_tokens": 3926288} {"current_steps": 43600, "total_steps": 76960, "loss": 0.134, "lr": 2.3559586162200164e-05, "epoch": 11.33056133056133, "percentage": 56.65, "elapsed_time": "1:03:24", "remaining_time": "0:48:30", "throughput": 1032.18, "total_tokens": 3926704} {"current_steps": 43605, "total_steps": 76960, "loss": 0.0703, "lr": 2.355392601904145e-05, "epoch": 11.331860706860708, "percentage": 56.66, "elapsed_time": "1:03:24", "remaining_time": "0:48:30", "throughput": 1032.19, "total_tokens": 3927152} {"current_steps": 43610, "total_steps": 76960, "loss": 0.4291, "lr": 2.3548265950255717e-05, "epoch": 11.333160083160083, "percentage": 56.67, "elapsed_time": "1:03:25", "remaining_time": "0:48:29", "throughput": 1032.19, "total_tokens": 3927584} {"current_steps": 43615, "total_steps": 76960, "loss": 0.1568, "lr": 2.3542605956134044e-05, "epoch": 11.33445945945946, "percentage": 56.67, "elapsed_time": "1:03:25", "remaining_time": "0:48:29", "throughput": 1032.2, "total_tokens": 3928048} {"current_steps": 43620, "total_steps": 76960, "loss": 0.162, "lr": 2.353694603696755e-05, "epoch": 11.335758835758837, "percentage": 56.68, "elapsed_time": "1:03:25", "remaining_time": "0:48:28", "throughput": 1032.19, "total_tokens": 3928464} {"current_steps": 43625, "total_steps": 76960, "loss": 0.1478, "lr": 2.353128619304733e-05, "epoch": 11.337058212058212, "percentage": 56.69, "elapsed_time": "1:03:26", "remaining_time": "0:48:28", "throughput": 1032.21, "total_tokens": 3928944} {"current_steps": 43630, "total_steps": 76960, "loss": 0.3338, "lr": 2.3525626424664456e-05, "epoch": 11.338357588357589, "percentage": 56.69, "elapsed_time": "1:03:26", "remaining_time": "0:48:28", "throughput": 1032.2, "total_tokens": 3929360} {"current_steps": 43635, "total_steps": 76960, "loss": 0.3832, "lr": 2.3519966732110037e-05, "epoch": 11.339656964656964, "percentage": 56.7, "elapsed_time": "1:03:27", "remaining_time": "0:48:27", "throughput": 1032.21, "total_tokens": 3929824} {"current_steps": 43640, "total_steps": 76960, "loss": 0.2606, "lr": 2.3514307115675138e-05, "epoch": 11.34095634095634, "percentage": 56.7, "elapsed_time": "1:03:27", "remaining_time": "0:48:27", "throughput": 1032.22, "total_tokens": 3930272} {"current_steps": 43645, "total_steps": 76960, "loss": 0.4245, "lr": 2.3508647575650858e-05, "epoch": 11.342255717255718, "percentage": 56.71, "elapsed_time": "1:03:28", "remaining_time": "0:48:26", "throughput": 1032.22, "total_tokens": 3930720} {"current_steps": 43650, "total_steps": 76960, "loss": 0.3643, "lr": 2.3502988112328253e-05, "epoch": 11.343555093555093, "percentage": 56.72, "elapsed_time": "1:03:28", "remaining_time": "0:48:26", "throughput": 1032.23, "total_tokens": 3931184} {"current_steps": 43655, "total_steps": 76960, "loss": 0.2391, "lr": 2.3497328725998406e-05, "epoch": 11.34485446985447, "percentage": 56.72, "elapsed_time": "1:03:28", "remaining_time": "0:48:25", "throughput": 1032.23, "total_tokens": 3931616} {"current_steps": 43660, "total_steps": 76960, "loss": 0.1273, "lr": 2.349166941695238e-05, "epoch": 11.346153846153847, "percentage": 56.73, "elapsed_time": "1:03:29", "remaining_time": "0:48:25", "throughput": 1032.24, "total_tokens": 3932064} {"current_steps": 43665, "total_steps": 76960, "loss": 0.1568, "lr": 2.3486010185481248e-05, "epoch": 11.347453222453222, "percentage": 56.74, "elapsed_time": "1:03:29", "remaining_time": "0:48:24", "throughput": 1032.25, "total_tokens": 3932528} {"current_steps": 43670, "total_steps": 76960, "loss": 0.2897, "lr": 2.3480351031876054e-05, "epoch": 11.348752598752599, "percentage": 56.74, "elapsed_time": "1:03:30", "remaining_time": "0:48:24", "throughput": 1032.25, "total_tokens": 3932976} {"current_steps": 43675, "total_steps": 76960, "loss": 0.268, "lr": 2.3474691956427875e-05, "epoch": 11.350051975051976, "percentage": 56.75, "elapsed_time": "1:03:30", "remaining_time": "0:48:24", "throughput": 1032.25, "total_tokens": 3933392} {"current_steps": 43680, "total_steps": 76960, "loss": 0.226, "lr": 2.346903295942774e-05, "epoch": 11.35135135135135, "percentage": 56.76, "elapsed_time": "1:03:30", "remaining_time": "0:48:23", "throughput": 1032.25, "total_tokens": 3933824} {"current_steps": 43685, "total_steps": 76960, "loss": 0.253, "lr": 2.346337404116671e-05, "epoch": 11.352650727650728, "percentage": 56.76, "elapsed_time": "1:03:31", "remaining_time": "0:48:23", "throughput": 1032.26, "total_tokens": 3934288} {"current_steps": 43690, "total_steps": 76960, "loss": 0.2183, "lr": 2.345771520193583e-05, "epoch": 11.353950103950105, "percentage": 56.77, "elapsed_time": "1:03:31", "remaining_time": "0:48:22", "throughput": 1032.25, "total_tokens": 3934704} {"current_steps": 43695, "total_steps": 76960, "loss": 0.251, "lr": 2.3452056442026127e-05, "epoch": 11.35524948024948, "percentage": 56.78, "elapsed_time": "1:03:32", "remaining_time": "0:48:22", "throughput": 1032.26, "total_tokens": 3935152} {"current_steps": 43700, "total_steps": 76960, "loss": 0.123, "lr": 2.344639776172865e-05, "epoch": 11.356548856548857, "percentage": 56.78, "elapsed_time": "1:03:32", "remaining_time": "0:48:21", "throughput": 1032.26, "total_tokens": 3935584} {"current_steps": 43705, "total_steps": 76960, "loss": 0.0882, "lr": 2.3440739161334417e-05, "epoch": 11.357848232848234, "percentage": 56.79, "elapsed_time": "1:03:33", "remaining_time": "0:48:21", "throughput": 1032.27, "total_tokens": 3936064} {"current_steps": 43710, "total_steps": 76960, "loss": 0.4284, "lr": 2.3435080641134478e-05, "epoch": 11.359147609147609, "percentage": 56.8, "elapsed_time": "1:03:33", "remaining_time": "0:48:20", "throughput": 1032.29, "total_tokens": 3936560} {"current_steps": 43715, "total_steps": 76960, "loss": 0.0726, "lr": 2.3429422201419827e-05, "epoch": 11.360446985446986, "percentage": 56.8, "elapsed_time": "1:03:33", "remaining_time": "0:48:20", "throughput": 1032.28, "total_tokens": 3936976} {"current_steps": 43720, "total_steps": 76960, "loss": 0.3879, "lr": 2.34237638424815e-05, "epoch": 11.361746361746361, "percentage": 56.81, "elapsed_time": "1:03:34", "remaining_time": "0:48:19", "throughput": 1032.29, "total_tokens": 3937440} {"current_steps": 43725, "total_steps": 76960, "loss": 0.3374, "lr": 2.3418105564610508e-05, "epoch": 11.363045738045738, "percentage": 56.82, "elapsed_time": "1:03:34", "remaining_time": "0:48:19", "throughput": 1032.3, "total_tokens": 3937888} {"current_steps": 43730, "total_steps": 76960, "loss": 0.3754, "lr": 2.341244736809787e-05, "epoch": 11.364345114345115, "percentage": 56.82, "elapsed_time": "1:03:35", "remaining_time": "0:48:19", "throughput": 1032.3, "total_tokens": 3938320} {"current_steps": 43735, "total_steps": 76960, "loss": 0.3414, "lr": 2.3406789253234575e-05, "epoch": 11.36564449064449, "percentage": 56.83, "elapsed_time": "1:03:35", "remaining_time": "0:48:18", "throughput": 1032.3, "total_tokens": 3938752} {"current_steps": 43740, "total_steps": 76960, "loss": 0.2263, "lr": 2.3401131220311643e-05, "epoch": 11.366943866943867, "percentage": 56.83, "elapsed_time": "1:03:35", "remaining_time": "0:48:18", "throughput": 1032.31, "total_tokens": 3939232} {"current_steps": 43745, "total_steps": 76960, "loss": 0.2703, "lr": 2.3395473269620056e-05, "epoch": 11.368243243243244, "percentage": 56.84, "elapsed_time": "1:03:36", "remaining_time": "0:48:17", "throughput": 1032.32, "total_tokens": 3939696} {"current_steps": 43750, "total_steps": 76960, "loss": 0.2411, "lr": 2.3389815401450827e-05, "epoch": 11.369542619542619, "percentage": 56.85, "elapsed_time": "1:03:36", "remaining_time": "0:48:17", "throughput": 1032.33, "total_tokens": 3940144} {"current_steps": 43755, "total_steps": 76960, "loss": 0.4106, "lr": 2.338415761609493e-05, "epoch": 11.370841995841996, "percentage": 56.85, "elapsed_time": "1:03:37", "remaining_time": "0:48:16", "throughput": 1032.34, "total_tokens": 3940608} {"current_steps": 43760, "total_steps": 76960, "loss": 0.1981, "lr": 2.337849991384335e-05, "epoch": 11.372141372141373, "percentage": 56.86, "elapsed_time": "1:03:37", "remaining_time": "0:48:16", "throughput": 1032.34, "total_tokens": 3941056} {"current_steps": 43765, "total_steps": 76960, "loss": 0.2341, "lr": 2.3372842294987083e-05, "epoch": 11.373440748440748, "percentage": 56.87, "elapsed_time": "1:03:38", "remaining_time": "0:48:15", "throughput": 1032.35, "total_tokens": 3941536} {"current_steps": 43770, "total_steps": 76960, "loss": 0.2849, "lr": 2.3367184759817087e-05, "epoch": 11.374740124740125, "percentage": 56.87, "elapsed_time": "1:03:38", "remaining_time": "0:48:15", "throughput": 1032.36, "total_tokens": 3941984} {"current_steps": 43775, "total_steps": 76960, "loss": 0.2889, "lr": 2.336152730862435e-05, "epoch": 11.3760395010395, "percentage": 56.88, "elapsed_time": "1:03:38", "remaining_time": "0:48:14", "throughput": 1032.36, "total_tokens": 3942400} {"current_steps": 43780, "total_steps": 76960, "loss": 0.135, "lr": 2.3355869941699822e-05, "epoch": 11.377338877338877, "percentage": 56.89, "elapsed_time": "1:03:39", "remaining_time": "0:48:14", "throughput": 1032.36, "total_tokens": 3942832} {"current_steps": 43785, "total_steps": 76960, "loss": 0.1364, "lr": 2.3350212659334493e-05, "epoch": 11.378638253638254, "percentage": 56.89, "elapsed_time": "1:03:39", "remaining_time": "0:48:14", "throughput": 1032.38, "total_tokens": 3943360} {"current_steps": 43790, "total_steps": 76960, "loss": 0.3155, "lr": 2.3344555461819297e-05, "epoch": 11.37993762993763, "percentage": 56.9, "elapsed_time": "1:03:40", "remaining_time": "0:48:13", "throughput": 1032.38, "total_tokens": 3943792} {"current_steps": 43795, "total_steps": 76960, "loss": 0.1451, "lr": 2.3338898349445203e-05, "epoch": 11.381237006237006, "percentage": 56.91, "elapsed_time": "1:03:40", "remaining_time": "0:48:13", "throughput": 1032.38, "total_tokens": 3944208} {"current_steps": 43800, "total_steps": 76960, "loss": 0.2807, "lr": 2.3333241322503157e-05, "epoch": 11.382536382536383, "percentage": 56.91, "elapsed_time": "1:03:40", "remaining_time": "0:48:12", "throughput": 1032.38, "total_tokens": 3944656} {"current_steps": 43805, "total_steps": 76960, "loss": 0.645, "lr": 2.3327584381284115e-05, "epoch": 11.383835758835758, "percentage": 56.92, "elapsed_time": "1:03:41", "remaining_time": "0:48:12", "throughput": 1032.4, "total_tokens": 3945152} {"current_steps": 43810, "total_steps": 76960, "loss": 0.106, "lr": 2.3321927526079e-05, "epoch": 11.385135135135135, "percentage": 56.93, "elapsed_time": "1:03:41", "remaining_time": "0:48:11", "throughput": 1032.4, "total_tokens": 3945568} {"current_steps": 43815, "total_steps": 76960, "loss": 0.3419, "lr": 2.3316270757178764e-05, "epoch": 11.386434511434512, "percentage": 56.93, "elapsed_time": "1:03:42", "remaining_time": "0:48:11", "throughput": 1032.4, "total_tokens": 3946016} {"current_steps": 43820, "total_steps": 76960, "loss": 0.2585, "lr": 2.3310614074874346e-05, "epoch": 11.387733887733887, "percentage": 56.94, "elapsed_time": "1:03:42", "remaining_time": "0:48:10", "throughput": 1032.41, "total_tokens": 3946480} {"current_steps": 43825, "total_steps": 76960, "loss": 0.2425, "lr": 2.330495747945665e-05, "epoch": 11.389033264033264, "percentage": 56.95, "elapsed_time": "1:03:43", "remaining_time": "0:48:10", "throughput": 1032.42, "total_tokens": 3946928} {"current_steps": 43830, "total_steps": 76960, "loss": 0.3275, "lr": 2.3299300971216623e-05, "epoch": 11.390332640332641, "percentage": 56.95, "elapsed_time": "1:03:43", "remaining_time": "0:48:10", "throughput": 1032.42, "total_tokens": 3947360} {"current_steps": 43835, "total_steps": 76960, "loss": 0.1302, "lr": 2.329364455044517e-05, "epoch": 11.391632016632016, "percentage": 56.96, "elapsed_time": "1:03:43", "remaining_time": "0:48:09", "throughput": 1032.41, "total_tokens": 3947776} {"current_steps": 43840, "total_steps": 76960, "loss": 0.0729, "lr": 2.3287988217433224e-05, "epoch": 11.392931392931393, "percentage": 56.96, "elapsed_time": "1:03:44", "remaining_time": "0:48:09", "throughput": 1032.42, "total_tokens": 3948240} {"current_steps": 43845, "total_steps": 76960, "loss": 0.2169, "lr": 2.3282331972471673e-05, "epoch": 11.39423076923077, "percentage": 56.97, "elapsed_time": "1:03:44", "remaining_time": "0:48:08", "throughput": 1032.43, "total_tokens": 3948688} {"current_steps": 43850, "total_steps": 76960, "loss": 0.3502, "lr": 2.327667581585144e-05, "epoch": 11.395530145530145, "percentage": 56.98, "elapsed_time": "1:03:45", "remaining_time": "0:48:08", "throughput": 1032.44, "total_tokens": 3949152} {"current_steps": 43855, "total_steps": 76960, "loss": 0.362, "lr": 2.3271019747863414e-05, "epoch": 11.396829521829522, "percentage": 56.98, "elapsed_time": "1:03:45", "remaining_time": "0:48:07", "throughput": 1032.44, "total_tokens": 3949616} {"current_steps": 43860, "total_steps": 76960, "loss": 0.1403, "lr": 2.3265363768798512e-05, "epoch": 11.398128898128897, "percentage": 56.99, "elapsed_time": "1:03:45", "remaining_time": "0:48:07", "throughput": 1032.45, "total_tokens": 3950064} {"current_steps": 43865, "total_steps": 76960, "loss": 0.0748, "lr": 2.32597078789476e-05, "epoch": 11.399428274428274, "percentage": 57.0, "elapsed_time": "1:03:46", "remaining_time": "0:48:06", "throughput": 1032.47, "total_tokens": 3950560} {"current_steps": 43870, "total_steps": 76960, "loss": 0.1103, "lr": 2.3254052078601588e-05, "epoch": 11.400727650727651, "percentage": 57.0, "elapsed_time": "1:03:46", "remaining_time": "0:48:06", "throughput": 1032.46, "total_tokens": 3950976} {"current_steps": 43875, "total_steps": 76960, "loss": 0.1898, "lr": 2.324839636805134e-05, "epoch": 11.402027027027026, "percentage": 57.01, "elapsed_time": "1:03:47", "remaining_time": "0:48:05", "throughput": 1032.46, "total_tokens": 3951408} {"current_steps": 43880, "total_steps": 76960, "loss": 0.3416, "lr": 2.3242740747587762e-05, "epoch": 11.403326403326403, "percentage": 57.02, "elapsed_time": "1:03:47", "remaining_time": "0:48:05", "throughput": 1032.48, "total_tokens": 3951888} {"current_steps": 43885, "total_steps": 76960, "loss": 0.2529, "lr": 2.3237085217501697e-05, "epoch": 11.40462577962578, "percentage": 57.02, "elapsed_time": "1:03:47", "remaining_time": "0:48:05", "throughput": 1032.5, "total_tokens": 3952400} {"current_steps": 43890, "total_steps": 76960, "loss": 0.0574, "lr": 2.3231429778084034e-05, "epoch": 11.405925155925155, "percentage": 57.03, "elapsed_time": "1:03:48", "remaining_time": "0:48:04", "throughput": 1032.5, "total_tokens": 3952848} {"current_steps": 43895, "total_steps": 76960, "loss": 0.278, "lr": 2.322577442962564e-05, "epoch": 11.407224532224532, "percentage": 57.04, "elapsed_time": "1:03:48", "remaining_time": "0:48:04", "throughput": 1032.51, "total_tokens": 3953312} {"current_steps": 43900, "total_steps": 76960, "loss": 0.3409, "lr": 2.3220119172417348e-05, "epoch": 11.40852390852391, "percentage": 57.04, "elapsed_time": "1:03:49", "remaining_time": "0:48:03", "throughput": 1032.51, "total_tokens": 3953744} {"current_steps": 43905, "total_steps": 76960, "loss": 0.0766, "lr": 2.321446400675005e-05, "epoch": 11.409823284823284, "percentage": 57.05, "elapsed_time": "1:03:49", "remaining_time": "0:48:03", "throughput": 1032.52, "total_tokens": 3954208} {"current_steps": 43910, "total_steps": 76960, "loss": 0.4248, "lr": 2.320880893291457e-05, "epoch": 11.411122661122661, "percentage": 57.06, "elapsed_time": "1:03:50", "remaining_time": "0:48:02", "throughput": 1032.53, "total_tokens": 3954672} {"current_steps": 43915, "total_steps": 76960, "loss": 0.2268, "lr": 2.3203153951201764e-05, "epoch": 11.412422037422038, "percentage": 57.06, "elapsed_time": "1:03:50", "remaining_time": "0:48:02", "throughput": 1032.53, "total_tokens": 3955120} {"current_steps": 43920, "total_steps": 76960, "loss": 0.3224, "lr": 2.319749906190247e-05, "epoch": 11.413721413721413, "percentage": 57.07, "elapsed_time": "1:03:50", "remaining_time": "0:48:01", "throughput": 1032.54, "total_tokens": 3955568} {"current_steps": 43925, "total_steps": 76960, "loss": 0.1957, "lr": 2.3191844265307532e-05, "epoch": 11.41502079002079, "percentage": 57.08, "elapsed_time": "1:03:51", "remaining_time": "0:48:01", "throughput": 1032.54, "total_tokens": 3955984} {"current_steps": 43930, "total_steps": 76960, "loss": 0.1483, "lr": 2.3186189561707773e-05, "epoch": 11.416320166320165, "percentage": 57.08, "elapsed_time": "1:03:51", "remaining_time": "0:48:01", "throughput": 1032.54, "total_tokens": 3956432} {"current_steps": 43935, "total_steps": 76960, "loss": 0.2839, "lr": 2.3180534951394022e-05, "epoch": 11.417619542619542, "percentage": 57.09, "elapsed_time": "1:03:52", "remaining_time": "0:48:00", "throughput": 1032.54, "total_tokens": 3956864} {"current_steps": 43940, "total_steps": 76960, "loss": 0.2133, "lr": 2.3174880434657097e-05, "epoch": 11.41891891891892, "percentage": 57.09, "elapsed_time": "1:03:52", "remaining_time": "0:48:00", "throughput": 1032.54, "total_tokens": 3957296} {"current_steps": 43945, "total_steps": 76960, "loss": 0.3156, "lr": 2.3169226011787835e-05, "epoch": 11.420218295218294, "percentage": 57.1, "elapsed_time": "1:03:52", "remaining_time": "0:47:59", "throughput": 1032.55, "total_tokens": 3957760} {"current_steps": 43950, "total_steps": 76960, "loss": 0.1482, "lr": 2.316357168307702e-05, "epoch": 11.421517671517671, "percentage": 57.11, "elapsed_time": "1:03:53", "remaining_time": "0:47:59", "throughput": 1032.55, "total_tokens": 3958192} {"current_steps": 43955, "total_steps": 76960, "loss": 0.2641, "lr": 2.3157917448815475e-05, "epoch": 11.422817047817048, "percentage": 57.11, "elapsed_time": "1:03:53", "remaining_time": "0:47:58", "throughput": 1032.55, "total_tokens": 3958608} {"current_steps": 43960, "total_steps": 76960, "loss": 0.1724, "lr": 2.315226330929401e-05, "epoch": 11.424116424116423, "percentage": 57.12, "elapsed_time": "1:03:54", "remaining_time": "0:47:58", "throughput": 1032.54, "total_tokens": 3959024} {"current_steps": 43965, "total_steps": 76960, "loss": 0.1857, "lr": 2.31466092648034e-05, "epoch": 11.4254158004158, "percentage": 57.13, "elapsed_time": "1:03:54", "remaining_time": "0:47:57", "throughput": 1032.55, "total_tokens": 3959488} {"current_steps": 43970, "total_steps": 76960, "loss": 0.2801, "lr": 2.314095531563446e-05, "epoch": 11.426715176715177, "percentage": 57.13, "elapsed_time": "1:03:55", "remaining_time": "0:47:57", "throughput": 1032.56, "total_tokens": 3959952} {"current_steps": 43975, "total_steps": 76960, "loss": 0.2793, "lr": 2.313530146207796e-05, "epoch": 11.428014553014552, "percentage": 57.14, "elapsed_time": "1:03:55", "remaining_time": "0:47:56", "throughput": 1032.56, "total_tokens": 3960384} {"current_steps": 43980, "total_steps": 76960, "loss": 0.026, "lr": 2.3129647704424706e-05, "epoch": 11.42931392931393, "percentage": 57.15, "elapsed_time": "1:03:55", "remaining_time": "0:47:56", "throughput": 1032.57, "total_tokens": 3960832} {"current_steps": 43985, "total_steps": 76960, "loss": 0.2183, "lr": 2.3123994042965453e-05, "epoch": 11.430613305613306, "percentage": 57.15, "elapsed_time": "1:03:56", "remaining_time": "0:47:56", "throughput": 1032.58, "total_tokens": 3961296} {"current_steps": 43990, "total_steps": 76960, "loss": 0.4997, "lr": 2.3118340477990987e-05, "epoch": 11.431912681912682, "percentage": 57.16, "elapsed_time": "1:03:56", "remaining_time": "0:47:55", "throughput": 1032.58, "total_tokens": 3961744} {"current_steps": 43995, "total_steps": 76960, "loss": 0.3404, "lr": 2.3112687009792068e-05, "epoch": 11.433212058212058, "percentage": 57.17, "elapsed_time": "1:03:57", "remaining_time": "0:47:55", "throughput": 1032.6, "total_tokens": 3962240} {"current_steps": 44000, "total_steps": 76960, "loss": 0.3542, "lr": 2.3107033638659476e-05, "epoch": 11.434511434511435, "percentage": 57.17, "elapsed_time": "1:03:57", "remaining_time": "0:47:54", "throughput": 1032.61, "total_tokens": 3962720} {"current_steps": 44005, "total_steps": 76960, "loss": 0.4345, "lr": 2.3101380364883946e-05, "epoch": 11.43581081081081, "percentage": 57.18, "elapsed_time": "1:03:57", "remaining_time": "0:47:54", "throughput": 1032.61, "total_tokens": 3963136} {"current_steps": 44010, "total_steps": 76960, "loss": 0.2551, "lr": 2.309572718875625e-05, "epoch": 11.437110187110187, "percentage": 57.19, "elapsed_time": "1:03:58", "remaining_time": "0:47:53", "throughput": 1032.62, "total_tokens": 3963600} {"current_steps": 44015, "total_steps": 76960, "loss": 0.3579, "lr": 2.3090074110567124e-05, "epoch": 11.438409563409563, "percentage": 57.19, "elapsed_time": "1:03:58", "remaining_time": "0:47:53", "throughput": 1032.63, "total_tokens": 3964064} {"current_steps": 44020, "total_steps": 76960, "loss": 0.3316, "lr": 2.3084421130607323e-05, "epoch": 11.43970893970894, "percentage": 57.2, "elapsed_time": "1:03:59", "remaining_time": "0:47:52", "throughput": 1032.63, "total_tokens": 3964512} {"current_steps": 44025, "total_steps": 76960, "loss": 0.3177, "lr": 2.3078768249167575e-05, "epoch": 11.441008316008316, "percentage": 57.21, "elapsed_time": "1:03:59", "remaining_time": "0:47:52", "throughput": 1032.63, "total_tokens": 3964928} {"current_steps": 44030, "total_steps": 76960, "loss": 0.1171, "lr": 2.3073115466538614e-05, "epoch": 11.442307692307692, "percentage": 57.21, "elapsed_time": "1:04:00", "remaining_time": "0:47:51", "throughput": 1032.63, "total_tokens": 3965360} {"current_steps": 44035, "total_steps": 76960, "loss": 0.1241, "lr": 2.3067462783011183e-05, "epoch": 11.443607068607069, "percentage": 57.22, "elapsed_time": "1:04:00", "remaining_time": "0:47:51", "throughput": 1032.64, "total_tokens": 3965824} {"current_steps": 44040, "total_steps": 76960, "loss": 0.0751, "lr": 2.3061810198875978e-05, "epoch": 11.444906444906445, "percentage": 57.22, "elapsed_time": "1:04:00", "remaining_time": "0:47:51", "throughput": 1032.63, "total_tokens": 3966240} {"current_steps": 44045, "total_steps": 76960, "loss": 0.3591, "lr": 2.3056157714423736e-05, "epoch": 11.44620582120582, "percentage": 57.23, "elapsed_time": "1:04:01", "remaining_time": "0:47:50", "throughput": 1032.64, "total_tokens": 3966688} {"current_steps": 44050, "total_steps": 76960, "loss": 0.2018, "lr": 2.3050505329945163e-05, "epoch": 11.447505197505198, "percentage": 57.24, "elapsed_time": "1:04:01", "remaining_time": "0:47:50", "throughput": 1032.65, "total_tokens": 3967152} {"current_steps": 44055, "total_steps": 76960, "loss": 0.3532, "lr": 2.304485304573098e-05, "epoch": 11.448804573804575, "percentage": 57.24, "elapsed_time": "1:04:02", "remaining_time": "0:47:49", "throughput": 1032.65, "total_tokens": 3967584} {"current_steps": 44060, "total_steps": 76960, "loss": 0.2308, "lr": 2.3039200862071863e-05, "epoch": 11.45010395010395, "percentage": 57.25, "elapsed_time": "1:04:02", "remaining_time": "0:47:49", "throughput": 1032.65, "total_tokens": 3968032} {"current_steps": 44065, "total_steps": 76960, "loss": 0.1259, "lr": 2.3033548779258535e-05, "epoch": 11.451403326403327, "percentage": 57.26, "elapsed_time": "1:04:02", "remaining_time": "0:47:48", "throughput": 1032.66, "total_tokens": 3968480} {"current_steps": 44070, "total_steps": 76960, "loss": 0.0741, "lr": 2.302789679758167e-05, "epoch": 11.452702702702704, "percentage": 57.26, "elapsed_time": "1:04:03", "remaining_time": "0:47:48", "throughput": 1032.66, "total_tokens": 3968944} {"current_steps": 44075, "total_steps": 76960, "loss": 0.1999, "lr": 2.3022244917331974e-05, "epoch": 11.454002079002079, "percentage": 57.27, "elapsed_time": "1:04:03", "remaining_time": "0:47:47", "throughput": 1032.68, "total_tokens": 3969440} {"current_steps": 44080, "total_steps": 76960, "loss": 0.2263, "lr": 2.3016593138800104e-05, "epoch": 11.455301455301456, "percentage": 57.28, "elapsed_time": "1:04:04", "remaining_time": "0:47:47", "throughput": 1032.68, "total_tokens": 3969872} {"current_steps": 44085, "total_steps": 76960, "loss": 0.3595, "lr": 2.3010941462276755e-05, "epoch": 11.45660083160083, "percentage": 57.28, "elapsed_time": "1:04:04", "remaining_time": "0:47:47", "throughput": 1032.69, "total_tokens": 3970336} {"current_steps": 44090, "total_steps": 76960, "loss": 0.3104, "lr": 2.30052898880526e-05, "epoch": 11.457900207900208, "percentage": 57.29, "elapsed_time": "1:04:05", "remaining_time": "0:47:46", "throughput": 1032.7, "total_tokens": 3970816} {"current_steps": 44095, "total_steps": 76960, "loss": 0.3647, "lr": 2.2999638416418283e-05, "epoch": 11.459199584199585, "percentage": 57.3, "elapsed_time": "1:04:05", "remaining_time": "0:47:46", "throughput": 1032.7, "total_tokens": 3971248} {"current_steps": 44100, "total_steps": 76960, "loss": 0.1323, "lr": 2.299398704766449e-05, "epoch": 11.46049896049896, "percentage": 57.3, "elapsed_time": "1:04:05", "remaining_time": "0:47:45", "throughput": 1032.71, "total_tokens": 3971712} {"current_steps": 44105, "total_steps": 76960, "loss": 0.3615, "lr": 2.2988335782081855e-05, "epoch": 11.461798336798337, "percentage": 57.31, "elapsed_time": "1:04:06", "remaining_time": "0:47:45", "throughput": 1032.71, "total_tokens": 3972128} {"current_steps": 44110, "total_steps": 76960, "loss": 0.2768, "lr": 2.2982684619961048e-05, "epoch": 11.463097713097714, "percentage": 57.32, "elapsed_time": "1:04:06", "remaining_time": "0:47:44", "throughput": 1032.72, "total_tokens": 3972592} {"current_steps": 44115, "total_steps": 76960, "loss": 0.404, "lr": 2.2977033561592694e-05, "epoch": 11.464397089397089, "percentage": 57.32, "elapsed_time": "1:04:07", "remaining_time": "0:47:44", "throughput": 1032.72, "total_tokens": 3973040} {"current_steps": 44120, "total_steps": 76960, "loss": 0.1467, "lr": 2.297138260726745e-05, "epoch": 11.465696465696466, "percentage": 57.33, "elapsed_time": "1:04:07", "remaining_time": "0:47:43", "throughput": 1032.73, "total_tokens": 3973488} {"current_steps": 44125, "total_steps": 76960, "loss": 0.1274, "lr": 2.2965731757275936e-05, "epoch": 11.466995841995843, "percentage": 57.33, "elapsed_time": "1:04:07", "remaining_time": "0:47:43", "throughput": 1032.73, "total_tokens": 3973936} {"current_steps": 44130, "total_steps": 76960, "loss": 0.2042, "lr": 2.2960081011908797e-05, "epoch": 11.468295218295218, "percentage": 57.34, "elapsed_time": "1:04:08", "remaining_time": "0:47:42", "throughput": 1032.74, "total_tokens": 3974384} {"current_steps": 44135, "total_steps": 76960, "loss": 0.1289, "lr": 2.295443037145663e-05, "epoch": 11.469594594594595, "percentage": 57.35, "elapsed_time": "1:04:08", "remaining_time": "0:47:42", "throughput": 1032.73, "total_tokens": 3974800} {"current_steps": 44140, "total_steps": 76960, "loss": 0.2432, "lr": 2.2948779836210088e-05, "epoch": 11.470893970893972, "percentage": 57.35, "elapsed_time": "1:04:09", "remaining_time": "0:47:42", "throughput": 1032.74, "total_tokens": 3975248} {"current_steps": 44145, "total_steps": 76960, "loss": 0.2823, "lr": 2.294312940645975e-05, "epoch": 11.472193347193347, "percentage": 57.36, "elapsed_time": "1:04:09", "remaining_time": "0:47:41", "throughput": 1032.74, "total_tokens": 3975696} {"current_steps": 44150, "total_steps": 76960, "loss": 0.157, "lr": 2.2937479082496243e-05, "epoch": 11.473492723492724, "percentage": 57.37, "elapsed_time": "1:04:10", "remaining_time": "0:47:41", "throughput": 1032.74, "total_tokens": 3976128} {"current_steps": 44155, "total_steps": 76960, "loss": 0.4562, "lr": 2.293182886461017e-05, "epoch": 11.4747920997921, "percentage": 57.37, "elapsed_time": "1:04:10", "remaining_time": "0:47:40", "throughput": 1032.74, "total_tokens": 3976560} {"current_steps": 44160, "total_steps": 76960, "loss": 0.2393, "lr": 2.292617875309211e-05, "epoch": 11.476091476091476, "percentage": 57.38, "elapsed_time": "1:04:10", "remaining_time": "0:47:40", "throughput": 1032.74, "total_tokens": 3976992} {"current_steps": 44165, "total_steps": 76960, "loss": 0.274, "lr": 2.2920528748232668e-05, "epoch": 11.477390852390853, "percentage": 57.39, "elapsed_time": "1:04:11", "remaining_time": "0:47:39", "throughput": 1032.75, "total_tokens": 3977440} {"current_steps": 44170, "total_steps": 76960, "loss": 0.2316, "lr": 2.291487885032242e-05, "epoch": 11.478690228690228, "percentage": 57.39, "elapsed_time": "1:04:11", "remaining_time": "0:47:39", "throughput": 1032.75, "total_tokens": 3977888} {"current_steps": 44175, "total_steps": 76960, "loss": 0.2095, "lr": 2.290922905965196e-05, "epoch": 11.479989604989605, "percentage": 57.4, "elapsed_time": "1:04:12", "remaining_time": "0:47:38", "throughput": 1032.75, "total_tokens": 3978320} {"current_steps": 44180, "total_steps": 76960, "loss": 0.1495, "lr": 2.2903579376511842e-05, "epoch": 11.481288981288982, "percentage": 57.41, "elapsed_time": "1:04:12", "remaining_time": "0:47:38", "throughput": 1032.77, "total_tokens": 3978800} {"current_steps": 44185, "total_steps": 76960, "loss": 0.3276, "lr": 2.289792980119265e-05, "epoch": 11.482588357588357, "percentage": 57.41, "elapsed_time": "1:04:12", "remaining_time": "0:47:38", "throughput": 1032.78, "total_tokens": 3979280} {"current_steps": 44190, "total_steps": 76960, "loss": 0.2587, "lr": 2.2892280333984938e-05, "epoch": 11.483887733887734, "percentage": 57.42, "elapsed_time": "1:04:13", "remaining_time": "0:47:37", "throughput": 1032.79, "total_tokens": 3979760} {"current_steps": 44195, "total_steps": 76960, "loss": 0.1048, "lr": 2.288663097517928e-05, "epoch": 11.48518711018711, "percentage": 57.43, "elapsed_time": "1:04:13", "remaining_time": "0:47:37", "throughput": 1032.8, "total_tokens": 3980208} {"current_steps": 44200, "total_steps": 76960, "loss": 0.4423, "lr": 2.2880981725066205e-05, "epoch": 11.486486486486486, "percentage": 57.43, "elapsed_time": "1:04:14", "remaining_time": "0:47:36", "throughput": 1032.79, "total_tokens": 3980624} {"current_steps": 44205, "total_steps": 76960, "loss": 0.497, "lr": 2.2875332583936276e-05, "epoch": 11.487785862785863, "percentage": 57.44, "elapsed_time": "1:04:14", "remaining_time": "0:47:36", "throughput": 1032.79, "total_tokens": 3981056} {"current_steps": 44210, "total_steps": 76960, "loss": 0.0267, "lr": 2.286968355208002e-05, "epoch": 11.48908523908524, "percentage": 57.45, "elapsed_time": "1:04:15", "remaining_time": "0:47:35", "throughput": 1032.81, "total_tokens": 3981536} {"current_steps": 44215, "total_steps": 76960, "loss": 0.1366, "lr": 2.2864034629787993e-05, "epoch": 11.490384615384615, "percentage": 57.45, "elapsed_time": "1:04:15", "remaining_time": "0:47:35", "throughput": 1032.8, "total_tokens": 3981968} {"current_steps": 44220, "total_steps": 76960, "loss": 0.5351, "lr": 2.2858385817350704e-05, "epoch": 11.491683991683992, "percentage": 57.46, "elapsed_time": "1:04:15", "remaining_time": "0:47:34", "throughput": 1032.81, "total_tokens": 3982416} {"current_steps": 44225, "total_steps": 76960, "loss": 0.4252, "lr": 2.2852737115058682e-05, "epoch": 11.492983367983369, "percentage": 57.46, "elapsed_time": "1:04:16", "remaining_time": "0:47:34", "throughput": 1032.82, "total_tokens": 3982880} {"current_steps": 44230, "total_steps": 76960, "loss": 0.0444, "lr": 2.2847088523202457e-05, "epoch": 11.494282744282744, "percentage": 57.47, "elapsed_time": "1:04:16", "remaining_time": "0:47:33", "throughput": 1032.82, "total_tokens": 3983312} {"current_steps": 44235, "total_steps": 76960, "loss": 0.1002, "lr": 2.284144004207252e-05, "epoch": 11.495582120582121, "percentage": 57.48, "elapsed_time": "1:04:17", "remaining_time": "0:47:33", "throughput": 1032.83, "total_tokens": 3983792} {"current_steps": 44240, "total_steps": 76960, "loss": 0.2139, "lr": 2.2835791671959397e-05, "epoch": 11.496881496881496, "percentage": 57.48, "elapsed_time": "1:04:17", "remaining_time": "0:47:33", "throughput": 1032.83, "total_tokens": 3984208} {"current_steps": 44245, "total_steps": 76960, "loss": 0.1791, "lr": 2.2830143413153576e-05, "epoch": 11.498180873180873, "percentage": 57.49, "elapsed_time": "1:04:17", "remaining_time": "0:47:32", "throughput": 1032.83, "total_tokens": 3984640} {"current_steps": 44250, "total_steps": 76960, "loss": 0.4928, "lr": 2.2824495265945568e-05, "epoch": 11.49948024948025, "percentage": 57.5, "elapsed_time": "1:04:18", "remaining_time": "0:47:32", "throughput": 1032.84, "total_tokens": 3985104} {"current_steps": 44255, "total_steps": 76960, "loss": 0.0961, "lr": 2.2818847230625846e-05, "epoch": 11.500779625779625, "percentage": 57.5, "elapsed_time": "1:04:18", "remaining_time": "0:47:31", "throughput": 1032.84, "total_tokens": 3985536} {"current_steps": 44260, "total_steps": 76960, "loss": 0.2718, "lr": 2.2813199307484904e-05, "epoch": 11.502079002079002, "percentage": 57.51, "elapsed_time": "1:04:19", "remaining_time": "0:47:31", "throughput": 1032.84, "total_tokens": 3985984} {"current_steps": 44265, "total_steps": 76960, "loss": 0.4683, "lr": 2.280755149681321e-05, "epoch": 11.503378378378379, "percentage": 57.52, "elapsed_time": "1:04:19", "remaining_time": "0:47:30", "throughput": 1032.85, "total_tokens": 3986432} {"current_steps": 44270, "total_steps": 76960, "loss": 0.3585, "lr": 2.2801903798901256e-05, "epoch": 11.504677754677754, "percentage": 57.52, "elapsed_time": "1:04:20", "remaining_time": "0:47:30", "throughput": 1032.85, "total_tokens": 3986880} {"current_steps": 44275, "total_steps": 76960, "loss": 0.373, "lr": 2.2796256214039483e-05, "epoch": 11.505977130977131, "percentage": 57.53, "elapsed_time": "1:04:20", "remaining_time": "0:47:29", "throughput": 1032.85, "total_tokens": 3987312} {"current_steps": 44280, "total_steps": 76960, "loss": 0.1483, "lr": 2.2790608742518372e-05, "epoch": 11.507276507276508, "percentage": 57.54, "elapsed_time": "1:04:20", "remaining_time": "0:47:29", "throughput": 1032.87, "total_tokens": 3987808} {"current_steps": 44285, "total_steps": 76960, "loss": 0.2936, "lr": 2.2784961384628374e-05, "epoch": 11.508575883575883, "percentage": 57.54, "elapsed_time": "1:04:21", "remaining_time": "0:47:29", "throughput": 1032.88, "total_tokens": 3988272} {"current_steps": 44290, "total_steps": 76960, "loss": 0.194, "lr": 2.2779314140659923e-05, "epoch": 11.50987525987526, "percentage": 57.55, "elapsed_time": "1:04:21", "remaining_time": "0:47:28", "throughput": 1032.88, "total_tokens": 3988720} {"current_steps": 44295, "total_steps": 76960, "loss": 0.1114, "lr": 2.277366701090348e-05, "epoch": 11.511174636174637, "percentage": 57.56, "elapsed_time": "1:04:22", "remaining_time": "0:47:28", "throughput": 1032.88, "total_tokens": 3989152} {"current_steps": 44300, "total_steps": 76960, "loss": 0.2694, "lr": 2.276801999564947e-05, "epoch": 11.512474012474012, "percentage": 57.56, "elapsed_time": "1:04:22", "remaining_time": "0:47:27", "throughput": 1032.88, "total_tokens": 3989584} {"current_steps": 44305, "total_steps": 76960, "loss": 0.0623, "lr": 2.276237309518834e-05, "epoch": 11.513773388773389, "percentage": 57.57, "elapsed_time": "1:04:22", "remaining_time": "0:47:27", "throughput": 1032.91, "total_tokens": 3990112} {"current_steps": 44310, "total_steps": 76960, "loss": 0.3675, "lr": 2.2756726309810496e-05, "epoch": 11.515072765072766, "percentage": 57.58, "elapsed_time": "1:04:23", "remaining_time": "0:47:26", "throughput": 1032.92, "total_tokens": 3990576} {"current_steps": 44315, "total_steps": 76960, "loss": 0.1525, "lr": 2.2751079639806376e-05, "epoch": 11.516372141372141, "percentage": 57.58, "elapsed_time": "1:04:23", "remaining_time": "0:47:26", "throughput": 1032.91, "total_tokens": 3990992} {"current_steps": 44320, "total_steps": 76960, "loss": 0.1706, "lr": 2.2745433085466374e-05, "epoch": 11.517671517671518, "percentage": 57.59, "elapsed_time": "1:04:24", "remaining_time": "0:47:25", "throughput": 1032.92, "total_tokens": 3991440} {"current_steps": 44325, "total_steps": 76960, "loss": 0.5704, "lr": 2.2739786647080924e-05, "epoch": 11.518970893970893, "percentage": 57.59, "elapsed_time": "1:04:24", "remaining_time": "0:47:25", "throughput": 1032.94, "total_tokens": 3991936} {"current_steps": 44330, "total_steps": 76960, "loss": 0.1841, "lr": 2.2734140324940398e-05, "epoch": 11.52027027027027, "percentage": 57.6, "elapsed_time": "1:04:25", "remaining_time": "0:47:24", "throughput": 1032.94, "total_tokens": 3992368} {"current_steps": 44335, "total_steps": 76960, "loss": 0.517, "lr": 2.2728494119335214e-05, "epoch": 11.521569646569647, "percentage": 57.61, "elapsed_time": "1:04:25", "remaining_time": "0:47:24", "throughput": 1032.94, "total_tokens": 3992816} {"current_steps": 44340, "total_steps": 76960, "loss": 0.1733, "lr": 2.2722848030555745e-05, "epoch": 11.522869022869022, "percentage": 57.61, "elapsed_time": "1:04:25", "remaining_time": "0:47:24", "throughput": 1032.95, "total_tokens": 3993264} {"current_steps": 44345, "total_steps": 76960, "loss": 0.216, "lr": 2.27172020588924e-05, "epoch": 11.5241683991684, "percentage": 57.62, "elapsed_time": "1:04:26", "remaining_time": "0:47:23", "throughput": 1032.95, "total_tokens": 3993712} {"current_steps": 44350, "total_steps": 76960, "loss": 0.1712, "lr": 2.271155620463553e-05, "epoch": 11.525467775467776, "percentage": 57.63, "elapsed_time": "1:04:26", "remaining_time": "0:47:23", "throughput": 1032.95, "total_tokens": 3994128} {"current_steps": 44355, "total_steps": 76960, "loss": 0.1592, "lr": 2.2705910468075516e-05, "epoch": 11.526767151767151, "percentage": 57.63, "elapsed_time": "1:04:27", "remaining_time": "0:47:22", "throughput": 1032.96, "total_tokens": 3994592} {"current_steps": 44360, "total_steps": 76960, "loss": 0.2301, "lr": 2.270026484950273e-05, "epoch": 11.528066528066528, "percentage": 57.64, "elapsed_time": "1:04:27", "remaining_time": "0:47:22", "throughput": 1032.96, "total_tokens": 3995040} {"current_steps": 44365, "total_steps": 76960, "loss": 0.3041, "lr": 2.2694619349207523e-05, "epoch": 11.529365904365905, "percentage": 57.65, "elapsed_time": "1:04:27", "remaining_time": "0:47:21", "throughput": 1032.97, "total_tokens": 3995504} {"current_steps": 44370, "total_steps": 76960, "loss": 0.1841, "lr": 2.268897396748025e-05, "epoch": 11.53066528066528, "percentage": 57.65, "elapsed_time": "1:04:28", "remaining_time": "0:47:21", "throughput": 1032.97, "total_tokens": 3995952} {"current_steps": 44375, "total_steps": 76960, "loss": 0.2388, "lr": 2.2683328704611255e-05, "epoch": 11.531964656964657, "percentage": 57.66, "elapsed_time": "1:04:28", "remaining_time": "0:47:20", "throughput": 1032.99, "total_tokens": 3996432} {"current_steps": 44380, "total_steps": 76960, "loss": 0.2997, "lr": 2.26776835608909e-05, "epoch": 11.533264033264032, "percentage": 57.67, "elapsed_time": "1:04:29", "remaining_time": "0:47:20", "throughput": 1032.98, "total_tokens": 3996848} {"current_steps": 44385, "total_steps": 76960, "loss": 0.2617, "lr": 2.2672038536609487e-05, "epoch": 11.53456340956341, "percentage": 57.67, "elapsed_time": "1:04:29", "remaining_time": "0:47:20", "throughput": 1032.98, "total_tokens": 3997264} {"current_steps": 44390, "total_steps": 76960, "loss": 0.1499, "lr": 2.266639363205738e-05, "epoch": 11.535862785862786, "percentage": 57.68, "elapsed_time": "1:04:30", "remaining_time": "0:47:19", "throughput": 1032.99, "total_tokens": 3997744} {"current_steps": 44395, "total_steps": 76960, "loss": 0.372, "lr": 2.266074884752487e-05, "epoch": 11.537162162162161, "percentage": 57.69, "elapsed_time": "1:04:30", "remaining_time": "0:47:19", "throughput": 1033.0, "total_tokens": 3998192} {"current_steps": 44400, "total_steps": 76960, "loss": 0.4931, "lr": 2.2655104183302294e-05, "epoch": 11.538461538461538, "percentage": 57.69, "elapsed_time": "1:04:30", "remaining_time": "0:47:18", "throughput": 1032.99, "total_tokens": 3998608} {"current_steps": 44405, "total_steps": 76960, "loss": 0.1067, "lr": 2.2649459639679954e-05, "epoch": 11.539760914760915, "percentage": 57.7, "elapsed_time": "1:04:31", "remaining_time": "0:47:18", "throughput": 1033.0, "total_tokens": 3999056} {"current_steps": 44410, "total_steps": 76960, "loss": 0.2773, "lr": 2.2643815216948166e-05, "epoch": 11.54106029106029, "percentage": 57.71, "elapsed_time": "1:04:31", "remaining_time": "0:47:17", "throughput": 1033.02, "total_tokens": 3999584} {"current_steps": 44415, "total_steps": 76960, "loss": 0.2481, "lr": 2.2638170915397214e-05, "epoch": 11.542359667359667, "percentage": 57.71, "elapsed_time": "1:04:32", "remaining_time": "0:47:17", "throughput": 1033.03, "total_tokens": 4000032} {"current_steps": 44420, "total_steps": 76960, "loss": 0.2198, "lr": 2.2632526735317387e-05, "epoch": 11.543659043659044, "percentage": 57.72, "elapsed_time": "1:04:32", "remaining_time": "0:47:16", "throughput": 1033.04, "total_tokens": 4000512} {"current_steps": 44425, "total_steps": 76960, "loss": 0.3143, "lr": 2.2626882676998994e-05, "epoch": 11.54495841995842, "percentage": 57.72, "elapsed_time": "1:04:32", "remaining_time": "0:47:16", "throughput": 1033.04, "total_tokens": 4000928} {"current_steps": 44430, "total_steps": 76960, "loss": 0.165, "lr": 2.2621238740732284e-05, "epoch": 11.546257796257796, "percentage": 57.73, "elapsed_time": "1:04:33", "remaining_time": "0:47:15", "throughput": 1033.05, "total_tokens": 4001408} {"current_steps": 44435, "total_steps": 76960, "loss": 0.205, "lr": 2.261559492680755e-05, "epoch": 11.547557172557173, "percentage": 57.74, "elapsed_time": "1:04:33", "remaining_time": "0:47:15", "throughput": 1033.04, "total_tokens": 4001808} {"current_steps": 44440, "total_steps": 76960, "loss": 0.3714, "lr": 2.260995123551505e-05, "epoch": 11.548856548856548, "percentage": 57.74, "elapsed_time": "1:04:34", "remaining_time": "0:47:15", "throughput": 1033.06, "total_tokens": 4002288} {"current_steps": 44445, "total_steps": 76960, "loss": 0.3401, "lr": 2.260430766714506e-05, "epoch": 11.550155925155925, "percentage": 57.75, "elapsed_time": "1:04:34", "remaining_time": "0:47:14", "throughput": 1033.06, "total_tokens": 4002736} {"current_steps": 44450, "total_steps": 76960, "loss": 0.2461, "lr": 2.259866422198781e-05, "epoch": 11.551455301455302, "percentage": 57.76, "elapsed_time": "1:04:35", "remaining_time": "0:47:14", "throughput": 1033.06, "total_tokens": 4003152} {"current_steps": 44455, "total_steps": 76960, "loss": 0.1652, "lr": 2.2593020900333563e-05, "epoch": 11.552754677754677, "percentage": 57.76, "elapsed_time": "1:04:35", "remaining_time": "0:47:13", "throughput": 1033.05, "total_tokens": 4003568} {"current_steps": 44460, "total_steps": 76960, "loss": 0.3002, "lr": 2.2587377702472555e-05, "epoch": 11.554054054054054, "percentage": 57.77, "elapsed_time": "1:04:35", "remaining_time": "0:47:13", "throughput": 1033.06, "total_tokens": 4004016} {"current_steps": 44465, "total_steps": 76960, "loss": 0.1413, "lr": 2.2581734628695034e-05, "epoch": 11.55535343035343, "percentage": 57.78, "elapsed_time": "1:04:36", "remaining_time": "0:47:12", "throughput": 1033.05, "total_tokens": 4004432} {"current_steps": 44470, "total_steps": 76960, "loss": 0.2393, "lr": 2.2576091679291205e-05, "epoch": 11.556652806652806, "percentage": 57.78, "elapsed_time": "1:04:36", "remaining_time": "0:47:12", "throughput": 1033.06, "total_tokens": 4004880} {"current_steps": 44475, "total_steps": 76960, "loss": 0.4497, "lr": 2.257044885455131e-05, "epoch": 11.557952182952183, "percentage": 57.79, "elapsed_time": "1:04:37", "remaining_time": "0:47:11", "throughput": 1033.06, "total_tokens": 4005328} {"current_steps": 44480, "total_steps": 76960, "loss": 0.1676, "lr": 2.2564806154765565e-05, "epoch": 11.559251559251559, "percentage": 57.8, "elapsed_time": "1:04:37", "remaining_time": "0:47:11", "throughput": 1033.07, "total_tokens": 4005776} {"current_steps": 44485, "total_steps": 76960, "loss": 0.1363, "lr": 2.2559163580224163e-05, "epoch": 11.560550935550935, "percentage": 57.8, "elapsed_time": "1:04:37", "remaining_time": "0:47:11", "throughput": 1033.06, "total_tokens": 4006192} {"current_steps": 44490, "total_steps": 76960, "loss": 0.3314, "lr": 2.255352113121732e-05, "epoch": 11.561850311850312, "percentage": 57.81, "elapsed_time": "1:04:38", "remaining_time": "0:47:10", "throughput": 1033.07, "total_tokens": 4006640} {"current_steps": 44495, "total_steps": 76960, "loss": 0.0838, "lr": 2.2547878808035223e-05, "epoch": 11.563149688149688, "percentage": 57.82, "elapsed_time": "1:04:38", "remaining_time": "0:47:10", "throughput": 1033.08, "total_tokens": 4007120} {"current_steps": 44500, "total_steps": 76960, "loss": 0.044, "lr": 2.254223661096808e-05, "epoch": 11.564449064449065, "percentage": 57.82, "elapsed_time": "1:04:39", "remaining_time": "0:47:09", "throughput": 1033.08, "total_tokens": 4007552} {"current_steps": 44505, "total_steps": 76960, "loss": 0.3941, "lr": 2.253659454030605e-05, "epoch": 11.565748440748441, "percentage": 57.83, "elapsed_time": "1:04:39", "remaining_time": "0:47:09", "throughput": 1033.08, "total_tokens": 4007984} {"current_steps": 44510, "total_steps": 76960, "loss": 0.2514, "lr": 2.2530952596339334e-05, "epoch": 11.567047817047817, "percentage": 57.84, "elapsed_time": "1:04:40", "remaining_time": "0:47:08", "throughput": 1033.1, "total_tokens": 4008464} {"current_steps": 44515, "total_steps": 76960, "loss": 0.3421, "lr": 2.2525310779358084e-05, "epoch": 11.568347193347194, "percentage": 57.84, "elapsed_time": "1:04:40", "remaining_time": "0:47:08", "throughput": 1033.1, "total_tokens": 4008928} {"current_steps": 44520, "total_steps": 76960, "loss": 0.2899, "lr": 2.251966908965248e-05, "epoch": 11.56964656964657, "percentage": 57.85, "elapsed_time": "1:04:40", "remaining_time": "0:47:07", "throughput": 1033.11, "total_tokens": 4009376} {"current_steps": 44525, "total_steps": 76960, "loss": 0.279, "lr": 2.2514027527512664e-05, "epoch": 11.570945945945946, "percentage": 57.85, "elapsed_time": "1:04:41", "remaining_time": "0:47:07", "throughput": 1033.12, "total_tokens": 4009840} {"current_steps": 44530, "total_steps": 76960, "loss": 0.2884, "lr": 2.2508386093228798e-05, "epoch": 11.572245322245323, "percentage": 57.86, "elapsed_time": "1:04:41", "remaining_time": "0:47:06", "throughput": 1033.11, "total_tokens": 4010256} {"current_steps": 44535, "total_steps": 76960, "loss": 0.2967, "lr": 2.2502744787091015e-05, "epoch": 11.573544698544698, "percentage": 57.87, "elapsed_time": "1:04:42", "remaining_time": "0:47:06", "throughput": 1033.11, "total_tokens": 4010688} {"current_steps": 44540, "total_steps": 76960, "loss": 0.1278, "lr": 2.2497103609389475e-05, "epoch": 11.574844074844075, "percentage": 57.87, "elapsed_time": "1:04:42", "remaining_time": "0:47:06", "throughput": 1033.13, "total_tokens": 4011168} {"current_steps": 44545, "total_steps": 76960, "loss": 0.2428, "lr": 2.2491462560414287e-05, "epoch": 11.576143451143452, "percentage": 57.88, "elapsed_time": "1:04:42", "remaining_time": "0:47:05", "throughput": 1033.14, "total_tokens": 4011632} {"current_steps": 44550, "total_steps": 76960, "loss": 0.2401, "lr": 2.248582164045558e-05, "epoch": 11.577442827442827, "percentage": 57.89, "elapsed_time": "1:04:43", "remaining_time": "0:47:05", "throughput": 1033.14, "total_tokens": 4012080} {"current_steps": 44555, "total_steps": 76960, "loss": 0.2447, "lr": 2.248018084980348e-05, "epoch": 11.578742203742204, "percentage": 57.89, "elapsed_time": "1:04:43", "remaining_time": "0:47:04", "throughput": 1033.14, "total_tokens": 4012528} {"current_steps": 44560, "total_steps": 76960, "loss": 0.2539, "lr": 2.2474540188748088e-05, "epoch": 11.58004158004158, "percentage": 57.9, "elapsed_time": "1:04:44", "remaining_time": "0:47:04", "throughput": 1033.16, "total_tokens": 4013008} {"current_steps": 44565, "total_steps": 76960, "loss": 0.1814, "lr": 2.246889965757952e-05, "epoch": 11.581340956340956, "percentage": 57.91, "elapsed_time": "1:04:44", "remaining_time": "0:47:03", "throughput": 1033.16, "total_tokens": 4013456} {"current_steps": 44570, "total_steps": 76960, "loss": 0.1894, "lr": 2.2463259256587855e-05, "epoch": 11.582640332640333, "percentage": 57.91, "elapsed_time": "1:04:45", "remaining_time": "0:47:03", "throughput": 1033.18, "total_tokens": 4013952} {"current_steps": 44575, "total_steps": 76960, "loss": 0.166, "lr": 2.2457618986063217e-05, "epoch": 11.58393970893971, "percentage": 57.92, "elapsed_time": "1:04:45", "remaining_time": "0:47:02", "throughput": 1033.18, "total_tokens": 4014400} {"current_steps": 44580, "total_steps": 76960, "loss": 0.0633, "lr": 2.2451978846295654e-05, "epoch": 11.585239085239085, "percentage": 57.93, "elapsed_time": "1:04:45", "remaining_time": "0:47:02", "throughput": 1033.19, "total_tokens": 4014848} {"current_steps": 44585, "total_steps": 76960, "loss": 0.2199, "lr": 2.2446338837575268e-05, "epoch": 11.586538461538462, "percentage": 57.93, "elapsed_time": "1:04:46", "remaining_time": "0:47:02", "throughput": 1033.19, "total_tokens": 4015296} {"current_steps": 44590, "total_steps": 76960, "loss": 0.0986, "lr": 2.2440698960192115e-05, "epoch": 11.587837837837839, "percentage": 57.94, "elapsed_time": "1:04:46", "remaining_time": "0:47:01", "throughput": 1033.2, "total_tokens": 4015760} {"current_steps": 44595, "total_steps": 76960, "loss": 0.0912, "lr": 2.243505921443628e-05, "epoch": 11.589137214137214, "percentage": 57.95, "elapsed_time": "1:04:47", "remaining_time": "0:47:01", "throughput": 1033.2, "total_tokens": 4016208} {"current_steps": 44600, "total_steps": 76960, "loss": 0.1504, "lr": 2.2429419600597796e-05, "epoch": 11.59043659043659, "percentage": 57.95, "elapsed_time": "1:04:47", "remaining_time": "0:47:00", "throughput": 1033.21, "total_tokens": 4016672} {"current_steps": 44605, "total_steps": 76960, "loss": 0.4012, "lr": 2.242378011896673e-05, "epoch": 11.591735966735968, "percentage": 57.96, "elapsed_time": "1:04:47", "remaining_time": "0:47:00", "throughput": 1033.23, "total_tokens": 4017152} {"current_steps": 44610, "total_steps": 76960, "loss": 0.2061, "lr": 2.2418140769833125e-05, "epoch": 11.593035343035343, "percentage": 57.97, "elapsed_time": "1:04:48", "remaining_time": "0:46:59", "throughput": 1033.23, "total_tokens": 4017600} {"current_steps": 44615, "total_steps": 76960, "loss": 0.6149, "lr": 2.2412501553487003e-05, "epoch": 11.59433471933472, "percentage": 57.97, "elapsed_time": "1:04:48", "remaining_time": "0:46:59", "throughput": 1033.24, "total_tokens": 4018048} {"current_steps": 44620, "total_steps": 76960, "loss": 0.2238, "lr": 2.240686247021841e-05, "epoch": 11.595634095634095, "percentage": 57.98, "elapsed_time": "1:04:49", "remaining_time": "0:46:58", "throughput": 1033.24, "total_tokens": 4018512} {"current_steps": 44625, "total_steps": 76960, "loss": 0.3365, "lr": 2.2401223520317362e-05, "epoch": 11.596933471933472, "percentage": 57.98, "elapsed_time": "1:04:49", "remaining_time": "0:46:58", "throughput": 1033.25, "total_tokens": 4018976} {"current_steps": 44630, "total_steps": 76960, "loss": 0.291, "lr": 2.239558470407389e-05, "epoch": 11.598232848232849, "percentage": 57.99, "elapsed_time": "1:04:50", "remaining_time": "0:46:57", "throughput": 1033.25, "total_tokens": 4019392} {"current_steps": 44635, "total_steps": 76960, "loss": 0.1027, "lr": 2.2389946021777976e-05, "epoch": 11.599532224532224, "percentage": 58.0, "elapsed_time": "1:04:50", "remaining_time": "0:46:57", "throughput": 1033.25, "total_tokens": 4019840} {"current_steps": 44640, "total_steps": 76960, "loss": 0.1914, "lr": 2.238430747371965e-05, "epoch": 11.6008316008316, "percentage": 58.0, "elapsed_time": "1:04:50", "remaining_time": "0:46:57", "throughput": 1033.25, "total_tokens": 4020256} {"current_steps": 44645, "total_steps": 76960, "loss": 0.2519, "lr": 2.237866906018889e-05, "epoch": 11.602130977130978, "percentage": 58.01, "elapsed_time": "1:04:51", "remaining_time": "0:46:56", "throughput": 1033.25, "total_tokens": 4020672} {"current_steps": 44650, "total_steps": 76960, "loss": 0.1248, "lr": 2.2373030781475697e-05, "epoch": 11.603430353430353, "percentage": 58.02, "elapsed_time": "1:04:51", "remaining_time": "0:46:56", "throughput": 1033.25, "total_tokens": 4021120} {"current_steps": 44655, "total_steps": 76960, "loss": 0.1908, "lr": 2.236739263787004e-05, "epoch": 11.60472972972973, "percentage": 58.02, "elapsed_time": "1:04:52", "remaining_time": "0:46:55", "throughput": 1033.26, "total_tokens": 4021584} {"current_steps": 44660, "total_steps": 76960, "loss": 0.2101, "lr": 2.236175462966192e-05, "epoch": 11.606029106029107, "percentage": 58.03, "elapsed_time": "1:04:52", "remaining_time": "0:46:55", "throughput": 1033.27, "total_tokens": 4022048} {"current_steps": 44665, "total_steps": 76960, "loss": 0.1125, "lr": 2.235611675714127e-05, "epoch": 11.607328482328482, "percentage": 58.04, "elapsed_time": "1:04:52", "remaining_time": "0:46:54", "throughput": 1033.27, "total_tokens": 4022496} {"current_steps": 44670, "total_steps": 76960, "loss": 0.4746, "lr": 2.2350479020598074e-05, "epoch": 11.608627858627859, "percentage": 58.04, "elapsed_time": "1:04:53", "remaining_time": "0:46:54", "throughput": 1033.29, "total_tokens": 4022976} {"current_steps": 44675, "total_steps": 76960, "loss": 0.1423, "lr": 2.2344841420322287e-05, "epoch": 11.609927234927234, "percentage": 58.05, "elapsed_time": "1:04:53", "remaining_time": "0:46:53", "throughput": 1033.29, "total_tokens": 4023424} {"current_steps": 44680, "total_steps": 76960, "loss": 0.5336, "lr": 2.233920395660384e-05, "epoch": 11.611226611226611, "percentage": 58.06, "elapsed_time": "1:04:54", "remaining_time": "0:46:53", "throughput": 1033.29, "total_tokens": 4023872} {"current_steps": 44685, "total_steps": 76960, "loss": 0.0456, "lr": 2.233356662973269e-05, "epoch": 11.612525987525988, "percentage": 58.06, "elapsed_time": "1:04:54", "remaining_time": "0:46:53", "throughput": 1033.31, "total_tokens": 4024352} {"current_steps": 44690, "total_steps": 76960, "loss": 0.2499, "lr": 2.2327929439998755e-05, "epoch": 11.613825363825363, "percentage": 58.07, "elapsed_time": "1:04:55", "remaining_time": "0:46:52", "throughput": 1033.31, "total_tokens": 4024800} {"current_steps": 44695, "total_steps": 76960, "loss": 0.1788, "lr": 2.232229238769198e-05, "epoch": 11.61512474012474, "percentage": 58.08, "elapsed_time": "1:04:55", "remaining_time": "0:46:52", "throughput": 1033.32, "total_tokens": 4025248} {"current_steps": 44700, "total_steps": 76960, "loss": 0.1701, "lr": 2.231665547310226e-05, "epoch": 11.616424116424117, "percentage": 58.08, "elapsed_time": "1:04:55", "remaining_time": "0:46:51", "throughput": 1033.32, "total_tokens": 4025696} {"current_steps": 44705, "total_steps": 76960, "loss": 0.2032, "lr": 2.2311018696519532e-05, "epoch": 11.617723492723492, "percentage": 58.09, "elapsed_time": "1:04:56", "remaining_time": "0:46:51", "throughput": 1033.32, "total_tokens": 4026128} {"current_steps": 44710, "total_steps": 76960, "loss": 0.3947, "lr": 2.230538205823368e-05, "epoch": 11.619022869022869, "percentage": 58.1, "elapsed_time": "1:04:56", "remaining_time": "0:46:50", "throughput": 1033.33, "total_tokens": 4026576} {"current_steps": 44715, "total_steps": 76960, "loss": 0.2482, "lr": 2.229974555853462e-05, "epoch": 11.620322245322246, "percentage": 58.1, "elapsed_time": "1:04:57", "remaining_time": "0:46:50", "throughput": 1033.33, "total_tokens": 4027008} {"current_steps": 44720, "total_steps": 76960, "loss": 0.4792, "lr": 2.2294109197712223e-05, "epoch": 11.621621621621621, "percentage": 58.11, "elapsed_time": "1:04:57", "remaining_time": "0:46:49", "throughput": 1033.34, "total_tokens": 4027504} {"current_steps": 44725, "total_steps": 76960, "loss": 0.2783, "lr": 2.228847297605639e-05, "epoch": 11.622920997920998, "percentage": 58.11, "elapsed_time": "1:04:57", "remaining_time": "0:46:49", "throughput": 1033.34, "total_tokens": 4027936} {"current_steps": 44730, "total_steps": 76960, "loss": 0.2243, "lr": 2.228283689385698e-05, "epoch": 11.624220374220375, "percentage": 58.12, "elapsed_time": "1:04:58", "remaining_time": "0:46:48", "throughput": 1033.35, "total_tokens": 4028384} {"current_steps": 44735, "total_steps": 76960, "loss": 0.3171, "lr": 2.2277200951403887e-05, "epoch": 11.62551975051975, "percentage": 58.13, "elapsed_time": "1:04:58", "remaining_time": "0:46:48", "throughput": 1033.36, "total_tokens": 4028864} {"current_steps": 44740, "total_steps": 76960, "loss": 0.3205, "lr": 2.227156514898695e-05, "epoch": 11.626819126819127, "percentage": 58.13, "elapsed_time": "1:04:59", "remaining_time": "0:46:48", "throughput": 1033.38, "total_tokens": 4029360} {"current_steps": 44745, "total_steps": 76960, "loss": 0.408, "lr": 2.2265929486896028e-05, "epoch": 11.628118503118504, "percentage": 58.14, "elapsed_time": "1:04:59", "remaining_time": "0:46:47", "throughput": 1033.38, "total_tokens": 4029808} {"current_steps": 44750, "total_steps": 76960, "loss": 0.4869, "lr": 2.2260293965420982e-05, "epoch": 11.629417879417879, "percentage": 58.15, "elapsed_time": "1:05:00", "remaining_time": "0:46:47", "throughput": 1033.38, "total_tokens": 4030224} {"current_steps": 44755, "total_steps": 76960, "loss": 0.0311, "lr": 2.2254658584851633e-05, "epoch": 11.630717255717256, "percentage": 58.15, "elapsed_time": "1:05:00", "remaining_time": "0:46:46", "throughput": 1033.39, "total_tokens": 4030688} {"current_steps": 44760, "total_steps": 76960, "loss": 0.4247, "lr": 2.224902334547783e-05, "epoch": 11.632016632016633, "percentage": 58.16, "elapsed_time": "1:05:00", "remaining_time": "0:46:46", "throughput": 1033.39, "total_tokens": 4031152} {"current_steps": 44765, "total_steps": 76960, "loss": 0.232, "lr": 2.2243388247589382e-05, "epoch": 11.633316008316008, "percentage": 58.17, "elapsed_time": "1:05:01", "remaining_time": "0:46:45", "throughput": 1033.4, "total_tokens": 4031600} {"current_steps": 44770, "total_steps": 76960, "loss": 0.3151, "lr": 2.2237753291476133e-05, "epoch": 11.634615384615385, "percentage": 58.17, "elapsed_time": "1:05:01", "remaining_time": "0:46:45", "throughput": 1033.41, "total_tokens": 4032080} {"current_steps": 44775, "total_steps": 76960, "loss": 0.1533, "lr": 2.2232118477427867e-05, "epoch": 11.63591476091476, "percentage": 58.18, "elapsed_time": "1:05:02", "remaining_time": "0:46:44", "throughput": 1033.42, "total_tokens": 4032528} {"current_steps": 44780, "total_steps": 76960, "loss": 0.283, "lr": 2.2226483805734404e-05, "epoch": 11.637214137214137, "percentage": 58.19, "elapsed_time": "1:05:02", "remaining_time": "0:46:44", "throughput": 1033.42, "total_tokens": 4032960} {"current_steps": 44785, "total_steps": 76960, "loss": 0.5956, "lr": 2.222084927668553e-05, "epoch": 11.638513513513514, "percentage": 58.19, "elapsed_time": "1:05:02", "remaining_time": "0:46:44", "throughput": 1033.43, "total_tokens": 4033424} {"current_steps": 44790, "total_steps": 76960, "loss": 0.3115, "lr": 2.2215214890571053e-05, "epoch": 11.63981288981289, "percentage": 58.2, "elapsed_time": "1:05:03", "remaining_time": "0:46:43", "throughput": 1033.43, "total_tokens": 4033872} {"current_steps": 44795, "total_steps": 76960, "loss": 0.1251, "lr": 2.2209580647680735e-05, "epoch": 11.641112266112266, "percentage": 58.21, "elapsed_time": "1:05:03", "remaining_time": "0:46:43", "throughput": 1033.46, "total_tokens": 4034400} {"current_steps": 44800, "total_steps": 76960, "loss": 0.1681, "lr": 2.2203946548304358e-05, "epoch": 11.642411642411643, "percentage": 58.21, "elapsed_time": "1:05:04", "remaining_time": "0:46:42", "throughput": 1033.46, "total_tokens": 4034848} {"current_steps": 44805, "total_steps": 76960, "loss": 0.3774, "lr": 2.2198312592731695e-05, "epoch": 11.643711018711018, "percentage": 58.22, "elapsed_time": "1:05:04", "remaining_time": "0:46:42", "throughput": 1033.47, "total_tokens": 4035312} {"current_steps": 44810, "total_steps": 76960, "loss": 0.1436, "lr": 2.2192678781252492e-05, "epoch": 11.645010395010395, "percentage": 58.23, "elapsed_time": "1:05:05", "remaining_time": "0:46:41", "throughput": 1033.47, "total_tokens": 4035760} {"current_steps": 44815, "total_steps": 76960, "loss": 0.2097, "lr": 2.2187045114156513e-05, "epoch": 11.646309771309772, "percentage": 58.23, "elapsed_time": "1:05:05", "remaining_time": "0:46:41", "throughput": 1033.48, "total_tokens": 4036208} {"current_steps": 44820, "total_steps": 76960, "loss": 0.0979, "lr": 2.218141159173349e-05, "epoch": 11.647609147609147, "percentage": 58.24, "elapsed_time": "1:05:05", "remaining_time": "0:46:40", "throughput": 1033.48, "total_tokens": 4036640} {"current_steps": 44825, "total_steps": 76960, "loss": 0.4602, "lr": 2.2175778214273185e-05, "epoch": 11.648908523908524, "percentage": 58.24, "elapsed_time": "1:05:06", "remaining_time": "0:46:40", "throughput": 1033.48, "total_tokens": 4037072} {"current_steps": 44830, "total_steps": 76960, "loss": 0.2324, "lr": 2.2170144982065303e-05, "epoch": 11.6502079002079, "percentage": 58.25, "elapsed_time": "1:05:06", "remaining_time": "0:46:39", "throughput": 1033.48, "total_tokens": 4037520} {"current_steps": 44835, "total_steps": 76960, "loss": 0.1828, "lr": 2.216451189539958e-05, "epoch": 11.651507276507276, "percentage": 58.26, "elapsed_time": "1:05:07", "remaining_time": "0:46:39", "throughput": 1033.48, "total_tokens": 4037952} {"current_steps": 44840, "total_steps": 76960, "loss": 0.1535, "lr": 2.2158878954565717e-05, "epoch": 11.652806652806653, "percentage": 58.26, "elapsed_time": "1:05:07", "remaining_time": "0:46:39", "throughput": 1033.49, "total_tokens": 4038432} {"current_steps": 44845, "total_steps": 76960, "loss": 0.0254, "lr": 2.2153246159853446e-05, "epoch": 11.654106029106028, "percentage": 58.27, "elapsed_time": "1:05:07", "remaining_time": "0:46:38", "throughput": 1033.49, "total_tokens": 4038832} {"current_steps": 44850, "total_steps": 76960, "loss": 0.1318, "lr": 2.2147613511552443e-05, "epoch": 11.655405405405405, "percentage": 58.28, "elapsed_time": "1:05:08", "remaining_time": "0:46:38", "throughput": 1033.49, "total_tokens": 4039264} {"current_steps": 44855, "total_steps": 76960, "loss": 0.0117, "lr": 2.2141981009952414e-05, "epoch": 11.656704781704782, "percentage": 58.28, "elapsed_time": "1:05:08", "remaining_time": "0:46:37", "throughput": 1033.48, "total_tokens": 4039680} {"current_steps": 44860, "total_steps": 76960, "loss": 0.4031, "lr": 2.2136348655343033e-05, "epoch": 11.658004158004157, "percentage": 58.29, "elapsed_time": "1:05:09", "remaining_time": "0:46:37", "throughput": 1033.49, "total_tokens": 4040128} {"current_steps": 44865, "total_steps": 76960, "loss": 0.2123, "lr": 2.2130716448014e-05, "epoch": 11.659303534303534, "percentage": 58.3, "elapsed_time": "1:05:09", "remaining_time": "0:46:36", "throughput": 1033.5, "total_tokens": 4040592} {"current_steps": 44870, "total_steps": 76960, "loss": 0.4567, "lr": 2.2125084388254962e-05, "epoch": 11.660602910602911, "percentage": 58.3, "elapsed_time": "1:05:10", "remaining_time": "0:46:36", "throughput": 1033.5, "total_tokens": 4041040} {"current_steps": 44875, "total_steps": 76960, "loss": 0.6216, "lr": 2.2119452476355577e-05, "epoch": 11.661902286902286, "percentage": 58.31, "elapsed_time": "1:05:10", "remaining_time": "0:46:35", "throughput": 1033.52, "total_tokens": 4041552} {"current_steps": 44880, "total_steps": 76960, "loss": 0.0139, "lr": 2.211382071260553e-05, "epoch": 11.663201663201663, "percentage": 58.32, "elapsed_time": "1:05:10", "remaining_time": "0:46:35", "throughput": 1033.53, "total_tokens": 4042000} {"current_steps": 44885, "total_steps": 76960, "loss": 0.1692, "lr": 2.210818909729443e-05, "epoch": 11.66450103950104, "percentage": 58.32, "elapsed_time": "1:05:11", "remaining_time": "0:46:35", "throughput": 1033.53, "total_tokens": 4042464} {"current_steps": 44890, "total_steps": 76960, "loss": 0.1553, "lr": 2.210255763071195e-05, "epoch": 11.665800415800415, "percentage": 58.33, "elapsed_time": "1:05:11", "remaining_time": "0:46:34", "throughput": 1033.54, "total_tokens": 4042912} {"current_steps": 44895, "total_steps": 76960, "loss": 0.4951, "lr": 2.20969263131477e-05, "epoch": 11.667099792099792, "percentage": 58.34, "elapsed_time": "1:05:12", "remaining_time": "0:46:34", "throughput": 1033.55, "total_tokens": 4043376} {"current_steps": 44900, "total_steps": 76960, "loss": 0.5766, "lr": 2.2091295144891317e-05, "epoch": 11.66839916839917, "percentage": 58.34, "elapsed_time": "1:05:12", "remaining_time": "0:46:33", "throughput": 1033.56, "total_tokens": 4043840} {"current_steps": 44905, "total_steps": 76960, "loss": 0.5207, "lr": 2.20856641262324e-05, "epoch": 11.669698544698544, "percentage": 58.35, "elapsed_time": "1:05:12", "remaining_time": "0:46:33", "throughput": 1033.56, "total_tokens": 4044288} {"current_steps": 44910, "total_steps": 76960, "loss": 0.3373, "lr": 2.2080033257460586e-05, "epoch": 11.670997920997921, "percentage": 58.35, "elapsed_time": "1:05:13", "remaining_time": "0:46:32", "throughput": 1033.56, "total_tokens": 4044736} {"current_steps": 44915, "total_steps": 76960, "loss": 0.1575, "lr": 2.207440253886545e-05, "epoch": 11.672297297297296, "percentage": 58.36, "elapsed_time": "1:05:13", "remaining_time": "0:46:32", "throughput": 1033.58, "total_tokens": 4045216} {"current_steps": 44920, "total_steps": 76960, "loss": 0.4291, "lr": 2.2068771970736595e-05, "epoch": 11.673596673596673, "percentage": 58.37, "elapsed_time": "1:05:14", "remaining_time": "0:46:31", "throughput": 1033.58, "total_tokens": 4045648} {"current_steps": 44925, "total_steps": 76960, "loss": 0.2977, "lr": 2.2063141553363603e-05, "epoch": 11.67489604989605, "percentage": 58.37, "elapsed_time": "1:05:14", "remaining_time": "0:46:31", "throughput": 1033.59, "total_tokens": 4046128} {"current_steps": 44930, "total_steps": 76960, "loss": 0.2553, "lr": 2.2057511287036064e-05, "epoch": 11.676195426195425, "percentage": 58.38, "elapsed_time": "1:05:15", "remaining_time": "0:46:30", "throughput": 1033.59, "total_tokens": 4046576} {"current_steps": 44935, "total_steps": 76960, "loss": 0.2458, "lr": 2.2051881172043538e-05, "epoch": 11.677494802494802, "percentage": 58.39, "elapsed_time": "1:05:15", "remaining_time": "0:46:30", "throughput": 1033.61, "total_tokens": 4047072} {"current_steps": 44940, "total_steps": 76960, "loss": 0.3264, "lr": 2.2046251208675578e-05, "epoch": 11.67879417879418, "percentage": 58.39, "elapsed_time": "1:05:15", "remaining_time": "0:46:30", "throughput": 1033.61, "total_tokens": 4047520} {"current_steps": 44945, "total_steps": 76960, "loss": 0.2351, "lr": 2.204062139722176e-05, "epoch": 11.680093555093555, "percentage": 58.4, "elapsed_time": "1:05:16", "remaining_time": "0:46:29", "throughput": 1033.62, "total_tokens": 4047968} {"current_steps": 44950, "total_steps": 76960, "loss": 0.1597, "lr": 2.2034991737971608e-05, "epoch": 11.681392931392931, "percentage": 58.41, "elapsed_time": "1:05:16", "remaining_time": "0:46:29", "throughput": 1033.63, "total_tokens": 4048448} {"current_steps": 44955, "total_steps": 76960, "loss": 0.1676, "lr": 2.2029362231214677e-05, "epoch": 11.682692307692308, "percentage": 58.41, "elapsed_time": "1:05:17", "remaining_time": "0:46:28", "throughput": 1033.65, "total_tokens": 4048944} {"current_steps": 44960, "total_steps": 76960, "loss": 0.2836, "lr": 2.202373287724049e-05, "epoch": 11.683991683991684, "percentage": 58.42, "elapsed_time": "1:05:17", "remaining_time": "0:46:28", "throughput": 1033.65, "total_tokens": 4049392} {"current_steps": 44965, "total_steps": 76960, "loss": 0.3198, "lr": 2.2018103676338583e-05, "epoch": 11.68529106029106, "percentage": 58.43, "elapsed_time": "1:05:17", "remaining_time": "0:46:27", "throughput": 1033.66, "total_tokens": 4049840} {"current_steps": 44970, "total_steps": 76960, "loss": 0.1019, "lr": 2.2012474628798448e-05, "epoch": 11.686590436590437, "percentage": 58.43, "elapsed_time": "1:05:18", "remaining_time": "0:46:27", "throughput": 1033.67, "total_tokens": 4050304} {"current_steps": 44975, "total_steps": 76960, "loss": 0.3557, "lr": 2.2006845734909614e-05, "epoch": 11.687889812889813, "percentage": 58.44, "elapsed_time": "1:05:18", "remaining_time": "0:46:26", "throughput": 1033.67, "total_tokens": 4050736} {"current_steps": 44980, "total_steps": 76960, "loss": 0.3721, "lr": 2.2001216994961565e-05, "epoch": 11.68918918918919, "percentage": 58.45, "elapsed_time": "1:05:19", "remaining_time": "0:46:26", "throughput": 1033.67, "total_tokens": 4051184} {"current_steps": 44985, "total_steps": 76960, "loss": 0.2975, "lr": 2.199558840924381e-05, "epoch": 11.690488565488565, "percentage": 58.45, "elapsed_time": "1:05:19", "remaining_time": "0:46:26", "throughput": 1033.68, "total_tokens": 4051632} {"current_steps": 44990, "total_steps": 76960, "loss": 0.2828, "lr": 2.198995997804581e-05, "epoch": 11.691787941787942, "percentage": 58.46, "elapsed_time": "1:05:20", "remaining_time": "0:46:25", "throughput": 1033.68, "total_tokens": 4052096} {"current_steps": 44995, "total_steps": 76960, "loss": 0.3265, "lr": 2.198433170165706e-05, "epoch": 11.693087318087318, "percentage": 58.47, "elapsed_time": "1:05:20", "remaining_time": "0:46:25", "throughput": 1033.68, "total_tokens": 4052512} {"current_steps": 45000, "total_steps": 76960, "loss": 0.2421, "lr": 2.1978703580367024e-05, "epoch": 11.694386694386694, "percentage": 58.47, "elapsed_time": "1:05:20", "remaining_time": "0:46:24", "throughput": 1033.68, "total_tokens": 4052928} {"current_steps": 45005, "total_steps": 76960, "loss": 0.292, "lr": 2.1973075614465147e-05, "epoch": 11.69568607068607, "percentage": 58.48, "elapsed_time": "1:05:21", "remaining_time": "0:46:24", "throughput": 1033.67, "total_tokens": 4053344} {"current_steps": 45010, "total_steps": 76960, "loss": 0.1408, "lr": 2.1967447804240895e-05, "epoch": 11.696985446985448, "percentage": 58.48, "elapsed_time": "1:05:21", "remaining_time": "0:46:23", "throughput": 1033.68, "total_tokens": 4053808} {"current_steps": 45015, "total_steps": 76960, "loss": 0.1452, "lr": 2.1961820149983706e-05, "epoch": 11.698284823284823, "percentage": 58.49, "elapsed_time": "1:05:22", "remaining_time": "0:46:23", "throughput": 1033.68, "total_tokens": 4054240} {"current_steps": 45020, "total_steps": 76960, "loss": 0.1831, "lr": 2.1956192651983028e-05, "epoch": 11.6995841995842, "percentage": 58.5, "elapsed_time": "1:05:22", "remaining_time": "0:46:22", "throughput": 1033.69, "total_tokens": 4054688} {"current_steps": 45025, "total_steps": 76960, "loss": 0.1378, "lr": 2.1950565310528266e-05, "epoch": 11.700883575883577, "percentage": 58.5, "elapsed_time": "1:05:22", "remaining_time": "0:46:22", "throughput": 1033.68, "total_tokens": 4055104} {"current_steps": 45030, "total_steps": 76960, "loss": 0.2168, "lr": 2.1944938125908857e-05, "epoch": 11.702182952182952, "percentage": 58.51, "elapsed_time": "1:05:23", "remaining_time": "0:46:22", "throughput": 1033.7, "total_tokens": 4055600} {"current_steps": 45035, "total_steps": 76960, "loss": 0.2259, "lr": 2.1939311098414202e-05, "epoch": 11.703482328482329, "percentage": 58.52, "elapsed_time": "1:05:23", "remaining_time": "0:46:21", "throughput": 1033.72, "total_tokens": 4056096} {"current_steps": 45040, "total_steps": 76960, "loss": 0.2292, "lr": 2.1933684228333722e-05, "epoch": 11.704781704781706, "percentage": 58.52, "elapsed_time": "1:05:24", "remaining_time": "0:46:21", "throughput": 1033.71, "total_tokens": 4056496} {"current_steps": 45045, "total_steps": 76960, "loss": 0.2139, "lr": 2.1928057515956788e-05, "epoch": 11.70608108108108, "percentage": 58.53, "elapsed_time": "1:05:24", "remaining_time": "0:46:20", "throughput": 1033.71, "total_tokens": 4056944} {"current_steps": 45050, "total_steps": 76960, "loss": 0.3119, "lr": 2.1922430961572806e-05, "epoch": 11.707380457380458, "percentage": 58.54, "elapsed_time": "1:05:25", "remaining_time": "0:46:20", "throughput": 1033.72, "total_tokens": 4057408} {"current_steps": 45055, "total_steps": 76960, "loss": 0.1379, "lr": 2.1916804565471143e-05, "epoch": 11.708679833679835, "percentage": 58.54, "elapsed_time": "1:05:25", "remaining_time": "0:46:19", "throughput": 1033.72, "total_tokens": 4057824} {"current_steps": 45060, "total_steps": 76960, "loss": 0.5591, "lr": 2.1911178327941183e-05, "epoch": 11.70997920997921, "percentage": 58.55, "elapsed_time": "1:05:25", "remaining_time": "0:46:19", "throughput": 1033.72, "total_tokens": 4058256} {"current_steps": 45065, "total_steps": 76960, "loss": 0.2286, "lr": 2.1905552249272284e-05, "epoch": 11.711278586278587, "percentage": 58.56, "elapsed_time": "1:05:26", "remaining_time": "0:46:18", "throughput": 1033.72, "total_tokens": 4058688} {"current_steps": 45070, "total_steps": 76960, "loss": 0.2896, "lr": 2.1899926329753783e-05, "epoch": 11.712577962577962, "percentage": 58.56, "elapsed_time": "1:05:26", "remaining_time": "0:46:18", "throughput": 1033.72, "total_tokens": 4059120} {"current_steps": 45075, "total_steps": 76960, "loss": 0.2157, "lr": 2.1894300569675056e-05, "epoch": 11.713877338877339, "percentage": 58.57, "elapsed_time": "1:05:27", "remaining_time": "0:46:17", "throughput": 1033.72, "total_tokens": 4059568} {"current_steps": 45080, "total_steps": 76960, "loss": 0.2154, "lr": 2.1888674969325414e-05, "epoch": 11.715176715176716, "percentage": 58.58, "elapsed_time": "1:05:27", "remaining_time": "0:46:17", "throughput": 1033.72, "total_tokens": 4060000} {"current_steps": 45085, "total_steps": 76960, "loss": 0.5, "lr": 2.1883049528994208e-05, "epoch": 11.71647609147609, "percentage": 58.58, "elapsed_time": "1:05:27", "remaining_time": "0:46:17", "throughput": 1033.73, "total_tokens": 4060448} {"current_steps": 45090, "total_steps": 76960, "loss": 0.2524, "lr": 2.1877424248970743e-05, "epoch": 11.717775467775468, "percentage": 58.59, "elapsed_time": "1:05:28", "remaining_time": "0:46:16", "throughput": 1033.73, "total_tokens": 4060880} {"current_steps": 45095, "total_steps": 76960, "loss": 0.4448, "lr": 2.1871799129544355e-05, "epoch": 11.719074844074845, "percentage": 58.6, "elapsed_time": "1:05:28", "remaining_time": "0:46:16", "throughput": 1033.73, "total_tokens": 4061328} {"current_steps": 45100, "total_steps": 76960, "loss": 0.0818, "lr": 2.1866174171004324e-05, "epoch": 11.72037422037422, "percentage": 58.6, "elapsed_time": "1:05:29", "remaining_time": "0:46:15", "throughput": 1033.74, "total_tokens": 4061792} {"current_steps": 45105, "total_steps": 76960, "loss": 0.2743, "lr": 2.186054937363996e-05, "epoch": 11.721673596673597, "percentage": 58.61, "elapsed_time": "1:05:29", "remaining_time": "0:46:15", "throughput": 1033.76, "total_tokens": 4062288} {"current_steps": 45110, "total_steps": 76960, "loss": 0.1061, "lr": 2.1854924737740546e-05, "epoch": 11.722972972972974, "percentage": 58.61, "elapsed_time": "1:05:30", "remaining_time": "0:46:14", "throughput": 1033.76, "total_tokens": 4062736} {"current_steps": 45115, "total_steps": 76960, "loss": 0.3817, "lr": 2.1849300263595377e-05, "epoch": 11.724272349272349, "percentage": 58.62, "elapsed_time": "1:05:30", "remaining_time": "0:46:14", "throughput": 1033.78, "total_tokens": 4063232} {"current_steps": 45120, "total_steps": 76960, "loss": 0.2926, "lr": 2.1843675951493696e-05, "epoch": 11.725571725571726, "percentage": 58.63, "elapsed_time": "1:05:30", "remaining_time": "0:46:13", "throughput": 1033.79, "total_tokens": 4063696} {"current_steps": 45125, "total_steps": 76960, "loss": 0.2415, "lr": 2.1838051801724805e-05, "epoch": 11.726871101871101, "percentage": 58.63, "elapsed_time": "1:05:31", "remaining_time": "0:46:13", "throughput": 1033.79, "total_tokens": 4064144} {"current_steps": 45130, "total_steps": 76960, "loss": 0.1965, "lr": 2.1832427814577936e-05, "epoch": 11.728170478170478, "percentage": 58.64, "elapsed_time": "1:05:31", "remaining_time": "0:46:13", "throughput": 1033.79, "total_tokens": 4064560} {"current_steps": 45135, "total_steps": 76960, "loss": 0.2501, "lr": 2.1826803990342327e-05, "epoch": 11.729469854469855, "percentage": 58.65, "elapsed_time": "1:05:32", "remaining_time": "0:46:12", "throughput": 1033.79, "total_tokens": 4064992} {"current_steps": 45140, "total_steps": 76960, "loss": 0.2131, "lr": 2.1821180329307242e-05, "epoch": 11.73076923076923, "percentage": 58.65, "elapsed_time": "1:05:32", "remaining_time": "0:46:12", "throughput": 1033.79, "total_tokens": 4065440} {"current_steps": 45145, "total_steps": 76960, "loss": 0.2409, "lr": 2.1815556831761886e-05, "epoch": 11.732068607068607, "percentage": 58.66, "elapsed_time": "1:05:32", "remaining_time": "0:46:11", "throughput": 1033.79, "total_tokens": 4065872} {"current_steps": 45150, "total_steps": 76960, "loss": 0.2086, "lr": 2.1809933497995504e-05, "epoch": 11.733367983367984, "percentage": 58.67, "elapsed_time": "1:05:33", "remaining_time": "0:46:11", "throughput": 1033.78, "total_tokens": 4066272} {"current_steps": 45155, "total_steps": 76960, "loss": 0.0829, "lr": 2.1804310328297293e-05, "epoch": 11.734667359667359, "percentage": 58.67, "elapsed_time": "1:05:33", "remaining_time": "0:46:10", "throughput": 1033.78, "total_tokens": 4066704} {"current_steps": 45160, "total_steps": 76960, "loss": 0.2695, "lr": 2.179868732295647e-05, "epoch": 11.735966735966736, "percentage": 58.68, "elapsed_time": "1:05:34", "remaining_time": "0:46:10", "throughput": 1033.79, "total_tokens": 4067168} {"current_steps": 45165, "total_steps": 76960, "loss": 0.0259, "lr": 2.1793064482262218e-05, "epoch": 11.737266112266113, "percentage": 58.69, "elapsed_time": "1:05:34", "remaining_time": "0:46:09", "throughput": 1033.8, "total_tokens": 4067616} {"current_steps": 45170, "total_steps": 76960, "loss": 0.2363, "lr": 2.178744180650374e-05, "epoch": 11.738565488565488, "percentage": 58.69, "elapsed_time": "1:05:35", "remaining_time": "0:46:09", "throughput": 1033.79, "total_tokens": 4068032} {"current_steps": 45175, "total_steps": 76960, "loss": 0.2303, "lr": 2.1781819295970196e-05, "epoch": 11.739864864864865, "percentage": 58.7, "elapsed_time": "1:05:35", "remaining_time": "0:46:08", "throughput": 1033.8, "total_tokens": 4068480} {"current_steps": 45180, "total_steps": 76960, "loss": 0.3357, "lr": 2.1776196950950787e-05, "epoch": 11.741164241164242, "percentage": 58.71, "elapsed_time": "1:05:35", "remaining_time": "0:46:08", "throughput": 1033.8, "total_tokens": 4068912} {"current_steps": 45185, "total_steps": 76960, "loss": 0.3158, "lr": 2.1770574771734642e-05, "epoch": 11.742463617463617, "percentage": 58.71, "elapsed_time": "1:05:36", "remaining_time": "0:46:08", "throughput": 1033.8, "total_tokens": 4069344} {"current_steps": 45190, "total_steps": 76960, "loss": 0.5404, "lr": 2.176495275861094e-05, "epoch": 11.743762993762994, "percentage": 58.72, "elapsed_time": "1:05:36", "remaining_time": "0:46:07", "throughput": 1033.8, "total_tokens": 4069776} {"current_steps": 45195, "total_steps": 76960, "loss": 0.6293, "lr": 2.175933091186882e-05, "epoch": 11.74506237006237, "percentage": 58.73, "elapsed_time": "1:05:37", "remaining_time": "0:46:07", "throughput": 1033.8, "total_tokens": 4070224} {"current_steps": 45200, "total_steps": 76960, "loss": 0.2558, "lr": 2.1753709231797403e-05, "epoch": 11.746361746361746, "percentage": 58.73, "elapsed_time": "1:05:37", "remaining_time": "0:46:06", "throughput": 1033.8, "total_tokens": 4070656} {"current_steps": 45205, "total_steps": 76960, "loss": 0.2552, "lr": 2.174808771868584e-05, "epoch": 11.747661122661123, "percentage": 58.74, "elapsed_time": "1:05:37", "remaining_time": "0:46:06", "throughput": 1033.8, "total_tokens": 4071072} {"current_steps": 45210, "total_steps": 76960, "loss": 0.1988, "lr": 2.1742466372823233e-05, "epoch": 11.7489604989605, "percentage": 58.74, "elapsed_time": "1:05:38", "remaining_time": "0:46:05", "throughput": 1033.81, "total_tokens": 4071536} {"current_steps": 45215, "total_steps": 76960, "loss": 0.2834, "lr": 2.173684519449872e-05, "epoch": 11.750259875259875, "percentage": 58.75, "elapsed_time": "1:05:38", "remaining_time": "0:46:05", "throughput": 1033.81, "total_tokens": 4071968} {"current_steps": 45220, "total_steps": 76960, "loss": 0.305, "lr": 2.1731224184001365e-05, "epoch": 11.751559251559252, "percentage": 58.76, "elapsed_time": "1:05:39", "remaining_time": "0:46:04", "throughput": 1033.81, "total_tokens": 4072432} {"current_steps": 45225, "total_steps": 76960, "loss": 0.1859, "lr": 2.1725603341620293e-05, "epoch": 11.752858627858627, "percentage": 58.76, "elapsed_time": "1:05:39", "remaining_time": "0:46:04", "throughput": 1033.81, "total_tokens": 4072848} {"current_steps": 45230, "total_steps": 76960, "loss": 0.3516, "lr": 2.171998266764457e-05, "epoch": 11.754158004158004, "percentage": 58.77, "elapsed_time": "1:05:40", "remaining_time": "0:46:04", "throughput": 1033.82, "total_tokens": 4073296} {"current_steps": 45235, "total_steps": 76960, "loss": 0.2077, "lr": 2.1714362162363293e-05, "epoch": 11.755457380457381, "percentage": 58.78, "elapsed_time": "1:05:40", "remaining_time": "0:46:03", "throughput": 1033.82, "total_tokens": 4073728} {"current_steps": 45240, "total_steps": 76960, "loss": 0.3635, "lr": 2.170874182606551e-05, "epoch": 11.756756756756756, "percentage": 58.78, "elapsed_time": "1:05:40", "remaining_time": "0:46:03", "throughput": 1033.82, "total_tokens": 4074160} {"current_steps": 45245, "total_steps": 76960, "loss": 0.2713, "lr": 2.170312165904029e-05, "epoch": 11.758056133056133, "percentage": 58.79, "elapsed_time": "1:05:41", "remaining_time": "0:46:02", "throughput": 1033.82, "total_tokens": 4074592} {"current_steps": 45250, "total_steps": 76960, "loss": 0.1555, "lr": 2.169750166157668e-05, "epoch": 11.75935550935551, "percentage": 58.8, "elapsed_time": "1:05:41", "remaining_time": "0:46:02", "throughput": 1033.82, "total_tokens": 4075040} {"current_steps": 45255, "total_steps": 76960, "loss": 0.3033, "lr": 2.169188183396373e-05, "epoch": 11.760654885654885, "percentage": 58.8, "elapsed_time": "1:05:42", "remaining_time": "0:46:01", "throughput": 1033.83, "total_tokens": 4075488} {"current_steps": 45260, "total_steps": 76960, "loss": 0.1931, "lr": 2.1686262176490467e-05, "epoch": 11.761954261954262, "percentage": 58.81, "elapsed_time": "1:05:42", "remaining_time": "0:46:01", "throughput": 1033.82, "total_tokens": 4075904} {"current_steps": 45265, "total_steps": 76960, "loss": 0.3621, "lr": 2.168064268944591e-05, "epoch": 11.763253638253639, "percentage": 58.82, "elapsed_time": "1:05:42", "remaining_time": "0:46:00", "throughput": 1033.83, "total_tokens": 4076352} {"current_steps": 45270, "total_steps": 76960, "loss": 0.2606, "lr": 2.1675023373119085e-05, "epoch": 11.764553014553014, "percentage": 58.82, "elapsed_time": "1:05:43", "remaining_time": "0:46:00", "throughput": 1033.83, "total_tokens": 4076784} {"current_steps": 45275, "total_steps": 76960, "loss": 0.1289, "lr": 2.1669404227798988e-05, "epoch": 11.765852390852391, "percentage": 58.83, "elapsed_time": "1:05:43", "remaining_time": "0:46:00", "throughput": 1033.84, "total_tokens": 4077264} {"current_steps": 45280, "total_steps": 76960, "loss": 0.2611, "lr": 2.166378525377463e-05, "epoch": 11.767151767151766, "percentage": 58.84, "elapsed_time": "1:05:44", "remaining_time": "0:45:59", "throughput": 1033.84, "total_tokens": 4077680} {"current_steps": 45285, "total_steps": 76960, "loss": 0.1755, "lr": 2.165816645133498e-05, "epoch": 11.768451143451143, "percentage": 58.84, "elapsed_time": "1:05:44", "remaining_time": "0:45:59", "throughput": 1033.85, "total_tokens": 4078144} {"current_steps": 45290, "total_steps": 76960, "loss": 0.146, "lr": 2.1652547820769046e-05, "epoch": 11.76975051975052, "percentage": 58.85, "elapsed_time": "1:05:45", "remaining_time": "0:45:58", "throughput": 1033.84, "total_tokens": 4078560} {"current_steps": 45295, "total_steps": 76960, "loss": 0.679, "lr": 2.1646929362365774e-05, "epoch": 11.771049896049895, "percentage": 58.86, "elapsed_time": "1:05:45", "remaining_time": "0:45:58", "throughput": 1033.85, "total_tokens": 4079008} {"current_steps": 45300, "total_steps": 76960, "loss": 0.3677, "lr": 2.1641311076414145e-05, "epoch": 11.772349272349272, "percentage": 58.86, "elapsed_time": "1:05:45", "remaining_time": "0:45:57", "throughput": 1033.85, "total_tokens": 4079472} {"current_steps": 45305, "total_steps": 76960, "loss": 0.1946, "lr": 2.1635692963203098e-05, "epoch": 11.77364864864865, "percentage": 58.87, "elapsed_time": "1:05:46", "remaining_time": "0:45:57", "throughput": 1033.86, "total_tokens": 4079920} {"current_steps": 45310, "total_steps": 76960, "loss": 0.1862, "lr": 2.1630075023021596e-05, "epoch": 11.774948024948024, "percentage": 58.87, "elapsed_time": "1:05:46", "remaining_time": "0:45:56", "throughput": 1033.85, "total_tokens": 4080336} {"current_steps": 45315, "total_steps": 76960, "loss": 0.1683, "lr": 2.1624457256158554e-05, "epoch": 11.776247401247401, "percentage": 58.88, "elapsed_time": "1:05:47", "remaining_time": "0:45:56", "throughput": 1033.86, "total_tokens": 4080784} {"current_steps": 45320, "total_steps": 76960, "loss": 0.2289, "lr": 2.1618839662902916e-05, "epoch": 11.777546777546778, "percentage": 58.89, "elapsed_time": "1:05:47", "remaining_time": "0:45:55", "throughput": 1033.86, "total_tokens": 4081216} {"current_steps": 45325, "total_steps": 76960, "loss": 0.3163, "lr": 2.1613222243543597e-05, "epoch": 11.778846153846153, "percentage": 58.89, "elapsed_time": "1:05:47", "remaining_time": "0:45:55", "throughput": 1033.87, "total_tokens": 4081680} {"current_steps": 45330, "total_steps": 76960, "loss": 0.2711, "lr": 2.1607604998369495e-05, "epoch": 11.78014553014553, "percentage": 58.9, "elapsed_time": "1:05:48", "remaining_time": "0:45:55", "throughput": 1033.87, "total_tokens": 4082112} {"current_steps": 45335, "total_steps": 76960, "loss": 0.1067, "lr": 2.1601987927669524e-05, "epoch": 11.781444906444907, "percentage": 58.91, "elapsed_time": "1:05:48", "remaining_time": "0:45:54", "throughput": 1033.87, "total_tokens": 4082560} {"current_steps": 45340, "total_steps": 76960, "loss": 0.2021, "lr": 2.159637103173256e-05, "epoch": 11.782744282744282, "percentage": 58.91, "elapsed_time": "1:05:49", "remaining_time": "0:45:54", "throughput": 1033.87, "total_tokens": 4082992} {"current_steps": 45345, "total_steps": 76960, "loss": 0.5363, "lr": 2.159075431084751e-05, "epoch": 11.78404365904366, "percentage": 58.92, "elapsed_time": "1:05:49", "remaining_time": "0:45:53", "throughput": 1033.89, "total_tokens": 4083488} {"current_steps": 45350, "total_steps": 76960, "loss": 0.3327, "lr": 2.158513776530322e-05, "epoch": 11.785343035343036, "percentage": 58.93, "elapsed_time": "1:05:50", "remaining_time": "0:45:53", "throughput": 1033.89, "total_tokens": 4083936} {"current_steps": 45355, "total_steps": 76960, "loss": 0.3722, "lr": 2.1579521395388573e-05, "epoch": 11.786642411642411, "percentage": 58.93, "elapsed_time": "1:05:50", "remaining_time": "0:45:52", "throughput": 1033.91, "total_tokens": 4084432} {"current_steps": 45360, "total_steps": 76960, "loss": 0.1749, "lr": 2.157390520139241e-05, "epoch": 11.787941787941788, "percentage": 58.94, "elapsed_time": "1:05:50", "remaining_time": "0:45:52", "throughput": 1033.92, "total_tokens": 4084880} {"current_steps": 45365, "total_steps": 76960, "loss": 0.1049, "lr": 2.1568289183603598e-05, "epoch": 11.789241164241163, "percentage": 58.95, "elapsed_time": "1:05:51", "remaining_time": "0:45:51", "throughput": 1033.91, "total_tokens": 4085296} {"current_steps": 45370, "total_steps": 76960, "loss": 0.4353, "lr": 2.1562673342310946e-05, "epoch": 11.79054054054054, "percentage": 58.95, "elapsed_time": "1:05:51", "remaining_time": "0:45:51", "throughput": 1033.92, "total_tokens": 4085744} {"current_steps": 45375, "total_steps": 76960, "loss": 0.2265, "lr": 2.1557057677803313e-05, "epoch": 11.791839916839917, "percentage": 58.96, "elapsed_time": "1:05:52", "remaining_time": "0:45:51", "throughput": 1033.92, "total_tokens": 4086176} {"current_steps": 45380, "total_steps": 76960, "loss": 0.1386, "lr": 2.1551442190369493e-05, "epoch": 11.793139293139292, "percentage": 58.97, "elapsed_time": "1:05:52", "remaining_time": "0:45:50", "throughput": 1033.91, "total_tokens": 4086592} {"current_steps": 45385, "total_steps": 76960, "loss": 0.3176, "lr": 2.154582688029831e-05, "epoch": 11.79443866943867, "percentage": 58.97, "elapsed_time": "1:05:52", "remaining_time": "0:45:50", "throughput": 1033.92, "total_tokens": 4087040} {"current_steps": 45390, "total_steps": 76960, "loss": 0.3025, "lr": 2.1540211747878563e-05, "epoch": 11.795738045738046, "percentage": 58.98, "elapsed_time": "1:05:53", "remaining_time": "0:45:49", "throughput": 1033.93, "total_tokens": 4087504} {"current_steps": 45395, "total_steps": 76960, "loss": 0.5708, "lr": 2.1534596793399032e-05, "epoch": 11.797037422037421, "percentage": 58.99, "elapsed_time": "1:05:53", "remaining_time": "0:45:49", "throughput": 1033.93, "total_tokens": 4087968} {"current_steps": 45400, "total_steps": 76960, "loss": 0.2096, "lr": 2.1528982017148515e-05, "epoch": 11.798336798336798, "percentage": 58.99, "elapsed_time": "1:05:54", "remaining_time": "0:45:48", "throughput": 1033.93, "total_tokens": 4088400} {"current_steps": 45405, "total_steps": 76960, "loss": 0.1115, "lr": 2.152336741941577e-05, "epoch": 11.799636174636175, "percentage": 59.0, "elapsed_time": "1:05:54", "remaining_time": "0:45:48", "throughput": 1033.94, "total_tokens": 4088848} {"current_steps": 45410, "total_steps": 76960, "loss": 0.3877, "lr": 2.1517753000489586e-05, "epoch": 11.80093555093555, "percentage": 59.0, "elapsed_time": "1:05:55", "remaining_time": "0:45:47", "throughput": 1033.95, "total_tokens": 4089312} {"current_steps": 45415, "total_steps": 76960, "loss": 0.1907, "lr": 2.1512138760658684e-05, "epoch": 11.802234927234927, "percentage": 59.01, "elapsed_time": "1:05:55", "remaining_time": "0:45:47", "throughput": 1033.95, "total_tokens": 4089760} {"current_steps": 45420, "total_steps": 76960, "loss": 0.1404, "lr": 2.1506524700211838e-05, "epoch": 11.803534303534304, "percentage": 59.02, "elapsed_time": "1:05:55", "remaining_time": "0:45:46", "throughput": 1033.97, "total_tokens": 4090240} {"current_steps": 45425, "total_steps": 76960, "loss": 0.2486, "lr": 2.1500910819437766e-05, "epoch": 11.80483367983368, "percentage": 59.02, "elapsed_time": "1:05:56", "remaining_time": "0:45:46", "throughput": 1033.97, "total_tokens": 4090672} {"current_steps": 45430, "total_steps": 76960, "loss": 0.2105, "lr": 2.1495297118625215e-05, "epoch": 11.806133056133056, "percentage": 59.03, "elapsed_time": "1:05:56", "remaining_time": "0:45:46", "throughput": 1033.99, "total_tokens": 4091184} {"current_steps": 45435, "total_steps": 76960, "loss": 0.1106, "lr": 2.148968359806288e-05, "epoch": 11.807432432432432, "percentage": 59.04, "elapsed_time": "1:05:57", "remaining_time": "0:45:45", "throughput": 1033.99, "total_tokens": 4091632} {"current_steps": 45440, "total_steps": 76960, "loss": 0.4124, "lr": 2.1484070258039488e-05, "epoch": 11.808731808731808, "percentage": 59.04, "elapsed_time": "1:05:57", "remaining_time": "0:45:45", "throughput": 1033.99, "total_tokens": 4092048} {"current_steps": 45445, "total_steps": 76960, "loss": 0.3048, "lr": 2.1478457098843724e-05, "epoch": 11.810031185031185, "percentage": 59.05, "elapsed_time": "1:05:57", "remaining_time": "0:45:44", "throughput": 1034.0, "total_tokens": 4092512} {"current_steps": 45450, "total_steps": 76960, "loss": 0.4372, "lr": 2.1472844120764295e-05, "epoch": 11.81133056133056, "percentage": 59.06, "elapsed_time": "1:05:58", "remaining_time": "0:45:44", "throughput": 1034.0, "total_tokens": 4092960} {"current_steps": 45455, "total_steps": 76960, "loss": 0.2679, "lr": 2.146723132408987e-05, "epoch": 11.812629937629938, "percentage": 59.06, "elapsed_time": "1:05:58", "remaining_time": "0:45:43", "throughput": 1034.01, "total_tokens": 4093424} {"current_steps": 45460, "total_steps": 76960, "loss": 0.1344, "lr": 2.1461618709109116e-05, "epoch": 11.813929313929314, "percentage": 59.07, "elapsed_time": "1:05:59", "remaining_time": "0:45:43", "throughput": 1034.01, "total_tokens": 4093872} {"current_steps": 45465, "total_steps": 76960, "loss": 0.4258, "lr": 2.1456006276110717e-05, "epoch": 11.81522869022869, "percentage": 59.08, "elapsed_time": "1:05:59", "remaining_time": "0:45:42", "throughput": 1034.03, "total_tokens": 4094352} {"current_steps": 45470, "total_steps": 76960, "loss": 0.332, "lr": 2.1450394025383295e-05, "epoch": 11.816528066528067, "percentage": 59.08, "elapsed_time": "1:06:00", "remaining_time": "0:45:42", "throughput": 1034.03, "total_tokens": 4094784} {"current_steps": 45475, "total_steps": 76960, "loss": 0.3312, "lr": 2.1444781957215515e-05, "epoch": 11.817827442827443, "percentage": 59.09, "elapsed_time": "1:06:00", "remaining_time": "0:45:42", "throughput": 1034.03, "total_tokens": 4095248} {"current_steps": 45480, "total_steps": 76960, "loss": 0.1107, "lr": 2.1439170071896e-05, "epoch": 11.819126819126819, "percentage": 59.1, "elapsed_time": "1:06:00", "remaining_time": "0:45:41", "throughput": 1034.04, "total_tokens": 4095696} {"current_steps": 45485, "total_steps": 76960, "loss": 0.1076, "lr": 2.1433558369713394e-05, "epoch": 11.820426195426196, "percentage": 59.1, "elapsed_time": "1:06:01", "remaining_time": "0:45:41", "throughput": 1034.04, "total_tokens": 4096128} {"current_steps": 45490, "total_steps": 76960, "loss": 0.2701, "lr": 2.1427946850956286e-05, "epoch": 11.821725571725572, "percentage": 59.11, "elapsed_time": "1:06:01", "remaining_time": "0:45:40", "throughput": 1034.04, "total_tokens": 4096576} {"current_steps": 45495, "total_steps": 76960, "loss": 0.2624, "lr": 2.14223355159133e-05, "epoch": 11.823024948024948, "percentage": 59.12, "elapsed_time": "1:06:02", "remaining_time": "0:45:40", "throughput": 1034.05, "total_tokens": 4097040} {"current_steps": 45500, "total_steps": 76960, "loss": 0.1696, "lr": 2.141672436487302e-05, "epoch": 11.824324324324325, "percentage": 59.12, "elapsed_time": "1:06:02", "remaining_time": "0:45:39", "throughput": 1034.05, "total_tokens": 4097472} {"current_steps": 45505, "total_steps": 76960, "loss": 0.1169, "lr": 2.141111339812405e-05, "epoch": 11.825623700623701, "percentage": 59.13, "elapsed_time": "1:06:02", "remaining_time": "0:45:39", "throughput": 1034.05, "total_tokens": 4097904} {"current_steps": 45510, "total_steps": 76960, "loss": 0.2725, "lr": 2.1405502615954945e-05, "epoch": 11.826923076923077, "percentage": 59.13, "elapsed_time": "1:06:03", "remaining_time": "0:45:38", "throughput": 1034.05, "total_tokens": 4098320} {"current_steps": 45515, "total_steps": 76960, "loss": 0.1748, "lr": 2.139989201865429e-05, "epoch": 11.828222453222454, "percentage": 59.14, "elapsed_time": "1:06:03", "remaining_time": "0:45:38", "throughput": 1034.05, "total_tokens": 4098768} {"current_steps": 45520, "total_steps": 76960, "loss": 0.0455, "lr": 2.1394281606510635e-05, "epoch": 11.829521829521829, "percentage": 59.15, "elapsed_time": "1:06:04", "remaining_time": "0:45:38", "throughput": 1034.05, "total_tokens": 4099200} {"current_steps": 45525, "total_steps": 76960, "loss": 0.5663, "lr": 2.1388671379812543e-05, "epoch": 11.830821205821206, "percentage": 59.15, "elapsed_time": "1:06:04", "remaining_time": "0:45:37", "throughput": 1034.06, "total_tokens": 4099664} {"current_steps": 45530, "total_steps": 76960, "loss": 0.4036, "lr": 2.1383061338848533e-05, "epoch": 11.832120582120583, "percentage": 59.16, "elapsed_time": "1:06:05", "remaining_time": "0:45:37", "throughput": 1034.07, "total_tokens": 4100128} {"current_steps": 45535, "total_steps": 76960, "loss": 0.3273, "lr": 2.137745148390714e-05, "epoch": 11.833419958419958, "percentage": 59.17, "elapsed_time": "1:06:05", "remaining_time": "0:45:36", "throughput": 1034.07, "total_tokens": 4100544} {"current_steps": 45540, "total_steps": 76960, "loss": 0.1328, "lr": 2.13718418152769e-05, "epoch": 11.834719334719335, "percentage": 59.17, "elapsed_time": "1:06:05", "remaining_time": "0:45:36", "throughput": 1034.07, "total_tokens": 4100976} {"current_steps": 45545, "total_steps": 76960, "loss": 0.2302, "lr": 2.13662323332463e-05, "epoch": 11.836018711018712, "percentage": 59.18, "elapsed_time": "1:06:06", "remaining_time": "0:45:35", "throughput": 1034.08, "total_tokens": 4101456} {"current_steps": 45550, "total_steps": 76960, "loss": 0.4989, "lr": 2.1360623038103858e-05, "epoch": 11.837318087318087, "percentage": 59.19, "elapsed_time": "1:06:06", "remaining_time": "0:45:35", "throughput": 1034.08, "total_tokens": 4101904} {"current_steps": 45555, "total_steps": 76960, "loss": 0.3252, "lr": 2.1355013930138054e-05, "epoch": 11.838617463617464, "percentage": 59.19, "elapsed_time": "1:06:07", "remaining_time": "0:45:34", "throughput": 1034.08, "total_tokens": 4102320} {"current_steps": 45560, "total_steps": 76960, "loss": 0.212, "lr": 2.1349405009637388e-05, "epoch": 11.83991683991684, "percentage": 59.2, "elapsed_time": "1:06:07", "remaining_time": "0:45:34", "throughput": 1034.08, "total_tokens": 4102768} {"current_steps": 45565, "total_steps": 76960, "loss": 0.2321, "lr": 2.134379627689031e-05, "epoch": 11.841216216216216, "percentage": 59.21, "elapsed_time": "1:06:07", "remaining_time": "0:45:33", "throughput": 1034.08, "total_tokens": 4103168} {"current_steps": 45570, "total_steps": 76960, "loss": 0.2318, "lr": 2.13381877321853e-05, "epoch": 11.842515592515593, "percentage": 59.21, "elapsed_time": "1:06:08", "remaining_time": "0:45:33", "throughput": 1034.08, "total_tokens": 4103616} {"current_steps": 45575, "total_steps": 76960, "loss": 0.1896, "lr": 2.1332579375810794e-05, "epoch": 11.84381496881497, "percentage": 59.22, "elapsed_time": "1:06:08", "remaining_time": "0:45:33", "throughput": 1034.08, "total_tokens": 4104048} {"current_steps": 45580, "total_steps": 76960, "loss": 0.2119, "lr": 2.1326971208055258e-05, "epoch": 11.845114345114345, "percentage": 59.23, "elapsed_time": "1:06:09", "remaining_time": "0:45:32", "throughput": 1034.09, "total_tokens": 4104496} {"current_steps": 45585, "total_steps": 76960, "loss": 0.2263, "lr": 2.1321363229207096e-05, "epoch": 11.846413721413722, "percentage": 59.23, "elapsed_time": "1:06:09", "remaining_time": "0:45:32", "throughput": 1034.09, "total_tokens": 4104960} {"current_steps": 45590, "total_steps": 76960, "loss": 0.4231, "lr": 2.131575543955476e-05, "epoch": 11.847713097713097, "percentage": 59.24, "elapsed_time": "1:06:10", "remaining_time": "0:45:31", "throughput": 1034.1, "total_tokens": 4105424} {"current_steps": 45595, "total_steps": 76960, "loss": 0.1078, "lr": 2.131014783938666e-05, "epoch": 11.849012474012474, "percentage": 59.25, "elapsed_time": "1:06:10", "remaining_time": "0:45:31", "throughput": 1034.11, "total_tokens": 4105872} {"current_steps": 45600, "total_steps": 76960, "loss": 0.1359, "lr": 2.130454042899117e-05, "epoch": 11.85031185031185, "percentage": 59.25, "elapsed_time": "1:06:10", "remaining_time": "0:45:30", "throughput": 1034.12, "total_tokens": 4106336} {"current_steps": 45605, "total_steps": 76960, "loss": 0.1819, "lr": 2.1298933208656718e-05, "epoch": 11.851611226611226, "percentage": 59.26, "elapsed_time": "1:06:11", "remaining_time": "0:45:30", "throughput": 1034.12, "total_tokens": 4106784} {"current_steps": 45610, "total_steps": 76960, "loss": 0.3892, "lr": 2.1293326178671676e-05, "epoch": 11.852910602910603, "percentage": 59.26, "elapsed_time": "1:06:11", "remaining_time": "0:45:29", "throughput": 1034.14, "total_tokens": 4107280} {"current_steps": 45615, "total_steps": 76960, "loss": 0.2619, "lr": 2.1287719339324426e-05, "epoch": 11.85420997920998, "percentage": 59.27, "elapsed_time": "1:06:12", "remaining_time": "0:45:29", "throughput": 1034.13, "total_tokens": 4107696} {"current_steps": 45620, "total_steps": 76960, "loss": 0.2983, "lr": 2.128211269090331e-05, "epoch": 11.855509355509355, "percentage": 59.28, "elapsed_time": "1:06:12", "remaining_time": "0:45:29", "throughput": 1034.14, "total_tokens": 4108144} {"current_steps": 45625, "total_steps": 76960, "loss": 0.3437, "lr": 2.127650623369672e-05, "epoch": 11.856808731808732, "percentage": 59.28, "elapsed_time": "1:06:12", "remaining_time": "0:45:28", "throughput": 1034.14, "total_tokens": 4108592} {"current_steps": 45630, "total_steps": 76960, "loss": 0.0956, "lr": 2.127089996799297e-05, "epoch": 11.858108108108109, "percentage": 59.29, "elapsed_time": "1:06:13", "remaining_time": "0:45:28", "throughput": 1034.16, "total_tokens": 4109072} {"current_steps": 45635, "total_steps": 76960, "loss": 0.2232, "lr": 2.1265293894080412e-05, "epoch": 11.859407484407484, "percentage": 59.3, "elapsed_time": "1:06:13", "remaining_time": "0:45:27", "throughput": 1034.15, "total_tokens": 4109472} {"current_steps": 45640, "total_steps": 76960, "loss": 0.176, "lr": 2.1259688012247364e-05, "epoch": 11.86070686070686, "percentage": 59.3, "elapsed_time": "1:06:14", "remaining_time": "0:45:27", "throughput": 1034.15, "total_tokens": 4109936} {"current_steps": 45645, "total_steps": 76960, "loss": 0.2595, "lr": 2.1254082322782157e-05, "epoch": 11.862006237006238, "percentage": 59.31, "elapsed_time": "1:06:14", "remaining_time": "0:45:26", "throughput": 1034.17, "total_tokens": 4110416} {"current_steps": 45650, "total_steps": 76960, "loss": 0.1639, "lr": 2.124847682597307e-05, "epoch": 11.863305613305613, "percentage": 59.32, "elapsed_time": "1:06:15", "remaining_time": "0:45:26", "throughput": 1034.17, "total_tokens": 4110848} {"current_steps": 45655, "total_steps": 76960, "loss": 0.3611, "lr": 2.1242871522108422e-05, "epoch": 11.86460498960499, "percentage": 59.32, "elapsed_time": "1:06:15", "remaining_time": "0:45:25", "throughput": 1034.17, "total_tokens": 4111296} {"current_steps": 45660, "total_steps": 76960, "loss": 0.2843, "lr": 2.12372664114765e-05, "epoch": 11.865904365904367, "percentage": 59.33, "elapsed_time": "1:06:15", "remaining_time": "0:45:25", "throughput": 1034.18, "total_tokens": 4111760} {"current_steps": 45665, "total_steps": 76960, "loss": 0.2749, "lr": 2.123166149436556e-05, "epoch": 11.867203742203742, "percentage": 59.34, "elapsed_time": "1:06:16", "remaining_time": "0:45:25", "throughput": 1034.19, "total_tokens": 4112240} {"current_steps": 45670, "total_steps": 76960, "loss": 0.1785, "lr": 2.1226056771063883e-05, "epoch": 11.868503118503119, "percentage": 59.34, "elapsed_time": "1:06:16", "remaining_time": "0:45:24", "throughput": 1034.19, "total_tokens": 4112656} {"current_steps": 45675, "total_steps": 76960, "loss": 0.3445, "lr": 2.1220452241859718e-05, "epoch": 11.869802494802494, "percentage": 59.35, "elapsed_time": "1:06:17", "remaining_time": "0:45:24", "throughput": 1034.19, "total_tokens": 4113104} {"current_steps": 45680, "total_steps": 76960, "loss": 0.2244, "lr": 2.1214847907041326e-05, "epoch": 11.871101871101871, "percentage": 59.36, "elapsed_time": "1:06:17", "remaining_time": "0:45:23", "throughput": 1034.19, "total_tokens": 4113536} {"current_steps": 45685, "total_steps": 76960, "loss": 0.1309, "lr": 2.1209243766896923e-05, "epoch": 11.872401247401248, "percentage": 59.36, "elapsed_time": "1:06:17", "remaining_time": "0:45:23", "throughput": 1034.19, "total_tokens": 4113968} {"current_steps": 45690, "total_steps": 76960, "loss": 0.1953, "lr": 2.1203639821714748e-05, "epoch": 11.873700623700623, "percentage": 59.37, "elapsed_time": "1:06:18", "remaining_time": "0:45:22", "throughput": 1034.19, "total_tokens": 4114400} {"current_steps": 45695, "total_steps": 76960, "loss": 0.1782, "lr": 2.119803607178301e-05, "epoch": 11.875, "percentage": 59.38, "elapsed_time": "1:06:18", "remaining_time": "0:45:22", "throughput": 1034.21, "total_tokens": 4114896} {"current_steps": 45700, "total_steps": 76960, "loss": 0.1857, "lr": 2.119243251738993e-05, "epoch": 11.876299376299377, "percentage": 59.38, "elapsed_time": "1:06:19", "remaining_time": "0:45:21", "throughput": 1034.22, "total_tokens": 4115376} {"current_steps": 45705, "total_steps": 76960, "loss": 0.2667, "lr": 2.1186829158823686e-05, "epoch": 11.877598752598752, "percentage": 59.39, "elapsed_time": "1:06:19", "remaining_time": "0:45:21", "throughput": 1034.22, "total_tokens": 4115808} {"current_steps": 45710, "total_steps": 76960, "loss": 0.1732, "lr": 2.1181225996372477e-05, "epoch": 11.878898128898129, "percentage": 59.39, "elapsed_time": "1:06:20", "remaining_time": "0:45:20", "throughput": 1034.23, "total_tokens": 4116272} {"current_steps": 45715, "total_steps": 76960, "loss": 0.1146, "lr": 2.1175623030324468e-05, "epoch": 11.880197505197506, "percentage": 59.4, "elapsed_time": "1:06:20", "remaining_time": "0:45:20", "throughput": 1034.24, "total_tokens": 4116720} {"current_steps": 45720, "total_steps": 76960, "loss": 0.3013, "lr": 2.117002026096784e-05, "epoch": 11.881496881496881, "percentage": 59.41, "elapsed_time": "1:06:20", "remaining_time": "0:45:20", "throughput": 1034.25, "total_tokens": 4117216} {"current_steps": 45725, "total_steps": 76960, "loss": 0.2516, "lr": 2.116441768859074e-05, "epoch": 11.882796257796258, "percentage": 59.41, "elapsed_time": "1:06:21", "remaining_time": "0:45:19", "throughput": 1034.26, "total_tokens": 4117664} {"current_steps": 45730, "total_steps": 76960, "loss": 0.5683, "lr": 2.11588153134813e-05, "epoch": 11.884095634095633, "percentage": 59.42, "elapsed_time": "1:06:21", "remaining_time": "0:45:19", "throughput": 1034.26, "total_tokens": 4118112} {"current_steps": 45735, "total_steps": 76960, "loss": 0.2976, "lr": 2.115321313592768e-05, "epoch": 11.88539501039501, "percentage": 59.43, "elapsed_time": "1:06:22", "remaining_time": "0:45:18", "throughput": 1034.27, "total_tokens": 4118576} {"current_steps": 45740, "total_steps": 76960, "loss": 0.2205, "lr": 2.114761115621799e-05, "epoch": 11.886694386694387, "percentage": 59.43, "elapsed_time": "1:06:22", "remaining_time": "0:45:18", "throughput": 1034.27, "total_tokens": 4119008} {"current_steps": 45745, "total_steps": 76960, "loss": 0.5161, "lr": 2.114200937464035e-05, "epoch": 11.887993762993762, "percentage": 59.44, "elapsed_time": "1:06:22", "remaining_time": "0:45:17", "throughput": 1034.28, "total_tokens": 4119456} {"current_steps": 45750, "total_steps": 76960, "loss": 0.353, "lr": 2.1136407791482862e-05, "epoch": 11.88929313929314, "percentage": 59.45, "elapsed_time": "1:06:23", "remaining_time": "0:45:17", "throughput": 1034.27, "total_tokens": 4119872} {"current_steps": 45755, "total_steps": 76960, "loss": 0.3132, "lr": 2.1130806407033633e-05, "epoch": 11.890592515592516, "percentage": 59.45, "elapsed_time": "1:06:23", "remaining_time": "0:45:16", "throughput": 1034.28, "total_tokens": 4120336} {"current_steps": 45760, "total_steps": 76960, "loss": 0.1298, "lr": 2.1125205221580725e-05, "epoch": 11.891891891891891, "percentage": 59.46, "elapsed_time": "1:06:24", "remaining_time": "0:45:16", "throughput": 1034.28, "total_tokens": 4120784} {"current_steps": 45765, "total_steps": 76960, "loss": 0.2428, "lr": 2.1119604235412233e-05, "epoch": 11.893191268191268, "percentage": 59.47, "elapsed_time": "1:06:24", "remaining_time": "0:45:16", "throughput": 1034.29, "total_tokens": 4121248} {"current_steps": 45770, "total_steps": 76960, "loss": 0.271, "lr": 2.1114003448816206e-05, "epoch": 11.894490644490645, "percentage": 59.47, "elapsed_time": "1:06:25", "remaining_time": "0:45:15", "throughput": 1034.3, "total_tokens": 4121696} {"current_steps": 45775, "total_steps": 76960, "loss": 0.1251, "lr": 2.1108402862080716e-05, "epoch": 11.89579002079002, "percentage": 59.48, "elapsed_time": "1:06:25", "remaining_time": "0:45:15", "throughput": 1034.31, "total_tokens": 4122192} {"current_steps": 45780, "total_steps": 76960, "loss": 0.2245, "lr": 2.1102802475493786e-05, "epoch": 11.897089397089397, "percentage": 59.49, "elapsed_time": "1:06:25", "remaining_time": "0:45:14", "throughput": 1034.32, "total_tokens": 4122640} {"current_steps": 45785, "total_steps": 76960, "loss": 0.4158, "lr": 2.1097202289343464e-05, "epoch": 11.898388773388774, "percentage": 59.49, "elapsed_time": "1:06:26", "remaining_time": "0:45:14", "throughput": 1034.32, "total_tokens": 4123072} {"current_steps": 45790, "total_steps": 76960, "loss": 0.248, "lr": 2.109160230391777e-05, "epoch": 11.89968814968815, "percentage": 59.5, "elapsed_time": "1:06:26", "remaining_time": "0:45:13", "throughput": 1034.33, "total_tokens": 4123552} {"current_steps": 45795, "total_steps": 76960, "loss": 0.3457, "lr": 2.1086002519504707e-05, "epoch": 11.900987525987526, "percentage": 59.5, "elapsed_time": "1:06:27", "remaining_time": "0:45:13", "throughput": 1034.34, "total_tokens": 4124016} {"current_steps": 45800, "total_steps": 76960, "loss": 0.2175, "lr": 2.1080402936392292e-05, "epoch": 11.902286902286903, "percentage": 59.51, "elapsed_time": "1:06:27", "remaining_time": "0:45:12", "throughput": 1034.34, "total_tokens": 4124448} {"current_steps": 45805, "total_steps": 76960, "loss": 0.2597, "lr": 2.10748035548685e-05, "epoch": 11.903586278586278, "percentage": 59.52, "elapsed_time": "1:06:27", "remaining_time": "0:45:12", "throughput": 1034.35, "total_tokens": 4124912} {"current_steps": 45810, "total_steps": 76960, "loss": 0.3457, "lr": 2.1069204375221334e-05, "epoch": 11.904885654885655, "percentage": 59.52, "elapsed_time": "1:06:28", "remaining_time": "0:45:12", "throughput": 1034.35, "total_tokens": 4125328} {"current_steps": 45815, "total_steps": 76960, "loss": 0.1021, "lr": 2.1063605397738743e-05, "epoch": 11.90618503118503, "percentage": 59.53, "elapsed_time": "1:06:28", "remaining_time": "0:45:11", "throughput": 1034.35, "total_tokens": 4125760} {"current_steps": 45820, "total_steps": 76960, "loss": 0.172, "lr": 2.10580066227087e-05, "epoch": 11.907484407484407, "percentage": 59.54, "elapsed_time": "1:06:29", "remaining_time": "0:45:11", "throughput": 1034.36, "total_tokens": 4126224} {"current_steps": 45825, "total_steps": 76960, "loss": 0.4495, "lr": 2.1052408050419152e-05, "epoch": 11.908783783783784, "percentage": 59.54, "elapsed_time": "1:06:29", "remaining_time": "0:45:10", "throughput": 1034.35, "total_tokens": 4126624} {"current_steps": 45830, "total_steps": 76960, "loss": 0.0929, "lr": 2.104680968115805e-05, "epoch": 11.91008316008316, "percentage": 59.55, "elapsed_time": "1:06:30", "remaining_time": "0:45:10", "throughput": 1034.35, "total_tokens": 4127056} {"current_steps": 45835, "total_steps": 76960, "loss": 0.2424, "lr": 2.1041211515213304e-05, "epoch": 11.911382536382536, "percentage": 59.56, "elapsed_time": "1:06:30", "remaining_time": "0:45:09", "throughput": 1034.35, "total_tokens": 4127504} {"current_steps": 45840, "total_steps": 76960, "loss": 0.3039, "lr": 2.103561355287285e-05, "epoch": 11.912681912681913, "percentage": 59.56, "elapsed_time": "1:06:30", "remaining_time": "0:45:09", "throughput": 1034.36, "total_tokens": 4127968} {"current_steps": 45845, "total_steps": 76960, "loss": 0.1429, "lr": 2.103001579442458e-05, "epoch": 11.913981288981288, "percentage": 59.57, "elapsed_time": "1:06:31", "remaining_time": "0:45:08", "throughput": 1034.37, "total_tokens": 4128448} {"current_steps": 45850, "total_steps": 76960, "loss": 0.214, "lr": 2.1024418240156413e-05, "epoch": 11.915280665280665, "percentage": 59.58, "elapsed_time": "1:06:31", "remaining_time": "0:45:08", "throughput": 1034.37, "total_tokens": 4128864} {"current_steps": 45855, "total_steps": 76960, "loss": 0.2568, "lr": 2.1018820890356224e-05, "epoch": 11.916580041580042, "percentage": 59.58, "elapsed_time": "1:06:32", "remaining_time": "0:45:07", "throughput": 1034.37, "total_tokens": 4129312} {"current_steps": 45860, "total_steps": 76960, "loss": 0.7127, "lr": 2.101322374531188e-05, "epoch": 11.917879417879417, "percentage": 59.59, "elapsed_time": "1:06:32", "remaining_time": "0:45:07", "throughput": 1034.37, "total_tokens": 4129744} {"current_steps": 45865, "total_steps": 76960, "loss": 0.3815, "lr": 2.1007626805311272e-05, "epoch": 11.919178794178794, "percentage": 59.6, "elapsed_time": "1:06:32", "remaining_time": "0:45:07", "throughput": 1034.39, "total_tokens": 4130224} {"current_steps": 45870, "total_steps": 76960, "loss": 0.3531, "lr": 2.1002030070642224e-05, "epoch": 11.920478170478171, "percentage": 59.6, "elapsed_time": "1:06:33", "remaining_time": "0:45:06", "throughput": 1034.39, "total_tokens": 4130688} {"current_steps": 45875, "total_steps": 76960, "loss": 0.7763, "lr": 2.099643354159262e-05, "epoch": 11.921777546777546, "percentage": 59.61, "elapsed_time": "1:06:33", "remaining_time": "0:45:06", "throughput": 1034.4, "total_tokens": 4131136} {"current_steps": 45880, "total_steps": 76960, "loss": 0.2613, "lr": 2.0990837218450265e-05, "epoch": 11.923076923076923, "percentage": 59.62, "elapsed_time": "1:06:34", "remaining_time": "0:45:05", "throughput": 1034.39, "total_tokens": 4131552} {"current_steps": 45885, "total_steps": 76960, "loss": 0.2372, "lr": 2.0985241101502996e-05, "epoch": 11.924376299376299, "percentage": 59.62, "elapsed_time": "1:06:34", "remaining_time": "0:45:05", "throughput": 1034.4, "total_tokens": 4132016} {"current_steps": 45890, "total_steps": 76960, "loss": 0.2464, "lr": 2.0979645191038623e-05, "epoch": 11.925675675675675, "percentage": 59.63, "elapsed_time": "1:06:35", "remaining_time": "0:45:04", "throughput": 1034.41, "total_tokens": 4132464} {"current_steps": 45895, "total_steps": 76960, "loss": 0.4431, "lr": 2.0974049487344953e-05, "epoch": 11.926975051975052, "percentage": 59.63, "elapsed_time": "1:06:35", "remaining_time": "0:45:04", "throughput": 1034.41, "total_tokens": 4132896} {"current_steps": 45900, "total_steps": 76960, "loss": 0.2426, "lr": 2.0968453990709768e-05, "epoch": 11.928274428274428, "percentage": 59.64, "elapsed_time": "1:06:35", "remaining_time": "0:45:03", "throughput": 1034.41, "total_tokens": 4133344} {"current_steps": 45905, "total_steps": 76960, "loss": 0.3299, "lr": 2.0962858701420866e-05, "epoch": 11.929573804573804, "percentage": 59.65, "elapsed_time": "1:06:36", "remaining_time": "0:45:03", "throughput": 1034.43, "total_tokens": 4133824} {"current_steps": 45910, "total_steps": 76960, "loss": 0.2142, "lr": 2.0957263619766e-05, "epoch": 11.930873180873181, "percentage": 59.65, "elapsed_time": "1:06:36", "remaining_time": "0:45:03", "throughput": 1034.44, "total_tokens": 4134304} {"current_steps": 45915, "total_steps": 76960, "loss": 0.37, "lr": 2.0951668746032953e-05, "epoch": 11.932172557172557, "percentage": 59.66, "elapsed_time": "1:06:37", "remaining_time": "0:45:02", "throughput": 1034.45, "total_tokens": 4134768} {"current_steps": 45920, "total_steps": 76960, "loss": 0.2154, "lr": 2.0946074080509453e-05, "epoch": 11.933471933471933, "percentage": 59.67, "elapsed_time": "1:06:37", "remaining_time": "0:45:02", "throughput": 1034.46, "total_tokens": 4135232} {"current_steps": 45925, "total_steps": 76960, "loss": 0.1817, "lr": 2.0940479623483246e-05, "epoch": 11.93477130977131, "percentage": 59.67, "elapsed_time": "1:06:37", "remaining_time": "0:45:01", "throughput": 1034.46, "total_tokens": 4135696} {"current_steps": 45930, "total_steps": 76960, "loss": 0.1798, "lr": 2.0934885375242068e-05, "epoch": 11.936070686070686, "percentage": 59.68, "elapsed_time": "1:06:38", "remaining_time": "0:45:01", "throughput": 1034.46, "total_tokens": 4136112} {"current_steps": 45935, "total_steps": 76960, "loss": 0.3763, "lr": 2.092929133607362e-05, "epoch": 11.937370062370062, "percentage": 59.69, "elapsed_time": "1:06:38", "remaining_time": "0:45:00", "throughput": 1034.46, "total_tokens": 4136560} {"current_steps": 45940, "total_steps": 76960, "loss": 0.1001, "lr": 2.0923697506265625e-05, "epoch": 11.93866943866944, "percentage": 59.69, "elapsed_time": "1:06:39", "remaining_time": "0:45:00", "throughput": 1034.47, "total_tokens": 4137008} {"current_steps": 45945, "total_steps": 76960, "loss": 0.2924, "lr": 2.0918103886105768e-05, "epoch": 11.939968814968815, "percentage": 59.7, "elapsed_time": "1:06:39", "remaining_time": "0:44:59", "throughput": 1034.47, "total_tokens": 4137440} {"current_steps": 45950, "total_steps": 76960, "loss": 0.5767, "lr": 2.091251047588175e-05, "epoch": 11.941268191268192, "percentage": 59.71, "elapsed_time": "1:06:39", "remaining_time": "0:44:59", "throughput": 1034.48, "total_tokens": 4137904} {"current_steps": 45955, "total_steps": 76960, "loss": 0.2133, "lr": 2.0906917275881224e-05, "epoch": 11.942567567567568, "percentage": 59.71, "elapsed_time": "1:06:40", "remaining_time": "0:44:59", "throughput": 1034.47, "total_tokens": 4138320} {"current_steps": 45960, "total_steps": 76960, "loss": 0.3538, "lr": 2.090132428639187e-05, "epoch": 11.943866943866944, "percentage": 59.72, "elapsed_time": "1:06:40", "remaining_time": "0:44:58", "throughput": 1034.47, "total_tokens": 4138736} {"current_steps": 45965, "total_steps": 76960, "loss": 0.4233, "lr": 2.089573150770133e-05, "epoch": 11.94516632016632, "percentage": 59.73, "elapsed_time": "1:06:41", "remaining_time": "0:44:58", "throughput": 1034.48, "total_tokens": 4139184} {"current_steps": 45970, "total_steps": 76960, "loss": 0.2448, "lr": 2.089013894009726e-05, "epoch": 11.946465696465696, "percentage": 59.73, "elapsed_time": "1:06:41", "remaining_time": "0:44:57", "throughput": 1034.49, "total_tokens": 4139664} {"current_steps": 45975, "total_steps": 76960, "loss": 0.2699, "lr": 2.088454658386727e-05, "epoch": 11.947765072765073, "percentage": 59.74, "elapsed_time": "1:06:42", "remaining_time": "0:44:57", "throughput": 1034.49, "total_tokens": 4140112} {"current_steps": 45980, "total_steps": 76960, "loss": 0.1416, "lr": 2.0878954439299003e-05, "epoch": 11.94906444906445, "percentage": 59.75, "elapsed_time": "1:06:42", "remaining_time": "0:44:56", "throughput": 1034.5, "total_tokens": 4140592} {"current_steps": 45985, "total_steps": 76960, "loss": 0.1943, "lr": 2.0873362506680057e-05, "epoch": 11.950363825363825, "percentage": 59.75, "elapsed_time": "1:06:42", "remaining_time": "0:44:56", "throughput": 1034.53, "total_tokens": 4141104} {"current_steps": 45990, "total_steps": 76960, "loss": 0.2343, "lr": 2.0867770786298023e-05, "epoch": 11.951663201663202, "percentage": 59.76, "elapsed_time": "1:06:43", "remaining_time": "0:44:55", "throughput": 1034.55, "total_tokens": 4141616} {"current_steps": 45995, "total_steps": 76960, "loss": 0.1152, "lr": 2.0862179278440507e-05, "epoch": 11.952962577962579, "percentage": 59.76, "elapsed_time": "1:06:43", "remaining_time": "0:44:55", "throughput": 1034.56, "total_tokens": 4142096} {"current_steps": 46000, "total_steps": 76960, "loss": 0.1579, "lr": 2.0856587983395064e-05, "epoch": 11.954261954261954, "percentage": 59.77, "elapsed_time": "1:06:44", "remaining_time": "0:44:54", "throughput": 1034.56, "total_tokens": 4142528} {"current_steps": 46005, "total_steps": 76960, "loss": 0.4035, "lr": 2.0850996901449284e-05, "epoch": 11.95556133056133, "percentage": 59.78, "elapsed_time": "1:06:44", "remaining_time": "0:44:54", "throughput": 1034.56, "total_tokens": 4142944} {"current_steps": 46010, "total_steps": 76960, "loss": 0.277, "lr": 2.0845406032890698e-05, "epoch": 11.956860706860708, "percentage": 59.78, "elapsed_time": "1:06:44", "remaining_time": "0:44:54", "throughput": 1034.56, "total_tokens": 4143392} {"current_steps": 46015, "total_steps": 76960, "loss": 0.2869, "lr": 2.0839815378006865e-05, "epoch": 11.958160083160083, "percentage": 59.79, "elapsed_time": "1:06:45", "remaining_time": "0:44:53", "throughput": 1034.57, "total_tokens": 4143840} {"current_steps": 46020, "total_steps": 76960, "loss": 0.2103, "lr": 2.083422493708531e-05, "epoch": 11.95945945945946, "percentage": 59.8, "elapsed_time": "1:06:45", "remaining_time": "0:44:53", "throughput": 1034.57, "total_tokens": 4144304} {"current_steps": 46025, "total_steps": 76960, "loss": 0.2954, "lr": 2.0828634710413565e-05, "epoch": 11.960758835758837, "percentage": 59.8, "elapsed_time": "1:06:46", "remaining_time": "0:44:52", "throughput": 1034.57, "total_tokens": 4144736} {"current_steps": 46030, "total_steps": 76960, "loss": 0.1454, "lr": 2.0823044698279126e-05, "epoch": 11.962058212058212, "percentage": 59.81, "elapsed_time": "1:06:46", "remaining_time": "0:44:52", "throughput": 1034.58, "total_tokens": 4145200} {"current_steps": 46035, "total_steps": 76960, "loss": 0.3743, "lr": 2.0817454900969508e-05, "epoch": 11.963357588357589, "percentage": 59.82, "elapsed_time": "1:06:47", "remaining_time": "0:44:51", "throughput": 1034.59, "total_tokens": 4145664} {"current_steps": 46040, "total_steps": 76960, "loss": 0.183, "lr": 2.081186531877218e-05, "epoch": 11.964656964656964, "percentage": 59.82, "elapsed_time": "1:06:47", "remaining_time": "0:44:51", "throughput": 1034.59, "total_tokens": 4146080} {"current_steps": 46045, "total_steps": 76960, "loss": 0.2635, "lr": 2.0806275951974647e-05, "epoch": 11.96595634095634, "percentage": 59.83, "elapsed_time": "1:06:47", "remaining_time": "0:44:50", "throughput": 1034.58, "total_tokens": 4146496} {"current_steps": 46050, "total_steps": 76960, "loss": 0.228, "lr": 2.0800686800864353e-05, "epoch": 11.967255717255718, "percentage": 59.84, "elapsed_time": "1:06:48", "remaining_time": "0:44:50", "throughput": 1034.58, "total_tokens": 4146928} {"current_steps": 46055, "total_steps": 76960, "loss": 0.4353, "lr": 2.0795097865728755e-05, "epoch": 11.968555093555093, "percentage": 59.84, "elapsed_time": "1:06:48", "remaining_time": "0:44:50", "throughput": 1034.58, "total_tokens": 4147344} {"current_steps": 46060, "total_steps": 76960, "loss": 0.2053, "lr": 2.0789509146855316e-05, "epoch": 11.96985446985447, "percentage": 59.85, "elapsed_time": "1:06:49", "remaining_time": "0:44:49", "throughput": 1034.58, "total_tokens": 4147760} {"current_steps": 46065, "total_steps": 76960, "loss": 0.3361, "lr": 2.078392064453144e-05, "epoch": 11.971153846153847, "percentage": 59.86, "elapsed_time": "1:06:49", "remaining_time": "0:44:49", "throughput": 1034.59, "total_tokens": 4148256} {"current_steps": 46070, "total_steps": 76960, "loss": 0.3083, "lr": 2.0778332359044576e-05, "epoch": 11.972453222453222, "percentage": 59.86, "elapsed_time": "1:06:49", "remaining_time": "0:44:48", "throughput": 1034.59, "total_tokens": 4148688} {"current_steps": 46075, "total_steps": 76960, "loss": 0.237, "lr": 2.0772744290682113e-05, "epoch": 11.973752598752599, "percentage": 59.87, "elapsed_time": "1:06:50", "remaining_time": "0:44:48", "throughput": 1034.6, "total_tokens": 4149152} {"current_steps": 46080, "total_steps": 76960, "loss": 0.2837, "lr": 2.076715643973148e-05, "epoch": 11.975051975051976, "percentage": 59.88, "elapsed_time": "1:06:50", "remaining_time": "0:44:47", "throughput": 1034.6, "total_tokens": 4149584} {"current_steps": 46085, "total_steps": 76960, "loss": 0.2324, "lr": 2.076156880648003e-05, "epoch": 11.97635135135135, "percentage": 59.88, "elapsed_time": "1:06:51", "remaining_time": "0:44:47", "throughput": 1034.6, "total_tokens": 4150000} {"current_steps": 46090, "total_steps": 76960, "loss": 0.2007, "lr": 2.075598139121516e-05, "epoch": 11.977650727650728, "percentage": 59.89, "elapsed_time": "1:06:51", "remaining_time": "0:44:46", "throughput": 1034.61, "total_tokens": 4150464} {"current_steps": 46095, "total_steps": 76960, "loss": 0.4343, "lr": 2.0750394194224232e-05, "epoch": 11.978950103950105, "percentage": 59.89, "elapsed_time": "1:06:52", "remaining_time": "0:44:46", "throughput": 1034.61, "total_tokens": 4150896} {"current_steps": 46100, "total_steps": 76960, "loss": 0.1682, "lr": 2.0744807215794614e-05, "epoch": 11.98024948024948, "percentage": 59.9, "elapsed_time": "1:06:52", "remaining_time": "0:44:46", "throughput": 1034.61, "total_tokens": 4151360} {"current_steps": 46105, "total_steps": 76960, "loss": 0.3765, "lr": 2.073922045621362e-05, "epoch": 11.981548856548857, "percentage": 59.91, "elapsed_time": "1:06:52", "remaining_time": "0:44:45", "throughput": 1034.61, "total_tokens": 4151776} {"current_steps": 46110, "total_steps": 76960, "loss": 0.2099, "lr": 2.073363391576862e-05, "epoch": 11.982848232848234, "percentage": 59.91, "elapsed_time": "1:06:53", "remaining_time": "0:44:45", "throughput": 1034.62, "total_tokens": 4152256} {"current_steps": 46115, "total_steps": 76960, "loss": 0.2649, "lr": 2.0728047594746912e-05, "epoch": 11.984147609147609, "percentage": 59.92, "elapsed_time": "1:06:53", "remaining_time": "0:44:44", "throughput": 1034.63, "total_tokens": 4152720} {"current_steps": 46120, "total_steps": 76960, "loss": 0.3409, "lr": 2.0722461493435794e-05, "epoch": 11.985446985446986, "percentage": 59.93, "elapsed_time": "1:06:54", "remaining_time": "0:44:44", "throughput": 1034.63, "total_tokens": 4153136} {"current_steps": 46125, "total_steps": 76960, "loss": 0.1165, "lr": 2.0716875612122596e-05, "epoch": 11.986746361746361, "percentage": 59.93, "elapsed_time": "1:06:54", "remaining_time": "0:44:43", "throughput": 1034.64, "total_tokens": 4153600} {"current_steps": 46130, "total_steps": 76960, "loss": 0.1521, "lr": 2.071128995109458e-05, "epoch": 11.988045738045738, "percentage": 59.94, "elapsed_time": "1:06:54", "remaining_time": "0:44:43", "throughput": 1034.65, "total_tokens": 4154080} {"current_steps": 46135, "total_steps": 76960, "loss": 0.2066, "lr": 2.0705704510639035e-05, "epoch": 11.989345114345115, "percentage": 59.95, "elapsed_time": "1:06:55", "remaining_time": "0:44:42", "throughput": 1034.66, "total_tokens": 4154544} {"current_steps": 46140, "total_steps": 76960, "loss": 0.3007, "lr": 2.0700119291043215e-05, "epoch": 11.99064449064449, "percentage": 59.95, "elapsed_time": "1:06:55", "remaining_time": "0:44:42", "throughput": 1034.65, "total_tokens": 4154944} {"current_steps": 46145, "total_steps": 76960, "loss": 0.1536, "lr": 2.0694534292594392e-05, "epoch": 11.991943866943867, "percentage": 59.96, "elapsed_time": "1:06:56", "remaining_time": "0:44:41", "throughput": 1034.66, "total_tokens": 4155424} {"current_steps": 46150, "total_steps": 76960, "loss": 0.2133, "lr": 2.0688949515579785e-05, "epoch": 11.993243243243244, "percentage": 59.97, "elapsed_time": "1:06:56", "remaining_time": "0:44:41", "throughput": 1034.67, "total_tokens": 4155888} {"current_steps": 46155, "total_steps": 76960, "loss": 0.2207, "lr": 2.068336496028664e-05, "epoch": 11.994542619542619, "percentage": 59.97, "elapsed_time": "1:06:57", "remaining_time": "0:44:41", "throughput": 1034.67, "total_tokens": 4156336} {"current_steps": 46160, "total_steps": 76960, "loss": 0.3826, "lr": 2.0677780627002166e-05, "epoch": 11.995841995841996, "percentage": 59.98, "elapsed_time": "1:06:57", "remaining_time": "0:44:40", "throughput": 1034.68, "total_tokens": 4156784} {"current_steps": 46165, "total_steps": 76960, "loss": 0.4042, "lr": 2.0672196516013587e-05, "epoch": 11.997141372141373, "percentage": 59.99, "elapsed_time": "1:06:57", "remaining_time": "0:44:40", "throughput": 1034.69, "total_tokens": 4157248} {"current_steps": 46170, "total_steps": 76960, "loss": 0.1922, "lr": 2.066661262760808e-05, "epoch": 11.998440748440748, "percentage": 59.99, "elapsed_time": "1:06:58", "remaining_time": "0:44:39", "throughput": 1034.7, "total_tokens": 4157728} {"current_steps": 46175, "total_steps": 76960, "loss": 0.0849, "lr": 2.0661028962072836e-05, "epoch": 11.999740124740125, "percentage": 60.0, "elapsed_time": "1:06:58", "remaining_time": "0:44:39", "throughput": 1034.7, "total_tokens": 4158128} {"current_steps": 46176, "total_steps": 76960, "eval_loss": 0.2743130028247833, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "1:07:11", "remaining_time": "0:44:47", "throughput": 1031.29, "total_tokens": 4158168} {"current_steps": 46180, "total_steps": 76960, "loss": 0.0922, "lr": 2.065544551969504e-05, "epoch": 12.001039501039502, "percentage": 60.01, "elapsed_time": "1:07:14", "remaining_time": "0:44:48", "throughput": 1030.86, "total_tokens": 4158536} {"current_steps": 46185, "total_steps": 76960, "loss": 0.1746, "lr": 2.0649862300761833e-05, "epoch": 12.002338877338877, "percentage": 60.01, "elapsed_time": "1:07:14", "remaining_time": "0:44:48", "throughput": 1030.86, "total_tokens": 4158968} {"current_steps": 46190, "total_steps": 76960, "loss": 0.2245, "lr": 2.064427930556038e-05, "epoch": 12.003638253638254, "percentage": 60.02, "elapsed_time": "1:07:14", "remaining_time": "0:44:47", "throughput": 1030.86, "total_tokens": 4159416} {"current_steps": 46195, "total_steps": 76960, "loss": 0.3747, "lr": 2.063869653437781e-05, "epoch": 12.00493762993763, "percentage": 60.02, "elapsed_time": "1:07:15", "remaining_time": "0:44:47", "throughput": 1030.86, "total_tokens": 4159848} {"current_steps": 46200, "total_steps": 76960, "loss": 0.3108, "lr": 2.063311398750127e-05, "epoch": 12.006237006237006, "percentage": 60.03, "elapsed_time": "1:07:15", "remaining_time": "0:44:47", "throughput": 1030.86, "total_tokens": 4160280} {"current_steps": 46205, "total_steps": 76960, "loss": 0.2724, "lr": 2.0627531665217844e-05, "epoch": 12.007536382536383, "percentage": 60.04, "elapsed_time": "1:07:16", "remaining_time": "0:44:46", "throughput": 1030.87, "total_tokens": 4160744} {"current_steps": 46210, "total_steps": 76960, "loss": 0.2015, "lr": 2.0621949567814663e-05, "epoch": 12.008835758835758, "percentage": 60.04, "elapsed_time": "1:07:16", "remaining_time": "0:44:46", "throughput": 1030.86, "total_tokens": 4161192} {"current_steps": 46215, "total_steps": 76960, "loss": 0.2151, "lr": 2.061636769557881e-05, "epoch": 12.010135135135135, "percentage": 60.05, "elapsed_time": "1:07:17", "remaining_time": "0:44:45", "throughput": 1030.87, "total_tokens": 4161640} {"current_steps": 46220, "total_steps": 76960, "loss": 0.3001, "lr": 2.061078604879737e-05, "epoch": 12.011434511434512, "percentage": 60.06, "elapsed_time": "1:07:17", "remaining_time": "0:44:45", "throughput": 1030.88, "total_tokens": 4162104} {"current_steps": 46225, "total_steps": 76960, "loss": 0.1857, "lr": 2.0605204627757403e-05, "epoch": 12.012733887733887, "percentage": 60.06, "elapsed_time": "1:07:17", "remaining_time": "0:44:44", "throughput": 1030.88, "total_tokens": 4162536} {"current_steps": 46230, "total_steps": 76960, "loss": 0.4462, "lr": 2.0599623432745976e-05, "epoch": 12.014033264033264, "percentage": 60.07, "elapsed_time": "1:07:18", "remaining_time": "0:44:44", "throughput": 1030.89, "total_tokens": 4163000} {"current_steps": 46235, "total_steps": 76960, "loss": 0.2057, "lr": 2.059404246405013e-05, "epoch": 12.015332640332641, "percentage": 60.08, "elapsed_time": "1:07:18", "remaining_time": "0:44:43", "throughput": 1030.89, "total_tokens": 4163464} {"current_steps": 46240, "total_steps": 76960, "loss": 0.4208, "lr": 2.058846172195691e-05, "epoch": 12.016632016632016, "percentage": 60.08, "elapsed_time": "1:07:19", "remaining_time": "0:44:43", "throughput": 1030.9, "total_tokens": 4163912} {"current_steps": 46245, "total_steps": 76960, "loss": 0.1011, "lr": 2.0582881206753323e-05, "epoch": 12.017931392931393, "percentage": 60.09, "elapsed_time": "1:07:19", "remaining_time": "0:44:42", "throughput": 1030.9, "total_tokens": 4164344} {"current_steps": 46250, "total_steps": 76960, "loss": 0.2519, "lr": 2.0577300918726382e-05, "epoch": 12.01923076923077, "percentage": 60.1, "elapsed_time": "1:07:19", "remaining_time": "0:44:42", "throughput": 1030.9, "total_tokens": 4164776} {"current_steps": 46255, "total_steps": 76960, "loss": 0.191, "lr": 2.0571720858163105e-05, "epoch": 12.020530145530145, "percentage": 60.1, "elapsed_time": "1:07:20", "remaining_time": "0:44:42", "throughput": 1030.9, "total_tokens": 4165224} {"current_steps": 46260, "total_steps": 76960, "loss": 0.2391, "lr": 2.056614102535046e-05, "epoch": 12.021829521829522, "percentage": 60.11, "elapsed_time": "1:07:20", "remaining_time": "0:44:41", "throughput": 1030.91, "total_tokens": 4165672} {"current_steps": 46265, "total_steps": 76960, "loss": 0.25, "lr": 2.0560561420575434e-05, "epoch": 12.023128898128897, "percentage": 60.12, "elapsed_time": "1:07:21", "remaining_time": "0:44:41", "throughput": 1030.92, "total_tokens": 4166136} {"current_steps": 46270, "total_steps": 76960, "loss": 0.1578, "lr": 2.055498204412498e-05, "epoch": 12.024428274428274, "percentage": 60.12, "elapsed_time": "1:07:21", "remaining_time": "0:44:40", "throughput": 1030.93, "total_tokens": 4166600} {"current_steps": 46275, "total_steps": 76960, "loss": 0.1297, "lr": 2.0549402896286072e-05, "epoch": 12.025727650727651, "percentage": 60.13, "elapsed_time": "1:07:22", "remaining_time": "0:44:40", "throughput": 1030.93, "total_tokens": 4167048} {"current_steps": 46280, "total_steps": 76960, "loss": 0.2984, "lr": 2.0543823977345626e-05, "epoch": 12.027027027027026, "percentage": 60.14, "elapsed_time": "1:07:22", "remaining_time": "0:44:39", "throughput": 1030.93, "total_tokens": 4167480} {"current_steps": 46285, "total_steps": 76960, "loss": 0.2256, "lr": 2.0538245287590585e-05, "epoch": 12.028326403326403, "percentage": 60.14, "elapsed_time": "1:07:22", "remaining_time": "0:44:39", "throughput": 1030.93, "total_tokens": 4167928} {"current_steps": 46290, "total_steps": 76960, "loss": 0.1993, "lr": 2.0532666827307862e-05, "epoch": 12.02962577962578, "percentage": 60.15, "elapsed_time": "1:07:23", "remaining_time": "0:44:38", "throughput": 1030.96, "total_tokens": 4168456} {"current_steps": 46295, "total_steps": 76960, "loss": 0.1234, "lr": 2.0527088596784374e-05, "epoch": 12.030925155925155, "percentage": 60.15, "elapsed_time": "1:07:23", "remaining_time": "0:44:38", "throughput": 1030.95, "total_tokens": 4168856} {"current_steps": 46300, "total_steps": 76960, "loss": 0.1265, "lr": 2.0521510596306994e-05, "epoch": 12.032224532224532, "percentage": 60.16, "elapsed_time": "1:07:24", "remaining_time": "0:44:38", "throughput": 1030.95, "total_tokens": 4169304} {"current_steps": 46305, "total_steps": 76960, "loss": 0.3331, "lr": 2.051593282616262e-05, "epoch": 12.03352390852391, "percentage": 60.17, "elapsed_time": "1:07:24", "remaining_time": "0:44:37", "throughput": 1030.95, "total_tokens": 4169720} {"current_steps": 46310, "total_steps": 76960, "loss": 0.1153, "lr": 2.0510355286638124e-05, "epoch": 12.034823284823284, "percentage": 60.17, "elapsed_time": "1:07:24", "remaining_time": "0:44:37", "throughput": 1030.95, "total_tokens": 4170168} {"current_steps": 46315, "total_steps": 76960, "loss": 0.3041, "lr": 2.0504777978020346e-05, "epoch": 12.036122661122661, "percentage": 60.18, "elapsed_time": "1:07:25", "remaining_time": "0:44:36", "throughput": 1030.95, "total_tokens": 4170616} {"current_steps": 46320, "total_steps": 76960, "loss": 0.1744, "lr": 2.0499200900596148e-05, "epoch": 12.037422037422038, "percentage": 60.19, "elapsed_time": "1:07:25", "remaining_time": "0:44:36", "throughput": 1030.94, "total_tokens": 4171016} {"current_steps": 46325, "total_steps": 76960, "loss": 0.2806, "lr": 2.0493624054652357e-05, "epoch": 12.038721413721413, "percentage": 60.19, "elapsed_time": "1:07:26", "remaining_time": "0:44:35", "throughput": 1030.95, "total_tokens": 4171464} {"current_steps": 46330, "total_steps": 76960, "loss": 0.0926, "lr": 2.048804744047581e-05, "epoch": 12.04002079002079, "percentage": 60.2, "elapsed_time": "1:07:26", "remaining_time": "0:44:35", "throughput": 1030.95, "total_tokens": 4171896} {"current_steps": 46335, "total_steps": 76960, "loss": 0.1034, "lr": 2.0482471058353292e-05, "epoch": 12.041320166320165, "percentage": 60.21, "elapsed_time": "1:07:27", "remaining_time": "0:44:34", "throughput": 1030.95, "total_tokens": 4172344} {"current_steps": 46340, "total_steps": 76960, "loss": 0.1332, "lr": 2.0476894908571626e-05, "epoch": 12.042619542619542, "percentage": 60.21, "elapsed_time": "1:07:27", "remaining_time": "0:44:34", "throughput": 1030.96, "total_tokens": 4172808} {"current_steps": 46345, "total_steps": 76960, "loss": 0.3275, "lr": 2.0471318991417578e-05, "epoch": 12.04391891891892, "percentage": 60.22, "elapsed_time": "1:07:27", "remaining_time": "0:44:34", "throughput": 1030.98, "total_tokens": 4173304} {"current_steps": 46350, "total_steps": 76960, "loss": 0.3394, "lr": 2.046574330717795e-05, "epoch": 12.045218295218294, "percentage": 60.23, "elapsed_time": "1:07:28", "remaining_time": "0:44:33", "throughput": 1030.98, "total_tokens": 4173768} {"current_steps": 46355, "total_steps": 76960, "loss": 0.2277, "lr": 2.0460167856139467e-05, "epoch": 12.046517671517671, "percentage": 60.23, "elapsed_time": "1:07:28", "remaining_time": "0:44:33", "throughput": 1030.98, "total_tokens": 4174184} {"current_steps": 46360, "total_steps": 76960, "loss": 0.2232, "lr": 2.0454592638588917e-05, "epoch": 12.047817047817048, "percentage": 60.24, "elapsed_time": "1:07:29", "remaining_time": "0:44:32", "throughput": 1030.98, "total_tokens": 4174616} {"current_steps": 46365, "total_steps": 76960, "loss": 0.1084, "lr": 2.0449017654813013e-05, "epoch": 12.049116424116423, "percentage": 60.25, "elapsed_time": "1:07:29", "remaining_time": "0:44:32", "throughput": 1031.0, "total_tokens": 4175112} {"current_steps": 46370, "total_steps": 76960, "loss": 0.6514, "lr": 2.04434429050985e-05, "epoch": 12.0504158004158, "percentage": 60.25, "elapsed_time": "1:07:30", "remaining_time": "0:44:31", "throughput": 1031.02, "total_tokens": 4175624} {"current_steps": 46375, "total_steps": 76960, "loss": 0.4479, "lr": 2.0437868389732086e-05, "epoch": 12.051715176715177, "percentage": 60.26, "elapsed_time": "1:07:30", "remaining_time": "0:44:31", "throughput": 1031.01, "total_tokens": 4176024} {"current_steps": 46380, "total_steps": 76960, "loss": 0.3399, "lr": 2.0432294109000463e-05, "epoch": 12.053014553014552, "percentage": 60.27, "elapsed_time": "1:07:30", "remaining_time": "0:44:30", "throughput": 1031.02, "total_tokens": 4176488} {"current_steps": 46385, "total_steps": 76960, "loss": 0.363, "lr": 2.0426720063190335e-05, "epoch": 12.05431392931393, "percentage": 60.27, "elapsed_time": "1:07:31", "remaining_time": "0:44:30", "throughput": 1031.02, "total_tokens": 4176936} {"current_steps": 46390, "total_steps": 76960, "loss": 0.1392, "lr": 2.0421146252588375e-05, "epoch": 12.055613305613306, "percentage": 60.28, "elapsed_time": "1:07:31", "remaining_time": "0:44:29", "throughput": 1031.03, "total_tokens": 4177384} {"current_steps": 46395, "total_steps": 76960, "loss": 0.2871, "lr": 2.0415572677481252e-05, "epoch": 12.056912681912682, "percentage": 60.28, "elapsed_time": "1:07:32", "remaining_time": "0:44:29", "throughput": 1031.03, "total_tokens": 4177832} {"current_steps": 46400, "total_steps": 76960, "loss": 0.0905, "lr": 2.0409999338155617e-05, "epoch": 12.058212058212058, "percentage": 60.29, "elapsed_time": "1:07:32", "remaining_time": "0:44:29", "throughput": 1031.03, "total_tokens": 4178264} {"current_steps": 46405, "total_steps": 76960, "loss": 0.1198, "lr": 2.0404426234898115e-05, "epoch": 12.059511434511435, "percentage": 60.3, "elapsed_time": "1:07:32", "remaining_time": "0:44:28", "throughput": 1031.04, "total_tokens": 4178744} {"current_steps": 46410, "total_steps": 76960, "loss": 0.2213, "lr": 2.039885336799537e-05, "epoch": 12.06081081081081, "percentage": 60.3, "elapsed_time": "1:07:33", "remaining_time": "0:44:28", "throughput": 1031.05, "total_tokens": 4179208} {"current_steps": 46415, "total_steps": 76960, "loss": 0.1911, "lr": 2.0393280737734017e-05, "epoch": 12.062110187110187, "percentage": 60.31, "elapsed_time": "1:07:33", "remaining_time": "0:44:27", "throughput": 1031.07, "total_tokens": 4179688} {"current_steps": 46420, "total_steps": 76960, "loss": 0.0583, "lr": 2.038770834440064e-05, "epoch": 12.063409563409563, "percentage": 60.32, "elapsed_time": "1:07:34", "remaining_time": "0:44:27", "throughput": 1031.06, "total_tokens": 4180104} {"current_steps": 46425, "total_steps": 76960, "loss": 0.1874, "lr": 2.0382136188281846e-05, "epoch": 12.06470893970894, "percentage": 60.32, "elapsed_time": "1:07:34", "remaining_time": "0:44:26", "throughput": 1031.06, "total_tokens": 4180536} {"current_steps": 46430, "total_steps": 76960, "loss": 0.3825, "lr": 2.0376564269664207e-05, "epoch": 12.066008316008316, "percentage": 60.33, "elapsed_time": "1:07:35", "remaining_time": "0:44:26", "throughput": 1031.07, "total_tokens": 4181000} {"current_steps": 46435, "total_steps": 76960, "loss": 0.1474, "lr": 2.0370992588834306e-05, "epoch": 12.067307692307692, "percentage": 60.34, "elapsed_time": "1:07:35", "remaining_time": "0:44:25", "throughput": 1031.08, "total_tokens": 4181448} {"current_steps": 46440, "total_steps": 76960, "loss": 0.2473, "lr": 2.036542114607869e-05, "epoch": 12.068607068607069, "percentage": 60.34, "elapsed_time": "1:07:35", "remaining_time": "0:44:25", "throughput": 1031.09, "total_tokens": 4181912} {"current_steps": 46445, "total_steps": 76960, "loss": 0.1845, "lr": 2.0359849941683894e-05, "epoch": 12.069906444906445, "percentage": 60.35, "elapsed_time": "1:07:36", "remaining_time": "0:44:25", "throughput": 1031.09, "total_tokens": 4182344} {"current_steps": 46450, "total_steps": 76960, "loss": 0.265, "lr": 2.0354278975936477e-05, "epoch": 12.07120582120582, "percentage": 60.36, "elapsed_time": "1:07:36", "remaining_time": "0:44:24", "throughput": 1031.09, "total_tokens": 4182792} {"current_steps": 46455, "total_steps": 76960, "loss": 0.3344, "lr": 2.0348708249122933e-05, "epoch": 12.072505197505198, "percentage": 60.36, "elapsed_time": "1:07:37", "remaining_time": "0:44:24", "throughput": 1031.1, "total_tokens": 4183240} {"current_steps": 46460, "total_steps": 76960, "loss": 0.2507, "lr": 2.0343137761529785e-05, "epoch": 12.073804573804575, "percentage": 60.37, "elapsed_time": "1:07:37", "remaining_time": "0:44:23", "throughput": 1031.11, "total_tokens": 4183720} {"current_steps": 46465, "total_steps": 76960, "loss": 0.311, "lr": 2.033756751344352e-05, "epoch": 12.07510395010395, "percentage": 60.38, "elapsed_time": "1:07:37", "remaining_time": "0:44:23", "throughput": 1031.11, "total_tokens": 4184168} {"current_steps": 46470, "total_steps": 76960, "loss": 0.3792, "lr": 2.0331997505150632e-05, "epoch": 12.076403326403327, "percentage": 60.38, "elapsed_time": "1:07:38", "remaining_time": "0:44:22", "throughput": 1031.11, "total_tokens": 4184600} {"current_steps": 46475, "total_steps": 76960, "loss": 0.1529, "lr": 2.0326427736937576e-05, "epoch": 12.077702702702704, "percentage": 60.39, "elapsed_time": "1:07:38", "remaining_time": "0:44:22", "throughput": 1031.11, "total_tokens": 4185016} {"current_steps": 46480, "total_steps": 76960, "loss": 0.3086, "lr": 2.0320858209090827e-05, "epoch": 12.079002079002079, "percentage": 60.4, "elapsed_time": "1:07:39", "remaining_time": "0:44:21", "throughput": 1031.11, "total_tokens": 4185464} {"current_steps": 46485, "total_steps": 76960, "loss": 0.0843, "lr": 2.0315288921896815e-05, "epoch": 12.080301455301456, "percentage": 60.4, "elapsed_time": "1:07:39", "remaining_time": "0:44:21", "throughput": 1031.12, "total_tokens": 4185912} {"current_steps": 46490, "total_steps": 76960, "loss": 0.128, "lr": 2.0309719875641995e-05, "epoch": 12.08160083160083, "percentage": 60.41, "elapsed_time": "1:07:39", "remaining_time": "0:44:20", "throughput": 1031.13, "total_tokens": 4186376} {"current_steps": 46495, "total_steps": 76960, "loss": 0.178, "lr": 2.0304151070612763e-05, "epoch": 12.082900207900208, "percentage": 60.41, "elapsed_time": "1:07:40", "remaining_time": "0:44:20", "throughput": 1031.13, "total_tokens": 4186824} {"current_steps": 46500, "total_steps": 76960, "loss": 0.3249, "lr": 2.029858250709555e-05, "epoch": 12.084199584199585, "percentage": 60.42, "elapsed_time": "1:07:40", "remaining_time": "0:44:20", "throughput": 1031.14, "total_tokens": 4187304} {"current_steps": 46505, "total_steps": 76960, "loss": 0.0652, "lr": 2.0293014185376747e-05, "epoch": 12.08549896049896, "percentage": 60.43, "elapsed_time": "1:07:41", "remaining_time": "0:44:19", "throughput": 1031.15, "total_tokens": 4187768} {"current_steps": 46510, "total_steps": 76960, "loss": 0.0476, "lr": 2.0287446105742723e-05, "epoch": 12.086798336798337, "percentage": 60.43, "elapsed_time": "1:07:41", "remaining_time": "0:44:19", "throughput": 1031.16, "total_tokens": 4188232} {"current_steps": 46515, "total_steps": 76960, "loss": 0.1659, "lr": 2.0281878268479865e-05, "epoch": 12.088097713097714, "percentage": 60.44, "elapsed_time": "1:07:42", "remaining_time": "0:44:18", "throughput": 1031.17, "total_tokens": 4188696} {"current_steps": 46520, "total_steps": 76960, "loss": 0.2385, "lr": 2.0276310673874525e-05, "epoch": 12.089397089397089, "percentage": 60.45, "elapsed_time": "1:07:42", "remaining_time": "0:44:18", "throughput": 1031.18, "total_tokens": 4189160} {"current_steps": 46525, "total_steps": 76960, "loss": 0.4437, "lr": 2.027074332221306e-05, "epoch": 12.090696465696466, "percentage": 60.45, "elapsed_time": "1:07:42", "remaining_time": "0:44:17", "throughput": 1031.19, "total_tokens": 4189624} {"current_steps": 46530, "total_steps": 76960, "loss": 0.2597, "lr": 2.0265176213781793e-05, "epoch": 12.091995841995843, "percentage": 60.46, "elapsed_time": "1:07:43", "remaining_time": "0:44:17", "throughput": 1031.19, "total_tokens": 4190072} {"current_steps": 46535, "total_steps": 76960, "loss": 0.26, "lr": 2.0259609348867053e-05, "epoch": 12.093295218295218, "percentage": 60.47, "elapsed_time": "1:07:43", "remaining_time": "0:44:16", "throughput": 1031.19, "total_tokens": 4190488} {"current_steps": 46540, "total_steps": 76960, "loss": 0.1595, "lr": 2.025404272775514e-05, "epoch": 12.094594594594595, "percentage": 60.47, "elapsed_time": "1:07:44", "remaining_time": "0:44:16", "throughput": 1031.19, "total_tokens": 4190936} {"current_steps": 46545, "total_steps": 76960, "loss": 0.4296, "lr": 2.0248476350732368e-05, "epoch": 12.095893970893972, "percentage": 60.48, "elapsed_time": "1:07:44", "remaining_time": "0:44:16", "throughput": 1031.2, "total_tokens": 4191384} {"current_steps": 46550, "total_steps": 76960, "loss": 0.2024, "lr": 2.0242910218085e-05, "epoch": 12.097193347193347, "percentage": 60.49, "elapsed_time": "1:07:44", "remaining_time": "0:44:15", "throughput": 1031.19, "total_tokens": 4191800} {"current_steps": 46555, "total_steps": 76960, "loss": 0.2014, "lr": 2.023734433009932e-05, "epoch": 12.098492723492724, "percentage": 60.49, "elapsed_time": "1:07:45", "remaining_time": "0:44:15", "throughput": 1031.19, "total_tokens": 4192232} {"current_steps": 46560, "total_steps": 76960, "loss": 0.3091, "lr": 2.023177868706158e-05, "epoch": 12.0997920997921, "percentage": 60.5, "elapsed_time": "1:07:45", "remaining_time": "0:44:14", "throughput": 1031.19, "total_tokens": 4192664} {"current_steps": 46565, "total_steps": 76960, "loss": 0.491, "lr": 2.0226213289258043e-05, "epoch": 12.101091476091476, "percentage": 60.51, "elapsed_time": "1:07:46", "remaining_time": "0:44:14", "throughput": 1031.19, "total_tokens": 4193096} {"current_steps": 46570, "total_steps": 76960, "loss": 0.2483, "lr": 2.0220648136974927e-05, "epoch": 12.102390852390853, "percentage": 60.51, "elapsed_time": "1:07:46", "remaining_time": "0:44:13", "throughput": 1031.19, "total_tokens": 4193528} {"current_steps": 46575, "total_steps": 76960, "loss": 0.2245, "lr": 2.021508323049845e-05, "epoch": 12.103690228690228, "percentage": 60.52, "elapsed_time": "1:07:47", "remaining_time": "0:44:13", "throughput": 1031.2, "total_tokens": 4193976} {"current_steps": 46580, "total_steps": 76960, "loss": 0.2246, "lr": 2.0209518570114837e-05, "epoch": 12.104989604989605, "percentage": 60.52, "elapsed_time": "1:07:47", "remaining_time": "0:44:12", "throughput": 1031.2, "total_tokens": 4194408} {"current_steps": 46585, "total_steps": 76960, "loss": 0.0397, "lr": 2.0203954156110262e-05, "epoch": 12.106288981288982, "percentage": 60.53, "elapsed_time": "1:07:47", "remaining_time": "0:44:12", "throughput": 1031.21, "total_tokens": 4194872} {"current_steps": 46590, "total_steps": 76960, "loss": 0.1719, "lr": 2.0198389988770927e-05, "epoch": 12.107588357588357, "percentage": 60.54, "elapsed_time": "1:07:48", "remaining_time": "0:44:11", "throughput": 1031.21, "total_tokens": 4195304} {"current_steps": 46595, "total_steps": 76960, "loss": 0.5185, "lr": 2.0192826068382988e-05, "epoch": 12.108887733887734, "percentage": 60.54, "elapsed_time": "1:07:48", "remaining_time": "0:44:11", "throughput": 1031.21, "total_tokens": 4195736} {"current_steps": 46600, "total_steps": 76960, "loss": 0.2937, "lr": 2.0187262395232622e-05, "epoch": 12.11018711018711, "percentage": 60.55, "elapsed_time": "1:07:49", "remaining_time": "0:44:11", "throughput": 1031.21, "total_tokens": 4196168} {"current_steps": 46605, "total_steps": 76960, "loss": 0.2187, "lr": 2.018169896960595e-05, "epoch": 12.111486486486486, "percentage": 60.56, "elapsed_time": "1:07:49", "remaining_time": "0:44:10", "throughput": 1031.21, "total_tokens": 4196584} {"current_steps": 46610, "total_steps": 76960, "loss": 0.3754, "lr": 2.0176135791789127e-05, "epoch": 12.112785862785863, "percentage": 60.56, "elapsed_time": "1:07:49", "remaining_time": "0:44:10", "throughput": 1031.21, "total_tokens": 4197032} {"current_steps": 46615, "total_steps": 76960, "loss": 0.2451, "lr": 2.0170572862068253e-05, "epoch": 12.11408523908524, "percentage": 60.57, "elapsed_time": "1:07:50", "remaining_time": "0:44:09", "throughput": 1031.23, "total_tokens": 4197544} {"current_steps": 46620, "total_steps": 76960, "loss": 0.2692, "lr": 2.0165010180729453e-05, "epoch": 12.115384615384615, "percentage": 60.58, "elapsed_time": "1:07:50", "remaining_time": "0:44:09", "throughput": 1031.24, "total_tokens": 4198008} {"current_steps": 46625, "total_steps": 76960, "loss": 0.0855, "lr": 2.0159447748058805e-05, "epoch": 12.116683991683992, "percentage": 60.58, "elapsed_time": "1:07:51", "remaining_time": "0:44:08", "throughput": 1031.24, "total_tokens": 4198440} {"current_steps": 46630, "total_steps": 76960, "loss": 0.4258, "lr": 2.0153885564342405e-05, "epoch": 12.117983367983369, "percentage": 60.59, "elapsed_time": "1:07:51", "remaining_time": "0:44:08", "throughput": 1031.25, "total_tokens": 4198888} {"current_steps": 46635, "total_steps": 76960, "loss": 0.2077, "lr": 2.0148323629866315e-05, "epoch": 12.119282744282744, "percentage": 60.6, "elapsed_time": "1:07:52", "remaining_time": "0:44:07", "throughput": 1031.25, "total_tokens": 4199336} {"current_steps": 46640, "total_steps": 76960, "loss": 0.2663, "lr": 2.0142761944916576e-05, "epoch": 12.120582120582121, "percentage": 60.6, "elapsed_time": "1:07:52", "remaining_time": "0:44:07", "throughput": 1031.25, "total_tokens": 4199752} {"current_steps": 46645, "total_steps": 76960, "loss": 0.2943, "lr": 2.0137200509779262e-05, "epoch": 12.121881496881496, "percentage": 60.61, "elapsed_time": "1:07:52", "remaining_time": "0:44:07", "throughput": 1031.25, "total_tokens": 4200200} {"current_steps": 46650, "total_steps": 76960, "loss": 0.3241, "lr": 2.013163932474037e-05, "epoch": 12.123180873180873, "percentage": 60.62, "elapsed_time": "1:07:53", "remaining_time": "0:44:06", "throughput": 1031.26, "total_tokens": 4200648} {"current_steps": 46655, "total_steps": 76960, "loss": 0.1673, "lr": 2.012607839008594e-05, "epoch": 12.12448024948025, "percentage": 60.62, "elapsed_time": "1:07:53", "remaining_time": "0:44:06", "throughput": 1031.26, "total_tokens": 4201096} {"current_steps": 46660, "total_steps": 76960, "loss": 0.1355, "lr": 2.012051770610196e-05, "epoch": 12.125779625779625, "percentage": 60.63, "elapsed_time": "1:07:54", "remaining_time": "0:44:05", "throughput": 1031.27, "total_tokens": 4201544} {"current_steps": 46665, "total_steps": 76960, "loss": 0.2333, "lr": 2.0114957273074442e-05, "epoch": 12.127079002079002, "percentage": 60.64, "elapsed_time": "1:07:54", "remaining_time": "0:44:05", "throughput": 1031.27, "total_tokens": 4201976} {"current_steps": 46670, "total_steps": 76960, "loss": 0.3311, "lr": 2.010939709128934e-05, "epoch": 12.128378378378379, "percentage": 60.64, "elapsed_time": "1:07:54", "remaining_time": "0:44:04", "throughput": 1031.27, "total_tokens": 4202408} {"current_steps": 46675, "total_steps": 76960, "loss": 0.4093, "lr": 2.010383716103264e-05, "epoch": 12.129677754677754, "percentage": 60.65, "elapsed_time": "1:07:55", "remaining_time": "0:44:04", "throughput": 1031.27, "total_tokens": 4202856} {"current_steps": 46680, "total_steps": 76960, "loss": 0.0745, "lr": 2.009827748259028e-05, "epoch": 12.130977130977131, "percentage": 60.65, "elapsed_time": "1:07:55", "remaining_time": "0:44:03", "throughput": 1031.28, "total_tokens": 4203320} {"current_steps": 46685, "total_steps": 76960, "loss": 0.1302, "lr": 2.0092718056248216e-05, "epoch": 12.132276507276508, "percentage": 60.66, "elapsed_time": "1:07:56", "remaining_time": "0:44:03", "throughput": 1031.28, "total_tokens": 4203752} {"current_steps": 46690, "total_steps": 76960, "loss": 0.1724, "lr": 2.0087158882292352e-05, "epoch": 12.133575883575883, "percentage": 60.67, "elapsed_time": "1:07:56", "remaining_time": "0:44:02", "throughput": 1031.3, "total_tokens": 4204248} {"current_steps": 46695, "total_steps": 76960, "loss": 0.0359, "lr": 2.008159996100862e-05, "epoch": 12.13487525987526, "percentage": 60.67, "elapsed_time": "1:07:57", "remaining_time": "0:44:02", "throughput": 1031.3, "total_tokens": 4204696} {"current_steps": 46700, "total_steps": 76960, "loss": 0.2191, "lr": 2.0076041292682922e-05, "epoch": 12.136174636174637, "percentage": 60.68, "elapsed_time": "1:07:57", "remaining_time": "0:44:02", "throughput": 1031.3, "total_tokens": 4205128} {"current_steps": 46705, "total_steps": 76960, "loss": 0.3094, "lr": 2.0070482877601127e-05, "epoch": 12.137474012474012, "percentage": 60.69, "elapsed_time": "1:07:57", "remaining_time": "0:44:01", "throughput": 1031.3, "total_tokens": 4205544} {"current_steps": 46710, "total_steps": 76960, "loss": 0.3245, "lr": 2.0064924716049125e-05, "epoch": 12.138773388773389, "percentage": 60.69, "elapsed_time": "1:07:58", "remaining_time": "0:44:01", "throughput": 1031.3, "total_tokens": 4205992} {"current_steps": 46715, "total_steps": 76960, "loss": 0.2651, "lr": 2.0059366808312764e-05, "epoch": 12.140072765072764, "percentage": 60.7, "elapsed_time": "1:07:58", "remaining_time": "0:44:00", "throughput": 1031.31, "total_tokens": 4206440} {"current_steps": 46720, "total_steps": 76960, "loss": 0.3682, "lr": 2.005380915467792e-05, "epoch": 12.141372141372141, "percentage": 60.71, "elapsed_time": "1:07:59", "remaining_time": "0:44:00", "throughput": 1031.3, "total_tokens": 4206856} {"current_steps": 46725, "total_steps": 76960, "loss": 0.1524, "lr": 2.0048251755430398e-05, "epoch": 12.142671517671518, "percentage": 60.71, "elapsed_time": "1:07:59", "remaining_time": "0:43:59", "throughput": 1031.31, "total_tokens": 4207304} {"current_steps": 46730, "total_steps": 76960, "loss": 0.4712, "lr": 2.0042694610856032e-05, "epoch": 12.143970893970893, "percentage": 60.72, "elapsed_time": "1:07:59", "remaining_time": "0:43:59", "throughput": 1031.31, "total_tokens": 4207752} {"current_steps": 46735, "total_steps": 76960, "loss": 0.1531, "lr": 2.0037137721240633e-05, "epoch": 12.14527027027027, "percentage": 60.73, "elapsed_time": "1:08:00", "remaining_time": "0:43:58", "throughput": 1031.32, "total_tokens": 4208200} {"current_steps": 46740, "total_steps": 76960, "loss": 0.329, "lr": 2.0031581086870006e-05, "epoch": 12.146569646569647, "percentage": 60.73, "elapsed_time": "1:08:00", "remaining_time": "0:43:58", "throughput": 1031.32, "total_tokens": 4208632} {"current_steps": 46745, "total_steps": 76960, "loss": 0.389, "lr": 2.002602470802991e-05, "epoch": 12.147869022869022, "percentage": 60.74, "elapsed_time": "1:08:01", "remaining_time": "0:43:58", "throughput": 1031.32, "total_tokens": 4209064} {"current_steps": 46750, "total_steps": 76960, "loss": 0.1901, "lr": 2.002046858500614e-05, "epoch": 12.1491683991684, "percentage": 60.75, "elapsed_time": "1:08:01", "remaining_time": "0:43:57", "throughput": 1031.32, "total_tokens": 4209496} {"current_steps": 46755, "total_steps": 76960, "loss": 0.1001, "lr": 2.0014912718084432e-05, "epoch": 12.150467775467776, "percentage": 60.75, "elapsed_time": "1:08:02", "remaining_time": "0:43:57", "throughput": 1031.32, "total_tokens": 4209928} {"current_steps": 46760, "total_steps": 76960, "loss": 0.2576, "lr": 2.0009357107550553e-05, "epoch": 12.151767151767151, "percentage": 60.76, "elapsed_time": "1:08:02", "remaining_time": "0:43:56", "throughput": 1031.33, "total_tokens": 4210392} {"current_steps": 46765, "total_steps": 76960, "loss": 0.1341, "lr": 2.0003801753690214e-05, "epoch": 12.153066528066528, "percentage": 60.77, "elapsed_time": "1:08:02", "remaining_time": "0:43:56", "throughput": 1031.33, "total_tokens": 4210808} {"current_steps": 46770, "total_steps": 76960, "loss": 0.0545, "lr": 1.999824665678913e-05, "epoch": 12.154365904365905, "percentage": 60.77, "elapsed_time": "1:08:03", "remaining_time": "0:43:55", "throughput": 1031.33, "total_tokens": 4211256} {"current_steps": 46775, "total_steps": 76960, "loss": 0.3399, "lr": 1.9992691817133024e-05, "epoch": 12.15566528066528, "percentage": 60.78, "elapsed_time": "1:08:03", "remaining_time": "0:43:55", "throughput": 1031.34, "total_tokens": 4211736} {"current_steps": 46780, "total_steps": 76960, "loss": 0.1544, "lr": 1.9987137235007565e-05, "epoch": 12.156964656964657, "percentage": 60.78, "elapsed_time": "1:08:04", "remaining_time": "0:43:54", "throughput": 1031.35, "total_tokens": 4212200} {"current_steps": 46785, "total_steps": 76960, "loss": 0.5723, "lr": 1.998158291069845e-05, "epoch": 12.158264033264032, "percentage": 60.79, "elapsed_time": "1:08:04", "remaining_time": "0:43:54", "throughput": 1031.36, "total_tokens": 4212648} {"current_steps": 46790, "total_steps": 76960, "loss": 0.1306, "lr": 1.9976028844491326e-05, "epoch": 12.15956340956341, "percentage": 60.8, "elapsed_time": "1:08:04", "remaining_time": "0:43:53", "throughput": 1031.36, "total_tokens": 4213080} {"current_steps": 46795, "total_steps": 76960, "loss": 0.1873, "lr": 1.9970475036671864e-05, "epoch": 12.160862785862786, "percentage": 60.8, "elapsed_time": "1:08:05", "remaining_time": "0:43:53", "throughput": 1031.36, "total_tokens": 4213512} {"current_steps": 46800, "total_steps": 76960, "loss": 0.408, "lr": 1.996492148752568e-05, "epoch": 12.162162162162161, "percentage": 60.81, "elapsed_time": "1:08:05", "remaining_time": "0:43:53", "throughput": 1031.36, "total_tokens": 4213960} {"current_steps": 46805, "total_steps": 76960, "loss": 0.1963, "lr": 1.995936819733841e-05, "epoch": 12.163461538461538, "percentage": 60.82, "elapsed_time": "1:08:06", "remaining_time": "0:43:52", "throughput": 1031.37, "total_tokens": 4214424} {"current_steps": 46810, "total_steps": 76960, "loss": 0.3705, "lr": 1.995381516639566e-05, "epoch": 12.164760914760915, "percentage": 60.82, "elapsed_time": "1:08:06", "remaining_time": "0:43:52", "throughput": 1031.39, "total_tokens": 4214920} {"current_steps": 46815, "total_steps": 76960, "loss": 0.3101, "lr": 1.994826239498304e-05, "epoch": 12.16606029106029, "percentage": 60.83, "elapsed_time": "1:08:07", "remaining_time": "0:43:51", "throughput": 1031.39, "total_tokens": 4215352} {"current_steps": 46820, "total_steps": 76960, "loss": 0.1337, "lr": 1.994270988338612e-05, "epoch": 12.167359667359667, "percentage": 60.84, "elapsed_time": "1:08:07", "remaining_time": "0:43:51", "throughput": 1031.39, "total_tokens": 4215800} {"current_steps": 46825, "total_steps": 76960, "loss": 0.4194, "lr": 1.993715763189048e-05, "epoch": 12.168659043659044, "percentage": 60.84, "elapsed_time": "1:08:07", "remaining_time": "0:43:50", "throughput": 1031.41, "total_tokens": 4216280} {"current_steps": 46830, "total_steps": 76960, "loss": 0.6489, "lr": 1.9931605640781676e-05, "epoch": 12.16995841995842, "percentage": 60.85, "elapsed_time": "1:08:08", "remaining_time": "0:43:50", "throughput": 1031.4, "total_tokens": 4216696} {"current_steps": 46835, "total_steps": 76960, "loss": 0.4903, "lr": 1.9926053910345242e-05, "epoch": 12.171257796257796, "percentage": 60.86, "elapsed_time": "1:08:08", "remaining_time": "0:43:49", "throughput": 1031.4, "total_tokens": 4217128} {"current_steps": 46840, "total_steps": 76960, "loss": 0.1911, "lr": 1.992050244086672e-05, "epoch": 12.172557172557173, "percentage": 60.86, "elapsed_time": "1:08:09", "remaining_time": "0:43:49", "throughput": 1031.41, "total_tokens": 4217592} {"current_steps": 46845, "total_steps": 76960, "loss": 0.1104, "lr": 1.991495123263162e-05, "epoch": 12.173856548856548, "percentage": 60.87, "elapsed_time": "1:08:09", "remaining_time": "0:43:49", "throughput": 1031.43, "total_tokens": 4218088} {"current_steps": 46850, "total_steps": 76960, "loss": 0.1876, "lr": 1.9909400285925464e-05, "epoch": 12.175155925155925, "percentage": 60.88, "elapsed_time": "1:08:09", "remaining_time": "0:43:48", "throughput": 1031.44, "total_tokens": 4218568} {"current_steps": 46855, "total_steps": 76960, "loss": 0.1449, "lr": 1.990384960103371e-05, "epoch": 12.176455301455302, "percentage": 60.88, "elapsed_time": "1:08:10", "remaining_time": "0:43:48", "throughput": 1031.44, "total_tokens": 4219000} {"current_steps": 46860, "total_steps": 76960, "loss": 0.1133, "lr": 1.9898299178241868e-05, "epoch": 12.177754677754677, "percentage": 60.89, "elapsed_time": "1:08:10", "remaining_time": "0:43:47", "throughput": 1031.45, "total_tokens": 4219448} {"current_steps": 46865, "total_steps": 76960, "loss": 0.2391, "lr": 1.9892749017835384e-05, "epoch": 12.179054054054054, "percentage": 60.9, "elapsed_time": "1:08:11", "remaining_time": "0:43:47", "throughput": 1031.46, "total_tokens": 4219928} {"current_steps": 46870, "total_steps": 76960, "loss": 0.2041, "lr": 1.988719912009971e-05, "epoch": 12.18035343035343, "percentage": 60.9, "elapsed_time": "1:08:11", "remaining_time": "0:43:46", "throughput": 1031.46, "total_tokens": 4220360} {"current_steps": 46875, "total_steps": 76960, "loss": 0.5748, "lr": 1.988164948532028e-05, "epoch": 12.181652806652806, "percentage": 60.91, "elapsed_time": "1:08:12", "remaining_time": "0:43:46", "throughput": 1031.47, "total_tokens": 4220824} {"current_steps": 46880, "total_steps": 76960, "loss": 0.2207, "lr": 1.9876100113782533e-05, "epoch": 12.182952182952183, "percentage": 60.91, "elapsed_time": "1:08:12", "remaining_time": "0:43:45", "throughput": 1031.47, "total_tokens": 4221256} {"current_steps": 46885, "total_steps": 76960, "loss": 0.1183, "lr": 1.9870551005771857e-05, "epoch": 12.184251559251559, "percentage": 60.92, "elapsed_time": "1:08:12", "remaining_time": "0:43:45", "throughput": 1031.48, "total_tokens": 4221736} {"current_steps": 46890, "total_steps": 76960, "loss": 0.388, "lr": 1.9865002161573658e-05, "epoch": 12.185550935550935, "percentage": 60.93, "elapsed_time": "1:08:13", "remaining_time": "0:43:44", "throughput": 1031.49, "total_tokens": 4222200} {"current_steps": 46895, "total_steps": 76960, "loss": 0.139, "lr": 1.985945358147333e-05, "epoch": 12.186850311850312, "percentage": 60.93, "elapsed_time": "1:08:13", "remaining_time": "0:43:44", "throughput": 1031.5, "total_tokens": 4222680} {"current_steps": 46900, "total_steps": 76960, "loss": 0.0904, "lr": 1.9853905265756215e-05, "epoch": 12.188149688149688, "percentage": 60.94, "elapsed_time": "1:08:14", "remaining_time": "0:43:44", "throughput": 1031.51, "total_tokens": 4223144} {"current_steps": 46905, "total_steps": 76960, "loss": 0.1978, "lr": 1.984835721470769e-05, "epoch": 12.189449064449065, "percentage": 60.95, "elapsed_time": "1:08:14", "remaining_time": "0:43:43", "throughput": 1031.52, "total_tokens": 4223592} {"current_steps": 46910, "total_steps": 76960, "loss": 0.181, "lr": 1.984280942861308e-05, "epoch": 12.190748440748441, "percentage": 60.95, "elapsed_time": "1:08:14", "remaining_time": "0:43:43", "throughput": 1031.52, "total_tokens": 4224040} {"current_steps": 46915, "total_steps": 76960, "loss": 0.4126, "lr": 1.983726190775774e-05, "epoch": 12.192047817047817, "percentage": 60.96, "elapsed_time": "1:08:15", "remaining_time": "0:43:42", "throughput": 1031.52, "total_tokens": 4224472} {"current_steps": 46920, "total_steps": 76960, "loss": 0.1304, "lr": 1.983171465242695e-05, "epoch": 12.193347193347194, "percentage": 60.97, "elapsed_time": "1:08:15", "remaining_time": "0:43:42", "throughput": 1031.53, "total_tokens": 4224936} {"current_steps": 46925, "total_steps": 76960, "loss": 0.3199, "lr": 1.9826167662906036e-05, "epoch": 12.19464656964657, "percentage": 60.97, "elapsed_time": "1:08:16", "remaining_time": "0:43:41", "throughput": 1031.53, "total_tokens": 4225384} {"current_steps": 46930, "total_steps": 76960, "loss": 0.4072, "lr": 1.9820620939480274e-05, "epoch": 12.195945945945946, "percentage": 60.98, "elapsed_time": "1:08:16", "remaining_time": "0:43:41", "throughput": 1031.54, "total_tokens": 4225848} {"current_steps": 46935, "total_steps": 76960, "loss": 0.3491, "lr": 1.9815074482434945e-05, "epoch": 12.197245322245323, "percentage": 60.99, "elapsed_time": "1:08:17", "remaining_time": "0:43:40", "throughput": 1031.54, "total_tokens": 4226264} {"current_steps": 46940, "total_steps": 76960, "loss": 0.2334, "lr": 1.9809528292055297e-05, "epoch": 12.198544698544698, "percentage": 60.99, "elapsed_time": "1:08:17", "remaining_time": "0:43:40", "throughput": 1031.54, "total_tokens": 4226712} {"current_steps": 46945, "total_steps": 76960, "loss": 0.2326, "lr": 1.9803982368626583e-05, "epoch": 12.199844074844075, "percentage": 61.0, "elapsed_time": "1:08:17", "remaining_time": "0:43:40", "throughput": 1031.54, "total_tokens": 4227144} {"current_steps": 46950, "total_steps": 76960, "loss": 0.1011, "lr": 1.9798436712434033e-05, "epoch": 12.201143451143452, "percentage": 61.01, "elapsed_time": "1:08:18", "remaining_time": "0:43:39", "throughput": 1031.54, "total_tokens": 4227576} {"current_steps": 46955, "total_steps": 76960, "loss": 0.1966, "lr": 1.9792891323762874e-05, "epoch": 12.202442827442827, "percentage": 61.01, "elapsed_time": "1:08:18", "remaining_time": "0:43:39", "throughput": 1031.55, "total_tokens": 4228040} {"current_steps": 46960, "total_steps": 76960, "loss": 0.1512, "lr": 1.9787346202898298e-05, "epoch": 12.203742203742204, "percentage": 61.02, "elapsed_time": "1:08:19", "remaining_time": "0:43:38", "throughput": 1031.57, "total_tokens": 4228520} {"current_steps": 46965, "total_steps": 76960, "loss": 0.1453, "lr": 1.9781801350125497e-05, "epoch": 12.20504158004158, "percentage": 61.03, "elapsed_time": "1:08:19", "remaining_time": "0:43:38", "throughput": 1031.57, "total_tokens": 4228968} {"current_steps": 46970, "total_steps": 76960, "loss": 0.5323, "lr": 1.977625676572967e-05, "epoch": 12.206340956340956, "percentage": 61.03, "elapsed_time": "1:08:19", "remaining_time": "0:43:37", "throughput": 1031.58, "total_tokens": 4229416} {"current_steps": 46975, "total_steps": 76960, "loss": 0.1591, "lr": 1.9770712449995943e-05, "epoch": 12.207640332640333, "percentage": 61.04, "elapsed_time": "1:08:20", "remaining_time": "0:43:37", "throughput": 1031.58, "total_tokens": 4229848} {"current_steps": 46980, "total_steps": 76960, "loss": 0.2001, "lr": 1.976516840320949e-05, "epoch": 12.20893970893971, "percentage": 61.04, "elapsed_time": "1:08:20", "remaining_time": "0:43:36", "throughput": 1031.59, "total_tokens": 4230312} {"current_steps": 46985, "total_steps": 76960, "loss": 0.1572, "lr": 1.975962462565544e-05, "epoch": 12.210239085239085, "percentage": 61.05, "elapsed_time": "1:08:21", "remaining_time": "0:43:36", "throughput": 1031.59, "total_tokens": 4230776} {"current_steps": 46990, "total_steps": 76960, "loss": 0.2356, "lr": 1.9754081117618926e-05, "epoch": 12.211538461538462, "percentage": 61.06, "elapsed_time": "1:08:21", "remaining_time": "0:43:35", "throughput": 1031.59, "total_tokens": 4231192} {"current_steps": 46995, "total_steps": 76960, "loss": 0.2126, "lr": 1.974853787938504e-05, "epoch": 12.212837837837839, "percentage": 61.06, "elapsed_time": "1:08:22", "remaining_time": "0:43:35", "throughput": 1031.59, "total_tokens": 4231624} {"current_steps": 47000, "total_steps": 76960, "loss": 0.2259, "lr": 1.9742994911238882e-05, "epoch": 12.214137214137214, "percentage": 61.07, "elapsed_time": "1:08:22", "remaining_time": "0:43:35", "throughput": 1031.6, "total_tokens": 4232088} {"current_steps": 47005, "total_steps": 76960, "loss": 0.1499, "lr": 1.973745221346553e-05, "epoch": 12.21543659043659, "percentage": 61.08, "elapsed_time": "1:08:22", "remaining_time": "0:43:34", "throughput": 1031.6, "total_tokens": 4232520} {"current_steps": 47010, "total_steps": 76960, "loss": 0.0878, "lr": 1.9731909786350068e-05, "epoch": 12.216735966735968, "percentage": 61.08, "elapsed_time": "1:08:23", "remaining_time": "0:43:34", "throughput": 1031.62, "total_tokens": 4233016} {"current_steps": 47015, "total_steps": 76960, "loss": 0.4069, "lr": 1.9726367630177518e-05, "epoch": 12.218035343035343, "percentage": 61.09, "elapsed_time": "1:08:23", "remaining_time": "0:43:33", "throughput": 1031.62, "total_tokens": 4233464} {"current_steps": 47020, "total_steps": 76960, "loss": 0.4537, "lr": 1.9720825745232937e-05, "epoch": 12.21933471933472, "percentage": 61.1, "elapsed_time": "1:08:24", "remaining_time": "0:43:33", "throughput": 1031.62, "total_tokens": 4233896} {"current_steps": 47025, "total_steps": 76960, "loss": 0.3005, "lr": 1.9715284131801353e-05, "epoch": 12.220634095634095, "percentage": 61.1, "elapsed_time": "1:08:24", "remaining_time": "0:43:32", "throughput": 1031.62, "total_tokens": 4234328} {"current_steps": 47030, "total_steps": 76960, "loss": 0.236, "lr": 1.9709742790167763e-05, "epoch": 12.221933471933472, "percentage": 61.11, "elapsed_time": "1:08:24", "remaining_time": "0:43:32", "throughput": 1031.63, "total_tokens": 4234760} {"current_steps": 47035, "total_steps": 76960, "loss": 0.2544, "lr": 1.9704201720617172e-05, "epoch": 12.223232848232849, "percentage": 61.12, "elapsed_time": "1:08:25", "remaining_time": "0:43:31", "throughput": 1031.63, "total_tokens": 4235192} {"current_steps": 47040, "total_steps": 76960, "loss": 0.0666, "lr": 1.9698660923434552e-05, "epoch": 12.224532224532224, "percentage": 61.12, "elapsed_time": "1:08:25", "remaining_time": "0:43:31", "throughput": 1031.64, "total_tokens": 4235672} {"current_steps": 47045, "total_steps": 76960, "loss": 0.0139, "lr": 1.9693120398904896e-05, "epoch": 12.2258316008316, "percentage": 61.13, "elapsed_time": "1:08:26", "remaining_time": "0:43:31", "throughput": 1031.64, "total_tokens": 4236104} {"current_steps": 47050, "total_steps": 76960, "loss": 0.1883, "lr": 1.9687580147313134e-05, "epoch": 12.227130977130978, "percentage": 61.14, "elapsed_time": "1:08:26", "remaining_time": "0:43:30", "throughput": 1031.65, "total_tokens": 4236568} {"current_steps": 47055, "total_steps": 76960, "loss": 0.5268, "lr": 1.9682040168944216e-05, "epoch": 12.228430353430353, "percentage": 61.14, "elapsed_time": "1:08:27", "remaining_time": "0:43:30", "throughput": 1031.64, "total_tokens": 4236984} {"current_steps": 47060, "total_steps": 76960, "loss": 0.2191, "lr": 1.9676500464083064e-05, "epoch": 12.22972972972973, "percentage": 61.15, "elapsed_time": "1:08:27", "remaining_time": "0:43:29", "throughput": 1031.65, "total_tokens": 4237432} {"current_steps": 47065, "total_steps": 76960, "loss": 0.634, "lr": 1.9670961033014605e-05, "epoch": 12.231029106029107, "percentage": 61.16, "elapsed_time": "1:08:27", "remaining_time": "0:43:29", "throughput": 1031.65, "total_tokens": 4237864} {"current_steps": 47070, "total_steps": 76960, "loss": 0.1836, "lr": 1.966542187602371e-05, "epoch": 12.232328482328482, "percentage": 61.16, "elapsed_time": "1:08:28", "remaining_time": "0:43:28", "throughput": 1031.65, "total_tokens": 4238280} {"current_steps": 47075, "total_steps": 76960, "loss": 0.208, "lr": 1.965988299339529e-05, "epoch": 12.233627858627859, "percentage": 61.17, "elapsed_time": "1:08:28", "remaining_time": "0:43:28", "throughput": 1031.65, "total_tokens": 4238728} {"current_steps": 47080, "total_steps": 76960, "loss": 0.3165, "lr": 1.96543443854142e-05, "epoch": 12.234927234927236, "percentage": 61.17, "elapsed_time": "1:08:29", "remaining_time": "0:43:27", "throughput": 1031.65, "total_tokens": 4239176} {"current_steps": 47085, "total_steps": 76960, "loss": 0.1471, "lr": 1.964880605236531e-05, "epoch": 12.236226611226611, "percentage": 61.18, "elapsed_time": "1:08:29", "remaining_time": "0:43:27", "throughput": 1031.66, "total_tokens": 4239640} {"current_steps": 47090, "total_steps": 76960, "loss": 0.3963, "lr": 1.9643267994533444e-05, "epoch": 12.237525987525988, "percentage": 61.19, "elapsed_time": "1:08:29", "remaining_time": "0:43:27", "throughput": 1031.67, "total_tokens": 4240088} {"current_steps": 47095, "total_steps": 76960, "loss": 0.3465, "lr": 1.9637730212203433e-05, "epoch": 12.238825363825363, "percentage": 61.19, "elapsed_time": "1:08:30", "remaining_time": "0:43:26", "throughput": 1031.68, "total_tokens": 4240568} {"current_steps": 47100, "total_steps": 76960, "loss": 0.1722, "lr": 1.963219270566011e-05, "epoch": 12.24012474012474, "percentage": 61.2, "elapsed_time": "1:08:30", "remaining_time": "0:43:26", "throughput": 1031.68, "total_tokens": 4241000} {"current_steps": 47105, "total_steps": 76960, "loss": 0.2218, "lr": 1.9626655475188238e-05, "epoch": 12.241424116424117, "percentage": 61.21, "elapsed_time": "1:08:31", "remaining_time": "0:43:25", "throughput": 1031.69, "total_tokens": 4241464} {"current_steps": 47110, "total_steps": 76960, "loss": 0.2762, "lr": 1.962111852107264e-05, "epoch": 12.242723492723492, "percentage": 61.21, "elapsed_time": "1:08:31", "remaining_time": "0:43:25", "throughput": 1031.7, "total_tokens": 4241928} {"current_steps": 47115, "total_steps": 76960, "loss": 0.3093, "lr": 1.961558184359806e-05, "epoch": 12.244022869022869, "percentage": 61.22, "elapsed_time": "1:08:32", "remaining_time": "0:43:24", "throughput": 1031.71, "total_tokens": 4242392} {"current_steps": 47120, "total_steps": 76960, "loss": 0.1592, "lr": 1.961004544304927e-05, "epoch": 12.245322245322246, "percentage": 61.23, "elapsed_time": "1:08:32", "remaining_time": "0:43:24", "throughput": 1031.71, "total_tokens": 4242840} {"current_steps": 47125, "total_steps": 76960, "loss": 0.2291, "lr": 1.9604509319711007e-05, "epoch": 12.246621621621621, "percentage": 61.23, "elapsed_time": "1:08:32", "remaining_time": "0:43:23", "throughput": 1031.72, "total_tokens": 4243288} {"current_steps": 47130, "total_steps": 76960, "loss": 0.1219, "lr": 1.9598973473868004e-05, "epoch": 12.247920997920998, "percentage": 61.24, "elapsed_time": "1:08:33", "remaining_time": "0:43:23", "throughput": 1031.71, "total_tokens": 4243704} {"current_steps": 47135, "total_steps": 76960, "loss": 0.383, "lr": 1.959343790580496e-05, "epoch": 12.249220374220375, "percentage": 61.25, "elapsed_time": "1:08:33", "remaining_time": "0:43:22", "throughput": 1031.72, "total_tokens": 4244168} {"current_steps": 47140, "total_steps": 76960, "loss": 0.1781, "lr": 1.9587902615806595e-05, "epoch": 12.25051975051975, "percentage": 61.25, "elapsed_time": "1:08:34", "remaining_time": "0:43:22", "throughput": 1031.72, "total_tokens": 4244584} {"current_steps": 47145, "total_steps": 76960, "loss": 0.4155, "lr": 1.9582367604157577e-05, "epoch": 12.251819126819127, "percentage": 61.26, "elapsed_time": "1:08:34", "remaining_time": "0:43:22", "throughput": 1031.71, "total_tokens": 4245000} {"current_steps": 47150, "total_steps": 76960, "loss": 0.3261, "lr": 1.957683287114259e-05, "epoch": 12.253118503118504, "percentage": 61.27, "elapsed_time": "1:08:34", "remaining_time": "0:43:21", "throughput": 1031.72, "total_tokens": 4245432} {"current_steps": 47155, "total_steps": 76960, "loss": 0.381, "lr": 1.957129841704628e-05, "epoch": 12.254417879417879, "percentage": 61.27, "elapsed_time": "1:08:35", "remaining_time": "0:43:21", "throughput": 1031.71, "total_tokens": 4245848} {"current_steps": 47160, "total_steps": 76960, "loss": 0.408, "lr": 1.9565764242153296e-05, "epoch": 12.255717255717256, "percentage": 61.28, "elapsed_time": "1:08:35", "remaining_time": "0:43:20", "throughput": 1031.71, "total_tokens": 4246264} {"current_steps": 47165, "total_steps": 76960, "loss": 0.1726, "lr": 1.9560230346748266e-05, "epoch": 12.257016632016631, "percentage": 61.29, "elapsed_time": "1:08:36", "remaining_time": "0:43:20", "throughput": 1031.72, "total_tokens": 4246744} {"current_steps": 47170, "total_steps": 76960, "loss": 0.2239, "lr": 1.9554696731115797e-05, "epoch": 12.258316008316008, "percentage": 61.29, "elapsed_time": "1:08:36", "remaining_time": "0:43:19", "throughput": 1031.74, "total_tokens": 4247224} {"current_steps": 47175, "total_steps": 76960, "loss": 0.2634, "lr": 1.9549163395540495e-05, "epoch": 12.259615384615385, "percentage": 61.3, "elapsed_time": "1:08:36", "remaining_time": "0:43:19", "throughput": 1031.73, "total_tokens": 4247640} {"current_steps": 47180, "total_steps": 76960, "loss": 0.2621, "lr": 1.9543630340306938e-05, "epoch": 12.26091476091476, "percentage": 61.3, "elapsed_time": "1:08:37", "remaining_time": "0:43:18", "throughput": 1031.73, "total_tokens": 4248072} {"current_steps": 47185, "total_steps": 76960, "loss": 0.3438, "lr": 1.953809756569971e-05, "epoch": 12.262214137214137, "percentage": 61.31, "elapsed_time": "1:08:37", "remaining_time": "0:43:18", "throughput": 1031.74, "total_tokens": 4248520} {"current_steps": 47190, "total_steps": 76960, "loss": 0.0714, "lr": 1.9532565072003348e-05, "epoch": 12.263513513513514, "percentage": 61.32, "elapsed_time": "1:08:38", "remaining_time": "0:43:18", "throughput": 1031.75, "total_tokens": 4248984} {"current_steps": 47195, "total_steps": 76960, "loss": 0.0975, "lr": 1.952703285950241e-05, "epoch": 12.26481288981289, "percentage": 61.32, "elapsed_time": "1:08:38", "remaining_time": "0:43:17", "throughput": 1031.76, "total_tokens": 4249448} {"current_steps": 47200, "total_steps": 76960, "loss": 0.3429, "lr": 1.9521500928481405e-05, "epoch": 12.266112266112266, "percentage": 61.33, "elapsed_time": "1:08:39", "remaining_time": "0:43:17", "throughput": 1031.75, "total_tokens": 4249864} {"current_steps": 47205, "total_steps": 76960, "loss": 0.4039, "lr": 1.951596927922487e-05, "epoch": 12.267411642411643, "percentage": 61.34, "elapsed_time": "1:08:39", "remaining_time": "0:43:16", "throughput": 1031.75, "total_tokens": 4250296} {"current_steps": 47210, "total_steps": 76960, "loss": 0.4376, "lr": 1.951043791201728e-05, "epoch": 12.268711018711018, "percentage": 61.34, "elapsed_time": "1:08:39", "remaining_time": "0:43:16", "throughput": 1031.76, "total_tokens": 4250744} {"current_steps": 47215, "total_steps": 76960, "loss": 0.3048, "lr": 1.9504906827143136e-05, "epoch": 12.270010395010395, "percentage": 61.35, "elapsed_time": "1:08:40", "remaining_time": "0:43:15", "throughput": 1031.75, "total_tokens": 4251160} {"current_steps": 47220, "total_steps": 76960, "loss": 0.2253, "lr": 1.9499376024886888e-05, "epoch": 12.271309771309772, "percentage": 61.36, "elapsed_time": "1:08:40", "remaining_time": "0:43:15", "throughput": 1031.75, "total_tokens": 4251576} {"current_steps": 47225, "total_steps": 76960, "loss": 0.1217, "lr": 1.9493845505533016e-05, "epoch": 12.272609147609147, "percentage": 61.36, "elapsed_time": "1:08:41", "remaining_time": "0:43:14", "throughput": 1031.76, "total_tokens": 4252040} {"current_steps": 47230, "total_steps": 76960, "loss": 0.2542, "lr": 1.948831526936594e-05, "epoch": 12.273908523908524, "percentage": 61.37, "elapsed_time": "1:08:41", "remaining_time": "0:43:14", "throughput": 1031.76, "total_tokens": 4252456} {"current_steps": 47235, "total_steps": 76960, "loss": 0.2187, "lr": 1.9482785316670082e-05, "epoch": 12.2752079002079, "percentage": 61.38, "elapsed_time": "1:08:41", "remaining_time": "0:43:13", "throughput": 1031.77, "total_tokens": 4252920} {"current_steps": 47240, "total_steps": 76960, "loss": 0.1408, "lr": 1.9477255647729873e-05, "epoch": 12.276507276507276, "percentage": 61.38, "elapsed_time": "1:08:42", "remaining_time": "0:43:13", "throughput": 1031.77, "total_tokens": 4253352} {"current_steps": 47245, "total_steps": 76960, "loss": 0.0877, "lr": 1.9471726262829688e-05, "epoch": 12.277806652806653, "percentage": 61.39, "elapsed_time": "1:08:42", "remaining_time": "0:43:13", "throughput": 1031.77, "total_tokens": 4253800} {"current_steps": 47250, "total_steps": 76960, "loss": 0.1572, "lr": 1.9466197162253927e-05, "epoch": 12.279106029106028, "percentage": 61.4, "elapsed_time": "1:08:43", "remaining_time": "0:43:12", "throughput": 1031.77, "total_tokens": 4254232} {"current_steps": 47255, "total_steps": 76960, "loss": 0.2979, "lr": 1.946066834628694e-05, "epoch": 12.280405405405405, "percentage": 61.4, "elapsed_time": "1:08:43", "remaining_time": "0:43:12", "throughput": 1031.78, "total_tokens": 4254680} {"current_steps": 47260, "total_steps": 76960, "loss": 0.3249, "lr": 1.9455139815213097e-05, "epoch": 12.281704781704782, "percentage": 61.41, "elapsed_time": "1:08:44", "remaining_time": "0:43:11", "throughput": 1031.78, "total_tokens": 4255144} {"current_steps": 47265, "total_steps": 76960, "loss": 0.403, "lr": 1.9449611569316717e-05, "epoch": 12.283004158004157, "percentage": 61.42, "elapsed_time": "1:08:44", "remaining_time": "0:43:11", "throughput": 1031.78, "total_tokens": 4255576} {"current_steps": 47270, "total_steps": 76960, "loss": 0.1609, "lr": 1.9444083608882135e-05, "epoch": 12.284303534303534, "percentage": 61.42, "elapsed_time": "1:08:44", "remaining_time": "0:43:10", "throughput": 1031.78, "total_tokens": 4256008} {"current_steps": 47275, "total_steps": 76960, "loss": 0.3321, "lr": 1.943855593419365e-05, "epoch": 12.285602910602911, "percentage": 61.43, "elapsed_time": "1:08:45", "remaining_time": "0:43:10", "throughput": 1031.78, "total_tokens": 4256440} {"current_steps": 47280, "total_steps": 76960, "loss": 0.09, "lr": 1.943302854553558e-05, "epoch": 12.286902286902286, "percentage": 61.43, "elapsed_time": "1:08:45", "remaining_time": "0:43:09", "throughput": 1031.78, "total_tokens": 4256872} {"current_steps": 47285, "total_steps": 76960, "loss": 0.3756, "lr": 1.942750144319217e-05, "epoch": 12.288201663201663, "percentage": 61.44, "elapsed_time": "1:08:46", "remaining_time": "0:43:09", "throughput": 1031.79, "total_tokens": 4257304} {"current_steps": 47290, "total_steps": 76960, "loss": 0.3148, "lr": 1.942197462744771e-05, "epoch": 12.28950103950104, "percentage": 61.45, "elapsed_time": "1:08:46", "remaining_time": "0:43:09", "throughput": 1031.8, "total_tokens": 4257784} {"current_steps": 47295, "total_steps": 76960, "loss": 0.0896, "lr": 1.9416448098586436e-05, "epoch": 12.290800415800415, "percentage": 61.45, "elapsed_time": "1:08:46", "remaining_time": "0:43:08", "throughput": 1031.81, "total_tokens": 4258248} {"current_steps": 47300, "total_steps": 76960, "loss": 0.1349, "lr": 1.9410921856892582e-05, "epoch": 12.292099792099792, "percentage": 61.46, "elapsed_time": "1:08:47", "remaining_time": "0:43:08", "throughput": 1031.81, "total_tokens": 4258680} {"current_steps": 47305, "total_steps": 76960, "loss": 0.1622, "lr": 1.940539590265038e-05, "epoch": 12.29339916839917, "percentage": 61.47, "elapsed_time": "1:08:47", "remaining_time": "0:43:07", "throughput": 1031.82, "total_tokens": 4259144} {"current_steps": 47310, "total_steps": 76960, "loss": 0.191, "lr": 1.9399870236144015e-05, "epoch": 12.294698544698544, "percentage": 61.47, "elapsed_time": "1:08:48", "remaining_time": "0:43:07", "throughput": 1031.83, "total_tokens": 4259608} {"current_steps": 47315, "total_steps": 76960, "loss": 0.2342, "lr": 1.9394344857657704e-05, "epoch": 12.295997920997921, "percentage": 61.48, "elapsed_time": "1:08:48", "remaining_time": "0:43:06", "throughput": 1031.83, "total_tokens": 4260056} {"current_steps": 47320, "total_steps": 76960, "loss": 0.1947, "lr": 1.9388819767475596e-05, "epoch": 12.297297297297296, "percentage": 61.49, "elapsed_time": "1:08:49", "remaining_time": "0:43:06", "throughput": 1031.84, "total_tokens": 4260520} {"current_steps": 47325, "total_steps": 76960, "loss": 0.2581, "lr": 1.938329496588187e-05, "epoch": 12.298596673596673, "percentage": 61.49, "elapsed_time": "1:08:49", "remaining_time": "0:43:05", "throughput": 1031.84, "total_tokens": 4260952} {"current_steps": 47330, "total_steps": 76960, "loss": 0.1484, "lr": 1.937777045316066e-05, "epoch": 12.29989604989605, "percentage": 61.5, "elapsed_time": "1:08:49", "remaining_time": "0:43:05", "throughput": 1031.84, "total_tokens": 4261384} {"current_steps": 47335, "total_steps": 76960, "loss": 0.2042, "lr": 1.9372246229596113e-05, "epoch": 12.301195426195425, "percentage": 61.51, "elapsed_time": "1:08:50", "remaining_time": "0:43:04", "throughput": 1031.84, "total_tokens": 4261832} {"current_steps": 47340, "total_steps": 76960, "loss": 0.1831, "lr": 1.9366722295472318e-05, "epoch": 12.302494802494802, "percentage": 61.51, "elapsed_time": "1:08:50", "remaining_time": "0:43:04", "throughput": 1031.84, "total_tokens": 4262248} {"current_steps": 47345, "total_steps": 76960, "loss": 0.4669, "lr": 1.9361198651073408e-05, "epoch": 12.30379417879418, "percentage": 61.52, "elapsed_time": "1:08:51", "remaining_time": "0:43:04", "throughput": 1031.84, "total_tokens": 4262696} {"current_steps": 47350, "total_steps": 76960, "loss": 0.1158, "lr": 1.9355675296683447e-05, "epoch": 12.305093555093555, "percentage": 61.53, "elapsed_time": "1:08:51", "remaining_time": "0:43:03", "throughput": 1031.86, "total_tokens": 4263176} {"current_steps": 47355, "total_steps": 76960, "loss": 0.2378, "lr": 1.9350152232586518e-05, "epoch": 12.306392931392931, "percentage": 61.53, "elapsed_time": "1:08:51", "remaining_time": "0:43:03", "throughput": 1031.86, "total_tokens": 4263608} {"current_steps": 47360, "total_steps": 76960, "loss": 0.1069, "lr": 1.9344629459066677e-05, "epoch": 12.307692307692308, "percentage": 61.54, "elapsed_time": "1:08:52", "remaining_time": "0:43:02", "throughput": 1031.86, "total_tokens": 4264056} {"current_steps": 47365, "total_steps": 76960, "loss": 0.2794, "lr": 1.9339106976407952e-05, "epoch": 12.308991683991684, "percentage": 61.54, "elapsed_time": "1:08:52", "remaining_time": "0:43:02", "throughput": 1031.87, "total_tokens": 4264520} {"current_steps": 47370, "total_steps": 76960, "loss": 0.5124, "lr": 1.9333584784894383e-05, "epoch": 12.31029106029106, "percentage": 61.55, "elapsed_time": "1:08:53", "remaining_time": "0:43:01", "throughput": 1031.87, "total_tokens": 4264968} {"current_steps": 47375, "total_steps": 76960, "loss": 0.0983, "lr": 1.9328062884809975e-05, "epoch": 12.311590436590437, "percentage": 61.56, "elapsed_time": "1:08:53", "remaining_time": "0:43:01", "throughput": 1031.88, "total_tokens": 4265416} {"current_steps": 47380, "total_steps": 76960, "loss": 0.0588, "lr": 1.932254127643874e-05, "epoch": 12.312889812889813, "percentage": 61.56, "elapsed_time": "1:08:54", "remaining_time": "0:43:00", "throughput": 1031.9, "total_tokens": 4265928} {"current_steps": 47385, "total_steps": 76960, "loss": 0.2473, "lr": 1.9317019960064632e-05, "epoch": 12.31418918918919, "percentage": 61.57, "elapsed_time": "1:08:54", "remaining_time": "0:43:00", "throughput": 1031.9, "total_tokens": 4266360} {"current_steps": 47390, "total_steps": 76960, "loss": 0.0886, "lr": 1.9311498935971638e-05, "epoch": 12.315488565488565, "percentage": 61.58, "elapsed_time": "1:08:54", "remaining_time": "0:43:00", "throughput": 1031.91, "total_tokens": 4266808} {"current_steps": 47395, "total_steps": 76960, "loss": 0.3753, "lr": 1.93059782044437e-05, "epoch": 12.316787941787942, "percentage": 61.58, "elapsed_time": "1:08:55", "remaining_time": "0:42:59", "throughput": 1031.9, "total_tokens": 4267224} {"current_steps": 47400, "total_steps": 76960, "loss": 0.2651, "lr": 1.930045776576477e-05, "epoch": 12.318087318087318, "percentage": 61.59, "elapsed_time": "1:08:55", "remaining_time": "0:42:59", "throughput": 1031.91, "total_tokens": 4267672} {"current_steps": 47405, "total_steps": 76960, "loss": 0.2314, "lr": 1.9294937620218746e-05, "epoch": 12.319386694386694, "percentage": 61.6, "elapsed_time": "1:08:56", "remaining_time": "0:42:58", "throughput": 1031.91, "total_tokens": 4268120} {"current_steps": 47410, "total_steps": 76960, "loss": 0.2078, "lr": 1.9289417768089553e-05, "epoch": 12.32068607068607, "percentage": 61.6, "elapsed_time": "1:08:56", "remaining_time": "0:42:58", "throughput": 1031.91, "total_tokens": 4268536} {"current_steps": 47415, "total_steps": 76960, "loss": 0.277, "lr": 1.9283898209661066e-05, "epoch": 12.321985446985448, "percentage": 61.61, "elapsed_time": "1:08:56", "remaining_time": "0:42:57", "throughput": 1031.91, "total_tokens": 4268968} {"current_steps": 47420, "total_steps": 76960, "loss": 0.2773, "lr": 1.9278378945217186e-05, "epoch": 12.323284823284823, "percentage": 61.62, "elapsed_time": "1:08:57", "remaining_time": "0:42:57", "throughput": 1031.91, "total_tokens": 4269384} {"current_steps": 47425, "total_steps": 76960, "loss": 0.3682, "lr": 1.9272859975041754e-05, "epoch": 12.3245841995842, "percentage": 61.62, "elapsed_time": "1:08:57", "remaining_time": "0:42:56", "throughput": 1031.91, "total_tokens": 4269816} {"current_steps": 47430, "total_steps": 76960, "loss": 0.2992, "lr": 1.9267341299418615e-05, "epoch": 12.325883575883577, "percentage": 61.63, "elapsed_time": "1:08:58", "remaining_time": "0:42:56", "throughput": 1031.91, "total_tokens": 4270248} {"current_steps": 47435, "total_steps": 76960, "loss": 0.2006, "lr": 1.926182291863162e-05, "epoch": 12.327182952182952, "percentage": 61.64, "elapsed_time": "1:08:58", "remaining_time": "0:42:55", "throughput": 1031.92, "total_tokens": 4270696} {"current_steps": 47440, "total_steps": 76960, "loss": 0.2237, "lr": 1.925630483296455e-05, "epoch": 12.328482328482329, "percentage": 61.64, "elapsed_time": "1:08:59", "remaining_time": "0:42:55", "throughput": 1031.93, "total_tokens": 4271192} {"current_steps": 47445, "total_steps": 76960, "loss": 0.1857, "lr": 1.925078704270124e-05, "epoch": 12.329781704781706, "percentage": 61.65, "elapsed_time": "1:08:59", "remaining_time": "0:42:55", "throughput": 1031.94, "total_tokens": 4271656} {"current_steps": 47450, "total_steps": 76960, "loss": 0.08, "lr": 1.924526954812545e-05, "epoch": 12.33108108108108, "percentage": 61.66, "elapsed_time": "1:08:59", "remaining_time": "0:42:54", "throughput": 1031.96, "total_tokens": 4272152} {"current_steps": 47455, "total_steps": 76960, "loss": 0.1903, "lr": 1.923975234952098e-05, "epoch": 12.332380457380458, "percentage": 61.66, "elapsed_time": "1:09:00", "remaining_time": "0:42:54", "throughput": 1031.96, "total_tokens": 4272584} {"current_steps": 47460, "total_steps": 76960, "loss": 0.1086, "lr": 1.9234235447171548e-05, "epoch": 12.333679833679835, "percentage": 61.67, "elapsed_time": "1:09:00", "remaining_time": "0:42:53", "throughput": 1031.96, "total_tokens": 4273016} {"current_steps": 47465, "total_steps": 76960, "loss": 0.1838, "lr": 1.9228718841360917e-05, "epoch": 12.33497920997921, "percentage": 61.67, "elapsed_time": "1:09:01", "remaining_time": "0:42:53", "throughput": 1031.96, "total_tokens": 4273464} {"current_steps": 47470, "total_steps": 76960, "loss": 0.1594, "lr": 1.9223202532372802e-05, "epoch": 12.336278586278587, "percentage": 61.68, "elapsed_time": "1:09:01", "remaining_time": "0:42:52", "throughput": 1031.97, "total_tokens": 4273912} {"current_steps": 47475, "total_steps": 76960, "loss": 0.1602, "lr": 1.921768652049093e-05, "epoch": 12.337577962577962, "percentage": 61.69, "elapsed_time": "1:09:01", "remaining_time": "0:42:52", "throughput": 1031.97, "total_tokens": 4274360} {"current_steps": 47480, "total_steps": 76960, "loss": 0.6146, "lr": 1.9212170805998965e-05, "epoch": 12.338877338877339, "percentage": 61.69, "elapsed_time": "1:09:02", "remaining_time": "0:42:51", "throughput": 1031.97, "total_tokens": 4274808} {"current_steps": 47485, "total_steps": 76960, "loss": 0.0082, "lr": 1.9206655389180604e-05, "epoch": 12.340176715176716, "percentage": 61.7, "elapsed_time": "1:09:02", "remaining_time": "0:42:51", "throughput": 1031.99, "total_tokens": 4275304} {"current_steps": 47490, "total_steps": 76960, "loss": 0.1637, "lr": 1.920114027031952e-05, "epoch": 12.34147609147609, "percentage": 61.71, "elapsed_time": "1:09:03", "remaining_time": "0:42:51", "throughput": 1032.0, "total_tokens": 4275768} {"current_steps": 47495, "total_steps": 76960, "loss": 0.3417, "lr": 1.9195625449699334e-05, "epoch": 12.342775467775468, "percentage": 61.71, "elapsed_time": "1:09:03", "remaining_time": "0:42:50", "throughput": 1032.0, "total_tokens": 4276216} {"current_steps": 47500, "total_steps": 76960, "loss": 0.4548, "lr": 1.9190110927603695e-05, "epoch": 12.344074844074845, "percentage": 61.72, "elapsed_time": "1:09:04", "remaining_time": "0:42:50", "throughput": 1032.01, "total_tokens": 4276664} {"current_steps": 47505, "total_steps": 76960, "loss": 0.1874, "lr": 1.918459670431622e-05, "epoch": 12.34537422037422, "percentage": 61.73, "elapsed_time": "1:09:04", "remaining_time": "0:42:49", "throughput": 1032.01, "total_tokens": 4277096} {"current_steps": 47510, "total_steps": 76960, "loss": 0.2871, "lr": 1.917908278012051e-05, "epoch": 12.346673596673597, "percentage": 61.73, "elapsed_time": "1:09:04", "remaining_time": "0:42:49", "throughput": 1032.01, "total_tokens": 4277528} {"current_steps": 47515, "total_steps": 76960, "loss": 0.4327, "lr": 1.9173569155300148e-05, "epoch": 12.347972972972974, "percentage": 61.74, "elapsed_time": "1:09:05", "remaining_time": "0:42:48", "throughput": 1032.01, "total_tokens": 4277944} {"current_steps": 47520, "total_steps": 76960, "loss": 0.1356, "lr": 1.9168055830138706e-05, "epoch": 12.349272349272349, "percentage": 61.75, "elapsed_time": "1:09:05", "remaining_time": "0:42:48", "throughput": 1032.0, "total_tokens": 4278344} {"current_steps": 47525, "total_steps": 76960, "loss": 0.0917, "lr": 1.9162542804919736e-05, "epoch": 12.350571725571726, "percentage": 61.75, "elapsed_time": "1:09:06", "remaining_time": "0:42:47", "throughput": 1032.0, "total_tokens": 4278776} {"current_steps": 47530, "total_steps": 76960, "loss": 0.3034, "lr": 1.9157030079926796e-05, "epoch": 12.351871101871103, "percentage": 61.76, "elapsed_time": "1:09:06", "remaining_time": "0:42:47", "throughput": 1032.01, "total_tokens": 4279256} {"current_steps": 47535, "total_steps": 76960, "loss": 0.0844, "lr": 1.9151517655443386e-05, "epoch": 12.353170478170478, "percentage": 61.77, "elapsed_time": "1:09:06", "remaining_time": "0:42:47", "throughput": 1032.02, "total_tokens": 4279704} {"current_steps": 47540, "total_steps": 76960, "loss": 0.1507, "lr": 1.914600553175303e-05, "epoch": 12.354469854469855, "percentage": 61.77, "elapsed_time": "1:09:07", "remaining_time": "0:42:46", "throughput": 1032.01, "total_tokens": 4280120} {"current_steps": 47545, "total_steps": 76960, "loss": 0.2969, "lr": 1.9140493709139214e-05, "epoch": 12.35576923076923, "percentage": 61.78, "elapsed_time": "1:09:07", "remaining_time": "0:42:46", "throughput": 1032.02, "total_tokens": 4280568} {"current_steps": 47550, "total_steps": 76960, "loss": 0.1575, "lr": 1.9134982187885433e-05, "epoch": 12.357068607068607, "percentage": 61.79, "elapsed_time": "1:09:08", "remaining_time": "0:42:45", "throughput": 1032.02, "total_tokens": 4281000} {"current_steps": 47555, "total_steps": 76960, "loss": 0.1706, "lr": 1.912947096827513e-05, "epoch": 12.358367983367984, "percentage": 61.79, "elapsed_time": "1:09:08", "remaining_time": "0:42:45", "throughput": 1032.02, "total_tokens": 4281448} {"current_steps": 47560, "total_steps": 76960, "loss": 0.6045, "lr": 1.912396005059176e-05, "epoch": 12.359667359667359, "percentage": 61.8, "elapsed_time": "1:09:09", "remaining_time": "0:42:44", "throughput": 1032.03, "total_tokens": 4281912} {"current_steps": 47565, "total_steps": 76960, "loss": 0.336, "lr": 1.911844943511876e-05, "epoch": 12.360966735966736, "percentage": 61.8, "elapsed_time": "1:09:09", "remaining_time": "0:42:44", "throughput": 1032.03, "total_tokens": 4282344} {"current_steps": 47570, "total_steps": 76960, "loss": 0.6087, "lr": 1.911293912213953e-05, "epoch": 12.362266112266113, "percentage": 61.81, "elapsed_time": "1:09:09", "remaining_time": "0:42:43", "throughput": 1032.04, "total_tokens": 4282824} {"current_steps": 47575, "total_steps": 76960, "loss": 0.429, "lr": 1.9107429111937493e-05, "epoch": 12.363565488565488, "percentage": 61.82, "elapsed_time": "1:09:10", "remaining_time": "0:42:43", "throughput": 1032.04, "total_tokens": 4283256} {"current_steps": 47580, "total_steps": 76960, "loss": 0.3235, "lr": 1.9101919404796008e-05, "epoch": 12.364864864864865, "percentage": 61.82, "elapsed_time": "1:09:10", "remaining_time": "0:42:42", "throughput": 1032.05, "total_tokens": 4283720} {"current_steps": 47585, "total_steps": 76960, "loss": 0.3593, "lr": 1.9096410000998475e-05, "epoch": 12.366164241164242, "percentage": 61.83, "elapsed_time": "1:09:11", "remaining_time": "0:42:42", "throughput": 1032.07, "total_tokens": 4284216} {"current_steps": 47590, "total_steps": 76960, "loss": 0.1249, "lr": 1.9090900900828217e-05, "epoch": 12.367463617463617, "percentage": 61.84, "elapsed_time": "1:09:11", "remaining_time": "0:42:42", "throughput": 1032.07, "total_tokens": 4284648} {"current_steps": 47595, "total_steps": 76960, "loss": 0.0649, "lr": 1.9085392104568606e-05, "epoch": 12.368762993762994, "percentage": 61.84, "elapsed_time": "1:09:11", "remaining_time": "0:42:41", "throughput": 1032.07, "total_tokens": 4285080} {"current_steps": 47600, "total_steps": 76960, "loss": 0.2228, "lr": 1.907988361250293e-05, "epoch": 12.37006237006237, "percentage": 61.85, "elapsed_time": "1:09:12", "remaining_time": "0:42:41", "throughput": 1032.07, "total_tokens": 4285496} {"current_steps": 47605, "total_steps": 76960, "loss": 0.2617, "lr": 1.907437542491452e-05, "epoch": 12.371361746361746, "percentage": 61.86, "elapsed_time": "1:09:12", "remaining_time": "0:42:40", "throughput": 1032.09, "total_tokens": 4285992} {"current_steps": 47610, "total_steps": 76960, "loss": 0.1136, "lr": 1.9068867542086656e-05, "epoch": 12.372661122661123, "percentage": 61.86, "elapsed_time": "1:09:13", "remaining_time": "0:42:40", "throughput": 1032.1, "total_tokens": 4286456} {"current_steps": 47615, "total_steps": 76960, "loss": 0.3204, "lr": 1.9063359964302628e-05, "epoch": 12.3739604989605, "percentage": 61.87, "elapsed_time": "1:09:13", "remaining_time": "0:42:39", "throughput": 1032.11, "total_tokens": 4286952} {"current_steps": 47620, "total_steps": 76960, "loss": 0.4006, "lr": 1.9057852691845677e-05, "epoch": 12.375259875259875, "percentage": 61.88, "elapsed_time": "1:09:13", "remaining_time": "0:42:39", "throughput": 1032.11, "total_tokens": 4287384} {"current_steps": 47625, "total_steps": 76960, "loss": 0.1556, "lr": 1.905234572499905e-05, "epoch": 12.376559251559252, "percentage": 61.88, "elapsed_time": "1:09:14", "remaining_time": "0:42:38", "throughput": 1032.11, "total_tokens": 4287816} {"current_steps": 47630, "total_steps": 76960, "loss": 0.3758, "lr": 1.9046839064045993e-05, "epoch": 12.377858627858627, "percentage": 61.89, "elapsed_time": "1:09:14", "remaining_time": "0:42:38", "throughput": 1032.12, "total_tokens": 4288264} {"current_steps": 47635, "total_steps": 76960, "loss": 0.3333, "lr": 1.9041332709269697e-05, "epoch": 12.379158004158004, "percentage": 61.9, "elapsed_time": "1:09:15", "remaining_time": "0:42:38", "throughput": 1032.12, "total_tokens": 4288696} {"current_steps": 47640, "total_steps": 76960, "loss": 0.063, "lr": 1.9035826660953374e-05, "epoch": 12.380457380457381, "percentage": 61.9, "elapsed_time": "1:09:15", "remaining_time": "0:42:37", "throughput": 1032.12, "total_tokens": 4289128} {"current_steps": 47645, "total_steps": 76960, "loss": 0.2939, "lr": 1.9030320919380194e-05, "epoch": 12.381756756756756, "percentage": 61.91, "elapsed_time": "1:09:16", "remaining_time": "0:42:37", "throughput": 1032.12, "total_tokens": 4289560} {"current_steps": 47650, "total_steps": 76960, "loss": 0.1722, "lr": 1.902481548483334e-05, "epoch": 12.383056133056133, "percentage": 61.92, "elapsed_time": "1:09:16", "remaining_time": "0:42:36", "throughput": 1032.12, "total_tokens": 4289992} {"current_steps": 47655, "total_steps": 76960, "loss": 0.2782, "lr": 1.901931035759594e-05, "epoch": 12.38435550935551, "percentage": 61.92, "elapsed_time": "1:09:16", "remaining_time": "0:42:36", "throughput": 1032.12, "total_tokens": 4290424} {"current_steps": 47660, "total_steps": 76960, "loss": 0.2142, "lr": 1.9013805537951144e-05, "epoch": 12.385654885654885, "percentage": 61.93, "elapsed_time": "1:09:17", "remaining_time": "0:42:35", "throughput": 1032.13, "total_tokens": 4290920} {"current_steps": 47665, "total_steps": 76960, "loss": 0.3486, "lr": 1.900830102618206e-05, "epoch": 12.386954261954262, "percentage": 61.93, "elapsed_time": "1:09:17", "remaining_time": "0:42:35", "throughput": 1032.14, "total_tokens": 4291368} {"current_steps": 47670, "total_steps": 76960, "loss": 0.3997, "lr": 1.9002796822571807e-05, "epoch": 12.388253638253639, "percentage": 61.94, "elapsed_time": "1:09:18", "remaining_time": "0:42:34", "throughput": 1032.14, "total_tokens": 4291800} {"current_steps": 47675, "total_steps": 76960, "loss": 0.1856, "lr": 1.8997292927403448e-05, "epoch": 12.389553014553014, "percentage": 61.95, "elapsed_time": "1:09:18", "remaining_time": "0:42:34", "throughput": 1032.15, "total_tokens": 4292264} {"current_steps": 47680, "total_steps": 76960, "loss": 0.4569, "lr": 1.8991789340960072e-05, "epoch": 12.390852390852391, "percentage": 61.95, "elapsed_time": "1:09:18", "remaining_time": "0:42:34", "throughput": 1032.16, "total_tokens": 4292760} {"current_steps": 47685, "total_steps": 76960, "loss": 0.2325, "lr": 1.8986286063524733e-05, "epoch": 12.392151767151766, "percentage": 61.96, "elapsed_time": "1:09:19", "remaining_time": "0:42:33", "throughput": 1032.17, "total_tokens": 4293224} {"current_steps": 47690, "total_steps": 76960, "loss": 0.2896, "lr": 1.898078309538045e-05, "epoch": 12.393451143451143, "percentage": 61.97, "elapsed_time": "1:09:19", "remaining_time": "0:42:33", "throughput": 1032.18, "total_tokens": 4293688} {"current_steps": 47695, "total_steps": 76960, "loss": 0.461, "lr": 1.8975280436810266e-05, "epoch": 12.39475051975052, "percentage": 61.97, "elapsed_time": "1:09:20", "remaining_time": "0:42:32", "throughput": 1032.18, "total_tokens": 4294104} {"current_steps": 47700, "total_steps": 76960, "loss": 0.2031, "lr": 1.8969778088097175e-05, "epoch": 12.396049896049895, "percentage": 61.98, "elapsed_time": "1:09:20", "remaining_time": "0:42:32", "throughput": 1032.19, "total_tokens": 4294568} {"current_steps": 47705, "total_steps": 76960, "loss": 0.071, "lr": 1.896427604952419e-05, "epoch": 12.397349272349272, "percentage": 61.99, "elapsed_time": "1:09:21", "remaining_time": "0:42:31", "throughput": 1032.2, "total_tokens": 4295032} {"current_steps": 47710, "total_steps": 76960, "loss": 0.0354, "lr": 1.8958774321374256e-05, "epoch": 12.39864864864865, "percentage": 61.99, "elapsed_time": "1:09:21", "remaining_time": "0:42:31", "throughput": 1032.2, "total_tokens": 4295480} {"current_steps": 47715, "total_steps": 76960, "loss": 0.0609, "lr": 1.8953272903930353e-05, "epoch": 12.399948024948024, "percentage": 62.0, "elapsed_time": "1:09:21", "remaining_time": "0:42:30", "throughput": 1032.21, "total_tokens": 4295928} {"current_steps": 47720, "total_steps": 76960, "loss": 0.3914, "lr": 1.8947771797475414e-05, "epoch": 12.401247401247401, "percentage": 62.01, "elapsed_time": "1:09:22", "remaining_time": "0:42:30", "throughput": 1032.21, "total_tokens": 4296392} {"current_steps": 47725, "total_steps": 76960, "loss": 0.3982, "lr": 1.894227100229238e-05, "epoch": 12.402546777546778, "percentage": 62.01, "elapsed_time": "1:09:22", "remaining_time": "0:42:29", "throughput": 1032.22, "total_tokens": 4296856} {"current_steps": 47730, "total_steps": 76960, "loss": 0.0403, "lr": 1.8936770518664145e-05, "epoch": 12.403846153846153, "percentage": 62.02, "elapsed_time": "1:09:23", "remaining_time": "0:42:29", "throughput": 1032.22, "total_tokens": 4297288} {"current_steps": 47735, "total_steps": 76960, "loss": 0.2928, "lr": 1.8931270346873613e-05, "epoch": 12.40514553014553, "percentage": 62.03, "elapsed_time": "1:09:23", "remaining_time": "0:42:29", "throughput": 1032.24, "total_tokens": 4297784} {"current_steps": 47740, "total_steps": 76960, "loss": 0.3908, "lr": 1.892577048720366e-05, "epoch": 12.406444906444907, "percentage": 62.03, "elapsed_time": "1:09:23", "remaining_time": "0:42:28", "throughput": 1032.24, "total_tokens": 4298216} {"current_steps": 47745, "total_steps": 76960, "loss": 0.2268, "lr": 1.892027093993716e-05, "epoch": 12.407744282744282, "percentage": 62.04, "elapsed_time": "1:09:24", "remaining_time": "0:42:28", "throughput": 1032.24, "total_tokens": 4298648} {"current_steps": 47750, "total_steps": 76960, "loss": 0.5287, "lr": 1.8914771705356944e-05, "epoch": 12.40904365904366, "percentage": 62.05, "elapsed_time": "1:09:24", "remaining_time": "0:42:27", "throughput": 1032.24, "total_tokens": 4299096} {"current_steps": 47755, "total_steps": 76960, "loss": 0.1777, "lr": 1.8909272783745846e-05, "epoch": 12.410343035343036, "percentage": 62.05, "elapsed_time": "1:09:25", "remaining_time": "0:42:27", "throughput": 1032.24, "total_tokens": 4299528} {"current_steps": 47760, "total_steps": 76960, "loss": 0.0382, "lr": 1.8903774175386695e-05, "epoch": 12.411642411642411, "percentage": 62.06, "elapsed_time": "1:09:25", "remaining_time": "0:42:26", "throughput": 1032.25, "total_tokens": 4299976} {"current_steps": 47765, "total_steps": 76960, "loss": 0.1968, "lr": 1.889827588056227e-05, "epoch": 12.412941787941788, "percentage": 62.06, "elapsed_time": "1:09:26", "remaining_time": "0:42:26", "throughput": 1032.25, "total_tokens": 4300408} {"current_steps": 47770, "total_steps": 76960, "loss": 0.119, "lr": 1.8892777899555363e-05, "epoch": 12.414241164241163, "percentage": 62.07, "elapsed_time": "1:09:26", "remaining_time": "0:42:25", "throughput": 1032.25, "total_tokens": 4300856} {"current_steps": 47775, "total_steps": 76960, "loss": 0.0938, "lr": 1.8887280232648742e-05, "epoch": 12.41554054054054, "percentage": 62.08, "elapsed_time": "1:09:26", "remaining_time": "0:42:25", "throughput": 1032.25, "total_tokens": 4301272} {"current_steps": 47780, "total_steps": 76960, "loss": 0.4335, "lr": 1.8881782880125163e-05, "epoch": 12.416839916839917, "percentage": 62.08, "elapsed_time": "1:09:27", "remaining_time": "0:42:25", "throughput": 1032.26, "total_tokens": 4301720} {"current_steps": 47785, "total_steps": 76960, "loss": 0.369, "lr": 1.887628584226734e-05, "epoch": 12.418139293139292, "percentage": 62.09, "elapsed_time": "1:09:27", "remaining_time": "0:42:24", "throughput": 1032.26, "total_tokens": 4302152} {"current_steps": 47790, "total_steps": 76960, "loss": 0.107, "lr": 1.8870789119358014e-05, "epoch": 12.41943866943867, "percentage": 62.1, "elapsed_time": "1:09:28", "remaining_time": "0:42:24", "throughput": 1032.26, "total_tokens": 4302600} {"current_steps": 47795, "total_steps": 76960, "loss": 0.3801, "lr": 1.8865292711679866e-05, "epoch": 12.420738045738046, "percentage": 62.1, "elapsed_time": "1:09:28", "remaining_time": "0:42:23", "throughput": 1032.26, "total_tokens": 4303032} {"current_steps": 47800, "total_steps": 76960, "loss": 0.1819, "lr": 1.8859796619515606e-05, "epoch": 12.422037422037421, "percentage": 62.11, "elapsed_time": "1:09:28", "remaining_time": "0:42:23", "throughput": 1032.27, "total_tokens": 4303480} {"current_steps": 47805, "total_steps": 76960, "loss": 0.1456, "lr": 1.8854300843147875e-05, "epoch": 12.423336798336798, "percentage": 62.12, "elapsed_time": "1:09:29", "remaining_time": "0:42:22", "throughput": 1032.27, "total_tokens": 4303928} {"current_steps": 47810, "total_steps": 76960, "loss": 0.3261, "lr": 1.8848805382859348e-05, "epoch": 12.424636174636175, "percentage": 62.12, "elapsed_time": "1:09:29", "remaining_time": "0:42:22", "throughput": 1032.27, "total_tokens": 4304376} {"current_steps": 47815, "total_steps": 76960, "loss": 0.305, "lr": 1.884331023893266e-05, "epoch": 12.42593555093555, "percentage": 62.13, "elapsed_time": "1:09:30", "remaining_time": "0:42:21", "throughput": 1032.27, "total_tokens": 4304792} {"current_steps": 47820, "total_steps": 76960, "loss": 0.2861, "lr": 1.883781541165041e-05, "epoch": 12.427234927234927, "percentage": 62.14, "elapsed_time": "1:09:30", "remaining_time": "0:42:21", "throughput": 1032.28, "total_tokens": 4305272} {"current_steps": 47825, "total_steps": 76960, "loss": 0.125, "lr": 1.8832320901295227e-05, "epoch": 12.428534303534304, "percentage": 62.14, "elapsed_time": "1:09:31", "remaining_time": "0:42:21", "throughput": 1032.28, "total_tokens": 4305688} {"current_steps": 47830, "total_steps": 76960, "loss": 0.1222, "lr": 1.8826826708149687e-05, "epoch": 12.42983367983368, "percentage": 62.15, "elapsed_time": "1:09:31", "remaining_time": "0:42:20", "throughput": 1032.28, "total_tokens": 4306136} {"current_steps": 47835, "total_steps": 76960, "loss": 0.1852, "lr": 1.8821332832496367e-05, "epoch": 12.431133056133056, "percentage": 62.16, "elapsed_time": "1:09:31", "remaining_time": "0:42:20", "throughput": 1032.29, "total_tokens": 4306600} {"current_steps": 47840, "total_steps": 76960, "loss": 0.0606, "lr": 1.881583927461781e-05, "epoch": 12.432432432432432, "percentage": 62.16, "elapsed_time": "1:09:32", "remaining_time": "0:42:19", "throughput": 1032.29, "total_tokens": 4307032} {"current_steps": 47845, "total_steps": 76960, "loss": 0.0212, "lr": 1.8810346034796582e-05, "epoch": 12.433731808731808, "percentage": 62.17, "elapsed_time": "1:09:32", "remaining_time": "0:42:19", "throughput": 1032.29, "total_tokens": 4307464} {"current_steps": 47850, "total_steps": 76960, "loss": 0.0974, "lr": 1.880485311331517e-05, "epoch": 12.435031185031185, "percentage": 62.18, "elapsed_time": "1:09:33", "remaining_time": "0:42:18", "throughput": 1032.3, "total_tokens": 4307912} {"current_steps": 47855, "total_steps": 76960, "loss": 0.3295, "lr": 1.879936051045611e-05, "epoch": 12.43633056133056, "percentage": 62.18, "elapsed_time": "1:09:33", "remaining_time": "0:42:18", "throughput": 1032.31, "total_tokens": 4308376} {"current_steps": 47860, "total_steps": 76960, "loss": 0.4736, "lr": 1.879386822650187e-05, "epoch": 12.437629937629938, "percentage": 62.19, "elapsed_time": "1:09:33", "remaining_time": "0:42:17", "throughput": 1032.32, "total_tokens": 4308856} {"current_steps": 47865, "total_steps": 76960, "loss": 0.1605, "lr": 1.8788376261734948e-05, "epoch": 12.438929313929314, "percentage": 62.19, "elapsed_time": "1:09:34", "remaining_time": "0:42:17", "throughput": 1032.32, "total_tokens": 4309288} {"current_steps": 47870, "total_steps": 76960, "loss": 0.0788, "lr": 1.8782884616437777e-05, "epoch": 12.44022869022869, "percentage": 62.2, "elapsed_time": "1:09:34", "remaining_time": "0:42:16", "throughput": 1032.32, "total_tokens": 4309704} {"current_steps": 47875, "total_steps": 76960, "loss": 0.3597, "lr": 1.877739329089281e-05, "epoch": 12.441528066528067, "percentage": 62.21, "elapsed_time": "1:09:35", "remaining_time": "0:42:16", "throughput": 1032.31, "total_tokens": 4310120} {"current_steps": 47880, "total_steps": 76960, "loss": 0.1943, "lr": 1.8771902285382474e-05, "epoch": 12.442827442827443, "percentage": 62.21, "elapsed_time": "1:09:35", "remaining_time": "0:42:16", "throughput": 1032.31, "total_tokens": 4310552} {"current_steps": 47885, "total_steps": 76960, "loss": 0.3356, "lr": 1.876641160018916e-05, "epoch": 12.444126819126819, "percentage": 62.22, "elapsed_time": "1:09:36", "remaining_time": "0:42:15", "throughput": 1032.32, "total_tokens": 4311016} {"current_steps": 47890, "total_steps": 76960, "loss": 0.2158, "lr": 1.8760921235595275e-05, "epoch": 12.445426195426196, "percentage": 62.23, "elapsed_time": "1:09:36", "remaining_time": "0:42:15", "throughput": 1032.32, "total_tokens": 4311432} {"current_steps": 47895, "total_steps": 76960, "loss": 0.3146, "lr": 1.8755431191883183e-05, "epoch": 12.446725571725572, "percentage": 62.23, "elapsed_time": "1:09:36", "remaining_time": "0:42:14", "throughput": 1032.33, "total_tokens": 4311896} {"current_steps": 47900, "total_steps": 76960, "loss": 0.1138, "lr": 1.8749941469335258e-05, "epoch": 12.448024948024948, "percentage": 62.24, "elapsed_time": "1:09:37", "remaining_time": "0:42:14", "throughput": 1032.34, "total_tokens": 4312360} {"current_steps": 47905, "total_steps": 76960, "loss": 0.2347, "lr": 1.8744452068233825e-05, "epoch": 12.449324324324325, "percentage": 62.25, "elapsed_time": "1:09:37", "remaining_time": "0:42:13", "throughput": 1032.34, "total_tokens": 4312808} {"current_steps": 47910, "total_steps": 76960, "loss": 0.3241, "lr": 1.873896298886122e-05, "epoch": 12.450623700623701, "percentage": 62.25, "elapsed_time": "1:09:38", "remaining_time": "0:42:13", "throughput": 1032.34, "total_tokens": 4313256} {"current_steps": 47915, "total_steps": 76960, "loss": 0.1044, "lr": 1.873347423149974e-05, "epoch": 12.451923076923077, "percentage": 62.26, "elapsed_time": "1:09:38", "remaining_time": "0:42:12", "throughput": 1032.35, "total_tokens": 4313704} {"current_steps": 47920, "total_steps": 76960, "loss": 0.0647, "lr": 1.8727985796431697e-05, "epoch": 12.453222453222454, "percentage": 62.27, "elapsed_time": "1:09:38", "remaining_time": "0:42:12", "throughput": 1032.35, "total_tokens": 4314152} {"current_steps": 47925, "total_steps": 76960, "loss": 0.3351, "lr": 1.8722497683939343e-05, "epoch": 12.454521829521829, "percentage": 62.27, "elapsed_time": "1:09:39", "remaining_time": "0:42:12", "throughput": 1032.35, "total_tokens": 4314568} {"current_steps": 47930, "total_steps": 76960, "loss": 0.4956, "lr": 1.871700989430495e-05, "epoch": 12.455821205821206, "percentage": 62.28, "elapsed_time": "1:09:39", "remaining_time": "0:42:11", "throughput": 1032.34, "total_tokens": 4314968} {"current_steps": 47935, "total_steps": 76960, "loss": 0.2629, "lr": 1.8711522427810757e-05, "epoch": 12.457120582120583, "percentage": 62.29, "elapsed_time": "1:09:40", "remaining_time": "0:42:11", "throughput": 1032.36, "total_tokens": 4315464} {"current_steps": 47940, "total_steps": 76960, "loss": 0.3066, "lr": 1.8706035284739e-05, "epoch": 12.458419958419958, "percentage": 62.29, "elapsed_time": "1:09:40", "remaining_time": "0:42:10", "throughput": 1032.36, "total_tokens": 4315912} {"current_steps": 47945, "total_steps": 76960, "loss": 0.1316, "lr": 1.8700548465371874e-05, "epoch": 12.459719334719335, "percentage": 62.3, "elapsed_time": "1:09:41", "remaining_time": "0:42:10", "throughput": 1032.37, "total_tokens": 4316392} {"current_steps": 47950, "total_steps": 76960, "loss": 0.5037, "lr": 1.8695061969991574e-05, "epoch": 12.461018711018712, "percentage": 62.31, "elapsed_time": "1:09:41", "remaining_time": "0:42:09", "throughput": 1032.37, "total_tokens": 4316808} {"current_steps": 47955, "total_steps": 76960, "loss": 0.1062, "lr": 1.8689575798880283e-05, "epoch": 12.462318087318087, "percentage": 62.31, "elapsed_time": "1:09:41", "remaining_time": "0:42:09", "throughput": 1032.38, "total_tokens": 4317272} {"current_steps": 47960, "total_steps": 76960, "loss": 0.0752, "lr": 1.868408995232015e-05, "epoch": 12.463617463617464, "percentage": 62.32, "elapsed_time": "1:09:42", "remaining_time": "0:42:08", "throughput": 1032.38, "total_tokens": 4317720} {"current_steps": 47965, "total_steps": 76960, "loss": 0.1952, "lr": 1.867860443059332e-05, "epoch": 12.46491683991684, "percentage": 62.32, "elapsed_time": "1:09:42", "remaining_time": "0:42:08", "throughput": 1032.39, "total_tokens": 4318184} {"current_steps": 47970, "total_steps": 76960, "loss": 0.2368, "lr": 1.8673119233981923e-05, "epoch": 12.466216216216216, "percentage": 62.33, "elapsed_time": "1:09:43", "remaining_time": "0:42:08", "throughput": 1032.4, "total_tokens": 4318648} {"current_steps": 47975, "total_steps": 76960, "loss": 0.3366, "lr": 1.866763436276807e-05, "epoch": 12.467515592515593, "percentage": 62.34, "elapsed_time": "1:09:43", "remaining_time": "0:42:07", "throughput": 1032.42, "total_tokens": 4319144} {"current_steps": 47980, "total_steps": 76960, "loss": 0.4906, "lr": 1.8662149817233847e-05, "epoch": 12.46881496881497, "percentage": 62.34, "elapsed_time": "1:09:43", "remaining_time": "0:42:07", "throughput": 1032.43, "total_tokens": 4319608} {"current_steps": 47985, "total_steps": 76960, "loss": 0.4753, "lr": 1.8656665597661333e-05, "epoch": 12.470114345114345, "percentage": 62.35, "elapsed_time": "1:09:44", "remaining_time": "0:42:06", "throughput": 1032.43, "total_tokens": 4320056} {"current_steps": 47990, "total_steps": 76960, "loss": 0.071, "lr": 1.8651181704332578e-05, "epoch": 12.471413721413722, "percentage": 62.36, "elapsed_time": "1:09:44", "remaining_time": "0:42:06", "throughput": 1032.43, "total_tokens": 4320488} {"current_steps": 47995, "total_steps": 76960, "loss": 0.2273, "lr": 1.8645698137529644e-05, "epoch": 12.472713097713097, "percentage": 62.36, "elapsed_time": "1:09:45", "remaining_time": "0:42:05", "throughput": 1032.43, "total_tokens": 4320920} {"current_steps": 48000, "total_steps": 76960, "loss": 0.4636, "lr": 1.8640214897534532e-05, "epoch": 12.474012474012474, "percentage": 62.37, "elapsed_time": "1:09:45", "remaining_time": "0:42:05", "throughput": 1032.44, "total_tokens": 4321400} {"current_steps": 48005, "total_steps": 76960, "loss": 0.1108, "lr": 1.8634731984629263e-05, "epoch": 12.47531185031185, "percentage": 62.38, "elapsed_time": "1:09:46", "remaining_time": "0:42:04", "throughput": 1032.44, "total_tokens": 4321832} {"current_steps": 48010, "total_steps": 76960, "loss": 0.0841, "lr": 1.8629249399095835e-05, "epoch": 12.476611226611226, "percentage": 62.38, "elapsed_time": "1:09:46", "remaining_time": "0:42:04", "throughput": 1032.45, "total_tokens": 4322296} {"current_steps": 48015, "total_steps": 76960, "loss": 0.3293, "lr": 1.8623767141216207e-05, "epoch": 12.477910602910603, "percentage": 62.39, "elapsed_time": "1:09:46", "remaining_time": "0:42:03", "throughput": 1032.44, "total_tokens": 4322696} {"current_steps": 48020, "total_steps": 76960, "loss": 0.4278, "lr": 1.8618285211272345e-05, "epoch": 12.47920997920998, "percentage": 62.4, "elapsed_time": "1:09:47", "remaining_time": "0:42:03", "throughput": 1032.45, "total_tokens": 4323160} {"current_steps": 48025, "total_steps": 76960, "loss": 0.185, "lr": 1.8612803609546187e-05, "epoch": 12.480509355509355, "percentage": 62.4, "elapsed_time": "1:09:47", "remaining_time": "0:42:03", "throughput": 1032.46, "total_tokens": 4323608} {"current_steps": 48030, "total_steps": 76960, "loss": 0.2416, "lr": 1.8607322336319667e-05, "epoch": 12.481808731808732, "percentage": 62.41, "elapsed_time": "1:09:48", "remaining_time": "0:42:02", "throughput": 1032.45, "total_tokens": 4324024} {"current_steps": 48035, "total_steps": 76960, "loss": 0.4004, "lr": 1.8601841391874674e-05, "epoch": 12.483108108108109, "percentage": 62.42, "elapsed_time": "1:09:48", "remaining_time": "0:42:02", "throughput": 1032.45, "total_tokens": 4324456} {"current_steps": 48040, "total_steps": 76960, "loss": 0.1516, "lr": 1.859636077649312e-05, "epoch": 12.484407484407484, "percentage": 62.42, "elapsed_time": "1:09:48", "remaining_time": "0:42:01", "throughput": 1032.46, "total_tokens": 4324904} {"current_steps": 48045, "total_steps": 76960, "loss": 0.2241, "lr": 1.8590880490456854e-05, "epoch": 12.48570686070686, "percentage": 62.43, "elapsed_time": "1:09:49", "remaining_time": "0:42:01", "throughput": 1032.46, "total_tokens": 4325352} {"current_steps": 48050, "total_steps": 76960, "loss": 0.1702, "lr": 1.8585400534047758e-05, "epoch": 12.487006237006238, "percentage": 62.44, "elapsed_time": "1:09:49", "remaining_time": "0:42:00", "throughput": 1032.46, "total_tokens": 4325784} {"current_steps": 48055, "total_steps": 76960, "loss": 0.3899, "lr": 1.857992090754765e-05, "epoch": 12.488305613305613, "percentage": 62.44, "elapsed_time": "1:09:50", "remaining_time": "0:42:00", "throughput": 1032.47, "total_tokens": 4326232} {"current_steps": 48060, "total_steps": 76960, "loss": 0.2588, "lr": 1.857444161123837e-05, "epoch": 12.48960498960499, "percentage": 62.45, "elapsed_time": "1:09:50", "remaining_time": "0:41:59", "throughput": 1032.47, "total_tokens": 4326680} {"current_steps": 48065, "total_steps": 76960, "loss": 0.291, "lr": 1.85689626454017e-05, "epoch": 12.490904365904367, "percentage": 62.45, "elapsed_time": "1:09:51", "remaining_time": "0:41:59", "throughput": 1032.49, "total_tokens": 4327176} {"current_steps": 48070, "total_steps": 76960, "loss": 0.4023, "lr": 1.856348401031946e-05, "epoch": 12.492203742203742, "percentage": 62.46, "elapsed_time": "1:09:51", "remaining_time": "0:41:59", "throughput": 1032.5, "total_tokens": 4327656} {"current_steps": 48075, "total_steps": 76960, "loss": 0.2053, "lr": 1.85580057062734e-05, "epoch": 12.493503118503119, "percentage": 62.47, "elapsed_time": "1:09:51", "remaining_time": "0:41:58", "throughput": 1032.52, "total_tokens": 4328136} {"current_steps": 48080, "total_steps": 76960, "loss": 0.1683, "lr": 1.855252773354527e-05, "epoch": 12.494802494802494, "percentage": 62.47, "elapsed_time": "1:09:52", "remaining_time": "0:41:58", "throughput": 1032.52, "total_tokens": 4328600} {"current_steps": 48085, "total_steps": 76960, "loss": 0.1649, "lr": 1.8547050092416828e-05, "epoch": 12.496101871101871, "percentage": 62.48, "elapsed_time": "1:09:52", "remaining_time": "0:41:57", "throughput": 1032.53, "total_tokens": 4329064} {"current_steps": 48090, "total_steps": 76960, "loss": 0.2239, "lr": 1.854157278316977e-05, "epoch": 12.497401247401248, "percentage": 62.49, "elapsed_time": "1:09:53", "remaining_time": "0:41:57", "throughput": 1032.53, "total_tokens": 4329496} {"current_steps": 48095, "total_steps": 76960, "loss": 0.0552, "lr": 1.8536095806085823e-05, "epoch": 12.498700623700623, "percentage": 62.49, "elapsed_time": "1:09:53", "remaining_time": "0:41:56", "throughput": 1032.53, "total_tokens": 4329912} {"current_steps": 48100, "total_steps": 76960, "loss": 0.169, "lr": 1.8530619161446655e-05, "epoch": 12.5, "percentage": 62.5, "elapsed_time": "1:09:53", "remaining_time": "0:41:56", "throughput": 1032.53, "total_tokens": 4330344} {"current_steps": 48105, "total_steps": 76960, "loss": 0.1912, "lr": 1.8525142849533946e-05, "epoch": 12.501299376299377, "percentage": 62.51, "elapsed_time": "1:09:54", "remaining_time": "0:41:55", "throughput": 1032.53, "total_tokens": 4330776} {"current_steps": 48110, "total_steps": 76960, "loss": 0.1438, "lr": 1.851966687062934e-05, "epoch": 12.502598752598752, "percentage": 62.51, "elapsed_time": "1:09:54", "remaining_time": "0:41:55", "throughput": 1032.54, "total_tokens": 4331256} {"current_steps": 48115, "total_steps": 76960, "loss": 0.1191, "lr": 1.8514191225014484e-05, "epoch": 12.503898128898129, "percentage": 62.52, "elapsed_time": "1:09:55", "remaining_time": "0:41:55", "throughput": 1032.54, "total_tokens": 4331688} {"current_steps": 48120, "total_steps": 76960, "loss": 0.148, "lr": 1.8508715912970978e-05, "epoch": 12.505197505197506, "percentage": 62.53, "elapsed_time": "1:09:55", "remaining_time": "0:41:54", "throughput": 1032.54, "total_tokens": 4332120} {"current_steps": 48125, "total_steps": 76960, "loss": 0.5795, "lr": 1.8503240934780436e-05, "epoch": 12.506496881496881, "percentage": 62.53, "elapsed_time": "1:09:55", "remaining_time": "0:41:54", "throughput": 1032.54, "total_tokens": 4332536} {"current_steps": 48130, "total_steps": 76960, "loss": 0.5817, "lr": 1.8497766290724436e-05, "epoch": 12.507796257796258, "percentage": 62.54, "elapsed_time": "1:09:56", "remaining_time": "0:41:53", "throughput": 1032.56, "total_tokens": 4333048} {"current_steps": 48135, "total_steps": 76960, "loss": 0.2091, "lr": 1.8492291981084552e-05, "epoch": 12.509095634095633, "percentage": 62.55, "elapsed_time": "1:09:56", "remaining_time": "0:41:53", "throughput": 1032.56, "total_tokens": 4333464} {"current_steps": 48140, "total_steps": 76960, "loss": 0.1469, "lr": 1.8486818006142327e-05, "epoch": 12.51039501039501, "percentage": 62.55, "elapsed_time": "1:09:57", "remaining_time": "0:41:52", "throughput": 1032.58, "total_tokens": 4333992} {"current_steps": 48145, "total_steps": 76960, "loss": 0.159, "lr": 1.8481344366179284e-05, "epoch": 12.511694386694387, "percentage": 62.56, "elapsed_time": "1:09:57", "remaining_time": "0:41:52", "throughput": 1032.59, "total_tokens": 4334472} {"current_steps": 48150, "total_steps": 76960, "loss": 0.1443, "lr": 1.8475871061476958e-05, "epoch": 12.512993762993762, "percentage": 62.56, "elapsed_time": "1:09:58", "remaining_time": "0:41:51", "throughput": 1032.6, "total_tokens": 4334920} {"current_steps": 48155, "total_steps": 76960, "loss": 0.152, "lr": 1.8470398092316823e-05, "epoch": 12.51429313929314, "percentage": 62.57, "elapsed_time": "1:09:58", "remaining_time": "0:41:51", "throughput": 1032.6, "total_tokens": 4335352} {"current_steps": 48160, "total_steps": 76960, "loss": 0.4751, "lr": 1.8464925458980376e-05, "epoch": 12.515592515592516, "percentage": 62.58, "elapsed_time": "1:09:58", "remaining_time": "0:41:50", "throughput": 1032.6, "total_tokens": 4335784} {"current_steps": 48165, "total_steps": 76960, "loss": 0.3703, "lr": 1.845945316174907e-05, "epoch": 12.516891891891891, "percentage": 62.58, "elapsed_time": "1:09:59", "remaining_time": "0:41:50", "throughput": 1032.6, "total_tokens": 4336232} {"current_steps": 48170, "total_steps": 76960, "loss": 0.2761, "lr": 1.8453981200904365e-05, "epoch": 12.518191268191268, "percentage": 62.59, "elapsed_time": "1:09:59", "remaining_time": "0:41:50", "throughput": 1032.61, "total_tokens": 4336696} {"current_steps": 48175, "total_steps": 76960, "loss": 0.4742, "lr": 1.8448509576727667e-05, "epoch": 12.519490644490645, "percentage": 62.6, "elapsed_time": "1:10:00", "remaining_time": "0:41:49", "throughput": 1032.61, "total_tokens": 4337144} {"current_steps": 48180, "total_steps": 76960, "loss": 0.2343, "lr": 1.84430382895004e-05, "epoch": 12.52079002079002, "percentage": 62.6, "elapsed_time": "1:10:00", "remaining_time": "0:41:49", "throughput": 1032.61, "total_tokens": 4337560} {"current_steps": 48185, "total_steps": 76960, "loss": 0.3255, "lr": 1.843756733950396e-05, "epoch": 12.522089397089397, "percentage": 62.61, "elapsed_time": "1:10:00", "remaining_time": "0:41:48", "throughput": 1032.62, "total_tokens": 4338024} {"current_steps": 48190, "total_steps": 76960, "loss": 0.283, "lr": 1.8432096727019727e-05, "epoch": 12.523388773388774, "percentage": 62.62, "elapsed_time": "1:10:01", "remaining_time": "0:41:48", "throughput": 1032.62, "total_tokens": 4338472} {"current_steps": 48195, "total_steps": 76960, "loss": 0.3383, "lr": 1.8426626452329036e-05, "epoch": 12.52468814968815, "percentage": 62.62, "elapsed_time": "1:10:01", "remaining_time": "0:41:47", "throughput": 1032.62, "total_tokens": 4338888} {"current_steps": 48200, "total_steps": 76960, "loss": 0.1484, "lr": 1.8421156515713257e-05, "epoch": 12.525987525987526, "percentage": 62.63, "elapsed_time": "1:10:02", "remaining_time": "0:41:47", "throughput": 1032.63, "total_tokens": 4339368} {"current_steps": 48205, "total_steps": 76960, "loss": 0.2262, "lr": 1.8415686917453707e-05, "epoch": 12.527286902286903, "percentage": 62.64, "elapsed_time": "1:10:02", "remaining_time": "0:41:46", "throughput": 1032.63, "total_tokens": 4339800} {"current_steps": 48210, "total_steps": 76960, "loss": 0.234, "lr": 1.8410217657831674e-05, "epoch": 12.528586278586278, "percentage": 62.64, "elapsed_time": "1:10:03", "remaining_time": "0:41:46", "throughput": 1032.64, "total_tokens": 4340264} {"current_steps": 48215, "total_steps": 76960, "loss": 0.0734, "lr": 1.840474873712847e-05, "epoch": 12.529885654885655, "percentage": 62.65, "elapsed_time": "1:10:03", "remaining_time": "0:41:46", "throughput": 1032.65, "total_tokens": 4340712} {"current_steps": 48220, "total_steps": 76960, "loss": 0.2006, "lr": 1.8399280155625347e-05, "epoch": 12.53118503118503, "percentage": 62.66, "elapsed_time": "1:10:03", "remaining_time": "0:41:45", "throughput": 1032.65, "total_tokens": 4341176} {"current_steps": 48225, "total_steps": 76960, "loss": 0.2316, "lr": 1.839381191360358e-05, "epoch": 12.532484407484407, "percentage": 62.66, "elapsed_time": "1:10:04", "remaining_time": "0:41:45", "throughput": 1032.66, "total_tokens": 4341640} {"current_steps": 48230, "total_steps": 76960, "loss": 0.129, "lr": 1.8388344011344395e-05, "epoch": 12.533783783783784, "percentage": 62.67, "elapsed_time": "1:10:04", "remaining_time": "0:41:44", "throughput": 1032.68, "total_tokens": 4342120} {"current_steps": 48235, "total_steps": 76960, "loss": 0.2001, "lr": 1.838287644912901e-05, "epoch": 12.53508316008316, "percentage": 62.68, "elapsed_time": "1:10:05", "remaining_time": "0:41:44", "throughput": 1032.67, "total_tokens": 4342536} {"current_steps": 48240, "total_steps": 76960, "loss": 0.0561, "lr": 1.8377409227238624e-05, "epoch": 12.536382536382536, "percentage": 62.68, "elapsed_time": "1:10:05", "remaining_time": "0:41:43", "throughput": 1032.68, "total_tokens": 4342984} {"current_steps": 48245, "total_steps": 76960, "loss": 0.1452, "lr": 1.837194234595444e-05, "epoch": 12.537681912681913, "percentage": 62.69, "elapsed_time": "1:10:05", "remaining_time": "0:41:43", "throughput": 1032.68, "total_tokens": 4343448} {"current_steps": 48250, "total_steps": 76960, "loss": 0.3319, "lr": 1.8366475805557602e-05, "epoch": 12.538981288981288, "percentage": 62.69, "elapsed_time": "1:10:06", "remaining_time": "0:41:42", "throughput": 1032.69, "total_tokens": 4343880} {"current_steps": 48255, "total_steps": 76960, "loss": 0.1988, "lr": 1.836100960632927e-05, "epoch": 12.540280665280665, "percentage": 62.7, "elapsed_time": "1:10:06", "remaining_time": "0:41:42", "throughput": 1032.7, "total_tokens": 4344376} {"current_steps": 48260, "total_steps": 76960, "loss": 0.1799, "lr": 1.8355543748550573e-05, "epoch": 12.541580041580042, "percentage": 62.71, "elapsed_time": "1:10:07", "remaining_time": "0:41:42", "throughput": 1032.71, "total_tokens": 4344824} {"current_steps": 48265, "total_steps": 76960, "loss": 0.3078, "lr": 1.835007823250264e-05, "epoch": 12.542879417879417, "percentage": 62.71, "elapsed_time": "1:10:07", "remaining_time": "0:41:41", "throughput": 1032.71, "total_tokens": 4345272} {"current_steps": 48270, "total_steps": 76960, "loss": 0.1985, "lr": 1.8344613058466547e-05, "epoch": 12.544178794178794, "percentage": 62.72, "elapsed_time": "1:10:08", "remaining_time": "0:41:41", "throughput": 1032.72, "total_tokens": 4345752} {"current_steps": 48275, "total_steps": 76960, "loss": 0.1371, "lr": 1.8339148226723378e-05, "epoch": 12.545478170478171, "percentage": 62.73, "elapsed_time": "1:10:08", "remaining_time": "0:41:40", "throughput": 1032.72, "total_tokens": 4346184} {"current_steps": 48280, "total_steps": 76960, "loss": 0.147, "lr": 1.8333683737554207e-05, "epoch": 12.546777546777546, "percentage": 62.73, "elapsed_time": "1:10:08", "remaining_time": "0:41:40", "throughput": 1032.72, "total_tokens": 4346616} {"current_steps": 48285, "total_steps": 76960, "loss": 0.1941, "lr": 1.832821959124006e-05, "epoch": 12.548076923076923, "percentage": 62.74, "elapsed_time": "1:10:09", "remaining_time": "0:41:39", "throughput": 1032.74, "total_tokens": 4347112} {"current_steps": 48290, "total_steps": 76960, "loss": 0.2061, "lr": 1.8322755788061975e-05, "epoch": 12.549376299376299, "percentage": 62.75, "elapsed_time": "1:10:09", "remaining_time": "0:41:39", "throughput": 1032.75, "total_tokens": 4347576} {"current_steps": 48295, "total_steps": 76960, "loss": 0.1515, "lr": 1.831729232830095e-05, "epoch": 12.550675675675675, "percentage": 62.75, "elapsed_time": "1:10:10", "remaining_time": "0:41:38", "throughput": 1032.75, "total_tokens": 4348008} {"current_steps": 48300, "total_steps": 76960, "loss": 0.3311, "lr": 1.8311829212237995e-05, "epoch": 12.551975051975052, "percentage": 62.76, "elapsed_time": "1:10:10", "remaining_time": "0:41:38", "throughput": 1032.75, "total_tokens": 4348440} {"current_steps": 48305, "total_steps": 76960, "loss": 0.1771, "lr": 1.8306366440154066e-05, "epoch": 12.553274428274428, "percentage": 62.77, "elapsed_time": "1:10:10", "remaining_time": "0:41:37", "throughput": 1032.76, "total_tokens": 4348904} {"current_steps": 48310, "total_steps": 76960, "loss": 0.4069, "lr": 1.8300904012330127e-05, "epoch": 12.554573804573804, "percentage": 62.77, "elapsed_time": "1:10:11", "remaining_time": "0:41:37", "throughput": 1032.76, "total_tokens": 4349336} {"current_steps": 48315, "total_steps": 76960, "loss": 0.3278, "lr": 1.829544192904711e-05, "epoch": 12.555873180873181, "percentage": 62.78, "elapsed_time": "1:10:11", "remaining_time": "0:41:37", "throughput": 1032.76, "total_tokens": 4349784} {"current_steps": 48320, "total_steps": 76960, "loss": 0.2157, "lr": 1.828998019058595e-05, "epoch": 12.557172557172557, "percentage": 62.79, "elapsed_time": "1:10:12", "remaining_time": "0:41:36", "throughput": 1032.77, "total_tokens": 4350232} {"current_steps": 48325, "total_steps": 76960, "loss": 0.4988, "lr": 1.828451879722752e-05, "epoch": 12.558471933471933, "percentage": 62.79, "elapsed_time": "1:10:12", "remaining_time": "0:41:36", "throughput": 1032.77, "total_tokens": 4350680} {"current_steps": 48330, "total_steps": 76960, "loss": 0.1696, "lr": 1.8279057749252736e-05, "epoch": 12.55977130977131, "percentage": 62.8, "elapsed_time": "1:10:13", "remaining_time": "0:41:35", "throughput": 1032.77, "total_tokens": 4351128} {"current_steps": 48335, "total_steps": 76960, "loss": 0.1324, "lr": 1.8273597046942453e-05, "epoch": 12.561070686070686, "percentage": 62.81, "elapsed_time": "1:10:13", "remaining_time": "0:41:35", "throughput": 1032.77, "total_tokens": 4351560} {"current_steps": 48340, "total_steps": 76960, "loss": 0.3559, "lr": 1.8268136690577502e-05, "epoch": 12.562370062370062, "percentage": 62.81, "elapsed_time": "1:10:13", "remaining_time": "0:41:34", "throughput": 1032.79, "total_tokens": 4352040} {"current_steps": 48345, "total_steps": 76960, "loss": 0.2671, "lr": 1.826267668043875e-05, "epoch": 12.56366943866944, "percentage": 62.82, "elapsed_time": "1:10:14", "remaining_time": "0:41:34", "throughput": 1032.79, "total_tokens": 4352472} {"current_steps": 48350, "total_steps": 76960, "loss": 0.0755, "lr": 1.8257217016806982e-05, "epoch": 12.564968814968815, "percentage": 62.82, "elapsed_time": "1:10:14", "remaining_time": "0:41:33", "throughput": 1032.79, "total_tokens": 4352920} {"current_steps": 48355, "total_steps": 76960, "loss": 0.2455, "lr": 1.8251757699963006e-05, "epoch": 12.566268191268192, "percentage": 62.83, "elapsed_time": "1:10:15", "remaining_time": "0:41:33", "throughput": 1032.8, "total_tokens": 4353384} {"current_steps": 48360, "total_steps": 76960, "loss": 0.3831, "lr": 1.824629873018759e-05, "epoch": 12.567567567567568, "percentage": 62.84, "elapsed_time": "1:10:15", "remaining_time": "0:41:33", "throughput": 1032.8, "total_tokens": 4353832} {"current_steps": 48365, "total_steps": 76960, "loss": 0.1428, "lr": 1.8240840107761516e-05, "epoch": 12.568866943866944, "percentage": 62.84, "elapsed_time": "1:10:15", "remaining_time": "0:41:32", "throughput": 1032.81, "total_tokens": 4354296} {"current_steps": 48370, "total_steps": 76960, "loss": 0.0217, "lr": 1.82353818329655e-05, "epoch": 12.57016632016632, "percentage": 62.85, "elapsed_time": "1:10:16", "remaining_time": "0:41:32", "throughput": 1032.82, "total_tokens": 4354776} {"current_steps": 48375, "total_steps": 76960, "loss": 0.7209, "lr": 1.822992390608028e-05, "epoch": 12.571465696465696, "percentage": 62.86, "elapsed_time": "1:10:16", "remaining_time": "0:41:31", "throughput": 1032.82, "total_tokens": 4355208} {"current_steps": 48380, "total_steps": 76960, "loss": 0.1511, "lr": 1.8224466327386564e-05, "epoch": 12.572765072765073, "percentage": 62.86, "elapsed_time": "1:10:17", "remaining_time": "0:41:31", "throughput": 1032.82, "total_tokens": 4355624} {"current_steps": 48385, "total_steps": 76960, "loss": 0.2548, "lr": 1.821900909716504e-05, "epoch": 12.57406444906445, "percentage": 62.87, "elapsed_time": "1:10:17", "remaining_time": "0:41:30", "throughput": 1032.83, "total_tokens": 4356088} {"current_steps": 48390, "total_steps": 76960, "loss": 0.3517, "lr": 1.8213552215696367e-05, "epoch": 12.575363825363825, "percentage": 62.88, "elapsed_time": "1:10:18", "remaining_time": "0:41:30", "throughput": 1032.84, "total_tokens": 4356552} {"current_steps": 48395, "total_steps": 76960, "loss": 0.0764, "lr": 1.820809568326121e-05, "epoch": 12.576663201663202, "percentage": 62.88, "elapsed_time": "1:10:18", "remaining_time": "0:41:29", "throughput": 1032.84, "total_tokens": 4357000} {"current_steps": 48400, "total_steps": 76960, "loss": 0.1188, "lr": 1.8202639500140203e-05, "epoch": 12.577962577962579, "percentage": 62.89, "elapsed_time": "1:10:18", "remaining_time": "0:41:29", "throughput": 1032.85, "total_tokens": 4357448} {"current_steps": 48405, "total_steps": 76960, "loss": 0.2892, "lr": 1.8197183666613953e-05, "epoch": 12.579261954261954, "percentage": 62.9, "elapsed_time": "1:10:19", "remaining_time": "0:41:29", "throughput": 1032.85, "total_tokens": 4357912} {"current_steps": 48410, "total_steps": 76960, "loss": 0.2227, "lr": 1.8191728182963068e-05, "epoch": 12.58056133056133, "percentage": 62.9, "elapsed_time": "1:10:19", "remaining_time": "0:41:28", "throughput": 1032.85, "total_tokens": 4358328} {"current_steps": 48415, "total_steps": 76960, "loss": 0.1558, "lr": 1.8186273049468122e-05, "epoch": 12.581860706860708, "percentage": 62.91, "elapsed_time": "1:10:20", "remaining_time": "0:41:28", "throughput": 1032.86, "total_tokens": 4358792} {"current_steps": 48420, "total_steps": 76960, "loss": 0.2395, "lr": 1.818081826640969e-05, "epoch": 12.583160083160083, "percentage": 62.92, "elapsed_time": "1:10:20", "remaining_time": "0:41:27", "throughput": 1032.86, "total_tokens": 4359240} {"current_steps": 48425, "total_steps": 76960, "loss": 0.1481, "lr": 1.81753638340683e-05, "epoch": 12.58445945945946, "percentage": 62.92, "elapsed_time": "1:10:20", "remaining_time": "0:41:27", "throughput": 1032.87, "total_tokens": 4359704} {"current_steps": 48430, "total_steps": 76960, "loss": 0.3667, "lr": 1.8169909752724494e-05, "epoch": 12.585758835758837, "percentage": 62.93, "elapsed_time": "1:10:21", "remaining_time": "0:41:26", "throughput": 1032.88, "total_tokens": 4360152} {"current_steps": 48435, "total_steps": 76960, "loss": 0.0871, "lr": 1.8164456022658767e-05, "epoch": 12.587058212058212, "percentage": 62.94, "elapsed_time": "1:10:21", "remaining_time": "0:41:26", "throughput": 1032.88, "total_tokens": 4360600} {"current_steps": 48440, "total_steps": 76960, "loss": 0.2339, "lr": 1.8159002644151625e-05, "epoch": 12.588357588357589, "percentage": 62.94, "elapsed_time": "1:10:22", "remaining_time": "0:41:25", "throughput": 1032.89, "total_tokens": 4361064} {"current_steps": 48445, "total_steps": 76960, "loss": 0.0237, "lr": 1.815354961748352e-05, "epoch": 12.589656964656964, "percentage": 62.95, "elapsed_time": "1:10:22", "remaining_time": "0:41:25", "throughput": 1032.9, "total_tokens": 4361544} {"current_steps": 48450, "total_steps": 76960, "loss": 0.3492, "lr": 1.8148096942934928e-05, "epoch": 12.59095634095634, "percentage": 62.95, "elapsed_time": "1:10:23", "remaining_time": "0:41:25", "throughput": 1032.92, "total_tokens": 4362056} {"current_steps": 48455, "total_steps": 76960, "loss": 0.1179, "lr": 1.8142644620786264e-05, "epoch": 12.592255717255718, "percentage": 62.96, "elapsed_time": "1:10:23", "remaining_time": "0:41:24", "throughput": 1032.92, "total_tokens": 4362488} {"current_steps": 48460, "total_steps": 76960, "loss": 0.0505, "lr": 1.8137192651317973e-05, "epoch": 12.593555093555093, "percentage": 62.97, "elapsed_time": "1:10:23", "remaining_time": "0:41:24", "throughput": 1032.92, "total_tokens": 4362936} {"current_steps": 48465, "total_steps": 76960, "loss": 0.1697, "lr": 1.8131741034810435e-05, "epoch": 12.59485446985447, "percentage": 62.97, "elapsed_time": "1:10:24", "remaining_time": "0:41:23", "throughput": 1032.93, "total_tokens": 4363400} {"current_steps": 48470, "total_steps": 76960, "loss": 0.1991, "lr": 1.812628977154403e-05, "epoch": 12.596153846153847, "percentage": 62.98, "elapsed_time": "1:10:24", "remaining_time": "0:41:23", "throughput": 1032.94, "total_tokens": 4363864} {"current_steps": 48475, "total_steps": 76960, "loss": 0.3568, "lr": 1.8120838861799135e-05, "epoch": 12.597453222453222, "percentage": 62.99, "elapsed_time": "1:10:25", "remaining_time": "0:41:22", "throughput": 1032.95, "total_tokens": 4364328} {"current_steps": 48480, "total_steps": 76960, "loss": 0.1545, "lr": 1.8115388305856082e-05, "epoch": 12.598752598752599, "percentage": 62.99, "elapsed_time": "1:10:25", "remaining_time": "0:41:22", "throughput": 1032.95, "total_tokens": 4364760} {"current_steps": 48485, "total_steps": 76960, "loss": 0.5085, "lr": 1.810993810399521e-05, "epoch": 12.600051975051976, "percentage": 63.0, "elapsed_time": "1:10:25", "remaining_time": "0:41:21", "throughput": 1032.96, "total_tokens": 4365224} {"current_steps": 48490, "total_steps": 76960, "loss": 0.3994, "lr": 1.8104488256496816e-05, "epoch": 12.60135135135135, "percentage": 63.01, "elapsed_time": "1:10:26", "remaining_time": "0:41:21", "throughput": 1032.97, "total_tokens": 4365688} {"current_steps": 48495, "total_steps": 76960, "loss": 0.0347, "lr": 1.809903876364121e-05, "epoch": 12.602650727650728, "percentage": 63.01, "elapsed_time": "1:10:26", "remaining_time": "0:41:20", "throughput": 1032.97, "total_tokens": 4366120} {"current_steps": 48500, "total_steps": 76960, "loss": 0.3574, "lr": 1.809358962570864e-05, "epoch": 12.603950103950105, "percentage": 63.02, "elapsed_time": "1:10:27", "remaining_time": "0:41:20", "throughput": 1032.97, "total_tokens": 4366552} {"current_steps": 48505, "total_steps": 76960, "loss": 0.649, "lr": 1.8088140842979383e-05, "epoch": 12.60524948024948, "percentage": 63.03, "elapsed_time": "1:10:27", "remaining_time": "0:41:20", "throughput": 1032.97, "total_tokens": 4367000} {"current_steps": 48510, "total_steps": 76960, "loss": 0.3116, "lr": 1.8082692415733654e-05, "epoch": 12.606548856548857, "percentage": 63.03, "elapsed_time": "1:10:28", "remaining_time": "0:41:19", "throughput": 1032.98, "total_tokens": 4367448} {"current_steps": 48515, "total_steps": 76960, "loss": 0.1312, "lr": 1.8077244344251697e-05, "epoch": 12.607848232848234, "percentage": 63.04, "elapsed_time": "1:10:28", "remaining_time": "0:41:19", "throughput": 1032.98, "total_tokens": 4367912} {"current_steps": 48520, "total_steps": 76960, "loss": 0.2751, "lr": 1.807179662881368e-05, "epoch": 12.609147609147609, "percentage": 63.05, "elapsed_time": "1:10:28", "remaining_time": "0:41:18", "throughput": 1032.99, "total_tokens": 4368376} {"current_steps": 48525, "total_steps": 76960, "loss": 0.1402, "lr": 1.806634926969981e-05, "epoch": 12.610446985446986, "percentage": 63.05, "elapsed_time": "1:10:29", "remaining_time": "0:41:18", "throughput": 1033.0, "total_tokens": 4368856} {"current_steps": 48530, "total_steps": 76960, "loss": 0.2063, "lr": 1.806090226719025e-05, "epoch": 12.611746361746361, "percentage": 63.06, "elapsed_time": "1:10:29", "remaining_time": "0:41:17", "throughput": 1033.02, "total_tokens": 4369336} {"current_steps": 48535, "total_steps": 76960, "loss": 0.2717, "lr": 1.8055455621565117e-05, "epoch": 12.613045738045738, "percentage": 63.07, "elapsed_time": "1:10:30", "remaining_time": "0:41:17", "throughput": 1033.02, "total_tokens": 4369768} {"current_steps": 48540, "total_steps": 76960, "loss": 0.1483, "lr": 1.8050009333104566e-05, "epoch": 12.614345114345115, "percentage": 63.07, "elapsed_time": "1:10:30", "remaining_time": "0:41:16", "throughput": 1033.02, "total_tokens": 4370216} {"current_steps": 48545, "total_steps": 76960, "loss": 0.3515, "lr": 1.8044563402088684e-05, "epoch": 12.61564449064449, "percentage": 63.08, "elapsed_time": "1:10:30", "remaining_time": "0:41:16", "throughput": 1033.03, "total_tokens": 4370680} {"current_steps": 48550, "total_steps": 76960, "loss": 0.0502, "lr": 1.8039117828797586e-05, "epoch": 12.616943866943867, "percentage": 63.08, "elapsed_time": "1:10:31", "remaining_time": "0:41:16", "throughput": 1033.04, "total_tokens": 4371144} {"current_steps": 48555, "total_steps": 76960, "loss": 0.0735, "lr": 1.8033672613511317e-05, "epoch": 12.618243243243244, "percentage": 63.09, "elapsed_time": "1:10:31", "remaining_time": "0:41:15", "throughput": 1033.03, "total_tokens": 4371560} {"current_steps": 48560, "total_steps": 76960, "loss": 0.3173, "lr": 1.8028227756509942e-05, "epoch": 12.619542619542619, "percentage": 63.1, "elapsed_time": "1:10:32", "remaining_time": "0:41:15", "throughput": 1033.04, "total_tokens": 4372024} {"current_steps": 48565, "total_steps": 76960, "loss": 0.2856, "lr": 1.802278325807349e-05, "epoch": 12.620841995841996, "percentage": 63.1, "elapsed_time": "1:10:32", "remaining_time": "0:41:14", "throughput": 1033.04, "total_tokens": 4372472} {"current_steps": 48570, "total_steps": 76960, "loss": 0.3532, "lr": 1.801733911848199e-05, "epoch": 12.622141372141373, "percentage": 63.11, "elapsed_time": "1:10:33", "remaining_time": "0:41:14", "throughput": 1033.05, "total_tokens": 4372904} {"current_steps": 48575, "total_steps": 76960, "loss": 0.5184, "lr": 1.8011895338015415e-05, "epoch": 12.623440748440748, "percentage": 63.12, "elapsed_time": "1:10:33", "remaining_time": "0:41:13", "throughput": 1033.05, "total_tokens": 4373336} {"current_steps": 48580, "total_steps": 76960, "loss": 0.5869, "lr": 1.800645191695377e-05, "epoch": 12.624740124740125, "percentage": 63.12, "elapsed_time": "1:10:33", "remaining_time": "0:41:13", "throughput": 1033.05, "total_tokens": 4373784} {"current_steps": 48585, "total_steps": 76960, "loss": 0.4032, "lr": 1.8001008855577e-05, "epoch": 12.6260395010395, "percentage": 63.13, "elapsed_time": "1:10:34", "remaining_time": "0:41:12", "throughput": 1033.05, "total_tokens": 4374200} {"current_steps": 48590, "total_steps": 76960, "loss": 0.163, "lr": 1.799556615416505e-05, "epoch": 12.627338877338877, "percentage": 63.14, "elapsed_time": "1:10:34", "remaining_time": "0:41:12", "throughput": 1033.05, "total_tokens": 4374648} {"current_steps": 48595, "total_steps": 76960, "loss": 0.062, "lr": 1.7990123812997854e-05, "epoch": 12.628638253638254, "percentage": 63.14, "elapsed_time": "1:10:35", "remaining_time": "0:41:12", "throughput": 1033.05, "total_tokens": 4375080} {"current_steps": 48600, "total_steps": 76960, "loss": 0.4218, "lr": 1.7984681832355295e-05, "epoch": 12.62993762993763, "percentage": 63.15, "elapsed_time": "1:10:35", "remaining_time": "0:41:11", "throughput": 1033.06, "total_tokens": 4375528} {"current_steps": 48605, "total_steps": 76960, "loss": 0.2831, "lr": 1.7979240212517275e-05, "epoch": 12.631237006237006, "percentage": 63.16, "elapsed_time": "1:10:35", "remaining_time": "0:41:11", "throughput": 1033.06, "total_tokens": 4375992} {"current_steps": 48610, "total_steps": 76960, "loss": 0.2204, "lr": 1.7973798953763654e-05, "epoch": 12.632536382536383, "percentage": 63.16, "elapsed_time": "1:10:36", "remaining_time": "0:41:10", "throughput": 1033.08, "total_tokens": 4376488} {"current_steps": 48615, "total_steps": 76960, "loss": 0.102, "lr": 1.7968358056374295e-05, "epoch": 12.633835758835758, "percentage": 63.17, "elapsed_time": "1:10:36", "remaining_time": "0:41:10", "throughput": 1033.08, "total_tokens": 4376920} {"current_steps": 48620, "total_steps": 76960, "loss": 0.2225, "lr": 1.7962917520629008e-05, "epoch": 12.635135135135135, "percentage": 63.18, "elapsed_time": "1:10:37", "remaining_time": "0:41:09", "throughput": 1033.09, "total_tokens": 4377384} {"current_steps": 48625, "total_steps": 76960, "loss": 0.3102, "lr": 1.795747734680762e-05, "epoch": 12.636434511434512, "percentage": 63.18, "elapsed_time": "1:10:37", "remaining_time": "0:41:09", "throughput": 1033.09, "total_tokens": 4377800} {"current_steps": 48630, "total_steps": 76960, "loss": 0.0746, "lr": 1.7952037535189916e-05, "epoch": 12.637733887733887, "percentage": 63.19, "elapsed_time": "1:10:38", "remaining_time": "0:41:08", "throughput": 1033.09, "total_tokens": 4378232} {"current_steps": 48635, "total_steps": 76960, "loss": 0.2894, "lr": 1.7946598086055684e-05, "epoch": 12.639033264033264, "percentage": 63.2, "elapsed_time": "1:10:38", "remaining_time": "0:41:08", "throughput": 1033.08, "total_tokens": 4378648} {"current_steps": 48640, "total_steps": 76960, "loss": 0.2114, "lr": 1.794115899968466e-05, "epoch": 12.640332640332641, "percentage": 63.2, "elapsed_time": "1:10:38", "remaining_time": "0:41:08", "throughput": 1033.09, "total_tokens": 4379096} {"current_steps": 48645, "total_steps": 76960, "loss": 0.0464, "lr": 1.7935720276356598e-05, "epoch": 12.641632016632016, "percentage": 63.21, "elapsed_time": "1:10:39", "remaining_time": "0:41:07", "throughput": 1033.09, "total_tokens": 4379544} {"current_steps": 48650, "total_steps": 76960, "loss": 0.4364, "lr": 1.7930281916351205e-05, "epoch": 12.642931392931393, "percentage": 63.21, "elapsed_time": "1:10:39", "remaining_time": "0:41:07", "throughput": 1033.1, "total_tokens": 4379992} {"current_steps": 48655, "total_steps": 76960, "loss": 0.4985, "lr": 1.79248439199482e-05, "epoch": 12.64423076923077, "percentage": 63.22, "elapsed_time": "1:10:40", "remaining_time": "0:41:06", "throughput": 1033.1, "total_tokens": 4380424} {"current_steps": 48660, "total_steps": 76960, "loss": 0.1554, "lr": 1.7919406287427244e-05, "epoch": 12.645530145530145, "percentage": 63.23, "elapsed_time": "1:10:40", "remaining_time": "0:41:06", "throughput": 1033.11, "total_tokens": 4380904} {"current_steps": 48665, "total_steps": 76960, "loss": 0.3095, "lr": 1.7913969019068e-05, "epoch": 12.646829521829522, "percentage": 63.23, "elapsed_time": "1:10:40", "remaining_time": "0:41:05", "throughput": 1033.11, "total_tokens": 4381352} {"current_steps": 48670, "total_steps": 76960, "loss": 0.553, "lr": 1.7908532115150135e-05, "epoch": 12.648128898128899, "percentage": 63.24, "elapsed_time": "1:10:41", "remaining_time": "0:41:05", "throughput": 1033.12, "total_tokens": 4381816} {"current_steps": 48675, "total_steps": 76960, "loss": 0.2639, "lr": 1.790309557595324e-05, "epoch": 12.649428274428274, "percentage": 63.25, "elapsed_time": "1:10:41", "remaining_time": "0:41:04", "throughput": 1033.12, "total_tokens": 4382248} {"current_steps": 48680, "total_steps": 76960, "loss": 0.2322, "lr": 1.789765940175695e-05, "epoch": 12.650727650727651, "percentage": 63.25, "elapsed_time": "1:10:42", "remaining_time": "0:41:04", "throughput": 1033.13, "total_tokens": 4382728} {"current_steps": 48685, "total_steps": 76960, "loss": 0.2149, "lr": 1.7892223592840834e-05, "epoch": 12.652027027027026, "percentage": 63.26, "elapsed_time": "1:10:42", "remaining_time": "0:41:03", "throughput": 1033.13, "total_tokens": 4383144} {"current_steps": 48690, "total_steps": 76960, "loss": 0.222, "lr": 1.788678814948448e-05, "epoch": 12.653326403326403, "percentage": 63.27, "elapsed_time": "1:10:43", "remaining_time": "0:41:03", "throughput": 1033.13, "total_tokens": 4383576} {"current_steps": 48695, "total_steps": 76960, "loss": 0.1568, "lr": 1.7881353071967415e-05, "epoch": 12.65462577962578, "percentage": 63.27, "elapsed_time": "1:10:43", "remaining_time": "0:41:03", "throughput": 1033.14, "total_tokens": 4384040} {"current_steps": 48700, "total_steps": 76960, "loss": 0.2641, "lr": 1.7875918360569195e-05, "epoch": 12.655925155925155, "percentage": 63.28, "elapsed_time": "1:10:43", "remaining_time": "0:41:02", "throughput": 1033.15, "total_tokens": 4384520} {"current_steps": 48705, "total_steps": 76960, "loss": 0.0848, "lr": 1.7870484015569306e-05, "epoch": 12.657224532224532, "percentage": 63.29, "elapsed_time": "1:10:44", "remaining_time": "0:41:02", "throughput": 1033.16, "total_tokens": 4384984} {"current_steps": 48710, "total_steps": 76960, "loss": 0.3707, "lr": 1.786505003724727e-05, "epoch": 12.65852390852391, "percentage": 63.29, "elapsed_time": "1:10:44", "remaining_time": "0:41:01", "throughput": 1033.16, "total_tokens": 4385432} {"current_steps": 48715, "total_steps": 76960, "loss": 0.4363, "lr": 1.7859616425882536e-05, "epoch": 12.659823284823284, "percentage": 63.3, "elapsed_time": "1:10:45", "remaining_time": "0:41:01", "throughput": 1033.17, "total_tokens": 4385896} {"current_steps": 48720, "total_steps": 76960, "loss": 0.0741, "lr": 1.7854183181754574e-05, "epoch": 12.661122661122661, "percentage": 63.31, "elapsed_time": "1:10:45", "remaining_time": "0:41:00", "throughput": 1033.2, "total_tokens": 4386440} {"current_steps": 48725, "total_steps": 76960, "loss": 0.2904, "lr": 1.7848750305142824e-05, "epoch": 12.662422037422038, "percentage": 63.31, "elapsed_time": "1:10:45", "remaining_time": "0:41:00", "throughput": 1033.2, "total_tokens": 4386888} {"current_steps": 48730, "total_steps": 76960, "loss": 0.0268, "lr": 1.7843317796326688e-05, "epoch": 12.663721413721413, "percentage": 63.32, "elapsed_time": "1:10:46", "remaining_time": "0:40:59", "throughput": 1033.2, "total_tokens": 4387320} {"current_steps": 48735, "total_steps": 76960, "loss": 0.2905, "lr": 1.7837885655585578e-05, "epoch": 12.66502079002079, "percentage": 63.33, "elapsed_time": "1:10:46", "remaining_time": "0:40:59", "throughput": 1033.21, "total_tokens": 4387768} {"current_steps": 48740, "total_steps": 76960, "loss": 0.479, "lr": 1.783245388319887e-05, "epoch": 12.666320166320165, "percentage": 63.33, "elapsed_time": "1:10:47", "remaining_time": "0:40:59", "throughput": 1033.21, "total_tokens": 4388200} {"current_steps": 48745, "total_steps": 76960, "loss": 0.3655, "lr": 1.7827022479445935e-05, "epoch": 12.667619542619542, "percentage": 63.34, "elapsed_time": "1:10:47", "remaining_time": "0:40:58", "throughput": 1033.2, "total_tokens": 4388616} {"current_steps": 48750, "total_steps": 76960, "loss": 0.1411, "lr": 1.7821591444606094e-05, "epoch": 12.66891891891892, "percentage": 63.34, "elapsed_time": "1:10:48", "remaining_time": "0:40:58", "throughput": 1033.22, "total_tokens": 4389128} {"current_steps": 48755, "total_steps": 76960, "loss": 0.2761, "lr": 1.781616077895869e-05, "epoch": 12.670218295218294, "percentage": 63.35, "elapsed_time": "1:10:48", "remaining_time": "0:40:57", "throughput": 1033.23, "total_tokens": 4389608} {"current_steps": 48760, "total_steps": 76960, "loss": 0.1218, "lr": 1.7810730482783017e-05, "epoch": 12.671517671517671, "percentage": 63.36, "elapsed_time": "1:10:48", "remaining_time": "0:40:57", "throughput": 1033.25, "total_tokens": 4390088} {"current_steps": 48765, "total_steps": 76960, "loss": 0.2898, "lr": 1.7805300556358372e-05, "epoch": 12.672817047817048, "percentage": 63.36, "elapsed_time": "1:10:49", "remaining_time": "0:40:56", "throughput": 1033.25, "total_tokens": 4390536} {"current_steps": 48770, "total_steps": 76960, "loss": 0.1818, "lr": 1.7799870999964004e-05, "epoch": 12.674116424116423, "percentage": 63.37, "elapsed_time": "1:10:49", "remaining_time": "0:40:56", "throughput": 1033.25, "total_tokens": 4390984} {"current_steps": 48775, "total_steps": 76960, "loss": 0.2527, "lr": 1.7794441813879172e-05, "epoch": 12.6754158004158, "percentage": 63.38, "elapsed_time": "1:10:50", "remaining_time": "0:40:55", "throughput": 1033.26, "total_tokens": 4391432} {"current_steps": 48780, "total_steps": 76960, "loss": 0.1397, "lr": 1.7789012998383096e-05, "epoch": 12.676715176715177, "percentage": 63.38, "elapsed_time": "1:10:50", "remaining_time": "0:40:55", "throughput": 1033.26, "total_tokens": 4391864} {"current_steps": 48785, "total_steps": 76960, "loss": 0.2479, "lr": 1.7783584553755006e-05, "epoch": 12.678014553014552, "percentage": 63.39, "elapsed_time": "1:10:50", "remaining_time": "0:40:55", "throughput": 1033.26, "total_tokens": 4392280} {"current_steps": 48790, "total_steps": 76960, "loss": 0.1509, "lr": 1.7778156480274066e-05, "epoch": 12.67931392931393, "percentage": 63.4, "elapsed_time": "1:10:51", "remaining_time": "0:40:54", "throughput": 1033.26, "total_tokens": 4392728} {"current_steps": 48795, "total_steps": 76960, "loss": 0.4261, "lr": 1.777272877821946e-05, "epoch": 12.680613305613306, "percentage": 63.4, "elapsed_time": "1:10:51", "remaining_time": "0:40:54", "throughput": 1033.27, "total_tokens": 4393192} {"current_steps": 48800, "total_steps": 76960, "loss": 0.1875, "lr": 1.7767301447870342e-05, "epoch": 12.681912681912682, "percentage": 63.41, "elapsed_time": "1:10:52", "remaining_time": "0:40:53", "throughput": 1033.28, "total_tokens": 4393656} {"current_steps": 48805, "total_steps": 76960, "loss": 0.3089, "lr": 1.776187448950583e-05, "epoch": 12.683212058212058, "percentage": 63.42, "elapsed_time": "1:10:52", "remaining_time": "0:40:53", "throughput": 1033.27, "total_tokens": 4394072} {"current_steps": 48810, "total_steps": 76960, "loss": 0.2825, "lr": 1.7756447903405053e-05, "epoch": 12.684511434511435, "percentage": 63.42, "elapsed_time": "1:10:52", "remaining_time": "0:40:52", "throughput": 1033.29, "total_tokens": 4394552} {"current_steps": 48815, "total_steps": 76960, "loss": 0.0914, "lr": 1.77510216898471e-05, "epoch": 12.68581081081081, "percentage": 63.43, "elapsed_time": "1:10:53", "remaining_time": "0:40:52", "throughput": 1033.28, "total_tokens": 4394952} {"current_steps": 48820, "total_steps": 76960, "loss": 0.2538, "lr": 1.7745595849111056e-05, "epoch": 12.687110187110187, "percentage": 63.44, "elapsed_time": "1:10:53", "remaining_time": "0:40:51", "throughput": 1033.27, "total_tokens": 4395352} {"current_steps": 48825, "total_steps": 76960, "loss": 0.1742, "lr": 1.7740170381475953e-05, "epoch": 12.688409563409563, "percentage": 63.44, "elapsed_time": "1:10:54", "remaining_time": "0:40:51", "throughput": 1033.28, "total_tokens": 4395816} {"current_steps": 48830, "total_steps": 76960, "loss": 0.2394, "lr": 1.7734745287220854e-05, "epoch": 12.68970893970894, "percentage": 63.45, "elapsed_time": "1:10:54", "remaining_time": "0:40:51", "throughput": 1033.28, "total_tokens": 4396232} {"current_steps": 48835, "total_steps": 76960, "loss": 0.3203, "lr": 1.772932056662476e-05, "epoch": 12.691008316008316, "percentage": 63.46, "elapsed_time": "1:10:55", "remaining_time": "0:40:50", "throughput": 1033.28, "total_tokens": 4396664} {"current_steps": 48840, "total_steps": 76960, "loss": 0.0746, "lr": 1.772389621996668e-05, "epoch": 12.692307692307692, "percentage": 63.46, "elapsed_time": "1:10:55", "remaining_time": "0:40:50", "throughput": 1033.28, "total_tokens": 4397112} {"current_steps": 48845, "total_steps": 76960, "loss": 0.8697, "lr": 1.7718472247525585e-05, "epoch": 12.693607068607069, "percentage": 63.47, "elapsed_time": "1:10:55", "remaining_time": "0:40:49", "throughput": 1033.3, "total_tokens": 4397624} {"current_steps": 48850, "total_steps": 76960, "loss": 0.5203, "lr": 1.771304864958045e-05, "epoch": 12.694906444906445, "percentage": 63.47, "elapsed_time": "1:10:56", "remaining_time": "0:40:49", "throughput": 1033.3, "total_tokens": 4398072} {"current_steps": 48855, "total_steps": 76960, "loss": 0.2258, "lr": 1.7707625426410194e-05, "epoch": 12.69620582120582, "percentage": 63.48, "elapsed_time": "1:10:56", "remaining_time": "0:40:48", "throughput": 1033.31, "total_tokens": 4398536} {"current_steps": 48860, "total_steps": 76960, "loss": 0.1798, "lr": 1.7702202578293754e-05, "epoch": 12.697505197505198, "percentage": 63.49, "elapsed_time": "1:10:57", "remaining_time": "0:40:48", "throughput": 1033.32, "total_tokens": 4398984} {"current_steps": 48865, "total_steps": 76960, "loss": 0.0414, "lr": 1.769678010551003e-05, "epoch": 12.698804573804575, "percentage": 63.49, "elapsed_time": "1:10:57", "remaining_time": "0:40:47", "throughput": 1033.32, "total_tokens": 4399432} {"current_steps": 48870, "total_steps": 76960, "loss": 0.2724, "lr": 1.76913580083379e-05, "epoch": 12.70010395010395, "percentage": 63.5, "elapsed_time": "1:10:57", "remaining_time": "0:40:47", "throughput": 1033.32, "total_tokens": 4399864} {"current_steps": 48875, "total_steps": 76960, "loss": 0.116, "lr": 1.7685936287056228e-05, "epoch": 12.701403326403327, "percentage": 63.51, "elapsed_time": "1:10:58", "remaining_time": "0:40:47", "throughput": 1033.32, "total_tokens": 4400296} {"current_steps": 48880, "total_steps": 76960, "loss": 0.3039, "lr": 1.768051494194386e-05, "epoch": 12.702702702702704, "percentage": 63.51, "elapsed_time": "1:10:58", "remaining_time": "0:40:46", "throughput": 1033.32, "total_tokens": 4400728} {"current_steps": 48885, "total_steps": 76960, "loss": 0.1289, "lr": 1.767509397327963e-05, "epoch": 12.704002079002079, "percentage": 63.52, "elapsed_time": "1:10:59", "remaining_time": "0:40:46", "throughput": 1033.33, "total_tokens": 4401192} {"current_steps": 48890, "total_steps": 76960, "loss": 0.3322, "lr": 1.7669673381342328e-05, "epoch": 12.705301455301456, "percentage": 63.53, "elapsed_time": "1:10:59", "remaining_time": "0:40:45", "throughput": 1033.34, "total_tokens": 4401672} {"current_steps": 48895, "total_steps": 76960, "loss": 0.2773, "lr": 1.766425316641075e-05, "epoch": 12.70660083160083, "percentage": 63.53, "elapsed_time": "1:11:00", "remaining_time": "0:40:45", "throughput": 1033.35, "total_tokens": 4402120} {"current_steps": 48900, "total_steps": 76960, "loss": 0.3505, "lr": 1.7658833328763653e-05, "epoch": 12.707900207900208, "percentage": 63.54, "elapsed_time": "1:11:00", "remaining_time": "0:40:44", "throughput": 1033.36, "total_tokens": 4402616} {"current_steps": 48905, "total_steps": 76960, "loss": 0.2649, "lr": 1.7653413868679804e-05, "epoch": 12.709199584199585, "percentage": 63.55, "elapsed_time": "1:11:00", "remaining_time": "0:40:44", "throughput": 1033.36, "total_tokens": 4403048} {"current_steps": 48910, "total_steps": 76960, "loss": 0.184, "lr": 1.764799478643791e-05, "epoch": 12.71049896049896, "percentage": 63.55, "elapsed_time": "1:11:01", "remaining_time": "0:40:43", "throughput": 1033.36, "total_tokens": 4403480} {"current_steps": 48915, "total_steps": 76960, "loss": 0.0506, "lr": 1.7642576082316695e-05, "epoch": 12.711798336798337, "percentage": 63.56, "elapsed_time": "1:11:01", "remaining_time": "0:40:43", "throughput": 1033.37, "total_tokens": 4403944} {"current_steps": 48920, "total_steps": 76960, "loss": 0.2075, "lr": 1.7637157756594836e-05, "epoch": 12.713097713097714, "percentage": 63.57, "elapsed_time": "1:11:02", "remaining_time": "0:40:42", "throughput": 1033.37, "total_tokens": 4404360} {"current_steps": 48925, "total_steps": 76960, "loss": 0.1627, "lr": 1.7631739809551014e-05, "epoch": 12.714397089397089, "percentage": 63.57, "elapsed_time": "1:11:02", "remaining_time": "0:40:42", "throughput": 1033.38, "total_tokens": 4404840} {"current_steps": 48930, "total_steps": 76960, "loss": 0.4625, "lr": 1.7626322241463873e-05, "epoch": 12.715696465696466, "percentage": 63.58, "elapsed_time": "1:11:02", "remaining_time": "0:40:42", "throughput": 1033.39, "total_tokens": 4405304} {"current_steps": 48935, "total_steps": 76960, "loss": 0.2837, "lr": 1.7620905052612035e-05, "epoch": 12.716995841995843, "percentage": 63.58, "elapsed_time": "1:11:03", "remaining_time": "0:40:41", "throughput": 1033.39, "total_tokens": 4405736} {"current_steps": 48940, "total_steps": 76960, "loss": 0.2301, "lr": 1.7615488243274135e-05, "epoch": 12.718295218295218, "percentage": 63.59, "elapsed_time": "1:11:03", "remaining_time": "0:40:41", "throughput": 1033.39, "total_tokens": 4406152} {"current_steps": 48945, "total_steps": 76960, "loss": 0.3924, "lr": 1.761007181372874e-05, "epoch": 12.719594594594595, "percentage": 63.6, "elapsed_time": "1:11:04", "remaining_time": "0:40:40", "throughput": 1033.4, "total_tokens": 4406632} {"current_steps": 48950, "total_steps": 76960, "loss": 0.3826, "lr": 1.7604655764254435e-05, "epoch": 12.720893970893972, "percentage": 63.6, "elapsed_time": "1:11:04", "remaining_time": "0:40:40", "throughput": 1033.41, "total_tokens": 4407112} {"current_steps": 48955, "total_steps": 76960, "loss": 0.3356, "lr": 1.7599240095129764e-05, "epoch": 12.722193347193347, "percentage": 63.61, "elapsed_time": "1:11:05", "remaining_time": "0:40:39", "throughput": 1033.41, "total_tokens": 4407544} {"current_steps": 48960, "total_steps": 76960, "loss": 0.2475, "lr": 1.759382480663328e-05, "epoch": 12.723492723492724, "percentage": 63.62, "elapsed_time": "1:11:05", "remaining_time": "0:40:39", "throughput": 1033.42, "total_tokens": 4408008} {"current_steps": 48965, "total_steps": 76960, "loss": 0.1722, "lr": 1.7588409899043468e-05, "epoch": 12.7247920997921, "percentage": 63.62, "elapsed_time": "1:11:05", "remaining_time": "0:40:38", "throughput": 1033.42, "total_tokens": 4408440} {"current_steps": 48970, "total_steps": 76960, "loss": 0.3528, "lr": 1.7582995372638844e-05, "epoch": 12.726091476091476, "percentage": 63.63, "elapsed_time": "1:11:06", "remaining_time": "0:40:38", "throughput": 1033.42, "total_tokens": 4408872} {"current_steps": 48975, "total_steps": 76960, "loss": 0.0902, "lr": 1.757758122769787e-05, "epoch": 12.727390852390853, "percentage": 63.64, "elapsed_time": "1:11:06", "remaining_time": "0:40:38", "throughput": 1033.42, "total_tokens": 4409304} {"current_steps": 48980, "total_steps": 76960, "loss": 0.1045, "lr": 1.757216746449901e-05, "epoch": 12.728690228690228, "percentage": 63.64, "elapsed_time": "1:11:07", "remaining_time": "0:40:37", "throughput": 1033.43, "total_tokens": 4409768} {"current_steps": 48985, "total_steps": 76960, "loss": 0.5262, "lr": 1.756675408332069e-05, "epoch": 12.729989604989605, "percentage": 63.65, "elapsed_time": "1:11:07", "remaining_time": "0:40:37", "throughput": 1033.44, "total_tokens": 4410232} {"current_steps": 48990, "total_steps": 76960, "loss": 0.1872, "lr": 1.7561341084441334e-05, "epoch": 12.731288981288982, "percentage": 63.66, "elapsed_time": "1:11:07", "remaining_time": "0:40:36", "throughput": 1033.44, "total_tokens": 4410664} {"current_steps": 48995, "total_steps": 76960, "loss": 0.5493, "lr": 1.7555928468139337e-05, "epoch": 12.732588357588357, "percentage": 63.66, "elapsed_time": "1:11:08", "remaining_time": "0:40:36", "throughput": 1033.45, "total_tokens": 4411160} {"current_steps": 49000, "total_steps": 76960, "loss": 0.0557, "lr": 1.7550516234693065e-05, "epoch": 12.733887733887734, "percentage": 63.67, "elapsed_time": "1:11:08", "remaining_time": "0:40:35", "throughput": 1033.46, "total_tokens": 4411608} {"current_steps": 49005, "total_steps": 76960, "loss": 0.0367, "lr": 1.7545104384380885e-05, "epoch": 12.73518711018711, "percentage": 63.68, "elapsed_time": "1:11:09", "remaining_time": "0:40:35", "throughput": 1033.46, "total_tokens": 4412040} {"current_steps": 49010, "total_steps": 76960, "loss": 0.3503, "lr": 1.753969291748112e-05, "epoch": 12.736486486486486, "percentage": 63.68, "elapsed_time": "1:11:09", "remaining_time": "0:40:34", "throughput": 1033.46, "total_tokens": 4412488} {"current_steps": 49015, "total_steps": 76960, "loss": 0.1154, "lr": 1.753428183427211e-05, "epoch": 12.737785862785863, "percentage": 63.69, "elapsed_time": "1:11:10", "remaining_time": "0:40:34", "throughput": 1033.46, "total_tokens": 4412920} {"current_steps": 49020, "total_steps": 76960, "loss": 0.0483, "lr": 1.7528871135032127e-05, "epoch": 12.73908523908524, "percentage": 63.7, "elapsed_time": "1:11:10", "remaining_time": "0:40:34", "throughput": 1033.47, "total_tokens": 4413384} {"current_steps": 49025, "total_steps": 76960, "loss": 0.3362, "lr": 1.7523460820039464e-05, "epoch": 12.740384615384615, "percentage": 63.7, "elapsed_time": "1:11:10", "remaining_time": "0:40:33", "throughput": 1033.47, "total_tokens": 4413816} {"current_steps": 49030, "total_steps": 76960, "loss": 0.379, "lr": 1.7518050889572372e-05, "epoch": 12.741683991683992, "percentage": 63.71, "elapsed_time": "1:11:11", "remaining_time": "0:40:33", "throughput": 1033.48, "total_tokens": 4414280} {"current_steps": 49035, "total_steps": 76960, "loss": 0.5843, "lr": 1.75126413439091e-05, "epoch": 12.742983367983367, "percentage": 63.71, "elapsed_time": "1:11:11", "remaining_time": "0:40:32", "throughput": 1033.49, "total_tokens": 4414744} {"current_steps": 49040, "total_steps": 76960, "loss": 0.3959, "lr": 1.750723218332785e-05, "epoch": 12.744282744282744, "percentage": 63.72, "elapsed_time": "1:11:12", "remaining_time": "0:40:32", "throughput": 1033.49, "total_tokens": 4415176} {"current_steps": 49045, "total_steps": 76960, "loss": 0.1055, "lr": 1.750182340810683e-05, "epoch": 12.745582120582121, "percentage": 63.73, "elapsed_time": "1:11:12", "remaining_time": "0:40:31", "throughput": 1033.49, "total_tokens": 4415592} {"current_steps": 49050, "total_steps": 76960, "loss": 0.1572, "lr": 1.7496415018524213e-05, "epoch": 12.746881496881496, "percentage": 63.73, "elapsed_time": "1:11:12", "remaining_time": "0:40:31", "throughput": 1033.49, "total_tokens": 4416040} {"current_steps": 49055, "total_steps": 76960, "loss": 0.2927, "lr": 1.7491007014858172e-05, "epoch": 12.748180873180873, "percentage": 63.74, "elapsed_time": "1:11:13", "remaining_time": "0:40:30", "throughput": 1033.5, "total_tokens": 4416520} {"current_steps": 49060, "total_steps": 76960, "loss": 0.3179, "lr": 1.7485599397386827e-05, "epoch": 12.74948024948025, "percentage": 63.75, "elapsed_time": "1:11:13", "remaining_time": "0:40:30", "throughput": 1033.51, "total_tokens": 4416968} {"current_steps": 49065, "total_steps": 76960, "loss": 0.4232, "lr": 1.7480192166388303e-05, "epoch": 12.750779625779625, "percentage": 63.75, "elapsed_time": "1:11:14", "remaining_time": "0:40:30", "throughput": 1033.52, "total_tokens": 4417448} {"current_steps": 49070, "total_steps": 76960, "loss": 0.0037, "lr": 1.747478532214071e-05, "epoch": 12.752079002079002, "percentage": 63.76, "elapsed_time": "1:11:14", "remaining_time": "0:40:29", "throughput": 1033.52, "total_tokens": 4417896} {"current_steps": 49075, "total_steps": 76960, "loss": 0.2064, "lr": 1.7469378864922102e-05, "epoch": 12.753378378378379, "percentage": 63.77, "elapsed_time": "1:11:15", "remaining_time": "0:40:29", "throughput": 1033.53, "total_tokens": 4418376} {"current_steps": 49080, "total_steps": 76960, "loss": 0.0967, "lr": 1.7463972795010573e-05, "epoch": 12.754677754677754, "percentage": 63.77, "elapsed_time": "1:11:15", "remaining_time": "0:40:28", "throughput": 1033.54, "total_tokens": 4418824} {"current_steps": 49085, "total_steps": 76960, "loss": 0.3095, "lr": 1.7458567112684133e-05, "epoch": 12.755977130977131, "percentage": 63.78, "elapsed_time": "1:11:15", "remaining_time": "0:40:28", "throughput": 1033.55, "total_tokens": 4419288} {"current_steps": 49090, "total_steps": 76960, "loss": 0.2477, "lr": 1.7453161818220814e-05, "epoch": 12.757276507276508, "percentage": 63.79, "elapsed_time": "1:11:16", "remaining_time": "0:40:27", "throughput": 1033.55, "total_tokens": 4419752} {"current_steps": 49095, "total_steps": 76960, "loss": 0.1927, "lr": 1.744775691189861e-05, "epoch": 12.758575883575883, "percentage": 63.79, "elapsed_time": "1:11:16", "remaining_time": "0:40:27", "throughput": 1033.56, "total_tokens": 4420200} {"current_steps": 49100, "total_steps": 76960, "loss": 0.1614, "lr": 1.7442352393995515e-05, "epoch": 12.75987525987526, "percentage": 63.8, "elapsed_time": "1:11:17", "remaining_time": "0:40:26", "throughput": 1033.56, "total_tokens": 4420616} {"current_steps": 49105, "total_steps": 76960, "loss": 0.1914, "lr": 1.7436948264789466e-05, "epoch": 12.761174636174637, "percentage": 63.81, "elapsed_time": "1:11:17", "remaining_time": "0:40:26", "throughput": 1033.56, "total_tokens": 4421048} {"current_steps": 49110, "total_steps": 76960, "loss": 0.3844, "lr": 1.7431544524558422e-05, "epoch": 12.762474012474012, "percentage": 63.81, "elapsed_time": "1:11:17", "remaining_time": "0:40:25", "throughput": 1033.56, "total_tokens": 4421480} {"current_steps": 49115, "total_steps": 76960, "loss": 0.3999, "lr": 1.742614117358029e-05, "epoch": 12.763773388773389, "percentage": 63.82, "elapsed_time": "1:11:18", "remaining_time": "0:40:25", "throughput": 1033.57, "total_tokens": 4421976} {"current_steps": 49120, "total_steps": 76960, "loss": 0.161, "lr": 1.7420738212132983e-05, "epoch": 12.765072765072766, "percentage": 63.83, "elapsed_time": "1:11:18", "remaining_time": "0:40:25", "throughput": 1033.57, "total_tokens": 4422392} {"current_steps": 49125, "total_steps": 76960, "loss": 0.4247, "lr": 1.7415335640494366e-05, "epoch": 12.766372141372141, "percentage": 63.83, "elapsed_time": "1:11:19", "remaining_time": "0:40:24", "throughput": 1033.56, "total_tokens": 4422808} {"current_steps": 49130, "total_steps": 76960, "loss": 0.5107, "lr": 1.7409933458942303e-05, "epoch": 12.767671517671518, "percentage": 63.84, "elapsed_time": "1:11:19", "remaining_time": "0:40:24", "throughput": 1033.57, "total_tokens": 4423256} {"current_steps": 49135, "total_steps": 76960, "loss": 0.2048, "lr": 1.740453166775464e-05, "epoch": 12.768970893970893, "percentage": 63.84, "elapsed_time": "1:11:20", "remaining_time": "0:40:23", "throughput": 1033.58, "total_tokens": 4423752} {"current_steps": 49140, "total_steps": 76960, "loss": 0.2261, "lr": 1.739913026720918e-05, "epoch": 12.77027027027027, "percentage": 63.85, "elapsed_time": "1:11:20", "remaining_time": "0:40:23", "throughput": 1033.58, "total_tokens": 4424168} {"current_steps": 49145, "total_steps": 76960, "loss": 0.0764, "lr": 1.739372925758374e-05, "epoch": 12.771569646569647, "percentage": 63.86, "elapsed_time": "1:11:20", "remaining_time": "0:40:22", "throughput": 1033.59, "total_tokens": 4424632} {"current_steps": 49150, "total_steps": 76960, "loss": 0.4189, "lr": 1.738832863915609e-05, "epoch": 12.772869022869022, "percentage": 63.86, "elapsed_time": "1:11:21", "remaining_time": "0:40:22", "throughput": 1033.6, "total_tokens": 4425096} {"current_steps": 49155, "total_steps": 76960, "loss": 0.1523, "lr": 1.7382928412204e-05, "epoch": 12.7741683991684, "percentage": 63.87, "elapsed_time": "1:11:21", "remaining_time": "0:40:21", "throughput": 1033.6, "total_tokens": 4425528} {"current_steps": 49160, "total_steps": 76960, "loss": 0.1299, "lr": 1.737752857700519e-05, "epoch": 12.775467775467776, "percentage": 63.88, "elapsed_time": "1:11:22", "remaining_time": "0:40:21", "throughput": 1033.6, "total_tokens": 4425976} {"current_steps": 49165, "total_steps": 76960, "loss": 0.3129, "lr": 1.7372129133837394e-05, "epoch": 12.776767151767151, "percentage": 63.88, "elapsed_time": "1:11:22", "remaining_time": "0:40:21", "throughput": 1033.6, "total_tokens": 4426408} {"current_steps": 49170, "total_steps": 76960, "loss": 0.2661, "lr": 1.7366730082978298e-05, "epoch": 12.778066528066528, "percentage": 63.89, "elapsed_time": "1:11:22", "remaining_time": "0:40:20", "throughput": 1033.6, "total_tokens": 4426840} {"current_steps": 49175, "total_steps": 76960, "loss": 0.2639, "lr": 1.73613314247056e-05, "epoch": 12.779365904365905, "percentage": 63.9, "elapsed_time": "1:11:23", "remaining_time": "0:40:20", "throughput": 1033.61, "total_tokens": 4427320} {"current_steps": 49180, "total_steps": 76960, "loss": 0.2233, "lr": 1.7355933159296934e-05, "epoch": 12.78066528066528, "percentage": 63.9, "elapsed_time": "1:11:23", "remaining_time": "0:40:19", "throughput": 1033.62, "total_tokens": 4427768} {"current_steps": 49185, "total_steps": 76960, "loss": 0.1356, "lr": 1.7350535287029957e-05, "epoch": 12.781964656964657, "percentage": 63.91, "elapsed_time": "1:11:24", "remaining_time": "0:40:19", "throughput": 1033.63, "total_tokens": 4428248} {"current_steps": 49190, "total_steps": 76960, "loss": 0.2127, "lr": 1.7345137808182282e-05, "epoch": 12.783264033264032, "percentage": 63.92, "elapsed_time": "1:11:24", "remaining_time": "0:40:18", "throughput": 1033.63, "total_tokens": 4428696} {"current_steps": 49195, "total_steps": 76960, "loss": 0.0732, "lr": 1.7339740723031497e-05, "epoch": 12.78456340956341, "percentage": 63.92, "elapsed_time": "1:11:25", "remaining_time": "0:40:18", "throughput": 1033.63, "total_tokens": 4429096} {"current_steps": 49200, "total_steps": 76960, "loss": 0.1584, "lr": 1.733434403185519e-05, "epoch": 12.785862785862786, "percentage": 63.93, "elapsed_time": "1:11:25", "remaining_time": "0:40:17", "throughput": 1033.64, "total_tokens": 4429592} {"current_steps": 49205, "total_steps": 76960, "loss": 0.3493, "lr": 1.732894773493091e-05, "epoch": 12.787162162162161, "percentage": 63.94, "elapsed_time": "1:11:25", "remaining_time": "0:40:17", "throughput": 1033.65, "total_tokens": 4430056} {"current_steps": 49210, "total_steps": 76960, "loss": 0.2667, "lr": 1.7323551832536206e-05, "epoch": 12.788461538461538, "percentage": 63.94, "elapsed_time": "1:11:26", "remaining_time": "0:40:17", "throughput": 1033.65, "total_tokens": 4430488} {"current_steps": 49215, "total_steps": 76960, "loss": 0.1468, "lr": 1.7318156324948577e-05, "epoch": 12.789760914760915, "percentage": 63.95, "elapsed_time": "1:11:26", "remaining_time": "0:40:16", "throughput": 1033.65, "total_tokens": 4430920} {"current_steps": 49220, "total_steps": 76960, "loss": 0.1431, "lr": 1.7312761212445534e-05, "epoch": 12.79106029106029, "percentage": 63.96, "elapsed_time": "1:11:27", "remaining_time": "0:40:16", "throughput": 1033.65, "total_tokens": 4431352} {"current_steps": 49225, "total_steps": 76960, "loss": 0.5543, "lr": 1.7307366495304545e-05, "epoch": 12.792359667359667, "percentage": 63.96, "elapsed_time": "1:11:27", "remaining_time": "0:40:15", "throughput": 1033.65, "total_tokens": 4431784} {"current_steps": 49230, "total_steps": 76960, "loss": 0.2586, "lr": 1.7301972173803078e-05, "epoch": 12.793659043659044, "percentage": 63.97, "elapsed_time": "1:11:27", "remaining_time": "0:40:15", "throughput": 1033.66, "total_tokens": 4432248} {"current_steps": 49235, "total_steps": 76960, "loss": 0.1866, "lr": 1.7296578248218543e-05, "epoch": 12.79495841995842, "percentage": 63.97, "elapsed_time": "1:11:28", "remaining_time": "0:40:14", "throughput": 1033.67, "total_tokens": 4432744} {"current_steps": 49240, "total_steps": 76960, "loss": 0.4676, "lr": 1.7291184718828376e-05, "epoch": 12.796257796257796, "percentage": 63.98, "elapsed_time": "1:11:28", "remaining_time": "0:40:14", "throughput": 1033.67, "total_tokens": 4433160} {"current_steps": 49245, "total_steps": 76960, "loss": 0.2613, "lr": 1.728579158590996e-05, "epoch": 12.797557172557173, "percentage": 63.99, "elapsed_time": "1:11:29", "remaining_time": "0:40:13", "throughput": 1033.67, "total_tokens": 4433608} {"current_steps": 49250, "total_steps": 76960, "loss": 0.3087, "lr": 1.7280398849740687e-05, "epoch": 12.798856548856548, "percentage": 63.99, "elapsed_time": "1:11:29", "remaining_time": "0:40:13", "throughput": 1033.67, "total_tokens": 4434040} {"current_steps": 49255, "total_steps": 76960, "loss": 0.1654, "lr": 1.727500651059789e-05, "epoch": 12.800155925155925, "percentage": 64.0, "elapsed_time": "1:11:30", "remaining_time": "0:40:13", "throughput": 1033.68, "total_tokens": 4434488} {"current_steps": 49260, "total_steps": 76960, "loss": 0.2891, "lr": 1.7269614568758907e-05, "epoch": 12.801455301455302, "percentage": 64.01, "elapsed_time": "1:11:30", "remaining_time": "0:40:12", "throughput": 1033.68, "total_tokens": 4434920} {"current_steps": 49265, "total_steps": 76960, "loss": 0.2824, "lr": 1.7264223024501064e-05, "epoch": 12.802754677754677, "percentage": 64.01, "elapsed_time": "1:11:30", "remaining_time": "0:40:12", "throughput": 1033.68, "total_tokens": 4435352} {"current_steps": 49270, "total_steps": 76960, "loss": 0.3202, "lr": 1.7258831878101634e-05, "epoch": 12.804054054054054, "percentage": 64.02, "elapsed_time": "1:11:31", "remaining_time": "0:40:11", "throughput": 1033.69, "total_tokens": 4435816} {"current_steps": 49275, "total_steps": 76960, "loss": 0.0952, "lr": 1.7253441129837898e-05, "epoch": 12.80535343035343, "percentage": 64.03, "elapsed_time": "1:11:31", "remaining_time": "0:40:11", "throughput": 1033.69, "total_tokens": 4436264} {"current_steps": 49280, "total_steps": 76960, "loss": 0.1928, "lr": 1.7248050779987106e-05, "epoch": 12.806652806652806, "percentage": 64.03, "elapsed_time": "1:11:32", "remaining_time": "0:40:10", "throughput": 1033.7, "total_tokens": 4436728} {"current_steps": 49285, "total_steps": 76960, "loss": 0.241, "lr": 1.72426608288265e-05, "epoch": 12.807952182952183, "percentage": 64.04, "elapsed_time": "1:11:32", "remaining_time": "0:40:10", "throughput": 1033.72, "total_tokens": 4437224} {"current_steps": 49290, "total_steps": 76960, "loss": 0.3766, "lr": 1.7237271276633265e-05, "epoch": 12.809251559251559, "percentage": 64.05, "elapsed_time": "1:11:32", "remaining_time": "0:40:09", "throughput": 1033.72, "total_tokens": 4437688} {"current_steps": 49295, "total_steps": 76960, "loss": 0.1287, "lr": 1.7231882123684616e-05, "epoch": 12.810550935550935, "percentage": 64.05, "elapsed_time": "1:11:33", "remaining_time": "0:40:09", "throughput": 1033.73, "total_tokens": 4438136} {"current_steps": 49300, "total_steps": 76960, "loss": 0.1955, "lr": 1.7226493370257708e-05, "epoch": 12.811850311850312, "percentage": 64.06, "elapsed_time": "1:11:33", "remaining_time": "0:40:09", "throughput": 1033.73, "total_tokens": 4438568} {"current_steps": 49305, "total_steps": 76960, "loss": 0.1757, "lr": 1.72211050166297e-05, "epoch": 12.813149688149688, "percentage": 64.07, "elapsed_time": "1:11:34", "remaining_time": "0:40:08", "throughput": 1033.74, "total_tokens": 4439048} {"current_steps": 49310, "total_steps": 76960, "loss": 0.402, "lr": 1.72157170630777e-05, "epoch": 12.814449064449065, "percentage": 64.07, "elapsed_time": "1:11:34", "remaining_time": "0:40:08", "throughput": 1033.74, "total_tokens": 4439496} {"current_steps": 49315, "total_steps": 76960, "loss": 0.2212, "lr": 1.721032950987885e-05, "epoch": 12.815748440748441, "percentage": 64.08, "elapsed_time": "1:11:34", "remaining_time": "0:40:07", "throughput": 1033.75, "total_tokens": 4439960} {"current_steps": 49320, "total_steps": 76960, "loss": 0.139, "lr": 1.7204942357310217e-05, "epoch": 12.817047817047817, "percentage": 64.09, "elapsed_time": "1:11:35", "remaining_time": "0:40:07", "throughput": 1033.76, "total_tokens": 4440424} {"current_steps": 49325, "total_steps": 76960, "loss": 0.2349, "lr": 1.719955560564885e-05, "epoch": 12.818347193347194, "percentage": 64.09, "elapsed_time": "1:11:35", "remaining_time": "0:40:06", "throughput": 1033.76, "total_tokens": 4440856} {"current_steps": 49330, "total_steps": 76960, "loss": 0.1373, "lr": 1.7194169255171824e-05, "epoch": 12.81964656964657, "percentage": 64.1, "elapsed_time": "1:11:36", "remaining_time": "0:40:06", "throughput": 1033.76, "total_tokens": 4441288} {"current_steps": 49335, "total_steps": 76960, "loss": 0.5554, "lr": 1.7188783306156146e-05, "epoch": 12.820945945945946, "percentage": 64.1, "elapsed_time": "1:11:36", "remaining_time": "0:40:05", "throughput": 1033.79, "total_tokens": 4441832} {"current_steps": 49340, "total_steps": 76960, "loss": 0.1811, "lr": 1.718339775887883e-05, "epoch": 12.822245322245323, "percentage": 64.11, "elapsed_time": "1:11:37", "remaining_time": "0:40:05", "throughput": 1033.79, "total_tokens": 4442264} {"current_steps": 49345, "total_steps": 76960, "loss": 0.1735, "lr": 1.717801261361685e-05, "epoch": 12.823544698544698, "percentage": 64.12, "elapsed_time": "1:11:37", "remaining_time": "0:40:05", "throughput": 1033.79, "total_tokens": 4442712} {"current_steps": 49350, "total_steps": 76960, "loss": 0.2394, "lr": 1.717262787064719e-05, "epoch": 12.824844074844075, "percentage": 64.12, "elapsed_time": "1:11:37", "remaining_time": "0:40:04", "throughput": 1033.81, "total_tokens": 4443208} {"current_steps": 49355, "total_steps": 76960, "loss": 0.2621, "lr": 1.7167243530246767e-05, "epoch": 12.826143451143452, "percentage": 64.13, "elapsed_time": "1:11:38", "remaining_time": "0:40:04", "throughput": 1033.82, "total_tokens": 4443704} {"current_steps": 49360, "total_steps": 76960, "loss": 0.4511, "lr": 1.7161859592692518e-05, "epoch": 12.827442827442827, "percentage": 64.14, "elapsed_time": "1:11:38", "remaining_time": "0:40:03", "throughput": 1033.82, "total_tokens": 4444120} {"current_steps": 49365, "total_steps": 76960, "loss": 0.3586, "lr": 1.715647605826134e-05, "epoch": 12.828742203742204, "percentage": 64.14, "elapsed_time": "1:11:39", "remaining_time": "0:40:03", "throughput": 1033.82, "total_tokens": 4444552} {"current_steps": 49370, "total_steps": 76960, "loss": 0.4046, "lr": 1.715109292723012e-05, "epoch": 12.83004158004158, "percentage": 64.15, "elapsed_time": "1:11:39", "remaining_time": "0:40:02", "throughput": 1033.83, "total_tokens": 4445016} {"current_steps": 49375, "total_steps": 76960, "loss": 0.1636, "lr": 1.71457101998757e-05, "epoch": 12.831340956340956, "percentage": 64.16, "elapsed_time": "1:11:39", "remaining_time": "0:40:02", "throughput": 1033.84, "total_tokens": 4445496} {"current_steps": 49380, "total_steps": 76960, "loss": 0.318, "lr": 1.7140327876474938e-05, "epoch": 12.832640332640333, "percentage": 64.16, "elapsed_time": "1:11:40", "remaining_time": "0:40:01", "throughput": 1033.84, "total_tokens": 4445944} {"current_steps": 49385, "total_steps": 76960, "loss": 0.2212, "lr": 1.713494595730465e-05, "epoch": 12.83393970893971, "percentage": 64.17, "elapsed_time": "1:11:40", "remaining_time": "0:40:01", "throughput": 1033.86, "total_tokens": 4446424} {"current_steps": 49390, "total_steps": 76960, "loss": 0.1988, "lr": 1.712956444264161e-05, "epoch": 12.835239085239085, "percentage": 64.18, "elapsed_time": "1:11:41", "remaining_time": "0:40:00", "throughput": 1033.86, "total_tokens": 4446872} {"current_steps": 49395, "total_steps": 76960, "loss": 0.2532, "lr": 1.712418333276262e-05, "epoch": 12.836538461538462, "percentage": 64.18, "elapsed_time": "1:11:41", "remaining_time": "0:40:00", "throughput": 1033.87, "total_tokens": 4447352} {"current_steps": 49400, "total_steps": 76960, "loss": 0.1037, "lr": 1.7118802627944428e-05, "epoch": 12.837837837837839, "percentage": 64.19, "elapsed_time": "1:11:42", "remaining_time": "0:40:00", "throughput": 1033.88, "total_tokens": 4447816} {"current_steps": 49405, "total_steps": 76960, "loss": 0.2101, "lr": 1.7113422328463773e-05, "epoch": 12.839137214137214, "percentage": 64.2, "elapsed_time": "1:11:42", "remaining_time": "0:39:59", "throughput": 1033.88, "total_tokens": 4448248} {"current_steps": 49410, "total_steps": 76960, "loss": 0.1563, "lr": 1.7108042434597356e-05, "epoch": 12.84043659043659, "percentage": 64.2, "elapsed_time": "1:11:42", "remaining_time": "0:39:59", "throughput": 1033.88, "total_tokens": 4448664} {"current_steps": 49415, "total_steps": 76960, "loss": 0.048, "lr": 1.7102662946621885e-05, "epoch": 12.841735966735968, "percentage": 64.21, "elapsed_time": "1:11:43", "remaining_time": "0:39:58", "throughput": 1033.88, "total_tokens": 4449096} {"current_steps": 49420, "total_steps": 76960, "loss": 0.3625, "lr": 1.709728386481402e-05, "epoch": 12.843035343035343, "percentage": 64.22, "elapsed_time": "1:11:43", "remaining_time": "0:39:58", "throughput": 1033.89, "total_tokens": 4449576} {"current_steps": 49425, "total_steps": 76960, "loss": 0.7354, "lr": 1.7091905189450423e-05, "epoch": 12.84433471933472, "percentage": 64.22, "elapsed_time": "1:11:44", "remaining_time": "0:39:57", "throughput": 1033.9, "total_tokens": 4450056} {"current_steps": 49430, "total_steps": 76960, "loss": 0.6769, "lr": 1.7086526920807712e-05, "epoch": 12.845634095634095, "percentage": 64.23, "elapsed_time": "1:11:44", "remaining_time": "0:39:57", "throughput": 1033.91, "total_tokens": 4450536} {"current_steps": 49435, "total_steps": 76960, "loss": 0.158, "lr": 1.708114905916251e-05, "epoch": 12.846933471933472, "percentage": 64.23, "elapsed_time": "1:11:44", "remaining_time": "0:39:56", "throughput": 1033.92, "total_tokens": 4450984} {"current_steps": 49440, "total_steps": 76960, "loss": 0.2179, "lr": 1.7075771604791395e-05, "epoch": 12.848232848232849, "percentage": 64.24, "elapsed_time": "1:11:45", "remaining_time": "0:39:56", "throughput": 1033.92, "total_tokens": 4451448} {"current_steps": 49445, "total_steps": 76960, "loss": 0.2448, "lr": 1.707039455797095e-05, "epoch": 12.849532224532224, "percentage": 64.25, "elapsed_time": "1:11:45", "remaining_time": "0:39:56", "throughput": 1033.93, "total_tokens": 4451912} {"current_steps": 49450, "total_steps": 76960, "loss": 0.1136, "lr": 1.70650179189777e-05, "epoch": 12.8508316008316, "percentage": 64.25, "elapsed_time": "1:11:46", "remaining_time": "0:39:55", "throughput": 1033.95, "total_tokens": 4452424} {"current_steps": 49455, "total_steps": 76960, "loss": 0.2412, "lr": 1.705964168808818e-05, "epoch": 12.852130977130978, "percentage": 64.26, "elapsed_time": "1:11:46", "remaining_time": "0:39:55", "throughput": 1033.95, "total_tokens": 4452872} {"current_steps": 49460, "total_steps": 76960, "loss": 0.1094, "lr": 1.7054265865578904e-05, "epoch": 12.853430353430353, "percentage": 64.27, "elapsed_time": "1:11:47", "remaining_time": "0:39:54", "throughput": 1033.96, "total_tokens": 4453336} {"current_steps": 49465, "total_steps": 76960, "loss": 0.1487, "lr": 1.704889045172634e-05, "epoch": 12.85472972972973, "percentage": 64.27, "elapsed_time": "1:11:47", "remaining_time": "0:39:54", "throughput": 1033.96, "total_tokens": 4453768} {"current_steps": 49470, "total_steps": 76960, "loss": 0.5882, "lr": 1.7043515446806964e-05, "epoch": 12.856029106029107, "percentage": 64.28, "elapsed_time": "1:11:47", "remaining_time": "0:39:53", "throughput": 1033.98, "total_tokens": 4454248} {"current_steps": 49475, "total_steps": 76960, "loss": 0.4091, "lr": 1.7038140851097206e-05, "epoch": 12.857328482328482, "percentage": 64.29, "elapsed_time": "1:11:48", "remaining_time": "0:39:53", "throughput": 1033.98, "total_tokens": 4454712} {"current_steps": 49480, "total_steps": 76960, "loss": 0.225, "lr": 1.7032766664873502e-05, "epoch": 12.858627858627859, "percentage": 64.29, "elapsed_time": "1:11:48", "remaining_time": "0:39:52", "throughput": 1033.99, "total_tokens": 4455176} {"current_steps": 49485, "total_steps": 76960, "loss": 0.344, "lr": 1.7027392888412235e-05, "epoch": 12.859927234927234, "percentage": 64.3, "elapsed_time": "1:11:49", "remaining_time": "0:39:52", "throughput": 1034.0, "total_tokens": 4455640} {"current_steps": 49490, "total_steps": 76960, "loss": 0.2566, "lr": 1.7022019521989793e-05, "epoch": 12.861226611226611, "percentage": 64.31, "elapsed_time": "1:11:49", "remaining_time": "0:39:52", "throughput": 1034.01, "total_tokens": 4456104} {"current_steps": 49495, "total_steps": 76960, "loss": 0.2701, "lr": 1.7016646565882527e-05, "epoch": 12.862525987525988, "percentage": 64.31, "elapsed_time": "1:11:49", "remaining_time": "0:39:51", "throughput": 1034.02, "total_tokens": 4456584} {"current_steps": 49500, "total_steps": 76960, "loss": 0.4488, "lr": 1.701127402036679e-05, "epoch": 12.863825363825363, "percentage": 64.32, "elapsed_time": "1:11:50", "remaining_time": "0:39:51", "throughput": 1034.03, "total_tokens": 4457048} {"current_steps": 49505, "total_steps": 76960, "loss": 0.2761, "lr": 1.700590188571887e-05, "epoch": 12.86512474012474, "percentage": 64.33, "elapsed_time": "1:11:50", "remaining_time": "0:39:50", "throughput": 1034.03, "total_tokens": 4457512} {"current_steps": 49510, "total_steps": 76960, "loss": 0.2199, "lr": 1.7000530162215083e-05, "epoch": 12.866424116424117, "percentage": 64.33, "elapsed_time": "1:11:51", "remaining_time": "0:39:50", "throughput": 1034.04, "total_tokens": 4457960} {"current_steps": 49515, "total_steps": 76960, "loss": 0.1824, "lr": 1.6995158850131697e-05, "epoch": 12.867723492723492, "percentage": 64.34, "elapsed_time": "1:11:51", "remaining_time": "0:39:49", "throughput": 1034.05, "total_tokens": 4458440} {"current_steps": 49520, "total_steps": 76960, "loss": 0.1684, "lr": 1.6989787949744954e-05, "epoch": 12.869022869022869, "percentage": 64.35, "elapsed_time": "1:11:52", "remaining_time": "0:39:49", "throughput": 1034.06, "total_tokens": 4458904} {"current_steps": 49525, "total_steps": 76960, "loss": 0.564, "lr": 1.6984417461331097e-05, "epoch": 12.870322245322246, "percentage": 64.35, "elapsed_time": "1:11:52", "remaining_time": "0:39:48", "throughput": 1034.06, "total_tokens": 4459352} {"current_steps": 49530, "total_steps": 76960, "loss": 0.381, "lr": 1.6979047385166325e-05, "epoch": 12.871621621621621, "percentage": 64.36, "elapsed_time": "1:11:52", "remaining_time": "0:39:48", "throughput": 1034.07, "total_tokens": 4459800} {"current_steps": 49535, "total_steps": 76960, "loss": 0.2188, "lr": 1.6973677721526836e-05, "epoch": 12.872920997920998, "percentage": 64.36, "elapsed_time": "1:11:53", "remaining_time": "0:39:48", "throughput": 1034.07, "total_tokens": 4460264} {"current_steps": 49540, "total_steps": 76960, "loss": 0.3345, "lr": 1.696830847068879e-05, "epoch": 12.874220374220375, "percentage": 64.37, "elapsed_time": "1:11:53", "remaining_time": "0:39:47", "throughput": 1034.08, "total_tokens": 4460712} {"current_steps": 49545, "total_steps": 76960, "loss": 0.4342, "lr": 1.6962939632928334e-05, "epoch": 12.87551975051975, "percentage": 64.38, "elapsed_time": "1:11:54", "remaining_time": "0:39:47", "throughput": 1034.08, "total_tokens": 4461144} {"current_steps": 49550, "total_steps": 76960, "loss": 0.2669, "lr": 1.695757120852159e-05, "epoch": 12.876819126819127, "percentage": 64.38, "elapsed_time": "1:11:54", "remaining_time": "0:39:46", "throughput": 1034.07, "total_tokens": 4461544} {"current_steps": 49555, "total_steps": 76960, "loss": 0.4085, "lr": 1.6952203197744675e-05, "epoch": 12.878118503118504, "percentage": 64.39, "elapsed_time": "1:11:54", "remaining_time": "0:39:46", "throughput": 1034.08, "total_tokens": 4462008} {"current_steps": 49560, "total_steps": 76960, "loss": 0.22, "lr": 1.694683560087365e-05, "epoch": 12.879417879417879, "percentage": 64.4, "elapsed_time": "1:11:55", "remaining_time": "0:39:45", "throughput": 1034.09, "total_tokens": 4462488} {"current_steps": 49565, "total_steps": 76960, "loss": 0.1906, "lr": 1.6941468418184597e-05, "epoch": 12.880717255717256, "percentage": 64.4, "elapsed_time": "1:11:55", "remaining_time": "0:39:45", "throughput": 1034.1, "total_tokens": 4462968} {"current_steps": 49570, "total_steps": 76960, "loss": 0.0973, "lr": 1.6936101649953535e-05, "epoch": 12.882016632016633, "percentage": 64.41, "elapsed_time": "1:11:56", "remaining_time": "0:39:44", "throughput": 1034.1, "total_tokens": 4463400} {"current_steps": 49575, "total_steps": 76960, "loss": 0.2113, "lr": 1.6930735296456496e-05, "epoch": 12.883316008316008, "percentage": 64.42, "elapsed_time": "1:11:56", "remaining_time": "0:39:44", "throughput": 1034.11, "total_tokens": 4463864} {"current_steps": 49580, "total_steps": 76960, "loss": 0.3103, "lr": 1.6925369357969477e-05, "epoch": 12.884615384615385, "percentage": 64.42, "elapsed_time": "1:11:57", "remaining_time": "0:39:44", "throughput": 1034.11, "total_tokens": 4464312} {"current_steps": 49585, "total_steps": 76960, "loss": 0.4844, "lr": 1.6920003834768438e-05, "epoch": 12.88591476091476, "percentage": 64.43, "elapsed_time": "1:11:57", "remaining_time": "0:39:43", "throughput": 1034.11, "total_tokens": 4464744} {"current_steps": 49590, "total_steps": 76960, "loss": 0.1304, "lr": 1.691463872712935e-05, "epoch": 12.887214137214137, "percentage": 64.44, "elapsed_time": "1:11:57", "remaining_time": "0:39:43", "throughput": 1034.12, "total_tokens": 4465208} {"current_steps": 49595, "total_steps": 76960, "loss": 0.1395, "lr": 1.6909274035328138e-05, "epoch": 12.888513513513514, "percentage": 64.44, "elapsed_time": "1:11:58", "remaining_time": "0:39:42", "throughput": 1034.13, "total_tokens": 4465672} {"current_steps": 49600, "total_steps": 76960, "loss": 0.3382, "lr": 1.6903909759640716e-05, "epoch": 12.88981288981289, "percentage": 64.45, "elapsed_time": "1:11:58", "remaining_time": "0:39:42", "throughput": 1034.14, "total_tokens": 4466152} {"current_steps": 49605, "total_steps": 76960, "loss": 0.0523, "lr": 1.6898545900342972e-05, "epoch": 12.891112266112266, "percentage": 64.46, "elapsed_time": "1:11:59", "remaining_time": "0:39:41", "throughput": 1034.14, "total_tokens": 4466584} {"current_steps": 49610, "total_steps": 76960, "loss": 0.1922, "lr": 1.6893182457710774e-05, "epoch": 12.892411642411643, "percentage": 64.46, "elapsed_time": "1:11:59", "remaining_time": "0:39:41", "throughput": 1034.14, "total_tokens": 4467032} {"current_steps": 49615, "total_steps": 76960, "loss": 0.1175, "lr": 1.6887819432019966e-05, "epoch": 12.893711018711018, "percentage": 64.47, "elapsed_time": "1:11:59", "remaining_time": "0:39:40", "throughput": 1034.14, "total_tokens": 4467464} {"current_steps": 49620, "total_steps": 76960, "loss": 0.2086, "lr": 1.688245682354639e-05, "epoch": 12.895010395010395, "percentage": 64.48, "elapsed_time": "1:12:00", "remaining_time": "0:39:40", "throughput": 1034.16, "total_tokens": 4467976} {"current_steps": 49625, "total_steps": 76960, "loss": 0.2886, "lr": 1.687709463256582e-05, "epoch": 12.896309771309772, "percentage": 64.48, "elapsed_time": "1:12:00", "remaining_time": "0:39:40", "throughput": 1034.16, "total_tokens": 4468408} {"current_steps": 49630, "total_steps": 76960, "loss": 0.4101, "lr": 1.6871732859354065e-05, "epoch": 12.897609147609147, "percentage": 64.49, "elapsed_time": "1:12:01", "remaining_time": "0:39:39", "throughput": 1034.18, "total_tokens": 4468888} {"current_steps": 49635, "total_steps": 76960, "loss": 0.3033, "lr": 1.6866371504186874e-05, "epoch": 12.898908523908524, "percentage": 64.49, "elapsed_time": "1:12:01", "remaining_time": "0:39:39", "throughput": 1034.17, "total_tokens": 4469304} {"current_steps": 49640, "total_steps": 76960, "loss": 0.1879, "lr": 1.686101056734e-05, "epoch": 12.9002079002079, "percentage": 64.5, "elapsed_time": "1:12:02", "remaining_time": "0:39:38", "throughput": 1034.17, "total_tokens": 4469736} {"current_steps": 49645, "total_steps": 76960, "loss": 0.5584, "lr": 1.6855650049089146e-05, "epoch": 12.901507276507276, "percentage": 64.51, "elapsed_time": "1:12:02", "remaining_time": "0:39:38", "throughput": 1034.19, "total_tokens": 4470232} {"current_steps": 49650, "total_steps": 76960, "loss": 0.2693, "lr": 1.6850289949710003e-05, "epoch": 12.902806652806653, "percentage": 64.51, "elapsed_time": "1:12:02", "remaining_time": "0:39:37", "throughput": 1034.21, "total_tokens": 4470760} {"current_steps": 49655, "total_steps": 76960, "loss": 0.2382, "lr": 1.6844930269478274e-05, "epoch": 12.904106029106028, "percentage": 64.52, "elapsed_time": "1:12:03", "remaining_time": "0:39:37", "throughput": 1034.21, "total_tokens": 4471192} {"current_steps": 49660, "total_steps": 76960, "loss": 0.1073, "lr": 1.683957100866958e-05, "epoch": 12.905405405405405, "percentage": 64.53, "elapsed_time": "1:12:03", "remaining_time": "0:39:36", "throughput": 1034.22, "total_tokens": 4471656} {"current_steps": 49665, "total_steps": 76960, "loss": 0.1343, "lr": 1.6834212167559575e-05, "epoch": 12.906704781704782, "percentage": 64.53, "elapsed_time": "1:12:04", "remaining_time": "0:39:36", "throughput": 1034.22, "total_tokens": 4472072} {"current_steps": 49670, "total_steps": 76960, "loss": 0.3212, "lr": 1.6828853746423857e-05, "epoch": 12.908004158004157, "percentage": 64.54, "elapsed_time": "1:12:04", "remaining_time": "0:39:36", "throughput": 1034.22, "total_tokens": 4472520} {"current_steps": 49675, "total_steps": 76960, "loss": 0.2429, "lr": 1.6823495745538033e-05, "epoch": 12.909303534303534, "percentage": 64.55, "elapsed_time": "1:12:04", "remaining_time": "0:39:35", "throughput": 1034.24, "total_tokens": 4473016} {"current_steps": 49680, "total_steps": 76960, "loss": 0.1613, "lr": 1.681813816517764e-05, "epoch": 12.910602910602911, "percentage": 64.55, "elapsed_time": "1:12:05", "remaining_time": "0:39:35", "throughput": 1034.23, "total_tokens": 4473416} {"current_steps": 49685, "total_steps": 76960, "loss": 0.1594, "lr": 1.6812781005618248e-05, "epoch": 12.911902286902286, "percentage": 64.56, "elapsed_time": "1:12:05", "remaining_time": "0:39:34", "throughput": 1034.23, "total_tokens": 4473848} {"current_steps": 49690, "total_steps": 76960, "loss": 0.2402, "lr": 1.6807424267135374e-05, "epoch": 12.913201663201663, "percentage": 64.57, "elapsed_time": "1:12:06", "remaining_time": "0:39:34", "throughput": 1034.24, "total_tokens": 4474312} {"current_steps": 49695, "total_steps": 76960, "loss": 0.438, "lr": 1.6802067950004523e-05, "epoch": 12.91450103950104, "percentage": 64.57, "elapsed_time": "1:12:06", "remaining_time": "0:39:33", "throughput": 1034.23, "total_tokens": 4474728} {"current_steps": 49700, "total_steps": 76960, "loss": 0.3756, "lr": 1.6796712054501167e-05, "epoch": 12.915800415800415, "percentage": 64.58, "elapsed_time": "1:12:07", "remaining_time": "0:39:33", "throughput": 1034.23, "total_tokens": 4475160} {"current_steps": 49705, "total_steps": 76960, "loss": 0.2285, "lr": 1.6791356580900775e-05, "epoch": 12.917099792099792, "percentage": 64.59, "elapsed_time": "1:12:07", "remaining_time": "0:39:32", "throughput": 1034.24, "total_tokens": 4475624} {"current_steps": 49710, "total_steps": 76960, "loss": 0.1731, "lr": 1.6786001529478782e-05, "epoch": 12.91839916839917, "percentage": 64.59, "elapsed_time": "1:12:07", "remaining_time": "0:39:32", "throughput": 1034.24, "total_tokens": 4476056} {"current_steps": 49715, "total_steps": 76960, "loss": 0.2111, "lr": 1.678064690051059e-05, "epoch": 12.919698544698544, "percentage": 64.6, "elapsed_time": "1:12:08", "remaining_time": "0:39:31", "throughput": 1034.25, "total_tokens": 4476536} {"current_steps": 49720, "total_steps": 76960, "loss": 0.3998, "lr": 1.677529269427161e-05, "epoch": 12.920997920997921, "percentage": 64.6, "elapsed_time": "1:12:08", "remaining_time": "0:39:31", "throughput": 1034.26, "total_tokens": 4477000} {"current_steps": 49725, "total_steps": 76960, "loss": 0.3234, "lr": 1.6769938911037204e-05, "epoch": 12.922297297297296, "percentage": 64.61, "elapsed_time": "1:12:09", "remaining_time": "0:39:31", "throughput": 1034.26, "total_tokens": 4477432} {"current_steps": 49730, "total_steps": 76960, "loss": 0.2852, "lr": 1.676458555108273e-05, "epoch": 12.923596673596673, "percentage": 64.62, "elapsed_time": "1:12:09", "remaining_time": "0:39:30", "throughput": 1034.27, "total_tokens": 4477896} {"current_steps": 49735, "total_steps": 76960, "loss": 0.1275, "lr": 1.6759232614683507e-05, "epoch": 12.92489604989605, "percentage": 64.62, "elapsed_time": "1:12:09", "remaining_time": "0:39:30", "throughput": 1034.28, "total_tokens": 4478360} {"current_steps": 49740, "total_steps": 76960, "loss": 0.1294, "lr": 1.675388010211485e-05, "epoch": 12.926195426195425, "percentage": 64.63, "elapsed_time": "1:12:10", "remaining_time": "0:39:29", "throughput": 1034.28, "total_tokens": 4478808} {"current_steps": 49745, "total_steps": 76960, "loss": 0.1888, "lr": 1.674852801365203e-05, "epoch": 12.927494802494802, "percentage": 64.64, "elapsed_time": "1:12:10", "remaining_time": "0:39:29", "throughput": 1034.28, "total_tokens": 4479256} {"current_steps": 49750, "total_steps": 76960, "loss": 0.3335, "lr": 1.674317634957034e-05, "epoch": 12.92879417879418, "percentage": 64.64, "elapsed_time": "1:12:11", "remaining_time": "0:39:28", "throughput": 1034.29, "total_tokens": 4479720} {"current_steps": 49755, "total_steps": 76960, "loss": 0.4592, "lr": 1.6737825110144982e-05, "epoch": 12.930093555093555, "percentage": 64.65, "elapsed_time": "1:12:11", "remaining_time": "0:39:28", "throughput": 1034.3, "total_tokens": 4480200} {"current_steps": 49760, "total_steps": 76960, "loss": 0.2348, "lr": 1.6732474295651207e-05, "epoch": 12.931392931392931, "percentage": 64.66, "elapsed_time": "1:12:12", "remaining_time": "0:39:27", "throughput": 1034.32, "total_tokens": 4480696} {"current_steps": 49765, "total_steps": 76960, "loss": 0.0993, "lr": 1.6727123906364194e-05, "epoch": 12.932692307692308, "percentage": 64.66, "elapsed_time": "1:12:12", "remaining_time": "0:39:27", "throughput": 1034.32, "total_tokens": 4481144} {"current_steps": 49770, "total_steps": 76960, "loss": 0.2342, "lr": 1.6721773942559137e-05, "epoch": 12.933991683991684, "percentage": 64.67, "elapsed_time": "1:12:12", "remaining_time": "0:39:27", "throughput": 1034.33, "total_tokens": 4481608} {"current_steps": 49775, "total_steps": 76960, "loss": 0.1243, "lr": 1.671642440451117e-05, "epoch": 12.93529106029106, "percentage": 64.68, "elapsed_time": "1:12:13", "remaining_time": "0:39:26", "throughput": 1034.33, "total_tokens": 4482024} {"current_steps": 49780, "total_steps": 76960, "loss": 0.2943, "lr": 1.6711075292495427e-05, "epoch": 12.936590436590437, "percentage": 64.68, "elapsed_time": "1:12:13", "remaining_time": "0:39:26", "throughput": 1034.33, "total_tokens": 4482456} {"current_steps": 49785, "total_steps": 76960, "loss": 0.1313, "lr": 1.6705726606787037e-05, "epoch": 12.937889812889813, "percentage": 64.69, "elapsed_time": "1:12:14", "remaining_time": "0:39:25", "throughput": 1034.33, "total_tokens": 4482904} {"current_steps": 49790, "total_steps": 76960, "loss": 0.1514, "lr": 1.670037834766106e-05, "epoch": 12.93918918918919, "percentage": 64.7, "elapsed_time": "1:12:14", "remaining_time": "0:39:25", "throughput": 1034.33, "total_tokens": 4483320} {"current_steps": 49795, "total_steps": 76960, "loss": 0.2288, "lr": 1.6695030515392586e-05, "epoch": 12.940488565488565, "percentage": 64.7, "elapsed_time": "1:12:14", "remaining_time": "0:39:24", "throughput": 1034.34, "total_tokens": 4483800} {"current_steps": 49800, "total_steps": 76960, "loss": 0.2971, "lr": 1.6689683110256646e-05, "epoch": 12.941787941787942, "percentage": 64.71, "elapsed_time": "1:12:15", "remaining_time": "0:39:24", "throughput": 1034.35, "total_tokens": 4484280} {"current_steps": 49805, "total_steps": 76960, "loss": 0.262, "lr": 1.6684336132528273e-05, "epoch": 12.943087318087318, "percentage": 64.72, "elapsed_time": "1:12:15", "remaining_time": "0:39:23", "throughput": 1034.35, "total_tokens": 4484728} {"current_steps": 49810, "total_steps": 76960, "loss": 0.2803, "lr": 1.6678989582482448e-05, "epoch": 12.944386694386694, "percentage": 64.72, "elapsed_time": "1:12:16", "remaining_time": "0:39:23", "throughput": 1034.35, "total_tokens": 4485160} {"current_steps": 49815, "total_steps": 76960, "loss": 0.2428, "lr": 1.6673643460394174e-05, "epoch": 12.94568607068607, "percentage": 64.73, "elapsed_time": "1:12:16", "remaining_time": "0:39:23", "throughput": 1034.35, "total_tokens": 4485592} {"current_steps": 49820, "total_steps": 76960, "loss": 0.3753, "lr": 1.666829776653839e-05, "epoch": 12.946985446985448, "percentage": 64.73, "elapsed_time": "1:12:17", "remaining_time": "0:39:22", "throughput": 1034.36, "total_tokens": 4486040} {"current_steps": 49825, "total_steps": 76960, "loss": 0.0888, "lr": 1.6662952501190033e-05, "epoch": 12.948284823284823, "percentage": 64.74, "elapsed_time": "1:12:17", "remaining_time": "0:39:22", "throughput": 1034.37, "total_tokens": 4486520} {"current_steps": 49830, "total_steps": 76960, "loss": 0.0509, "lr": 1.6657607664624013e-05, "epoch": 12.9495841995842, "percentage": 64.75, "elapsed_time": "1:12:17", "remaining_time": "0:39:21", "throughput": 1034.37, "total_tokens": 4486936} {"current_steps": 49835, "total_steps": 76960, "loss": 0.2373, "lr": 1.6652263257115237e-05, "epoch": 12.950883575883577, "percentage": 64.75, "elapsed_time": "1:12:18", "remaining_time": "0:39:21", "throughput": 1034.38, "total_tokens": 4487400} {"current_steps": 49840, "total_steps": 76960, "loss": 0.199, "lr": 1.6646919278938555e-05, "epoch": 12.952182952182952, "percentage": 64.76, "elapsed_time": "1:12:18", "remaining_time": "0:39:20", "throughput": 1034.38, "total_tokens": 4487848} {"current_steps": 49845, "total_steps": 76960, "loss": 0.3573, "lr": 1.664157573036881e-05, "epoch": 12.953482328482329, "percentage": 64.77, "elapsed_time": "1:12:19", "remaining_time": "0:39:20", "throughput": 1034.39, "total_tokens": 4488312} {"current_steps": 49850, "total_steps": 76960, "loss": 0.1743, "lr": 1.6636232611680848e-05, "epoch": 12.954781704781706, "percentage": 64.77, "elapsed_time": "1:12:19", "remaining_time": "0:39:19", "throughput": 1034.4, "total_tokens": 4488776} {"current_steps": 49855, "total_steps": 76960, "loss": 0.1647, "lr": 1.6630889923149446e-05, "epoch": 12.95608108108108, "percentage": 64.78, "elapsed_time": "1:12:19", "remaining_time": "0:39:19", "throughput": 1034.4, "total_tokens": 4489208} {"current_steps": 49860, "total_steps": 76960, "loss": 0.392, "lr": 1.6625547665049396e-05, "epoch": 12.957380457380458, "percentage": 64.79, "elapsed_time": "1:12:20", "remaining_time": "0:39:19", "throughput": 1034.39, "total_tokens": 4489624} {"current_steps": 49865, "total_steps": 76960, "loss": 0.4296, "lr": 1.662020583765545e-05, "epoch": 12.958679833679835, "percentage": 64.79, "elapsed_time": "1:12:20", "remaining_time": "0:39:18", "throughput": 1034.4, "total_tokens": 4490088} {"current_steps": 49870, "total_steps": 76960, "loss": 0.4787, "lr": 1.6614864441242356e-05, "epoch": 12.95997920997921, "percentage": 64.8, "elapsed_time": "1:12:21", "remaining_time": "0:39:18", "throughput": 1034.4, "total_tokens": 4490504} {"current_steps": 49875, "total_steps": 76960, "loss": 0.151, "lr": 1.660952347608481e-05, "epoch": 12.961278586278587, "percentage": 64.81, "elapsed_time": "1:12:21", "remaining_time": "0:39:17", "throughput": 1034.41, "total_tokens": 4491000} {"current_steps": 49880, "total_steps": 76960, "loss": 0.5963, "lr": 1.6604182942457518e-05, "epoch": 12.962577962577962, "percentage": 64.81, "elapsed_time": "1:12:22", "remaining_time": "0:39:17", "throughput": 1034.42, "total_tokens": 4491448} {"current_steps": 49885, "total_steps": 76960, "loss": 0.1344, "lr": 1.659884284063513e-05, "epoch": 12.963877338877339, "percentage": 64.82, "elapsed_time": "1:12:22", "remaining_time": "0:39:16", "throughput": 1034.41, "total_tokens": 4491848} {"current_steps": 49890, "total_steps": 76960, "loss": 0.1275, "lr": 1.659350317089232e-05, "epoch": 12.965176715176716, "percentage": 64.83, "elapsed_time": "1:12:22", "remaining_time": "0:39:16", "throughput": 1034.4, "total_tokens": 4492248} {"current_steps": 49895, "total_steps": 76960, "loss": 0.2726, "lr": 1.6588163933503685e-05, "epoch": 12.96647609147609, "percentage": 64.83, "elapsed_time": "1:12:23", "remaining_time": "0:39:15", "throughput": 1034.4, "total_tokens": 4492664} {"current_steps": 49900, "total_steps": 76960, "loss": 0.2278, "lr": 1.6582825128743846e-05, "epoch": 12.967775467775468, "percentage": 64.84, "elapsed_time": "1:12:23", "remaining_time": "0:39:15", "throughput": 1034.41, "total_tokens": 4493144} {"current_steps": 49905, "total_steps": 76960, "loss": 0.3431, "lr": 1.6577486756887374e-05, "epoch": 12.969074844074845, "percentage": 64.85, "elapsed_time": "1:12:24", "remaining_time": "0:39:15", "throughput": 1034.43, "total_tokens": 4493640} {"current_steps": 49910, "total_steps": 76960, "loss": 0.4234, "lr": 1.6572148818208824e-05, "epoch": 12.97037422037422, "percentage": 64.85, "elapsed_time": "1:12:24", "remaining_time": "0:39:14", "throughput": 1034.43, "total_tokens": 4494088} {"current_steps": 49915, "total_steps": 76960, "loss": 0.2439, "lr": 1.656681131298274e-05, "epoch": 12.971673596673597, "percentage": 64.86, "elapsed_time": "1:12:24", "remaining_time": "0:39:14", "throughput": 1034.43, "total_tokens": 4494536} {"current_steps": 49920, "total_steps": 76960, "loss": 0.1014, "lr": 1.6561474241483624e-05, "epoch": 12.972972972972974, "percentage": 64.86, "elapsed_time": "1:12:25", "remaining_time": "0:39:13", "throughput": 1034.45, "total_tokens": 4495016} {"current_steps": 49925, "total_steps": 76960, "loss": 0.2218, "lr": 1.6556137603985984e-05, "epoch": 12.974272349272349, "percentage": 64.87, "elapsed_time": "1:12:25", "remaining_time": "0:39:13", "throughput": 1034.45, "total_tokens": 4495448} {"current_steps": 49930, "total_steps": 76960, "loss": 0.1343, "lr": 1.6550801400764264e-05, "epoch": 12.975571725571726, "percentage": 64.88, "elapsed_time": "1:12:26", "remaining_time": "0:39:12", "throughput": 1034.46, "total_tokens": 4495944} {"current_steps": 49935, "total_steps": 76960, "loss": 0.1629, "lr": 1.6545465632092933e-05, "epoch": 12.976871101871101, "percentage": 64.88, "elapsed_time": "1:12:26", "remaining_time": "0:39:12", "throughput": 1034.47, "total_tokens": 4496424} {"current_steps": 49940, "total_steps": 76960, "loss": 0.3848, "lr": 1.65401302982464e-05, "epoch": 12.978170478170478, "percentage": 64.89, "elapsed_time": "1:12:26", "remaining_time": "0:39:11", "throughput": 1034.47, "total_tokens": 4496840} {"current_steps": 49945, "total_steps": 76960, "loss": 0.3836, "lr": 1.653479539949908e-05, "epoch": 12.979469854469855, "percentage": 64.9, "elapsed_time": "1:12:27", "remaining_time": "0:39:11", "throughput": 1034.48, "total_tokens": 4497304} {"current_steps": 49950, "total_steps": 76960, "loss": 0.3188, "lr": 1.6529460936125335e-05, "epoch": 12.98076923076923, "percentage": 64.9, "elapsed_time": "1:12:27", "remaining_time": "0:39:11", "throughput": 1034.48, "total_tokens": 4497736} {"current_steps": 49955, "total_steps": 76960, "loss": 0.3967, "lr": 1.6524126908399533e-05, "epoch": 12.982068607068607, "percentage": 64.91, "elapsed_time": "1:12:28", "remaining_time": "0:39:10", "throughput": 1034.49, "total_tokens": 4498200} {"current_steps": 49960, "total_steps": 76960, "loss": 0.1885, "lr": 1.6518793316596002e-05, "epoch": 12.983367983367984, "percentage": 64.92, "elapsed_time": "1:12:28", "remaining_time": "0:39:10", "throughput": 1034.49, "total_tokens": 4498664} {"current_steps": 49965, "total_steps": 76960, "loss": 0.1171, "lr": 1.6513460160989065e-05, "epoch": 12.984667359667359, "percentage": 64.92, "elapsed_time": "1:12:29", "remaining_time": "0:39:09", "throughput": 1034.51, "total_tokens": 4499144} {"current_steps": 49970, "total_steps": 76960, "loss": 0.1797, "lr": 1.6508127441852998e-05, "epoch": 12.985966735966736, "percentage": 64.93, "elapsed_time": "1:12:29", "remaining_time": "0:39:09", "throughput": 1034.51, "total_tokens": 4499576} {"current_steps": 49975, "total_steps": 76960, "loss": 0.2773, "lr": 1.6502795159462074e-05, "epoch": 12.987266112266113, "percentage": 64.94, "elapsed_time": "1:12:29", "remaining_time": "0:39:08", "throughput": 1034.51, "total_tokens": 4500024} {"current_steps": 49980, "total_steps": 76960, "loss": 0.4163, "lr": 1.649746331409054e-05, "epoch": 12.988565488565488, "percentage": 64.94, "elapsed_time": "1:12:30", "remaining_time": "0:39:08", "throughput": 1034.52, "total_tokens": 4500488} {"current_steps": 49985, "total_steps": 76960, "loss": 0.0843, "lr": 1.649213190601261e-05, "epoch": 12.989864864864865, "percentage": 64.95, "elapsed_time": "1:12:30", "remaining_time": "0:39:07", "throughput": 1034.52, "total_tokens": 4500952} {"current_steps": 49990, "total_steps": 76960, "loss": 0.0282, "lr": 1.648680093550249e-05, "epoch": 12.991164241164242, "percentage": 64.96, "elapsed_time": "1:12:31", "remaining_time": "0:39:07", "throughput": 1034.53, "total_tokens": 4501416} {"current_steps": 49995, "total_steps": 76960, "loss": 0.0776, "lr": 1.6481470402834347e-05, "epoch": 12.992463617463617, "percentage": 64.96, "elapsed_time": "1:12:31", "remaining_time": "0:39:07", "throughput": 1034.54, "total_tokens": 4501896} {"current_steps": 50000, "total_steps": 76960, "loss": 0.3479, "lr": 1.6476140308282357e-05, "epoch": 12.993762993762994, "percentage": 64.97, "elapsed_time": "1:12:31", "remaining_time": "0:39:06", "throughput": 1034.56, "total_tokens": 4502392} {"current_steps": 50005, "total_steps": 76960, "loss": 0.1368, "lr": 1.6470810652120626e-05, "epoch": 12.99506237006237, "percentage": 64.98, "elapsed_time": "1:12:32", "remaining_time": "0:39:06", "throughput": 1034.56, "total_tokens": 4502824} {"current_steps": 50010, "total_steps": 76960, "loss": 0.4048, "lr": 1.6465481434623283e-05, "epoch": 12.996361746361746, "percentage": 64.98, "elapsed_time": "1:12:32", "remaining_time": "0:39:05", "throughput": 1034.56, "total_tokens": 4503272} {"current_steps": 50015, "total_steps": 76960, "loss": 0.3055, "lr": 1.64601526560644e-05, "epoch": 12.997661122661123, "percentage": 64.99, "elapsed_time": "1:12:33", "remaining_time": "0:39:05", "throughput": 1034.56, "total_tokens": 4503704} {"current_steps": 50020, "total_steps": 76960, "loss": 0.1104, "lr": 1.645482431671806e-05, "epoch": 12.9989604989605, "percentage": 64.99, "elapsed_time": "1:12:33", "remaining_time": "0:39:04", "throughput": 1034.57, "total_tokens": 4504136} {"current_steps": 50024, "total_steps": 76960, "eval_loss": 0.32643255591392517, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "1:12:47", "remaining_time": "0:39:11", "throughput": 1031.42, "total_tokens": 4504416} {"current_steps": 50025, "total_steps": 76960, "loss": 0.0781, "lr": 1.6449496416858284e-05, "epoch": 13.000259875259875, "percentage": 65.0, "elapsed_time": "1:12:48", "remaining_time": "0:39:12", "throughput": 1031.03, "total_tokens": 4504512} {"current_steps": 50030, "total_steps": 76960, "loss": 0.1596, "lr": 1.6444168956759103e-05, "epoch": 13.001559251559252, "percentage": 65.01, "elapsed_time": "1:12:49", "remaining_time": "0:39:11", "throughput": 1031.04, "total_tokens": 4504992} {"current_steps": 50035, "total_steps": 76960, "loss": 0.3072, "lr": 1.6438841936694517e-05, "epoch": 13.002858627858627, "percentage": 65.01, "elapsed_time": "1:12:49", "remaining_time": "0:39:11", "throughput": 1031.03, "total_tokens": 4505440} {"current_steps": 50040, "total_steps": 76960, "loss": 0.1223, "lr": 1.6433515356938477e-05, "epoch": 13.004158004158004, "percentage": 65.02, "elapsed_time": "1:12:50", "remaining_time": "0:39:11", "throughput": 1031.04, "total_tokens": 4505920} {"current_steps": 50045, "total_steps": 76960, "loss": 0.1815, "lr": 1.642818921776496e-05, "epoch": 13.005457380457381, "percentage": 65.03, "elapsed_time": "1:12:50", "remaining_time": "0:39:10", "throughput": 1031.05, "total_tokens": 4506368} {"current_steps": 50050, "total_steps": 76960, "loss": 0.4132, "lr": 1.642286351944788e-05, "epoch": 13.006756756756756, "percentage": 65.03, "elapsed_time": "1:12:51", "remaining_time": "0:39:10", "throughput": 1031.05, "total_tokens": 4506784} {"current_steps": 50055, "total_steps": 76960, "loss": 0.1602, "lr": 1.641753826226116e-05, "epoch": 13.008056133056133, "percentage": 65.04, "elapsed_time": "1:12:51", "remaining_time": "0:39:09", "throughput": 1031.05, "total_tokens": 4507216} {"current_steps": 50060, "total_steps": 76960, "loss": 0.2854, "lr": 1.6412213446478653e-05, "epoch": 13.00935550935551, "percentage": 65.05, "elapsed_time": "1:12:51", "remaining_time": "0:39:09", "throughput": 1031.05, "total_tokens": 4507680} {"current_steps": 50065, "total_steps": 76960, "loss": 0.2979, "lr": 1.640688907237425e-05, "epoch": 13.010654885654885, "percentage": 65.05, "elapsed_time": "1:12:52", "remaining_time": "0:39:08", "throughput": 1031.05, "total_tokens": 4508144} {"current_steps": 50070, "total_steps": 76960, "loss": 0.1113, "lr": 1.6401565140221768e-05, "epoch": 13.011954261954262, "percentage": 65.06, "elapsed_time": "1:12:52", "remaining_time": "0:39:08", "throughput": 1031.06, "total_tokens": 4508608} {"current_steps": 50075, "total_steps": 76960, "loss": 0.1639, "lr": 1.639624165029503e-05, "epoch": 13.013253638253639, "percentage": 65.07, "elapsed_time": "1:12:53", "remaining_time": "0:39:07", "throughput": 1031.06, "total_tokens": 4509040} {"current_steps": 50080, "total_steps": 76960, "loss": 0.2391, "lr": 1.6390918602867828e-05, "epoch": 13.014553014553014, "percentage": 65.07, "elapsed_time": "1:12:53", "remaining_time": "0:39:07", "throughput": 1031.05, "total_tokens": 4509456} {"current_steps": 50085, "total_steps": 76960, "loss": 0.3673, "lr": 1.6385595998213936e-05, "epoch": 13.015852390852391, "percentage": 65.08, "elapsed_time": "1:12:54", "remaining_time": "0:39:07", "throughput": 1031.05, "total_tokens": 4509872} {"current_steps": 50090, "total_steps": 76960, "loss": 0.3338, "lr": 1.6380273836607092e-05, "epoch": 13.017151767151768, "percentage": 65.09, "elapsed_time": "1:12:54", "remaining_time": "0:39:06", "throughput": 1031.05, "total_tokens": 4510320} {"current_steps": 50095, "total_steps": 76960, "loss": 0.0796, "lr": 1.6374952118321023e-05, "epoch": 13.018451143451143, "percentage": 65.09, "elapsed_time": "1:12:54", "remaining_time": "0:39:06", "throughput": 1031.05, "total_tokens": 4510768} {"current_steps": 50100, "total_steps": 76960, "loss": 0.2352, "lr": 1.6369630843629442e-05, "epoch": 13.01975051975052, "percentage": 65.1, "elapsed_time": "1:12:55", "remaining_time": "0:39:05", "throughput": 1031.06, "total_tokens": 4511216} {"current_steps": 50105, "total_steps": 76960, "loss": 0.2014, "lr": 1.6364310012806e-05, "epoch": 13.021049896049895, "percentage": 65.11, "elapsed_time": "1:12:55", "remaining_time": "0:39:05", "throughput": 1031.07, "total_tokens": 4511696} {"current_steps": 50110, "total_steps": 76960, "loss": 0.3567, "lr": 1.6358989626124376e-05, "epoch": 13.022349272349272, "percentage": 65.11, "elapsed_time": "1:12:56", "remaining_time": "0:39:04", "throughput": 1031.07, "total_tokens": 4512144} {"current_steps": 50115, "total_steps": 76960, "loss": 0.2822, "lr": 1.635366968385819e-05, "epoch": 13.02364864864865, "percentage": 65.12, "elapsed_time": "1:12:56", "remaining_time": "0:39:04", "throughput": 1031.08, "total_tokens": 4512592} {"current_steps": 50120, "total_steps": 76960, "loss": 0.0854, "lr": 1.6348350186281065e-05, "epoch": 13.024948024948024, "percentage": 65.12, "elapsed_time": "1:12:57", "remaining_time": "0:39:03", "throughput": 1031.07, "total_tokens": 4513008} {"current_steps": 50125, "total_steps": 76960, "loss": 0.3008, "lr": 1.634303113366657e-05, "epoch": 13.026247401247401, "percentage": 65.13, "elapsed_time": "1:12:57", "remaining_time": "0:39:03", "throughput": 1031.08, "total_tokens": 4513472} {"current_steps": 50130, "total_steps": 76960, "loss": 0.1566, "lr": 1.6337712526288286e-05, "epoch": 13.027546777546778, "percentage": 65.14, "elapsed_time": "1:12:57", "remaining_time": "0:39:03", "throughput": 1031.08, "total_tokens": 4513904} {"current_steps": 50135, "total_steps": 76960, "loss": 0.0306, "lr": 1.6332394364419737e-05, "epoch": 13.028846153846153, "percentage": 65.14, "elapsed_time": "1:12:58", "remaining_time": "0:39:02", "throughput": 1031.09, "total_tokens": 4514368} {"current_steps": 50140, "total_steps": 76960, "loss": 0.1023, "lr": 1.6327076648334464e-05, "epoch": 13.03014553014553, "percentage": 65.15, "elapsed_time": "1:12:58", "remaining_time": "0:39:02", "throughput": 1031.09, "total_tokens": 4514800} {"current_steps": 50145, "total_steps": 76960, "loss": 0.8298, "lr": 1.632175937830594e-05, "epoch": 13.031444906444907, "percentage": 65.16, "elapsed_time": "1:12:59", "remaining_time": "0:39:01", "throughput": 1031.09, "total_tokens": 4515248} {"current_steps": 50150, "total_steps": 76960, "loss": 0.2816, "lr": 1.6316442554607646e-05, "epoch": 13.032744282744282, "percentage": 65.16, "elapsed_time": "1:12:59", "remaining_time": "0:39:01", "throughput": 1031.1, "total_tokens": 4515712} {"current_steps": 50155, "total_steps": 76960, "loss": 0.0586, "lr": 1.6311126177513032e-05, "epoch": 13.03404365904366, "percentage": 65.17, "elapsed_time": "1:12:59", "remaining_time": "0:39:00", "throughput": 1031.1, "total_tokens": 4516144} {"current_steps": 50160, "total_steps": 76960, "loss": 0.1344, "lr": 1.6305810247295534e-05, "epoch": 13.035343035343036, "percentage": 65.18, "elapsed_time": "1:13:00", "remaining_time": "0:39:00", "throughput": 1031.1, "total_tokens": 4516560} {"current_steps": 50165, "total_steps": 76960, "loss": 0.3909, "lr": 1.6300494764228536e-05, "epoch": 13.036642411642411, "percentage": 65.18, "elapsed_time": "1:13:00", "remaining_time": "0:38:59", "throughput": 1031.09, "total_tokens": 4516976} {"current_steps": 50170, "total_steps": 76960, "loss": 0.1804, "lr": 1.6295179728585424e-05, "epoch": 13.037941787941788, "percentage": 65.19, "elapsed_time": "1:13:01", "remaining_time": "0:38:59", "throughput": 1031.1, "total_tokens": 4517440} {"current_steps": 50175, "total_steps": 76960, "loss": 0.4007, "lr": 1.628986514063957e-05, "epoch": 13.039241164241163, "percentage": 65.2, "elapsed_time": "1:13:01", "remaining_time": "0:38:59", "throughput": 1031.12, "total_tokens": 4517936} {"current_steps": 50180, "total_steps": 76960, "loss": 0.1496, "lr": 1.628455100066429e-05, "epoch": 13.04054054054054, "percentage": 65.2, "elapsed_time": "1:13:02", "remaining_time": "0:38:58", "throughput": 1031.12, "total_tokens": 4518368} {"current_steps": 50185, "total_steps": 76960, "loss": 0.2177, "lr": 1.6279237308932905e-05, "epoch": 13.041839916839917, "percentage": 65.21, "elapsed_time": "1:13:02", "remaining_time": "0:38:58", "throughput": 1031.12, "total_tokens": 4518816} {"current_steps": 50190, "total_steps": 76960, "loss": 0.1764, "lr": 1.6273924065718697e-05, "epoch": 13.043139293139292, "percentage": 65.22, "elapsed_time": "1:13:02", "remaining_time": "0:38:57", "throughput": 1031.12, "total_tokens": 4519264} {"current_steps": 50195, "total_steps": 76960, "loss": 0.1719, "lr": 1.6268611271294945e-05, "epoch": 13.04443866943867, "percentage": 65.22, "elapsed_time": "1:13:03", "remaining_time": "0:38:57", "throughput": 1031.13, "total_tokens": 4519728} {"current_steps": 50200, "total_steps": 76960, "loss": 0.4136, "lr": 1.626329892593487e-05, "epoch": 13.045738045738046, "percentage": 65.23, "elapsed_time": "1:13:03", "remaining_time": "0:38:56", "throughput": 1031.14, "total_tokens": 4520176} {"current_steps": 50205, "total_steps": 76960, "loss": 0.2877, "lr": 1.625798702991171e-05, "epoch": 13.047037422037421, "percentage": 65.24, "elapsed_time": "1:13:04", "remaining_time": "0:38:56", "throughput": 1031.14, "total_tokens": 4520608} {"current_steps": 50210, "total_steps": 76960, "loss": 0.1497, "lr": 1.6252675583498645e-05, "epoch": 13.048336798336798, "percentage": 65.24, "elapsed_time": "1:13:04", "remaining_time": "0:38:55", "throughput": 1031.14, "total_tokens": 4521040} {"current_steps": 50215, "total_steps": 76960, "loss": 0.1489, "lr": 1.624736458696887e-05, "epoch": 13.049636174636175, "percentage": 65.25, "elapsed_time": "1:13:04", "remaining_time": "0:38:55", "throughput": 1031.15, "total_tokens": 4521504} {"current_steps": 50220, "total_steps": 76960, "loss": 0.0466, "lr": 1.6242054040595507e-05, "epoch": 13.05093555093555, "percentage": 65.25, "elapsed_time": "1:13:05", "remaining_time": "0:38:55", "throughput": 1031.15, "total_tokens": 4521952} {"current_steps": 50225, "total_steps": 76960, "loss": 0.327, "lr": 1.6236743944651703e-05, "epoch": 13.052234927234927, "percentage": 65.26, "elapsed_time": "1:13:05", "remaining_time": "0:38:54", "throughput": 1031.15, "total_tokens": 4522384} {"current_steps": 50230, "total_steps": 76960, "loss": 0.1233, "lr": 1.623143429941056e-05, "epoch": 13.053534303534304, "percentage": 65.27, "elapsed_time": "1:13:06", "remaining_time": "0:38:54", "throughput": 1031.16, "total_tokens": 4522832} {"current_steps": 50235, "total_steps": 76960, "loss": 0.3149, "lr": 1.622612510514514e-05, "epoch": 13.05483367983368, "percentage": 65.27, "elapsed_time": "1:13:06", "remaining_time": "0:38:53", "throughput": 1031.16, "total_tokens": 4523264} {"current_steps": 50240, "total_steps": 76960, "loss": 0.5105, "lr": 1.6220816362128522e-05, "epoch": 13.056133056133056, "percentage": 65.28, "elapsed_time": "1:13:07", "remaining_time": "0:38:53", "throughput": 1031.16, "total_tokens": 4523728} {"current_steps": 50245, "total_steps": 76960, "loss": 0.1988, "lr": 1.621550807063372e-05, "epoch": 13.057432432432432, "percentage": 65.29, "elapsed_time": "1:13:07", "remaining_time": "0:38:52", "throughput": 1031.16, "total_tokens": 4524160} {"current_steps": 50250, "total_steps": 76960, "loss": 0.1976, "lr": 1.6210200230933768e-05, "epoch": 13.058731808731808, "percentage": 65.29, "elapsed_time": "1:13:07", "remaining_time": "0:38:52", "throughput": 1031.18, "total_tokens": 4524656} {"current_steps": 50255, "total_steps": 76960, "loss": 0.0957, "lr": 1.6204892843301628e-05, "epoch": 13.060031185031185, "percentage": 65.3, "elapsed_time": "1:13:08", "remaining_time": "0:38:51", "throughput": 1031.19, "total_tokens": 4525120} {"current_steps": 50260, "total_steps": 76960, "loss": 0.1285, "lr": 1.6199585908010286e-05, "epoch": 13.06133056133056, "percentage": 65.31, "elapsed_time": "1:13:08", "remaining_time": "0:38:51", "throughput": 1031.2, "total_tokens": 4525584} {"current_steps": 50265, "total_steps": 76960, "loss": 0.0145, "lr": 1.6194279425332662e-05, "epoch": 13.062629937629938, "percentage": 65.31, "elapsed_time": "1:13:09", "remaining_time": "0:38:50", "throughput": 1031.2, "total_tokens": 4526016} {"current_steps": 50270, "total_steps": 76960, "loss": 0.192, "lr": 1.6188973395541696e-05, "epoch": 13.063929313929314, "percentage": 65.32, "elapsed_time": "1:13:09", "remaining_time": "0:38:50", "throughput": 1031.2, "total_tokens": 4526464} {"current_steps": 50275, "total_steps": 76960, "loss": 0.0566, "lr": 1.6183667818910263e-05, "epoch": 13.06522869022869, "percentage": 65.33, "elapsed_time": "1:13:09", "remaining_time": "0:38:50", "throughput": 1031.2, "total_tokens": 4526912} {"current_steps": 50280, "total_steps": 76960, "loss": 0.2305, "lr": 1.6178362695711243e-05, "epoch": 13.066528066528067, "percentage": 65.33, "elapsed_time": "1:13:10", "remaining_time": "0:38:49", "throughput": 1031.21, "total_tokens": 4527360} {"current_steps": 50285, "total_steps": 76960, "loss": 0.056, "lr": 1.617305802621748e-05, "epoch": 13.067827442827443, "percentage": 65.34, "elapsed_time": "1:13:10", "remaining_time": "0:38:49", "throughput": 1031.21, "total_tokens": 4527808} {"current_steps": 50290, "total_steps": 76960, "loss": 0.3611, "lr": 1.6167753810701806e-05, "epoch": 13.069126819126819, "percentage": 65.35, "elapsed_time": "1:13:11", "remaining_time": "0:38:48", "throughput": 1031.23, "total_tokens": 4528288} {"current_steps": 50295, "total_steps": 76960, "loss": 0.4196, "lr": 1.6162450049437017e-05, "epoch": 13.070426195426196, "percentage": 65.35, "elapsed_time": "1:13:11", "remaining_time": "0:38:48", "throughput": 1031.23, "total_tokens": 4528736} {"current_steps": 50300, "total_steps": 76960, "loss": 0.1952, "lr": 1.6157146742695884e-05, "epoch": 13.071725571725572, "percentage": 65.36, "elapsed_time": "1:13:12", "remaining_time": "0:38:47", "throughput": 1031.24, "total_tokens": 4529216} {"current_steps": 50305, "total_steps": 76960, "loss": 0.2346, "lr": 1.615184389075117e-05, "epoch": 13.073024948024948, "percentage": 65.37, "elapsed_time": "1:13:12", "remaining_time": "0:38:47", "throughput": 1031.25, "total_tokens": 4529680} {"current_steps": 50310, "total_steps": 76960, "loss": 0.4459, "lr": 1.6146541493875595e-05, "epoch": 13.074324324324325, "percentage": 65.37, "elapsed_time": "1:13:12", "remaining_time": "0:38:46", "throughput": 1031.25, "total_tokens": 4530112} {"current_steps": 50315, "total_steps": 76960, "loss": 0.261, "lr": 1.6141239552341885e-05, "epoch": 13.075623700623701, "percentage": 65.38, "elapsed_time": "1:13:13", "remaining_time": "0:38:46", "throughput": 1031.25, "total_tokens": 4530544} {"current_steps": 50320, "total_steps": 76960, "loss": 0.3945, "lr": 1.6135938066422707e-05, "epoch": 13.076923076923077, "percentage": 65.38, "elapsed_time": "1:13:13", "remaining_time": "0:38:46", "throughput": 1031.27, "total_tokens": 4531072} {"current_steps": 50325, "total_steps": 76960, "loss": 0.2433, "lr": 1.6130637036390726e-05, "epoch": 13.078222453222454, "percentage": 65.39, "elapsed_time": "1:13:14", "remaining_time": "0:38:45", "throughput": 1031.27, "total_tokens": 4531504} {"current_steps": 50330, "total_steps": 76960, "loss": 0.2903, "lr": 1.612533646251858e-05, "epoch": 13.079521829521829, "percentage": 65.4, "elapsed_time": "1:13:14", "remaining_time": "0:38:45", "throughput": 1031.27, "total_tokens": 4531936} {"current_steps": 50335, "total_steps": 76960, "loss": 0.0298, "lr": 1.6120036345078895e-05, "epoch": 13.080821205821206, "percentage": 65.4, "elapsed_time": "1:13:14", "remaining_time": "0:38:44", "throughput": 1031.28, "total_tokens": 4532416} {"current_steps": 50340, "total_steps": 76960, "loss": 0.1793, "lr": 1.6114736684344236e-05, "epoch": 13.082120582120583, "percentage": 65.41, "elapsed_time": "1:13:15", "remaining_time": "0:38:44", "throughput": 1031.29, "total_tokens": 4532880} {"current_steps": 50345, "total_steps": 76960, "loss": 0.0388, "lr": 1.610943748058719e-05, "epoch": 13.083419958419958, "percentage": 65.42, "elapsed_time": "1:13:15", "remaining_time": "0:38:43", "throughput": 1031.29, "total_tokens": 4533328} {"current_steps": 50350, "total_steps": 76960, "loss": 0.1137, "lr": 1.6104138734080285e-05, "epoch": 13.084719334719335, "percentage": 65.42, "elapsed_time": "1:13:16", "remaining_time": "0:38:43", "throughput": 1031.31, "total_tokens": 4533808} {"current_steps": 50355, "total_steps": 76960, "loss": 0.3012, "lr": 1.609884044509606e-05, "epoch": 13.086018711018712, "percentage": 65.43, "elapsed_time": "1:13:16", "remaining_time": "0:38:42", "throughput": 1031.31, "total_tokens": 4534272} {"current_steps": 50360, "total_steps": 76960, "loss": 0.1294, "lr": 1.6093542613906992e-05, "epoch": 13.087318087318087, "percentage": 65.44, "elapsed_time": "1:13:17", "remaining_time": "0:38:42", "throughput": 1031.32, "total_tokens": 4534704} {"current_steps": 50365, "total_steps": 76960, "loss": 0.1819, "lr": 1.608824524078556e-05, "epoch": 13.088617463617464, "percentage": 65.44, "elapsed_time": "1:13:17", "remaining_time": "0:38:42", "throughput": 1031.32, "total_tokens": 4535152} {"current_steps": 50370, "total_steps": 76960, "loss": 0.2073, "lr": 1.608294832600422e-05, "epoch": 13.08991683991684, "percentage": 65.45, "elapsed_time": "1:13:17", "remaining_time": "0:38:41", "throughput": 1031.33, "total_tokens": 4535632} {"current_steps": 50375, "total_steps": 76960, "loss": 0.2911, "lr": 1.6077651869835385e-05, "epoch": 13.091216216216216, "percentage": 65.46, "elapsed_time": "1:13:18", "remaining_time": "0:38:41", "throughput": 1031.34, "total_tokens": 4536080} {"current_steps": 50380, "total_steps": 76960, "loss": 0.1354, "lr": 1.6072355872551467e-05, "epoch": 13.092515592515593, "percentage": 65.46, "elapsed_time": "1:13:18", "remaining_time": "0:38:40", "throughput": 1031.34, "total_tokens": 4536544} {"current_steps": 50385, "total_steps": 76960, "loss": 0.412, "lr": 1.6067060334424835e-05, "epoch": 13.09381496881497, "percentage": 65.47, "elapsed_time": "1:13:19", "remaining_time": "0:38:40", "throughput": 1031.34, "total_tokens": 4536944} {"current_steps": 50390, "total_steps": 76960, "loss": 0.2279, "lr": 1.6061765255727863e-05, "epoch": 13.095114345114345, "percentage": 65.48, "elapsed_time": "1:13:19", "remaining_time": "0:38:39", "throughput": 1031.35, "total_tokens": 4537408} {"current_steps": 50395, "total_steps": 76960, "loss": 0.1949, "lr": 1.605647063673285e-05, "epoch": 13.096413721413722, "percentage": 65.48, "elapsed_time": "1:13:19", "remaining_time": "0:38:39", "throughput": 1031.35, "total_tokens": 4537856} {"current_steps": 50400, "total_steps": 76960, "loss": 0.4186, "lr": 1.6051176477712136e-05, "epoch": 13.097713097713097, "percentage": 65.49, "elapsed_time": "1:13:20", "remaining_time": "0:38:38", "throughput": 1031.35, "total_tokens": 4538288} {"current_steps": 50405, "total_steps": 76960, "loss": 0.0919, "lr": 1.604588277893798e-05, "epoch": 13.099012474012474, "percentage": 65.5, "elapsed_time": "1:13:20", "remaining_time": "0:38:38", "throughput": 1031.35, "total_tokens": 4538720} {"current_steps": 50410, "total_steps": 76960, "loss": 0.0909, "lr": 1.604058954068266e-05, "epoch": 13.10031185031185, "percentage": 65.5, "elapsed_time": "1:13:21", "remaining_time": "0:38:38", "throughput": 1031.36, "total_tokens": 4539168} {"current_steps": 50415, "total_steps": 76960, "loss": 0.1388, "lr": 1.6035296763218398e-05, "epoch": 13.101611226611226, "percentage": 65.51, "elapsed_time": "1:13:21", "remaining_time": "0:38:37", "throughput": 1031.36, "total_tokens": 4539616} {"current_steps": 50420, "total_steps": 76960, "loss": 0.396, "lr": 1.6030004446817417e-05, "epoch": 13.102910602910603, "percentage": 65.51, "elapsed_time": "1:13:21", "remaining_time": "0:38:37", "throughput": 1031.37, "total_tokens": 4540080} {"current_steps": 50425, "total_steps": 76960, "loss": 0.2687, "lr": 1.6024712591751907e-05, "epoch": 13.10420997920998, "percentage": 65.52, "elapsed_time": "1:13:22", "remaining_time": "0:38:36", "throughput": 1031.38, "total_tokens": 4540528} {"current_steps": 50430, "total_steps": 76960, "loss": 0.0785, "lr": 1.601942119829402e-05, "epoch": 13.105509355509355, "percentage": 65.53, "elapsed_time": "1:13:22", "remaining_time": "0:38:36", "throughput": 1031.38, "total_tokens": 4540976} {"current_steps": 50435, "total_steps": 76960, "loss": 0.1894, "lr": 1.6014130266715908e-05, "epoch": 13.106808731808732, "percentage": 65.53, "elapsed_time": "1:13:23", "remaining_time": "0:38:35", "throughput": 1031.39, "total_tokens": 4541440} {"current_steps": 50440, "total_steps": 76960, "loss": 0.4979, "lr": 1.6008839797289682e-05, "epoch": 13.108108108108109, "percentage": 65.54, "elapsed_time": "1:13:23", "remaining_time": "0:38:35", "throughput": 1031.39, "total_tokens": 4541872} {"current_steps": 50445, "total_steps": 76960, "loss": 0.037, "lr": 1.6003549790287446e-05, "epoch": 13.109407484407484, "percentage": 65.55, "elapsed_time": "1:13:24", "remaining_time": "0:38:34", "throughput": 1031.41, "total_tokens": 4542368} {"current_steps": 50450, "total_steps": 76960, "loss": 0.0501, "lr": 1.599826024598126e-05, "epoch": 13.11070686070686, "percentage": 65.55, "elapsed_time": "1:13:24", "remaining_time": "0:38:34", "throughput": 1031.41, "total_tokens": 4542816} {"current_steps": 50455, "total_steps": 76960, "loss": 0.2267, "lr": 1.599297116464318e-05, "epoch": 13.112006237006238, "percentage": 65.56, "elapsed_time": "1:13:24", "remaining_time": "0:38:33", "throughput": 1031.41, "total_tokens": 4543264} {"current_steps": 50460, "total_steps": 76960, "loss": 0.29, "lr": 1.5987682546545214e-05, "epoch": 13.113305613305613, "percentage": 65.57, "elapsed_time": "1:13:25", "remaining_time": "0:38:33", "throughput": 1031.42, "total_tokens": 4543712} {"current_steps": 50465, "total_steps": 76960, "loss": 0.2061, "lr": 1.5982394391959382e-05, "epoch": 13.11460498960499, "percentage": 65.57, "elapsed_time": "1:13:25", "remaining_time": "0:38:33", "throughput": 1031.43, "total_tokens": 4544192} {"current_steps": 50470, "total_steps": 76960, "loss": 0.521, "lr": 1.5977106701157634e-05, "epoch": 13.115904365904365, "percentage": 65.58, "elapsed_time": "1:13:26", "remaining_time": "0:38:32", "throughput": 1031.43, "total_tokens": 4544624} {"current_steps": 50475, "total_steps": 76960, "loss": 0.1504, "lr": 1.5971819474411943e-05, "epoch": 13.117203742203742, "percentage": 65.59, "elapsed_time": "1:13:26", "remaining_time": "0:38:32", "throughput": 1031.44, "total_tokens": 4545072} {"current_steps": 50480, "total_steps": 76960, "loss": 0.2518, "lr": 1.596653271199422e-05, "epoch": 13.118503118503119, "percentage": 65.59, "elapsed_time": "1:13:26", "remaining_time": "0:38:31", "throughput": 1031.44, "total_tokens": 4545520} {"current_steps": 50485, "total_steps": 76960, "loss": 0.1023, "lr": 1.5961246414176385e-05, "epoch": 13.119802494802494, "percentage": 65.6, "elapsed_time": "1:13:27", "remaining_time": "0:38:31", "throughput": 1031.44, "total_tokens": 4545968} {"current_steps": 50490, "total_steps": 76960, "loss": 0.3901, "lr": 1.5955960581230297e-05, "epoch": 13.121101871101871, "percentage": 65.61, "elapsed_time": "1:13:27", "remaining_time": "0:38:30", "throughput": 1031.45, "total_tokens": 4546432} {"current_steps": 50495, "total_steps": 76960, "loss": 0.2744, "lr": 1.5950675213427828e-05, "epoch": 13.122401247401248, "percentage": 65.61, "elapsed_time": "1:13:28", "remaining_time": "0:38:30", "throughput": 1031.46, "total_tokens": 4546880} {"current_steps": 50500, "total_steps": 76960, "loss": 0.1076, "lr": 1.594539031104081e-05, "epoch": 13.123700623700623, "percentage": 65.62, "elapsed_time": "1:13:28", "remaining_time": "0:38:29", "throughput": 1031.47, "total_tokens": 4547376} {"current_steps": 50505, "total_steps": 76960, "loss": 0.0325, "lr": 1.594010587434103e-05, "epoch": 13.125, "percentage": 65.62, "elapsed_time": "1:13:29", "remaining_time": "0:38:29", "throughput": 1031.48, "total_tokens": 4547840} {"current_steps": 50510, "total_steps": 76960, "loss": 0.4014, "lr": 1.5934821903600294e-05, "epoch": 13.126299376299377, "percentage": 65.63, "elapsed_time": "1:13:29", "remaining_time": "0:38:29", "throughput": 1031.49, "total_tokens": 4548304} {"current_steps": 50515, "total_steps": 76960, "loss": 0.2681, "lr": 1.5929538399090345e-05, "epoch": 13.127598752598752, "percentage": 65.64, "elapsed_time": "1:13:29", "remaining_time": "0:38:28", "throughput": 1031.49, "total_tokens": 4548752} {"current_steps": 50520, "total_steps": 76960, "loss": 0.2412, "lr": 1.5924255361082942e-05, "epoch": 13.128898128898129, "percentage": 65.64, "elapsed_time": "1:13:30", "remaining_time": "0:38:28", "throughput": 1031.49, "total_tokens": 4549184} {"current_steps": 50525, "total_steps": 76960, "loss": 0.2653, "lr": 1.5918972789849764e-05, "epoch": 13.130197505197506, "percentage": 65.65, "elapsed_time": "1:13:30", "remaining_time": "0:38:27", "throughput": 1031.5, "total_tokens": 4549664} {"current_steps": 50530, "total_steps": 76960, "loss": 0.3321, "lr": 1.5913690685662528e-05, "epoch": 13.131496881496881, "percentage": 65.66, "elapsed_time": "1:13:31", "remaining_time": "0:38:27", "throughput": 1031.51, "total_tokens": 4550112} {"current_steps": 50535, "total_steps": 76960, "loss": 0.2166, "lr": 1.590840904879288e-05, "epoch": 13.132796257796258, "percentage": 65.66, "elapsed_time": "1:13:31", "remaining_time": "0:38:26", "throughput": 1031.51, "total_tokens": 4550544} {"current_steps": 50540, "total_steps": 76960, "loss": 0.4896, "lr": 1.5903127879512474e-05, "epoch": 13.134095634095635, "percentage": 65.67, "elapsed_time": "1:13:31", "remaining_time": "0:38:26", "throughput": 1031.51, "total_tokens": 4550992} {"current_steps": 50545, "total_steps": 76960, "loss": 0.1256, "lr": 1.58978471780929e-05, "epoch": 13.13539501039501, "percentage": 65.68, "elapsed_time": "1:13:32", "remaining_time": "0:38:25", "throughput": 1031.51, "total_tokens": 4551424} {"current_steps": 50550, "total_steps": 76960, "loss": 0.1147, "lr": 1.5892566944805785e-05, "epoch": 13.136694386694387, "percentage": 65.68, "elapsed_time": "1:13:32", "remaining_time": "0:38:25", "throughput": 1031.51, "total_tokens": 4551856} {"current_steps": 50555, "total_steps": 76960, "loss": 0.5835, "lr": 1.5887287179922674e-05, "epoch": 13.137993762993762, "percentage": 65.69, "elapsed_time": "1:13:33", "remaining_time": "0:38:25", "throughput": 1031.52, "total_tokens": 4552288} {"current_steps": 50560, "total_steps": 76960, "loss": 0.019, "lr": 1.5882007883715112e-05, "epoch": 13.13929313929314, "percentage": 65.7, "elapsed_time": "1:13:33", "remaining_time": "0:38:24", "throughput": 1031.52, "total_tokens": 4552720} {"current_steps": 50565, "total_steps": 76960, "loss": 0.4875, "lr": 1.5876729056454627e-05, "epoch": 13.140592515592516, "percentage": 65.7, "elapsed_time": "1:13:34", "remaining_time": "0:38:24", "throughput": 1031.53, "total_tokens": 4553200} {"current_steps": 50570, "total_steps": 76960, "loss": 0.1753, "lr": 1.5871450698412697e-05, "epoch": 13.141891891891891, "percentage": 65.71, "elapsed_time": "1:13:34", "remaining_time": "0:38:23", "throughput": 1031.53, "total_tokens": 4553632} {"current_steps": 50575, "total_steps": 76960, "loss": 0.2257, "lr": 1.5866172809860812e-05, "epoch": 13.143191268191268, "percentage": 65.72, "elapsed_time": "1:13:34", "remaining_time": "0:38:23", "throughput": 1031.54, "total_tokens": 4554096} {"current_steps": 50580, "total_steps": 76960, "loss": 0.0444, "lr": 1.5860895391070408e-05, "epoch": 13.144490644490645, "percentage": 65.72, "elapsed_time": "1:13:35", "remaining_time": "0:38:22", "throughput": 1031.56, "total_tokens": 4554608} {"current_steps": 50585, "total_steps": 76960, "loss": 0.1844, "lr": 1.5855618442312918e-05, "epoch": 13.14579002079002, "percentage": 65.73, "elapsed_time": "1:13:35", "remaining_time": "0:38:22", "throughput": 1031.57, "total_tokens": 4555088} {"current_steps": 50590, "total_steps": 76960, "loss": 0.0928, "lr": 1.585034196385972e-05, "epoch": 13.147089397089397, "percentage": 65.74, "elapsed_time": "1:13:36", "remaining_time": "0:38:21", "throughput": 1031.57, "total_tokens": 4555536} {"current_steps": 50595, "total_steps": 76960, "loss": 0.3974, "lr": 1.5845065955982214e-05, "epoch": 13.148388773388774, "percentage": 65.74, "elapsed_time": "1:13:36", "remaining_time": "0:38:21", "throughput": 1031.56, "total_tokens": 4555936} {"current_steps": 50600, "total_steps": 76960, "loss": 0.0851, "lr": 1.5839790418951728e-05, "epoch": 13.14968814968815, "percentage": 65.75, "elapsed_time": "1:13:36", "remaining_time": "0:38:21", "throughput": 1031.57, "total_tokens": 4556400} {"current_steps": 50605, "total_steps": 76960, "loss": 0.3172, "lr": 1.583451535303961e-05, "epoch": 13.150987525987526, "percentage": 65.75, "elapsed_time": "1:13:37", "remaining_time": "0:38:20", "throughput": 1031.58, "total_tokens": 4556848} {"current_steps": 50610, "total_steps": 76960, "loss": 0.162, "lr": 1.5829240758517134e-05, "epoch": 13.152286902286903, "percentage": 65.76, "elapsed_time": "1:13:37", "remaining_time": "0:38:20", "throughput": 1031.58, "total_tokens": 4557280} {"current_steps": 50615, "total_steps": 76960, "loss": 0.3747, "lr": 1.58239666356556e-05, "epoch": 13.153586278586278, "percentage": 65.77, "elapsed_time": "1:13:38", "remaining_time": "0:38:19", "throughput": 1031.58, "total_tokens": 4557712} {"current_steps": 50620, "total_steps": 76960, "loss": 0.0611, "lr": 1.5818692984726253e-05, "epoch": 13.154885654885655, "percentage": 65.77, "elapsed_time": "1:13:38", "remaining_time": "0:38:19", "throughput": 1031.59, "total_tokens": 4558192} {"current_steps": 50625, "total_steps": 76960, "loss": 0.1301, "lr": 1.581341980600033e-05, "epoch": 13.15618503118503, "percentage": 65.78, "elapsed_time": "1:13:39", "remaining_time": "0:38:18", "throughput": 1031.59, "total_tokens": 4558640} {"current_steps": 50630, "total_steps": 76960, "loss": 0.4029, "lr": 1.5808147099749023e-05, "epoch": 13.157484407484407, "percentage": 65.79, "elapsed_time": "1:13:39", "remaining_time": "0:38:18", "throughput": 1031.59, "total_tokens": 4559056} {"current_steps": 50635, "total_steps": 76960, "loss": 0.1569, "lr": 1.5802874866243515e-05, "epoch": 13.158783783783784, "percentage": 65.79, "elapsed_time": "1:13:39", "remaining_time": "0:38:17", "throughput": 1031.59, "total_tokens": 4559504} {"current_steps": 50640, "total_steps": 76960, "loss": 0.4113, "lr": 1.579760310575497e-05, "epoch": 13.16008316008316, "percentage": 65.8, "elapsed_time": "1:13:40", "remaining_time": "0:38:17", "throughput": 1031.59, "total_tokens": 4559920} {"current_steps": 50645, "total_steps": 76960, "loss": 0.1188, "lr": 1.5792331818554513e-05, "epoch": 13.161382536382536, "percentage": 65.81, "elapsed_time": "1:13:40", "remaining_time": "0:38:16", "throughput": 1031.59, "total_tokens": 4560352} {"current_steps": 50650, "total_steps": 76960, "loss": 0.2121, "lr": 1.5787061004913252e-05, "epoch": 13.162681912681913, "percentage": 65.81, "elapsed_time": "1:13:41", "remaining_time": "0:38:16", "throughput": 1031.59, "total_tokens": 4560768} {"current_steps": 50655, "total_steps": 76960, "loss": 0.1834, "lr": 1.5781790665102265e-05, "epoch": 13.163981288981288, "percentage": 65.82, "elapsed_time": "1:13:41", "remaining_time": "0:38:16", "throughput": 1031.58, "total_tokens": 4561168} {"current_steps": 50660, "total_steps": 76960, "loss": 0.1375, "lr": 1.577652079939263e-05, "epoch": 13.165280665280665, "percentage": 65.83, "elapsed_time": "1:13:41", "remaining_time": "0:38:15", "throughput": 1031.59, "total_tokens": 4561632} {"current_steps": 50665, "total_steps": 76960, "loss": 0.1291, "lr": 1.5771251408055353e-05, "epoch": 13.166580041580042, "percentage": 65.83, "elapsed_time": "1:13:42", "remaining_time": "0:38:15", "throughput": 1031.59, "total_tokens": 4562080} {"current_steps": 50670, "total_steps": 76960, "loss": 0.3002, "lr": 1.576598249136147e-05, "epoch": 13.167879417879417, "percentage": 65.84, "elapsed_time": "1:13:42", "remaining_time": "0:38:14", "throughput": 1031.6, "total_tokens": 4562528} {"current_steps": 50675, "total_steps": 76960, "loss": 0.3514, "lr": 1.576071404958195e-05, "epoch": 13.169178794178794, "percentage": 65.85, "elapsed_time": "1:13:43", "remaining_time": "0:38:14", "throughput": 1031.61, "total_tokens": 4562992} {"current_steps": 50680, "total_steps": 76960, "loss": 0.1559, "lr": 1.5755446082987762e-05, "epoch": 13.170478170478171, "percentage": 65.85, "elapsed_time": "1:13:43", "remaining_time": "0:38:13", "throughput": 1031.61, "total_tokens": 4563440} {"current_steps": 50685, "total_steps": 76960, "loss": 0.2288, "lr": 1.5750178591849835e-05, "epoch": 13.171777546777546, "percentage": 65.86, "elapsed_time": "1:13:44", "remaining_time": "0:38:13", "throughput": 1031.6, "total_tokens": 4563840} {"current_steps": 50690, "total_steps": 76960, "loss": 0.2211, "lr": 1.574491157643909e-05, "epoch": 13.173076923076923, "percentage": 65.87, "elapsed_time": "1:13:44", "remaining_time": "0:38:12", "throughput": 1031.61, "total_tokens": 4564288} {"current_steps": 50695, "total_steps": 76960, "loss": 0.153, "lr": 1.5739645037026416e-05, "epoch": 13.174376299376299, "percentage": 65.87, "elapsed_time": "1:13:44", "remaining_time": "0:38:12", "throughput": 1031.62, "total_tokens": 4564752} {"current_steps": 50700, "total_steps": 76960, "loss": 0.206, "lr": 1.5734378973882656e-05, "epoch": 13.175675675675675, "percentage": 65.88, "elapsed_time": "1:13:45", "remaining_time": "0:38:12", "throughput": 1031.61, "total_tokens": 4565168} {"current_steps": 50705, "total_steps": 76960, "loss": 0.1635, "lr": 1.5729113387278673e-05, "epoch": 13.176975051975052, "percentage": 65.88, "elapsed_time": "1:13:45", "remaining_time": "0:38:11", "throughput": 1031.62, "total_tokens": 4565616} {"current_steps": 50710, "total_steps": 76960, "loss": 0.2749, "lr": 1.5723848277485264e-05, "epoch": 13.178274428274428, "percentage": 65.89, "elapsed_time": "1:13:46", "remaining_time": "0:38:11", "throughput": 1031.62, "total_tokens": 4566080} {"current_steps": 50715, "total_steps": 76960, "loss": 0.3011, "lr": 1.571858364477324e-05, "epoch": 13.179573804573804, "percentage": 65.9, "elapsed_time": "1:13:46", "remaining_time": "0:38:10", "throughput": 1031.62, "total_tokens": 4566512} {"current_steps": 50720, "total_steps": 76960, "loss": 0.1431, "lr": 1.571331948941334e-05, "epoch": 13.180873180873181, "percentage": 65.9, "elapsed_time": "1:13:46", "remaining_time": "0:38:10", "throughput": 1031.62, "total_tokens": 4566912} {"current_steps": 50725, "total_steps": 76960, "loss": 0.2295, "lr": 1.570805581167632e-05, "epoch": 13.182172557172557, "percentage": 65.91, "elapsed_time": "1:13:47", "remaining_time": "0:38:09", "throughput": 1031.63, "total_tokens": 4567376} {"current_steps": 50730, "total_steps": 76960, "loss": 0.0894, "lr": 1.570279261183289e-05, "epoch": 13.183471933471933, "percentage": 65.92, "elapsed_time": "1:13:47", "remaining_time": "0:38:09", "throughput": 1031.64, "total_tokens": 4567856} {"current_steps": 50735, "total_steps": 76960, "loss": 0.2933, "lr": 1.5697529890153754e-05, "epoch": 13.18477130977131, "percentage": 65.92, "elapsed_time": "1:13:48", "remaining_time": "0:38:08", "throughput": 1031.65, "total_tokens": 4568320} {"current_steps": 50740, "total_steps": 76960, "loss": 0.4052, "lr": 1.569226764690956e-05, "epoch": 13.186070686070686, "percentage": 65.93, "elapsed_time": "1:13:48", "remaining_time": "0:38:08", "throughput": 1031.66, "total_tokens": 4568800} {"current_steps": 50745, "total_steps": 76960, "loss": 0.4864, "lr": 1.568700588237096e-05, "epoch": 13.187370062370062, "percentage": 65.94, "elapsed_time": "1:13:49", "remaining_time": "0:38:08", "throughput": 1031.65, "total_tokens": 4569216} {"current_steps": 50750, "total_steps": 76960, "loss": 0.5318, "lr": 1.568174459680857e-05, "epoch": 13.18866943866944, "percentage": 65.94, "elapsed_time": "1:13:49", "remaining_time": "0:38:07", "throughput": 1031.66, "total_tokens": 4569680} {"current_steps": 50755, "total_steps": 76960, "loss": 0.1869, "lr": 1.567648379049299e-05, "epoch": 13.189968814968815, "percentage": 65.95, "elapsed_time": "1:13:49", "remaining_time": "0:38:07", "throughput": 1031.67, "total_tokens": 4570128} {"current_steps": 50760, "total_steps": 76960, "loss": 0.2383, "lr": 1.567122346369478e-05, "epoch": 13.191268191268192, "percentage": 65.96, "elapsed_time": "1:13:50", "remaining_time": "0:38:06", "throughput": 1031.66, "total_tokens": 4570544} {"current_steps": 50765, "total_steps": 76960, "loss": 0.2078, "lr": 1.5665963616684476e-05, "epoch": 13.192567567567568, "percentage": 65.96, "elapsed_time": "1:13:50", "remaining_time": "0:38:06", "throughput": 1031.66, "total_tokens": 4570960} {"current_steps": 50770, "total_steps": 76960, "loss": 0.2518, "lr": 1.5660704249732623e-05, "epoch": 13.193866943866944, "percentage": 65.97, "elapsed_time": "1:13:51", "remaining_time": "0:38:05", "throughput": 1031.67, "total_tokens": 4571424} {"current_steps": 50775, "total_steps": 76960, "loss": 0.2269, "lr": 1.5655445363109684e-05, "epoch": 13.19516632016632, "percentage": 65.98, "elapsed_time": "1:13:51", "remaining_time": "0:38:05", "throughput": 1031.68, "total_tokens": 4571888} {"current_steps": 50780, "total_steps": 76960, "loss": 0.1593, "lr": 1.565018695708615e-05, "epoch": 13.196465696465696, "percentage": 65.98, "elapsed_time": "1:13:51", "remaining_time": "0:38:04", "throughput": 1031.68, "total_tokens": 4572352} {"current_steps": 50785, "total_steps": 76960, "loss": 0.2746, "lr": 1.5644929031932454e-05, "epoch": 13.197765072765073, "percentage": 65.99, "elapsed_time": "1:13:52", "remaining_time": "0:38:04", "throughput": 1031.69, "total_tokens": 4572816} {"current_steps": 50790, "total_steps": 76960, "loss": 0.1967, "lr": 1.5639671587919032e-05, "epoch": 13.19906444906445, "percentage": 66.0, "elapsed_time": "1:13:52", "remaining_time": "0:38:04", "throughput": 1031.7, "total_tokens": 4573280} {"current_steps": 50795, "total_steps": 76960, "loss": 0.1461, "lr": 1.5634414625316258e-05, "epoch": 13.200363825363825, "percentage": 66.0, "elapsed_time": "1:13:53", "remaining_time": "0:38:03", "throughput": 1031.71, "total_tokens": 4573744} {"current_steps": 50800, "total_steps": 76960, "loss": 0.4776, "lr": 1.5629158144394524e-05, "epoch": 13.201663201663202, "percentage": 66.01, "elapsed_time": "1:13:53", "remaining_time": "0:38:03", "throughput": 1031.72, "total_tokens": 4574208} {"current_steps": 50805, "total_steps": 76960, "loss": 0.2641, "lr": 1.5623902145424153e-05, "epoch": 13.202962577962579, "percentage": 66.01, "elapsed_time": "1:13:54", "remaining_time": "0:38:02", "throughput": 1031.72, "total_tokens": 4574656} {"current_steps": 50810, "total_steps": 76960, "loss": 0.1269, "lr": 1.5618646628675486e-05, "epoch": 13.204261954261954, "percentage": 66.02, "elapsed_time": "1:13:54", "remaining_time": "0:38:02", "throughput": 1031.72, "total_tokens": 4575088} {"current_steps": 50815, "total_steps": 76960, "loss": 0.2051, "lr": 1.561339159441881e-05, "epoch": 13.20556133056133, "percentage": 66.03, "elapsed_time": "1:13:54", "remaining_time": "0:38:01", "throughput": 1031.72, "total_tokens": 4575504} {"current_steps": 50820, "total_steps": 76960, "loss": 0.2457, "lr": 1.5608137042924403e-05, "epoch": 13.206860706860708, "percentage": 66.03, "elapsed_time": "1:13:55", "remaining_time": "0:38:01", "throughput": 1031.72, "total_tokens": 4575936} {"current_steps": 50825, "total_steps": 76960, "loss": 0.1979, "lr": 1.5602882974462505e-05, "epoch": 13.208160083160083, "percentage": 66.04, "elapsed_time": "1:13:55", "remaining_time": "0:38:00", "throughput": 1031.73, "total_tokens": 4576416} {"current_steps": 50830, "total_steps": 76960, "loss": 0.0723, "lr": 1.559762938930333e-05, "epoch": 13.20945945945946, "percentage": 66.05, "elapsed_time": "1:13:56", "remaining_time": "0:38:00", "throughput": 1031.74, "total_tokens": 4576880} {"current_steps": 50835, "total_steps": 76960, "loss": 0.2317, "lr": 1.55923762877171e-05, "epoch": 13.210758835758837, "percentage": 66.05, "elapsed_time": "1:13:56", "remaining_time": "0:37:59", "throughput": 1031.74, "total_tokens": 4577328} {"current_steps": 50840, "total_steps": 76960, "loss": 0.1822, "lr": 1.558712366997396e-05, "epoch": 13.212058212058212, "percentage": 66.06, "elapsed_time": "1:13:56", "remaining_time": "0:37:59", "throughput": 1031.75, "total_tokens": 4577808} {"current_steps": 50845, "total_steps": 76960, "loss": 0.1413, "lr": 1.5581871536344072e-05, "epoch": 13.213357588357589, "percentage": 66.07, "elapsed_time": "1:13:57", "remaining_time": "0:37:59", "throughput": 1031.75, "total_tokens": 4578224} {"current_steps": 50850, "total_steps": 76960, "loss": 0.0484, "lr": 1.5576619887097553e-05, "epoch": 13.214656964656964, "percentage": 66.07, "elapsed_time": "1:13:57", "remaining_time": "0:37:58", "throughput": 1031.76, "total_tokens": 4578688} {"current_steps": 50855, "total_steps": 76960, "loss": 0.4423, "lr": 1.557136872250451e-05, "epoch": 13.21595634095634, "percentage": 66.08, "elapsed_time": "1:13:58", "remaining_time": "0:37:58", "throughput": 1031.77, "total_tokens": 4579168} {"current_steps": 50860, "total_steps": 76960, "loss": 0.0763, "lr": 1.5566118042834994e-05, "epoch": 13.217255717255718, "percentage": 66.09, "elapsed_time": "1:13:58", "remaining_time": "0:37:57", "throughput": 1031.78, "total_tokens": 4579648} {"current_steps": 50865, "total_steps": 76960, "loss": 0.5561, "lr": 1.5560867848359077e-05, "epoch": 13.218555093555093, "percentage": 66.09, "elapsed_time": "1:13:58", "remaining_time": "0:37:57", "throughput": 1031.79, "total_tokens": 4580096} {"current_steps": 50870, "total_steps": 76960, "loss": 0.4998, "lr": 1.5555618139346766e-05, "epoch": 13.21985446985447, "percentage": 66.1, "elapsed_time": "1:13:59", "remaining_time": "0:37:56", "throughput": 1031.79, "total_tokens": 4580528} {"current_steps": 50875, "total_steps": 76960, "loss": 0.231, "lr": 1.555036891606807e-05, "epoch": 13.221153846153847, "percentage": 66.11, "elapsed_time": "1:13:59", "remaining_time": "0:37:56", "throughput": 1031.79, "total_tokens": 4580976} {"current_steps": 50880, "total_steps": 76960, "loss": 0.1922, "lr": 1.5545120178792944e-05, "epoch": 13.222453222453222, "percentage": 66.11, "elapsed_time": "1:14:00", "remaining_time": "0:37:55", "throughput": 1031.79, "total_tokens": 4581408} {"current_steps": 50885, "total_steps": 76960, "loss": 0.0532, "lr": 1.5539871927791356e-05, "epoch": 13.223752598752599, "percentage": 66.12, "elapsed_time": "1:14:00", "remaining_time": "0:37:55", "throughput": 1031.8, "total_tokens": 4581872} {"current_steps": 50890, "total_steps": 76960, "loss": 0.2764, "lr": 1.5534624163333215e-05, "epoch": 13.225051975051976, "percentage": 66.13, "elapsed_time": "1:14:01", "remaining_time": "0:37:55", "throughput": 1031.8, "total_tokens": 4582288} {"current_steps": 50895, "total_steps": 76960, "loss": 0.172, "lr": 1.5529376885688422e-05, "epoch": 13.22635135135135, "percentage": 66.13, "elapsed_time": "1:14:01", "remaining_time": "0:37:54", "throughput": 1031.8, "total_tokens": 4582720} {"current_steps": 50900, "total_steps": 76960, "loss": 0.3443, "lr": 1.5524130095126853e-05, "epoch": 13.227650727650728, "percentage": 66.14, "elapsed_time": "1:14:01", "remaining_time": "0:37:54", "throughput": 1031.81, "total_tokens": 4583184} {"current_steps": 50905, "total_steps": 76960, "loss": 0.3116, "lr": 1.5518883791918345e-05, "epoch": 13.228950103950105, "percentage": 66.14, "elapsed_time": "1:14:02", "remaining_time": "0:37:53", "throughput": 1031.81, "total_tokens": 4583616} {"current_steps": 50910, "total_steps": 76960, "loss": 0.4443, "lr": 1.551363797633274e-05, "epoch": 13.23024948024948, "percentage": 66.15, "elapsed_time": "1:14:02", "remaining_time": "0:37:53", "throughput": 1031.81, "total_tokens": 4584080} {"current_steps": 50915, "total_steps": 76960, "loss": 0.127, "lr": 1.5508392648639813e-05, "epoch": 13.231548856548857, "percentage": 66.16, "elapsed_time": "1:14:03", "remaining_time": "0:37:52", "throughput": 1031.82, "total_tokens": 4584528} {"current_steps": 50920, "total_steps": 76960, "loss": 0.1286, "lr": 1.550314780910935e-05, "epoch": 13.232848232848234, "percentage": 66.16, "elapsed_time": "1:14:03", "remaining_time": "0:37:52", "throughput": 1031.82, "total_tokens": 4584960} {"current_steps": 50925, "total_steps": 76960, "loss": 0.165, "lr": 1.5497903458011092e-05, "epoch": 13.234147609147609, "percentage": 66.17, "elapsed_time": "1:14:03", "remaining_time": "0:37:51", "throughput": 1031.82, "total_tokens": 4585392} {"current_steps": 50930, "total_steps": 76960, "loss": 0.3821, "lr": 1.5492659595614774e-05, "epoch": 13.235446985446986, "percentage": 66.18, "elapsed_time": "1:14:04", "remaining_time": "0:37:51", "throughput": 1031.83, "total_tokens": 4585856} {"current_steps": 50935, "total_steps": 76960, "loss": 0.1698, "lr": 1.5487416222190068e-05, "epoch": 13.236746361746361, "percentage": 66.18, "elapsed_time": "1:14:04", "remaining_time": "0:37:51", "throughput": 1031.83, "total_tokens": 4586288} {"current_steps": 50940, "total_steps": 76960, "loss": 0.1206, "lr": 1.5482173338006666e-05, "epoch": 13.238045738045738, "percentage": 66.19, "elapsed_time": "1:14:05", "remaining_time": "0:37:50", "throughput": 1031.83, "total_tokens": 4586736} {"current_steps": 50945, "total_steps": 76960, "loss": 0.2834, "lr": 1.547693094333421e-05, "epoch": 13.239345114345115, "percentage": 66.2, "elapsed_time": "1:14:05", "remaining_time": "0:37:50", "throughput": 1031.83, "total_tokens": 4587168} {"current_steps": 50950, "total_steps": 76960, "loss": 0.3759, "lr": 1.5471689038442326e-05, "epoch": 13.24064449064449, "percentage": 66.2, "elapsed_time": "1:14:06", "remaining_time": "0:37:49", "throughput": 1031.83, "total_tokens": 4587568} {"current_steps": 50955, "total_steps": 76960, "loss": 0.3957, "lr": 1.54664476236006e-05, "epoch": 13.241943866943867, "percentage": 66.21, "elapsed_time": "1:14:06", "remaining_time": "0:37:49", "throughput": 1031.83, "total_tokens": 4588016} {"current_steps": 50960, "total_steps": 76960, "loss": 0.6387, "lr": 1.5461206699078602e-05, "epoch": 13.243243243243244, "percentage": 66.22, "elapsed_time": "1:14:06", "remaining_time": "0:37:48", "throughput": 1031.83, "total_tokens": 4588464} {"current_steps": 50965, "total_steps": 76960, "loss": 0.2268, "lr": 1.545596626514589e-05, "epoch": 13.244542619542619, "percentage": 66.22, "elapsed_time": "1:14:07", "remaining_time": "0:37:48", "throughput": 1031.84, "total_tokens": 4588928} {"current_steps": 50970, "total_steps": 76960, "loss": 0.4034, "lr": 1.545072632207197e-05, "epoch": 13.245841995841996, "percentage": 66.23, "elapsed_time": "1:14:07", "remaining_time": "0:37:47", "throughput": 1031.85, "total_tokens": 4589376} {"current_steps": 50975, "total_steps": 76960, "loss": 0.2222, "lr": 1.5445486870126353e-05, "epoch": 13.247141372141373, "percentage": 66.24, "elapsed_time": "1:14:08", "remaining_time": "0:37:47", "throughput": 1031.85, "total_tokens": 4589808} {"current_steps": 50980, "total_steps": 76960, "loss": 0.1383, "lr": 1.5440247909578494e-05, "epoch": 13.248440748440748, "percentage": 66.24, "elapsed_time": "1:14:08", "remaining_time": "0:37:47", "throughput": 1031.86, "total_tokens": 4590272} {"current_steps": 50985, "total_steps": 76960, "loss": 0.2784, "lr": 1.543500944069785e-05, "epoch": 13.249740124740125, "percentage": 66.25, "elapsed_time": "1:14:08", "remaining_time": "0:37:46", "throughput": 1031.86, "total_tokens": 4590736} {"current_steps": 50990, "total_steps": 76960, "loss": 0.2188, "lr": 1.542977146375383e-05, "epoch": 13.2510395010395, "percentage": 66.26, "elapsed_time": "1:14:09", "remaining_time": "0:37:46", "throughput": 1031.87, "total_tokens": 4591200} {"current_steps": 50995, "total_steps": 76960, "loss": 0.1915, "lr": 1.5424533979015837e-05, "epoch": 13.252338877338877, "percentage": 66.26, "elapsed_time": "1:14:09", "remaining_time": "0:37:45", "throughput": 1031.88, "total_tokens": 4591680} {"current_steps": 51000, "total_steps": 76960, "loss": 0.0162, "lr": 1.5419296986753233e-05, "epoch": 13.253638253638254, "percentage": 66.27, "elapsed_time": "1:14:10", "remaining_time": "0:37:45", "throughput": 1031.89, "total_tokens": 4592128} {"current_steps": 51005, "total_steps": 76960, "loss": 0.3253, "lr": 1.541406048723537e-05, "epoch": 13.25493762993763, "percentage": 66.27, "elapsed_time": "1:14:10", "remaining_time": "0:37:44", "throughput": 1031.88, "total_tokens": 4592544} {"current_steps": 51010, "total_steps": 76960, "loss": 0.792, "lr": 1.5408824480731557e-05, "epoch": 13.256237006237006, "percentage": 66.28, "elapsed_time": "1:14:11", "remaining_time": "0:37:44", "throughput": 1031.88, "total_tokens": 4592976} {"current_steps": 51015, "total_steps": 76960, "loss": 0.1486, "lr": 1.5403588967511092e-05, "epoch": 13.257536382536383, "percentage": 66.29, "elapsed_time": "1:14:11", "remaining_time": "0:37:43", "throughput": 1031.9, "total_tokens": 4593456} {"current_steps": 51020, "total_steps": 76960, "loss": 0.7177, "lr": 1.5398353947843247e-05, "epoch": 13.258835758835758, "percentage": 66.29, "elapsed_time": "1:14:11", "remaining_time": "0:37:43", "throughput": 1031.89, "total_tokens": 4593872} {"current_steps": 51025, "total_steps": 76960, "loss": 0.0969, "lr": 1.539311942199725e-05, "epoch": 13.260135135135135, "percentage": 66.3, "elapsed_time": "1:14:12", "remaining_time": "0:37:43", "throughput": 1031.9, "total_tokens": 4594320} {"current_steps": 51030, "total_steps": 76960, "loss": 0.2712, "lr": 1.538788539024233e-05, "epoch": 13.261434511434512, "percentage": 66.31, "elapsed_time": "1:14:12", "remaining_time": "0:37:42", "throughput": 1031.9, "total_tokens": 4594784} {"current_steps": 51035, "total_steps": 76960, "loss": 0.1559, "lr": 1.538265185284767e-05, "epoch": 13.262733887733887, "percentage": 66.31, "elapsed_time": "1:14:13", "remaining_time": "0:37:42", "throughput": 1031.91, "total_tokens": 4595232} {"current_steps": 51040, "total_steps": 76960, "loss": 0.1234, "lr": 1.537741881008245e-05, "epoch": 13.264033264033264, "percentage": 66.32, "elapsed_time": "1:14:13", "remaining_time": "0:37:41", "throughput": 1031.91, "total_tokens": 4595664} {"current_steps": 51045, "total_steps": 76960, "loss": 0.2703, "lr": 1.5372186262215783e-05, "epoch": 13.265332640332641, "percentage": 66.33, "elapsed_time": "1:14:13", "remaining_time": "0:37:41", "throughput": 1031.91, "total_tokens": 4596112} {"current_steps": 51050, "total_steps": 76960, "loss": 0.4208, "lr": 1.536695420951682e-05, "epoch": 13.266632016632016, "percentage": 66.33, "elapsed_time": "1:14:14", "remaining_time": "0:37:40", "throughput": 1031.92, "total_tokens": 4596560} {"current_steps": 51055, "total_steps": 76960, "loss": 0.0779, "lr": 1.5361722652254617e-05, "epoch": 13.267931392931393, "percentage": 66.34, "elapsed_time": "1:14:14", "remaining_time": "0:37:40", "throughput": 1031.92, "total_tokens": 4597008} {"current_steps": 51060, "total_steps": 76960, "loss": 0.2226, "lr": 1.5356491590698263e-05, "epoch": 13.26923076923077, "percentage": 66.35, "elapsed_time": "1:14:15", "remaining_time": "0:37:39", "throughput": 1031.92, "total_tokens": 4597424} {"current_steps": 51065, "total_steps": 76960, "loss": 0.0298, "lr": 1.535126102511678e-05, "epoch": 13.270530145530145, "percentage": 66.35, "elapsed_time": "1:14:15", "remaining_time": "0:37:39", "throughput": 1031.92, "total_tokens": 4597856} {"current_steps": 51070, "total_steps": 76960, "loss": 0.3623, "lr": 1.5346030955779195e-05, "epoch": 13.271829521829522, "percentage": 66.36, "elapsed_time": "1:14:16", "remaining_time": "0:37:39", "throughput": 1031.92, "total_tokens": 4598320} {"current_steps": 51075, "total_steps": 76960, "loss": 0.2495, "lr": 1.534080138295448e-05, "epoch": 13.273128898128897, "percentage": 66.37, "elapsed_time": "1:14:16", "remaining_time": "0:37:38", "throughput": 1031.92, "total_tokens": 4598736} {"current_steps": 51080, "total_steps": 76960, "loss": 0.0868, "lr": 1.533557230691161e-05, "epoch": 13.274428274428274, "percentage": 66.37, "elapsed_time": "1:14:16", "remaining_time": "0:37:38", "throughput": 1031.93, "total_tokens": 4599200} {"current_steps": 51085, "total_steps": 76960, "loss": 0.1944, "lr": 1.533034372791952e-05, "epoch": 13.275727650727651, "percentage": 66.38, "elapsed_time": "1:14:17", "remaining_time": "0:37:37", "throughput": 1031.93, "total_tokens": 4599648} {"current_steps": 51090, "total_steps": 76960, "loss": 0.1838, "lr": 1.532511564624711e-05, "epoch": 13.277027027027026, "percentage": 66.39, "elapsed_time": "1:14:17", "remaining_time": "0:37:37", "throughput": 1031.94, "total_tokens": 4600128} {"current_steps": 51095, "total_steps": 76960, "loss": 0.1052, "lr": 1.5319888062163273e-05, "epoch": 13.278326403326403, "percentage": 66.39, "elapsed_time": "1:14:18", "remaining_time": "0:37:36", "throughput": 1031.95, "total_tokens": 4600576} {"current_steps": 51100, "total_steps": 76960, "loss": 0.0991, "lr": 1.531466097593687e-05, "epoch": 13.27962577962578, "percentage": 66.4, "elapsed_time": "1:14:18", "remaining_time": "0:37:36", "throughput": 1031.96, "total_tokens": 4601056} {"current_steps": 51105, "total_steps": 76960, "loss": 0.0855, "lr": 1.5309434387836735e-05, "epoch": 13.280925155925155, "percentage": 66.4, "elapsed_time": "1:14:18", "remaining_time": "0:37:35", "throughput": 1031.96, "total_tokens": 4601504} {"current_steps": 51110, "total_steps": 76960, "loss": 0.1979, "lr": 1.5304208298131667e-05, "epoch": 13.282224532224532, "percentage": 66.41, "elapsed_time": "1:14:19", "remaining_time": "0:37:35", "throughput": 1031.98, "total_tokens": 4602000} {"current_steps": 51115, "total_steps": 76960, "loss": 0.3315, "lr": 1.5298982707090464e-05, "epoch": 13.28352390852391, "percentage": 66.42, "elapsed_time": "1:14:19", "remaining_time": "0:37:34", "throughput": 1031.99, "total_tokens": 4602464} {"current_steps": 51120, "total_steps": 76960, "loss": 0.3938, "lr": 1.529375761498187e-05, "epoch": 13.284823284823284, "percentage": 66.42, "elapsed_time": "1:14:20", "remaining_time": "0:37:34", "throughput": 1031.99, "total_tokens": 4602912} {"current_steps": 51125, "total_steps": 76960, "loss": 0.2281, "lr": 1.528853302207463e-05, "epoch": 13.286122661122661, "percentage": 66.43, "elapsed_time": "1:14:20", "remaining_time": "0:37:34", "throughput": 1031.99, "total_tokens": 4603344} {"current_steps": 51130, "total_steps": 76960, "loss": 0.2351, "lr": 1.528330892863743e-05, "epoch": 13.287422037422038, "percentage": 66.44, "elapsed_time": "1:14:21", "remaining_time": "0:37:33", "throughput": 1031.99, "total_tokens": 4603776} {"current_steps": 51135, "total_steps": 76960, "loss": 0.0199, "lr": 1.527808533493897e-05, "epoch": 13.288721413721413, "percentage": 66.44, "elapsed_time": "1:14:21", "remaining_time": "0:37:33", "throughput": 1032.0, "total_tokens": 4604256} {"current_steps": 51140, "total_steps": 76960, "loss": 0.1972, "lr": 1.5272862241247892e-05, "epoch": 13.29002079002079, "percentage": 66.45, "elapsed_time": "1:14:21", "remaining_time": "0:37:32", "throughput": 1032.0, "total_tokens": 4604688} {"current_steps": 51145, "total_steps": 76960, "loss": 0.0512, "lr": 1.5267639647832837e-05, "epoch": 13.291320166320165, "percentage": 66.46, "elapsed_time": "1:14:22", "remaining_time": "0:37:32", "throughput": 1032.01, "total_tokens": 4605152} {"current_steps": 51150, "total_steps": 76960, "loss": 0.0944, "lr": 1.5262417554962395e-05, "epoch": 13.292619542619542, "percentage": 66.46, "elapsed_time": "1:14:22", "remaining_time": "0:37:31", "throughput": 1032.01, "total_tokens": 4605584} {"current_steps": 51155, "total_steps": 76960, "loss": 0.3618, "lr": 1.5257195962905147e-05, "epoch": 13.29391891891892, "percentage": 66.47, "elapsed_time": "1:14:23", "remaining_time": "0:37:31", "throughput": 1032.01, "total_tokens": 4606016} {"current_steps": 51160, "total_steps": 76960, "loss": 0.3123, "lr": 1.525197487192965e-05, "epoch": 13.295218295218294, "percentage": 66.48, "elapsed_time": "1:14:23", "remaining_time": "0:37:30", "throughput": 1032.01, "total_tokens": 4606416} {"current_steps": 51165, "total_steps": 76960, "loss": 0.0323, "lr": 1.5246754282304418e-05, "epoch": 13.296517671517671, "percentage": 66.48, "elapsed_time": "1:14:23", "remaining_time": "0:37:30", "throughput": 1032.0, "total_tokens": 4606832} {"current_steps": 51170, "total_steps": 76960, "loss": 0.0619, "lr": 1.5241534194297963e-05, "epoch": 13.297817047817048, "percentage": 66.49, "elapsed_time": "1:14:24", "remaining_time": "0:37:30", "throughput": 1032.01, "total_tokens": 4607296} {"current_steps": 51175, "total_steps": 76960, "loss": 0.4179, "lr": 1.523631460817875e-05, "epoch": 13.299116424116423, "percentage": 66.5, "elapsed_time": "1:14:24", "remaining_time": "0:37:29", "throughput": 1032.01, "total_tokens": 4607728} {"current_steps": 51180, "total_steps": 76960, "loss": 0.045, "lr": 1.5231095524215244e-05, "epoch": 13.3004158004158, "percentage": 66.5, "elapsed_time": "1:14:25", "remaining_time": "0:37:29", "throughput": 1032.03, "total_tokens": 4608224} {"current_steps": 51185, "total_steps": 76960, "loss": 0.3287, "lr": 1.5225876942675842e-05, "epoch": 13.301715176715177, "percentage": 66.51, "elapsed_time": "1:14:25", "remaining_time": "0:37:28", "throughput": 1032.02, "total_tokens": 4608624} {"current_steps": 51190, "total_steps": 76960, "loss": 0.3399, "lr": 1.522065886382896e-05, "epoch": 13.303014553014552, "percentage": 66.52, "elapsed_time": "1:14:26", "remaining_time": "0:37:28", "throughput": 1032.02, "total_tokens": 4609072} {"current_steps": 51195, "total_steps": 76960, "loss": 0.2559, "lr": 1.5215441287942956e-05, "epoch": 13.30431392931393, "percentage": 66.52, "elapsed_time": "1:14:26", "remaining_time": "0:37:27", "throughput": 1032.02, "total_tokens": 4609488} {"current_steps": 51200, "total_steps": 76960, "loss": 0.0946, "lr": 1.5210224215286195e-05, "epoch": 13.305613305613306, "percentage": 66.53, "elapsed_time": "1:14:26", "remaining_time": "0:37:27", "throughput": 1032.02, "total_tokens": 4609920} {"current_steps": 51205, "total_steps": 76960, "loss": 0.2427, "lr": 1.520500764612697e-05, "epoch": 13.306912681912682, "percentage": 66.53, "elapsed_time": "1:14:27", "remaining_time": "0:37:26", "throughput": 1032.02, "total_tokens": 4610352} {"current_steps": 51210, "total_steps": 76960, "loss": 0.107, "lr": 1.5199791580733593e-05, "epoch": 13.308212058212058, "percentage": 66.54, "elapsed_time": "1:14:27", "remaining_time": "0:37:26", "throughput": 1032.03, "total_tokens": 4610816} {"current_steps": 51215, "total_steps": 76960, "loss": 0.0574, "lr": 1.519457601937433e-05, "epoch": 13.309511434511435, "percentage": 66.55, "elapsed_time": "1:14:28", "remaining_time": "0:37:26", "throughput": 1032.04, "total_tokens": 4611280} {"current_steps": 51220, "total_steps": 76960, "loss": 0.5958, "lr": 1.5189360962317409e-05, "epoch": 13.31081081081081, "percentage": 66.55, "elapsed_time": "1:14:28", "remaining_time": "0:37:25", "throughput": 1032.05, "total_tokens": 4611744} {"current_steps": 51225, "total_steps": 76960, "loss": 0.2434, "lr": 1.5184146409831057e-05, "epoch": 13.312110187110187, "percentage": 66.56, "elapsed_time": "1:14:28", "remaining_time": "0:37:25", "throughput": 1032.05, "total_tokens": 4612176} {"current_steps": 51230, "total_steps": 76960, "loss": 0.3849, "lr": 1.5178932362183457e-05, "epoch": 13.313409563409563, "percentage": 66.57, "elapsed_time": "1:14:29", "remaining_time": "0:37:24", "throughput": 1032.05, "total_tokens": 4612624} {"current_steps": 51235, "total_steps": 76960, "loss": 0.1114, "lr": 1.5173718819642783e-05, "epoch": 13.31470893970894, "percentage": 66.57, "elapsed_time": "1:14:29", "remaining_time": "0:37:24", "throughput": 1032.06, "total_tokens": 4613072} {"current_steps": 51240, "total_steps": 76960, "loss": 0.0624, "lr": 1.5168505782477155e-05, "epoch": 13.316008316008316, "percentage": 66.58, "elapsed_time": "1:14:30", "remaining_time": "0:37:23", "throughput": 1032.05, "total_tokens": 4613472} {"current_steps": 51245, "total_steps": 76960, "loss": 0.1575, "lr": 1.5163293250954702e-05, "epoch": 13.317307692307692, "percentage": 66.59, "elapsed_time": "1:14:30", "remaining_time": "0:37:23", "throughput": 1032.06, "total_tokens": 4613936} {"current_steps": 51250, "total_steps": 76960, "loss": 0.579, "lr": 1.5158081225343496e-05, "epoch": 13.318607068607069, "percentage": 66.59, "elapsed_time": "1:14:31", "remaining_time": "0:37:22", "throughput": 1032.07, "total_tokens": 4614416} {"current_steps": 51255, "total_steps": 76960, "loss": 0.2383, "lr": 1.5152869705911616e-05, "epoch": 13.319906444906445, "percentage": 66.6, "elapsed_time": "1:14:31", "remaining_time": "0:37:22", "throughput": 1032.07, "total_tokens": 4614864} {"current_steps": 51260, "total_steps": 76960, "loss": 0.3811, "lr": 1.5147658692927067e-05, "epoch": 13.32120582120582, "percentage": 66.61, "elapsed_time": "1:14:31", "remaining_time": "0:37:22", "throughput": 1032.08, "total_tokens": 4615344} {"current_steps": 51265, "total_steps": 76960, "loss": 0.1072, "lr": 1.5142448186657878e-05, "epoch": 13.322505197505198, "percentage": 66.61, "elapsed_time": "1:14:32", "remaining_time": "0:37:21", "throughput": 1032.09, "total_tokens": 4615808} {"current_steps": 51270, "total_steps": 76960, "loss": 0.3376, "lr": 1.5137238187372021e-05, "epoch": 13.323804573804575, "percentage": 66.62, "elapsed_time": "1:14:32", "remaining_time": "0:37:21", "throughput": 1032.09, "total_tokens": 4616224} {"current_steps": 51275, "total_steps": 76960, "loss": 0.0488, "lr": 1.5132028695337461e-05, "epoch": 13.32510395010395, "percentage": 66.63, "elapsed_time": "1:14:33", "remaining_time": "0:37:20", "throughput": 1032.09, "total_tokens": 4616656} {"current_steps": 51280, "total_steps": 76960, "loss": 0.3014, "lr": 1.5126819710822115e-05, "epoch": 13.326403326403327, "percentage": 66.63, "elapsed_time": "1:14:33", "remaining_time": "0:37:20", "throughput": 1032.1, "total_tokens": 4617136} {"current_steps": 51285, "total_steps": 76960, "loss": 0.219, "lr": 1.512161123409389e-05, "epoch": 13.327702702702704, "percentage": 66.64, "elapsed_time": "1:14:33", "remaining_time": "0:37:19", "throughput": 1032.1, "total_tokens": 4617584} {"current_steps": 51290, "total_steps": 76960, "loss": 0.1035, "lr": 1.511640326542067e-05, "epoch": 13.329002079002079, "percentage": 66.65, "elapsed_time": "1:14:34", "remaining_time": "0:37:19", "throughput": 1032.11, "total_tokens": 4618016} {"current_steps": 51295, "total_steps": 76960, "loss": 0.1875, "lr": 1.5111195805070288e-05, "epoch": 13.330301455301456, "percentage": 66.65, "elapsed_time": "1:14:34", "remaining_time": "0:37:18", "throughput": 1032.11, "total_tokens": 4618448} {"current_steps": 51300, "total_steps": 76960, "loss": 0.1553, "lr": 1.5105988853310596e-05, "epoch": 13.33160083160083, "percentage": 66.66, "elapsed_time": "1:14:35", "remaining_time": "0:37:18", "throughput": 1032.11, "total_tokens": 4618912} {"current_steps": 51305, "total_steps": 76960, "loss": 0.2036, "lr": 1.5100782410409367e-05, "epoch": 13.332900207900208, "percentage": 66.66, "elapsed_time": "1:14:35", "remaining_time": "0:37:18", "throughput": 1032.11, "total_tokens": 4619344} {"current_steps": 51310, "total_steps": 76960, "loss": 0.2569, "lr": 1.5095576476634388e-05, "epoch": 13.334199584199585, "percentage": 66.67, "elapsed_time": "1:14:36", "remaining_time": "0:37:17", "throughput": 1032.11, "total_tokens": 4619760} {"current_steps": 51315, "total_steps": 76960, "loss": 0.3013, "lr": 1.5090371052253394e-05, "epoch": 13.33549896049896, "percentage": 66.68, "elapsed_time": "1:14:36", "remaining_time": "0:37:17", "throughput": 1032.11, "total_tokens": 4620192} {"current_steps": 51320, "total_steps": 76960, "loss": 0.1932, "lr": 1.5085166137534123e-05, "epoch": 13.336798336798337, "percentage": 66.68, "elapsed_time": "1:14:36", "remaining_time": "0:37:16", "throughput": 1032.12, "total_tokens": 4620672} {"current_steps": 51325, "total_steps": 76960, "loss": 0.2923, "lr": 1.507996173274425e-05, "epoch": 13.338097713097714, "percentage": 66.69, "elapsed_time": "1:14:37", "remaining_time": "0:37:16", "throughput": 1032.14, "total_tokens": 4621152} {"current_steps": 51330, "total_steps": 76960, "loss": 0.3195, "lr": 1.5074757838151452e-05, "epoch": 13.339397089397089, "percentage": 66.7, "elapsed_time": "1:14:37", "remaining_time": "0:37:15", "throughput": 1032.15, "total_tokens": 4621632} {"current_steps": 51335, "total_steps": 76960, "loss": 0.1382, "lr": 1.5069554454023366e-05, "epoch": 13.340696465696466, "percentage": 66.7, "elapsed_time": "1:14:38", "remaining_time": "0:37:15", "throughput": 1032.14, "total_tokens": 4622048} {"current_steps": 51340, "total_steps": 76960, "loss": 0.6462, "lr": 1.5064351580627618e-05, "epoch": 13.341995841995843, "percentage": 66.71, "elapsed_time": "1:14:38", "remaining_time": "0:37:14", "throughput": 1032.16, "total_tokens": 4622528} {"current_steps": 51345, "total_steps": 76960, "loss": 0.006, "lr": 1.505914921823178e-05, "epoch": 13.343295218295218, "percentage": 66.72, "elapsed_time": "1:14:38", "remaining_time": "0:37:14", "throughput": 1032.16, "total_tokens": 4622992} {"current_steps": 51350, "total_steps": 76960, "loss": 0.1142, "lr": 1.5053947367103422e-05, "epoch": 13.344594594594595, "percentage": 66.72, "elapsed_time": "1:14:39", "remaining_time": "0:37:14", "throughput": 1032.16, "total_tokens": 4623424} {"current_steps": 51355, "total_steps": 76960, "loss": 0.6663, "lr": 1.5048746027510085e-05, "epoch": 13.345893970893972, "percentage": 66.73, "elapsed_time": "1:14:39", "remaining_time": "0:37:13", "throughput": 1032.17, "total_tokens": 4623872} {"current_steps": 51360, "total_steps": 76960, "loss": 0.0919, "lr": 1.5043545199719272e-05, "epoch": 13.347193347193347, "percentage": 66.74, "elapsed_time": "1:14:40", "remaining_time": "0:37:13", "throughput": 1032.17, "total_tokens": 4624304} {"current_steps": 51365, "total_steps": 76960, "loss": 0.0559, "lr": 1.503834488399847e-05, "epoch": 13.348492723492724, "percentage": 66.74, "elapsed_time": "1:14:40", "remaining_time": "0:37:12", "throughput": 1032.17, "total_tokens": 4624752} {"current_steps": 51370, "total_steps": 76960, "loss": 0.2964, "lr": 1.5033145080615129e-05, "epoch": 13.3497920997921, "percentage": 66.75, "elapsed_time": "1:14:41", "remaining_time": "0:37:12", "throughput": 1032.18, "total_tokens": 4625200} {"current_steps": 51375, "total_steps": 76960, "loss": 0.1023, "lr": 1.50279457898367e-05, "epoch": 13.351091476091476, "percentage": 66.76, "elapsed_time": "1:14:41", "remaining_time": "0:37:11", "throughput": 1032.18, "total_tokens": 4625632} {"current_steps": 51380, "total_steps": 76960, "loss": 0.2523, "lr": 1.5022747011930564e-05, "epoch": 13.352390852390853, "percentage": 66.76, "elapsed_time": "1:14:41", "remaining_time": "0:37:11", "throughput": 1032.19, "total_tokens": 4626112} {"current_steps": 51385, "total_steps": 76960, "loss": 0.2276, "lr": 1.5017548747164111e-05, "epoch": 13.353690228690228, "percentage": 66.77, "elapsed_time": "1:14:42", "remaining_time": "0:37:10", "throughput": 1032.19, "total_tokens": 4626560} {"current_steps": 51390, "total_steps": 76960, "loss": 0.1064, "lr": 1.5012350995804686e-05, "epoch": 13.354989604989605, "percentage": 66.77, "elapsed_time": "1:14:42", "remaining_time": "0:37:10", "throughput": 1032.21, "total_tokens": 4627072} {"current_steps": 51395, "total_steps": 76960, "loss": 0.1008, "lr": 1.500715375811963e-05, "epoch": 13.356288981288982, "percentage": 66.78, "elapsed_time": "1:14:43", "remaining_time": "0:37:09", "throughput": 1032.21, "total_tokens": 4627504} {"current_steps": 51400, "total_steps": 76960, "loss": 0.1843, "lr": 1.5001957034376221e-05, "epoch": 13.357588357588357, "percentage": 66.79, "elapsed_time": "1:14:43", "remaining_time": "0:37:09", "throughput": 1032.22, "total_tokens": 4627952} {"current_steps": 51405, "total_steps": 76960, "loss": 0.1857, "lr": 1.4996760824841747e-05, "epoch": 13.358887733887734, "percentage": 66.79, "elapsed_time": "1:14:43", "remaining_time": "0:37:09", "throughput": 1032.22, "total_tokens": 4628400} {"current_steps": 51410, "total_steps": 76960, "loss": 0.0289, "lr": 1.4991565129783452e-05, "epoch": 13.36018711018711, "percentage": 66.8, "elapsed_time": "1:14:44", "remaining_time": "0:37:08", "throughput": 1032.23, "total_tokens": 4628880} {"current_steps": 51415, "total_steps": 76960, "loss": 0.196, "lr": 1.4986369949468543e-05, "epoch": 13.361486486486486, "percentage": 66.81, "elapsed_time": "1:14:44", "remaining_time": "0:37:08", "throughput": 1032.25, "total_tokens": 4629392} {"current_steps": 51420, "total_steps": 76960, "loss": 0.534, "lr": 1.4981175284164226e-05, "epoch": 13.362785862785863, "percentage": 66.81, "elapsed_time": "1:14:45", "remaining_time": "0:37:07", "throughput": 1032.26, "total_tokens": 4629856} {"current_steps": 51425, "total_steps": 76960, "loss": 0.2251, "lr": 1.4975981134137659e-05, "epoch": 13.36408523908524, "percentage": 66.82, "elapsed_time": "1:14:45", "remaining_time": "0:37:07", "throughput": 1032.25, "total_tokens": 4630256} {"current_steps": 51430, "total_steps": 76960, "loss": 0.1082, "lr": 1.4970787499655998e-05, "epoch": 13.365384615384615, "percentage": 66.83, "elapsed_time": "1:14:46", "remaining_time": "0:37:06", "throughput": 1032.26, "total_tokens": 4630720} {"current_steps": 51435, "total_steps": 76960, "loss": 0.1975, "lr": 1.4965594380986334e-05, "epoch": 13.366683991683992, "percentage": 66.83, "elapsed_time": "1:14:46", "remaining_time": "0:37:06", "throughput": 1032.27, "total_tokens": 4631216} {"current_steps": 51440, "total_steps": 76960, "loss": 0.1285, "lr": 1.4960401778395771e-05, "epoch": 13.367983367983369, "percentage": 66.84, "elapsed_time": "1:14:46", "remaining_time": "0:37:05", "throughput": 1032.28, "total_tokens": 4631664} {"current_steps": 51445, "total_steps": 76960, "loss": 0.375, "lr": 1.4955209692151358e-05, "epoch": 13.369282744282744, "percentage": 66.85, "elapsed_time": "1:14:47", "remaining_time": "0:37:05", "throughput": 1032.29, "total_tokens": 4632144} {"current_steps": 51450, "total_steps": 76960, "loss": 0.6265, "lr": 1.4950018122520148e-05, "epoch": 13.370582120582121, "percentage": 66.85, "elapsed_time": "1:14:47", "remaining_time": "0:37:05", "throughput": 1032.3, "total_tokens": 4632624} {"current_steps": 51455, "total_steps": 76960, "loss": 0.3007, "lr": 1.4944827069769123e-05, "epoch": 13.371881496881496, "percentage": 66.86, "elapsed_time": "1:14:48", "remaining_time": "0:37:04", "throughput": 1032.3, "total_tokens": 4633056} {"current_steps": 51460, "total_steps": 76960, "loss": 0.1152, "lr": 1.493963653416528e-05, "epoch": 13.373180873180873, "percentage": 66.87, "elapsed_time": "1:14:48", "remaining_time": "0:37:04", "throughput": 1032.3, "total_tokens": 4633488} {"current_steps": 51465, "total_steps": 76960, "loss": 0.0278, "lr": 1.4934446515975568e-05, "epoch": 13.37448024948025, "percentage": 66.87, "elapsed_time": "1:14:48", "remaining_time": "0:37:03", "throughput": 1032.32, "total_tokens": 4633984} {"current_steps": 51470, "total_steps": 76960, "loss": 0.36, "lr": 1.4929257015466923e-05, "epoch": 13.375779625779625, "percentage": 66.88, "elapsed_time": "1:14:49", "remaining_time": "0:37:03", "throughput": 1032.32, "total_tokens": 4634416} {"current_steps": 51475, "total_steps": 76960, "loss": 0.3015, "lr": 1.4924068032906235e-05, "epoch": 13.377079002079002, "percentage": 66.89, "elapsed_time": "1:14:49", "remaining_time": "0:37:02", "throughput": 1032.33, "total_tokens": 4634896} {"current_steps": 51480, "total_steps": 76960, "loss": 0.2634, "lr": 1.491887956856038e-05, "epoch": 13.378378378378379, "percentage": 66.89, "elapsed_time": "1:14:50", "remaining_time": "0:37:02", "throughput": 1032.33, "total_tokens": 4635344} {"current_steps": 51485, "total_steps": 76960, "loss": 0.0023, "lr": 1.4913691622696213e-05, "epoch": 13.379677754677754, "percentage": 66.9, "elapsed_time": "1:14:50", "remaining_time": "0:37:01", "throughput": 1032.33, "total_tokens": 4635760} {"current_steps": 51490, "total_steps": 76960, "loss": 0.15, "lr": 1.4908504195580542e-05, "epoch": 13.380977130977131, "percentage": 66.9, "elapsed_time": "1:14:50", "remaining_time": "0:37:01", "throughput": 1032.33, "total_tokens": 4636192} {"current_steps": 51495, "total_steps": 76960, "loss": 0.324, "lr": 1.4903317287480175e-05, "epoch": 13.382276507276508, "percentage": 66.91, "elapsed_time": "1:14:51", "remaining_time": "0:37:01", "throughput": 1032.34, "total_tokens": 4636672} {"current_steps": 51500, "total_steps": 76960, "loss": 0.6629, "lr": 1.4898130898661871e-05, "epoch": 13.383575883575883, "percentage": 66.92, "elapsed_time": "1:14:51", "remaining_time": "0:37:00", "throughput": 1032.35, "total_tokens": 4637152} {"current_steps": 51505, "total_steps": 76960, "loss": 0.441, "lr": 1.489294502939238e-05, "epoch": 13.38487525987526, "percentage": 66.92, "elapsed_time": "1:14:52", "remaining_time": "0:37:00", "throughput": 1032.35, "total_tokens": 4637584} {"current_steps": 51510, "total_steps": 76960, "loss": 0.233, "lr": 1.4887759679938403e-05, "epoch": 13.386174636174637, "percentage": 66.93, "elapsed_time": "1:14:52", "remaining_time": "0:36:59", "throughput": 1032.35, "total_tokens": 4638016} {"current_steps": 51515, "total_steps": 76960, "loss": 0.2857, "lr": 1.488257485056664e-05, "epoch": 13.387474012474012, "percentage": 66.94, "elapsed_time": "1:14:53", "remaining_time": "0:36:59", "throughput": 1032.35, "total_tokens": 4638448} {"current_steps": 51520, "total_steps": 76960, "loss": 0.2346, "lr": 1.487739054154374e-05, "epoch": 13.388773388773389, "percentage": 66.94, "elapsed_time": "1:14:53", "remaining_time": "0:36:58", "throughput": 1032.35, "total_tokens": 4638880} {"current_steps": 51525, "total_steps": 76960, "loss": 0.0918, "lr": 1.4872206753136353e-05, "epoch": 13.390072765072764, "percentage": 66.95, "elapsed_time": "1:14:53", "remaining_time": "0:36:58", "throughput": 1032.37, "total_tokens": 4639360} {"current_steps": 51530, "total_steps": 76960, "loss": 0.3609, "lr": 1.4867023485611064e-05, "epoch": 13.391372141372141, "percentage": 66.96, "elapsed_time": "1:14:54", "remaining_time": "0:36:57", "throughput": 1032.37, "total_tokens": 4639808} {"current_steps": 51535, "total_steps": 76960, "loss": 0.5288, "lr": 1.4861840739234478e-05, "epoch": 13.392671517671518, "percentage": 66.96, "elapsed_time": "1:14:54", "remaining_time": "0:36:57", "throughput": 1032.37, "total_tokens": 4640240} {"current_steps": 51540, "total_steps": 76960, "loss": 0.3217, "lr": 1.4856658514273142e-05, "epoch": 13.393970893970893, "percentage": 66.97, "elapsed_time": "1:14:55", "remaining_time": "0:36:57", "throughput": 1032.38, "total_tokens": 4640688} {"current_steps": 51545, "total_steps": 76960, "loss": 0.0512, "lr": 1.4851476810993558e-05, "epoch": 13.39527027027027, "percentage": 66.98, "elapsed_time": "1:14:55", "remaining_time": "0:36:56", "throughput": 1032.38, "total_tokens": 4641136} {"current_steps": 51550, "total_steps": 76960, "loss": 0.4004, "lr": 1.484629562966226e-05, "epoch": 13.396569646569647, "percentage": 66.98, "elapsed_time": "1:14:55", "remaining_time": "0:36:56", "throughput": 1032.38, "total_tokens": 4641568} {"current_steps": 51555, "total_steps": 76960, "loss": 0.5209, "lr": 1.48411149705457e-05, "epoch": 13.397869022869022, "percentage": 66.99, "elapsed_time": "1:14:56", "remaining_time": "0:36:55", "throughput": 1032.39, "total_tokens": 4642048} {"current_steps": 51560, "total_steps": 76960, "loss": 0.547, "lr": 1.4835934833910331e-05, "epoch": 13.3991683991684, "percentage": 67.0, "elapsed_time": "1:14:56", "remaining_time": "0:36:55", "throughput": 1032.39, "total_tokens": 4642480} {"current_steps": 51565, "total_steps": 76960, "loss": 0.1058, "lr": 1.4830755220022572e-05, "epoch": 13.400467775467776, "percentage": 67.0, "elapsed_time": "1:14:57", "remaining_time": "0:36:54", "throughput": 1032.41, "total_tokens": 4642976} {"current_steps": 51570, "total_steps": 76960, "loss": 0.3081, "lr": 1.4825576129148825e-05, "epoch": 13.401767151767151, "percentage": 67.01, "elapsed_time": "1:14:57", "remaining_time": "0:36:54", "throughput": 1032.41, "total_tokens": 4643408} {"current_steps": 51575, "total_steps": 76960, "loss": 0.0954, "lr": 1.4820397561555432e-05, "epoch": 13.403066528066528, "percentage": 67.02, "elapsed_time": "1:14:58", "remaining_time": "0:36:53", "throughput": 1032.4, "total_tokens": 4643808} {"current_steps": 51580, "total_steps": 76960, "loss": 0.1487, "lr": 1.4815219517508756e-05, "epoch": 13.404365904365905, "percentage": 67.02, "elapsed_time": "1:14:58", "remaining_time": "0:36:53", "throughput": 1032.4, "total_tokens": 4644256} {"current_steps": 51585, "total_steps": 76960, "loss": 0.038, "lr": 1.4810041997275092e-05, "epoch": 13.40566528066528, "percentage": 67.03, "elapsed_time": "1:14:58", "remaining_time": "0:36:53", "throughput": 1032.4, "total_tokens": 4644688} {"current_steps": 51590, "total_steps": 76960, "loss": 0.034, "lr": 1.4804865001120744e-05, "epoch": 13.406964656964657, "percentage": 67.03, "elapsed_time": "1:14:59", "remaining_time": "0:36:52", "throughput": 1032.41, "total_tokens": 4645136} {"current_steps": 51595, "total_steps": 76960, "loss": 0.3423, "lr": 1.4799688529311945e-05, "epoch": 13.408264033264032, "percentage": 67.04, "elapsed_time": "1:14:59", "remaining_time": "0:36:52", "throughput": 1032.41, "total_tokens": 4645584} {"current_steps": 51600, "total_steps": 76960, "loss": 0.1971, "lr": 1.4794512582114941e-05, "epoch": 13.40956340956341, "percentage": 67.05, "elapsed_time": "1:15:00", "remaining_time": "0:36:51", "throughput": 1032.42, "total_tokens": 4646032} {"current_steps": 51605, "total_steps": 76960, "loss": 0.1782, "lr": 1.478933715979594e-05, "epoch": 13.410862785862786, "percentage": 67.05, "elapsed_time": "1:15:00", "remaining_time": "0:36:51", "throughput": 1032.42, "total_tokens": 4646496} {"current_steps": 51610, "total_steps": 76960, "loss": 0.0851, "lr": 1.4784162262621104e-05, "epoch": 13.412162162162161, "percentage": 67.06, "elapsed_time": "1:15:00", "remaining_time": "0:36:50", "throughput": 1032.43, "total_tokens": 4646944} {"current_steps": 51615, "total_steps": 76960, "loss": 0.5631, "lr": 1.4778987890856594e-05, "epoch": 13.413461538461538, "percentage": 67.07, "elapsed_time": "1:15:01", "remaining_time": "0:36:50", "throughput": 1032.43, "total_tokens": 4647376} {"current_steps": 51620, "total_steps": 76960, "loss": 0.0933, "lr": 1.4773814044768528e-05, "epoch": 13.414760914760915, "percentage": 67.07, "elapsed_time": "1:15:01", "remaining_time": "0:36:49", "throughput": 1032.44, "total_tokens": 4647840} {"current_steps": 51625, "total_steps": 76960, "loss": 0.2693, "lr": 1.4768640724623012e-05, "epoch": 13.41606029106029, "percentage": 67.08, "elapsed_time": "1:15:02", "remaining_time": "0:36:49", "throughput": 1032.43, "total_tokens": 4648256} {"current_steps": 51630, "total_steps": 76960, "loss": 0.106, "lr": 1.4763467930686097e-05, "epoch": 13.417359667359667, "percentage": 67.09, "elapsed_time": "1:15:02", "remaining_time": "0:36:49", "throughput": 1032.44, "total_tokens": 4648704} {"current_steps": 51635, "total_steps": 76960, "loss": 0.0093, "lr": 1.475829566322384e-05, "epoch": 13.418659043659044, "percentage": 67.09, "elapsed_time": "1:15:03", "remaining_time": "0:36:48", "throughput": 1032.43, "total_tokens": 4649120} {"current_steps": 51640, "total_steps": 76960, "loss": 0.0748, "lr": 1.4753123922502244e-05, "epoch": 13.41995841995842, "percentage": 67.1, "elapsed_time": "1:15:03", "remaining_time": "0:36:48", "throughput": 1032.44, "total_tokens": 4649584} {"current_steps": 51645, "total_steps": 76960, "loss": 0.2947, "lr": 1.4747952708787316e-05, "epoch": 13.421257796257796, "percentage": 67.11, "elapsed_time": "1:15:03", "remaining_time": "0:36:47", "throughput": 1032.45, "total_tokens": 4650032} {"current_steps": 51650, "total_steps": 76960, "loss": 0.0064, "lr": 1.474278202234499e-05, "epoch": 13.422557172557173, "percentage": 67.11, "elapsed_time": "1:15:04", "remaining_time": "0:36:47", "throughput": 1032.45, "total_tokens": 4650480} {"current_steps": 51655, "total_steps": 76960, "loss": 0.2075, "lr": 1.4737611863441217e-05, "epoch": 13.423856548856548, "percentage": 67.12, "elapsed_time": "1:15:04", "remaining_time": "0:36:46", "throughput": 1032.45, "total_tokens": 4650928} {"current_steps": 51660, "total_steps": 76960, "loss": 0.1969, "lr": 1.4732442232341894e-05, "epoch": 13.425155925155925, "percentage": 67.13, "elapsed_time": "1:15:05", "remaining_time": "0:36:46", "throughput": 1032.46, "total_tokens": 4651376} {"current_steps": 51665, "total_steps": 76960, "loss": 0.2501, "lr": 1.4727273129312918e-05, "epoch": 13.426455301455302, "percentage": 67.13, "elapsed_time": "1:15:05", "remaining_time": "0:36:45", "throughput": 1032.47, "total_tokens": 4651840} {"current_steps": 51670, "total_steps": 76960, "loss": 0.0428, "lr": 1.472210455462012e-05, "epoch": 13.427754677754677, "percentage": 67.14, "elapsed_time": "1:15:05", "remaining_time": "0:36:45", "throughput": 1032.47, "total_tokens": 4652304} {"current_steps": 51675, "total_steps": 76960, "loss": 0.3002, "lr": 1.4716936508529328e-05, "epoch": 13.429054054054054, "percentage": 67.15, "elapsed_time": "1:15:06", "remaining_time": "0:36:45", "throughput": 1032.47, "total_tokens": 4652736} {"current_steps": 51680, "total_steps": 76960, "loss": 0.1022, "lr": 1.4711768991306358e-05, "epoch": 13.43035343035343, "percentage": 67.15, "elapsed_time": "1:15:06", "remaining_time": "0:36:44", "throughput": 1032.49, "total_tokens": 4653216} {"current_steps": 51685, "total_steps": 76960, "loss": 0.2541, "lr": 1.4706602003216951e-05, "epoch": 13.431652806652806, "percentage": 67.16, "elapsed_time": "1:15:07", "remaining_time": "0:36:44", "throughput": 1032.49, "total_tokens": 4653648} {"current_steps": 51690, "total_steps": 76960, "loss": 0.0995, "lr": 1.470143554452687e-05, "epoch": 13.432952182952183, "percentage": 67.16, "elapsed_time": "1:15:07", "remaining_time": "0:36:43", "throughput": 1032.49, "total_tokens": 4654112} {"current_steps": 51695, "total_steps": 76960, "loss": 0.1515, "lr": 1.4696269615501826e-05, "epoch": 13.434251559251559, "percentage": 67.17, "elapsed_time": "1:15:08", "remaining_time": "0:36:43", "throughput": 1032.5, "total_tokens": 4654576} {"current_steps": 51700, "total_steps": 76960, "loss": 0.3433, "lr": 1.4691104216407518e-05, "epoch": 13.435550935550935, "percentage": 67.18, "elapsed_time": "1:15:08", "remaining_time": "0:36:42", "throughput": 1032.5, "total_tokens": 4654992} {"current_steps": 51705, "total_steps": 76960, "loss": 0.108, "lr": 1.4685939347509586e-05, "epoch": 13.436850311850312, "percentage": 67.18, "elapsed_time": "1:15:08", "remaining_time": "0:36:42", "throughput": 1032.5, "total_tokens": 4655424} {"current_steps": 51710, "total_steps": 76960, "loss": 0.2646, "lr": 1.4680775009073678e-05, "epoch": 13.438149688149688, "percentage": 67.19, "elapsed_time": "1:15:09", "remaining_time": "0:36:41", "throughput": 1032.51, "total_tokens": 4655888} {"current_steps": 51715, "total_steps": 76960, "loss": 0.2885, "lr": 1.4675611201365397e-05, "epoch": 13.439449064449065, "percentage": 67.2, "elapsed_time": "1:15:09", "remaining_time": "0:36:41", "throughput": 1032.51, "total_tokens": 4656336} {"current_steps": 51720, "total_steps": 76960, "loss": 0.0837, "lr": 1.4670447924650335e-05, "epoch": 13.440748440748441, "percentage": 67.2, "elapsed_time": "1:15:10", "remaining_time": "0:36:41", "throughput": 1032.52, "total_tokens": 4656816} {"current_steps": 51725, "total_steps": 76960, "loss": 0.1141, "lr": 1.4665285179194022e-05, "epoch": 13.442047817047817, "percentage": 67.21, "elapsed_time": "1:15:10", "remaining_time": "0:36:40", "throughput": 1032.52, "total_tokens": 4657216} {"current_steps": 51730, "total_steps": 76960, "loss": 0.3083, "lr": 1.4660122965262e-05, "epoch": 13.443347193347194, "percentage": 67.22, "elapsed_time": "1:15:10", "remaining_time": "0:36:40", "throughput": 1032.52, "total_tokens": 4657648} {"current_steps": 51735, "total_steps": 76960, "loss": 0.3184, "lr": 1.4654961283119768e-05, "epoch": 13.44464656964657, "percentage": 67.22, "elapsed_time": "1:15:11", "remaining_time": "0:36:39", "throughput": 1032.52, "total_tokens": 4658112} {"current_steps": 51740, "total_steps": 76960, "loss": 0.4025, "lr": 1.4649800133032775e-05, "epoch": 13.445945945945946, "percentage": 67.23, "elapsed_time": "1:15:11", "remaining_time": "0:36:39", "throughput": 1032.53, "total_tokens": 4658576} {"current_steps": 51745, "total_steps": 76960, "loss": 0.5485, "lr": 1.4644639515266483e-05, "epoch": 13.447245322245323, "percentage": 67.24, "elapsed_time": "1:15:12", "remaining_time": "0:36:38", "throughput": 1032.53, "total_tokens": 4658992} {"current_steps": 51750, "total_steps": 76960, "loss": 0.3563, "lr": 1.4639479430086304e-05, "epoch": 13.448544698544698, "percentage": 67.24, "elapsed_time": "1:15:12", "remaining_time": "0:36:38", "throughput": 1032.54, "total_tokens": 4659456} {"current_steps": 51755, "total_steps": 76960, "loss": 0.3413, "lr": 1.463431987775763e-05, "epoch": 13.449844074844075, "percentage": 67.25, "elapsed_time": "1:15:13", "remaining_time": "0:36:37", "throughput": 1032.54, "total_tokens": 4659904} {"current_steps": 51760, "total_steps": 76960, "loss": 0.3059, "lr": 1.462916085854581e-05, "epoch": 13.451143451143452, "percentage": 67.26, "elapsed_time": "1:15:13", "remaining_time": "0:36:37", "throughput": 1032.55, "total_tokens": 4660384} {"current_steps": 51765, "total_steps": 76960, "loss": 0.1734, "lr": 1.4624002372716184e-05, "epoch": 13.452442827442827, "percentage": 67.26, "elapsed_time": "1:15:13", "remaining_time": "0:36:36", "throughput": 1032.55, "total_tokens": 4660816} {"current_steps": 51770, "total_steps": 76960, "loss": 0.0736, "lr": 1.4618844420534055e-05, "epoch": 13.453742203742204, "percentage": 67.27, "elapsed_time": "1:15:14", "remaining_time": "0:36:36", "throughput": 1032.56, "total_tokens": 4661264} {"current_steps": 51775, "total_steps": 76960, "loss": 0.1503, "lr": 1.4613687002264713e-05, "epoch": 13.45504158004158, "percentage": 67.28, "elapsed_time": "1:15:14", "remaining_time": "0:36:36", "throughput": 1032.56, "total_tokens": 4661728} {"current_steps": 51780, "total_steps": 76960, "loss": 0.3571, "lr": 1.4608530118173388e-05, "epoch": 13.456340956340956, "percentage": 67.28, "elapsed_time": "1:15:15", "remaining_time": "0:36:35", "throughput": 1032.57, "total_tokens": 4662192} {"current_steps": 51785, "total_steps": 76960, "loss": 0.2015, "lr": 1.460337376852533e-05, "epoch": 13.457640332640333, "percentage": 67.29, "elapsed_time": "1:15:15", "remaining_time": "0:36:35", "throughput": 1032.57, "total_tokens": 4662624} {"current_steps": 51790, "total_steps": 76960, "loss": 0.0459, "lr": 1.4598217953585711e-05, "epoch": 13.45893970893971, "percentage": 67.29, "elapsed_time": "1:15:15", "remaining_time": "0:36:34", "throughput": 1032.57, "total_tokens": 4663072} {"current_steps": 51795, "total_steps": 76960, "loss": 0.248, "lr": 1.4593062673619711e-05, "epoch": 13.460239085239085, "percentage": 67.3, "elapsed_time": "1:15:16", "remaining_time": "0:36:34", "throughput": 1032.58, "total_tokens": 4663536} {"current_steps": 51800, "total_steps": 76960, "loss": 0.6093, "lr": 1.458790792889248e-05, "epoch": 13.461538461538462, "percentage": 67.31, "elapsed_time": "1:15:16", "remaining_time": "0:36:33", "throughput": 1032.58, "total_tokens": 4663968} {"current_steps": 51805, "total_steps": 76960, "loss": 0.1197, "lr": 1.4582753719669106e-05, "epoch": 13.462837837837839, "percentage": 67.31, "elapsed_time": "1:15:17", "remaining_time": "0:36:33", "throughput": 1032.59, "total_tokens": 4664416} {"current_steps": 51810, "total_steps": 76960, "loss": 0.0624, "lr": 1.4577600046214701e-05, "epoch": 13.464137214137214, "percentage": 67.32, "elapsed_time": "1:15:17", "remaining_time": "0:36:32", "throughput": 1032.59, "total_tokens": 4664864} {"current_steps": 51815, "total_steps": 76960, "loss": 0.2538, "lr": 1.45724469087943e-05, "epoch": 13.46543659043659, "percentage": 67.33, "elapsed_time": "1:15:18", "remaining_time": "0:36:32", "throughput": 1032.59, "total_tokens": 4665312} {"current_steps": 51820, "total_steps": 76960, "loss": 0.0291, "lr": 1.4567294307672947e-05, "epoch": 13.466735966735968, "percentage": 67.33, "elapsed_time": "1:15:18", "remaining_time": "0:36:32", "throughput": 1032.59, "total_tokens": 4665744} {"current_steps": 51825, "total_steps": 76960, "loss": 0.3481, "lr": 1.4562142243115644e-05, "epoch": 13.468035343035343, "percentage": 67.34, "elapsed_time": "1:15:18", "remaining_time": "0:36:31", "throughput": 1032.6, "total_tokens": 4666208} {"current_steps": 51830, "total_steps": 76960, "loss": 0.3779, "lr": 1.4556990715387375e-05, "epoch": 13.46933471933472, "percentage": 67.35, "elapsed_time": "1:15:19", "remaining_time": "0:36:31", "throughput": 1032.62, "total_tokens": 4666720} {"current_steps": 51835, "total_steps": 76960, "loss": 0.0486, "lr": 1.4551839724753074e-05, "epoch": 13.470634095634095, "percentage": 67.35, "elapsed_time": "1:15:19", "remaining_time": "0:36:30", "throughput": 1032.62, "total_tokens": 4667136} {"current_steps": 51840, "total_steps": 76960, "loss": 0.0886, "lr": 1.4546689271477674e-05, "epoch": 13.471933471933472, "percentage": 67.36, "elapsed_time": "1:15:20", "remaining_time": "0:36:30", "throughput": 1032.62, "total_tokens": 4667584} {"current_steps": 51845, "total_steps": 76960, "loss": 0.3235, "lr": 1.454153935582605e-05, "epoch": 13.473232848232849, "percentage": 67.37, "elapsed_time": "1:15:20", "remaining_time": "0:36:29", "throughput": 1032.63, "total_tokens": 4668048} {"current_steps": 51850, "total_steps": 76960, "loss": 0.3998, "lr": 1.4536389978063086e-05, "epoch": 13.474532224532224, "percentage": 67.37, "elapsed_time": "1:15:20", "remaining_time": "0:36:29", "throughput": 1032.63, "total_tokens": 4668480} {"current_steps": 51855, "total_steps": 76960, "loss": 0.1365, "lr": 1.4531241138453605e-05, "epoch": 13.4758316008316, "percentage": 67.38, "elapsed_time": "1:15:21", "remaining_time": "0:36:28", "throughput": 1032.64, "total_tokens": 4668944} {"current_steps": 51860, "total_steps": 76960, "loss": 0.1972, "lr": 1.4526092837262423e-05, "epoch": 13.477130977130978, "percentage": 67.39, "elapsed_time": "1:15:21", "remaining_time": "0:36:28", "throughput": 1032.65, "total_tokens": 4669424} {"current_steps": 51865, "total_steps": 76960, "loss": 0.361, "lr": 1.4520945074754327e-05, "epoch": 13.478430353430353, "percentage": 67.39, "elapsed_time": "1:15:22", "remaining_time": "0:36:28", "throughput": 1032.65, "total_tokens": 4669856} {"current_steps": 51870, "total_steps": 76960, "loss": 0.1599, "lr": 1.4515797851194064e-05, "epoch": 13.47972972972973, "percentage": 67.4, "elapsed_time": "1:15:22", "remaining_time": "0:36:27", "throughput": 1032.65, "total_tokens": 4670288} {"current_steps": 51875, "total_steps": 76960, "loss": 0.4796, "lr": 1.4510651166846367e-05, "epoch": 13.481029106029107, "percentage": 67.41, "elapsed_time": "1:15:23", "remaining_time": "0:36:27", "throughput": 1032.66, "total_tokens": 4670768} {"current_steps": 51880, "total_steps": 76960, "loss": 0.226, "lr": 1.4505505021975923e-05, "epoch": 13.482328482328482, "percentage": 67.41, "elapsed_time": "1:15:23", "remaining_time": "0:36:26", "throughput": 1032.66, "total_tokens": 4671216} {"current_steps": 51885, "total_steps": 76960, "loss": 0.0281, "lr": 1.450035941684742e-05, "epoch": 13.483627858627859, "percentage": 67.42, "elapsed_time": "1:15:23", "remaining_time": "0:36:26", "throughput": 1032.66, "total_tokens": 4671648} {"current_steps": 51890, "total_steps": 76960, "loss": 0.4182, "lr": 1.4495214351725483e-05, "epoch": 13.484927234927236, "percentage": 67.42, "elapsed_time": "1:15:24", "remaining_time": "0:36:25", "throughput": 1032.67, "total_tokens": 4672096} {"current_steps": 51895, "total_steps": 76960, "loss": 0.3074, "lr": 1.4490069826874736e-05, "epoch": 13.486226611226611, "percentage": 67.43, "elapsed_time": "1:15:24", "remaining_time": "0:36:25", "throughput": 1032.67, "total_tokens": 4672528} {"current_steps": 51900, "total_steps": 76960, "loss": 0.3015, "lr": 1.448492584255977e-05, "epoch": 13.487525987525988, "percentage": 67.44, "elapsed_time": "1:15:25", "remaining_time": "0:36:24", "throughput": 1032.67, "total_tokens": 4672976} {"current_steps": 51905, "total_steps": 76960, "loss": 0.1365, "lr": 1.4479782399045152e-05, "epoch": 13.488825363825363, "percentage": 67.44, "elapsed_time": "1:15:25", "remaining_time": "0:36:24", "throughput": 1032.68, "total_tokens": 4673424} {"current_steps": 51910, "total_steps": 76960, "loss": 0.3317, "lr": 1.4474639496595397e-05, "epoch": 13.49012474012474, "percentage": 67.45, "elapsed_time": "1:15:25", "remaining_time": "0:36:24", "throughput": 1032.68, "total_tokens": 4673872} {"current_steps": 51915, "total_steps": 76960, "loss": 0.1371, "lr": 1.4469497135475025e-05, "epoch": 13.491424116424117, "percentage": 67.46, "elapsed_time": "1:15:26", "remaining_time": "0:36:23", "throughput": 1032.69, "total_tokens": 4674320} {"current_steps": 51920, "total_steps": 76960, "loss": 0.2714, "lr": 1.4464355315948497e-05, "epoch": 13.492723492723492, "percentage": 67.46, "elapsed_time": "1:15:26", "remaining_time": "0:36:23", "throughput": 1032.69, "total_tokens": 4674752} {"current_steps": 51925, "total_steps": 76960, "loss": 0.2953, "lr": 1.4459214038280277e-05, "epoch": 13.494022869022869, "percentage": 67.47, "elapsed_time": "1:15:27", "remaining_time": "0:36:22", "throughput": 1032.7, "total_tokens": 4675248} {"current_steps": 51930, "total_steps": 76960, "loss": 0.1507, "lr": 1.4454073302734772e-05, "epoch": 13.495322245322246, "percentage": 67.48, "elapsed_time": "1:15:27", "remaining_time": "0:36:22", "throughput": 1032.71, "total_tokens": 4675728} {"current_steps": 51935, "total_steps": 76960, "loss": 0.1224, "lr": 1.4448933109576378e-05, "epoch": 13.496621621621621, "percentage": 67.48, "elapsed_time": "1:15:28", "remaining_time": "0:36:21", "throughput": 1032.72, "total_tokens": 4676176} {"current_steps": 51940, "total_steps": 76960, "loss": 0.1911, "lr": 1.4443793459069477e-05, "epoch": 13.497920997920998, "percentage": 67.49, "elapsed_time": "1:15:28", "remaining_time": "0:36:21", "throughput": 1032.73, "total_tokens": 4676640} {"current_steps": 51945, "total_steps": 76960, "loss": 0.1017, "lr": 1.4438654351478382e-05, "epoch": 13.499220374220375, "percentage": 67.5, "elapsed_time": "1:15:28", "remaining_time": "0:36:20", "throughput": 1032.74, "total_tokens": 4677136} {"current_steps": 51950, "total_steps": 76960, "loss": 0.4344, "lr": 1.4433515787067425e-05, "epoch": 13.50051975051975, "percentage": 67.5, "elapsed_time": "1:15:29", "remaining_time": "0:36:20", "throughput": 1032.75, "total_tokens": 4677584} {"current_steps": 51955, "total_steps": 76960, "loss": 0.115, "lr": 1.4428377766100861e-05, "epoch": 13.501819126819127, "percentage": 67.51, "elapsed_time": "1:15:29", "remaining_time": "0:36:20", "throughput": 1032.75, "total_tokens": 4678048} {"current_steps": 51960, "total_steps": 76960, "loss": 0.1012, "lr": 1.442324028884297e-05, "epoch": 13.503118503118504, "percentage": 67.52, "elapsed_time": "1:15:30", "remaining_time": "0:36:19", "throughput": 1032.76, "total_tokens": 4678496} {"current_steps": 51965, "total_steps": 76960, "loss": 0.1289, "lr": 1.4418103355557955e-05, "epoch": 13.504417879417879, "percentage": 67.52, "elapsed_time": "1:15:30", "remaining_time": "0:36:19", "throughput": 1032.76, "total_tokens": 4678928} {"current_steps": 51970, "total_steps": 76960, "loss": 0.2685, "lr": 1.4412966966510027e-05, "epoch": 13.505717255717256, "percentage": 67.53, "elapsed_time": "1:15:30", "remaining_time": "0:36:18", "throughput": 1032.76, "total_tokens": 4679392} {"current_steps": 51975, "total_steps": 76960, "loss": 0.2074, "lr": 1.4407831121963347e-05, "epoch": 13.507016632016633, "percentage": 67.54, "elapsed_time": "1:15:31", "remaining_time": "0:36:18", "throughput": 1032.77, "total_tokens": 4679856} {"current_steps": 51980, "total_steps": 76960, "loss": 0.1541, "lr": 1.4402695822182071e-05, "epoch": 13.508316008316008, "percentage": 67.54, "elapsed_time": "1:15:31", "remaining_time": "0:36:17", "throughput": 1032.78, "total_tokens": 4680304} {"current_steps": 51985, "total_steps": 76960, "loss": 0.1021, "lr": 1.4397561067430298e-05, "epoch": 13.509615384615385, "percentage": 67.55, "elapsed_time": "1:15:32", "remaining_time": "0:36:17", "throughput": 1032.78, "total_tokens": 4680752} {"current_steps": 51990, "total_steps": 76960, "loss": 0.249, "lr": 1.4392426857972124e-05, "epoch": 13.51091476091476, "percentage": 67.55, "elapsed_time": "1:15:32", "remaining_time": "0:36:16", "throughput": 1032.79, "total_tokens": 4681232} {"current_steps": 51995, "total_steps": 76960, "loss": 0.2883, "lr": 1.4387293194071599e-05, "epoch": 13.512214137214137, "percentage": 67.56, "elapsed_time": "1:15:33", "remaining_time": "0:36:16", "throughput": 1032.81, "total_tokens": 4681728} {"current_steps": 52000, "total_steps": 76960, "loss": 0.0983, "lr": 1.4382160075992748e-05, "epoch": 13.513513513513514, "percentage": 67.57, "elapsed_time": "1:15:33", "remaining_time": "0:36:16", "throughput": 1032.81, "total_tokens": 4682176} {"current_steps": 52005, "total_steps": 76960, "loss": 0.292, "lr": 1.4377027503999574e-05, "epoch": 13.51481288981289, "percentage": 67.57, "elapsed_time": "1:15:33", "remaining_time": "0:36:15", "throughput": 1032.81, "total_tokens": 4682592} {"current_steps": 52010, "total_steps": 76960, "loss": 0.0882, "lr": 1.4371895478356057e-05, "epoch": 13.516112266112266, "percentage": 67.58, "elapsed_time": "1:15:34", "remaining_time": "0:36:15", "throughput": 1032.82, "total_tokens": 4683072} {"current_steps": 52015, "total_steps": 76960, "loss": 0.041, "lr": 1.4366763999326149e-05, "epoch": 13.517411642411643, "percentage": 67.59, "elapsed_time": "1:15:34", "remaining_time": "0:36:14", "throughput": 1032.82, "total_tokens": 4683504} {"current_steps": 52020, "total_steps": 76960, "loss": 0.2542, "lr": 1.4361633067173743e-05, "epoch": 13.518711018711018, "percentage": 67.59, "elapsed_time": "1:15:35", "remaining_time": "0:36:14", "throughput": 1032.81, "total_tokens": 4683904} {"current_steps": 52025, "total_steps": 76960, "loss": 0.3802, "lr": 1.4356502682162754e-05, "epoch": 13.520010395010395, "percentage": 67.6, "elapsed_time": "1:15:35", "remaining_time": "0:36:13", "throughput": 1032.82, "total_tokens": 4684384} {"current_steps": 52030, "total_steps": 76960, "loss": 0.2326, "lr": 1.435137284455702e-05, "epoch": 13.521309771309772, "percentage": 67.61, "elapsed_time": "1:15:35", "remaining_time": "0:36:13", "throughput": 1032.83, "total_tokens": 4684848} {"current_steps": 52035, "total_steps": 76960, "loss": 0.08, "lr": 1.4346243554620383e-05, "epoch": 13.522609147609147, "percentage": 67.61, "elapsed_time": "1:15:36", "remaining_time": "0:36:12", "throughput": 1032.84, "total_tokens": 4685296} {"current_steps": 52040, "total_steps": 76960, "loss": 0.028, "lr": 1.4341114812616649e-05, "epoch": 13.523908523908524, "percentage": 67.62, "elapsed_time": "1:15:36", "remaining_time": "0:36:12", "throughput": 1032.84, "total_tokens": 4685760} {"current_steps": 52045, "total_steps": 76960, "loss": 0.2709, "lr": 1.4335986618809604e-05, "epoch": 13.5252079002079, "percentage": 67.63, "elapsed_time": "1:15:37", "remaining_time": "0:36:12", "throughput": 1032.85, "total_tokens": 4686208} {"current_steps": 52050, "total_steps": 76960, "loss": 0.0689, "lr": 1.4330858973462974e-05, "epoch": 13.526507276507276, "percentage": 67.63, "elapsed_time": "1:15:37", "remaining_time": "0:36:11", "throughput": 1032.85, "total_tokens": 4686656} {"current_steps": 52055, "total_steps": 76960, "loss": 0.1031, "lr": 1.4325731876840498e-05, "epoch": 13.527806652806653, "percentage": 67.64, "elapsed_time": "1:15:38", "remaining_time": "0:36:11", "throughput": 1032.86, "total_tokens": 4687104} {"current_steps": 52060, "total_steps": 76960, "loss": 0.0172, "lr": 1.432060532920586e-05, "epoch": 13.529106029106028, "percentage": 67.65, "elapsed_time": "1:15:38", "remaining_time": "0:36:10", "throughput": 1032.87, "total_tokens": 4687600} {"current_steps": 52065, "total_steps": 76960, "loss": 0.3378, "lr": 1.4315479330822712e-05, "epoch": 13.530405405405405, "percentage": 67.65, "elapsed_time": "1:15:38", "remaining_time": "0:36:10", "throughput": 1032.88, "total_tokens": 4688048} {"current_steps": 52070, "total_steps": 76960, "loss": 0.4019, "lr": 1.4310353881954702e-05, "epoch": 13.531704781704782, "percentage": 67.66, "elapsed_time": "1:15:39", "remaining_time": "0:36:09", "throughput": 1032.89, "total_tokens": 4688544} {"current_steps": 52075, "total_steps": 76960, "loss": 0.1748, "lr": 1.4305228982865432e-05, "epoch": 13.533004158004157, "percentage": 67.67, "elapsed_time": "1:15:39", "remaining_time": "0:36:09", "throughput": 1032.9, "total_tokens": 4689024} {"current_steps": 52080, "total_steps": 76960, "loss": 0.104, "lr": 1.4300104633818493e-05, "epoch": 13.534303534303534, "percentage": 67.67, "elapsed_time": "1:15:40", "remaining_time": "0:36:08", "throughput": 1032.9, "total_tokens": 4689440} {"current_steps": 52085, "total_steps": 76960, "loss": 0.2011, "lr": 1.4294980835077416e-05, "epoch": 13.535602910602911, "percentage": 67.68, "elapsed_time": "1:15:40", "remaining_time": "0:36:08", "throughput": 1032.9, "total_tokens": 4689888} {"current_steps": 52090, "total_steps": 76960, "loss": 0.1942, "lr": 1.4289857586905739e-05, "epoch": 13.536902286902286, "percentage": 67.68, "elapsed_time": "1:15:40", "remaining_time": "0:36:08", "throughput": 1032.91, "total_tokens": 4690352} {"current_steps": 52095, "total_steps": 76960, "loss": 0.0293, "lr": 1.4284734889566939e-05, "epoch": 13.538201663201663, "percentage": 67.69, "elapsed_time": "1:15:41", "remaining_time": "0:36:07", "throughput": 1032.91, "total_tokens": 4690784} {"current_steps": 52100, "total_steps": 76960, "loss": 0.5492, "lr": 1.4279612743324499e-05, "epoch": 13.53950103950104, "percentage": 67.7, "elapsed_time": "1:15:41", "remaining_time": "0:36:07", "throughput": 1032.91, "total_tokens": 4691232} {"current_steps": 52105, "total_steps": 76960, "loss": 0.3078, "lr": 1.4274491148441844e-05, "epoch": 13.540800415800415, "percentage": 67.7, "elapsed_time": "1:15:42", "remaining_time": "0:36:06", "throughput": 1032.92, "total_tokens": 4691680} {"current_steps": 52110, "total_steps": 76960, "loss": 0.3269, "lr": 1.4269370105182378e-05, "epoch": 13.542099792099792, "percentage": 67.71, "elapsed_time": "1:15:42", "remaining_time": "0:36:06", "throughput": 1032.93, "total_tokens": 4692144} {"current_steps": 52115, "total_steps": 76960, "loss": 0.1768, "lr": 1.4264249613809493e-05, "epoch": 13.54339916839917, "percentage": 67.72, "elapsed_time": "1:15:42", "remaining_time": "0:36:05", "throughput": 1032.94, "total_tokens": 4692624} {"current_steps": 52120, "total_steps": 76960, "loss": 0.3085, "lr": 1.4259129674586546e-05, "epoch": 13.544698544698544, "percentage": 67.72, "elapsed_time": "1:15:43", "remaining_time": "0:36:05", "throughput": 1032.95, "total_tokens": 4693120} {"current_steps": 52125, "total_steps": 76960, "loss": 0.0298, "lr": 1.4254010287776854e-05, "epoch": 13.545997920997921, "percentage": 67.73, "elapsed_time": "1:15:43", "remaining_time": "0:36:04", "throughput": 1032.96, "total_tokens": 4693568} {"current_steps": 52130, "total_steps": 76960, "loss": 0.2415, "lr": 1.4248891453643698e-05, "epoch": 13.547297297297296, "percentage": 67.74, "elapsed_time": "1:15:44", "remaining_time": "0:36:04", "throughput": 1032.96, "total_tokens": 4694016} {"current_steps": 52135, "total_steps": 76960, "loss": 0.1028, "lr": 1.4243773172450364e-05, "epoch": 13.548596673596673, "percentage": 67.74, "elapsed_time": "1:15:44", "remaining_time": "0:36:04", "throughput": 1032.97, "total_tokens": 4694480} {"current_steps": 52140, "total_steps": 76960, "loss": 0.1936, "lr": 1.4238655444460073e-05, "epoch": 13.54989604989605, "percentage": 67.75, "elapsed_time": "1:15:45", "remaining_time": "0:36:03", "throughput": 1032.97, "total_tokens": 4694912} {"current_steps": 52145, "total_steps": 76960, "loss": 0.2248, "lr": 1.4233538269936042e-05, "epoch": 13.551195426195425, "percentage": 67.76, "elapsed_time": "1:15:45", "remaining_time": "0:36:03", "throughput": 1032.97, "total_tokens": 4695360} {"current_steps": 52150, "total_steps": 76960, "loss": 0.0475, "lr": 1.4228421649141455e-05, "epoch": 13.552494802494802, "percentage": 67.76, "elapsed_time": "1:15:45", "remaining_time": "0:36:02", "throughput": 1032.98, "total_tokens": 4695824} {"current_steps": 52155, "total_steps": 76960, "loss": 0.398, "lr": 1.4223305582339475e-05, "epoch": 13.55379417879418, "percentage": 67.77, "elapsed_time": "1:15:46", "remaining_time": "0:36:02", "throughput": 1032.99, "total_tokens": 4696288} {"current_steps": 52160, "total_steps": 76960, "loss": 0.3504, "lr": 1.4218190069793202e-05, "epoch": 13.555093555093555, "percentage": 67.78, "elapsed_time": "1:15:46", "remaining_time": "0:36:01", "throughput": 1032.98, "total_tokens": 4696704} {"current_steps": 52165, "total_steps": 76960, "loss": 0.4796, "lr": 1.4213075111765756e-05, "epoch": 13.556392931392931, "percentage": 67.78, "elapsed_time": "1:15:47", "remaining_time": "0:36:01", "throughput": 1032.98, "total_tokens": 4697120} {"current_steps": 52170, "total_steps": 76960, "loss": 0.3889, "lr": 1.420796070852018e-05, "epoch": 13.557692307692308, "percentage": 67.79, "elapsed_time": "1:15:47", "remaining_time": "0:36:00", "throughput": 1032.98, "total_tokens": 4697536} {"current_steps": 52175, "total_steps": 76960, "loss": 0.105, "lr": 1.4202846860319538e-05, "epoch": 13.558991683991684, "percentage": 67.79, "elapsed_time": "1:15:47", "remaining_time": "0:36:00", "throughput": 1032.98, "total_tokens": 4697968} {"current_steps": 52180, "total_steps": 76960, "loss": 0.3319, "lr": 1.4197733567426816e-05, "epoch": 13.56029106029106, "percentage": 67.8, "elapsed_time": "1:15:48", "remaining_time": "0:36:00", "throughput": 1032.98, "total_tokens": 4698400} {"current_steps": 52185, "total_steps": 76960, "loss": 0.1936, "lr": 1.4192620830105007e-05, "epoch": 13.561590436590437, "percentage": 67.81, "elapsed_time": "1:15:48", "remaining_time": "0:35:59", "throughput": 1032.99, "total_tokens": 4698896} {"current_steps": 52190, "total_steps": 76960, "loss": 0.1301, "lr": 1.4187508648617064e-05, "epoch": 13.562889812889813, "percentage": 67.81, "elapsed_time": "1:15:49", "remaining_time": "0:35:59", "throughput": 1033.0, "total_tokens": 4699344} {"current_steps": 52195, "total_steps": 76960, "loss": 0.3496, "lr": 1.4182397023225921e-05, "epoch": 13.56418918918919, "percentage": 67.82, "elapsed_time": "1:15:49", "remaining_time": "0:35:58", "throughput": 1033.0, "total_tokens": 4699792} {"current_steps": 52200, "total_steps": 76960, "loss": 0.3623, "lr": 1.4177285954194463e-05, "epoch": 13.565488565488565, "percentage": 67.83, "elapsed_time": "1:15:50", "remaining_time": "0:35:58", "throughput": 1033.0, "total_tokens": 4700224} {"current_steps": 52205, "total_steps": 76960, "loss": 0.0282, "lr": 1.417217544178555e-05, "epoch": 13.566787941787942, "percentage": 67.83, "elapsed_time": "1:15:50", "remaining_time": "0:35:57", "throughput": 1033.01, "total_tokens": 4700672} {"current_steps": 52210, "total_steps": 76960, "loss": 0.3879, "lr": 1.4167065486262038e-05, "epoch": 13.568087318087318, "percentage": 67.84, "elapsed_time": "1:15:50", "remaining_time": "0:35:57", "throughput": 1033.01, "total_tokens": 4701104} {"current_steps": 52215, "total_steps": 76960, "loss": 0.3464, "lr": 1.4161956087886718e-05, "epoch": 13.569386694386694, "percentage": 67.85, "elapsed_time": "1:15:51", "remaining_time": "0:35:56", "throughput": 1033.01, "total_tokens": 4701552} {"current_steps": 52220, "total_steps": 76960, "loss": 0.3209, "lr": 1.4156847246922383e-05, "epoch": 13.57068607068607, "percentage": 67.85, "elapsed_time": "1:15:51", "remaining_time": "0:35:56", "throughput": 1033.01, "total_tokens": 4702000} {"current_steps": 52225, "total_steps": 76960, "loss": 0.5573, "lr": 1.415173896363178e-05, "epoch": 13.571985446985448, "percentage": 67.86, "elapsed_time": "1:15:52", "remaining_time": "0:35:56", "throughput": 1033.02, "total_tokens": 4702464} {"current_steps": 52230, "total_steps": 76960, "loss": 0.2046, "lr": 1.4146631238277647e-05, "epoch": 13.573284823284823, "percentage": 67.87, "elapsed_time": "1:15:52", "remaining_time": "0:35:55", "throughput": 1033.02, "total_tokens": 4702896} {"current_steps": 52235, "total_steps": 76960, "loss": 0.2368, "lr": 1.4141524071122659e-05, "epoch": 13.5745841995842, "percentage": 67.87, "elapsed_time": "1:15:52", "remaining_time": "0:35:55", "throughput": 1033.03, "total_tokens": 4703344} {"current_steps": 52240, "total_steps": 76960, "loss": 0.1112, "lr": 1.4136417462429502e-05, "epoch": 13.575883575883577, "percentage": 67.88, "elapsed_time": "1:15:53", "remaining_time": "0:35:54", "throughput": 1033.03, "total_tokens": 4703792} {"current_steps": 52245, "total_steps": 76960, "loss": 0.0794, "lr": 1.4131311412460796e-05, "epoch": 13.577182952182952, "percentage": 67.89, "elapsed_time": "1:15:53", "remaining_time": "0:35:54", "throughput": 1033.03, "total_tokens": 4704224} {"current_steps": 52250, "total_steps": 76960, "loss": 0.0691, "lr": 1.4126205921479167e-05, "epoch": 13.578482328482329, "percentage": 67.89, "elapsed_time": "1:15:54", "remaining_time": "0:35:53", "throughput": 1033.05, "total_tokens": 4704736} {"current_steps": 52255, "total_steps": 76960, "loss": 0.1111, "lr": 1.4121100989747166e-05, "epoch": 13.579781704781706, "percentage": 67.9, "elapsed_time": "1:15:54", "remaining_time": "0:35:53", "throughput": 1033.06, "total_tokens": 4705200} {"current_steps": 52260, "total_steps": 76960, "loss": 0.2667, "lr": 1.4115996617527382e-05, "epoch": 13.58108108108108, "percentage": 67.91, "elapsed_time": "1:15:55", "remaining_time": "0:35:52", "throughput": 1033.06, "total_tokens": 4705632} {"current_steps": 52265, "total_steps": 76960, "loss": 0.2878, "lr": 1.4110892805082323e-05, "epoch": 13.582380457380458, "percentage": 67.91, "elapsed_time": "1:15:55", "remaining_time": "0:35:52", "throughput": 1033.07, "total_tokens": 4706112} {"current_steps": 52270, "total_steps": 76960, "loss": 0.3143, "lr": 1.410578955267447e-05, "epoch": 13.583679833679835, "percentage": 67.92, "elapsed_time": "1:15:55", "remaining_time": "0:35:51", "throughput": 1033.07, "total_tokens": 4706560} {"current_steps": 52275, "total_steps": 76960, "loss": 0.5778, "lr": 1.4100686860566308e-05, "epoch": 13.58497920997921, "percentage": 67.92, "elapsed_time": "1:15:56", "remaining_time": "0:35:51", "throughput": 1033.08, "total_tokens": 4707024} {"current_steps": 52280, "total_steps": 76960, "loss": 0.5414, "lr": 1.4095584729020255e-05, "epoch": 13.586278586278587, "percentage": 67.93, "elapsed_time": "1:15:56", "remaining_time": "0:35:51", "throughput": 1033.08, "total_tokens": 4707440} {"current_steps": 52285, "total_steps": 76960, "loss": 0.2072, "lr": 1.4090483158298728e-05, "epoch": 13.587577962577962, "percentage": 67.94, "elapsed_time": "1:15:57", "remaining_time": "0:35:50", "throughput": 1033.09, "total_tokens": 4707904} {"current_steps": 52290, "total_steps": 76960, "loss": 0.1624, "lr": 1.4085382148664106e-05, "epoch": 13.588877338877339, "percentage": 67.94, "elapsed_time": "1:15:57", "remaining_time": "0:35:50", "throughput": 1033.09, "total_tokens": 4708336} {"current_steps": 52295, "total_steps": 76960, "loss": 0.1714, "lr": 1.4080281700378745e-05, "epoch": 13.590176715176716, "percentage": 67.95, "elapsed_time": "1:15:57", "remaining_time": "0:35:49", "throughput": 1033.09, "total_tokens": 4708784} {"current_steps": 52300, "total_steps": 76960, "loss": 0.4505, "lr": 1.4075181813704952e-05, "epoch": 13.59147609147609, "percentage": 67.96, "elapsed_time": "1:15:58", "remaining_time": "0:35:49", "throughput": 1033.09, "total_tokens": 4709216} {"current_steps": 52305, "total_steps": 76960, "loss": 0.1073, "lr": 1.4070082488905034e-05, "epoch": 13.592775467775468, "percentage": 67.96, "elapsed_time": "1:15:58", "remaining_time": "0:35:48", "throughput": 1033.1, "total_tokens": 4709696} {"current_steps": 52310, "total_steps": 76960, "loss": 0.4099, "lr": 1.4064983726241235e-05, "epoch": 13.594074844074845, "percentage": 67.97, "elapsed_time": "1:15:59", "remaining_time": "0:35:48", "throughput": 1033.13, "total_tokens": 4710224} {"current_steps": 52315, "total_steps": 76960, "loss": 0.1759, "lr": 1.4059885525975813e-05, "epoch": 13.59537422037422, "percentage": 67.98, "elapsed_time": "1:15:59", "remaining_time": "0:35:47", "throughput": 1033.13, "total_tokens": 4710688} {"current_steps": 52320, "total_steps": 76960, "loss": 0.487, "lr": 1.405478788837095e-05, "epoch": 13.596673596673597, "percentage": 67.98, "elapsed_time": "1:16:00", "remaining_time": "0:35:47", "throughput": 1033.14, "total_tokens": 4711136} {"current_steps": 52325, "total_steps": 76960, "loss": 0.3036, "lr": 1.4049690813688831e-05, "epoch": 13.597972972972974, "percentage": 67.99, "elapsed_time": "1:16:00", "remaining_time": "0:35:47", "throughput": 1033.14, "total_tokens": 4711584} {"current_steps": 52330, "total_steps": 76960, "loss": 0.3657, "lr": 1.4044594302191616e-05, "epoch": 13.599272349272349, "percentage": 68.0, "elapsed_time": "1:16:00", "remaining_time": "0:35:46", "throughput": 1033.15, "total_tokens": 4712048} {"current_steps": 52335, "total_steps": 76960, "loss": 0.209, "lr": 1.4039498354141407e-05, "epoch": 13.600571725571726, "percentage": 68.0, "elapsed_time": "1:16:01", "remaining_time": "0:35:46", "throughput": 1033.16, "total_tokens": 4712528} {"current_steps": 52340, "total_steps": 76960, "loss": 0.0766, "lr": 1.4034402969800303e-05, "epoch": 13.601871101871101, "percentage": 68.01, "elapsed_time": "1:16:01", "remaining_time": "0:35:45", "throughput": 1033.16, "total_tokens": 4712960} {"current_steps": 52345, "total_steps": 76960, "loss": 0.1336, "lr": 1.4029308149430356e-05, "epoch": 13.603170478170478, "percentage": 68.02, "elapsed_time": "1:16:02", "remaining_time": "0:35:45", "throughput": 1033.17, "total_tokens": 4713424} {"current_steps": 52350, "total_steps": 76960, "loss": 0.1547, "lr": 1.4024213893293612e-05, "epoch": 13.604469854469855, "percentage": 68.02, "elapsed_time": "1:16:02", "remaining_time": "0:35:44", "throughput": 1033.18, "total_tokens": 4713888} {"current_steps": 52355, "total_steps": 76960, "loss": 0.089, "lr": 1.4019120201652054e-05, "epoch": 13.60576923076923, "percentage": 68.03, "elapsed_time": "1:16:02", "remaining_time": "0:35:44", "throughput": 1033.19, "total_tokens": 4714368} {"current_steps": 52360, "total_steps": 76960, "loss": 0.1837, "lr": 1.4014027074767663e-05, "epoch": 13.607068607068607, "percentage": 68.04, "elapsed_time": "1:16:03", "remaining_time": "0:35:43", "throughput": 1033.2, "total_tokens": 4714864} {"current_steps": 52365, "total_steps": 76960, "loss": 0.3233, "lr": 1.4008934512902389e-05, "epoch": 13.608367983367984, "percentage": 68.04, "elapsed_time": "1:16:03", "remaining_time": "0:35:43", "throughput": 1033.21, "total_tokens": 4715328} {"current_steps": 52370, "total_steps": 76960, "loss": 0.4945, "lr": 1.400384251631815e-05, "epoch": 13.609667359667359, "percentage": 68.05, "elapsed_time": "1:16:04", "remaining_time": "0:35:43", "throughput": 1033.22, "total_tokens": 4715792} {"current_steps": 52375, "total_steps": 76960, "loss": 0.3292, "lr": 1.399875108527682e-05, "epoch": 13.610966735966736, "percentage": 68.05, "elapsed_time": "1:16:04", "remaining_time": "0:35:42", "throughput": 1033.22, "total_tokens": 4716224} {"current_steps": 52380, "total_steps": 76960, "loss": 0.3987, "lr": 1.3993660220040273e-05, "epoch": 13.612266112266113, "percentage": 68.06, "elapsed_time": "1:16:05", "remaining_time": "0:35:42", "throughput": 1033.23, "total_tokens": 4716720} {"current_steps": 52385, "total_steps": 76960, "loss": 0.2599, "lr": 1.3988569920870314e-05, "epoch": 13.613565488565488, "percentage": 68.07, "elapsed_time": "1:16:05", "remaining_time": "0:35:41", "throughput": 1033.23, "total_tokens": 4717168} {"current_steps": 52390, "total_steps": 76960, "loss": 0.2408, "lr": 1.3983480188028764e-05, "epoch": 13.614864864864865, "percentage": 68.07, "elapsed_time": "1:16:05", "remaining_time": "0:35:41", "throughput": 1033.24, "total_tokens": 4717600} {"current_steps": 52395, "total_steps": 76960, "loss": 0.4348, "lr": 1.3978391021777377e-05, "epoch": 13.616164241164242, "percentage": 68.08, "elapsed_time": "1:16:06", "remaining_time": "0:35:40", "throughput": 1033.24, "total_tokens": 4718048} {"current_steps": 52400, "total_steps": 76960, "loss": 0.1477, "lr": 1.3973302422377898e-05, "epoch": 13.617463617463617, "percentage": 68.09, "elapsed_time": "1:16:06", "remaining_time": "0:35:40", "throughput": 1033.24, "total_tokens": 4718464} {"current_steps": 52405, "total_steps": 76960, "loss": 0.1354, "lr": 1.396821439009205e-05, "epoch": 13.618762993762994, "percentage": 68.09, "elapsed_time": "1:16:07", "remaining_time": "0:35:39", "throughput": 1033.24, "total_tokens": 4718928} {"current_steps": 52410, "total_steps": 76960, "loss": 0.2567, "lr": 1.3963126925181497e-05, "epoch": 13.62006237006237, "percentage": 68.1, "elapsed_time": "1:16:07", "remaining_time": "0:35:39", "throughput": 1033.26, "total_tokens": 4719440} {"current_steps": 52415, "total_steps": 76960, "loss": 0.2374, "lr": 1.3958040027907911e-05, "epoch": 13.621361746361746, "percentage": 68.11, "elapsed_time": "1:16:07", "remaining_time": "0:35:39", "throughput": 1033.27, "total_tokens": 4719920} {"current_steps": 52420, "total_steps": 76960, "loss": 0.1415, "lr": 1.3952953698532898e-05, "epoch": 13.622661122661123, "percentage": 68.11, "elapsed_time": "1:16:08", "remaining_time": "0:35:38", "throughput": 1033.28, "total_tokens": 4720368} {"current_steps": 52425, "total_steps": 76960, "loss": 0.2254, "lr": 1.3947867937318068e-05, "epoch": 13.6239604989605, "percentage": 68.12, "elapsed_time": "1:16:08", "remaining_time": "0:35:38", "throughput": 1033.27, "total_tokens": 4720784} {"current_steps": 52430, "total_steps": 76960, "loss": 0.4285, "lr": 1.3942782744524973e-05, "epoch": 13.625259875259875, "percentage": 68.13, "elapsed_time": "1:16:09", "remaining_time": "0:35:37", "throughput": 1033.28, "total_tokens": 4721264} {"current_steps": 52435, "total_steps": 76960, "loss": 0.1315, "lr": 1.3937698120415154e-05, "epoch": 13.626559251559252, "percentage": 68.13, "elapsed_time": "1:16:09", "remaining_time": "0:35:37", "throughput": 1033.28, "total_tokens": 4721696} {"current_steps": 52440, "total_steps": 76960, "loss": 0.1476, "lr": 1.3932614065250122e-05, "epoch": 13.627858627858627, "percentage": 68.14, "elapsed_time": "1:16:10", "remaining_time": "0:35:36", "throughput": 1033.29, "total_tokens": 4722144} {"current_steps": 52445, "total_steps": 76960, "loss": 0.4416, "lr": 1.3927530579291359e-05, "epoch": 13.629158004158004, "percentage": 68.15, "elapsed_time": "1:16:10", "remaining_time": "0:35:36", "throughput": 1033.29, "total_tokens": 4722592} {"current_steps": 52450, "total_steps": 76960, "loss": 0.4025, "lr": 1.3922447662800297e-05, "epoch": 13.630457380457381, "percentage": 68.15, "elapsed_time": "1:16:10", "remaining_time": "0:35:35", "throughput": 1033.29, "total_tokens": 4723024} {"current_steps": 52455, "total_steps": 76960, "loss": 0.1329, "lr": 1.391736531603838e-05, "epoch": 13.631756756756756, "percentage": 68.16, "elapsed_time": "1:16:11", "remaining_time": "0:35:35", "throughput": 1033.3, "total_tokens": 4723504} {"current_steps": 52460, "total_steps": 76960, "loss": 0.2923, "lr": 1.3912283539266983e-05, "epoch": 13.633056133056133, "percentage": 68.17, "elapsed_time": "1:16:11", "remaining_time": "0:35:35", "throughput": 1033.31, "total_tokens": 4723984} {"current_steps": 52465, "total_steps": 76960, "loss": 0.2046, "lr": 1.3907202332747454e-05, "epoch": 13.63435550935551, "percentage": 68.17, "elapsed_time": "1:16:12", "remaining_time": "0:35:34", "throughput": 1033.32, "total_tokens": 4724448} {"current_steps": 52470, "total_steps": 76960, "loss": 0.341, "lr": 1.3902121696741141e-05, "epoch": 13.635654885654885, "percentage": 68.18, "elapsed_time": "1:16:12", "remaining_time": "0:35:34", "throughput": 1033.33, "total_tokens": 4724912} {"current_steps": 52475, "total_steps": 76960, "loss": 0.1678, "lr": 1.3897041631509342e-05, "epoch": 13.636954261954262, "percentage": 68.18, "elapsed_time": "1:16:12", "remaining_time": "0:35:33", "throughput": 1033.33, "total_tokens": 4725360} {"current_steps": 52480, "total_steps": 76960, "loss": 0.3291, "lr": 1.389196213731334e-05, "epoch": 13.638253638253639, "percentage": 68.19, "elapsed_time": "1:16:13", "remaining_time": "0:35:33", "throughput": 1033.34, "total_tokens": 4725808} {"current_steps": 52485, "total_steps": 76960, "loss": 0.3449, "lr": 1.3886883214414359e-05, "epoch": 13.639553014553014, "percentage": 68.2, "elapsed_time": "1:16:13", "remaining_time": "0:35:32", "throughput": 1033.34, "total_tokens": 4726272} {"current_steps": 52490, "total_steps": 76960, "loss": 0.1719, "lr": 1.3881804863073631e-05, "epoch": 13.640852390852391, "percentage": 68.2, "elapsed_time": "1:16:14", "remaining_time": "0:35:32", "throughput": 1033.35, "total_tokens": 4726736} {"current_steps": 52495, "total_steps": 76960, "loss": 0.0353, "lr": 1.387672708355232e-05, "epoch": 13.642151767151766, "percentage": 68.21, "elapsed_time": "1:16:14", "remaining_time": "0:35:31", "throughput": 1033.36, "total_tokens": 4727216} {"current_steps": 52500, "total_steps": 76960, "loss": 0.117, "lr": 1.3871649876111609e-05, "epoch": 13.643451143451143, "percentage": 68.22, "elapsed_time": "1:16:15", "remaining_time": "0:35:31", "throughput": 1033.37, "total_tokens": 4727680} {"current_steps": 52505, "total_steps": 76960, "loss": 0.1662, "lr": 1.3866573241012581e-05, "epoch": 13.64475051975052, "percentage": 68.22, "elapsed_time": "1:16:15", "remaining_time": "0:35:31", "throughput": 1033.37, "total_tokens": 4728128} {"current_steps": 52510, "total_steps": 76960, "loss": 0.2545, "lr": 1.386149717851638e-05, "epoch": 13.646049896049895, "percentage": 68.23, "elapsed_time": "1:16:15", "remaining_time": "0:35:30", "throughput": 1033.38, "total_tokens": 4728576} {"current_steps": 52515, "total_steps": 76960, "loss": 0.0936, "lr": 1.3856421688884047e-05, "epoch": 13.647349272349272, "percentage": 68.24, "elapsed_time": "1:16:16", "remaining_time": "0:35:30", "throughput": 1033.38, "total_tokens": 4729040} {"current_steps": 52520, "total_steps": 76960, "loss": 0.3405, "lr": 1.3851346772376627e-05, "epoch": 13.64864864864865, "percentage": 68.24, "elapsed_time": "1:16:16", "remaining_time": "0:35:29", "throughput": 1033.39, "total_tokens": 4729520} {"current_steps": 52525, "total_steps": 76960, "loss": 0.1305, "lr": 1.384627242925513e-05, "epoch": 13.649948024948024, "percentage": 68.25, "elapsed_time": "1:16:17", "remaining_time": "0:35:29", "throughput": 1033.4, "total_tokens": 4729984} {"current_steps": 52530, "total_steps": 76960, "loss": 0.558, "lr": 1.3841198659780514e-05, "epoch": 13.651247401247401, "percentage": 68.26, "elapsed_time": "1:16:17", "remaining_time": "0:35:28", "throughput": 1033.41, "total_tokens": 4730432} {"current_steps": 52535, "total_steps": 76960, "loss": 0.1444, "lr": 1.3836125464213745e-05, "epoch": 13.652546777546778, "percentage": 68.26, "elapsed_time": "1:16:17", "remaining_time": "0:35:28", "throughput": 1033.4, "total_tokens": 4730848} {"current_steps": 52540, "total_steps": 76960, "loss": 0.2088, "lr": 1.3831052842815742e-05, "epoch": 13.653846153846153, "percentage": 68.27, "elapsed_time": "1:16:18", "remaining_time": "0:35:27", "throughput": 1033.4, "total_tokens": 4731264} {"current_steps": 52545, "total_steps": 76960, "loss": 0.2269, "lr": 1.3825980795847402e-05, "epoch": 13.65514553014553, "percentage": 68.28, "elapsed_time": "1:16:18", "remaining_time": "0:35:27", "throughput": 1033.41, "total_tokens": 4731744} {"current_steps": 52550, "total_steps": 76960, "loss": 0.2981, "lr": 1.3820909323569564e-05, "epoch": 13.656444906444907, "percentage": 68.28, "elapsed_time": "1:16:19", "remaining_time": "0:35:27", "throughput": 1033.41, "total_tokens": 4732192} {"current_steps": 52555, "total_steps": 76960, "loss": 0.0802, "lr": 1.3815838426243083e-05, "epoch": 13.657744282744282, "percentage": 68.29, "elapsed_time": "1:16:19", "remaining_time": "0:35:26", "throughput": 1033.42, "total_tokens": 4732640} {"current_steps": 52560, "total_steps": 76960, "loss": 0.3483, "lr": 1.3810768104128736e-05, "epoch": 13.65904365904366, "percentage": 68.3, "elapsed_time": "1:16:20", "remaining_time": "0:35:26", "throughput": 1033.42, "total_tokens": 4733072} {"current_steps": 52565, "total_steps": 76960, "loss": 0.3613, "lr": 1.3805698357487318e-05, "epoch": 13.660343035343036, "percentage": 68.3, "elapsed_time": "1:16:20", "remaining_time": "0:35:25", "throughput": 1033.42, "total_tokens": 4733504} {"current_steps": 52570, "total_steps": 76960, "loss": 0.065, "lr": 1.380062918657955e-05, "epoch": 13.661642411642411, "percentage": 68.31, "elapsed_time": "1:16:20", "remaining_time": "0:35:25", "throughput": 1033.43, "total_tokens": 4734000} {"current_steps": 52575, "total_steps": 76960, "loss": 0.0866, "lr": 1.3795560591666152e-05, "epoch": 13.662941787941788, "percentage": 68.31, "elapsed_time": "1:16:21", "remaining_time": "0:35:24", "throughput": 1033.44, "total_tokens": 4734464} {"current_steps": 52580, "total_steps": 76960, "loss": 0.0697, "lr": 1.3790492573007807e-05, "epoch": 13.664241164241163, "percentage": 68.32, "elapsed_time": "1:16:21", "remaining_time": "0:35:24", "throughput": 1033.45, "total_tokens": 4734928} {"current_steps": 52585, "total_steps": 76960, "loss": 0.0716, "lr": 1.3785425130865181e-05, "epoch": 13.66554054054054, "percentage": 68.33, "elapsed_time": "1:16:22", "remaining_time": "0:35:23", "throughput": 1033.45, "total_tokens": 4735360} {"current_steps": 52590, "total_steps": 76960, "loss": 0.2885, "lr": 1.3780358265498889e-05, "epoch": 13.666839916839917, "percentage": 68.33, "elapsed_time": "1:16:22", "remaining_time": "0:35:23", "throughput": 1033.46, "total_tokens": 4735824} {"current_steps": 52595, "total_steps": 76960, "loss": 0.2912, "lr": 1.3775291977169507e-05, "epoch": 13.668139293139292, "percentage": 68.34, "elapsed_time": "1:16:22", "remaining_time": "0:35:23", "throughput": 1033.46, "total_tokens": 4736272} {"current_steps": 52600, "total_steps": 76960, "loss": 0.0633, "lr": 1.3770226266137625e-05, "epoch": 13.66943866943867, "percentage": 68.35, "elapsed_time": "1:16:23", "remaining_time": "0:35:22", "throughput": 1033.47, "total_tokens": 4736736} {"current_steps": 52605, "total_steps": 76960, "loss": 0.0358, "lr": 1.3765161132663757e-05, "epoch": 13.670738045738046, "percentage": 68.35, "elapsed_time": "1:16:23", "remaining_time": "0:35:22", "throughput": 1033.47, "total_tokens": 4737152} {"current_steps": 52610, "total_steps": 76960, "loss": 0.3144, "lr": 1.3760096577008413e-05, "epoch": 13.672037422037421, "percentage": 68.36, "elapsed_time": "1:16:24", "remaining_time": "0:35:21", "throughput": 1033.48, "total_tokens": 4737632} {"current_steps": 52615, "total_steps": 76960, "loss": 0.1472, "lr": 1.3755032599432075e-05, "epoch": 13.673336798336798, "percentage": 68.37, "elapsed_time": "1:16:24", "remaining_time": "0:35:21", "throughput": 1033.49, "total_tokens": 4738112} {"current_steps": 52620, "total_steps": 76960, "loss": 0.3118, "lr": 1.3749969200195196e-05, "epoch": 13.674636174636175, "percentage": 68.37, "elapsed_time": "1:16:25", "remaining_time": "0:35:20", "throughput": 1033.49, "total_tokens": 4738560} {"current_steps": 52625, "total_steps": 76960, "loss": 0.1504, "lr": 1.3744906379558165e-05, "epoch": 13.67593555093555, "percentage": 68.38, "elapsed_time": "1:16:25", "remaining_time": "0:35:20", "throughput": 1033.5, "total_tokens": 4739040} {"current_steps": 52630, "total_steps": 76960, "loss": 0.0678, "lr": 1.3739844137781399e-05, "epoch": 13.677234927234927, "percentage": 68.39, "elapsed_time": "1:16:25", "remaining_time": "0:35:19", "throughput": 1033.51, "total_tokens": 4739520} {"current_steps": 52635, "total_steps": 76960, "loss": 0.2065, "lr": 1.3734782475125224e-05, "epoch": 13.678534303534304, "percentage": 68.39, "elapsed_time": "1:16:26", "remaining_time": "0:35:19", "throughput": 1033.51, "total_tokens": 4739952} {"current_steps": 52640, "total_steps": 76960, "loss": 0.1602, "lr": 1.3729721391849992e-05, "epoch": 13.67983367983368, "percentage": 68.4, "elapsed_time": "1:16:26", "remaining_time": "0:35:19", "throughput": 1033.52, "total_tokens": 4740416} {"current_steps": 52645, "total_steps": 76960, "loss": 0.0759, "lr": 1.3724660888215975e-05, "epoch": 13.681133056133056, "percentage": 68.41, "elapsed_time": "1:16:27", "remaining_time": "0:35:18", "throughput": 1033.53, "total_tokens": 4740864} {"current_steps": 52650, "total_steps": 76960, "loss": 0.1655, "lr": 1.3719600964483455e-05, "epoch": 13.682432432432432, "percentage": 68.41, "elapsed_time": "1:16:27", "remaining_time": "0:35:18", "throughput": 1033.53, "total_tokens": 4741328} {"current_steps": 52655, "total_steps": 76960, "loss": 0.6833, "lr": 1.3714541620912675e-05, "epoch": 13.683731808731808, "percentage": 68.42, "elapsed_time": "1:16:27", "remaining_time": "0:35:17", "throughput": 1033.54, "total_tokens": 4741776} {"current_steps": 52660, "total_steps": 76960, "loss": 0.1342, "lr": 1.3709482857763822e-05, "epoch": 13.685031185031185, "percentage": 68.43, "elapsed_time": "1:16:28", "remaining_time": "0:35:17", "throughput": 1033.54, "total_tokens": 4742208} {"current_steps": 52665, "total_steps": 76960, "loss": 0.316, "lr": 1.3704424675297095e-05, "epoch": 13.68633056133056, "percentage": 68.43, "elapsed_time": "1:16:28", "remaining_time": "0:35:16", "throughput": 1033.54, "total_tokens": 4742640} {"current_steps": 52670, "total_steps": 76960, "loss": 0.0692, "lr": 1.3699367073772617e-05, "epoch": 13.687629937629938, "percentage": 68.44, "elapsed_time": "1:16:29", "remaining_time": "0:35:16", "throughput": 1033.55, "total_tokens": 4743136} {"current_steps": 52675, "total_steps": 76960, "loss": 0.2243, "lr": 1.3694310053450531e-05, "epoch": 13.688929313929314, "percentage": 68.44, "elapsed_time": "1:16:29", "remaining_time": "0:35:15", "throughput": 1033.56, "total_tokens": 4743600} {"current_steps": 52680, "total_steps": 76960, "loss": 0.127, "lr": 1.3689253614590902e-05, "epoch": 13.69022869022869, "percentage": 68.45, "elapsed_time": "1:16:29", "remaining_time": "0:35:15", "throughput": 1033.56, "total_tokens": 4744048} {"current_steps": 52685, "total_steps": 76960, "loss": 0.0868, "lr": 1.3684197757453796e-05, "epoch": 13.691528066528067, "percentage": 68.46, "elapsed_time": "1:16:30", "remaining_time": "0:35:15", "throughput": 1033.57, "total_tokens": 4744496} {"current_steps": 52690, "total_steps": 76960, "loss": 0.3478, "lr": 1.367914248229924e-05, "epoch": 13.692827442827443, "percentage": 68.46, "elapsed_time": "1:16:30", "remaining_time": "0:35:14", "throughput": 1033.58, "total_tokens": 4744960} {"current_steps": 52695, "total_steps": 76960, "loss": 0.0175, "lr": 1.3674087789387247e-05, "epoch": 13.694126819126819, "percentage": 68.47, "elapsed_time": "1:16:31", "remaining_time": "0:35:14", "throughput": 1033.59, "total_tokens": 4745440} {"current_steps": 52700, "total_steps": 76960, "loss": 0.3063, "lr": 1.3669033678977756e-05, "epoch": 13.695426195426196, "percentage": 68.48, "elapsed_time": "1:16:31", "remaining_time": "0:35:13", "throughput": 1033.6, "total_tokens": 4745920} {"current_steps": 52705, "total_steps": 76960, "loss": 0.1307, "lr": 1.3663980151330732e-05, "epoch": 13.696725571725572, "percentage": 68.48, "elapsed_time": "1:16:32", "remaining_time": "0:35:13", "throughput": 1033.6, "total_tokens": 4746352} {"current_steps": 52710, "total_steps": 76960, "loss": 0.2233, "lr": 1.3658927206706063e-05, "epoch": 13.698024948024948, "percentage": 68.49, "elapsed_time": "1:16:32", "remaining_time": "0:35:12", "throughput": 1033.6, "total_tokens": 4746816} {"current_steps": 52715, "total_steps": 76960, "loss": 0.4055, "lr": 1.365387484536364e-05, "epoch": 13.699324324324325, "percentage": 68.5, "elapsed_time": "1:16:32", "remaining_time": "0:35:12", "throughput": 1033.6, "total_tokens": 4747232} {"current_steps": 52720, "total_steps": 76960, "loss": 0.2956, "lr": 1.3648823067563297e-05, "epoch": 13.700623700623701, "percentage": 68.5, "elapsed_time": "1:16:33", "remaining_time": "0:35:11", "throughput": 1033.61, "total_tokens": 4747680} {"current_steps": 52725, "total_steps": 76960, "loss": 0.5475, "lr": 1.3643771873564859e-05, "epoch": 13.701923076923077, "percentage": 68.51, "elapsed_time": "1:16:33", "remaining_time": "0:35:11", "throughput": 1033.62, "total_tokens": 4748160} {"current_steps": 52730, "total_steps": 76960, "loss": 0.5592, "lr": 1.3638721263628123e-05, "epoch": 13.703222453222454, "percentage": 68.52, "elapsed_time": "1:16:34", "remaining_time": "0:35:11", "throughput": 1033.62, "total_tokens": 4748624} {"current_steps": 52735, "total_steps": 76960, "loss": 0.399, "lr": 1.3633671238012835e-05, "epoch": 13.704521829521829, "percentage": 68.52, "elapsed_time": "1:16:34", "remaining_time": "0:35:10", "throughput": 1033.63, "total_tokens": 4749072} {"current_steps": 52740, "total_steps": 76960, "loss": 0.4388, "lr": 1.362862179697873e-05, "epoch": 13.705821205821206, "percentage": 68.53, "elapsed_time": "1:16:34", "remaining_time": "0:35:10", "throughput": 1033.64, "total_tokens": 4749552} {"current_steps": 52745, "total_steps": 76960, "loss": 0.1655, "lr": 1.3623572940785493e-05, "epoch": 13.707120582120583, "percentage": 68.54, "elapsed_time": "1:16:35", "remaining_time": "0:35:09", "throughput": 1033.64, "total_tokens": 4749968} {"current_steps": 52750, "total_steps": 76960, "loss": 0.1066, "lr": 1.3618524669692811e-05, "epoch": 13.708419958419958, "percentage": 68.54, "elapsed_time": "1:16:35", "remaining_time": "0:35:09", "throughput": 1033.65, "total_tokens": 4750464} {"current_steps": 52755, "total_steps": 76960, "loss": 0.0838, "lr": 1.3613476983960287e-05, "epoch": 13.709719334719335, "percentage": 68.55, "elapsed_time": "1:16:36", "remaining_time": "0:35:08", "throughput": 1033.65, "total_tokens": 4750912} {"current_steps": 52760, "total_steps": 76960, "loss": 0.3492, "lr": 1.3608429883847573e-05, "epoch": 13.711018711018712, "percentage": 68.56, "elapsed_time": "1:16:36", "remaining_time": "0:35:08", "throughput": 1033.65, "total_tokens": 4751344} {"current_steps": 52765, "total_steps": 76960, "loss": 0.3782, "lr": 1.360338336961422e-05, "epoch": 13.712318087318087, "percentage": 68.56, "elapsed_time": "1:16:37", "remaining_time": "0:35:07", "throughput": 1033.66, "total_tokens": 4751776} {"current_steps": 52770, "total_steps": 76960, "loss": 0.2872, "lr": 1.3598337441519784e-05, "epoch": 13.713617463617464, "percentage": 68.57, "elapsed_time": "1:16:37", "remaining_time": "0:35:07", "throughput": 1033.66, "total_tokens": 4752224} {"current_steps": 52775, "total_steps": 76960, "loss": 0.3021, "lr": 1.359329209982377e-05, "epoch": 13.71491683991684, "percentage": 68.57, "elapsed_time": "1:16:37", "remaining_time": "0:35:07", "throughput": 1033.66, "total_tokens": 4752672} {"current_steps": 52780, "total_steps": 76960, "loss": 0.6732, "lr": 1.3588247344785681e-05, "epoch": 13.716216216216216, "percentage": 68.58, "elapsed_time": "1:16:38", "remaining_time": "0:35:06", "throughput": 1033.67, "total_tokens": 4753120} {"current_steps": 52785, "total_steps": 76960, "loss": 0.0995, "lr": 1.3583203176664961e-05, "epoch": 13.717515592515593, "percentage": 68.59, "elapsed_time": "1:16:38", "remaining_time": "0:35:06", "throughput": 1033.67, "total_tokens": 4753568} {"current_steps": 52790, "total_steps": 76960, "loss": 0.038, "lr": 1.3578159595721034e-05, "epoch": 13.71881496881497, "percentage": 68.59, "elapsed_time": "1:16:39", "remaining_time": "0:35:05", "throughput": 1033.67, "total_tokens": 4754016} {"current_steps": 52795, "total_steps": 76960, "loss": 0.5797, "lr": 1.3573116602213315e-05, "epoch": 13.720114345114345, "percentage": 68.6, "elapsed_time": "1:16:39", "remaining_time": "0:35:05", "throughput": 1033.69, "total_tokens": 4754512} {"current_steps": 52800, "total_steps": 76960, "loss": 0.2954, "lr": 1.3568074196401149e-05, "epoch": 13.721413721413722, "percentage": 68.61, "elapsed_time": "1:16:39", "remaining_time": "0:35:04", "throughput": 1033.69, "total_tokens": 4754944} {"current_steps": 52805, "total_steps": 76960, "loss": 0.1001, "lr": 1.356303237854389e-05, "epoch": 13.722713097713097, "percentage": 68.61, "elapsed_time": "1:16:40", "remaining_time": "0:35:04", "throughput": 1033.69, "total_tokens": 4755392} {"current_steps": 52810, "total_steps": 76960, "loss": 0.1912, "lr": 1.3557991148900825e-05, "epoch": 13.724012474012474, "percentage": 68.62, "elapsed_time": "1:16:40", "remaining_time": "0:35:03", "throughput": 1033.7, "total_tokens": 4755840} {"current_steps": 52815, "total_steps": 76960, "loss": 0.5899, "lr": 1.355295050773125e-05, "epoch": 13.72531185031185, "percentage": 68.63, "elapsed_time": "1:16:41", "remaining_time": "0:35:03", "throughput": 1033.69, "total_tokens": 4756256} {"current_steps": 52820, "total_steps": 76960, "loss": 0.1593, "lr": 1.3547910455294382e-05, "epoch": 13.726611226611226, "percentage": 68.63, "elapsed_time": "1:16:41", "remaining_time": "0:35:03", "throughput": 1033.7, "total_tokens": 4756704} {"current_steps": 52825, "total_steps": 76960, "loss": 0.0418, "lr": 1.354287099184946e-05, "epoch": 13.727910602910603, "percentage": 68.64, "elapsed_time": "1:16:42", "remaining_time": "0:35:02", "throughput": 1033.71, "total_tokens": 4757200} {"current_steps": 52830, "total_steps": 76960, "loss": 0.0818, "lr": 1.3537832117655655e-05, "epoch": 13.72920997920998, "percentage": 68.65, "elapsed_time": "1:16:42", "remaining_time": "0:35:02", "throughput": 1033.72, "total_tokens": 4757664} {"current_steps": 52835, "total_steps": 76960, "loss": 0.227, "lr": 1.3532793832972137e-05, "epoch": 13.730509355509355, "percentage": 68.65, "elapsed_time": "1:16:42", "remaining_time": "0:35:01", "throughput": 1033.73, "total_tokens": 4758128} {"current_steps": 52840, "total_steps": 76960, "loss": 0.2482, "lr": 1.3527756138058013e-05, "epoch": 13.731808731808732, "percentage": 68.66, "elapsed_time": "1:16:43", "remaining_time": "0:35:01", "throughput": 1033.73, "total_tokens": 4758560} {"current_steps": 52845, "total_steps": 76960, "loss": 0.0531, "lr": 1.352271903317239e-05, "epoch": 13.733108108108109, "percentage": 68.67, "elapsed_time": "1:16:43", "remaining_time": "0:35:00", "throughput": 1033.73, "total_tokens": 4759008} {"current_steps": 52850, "total_steps": 76960, "loss": 0.4497, "lr": 1.3517682518574326e-05, "epoch": 13.734407484407484, "percentage": 68.67, "elapsed_time": "1:16:44", "remaining_time": "0:35:00", "throughput": 1033.73, "total_tokens": 4759440} {"current_steps": 52855, "total_steps": 76960, "loss": 0.7613, "lr": 1.351264659452284e-05, "epoch": 13.73570686070686, "percentage": 68.68, "elapsed_time": "1:16:44", "remaining_time": "0:34:59", "throughput": 1033.73, "total_tokens": 4759872} {"current_steps": 52860, "total_steps": 76960, "loss": 0.0116, "lr": 1.3507611261276948e-05, "epoch": 13.737006237006238, "percentage": 68.69, "elapsed_time": "1:16:44", "remaining_time": "0:34:59", "throughput": 1033.73, "total_tokens": 4760304} {"current_steps": 52865, "total_steps": 76960, "loss": 0.1403, "lr": 1.350257651909562e-05, "epoch": 13.738305613305613, "percentage": 68.69, "elapsed_time": "1:16:45", "remaining_time": "0:34:59", "throughput": 1033.74, "total_tokens": 4760752} {"current_steps": 52870, "total_steps": 76960, "loss": 0.1918, "lr": 1.3497542368237808e-05, "epoch": 13.73960498960499, "percentage": 68.7, "elapsed_time": "1:16:45", "remaining_time": "0:34:58", "throughput": 1033.74, "total_tokens": 4761184} {"current_steps": 52875, "total_steps": 76960, "loss": 0.1914, "lr": 1.3492508808962401e-05, "epoch": 13.740904365904367, "percentage": 68.7, "elapsed_time": "1:16:46", "remaining_time": "0:34:58", "throughput": 1033.74, "total_tokens": 4761632} {"current_steps": 52880, "total_steps": 76960, "loss": 0.2162, "lr": 1.3487475841528301e-05, "epoch": 13.742203742203742, "percentage": 68.71, "elapsed_time": "1:16:46", "remaining_time": "0:34:57", "throughput": 1033.74, "total_tokens": 4762048} {"current_steps": 52885, "total_steps": 76960, "loss": 0.1636, "lr": 1.3482443466194345e-05, "epoch": 13.743503118503119, "percentage": 68.72, "elapsed_time": "1:16:47", "remaining_time": "0:34:57", "throughput": 1033.74, "total_tokens": 4762480} {"current_steps": 52890, "total_steps": 76960, "loss": 0.6725, "lr": 1.3477411683219365e-05, "epoch": 13.744802494802494, "percentage": 68.72, "elapsed_time": "1:16:47", "remaining_time": "0:34:56", "throughput": 1033.73, "total_tokens": 4762896} {"current_steps": 52895, "total_steps": 76960, "loss": 0.0698, "lr": 1.347238049286213e-05, "epoch": 13.746101871101871, "percentage": 68.73, "elapsed_time": "1:16:47", "remaining_time": "0:34:56", "throughput": 1033.74, "total_tokens": 4763360} {"current_steps": 52900, "total_steps": 76960, "loss": 0.0784, "lr": 1.3467349895381415e-05, "epoch": 13.747401247401248, "percentage": 68.74, "elapsed_time": "1:16:48", "remaining_time": "0:34:55", "throughput": 1033.75, "total_tokens": 4763808} {"current_steps": 52905, "total_steps": 76960, "loss": 0.1639, "lr": 1.346231989103594e-05, "epoch": 13.748700623700623, "percentage": 68.74, "elapsed_time": "1:16:48", "remaining_time": "0:34:55", "throughput": 1033.75, "total_tokens": 4764272} {"current_steps": 52910, "total_steps": 76960, "loss": 0.1933, "lr": 1.3457290480084422e-05, "epoch": 13.75, "percentage": 68.75, "elapsed_time": "1:16:49", "remaining_time": "0:34:55", "throughput": 1033.75, "total_tokens": 4764672} {"current_steps": 52915, "total_steps": 76960, "loss": 0.3303, "lr": 1.3452261662785515e-05, "epoch": 13.751299376299377, "percentage": 68.76, "elapsed_time": "1:16:49", "remaining_time": "0:34:54", "throughput": 1033.75, "total_tokens": 4765120} {"current_steps": 52920, "total_steps": 76960, "loss": 0.1245, "lr": 1.344723343939784e-05, "epoch": 13.752598752598752, "percentage": 68.76, "elapsed_time": "1:16:49", "remaining_time": "0:34:54", "throughput": 1033.77, "total_tokens": 4765648} {"current_steps": 52925, "total_steps": 76960, "loss": 0.4923, "lr": 1.3442205810180031e-05, "epoch": 13.753898128898129, "percentage": 68.77, "elapsed_time": "1:16:50", "remaining_time": "0:34:53", "throughput": 1033.77, "total_tokens": 4766064} {"current_steps": 52930, "total_steps": 76960, "loss": 0.2452, "lr": 1.3437178775390644e-05, "epoch": 13.755197505197506, "percentage": 68.78, "elapsed_time": "1:16:50", "remaining_time": "0:34:53", "throughput": 1033.77, "total_tokens": 4766512} {"current_steps": 52935, "total_steps": 76960, "loss": 0.0419, "lr": 1.3432152335288228e-05, "epoch": 13.756496881496881, "percentage": 68.78, "elapsed_time": "1:16:51", "remaining_time": "0:34:52", "throughput": 1033.77, "total_tokens": 4766944} {"current_steps": 52940, "total_steps": 76960, "loss": 0.4242, "lr": 1.3427126490131304e-05, "epoch": 13.757796257796258, "percentage": 68.79, "elapsed_time": "1:16:51", "remaining_time": "0:34:52", "throughput": 1033.77, "total_tokens": 4767376} {"current_steps": 52945, "total_steps": 76960, "loss": 0.4456, "lr": 1.3422101240178365e-05, "epoch": 13.759095634095633, "percentage": 68.8, "elapsed_time": "1:16:52", "remaining_time": "0:34:51", "throughput": 1033.77, "total_tokens": 4767792} {"current_steps": 52950, "total_steps": 76960, "loss": 0.3953, "lr": 1.3417076585687838e-05, "epoch": 13.76039501039501, "percentage": 68.8, "elapsed_time": "1:16:52", "remaining_time": "0:34:51", "throughput": 1033.77, "total_tokens": 4768240} {"current_steps": 52955, "total_steps": 76960, "loss": 0.4187, "lr": 1.3412052526918173e-05, "epoch": 13.761694386694387, "percentage": 68.81, "elapsed_time": "1:16:52", "remaining_time": "0:34:51", "throughput": 1033.78, "total_tokens": 4768704} {"current_steps": 52960, "total_steps": 76960, "loss": 0.4239, "lr": 1.3407029064127734e-05, "epoch": 13.762993762993762, "percentage": 68.81, "elapsed_time": "1:16:53", "remaining_time": "0:34:50", "throughput": 1033.78, "total_tokens": 4769152} {"current_steps": 52965, "total_steps": 76960, "loss": 0.2471, "lr": 1.3402006197574915e-05, "epoch": 13.76429313929314, "percentage": 68.82, "elapsed_time": "1:16:53", "remaining_time": "0:34:50", "throughput": 1033.79, "total_tokens": 4769616} {"current_steps": 52970, "total_steps": 76960, "loss": 0.1871, "lr": 1.339698392751802e-05, "epoch": 13.765592515592516, "percentage": 68.83, "elapsed_time": "1:16:54", "remaining_time": "0:34:49", "throughput": 1033.8, "total_tokens": 4770096} {"current_steps": 52975, "total_steps": 76960, "loss": 0.1812, "lr": 1.3391962254215356e-05, "epoch": 13.766891891891891, "percentage": 68.83, "elapsed_time": "1:16:54", "remaining_time": "0:34:49", "throughput": 1033.81, "total_tokens": 4770576} {"current_steps": 52980, "total_steps": 76960, "loss": 0.1864, "lr": 1.3386941177925206e-05, "epoch": 13.768191268191268, "percentage": 68.84, "elapsed_time": "1:16:54", "remaining_time": "0:34:48", "throughput": 1033.81, "total_tokens": 4771008} {"current_steps": 52985, "total_steps": 76960, "loss": 0.2268, "lr": 1.3381920698905787e-05, "epoch": 13.769490644490645, "percentage": 68.85, "elapsed_time": "1:16:55", "remaining_time": "0:34:48", "throughput": 1033.81, "total_tokens": 4771408} {"current_steps": 52990, "total_steps": 76960, "loss": 0.054, "lr": 1.337690081741533e-05, "epoch": 13.77079002079002, "percentage": 68.85, "elapsed_time": "1:16:55", "remaining_time": "0:34:47", "throughput": 1033.81, "total_tokens": 4771872} {"current_steps": 52995, "total_steps": 76960, "loss": 0.2657, "lr": 1.3371881533711992e-05, "epoch": 13.772089397089397, "percentage": 68.86, "elapsed_time": "1:16:56", "remaining_time": "0:34:47", "throughput": 1033.82, "total_tokens": 4772336} {"current_steps": 53000, "total_steps": 76960, "loss": 0.2351, "lr": 1.3366862848053935e-05, "epoch": 13.773388773388774, "percentage": 68.87, "elapsed_time": "1:16:56", "remaining_time": "0:34:47", "throughput": 1033.83, "total_tokens": 4772784} {"current_steps": 53005, "total_steps": 76960, "loss": 0.3764, "lr": 1.3361844760699251e-05, "epoch": 13.77468814968815, "percentage": 68.87, "elapsed_time": "1:16:57", "remaining_time": "0:34:46", "throughput": 1033.83, "total_tokens": 4773232} {"current_steps": 53010, "total_steps": 76960, "loss": 0.2117, "lr": 1.3356827271906061e-05, "epoch": 13.775987525987526, "percentage": 68.88, "elapsed_time": "1:16:57", "remaining_time": "0:34:46", "throughput": 1033.83, "total_tokens": 4773680} {"current_steps": 53015, "total_steps": 76960, "loss": 0.0882, "lr": 1.335181038193239e-05, "epoch": 13.777286902286903, "percentage": 68.89, "elapsed_time": "1:16:57", "remaining_time": "0:34:45", "throughput": 1033.84, "total_tokens": 4774144} {"current_steps": 53020, "total_steps": 76960, "loss": 0.2034, "lr": 1.3346794091036283e-05, "epoch": 13.778586278586278, "percentage": 68.89, "elapsed_time": "1:16:58", "remaining_time": "0:34:45", "throughput": 1033.85, "total_tokens": 4774608} {"current_steps": 53025, "total_steps": 76960, "loss": 0.0998, "lr": 1.3341778399475713e-05, "epoch": 13.779885654885655, "percentage": 68.9, "elapsed_time": "1:16:58", "remaining_time": "0:34:44", "throughput": 1033.85, "total_tokens": 4775056} {"current_steps": 53030, "total_steps": 76960, "loss": 0.2692, "lr": 1.3336763307508653e-05, "epoch": 13.78118503118503, "percentage": 68.91, "elapsed_time": "1:16:59", "remaining_time": "0:34:44", "throughput": 1033.85, "total_tokens": 4775488} {"current_steps": 53035, "total_steps": 76960, "loss": 0.1502, "lr": 1.333174881539303e-05, "epoch": 13.782484407484407, "percentage": 68.91, "elapsed_time": "1:16:59", "remaining_time": "0:34:43", "throughput": 1033.85, "total_tokens": 4775904} {"current_steps": 53040, "total_steps": 76960, "loss": 0.3718, "lr": 1.332673492338674e-05, "epoch": 13.783783783783784, "percentage": 68.92, "elapsed_time": "1:16:59", "remaining_time": "0:34:43", "throughput": 1033.85, "total_tokens": 4776336} {"current_steps": 53045, "total_steps": 76960, "loss": 0.2189, "lr": 1.332172163174767e-05, "epoch": 13.78508316008316, "percentage": 68.93, "elapsed_time": "1:17:00", "remaining_time": "0:34:43", "throughput": 1033.85, "total_tokens": 4776768} {"current_steps": 53050, "total_steps": 76960, "loss": 0.1136, "lr": 1.3316708940733635e-05, "epoch": 13.786382536382536, "percentage": 68.93, "elapsed_time": "1:17:00", "remaining_time": "0:34:42", "throughput": 1033.85, "total_tokens": 4777200} {"current_steps": 53055, "total_steps": 76960, "loss": 0.1923, "lr": 1.3311696850602465e-05, "epoch": 13.787681912681913, "percentage": 68.94, "elapsed_time": "1:17:01", "remaining_time": "0:34:42", "throughput": 1033.86, "total_tokens": 4777664} {"current_steps": 53060, "total_steps": 76960, "loss": 0.1385, "lr": 1.3306685361611914e-05, "epoch": 13.788981288981288, "percentage": 68.94, "elapsed_time": "1:17:01", "remaining_time": "0:34:41", "throughput": 1033.85, "total_tokens": 4778080} {"current_steps": 53065, "total_steps": 76960, "loss": 0.3431, "lr": 1.3301674474019748e-05, "epoch": 13.790280665280665, "percentage": 68.95, "elapsed_time": "1:17:02", "remaining_time": "0:34:41", "throughput": 1033.86, "total_tokens": 4778528} {"current_steps": 53070, "total_steps": 76960, "loss": 0.318, "lr": 1.3296664188083663e-05, "epoch": 13.791580041580042, "percentage": 68.96, "elapsed_time": "1:17:02", "remaining_time": "0:34:40", "throughput": 1033.86, "total_tokens": 4778960} {"current_steps": 53075, "total_steps": 76960, "loss": 0.0813, "lr": 1.3291654504061354e-05, "epoch": 13.792879417879417, "percentage": 68.96, "elapsed_time": "1:17:02", "remaining_time": "0:34:40", "throughput": 1033.86, "total_tokens": 4779392} {"current_steps": 53080, "total_steps": 76960, "loss": 0.2626, "lr": 1.328664542221047e-05, "epoch": 13.794178794178794, "percentage": 68.97, "elapsed_time": "1:17:03", "remaining_time": "0:34:39", "throughput": 1033.86, "total_tokens": 4779824} {"current_steps": 53085, "total_steps": 76960, "loss": 0.2085, "lr": 1.3281636942788647e-05, "epoch": 13.795478170478171, "percentage": 68.98, "elapsed_time": "1:17:03", "remaining_time": "0:34:39", "throughput": 1033.87, "total_tokens": 4780288} {"current_steps": 53090, "total_steps": 76960, "loss": 0.1205, "lr": 1.3276629066053454e-05, "epoch": 13.796777546777546, "percentage": 68.98, "elapsed_time": "1:17:04", "remaining_time": "0:34:39", "throughput": 1033.87, "total_tokens": 4780736} {"current_steps": 53095, "total_steps": 76960, "loss": 0.2069, "lr": 1.327162179226247e-05, "epoch": 13.798076923076923, "percentage": 68.99, "elapsed_time": "1:17:04", "remaining_time": "0:34:38", "throughput": 1033.88, "total_tokens": 4781216} {"current_steps": 53100, "total_steps": 76960, "loss": 0.5716, "lr": 1.3266615121673203e-05, "epoch": 13.799376299376299, "percentage": 69.0, "elapsed_time": "1:17:04", "remaining_time": "0:34:38", "throughput": 1033.89, "total_tokens": 4781680} {"current_steps": 53105, "total_steps": 76960, "loss": 0.0288, "lr": 1.3261609054543179e-05, "epoch": 13.800675675675675, "percentage": 69.0, "elapsed_time": "1:17:05", "remaining_time": "0:34:37", "throughput": 1033.89, "total_tokens": 4782128} {"current_steps": 53110, "total_steps": 76960, "loss": 0.1943, "lr": 1.3256603591129833e-05, "epoch": 13.801975051975052, "percentage": 69.01, "elapsed_time": "1:17:05", "remaining_time": "0:34:37", "throughput": 1033.9, "total_tokens": 4782592} {"current_steps": 53115, "total_steps": 76960, "loss": 0.3645, "lr": 1.3251598731690617e-05, "epoch": 13.803274428274428, "percentage": 69.02, "elapsed_time": "1:17:06", "remaining_time": "0:34:36", "throughput": 1033.9, "total_tokens": 4783024} {"current_steps": 53120, "total_steps": 76960, "loss": 0.097, "lr": 1.3246594476482946e-05, "epoch": 13.804573804573804, "percentage": 69.02, "elapsed_time": "1:17:06", "remaining_time": "0:34:36", "throughput": 1033.9, "total_tokens": 4783456} {"current_steps": 53125, "total_steps": 76960, "loss": 0.1336, "lr": 1.3241590825764172e-05, "epoch": 13.805873180873181, "percentage": 69.03, "elapsed_time": "1:17:07", "remaining_time": "0:34:35", "throughput": 1033.9, "total_tokens": 4783872} {"current_steps": 53130, "total_steps": 76960, "loss": 0.3155, "lr": 1.323658777979166e-05, "epoch": 13.807172557172557, "percentage": 69.04, "elapsed_time": "1:17:07", "remaining_time": "0:34:35", "throughput": 1033.9, "total_tokens": 4784320} {"current_steps": 53135, "total_steps": 76960, "loss": 0.1721, "lr": 1.3231585338822697e-05, "epoch": 13.808471933471933, "percentage": 69.04, "elapsed_time": "1:17:07", "remaining_time": "0:34:35", "throughput": 1033.9, "total_tokens": 4784752} {"current_steps": 53140, "total_steps": 76960, "loss": 0.1086, "lr": 1.3226583503114587e-05, "epoch": 13.80977130977131, "percentage": 69.05, "elapsed_time": "1:17:08", "remaining_time": "0:34:34", "throughput": 1033.9, "total_tokens": 4785168} {"current_steps": 53145, "total_steps": 76960, "loss": 0.0145, "lr": 1.3221582272924557e-05, "epoch": 13.811070686070686, "percentage": 69.06, "elapsed_time": "1:17:08", "remaining_time": "0:34:34", "throughput": 1033.9, "total_tokens": 4785600} {"current_steps": 53150, "total_steps": 76960, "loss": 0.2077, "lr": 1.3216581648509837e-05, "epoch": 13.812370062370062, "percentage": 69.06, "elapsed_time": "1:17:09", "remaining_time": "0:34:33", "throughput": 1033.9, "total_tokens": 4786016} {"current_steps": 53155, "total_steps": 76960, "loss": 0.2828, "lr": 1.3211581630127615e-05, "epoch": 13.81366943866944, "percentage": 69.07, "elapsed_time": "1:17:09", "remaining_time": "0:34:33", "throughput": 1033.91, "total_tokens": 4786480} {"current_steps": 53160, "total_steps": 76960, "loss": 0.0074, "lr": 1.3206582218035051e-05, "epoch": 13.814968814968815, "percentage": 69.07, "elapsed_time": "1:17:09", "remaining_time": "0:34:32", "throughput": 1033.92, "total_tokens": 4786960} {"current_steps": 53165, "total_steps": 76960, "loss": 0.3723, "lr": 1.320158341248926e-05, "epoch": 13.816268191268192, "percentage": 69.08, "elapsed_time": "1:17:10", "remaining_time": "0:34:32", "throughput": 1033.91, "total_tokens": 4787376} {"current_steps": 53170, "total_steps": 76960, "loss": 0.2391, "lr": 1.3196585213747342e-05, "epoch": 13.817567567567568, "percentage": 69.09, "elapsed_time": "1:17:10", "remaining_time": "0:34:31", "throughput": 1033.92, "total_tokens": 4787856} {"current_steps": 53175, "total_steps": 76960, "loss": 0.09, "lr": 1.3191587622066359e-05, "epoch": 13.818866943866944, "percentage": 69.09, "elapsed_time": "1:17:11", "remaining_time": "0:34:31", "throughput": 1033.92, "total_tokens": 4788272} {"current_steps": 53180, "total_steps": 76960, "loss": 0.0611, "lr": 1.3186590637703328e-05, "epoch": 13.82016632016632, "percentage": 69.1, "elapsed_time": "1:17:11", "remaining_time": "0:34:31", "throughput": 1033.92, "total_tokens": 4788720} {"current_steps": 53185, "total_steps": 76960, "loss": 0.3498, "lr": 1.3181594260915262e-05, "epoch": 13.821465696465696, "percentage": 69.11, "elapsed_time": "1:17:12", "remaining_time": "0:34:30", "throughput": 1033.93, "total_tokens": 4789152} {"current_steps": 53190, "total_steps": 76960, "loss": 0.0274, "lr": 1.3176598491959124e-05, "epoch": 13.822765072765073, "percentage": 69.11, "elapsed_time": "1:17:12", "remaining_time": "0:34:30", "throughput": 1033.92, "total_tokens": 4789568} {"current_steps": 53195, "total_steps": 76960, "loss": 0.1183, "lr": 1.3171603331091865e-05, "epoch": 13.82406444906445, "percentage": 69.12, "elapsed_time": "1:17:12", "remaining_time": "0:34:29", "throughput": 1033.92, "total_tokens": 4790000} {"current_steps": 53200, "total_steps": 76960, "loss": 0.0884, "lr": 1.3166608778570371e-05, "epoch": 13.825363825363825, "percentage": 69.13, "elapsed_time": "1:17:13", "remaining_time": "0:34:29", "throughput": 1033.93, "total_tokens": 4790480} {"current_steps": 53205, "total_steps": 76960, "loss": 0.4252, "lr": 1.3161614834651537e-05, "epoch": 13.826663201663202, "percentage": 69.13, "elapsed_time": "1:17:13", "remaining_time": "0:34:28", "throughput": 1033.94, "total_tokens": 4790960} {"current_steps": 53210, "total_steps": 76960, "loss": 0.3525, "lr": 1.3156621499592182e-05, "epoch": 13.827962577962579, "percentage": 69.14, "elapsed_time": "1:17:14", "remaining_time": "0:34:28", "throughput": 1033.95, "total_tokens": 4791408} {"current_steps": 53215, "total_steps": 76960, "loss": 0.1404, "lr": 1.3151628773649141e-05, "epoch": 13.829261954261954, "percentage": 69.15, "elapsed_time": "1:17:14", "remaining_time": "0:34:27", "throughput": 1033.95, "total_tokens": 4791856} {"current_steps": 53220, "total_steps": 76960, "loss": 0.2195, "lr": 1.3146636657079175e-05, "epoch": 13.83056133056133, "percentage": 69.15, "elapsed_time": "1:17:14", "remaining_time": "0:34:27", "throughput": 1033.95, "total_tokens": 4792272} {"current_steps": 53225, "total_steps": 76960, "loss": 0.2205, "lr": 1.3141645150139046e-05, "epoch": 13.831860706860708, "percentage": 69.16, "elapsed_time": "1:17:15", "remaining_time": "0:34:27", "throughput": 1033.96, "total_tokens": 4792736} {"current_steps": 53230, "total_steps": 76960, "loss": 0.4068, "lr": 1.3136654253085467e-05, "epoch": 13.833160083160083, "percentage": 69.17, "elapsed_time": "1:17:15", "remaining_time": "0:34:26", "throughput": 1033.96, "total_tokens": 4793200} {"current_steps": 53235, "total_steps": 76960, "loss": 0.3749, "lr": 1.3131663966175137e-05, "epoch": 13.83445945945946, "percentage": 69.17, "elapsed_time": "1:17:16", "remaining_time": "0:34:26", "throughput": 1033.97, "total_tokens": 4793664} {"current_steps": 53240, "total_steps": 76960, "loss": 0.1778, "lr": 1.31266742896647e-05, "epoch": 13.835758835758837, "percentage": 69.18, "elapsed_time": "1:17:16", "remaining_time": "0:34:25", "throughput": 1033.98, "total_tokens": 4794128} {"current_steps": 53245, "total_steps": 76960, "loss": 0.2801, "lr": 1.312168522381077e-05, "epoch": 13.837058212058212, "percentage": 69.19, "elapsed_time": "1:17:17", "remaining_time": "0:34:25", "throughput": 1033.99, "total_tokens": 4794608} {"current_steps": 53250, "total_steps": 76960, "loss": 0.2448, "lr": 1.3116696768869963e-05, "epoch": 13.838357588357589, "percentage": 69.19, "elapsed_time": "1:17:17", "remaining_time": "0:34:24", "throughput": 1034.0, "total_tokens": 4795072} {"current_steps": 53255, "total_steps": 76960, "loss": 0.4083, "lr": 1.3111708925098806e-05, "epoch": 13.839656964656964, "percentage": 69.2, "elapsed_time": "1:17:17", "remaining_time": "0:34:24", "throughput": 1034.0, "total_tokens": 4795520} {"current_steps": 53260, "total_steps": 76960, "loss": 0.2641, "lr": 1.310672169275387e-05, "epoch": 13.84095634095634, "percentage": 69.2, "elapsed_time": "1:17:18", "remaining_time": "0:34:23", "throughput": 1034.01, "total_tokens": 4796000} {"current_steps": 53265, "total_steps": 76960, "loss": 0.4384, "lr": 1.3101735072091622e-05, "epoch": 13.842255717255718, "percentage": 69.21, "elapsed_time": "1:17:18", "remaining_time": "0:34:23", "throughput": 1034.01, "total_tokens": 4796432} {"current_steps": 53270, "total_steps": 76960, "loss": 0.1143, "lr": 1.3096749063368553e-05, "epoch": 13.843555093555093, "percentage": 69.22, "elapsed_time": "1:17:19", "remaining_time": "0:34:23", "throughput": 1034.01, "total_tokens": 4796880} {"current_steps": 53275, "total_steps": 76960, "loss": 0.1104, "lr": 1.309176366684107e-05, "epoch": 13.84485446985447, "percentage": 69.22, "elapsed_time": "1:17:19", "remaining_time": "0:34:22", "throughput": 1034.02, "total_tokens": 4797360} {"current_steps": 53280, "total_steps": 76960, "loss": 0.1528, "lr": 1.3086778882765604e-05, "epoch": 13.846153846153847, "percentage": 69.23, "elapsed_time": "1:17:19", "remaining_time": "0:34:22", "throughput": 1034.02, "total_tokens": 4797792} {"current_steps": 53285, "total_steps": 76960, "loss": 0.2211, "lr": 1.3081794711398504e-05, "epoch": 13.847453222453222, "percentage": 69.24, "elapsed_time": "1:17:20", "remaining_time": "0:34:21", "throughput": 1034.03, "total_tokens": 4798256} {"current_steps": 53290, "total_steps": 76960, "loss": 0.23, "lr": 1.307681115299612e-05, "epoch": 13.848752598752599, "percentage": 69.24, "elapsed_time": "1:17:20", "remaining_time": "0:34:21", "throughput": 1034.04, "total_tokens": 4798704} {"current_steps": 53295, "total_steps": 76960, "loss": 0.2919, "lr": 1.3071828207814766e-05, "epoch": 13.850051975051976, "percentage": 69.25, "elapsed_time": "1:17:21", "remaining_time": "0:34:20", "throughput": 1034.04, "total_tokens": 4799136} {"current_steps": 53300, "total_steps": 76960, "loss": 0.1776, "lr": 1.3066845876110722e-05, "epoch": 13.85135135135135, "percentage": 69.26, "elapsed_time": "1:17:21", "remaining_time": "0:34:20", "throughput": 1034.04, "total_tokens": 4799584} {"current_steps": 53305, "total_steps": 76960, "loss": 0.2083, "lr": 1.3061864158140232e-05, "epoch": 13.852650727650728, "percentage": 69.26, "elapsed_time": "1:17:22", "remaining_time": "0:34:19", "throughput": 1034.04, "total_tokens": 4800000} {"current_steps": 53310, "total_steps": 76960, "loss": 0.0964, "lr": 1.3056883054159497e-05, "epoch": 13.853950103950105, "percentage": 69.27, "elapsed_time": "1:17:22", "remaining_time": "0:34:19", "throughput": 1034.03, "total_tokens": 4800416} {"current_steps": 53315, "total_steps": 76960, "loss": 0.4256, "lr": 1.3051902564424717e-05, "epoch": 13.85524948024948, "percentage": 69.28, "elapsed_time": "1:17:22", "remaining_time": "0:34:19", "throughput": 1034.03, "total_tokens": 4800848} {"current_steps": 53320, "total_steps": 76960, "loss": 0.3455, "lr": 1.304692268919203e-05, "epoch": 13.856548856548857, "percentage": 69.28, "elapsed_time": "1:17:23", "remaining_time": "0:34:18", "throughput": 1034.04, "total_tokens": 4801296} {"current_steps": 53325, "total_steps": 76960, "loss": 0.3109, "lr": 1.304194342871756e-05, "epoch": 13.857848232848234, "percentage": 69.29, "elapsed_time": "1:17:23", "remaining_time": "0:34:18", "throughput": 1034.04, "total_tokens": 4801744} {"current_steps": 53330, "total_steps": 76960, "loss": 0.4947, "lr": 1.30369647832574e-05, "epoch": 13.859147609147609, "percentage": 69.3, "elapsed_time": "1:17:24", "remaining_time": "0:34:17", "throughput": 1034.04, "total_tokens": 4802176} {"current_steps": 53335, "total_steps": 76960, "loss": 0.1245, "lr": 1.303198675306761e-05, "epoch": 13.860446985446986, "percentage": 69.3, "elapsed_time": "1:17:24", "remaining_time": "0:34:17", "throughput": 1034.05, "total_tokens": 4802640} {"current_steps": 53340, "total_steps": 76960, "loss": 0.525, "lr": 1.3027009338404198e-05, "epoch": 13.861746361746361, "percentage": 69.31, "elapsed_time": "1:17:24", "remaining_time": "0:34:16", "throughput": 1034.05, "total_tokens": 4803056} {"current_steps": 53345, "total_steps": 76960, "loss": 0.2122, "lr": 1.3022032539523176e-05, "epoch": 13.863045738045738, "percentage": 69.32, "elapsed_time": "1:17:25", "remaining_time": "0:34:16", "throughput": 1034.05, "total_tokens": 4803488} {"current_steps": 53350, "total_steps": 76960, "loss": 0.6402, "lr": 1.3017056356680493e-05, "epoch": 13.864345114345115, "percentage": 69.32, "elapsed_time": "1:17:25", "remaining_time": "0:34:15", "throughput": 1034.05, "total_tokens": 4803952} {"current_steps": 53355, "total_steps": 76960, "loss": 0.3664, "lr": 1.3012080790132092e-05, "epoch": 13.86564449064449, "percentage": 69.33, "elapsed_time": "1:17:26", "remaining_time": "0:34:15", "throughput": 1034.05, "total_tokens": 4804384} {"current_steps": 53360, "total_steps": 76960, "loss": 0.1251, "lr": 1.3007105840133849e-05, "epoch": 13.866943866943867, "percentage": 69.33, "elapsed_time": "1:17:26", "remaining_time": "0:34:15", "throughput": 1034.06, "total_tokens": 4804832} {"current_steps": 53365, "total_steps": 76960, "loss": 0.2818, "lr": 1.3002131506941645e-05, "epoch": 13.868243243243244, "percentage": 69.34, "elapsed_time": "1:17:26", "remaining_time": "0:34:14", "throughput": 1034.07, "total_tokens": 4805296} {"current_steps": 53370, "total_steps": 76960, "loss": 0.2371, "lr": 1.2997157790811324e-05, "epoch": 13.869542619542619, "percentage": 69.35, "elapsed_time": "1:17:27", "remaining_time": "0:34:14", "throughput": 1034.07, "total_tokens": 4805744} {"current_steps": 53375, "total_steps": 76960, "loss": 0.1616, "lr": 1.2992184691998666e-05, "epoch": 13.870841995841996, "percentage": 69.35, "elapsed_time": "1:17:27", "remaining_time": "0:34:13", "throughput": 1034.08, "total_tokens": 4806208} {"current_steps": 53380, "total_steps": 76960, "loss": 0.3213, "lr": 1.298721221075947e-05, "epoch": 13.872141372141373, "percentage": 69.36, "elapsed_time": "1:17:28", "remaining_time": "0:34:13", "throughput": 1034.08, "total_tokens": 4806656} {"current_steps": 53385, "total_steps": 76960, "loss": 0.0789, "lr": 1.2982240347349445e-05, "epoch": 13.873440748440748, "percentage": 69.37, "elapsed_time": "1:17:28", "remaining_time": "0:34:12", "throughput": 1034.09, "total_tokens": 4807120} {"current_steps": 53390, "total_steps": 76960, "loss": 0.114, "lr": 1.2977269102024326e-05, "epoch": 13.874740124740125, "percentage": 69.37, "elapsed_time": "1:17:29", "remaining_time": "0:34:12", "throughput": 1034.1, "total_tokens": 4807600} {"current_steps": 53395, "total_steps": 76960, "loss": 0.2054, "lr": 1.2972298475039766e-05, "epoch": 13.8760395010395, "percentage": 69.38, "elapsed_time": "1:17:29", "remaining_time": "0:34:11", "throughput": 1034.11, "total_tokens": 4808080} {"current_steps": 53400, "total_steps": 76960, "loss": 0.0506, "lr": 1.2967328466651418e-05, "epoch": 13.877338877338877, "percentage": 69.39, "elapsed_time": "1:17:29", "remaining_time": "0:34:11", "throughput": 1034.11, "total_tokens": 4808512} {"current_steps": 53405, "total_steps": 76960, "loss": 0.2114, "lr": 1.29623590771149e-05, "epoch": 13.878638253638254, "percentage": 69.39, "elapsed_time": "1:17:30", "remaining_time": "0:34:11", "throughput": 1034.11, "total_tokens": 4808960} {"current_steps": 53410, "total_steps": 76960, "loss": 0.2353, "lr": 1.2957390306685797e-05, "epoch": 13.87993762993763, "percentage": 69.4, "elapsed_time": "1:17:30", "remaining_time": "0:34:10", "throughput": 1034.11, "total_tokens": 4809360} {"current_steps": 53415, "total_steps": 76960, "loss": 0.1494, "lr": 1.2952422155619637e-05, "epoch": 13.881237006237006, "percentage": 69.41, "elapsed_time": "1:17:31", "remaining_time": "0:34:10", "throughput": 1034.11, "total_tokens": 4809824} {"current_steps": 53420, "total_steps": 76960, "loss": 0.0174, "lr": 1.2947454624171962e-05, "epoch": 13.882536382536383, "percentage": 69.41, "elapsed_time": "1:17:31", "remaining_time": "0:34:09", "throughput": 1034.12, "total_tokens": 4810304} {"current_steps": 53425, "total_steps": 76960, "loss": 0.1689, "lr": 1.2942487712598234e-05, "epoch": 13.883835758835758, "percentage": 69.42, "elapsed_time": "1:17:31", "remaining_time": "0:34:09", "throughput": 1034.12, "total_tokens": 4810736} {"current_steps": 53430, "total_steps": 76960, "loss": 0.0168, "lr": 1.2937521421153926e-05, "epoch": 13.885135135135135, "percentage": 69.43, "elapsed_time": "1:17:32", "remaining_time": "0:34:08", "throughput": 1034.13, "total_tokens": 4811216} {"current_steps": 53435, "total_steps": 76960, "loss": 0.0376, "lr": 1.2932555750094435e-05, "epoch": 13.886434511434512, "percentage": 69.43, "elapsed_time": "1:17:32", "remaining_time": "0:34:08", "throughput": 1034.14, "total_tokens": 4811664} {"current_steps": 53440, "total_steps": 76960, "loss": 0.2831, "lr": 1.2927590699675168e-05, "epoch": 13.887733887733887, "percentage": 69.44, "elapsed_time": "1:17:33", "remaining_time": "0:34:07", "throughput": 1034.15, "total_tokens": 4812144} {"current_steps": 53445, "total_steps": 76960, "loss": 0.1566, "lr": 1.2922626270151485e-05, "epoch": 13.889033264033264, "percentage": 69.45, "elapsed_time": "1:17:33", "remaining_time": "0:34:07", "throughput": 1034.15, "total_tokens": 4812576} {"current_steps": 53450, "total_steps": 76960, "loss": 0.4319, "lr": 1.2917662461778698e-05, "epoch": 13.890332640332641, "percentage": 69.45, "elapsed_time": "1:17:34", "remaining_time": "0:34:07", "throughput": 1034.16, "total_tokens": 4813056} {"current_steps": 53455, "total_steps": 76960, "loss": 0.2167, "lr": 1.2912699274812118e-05, "epoch": 13.891632016632016, "percentage": 69.46, "elapsed_time": "1:17:34", "remaining_time": "0:34:06", "throughput": 1034.17, "total_tokens": 4813520} {"current_steps": 53460, "total_steps": 76960, "loss": 0.1225, "lr": 1.2907736709506984e-05, "epoch": 13.892931392931393, "percentage": 69.46, "elapsed_time": "1:17:34", "remaining_time": "0:34:06", "throughput": 1034.16, "total_tokens": 4813936} {"current_steps": 53465, "total_steps": 76960, "loss": 0.424, "lr": 1.2902774766118548e-05, "epoch": 13.89423076923077, "percentage": 69.47, "elapsed_time": "1:17:35", "remaining_time": "0:34:05", "throughput": 1034.17, "total_tokens": 4814384} {"current_steps": 53470, "total_steps": 76960, "loss": 0.2002, "lr": 1.2897813444901985e-05, "epoch": 13.895530145530145, "percentage": 69.48, "elapsed_time": "1:17:35", "remaining_time": "0:34:05", "throughput": 1034.18, "total_tokens": 4814848} {"current_steps": 53475, "total_steps": 76960, "loss": 0.2375, "lr": 1.2892852746112477e-05, "epoch": 13.896829521829522, "percentage": 69.48, "elapsed_time": "1:17:36", "remaining_time": "0:34:04", "throughput": 1034.19, "total_tokens": 4815344} {"current_steps": 53480, "total_steps": 76960, "loss": 0.1237, "lr": 1.2887892670005147e-05, "epoch": 13.898128898128899, "percentage": 69.49, "elapsed_time": "1:17:36", "remaining_time": "0:34:04", "throughput": 1034.2, "total_tokens": 4815808} {"current_steps": 53485, "total_steps": 76960, "loss": 0.0654, "lr": 1.2882933216835117e-05, "epoch": 13.899428274428274, "percentage": 69.5, "elapsed_time": "1:17:36", "remaining_time": "0:34:03", "throughput": 1034.2, "total_tokens": 4816272} {"current_steps": 53490, "total_steps": 76960, "loss": 0.2549, "lr": 1.2877974386857428e-05, "epoch": 13.900727650727651, "percentage": 69.5, "elapsed_time": "1:17:37", "remaining_time": "0:34:03", "throughput": 1034.2, "total_tokens": 4816704} {"current_steps": 53495, "total_steps": 76960, "loss": 0.2526, "lr": 1.287301618032714e-05, "epoch": 13.902027027027026, "percentage": 69.51, "elapsed_time": "1:17:37", "remaining_time": "0:34:03", "throughput": 1034.21, "total_tokens": 4817168} {"current_steps": 53500, "total_steps": 76960, "loss": 0.3014, "lr": 1.2868058597499255e-05, "epoch": 13.903326403326403, "percentage": 69.52, "elapsed_time": "1:17:38", "remaining_time": "0:34:02", "throughput": 1034.22, "total_tokens": 4817616} {"current_steps": 53505, "total_steps": 76960, "loss": 0.4029, "lr": 1.2863101638628717e-05, "epoch": 13.90462577962578, "percentage": 69.52, "elapsed_time": "1:17:38", "remaining_time": "0:34:02", "throughput": 1034.22, "total_tokens": 4818064} {"current_steps": 53510, "total_steps": 76960, "loss": 0.1952, "lr": 1.2858145303970512e-05, "epoch": 13.905925155925155, "percentage": 69.53, "elapsed_time": "1:17:39", "remaining_time": "0:34:01", "throughput": 1034.22, "total_tokens": 4818496} {"current_steps": 53515, "total_steps": 76960, "loss": 0.245, "lr": 1.285318959377952e-05, "epoch": 13.907224532224532, "percentage": 69.54, "elapsed_time": "1:17:39", "remaining_time": "0:34:01", "throughput": 1034.22, "total_tokens": 4818944} {"current_steps": 53520, "total_steps": 76960, "loss": 0.2798, "lr": 1.2848234508310631e-05, "epoch": 13.90852390852391, "percentage": 69.54, "elapsed_time": "1:17:39", "remaining_time": "0:34:00", "throughput": 1034.23, "total_tokens": 4819424} {"current_steps": 53525, "total_steps": 76960, "loss": 0.1865, "lr": 1.2843280047818674e-05, "epoch": 13.909823284823284, "percentage": 69.55, "elapsed_time": "1:17:40", "remaining_time": "0:34:00", "throughput": 1034.24, "total_tokens": 4819888} {"current_steps": 53530, "total_steps": 76960, "loss": 0.3713, "lr": 1.2838326212558485e-05, "epoch": 13.911122661122661, "percentage": 69.56, "elapsed_time": "1:17:40", "remaining_time": "0:33:59", "throughput": 1034.26, "total_tokens": 4820384} {"current_steps": 53535, "total_steps": 76960, "loss": 0.1395, "lr": 1.2833373002784822e-05, "epoch": 13.912422037422038, "percentage": 69.56, "elapsed_time": "1:17:41", "remaining_time": "0:33:59", "throughput": 1034.26, "total_tokens": 4820848} {"current_steps": 53540, "total_steps": 76960, "loss": 0.3247, "lr": 1.282842041875244e-05, "epoch": 13.913721413721413, "percentage": 69.57, "elapsed_time": "1:17:41", "remaining_time": "0:33:59", "throughput": 1034.26, "total_tokens": 4821280} {"current_steps": 53545, "total_steps": 76960, "loss": 0.1146, "lr": 1.2823468460716063e-05, "epoch": 13.91502079002079, "percentage": 69.58, "elapsed_time": "1:17:41", "remaining_time": "0:33:58", "throughput": 1034.27, "total_tokens": 4821728} {"current_steps": 53550, "total_steps": 76960, "loss": 0.3454, "lr": 1.2818517128930374e-05, "epoch": 13.916320166320165, "percentage": 69.58, "elapsed_time": "1:17:42", "remaining_time": "0:33:58", "throughput": 1034.28, "total_tokens": 4822208} {"current_steps": 53555, "total_steps": 76960, "loss": 0.1375, "lr": 1.2813566423650014e-05, "epoch": 13.917619542619542, "percentage": 69.59, "elapsed_time": "1:17:42", "remaining_time": "0:33:57", "throughput": 1034.28, "total_tokens": 4822656} {"current_steps": 53560, "total_steps": 76960, "loss": 0.3578, "lr": 1.280861634512962e-05, "epoch": 13.91891891891892, "percentage": 69.59, "elapsed_time": "1:17:43", "remaining_time": "0:33:57", "throughput": 1034.28, "total_tokens": 4823072} {"current_steps": 53565, "total_steps": 76960, "loss": 0.425, "lr": 1.2803666893623767e-05, "epoch": 13.920218295218294, "percentage": 69.6, "elapsed_time": "1:17:43", "remaining_time": "0:33:56", "throughput": 1034.28, "total_tokens": 4823504} {"current_steps": 53570, "total_steps": 76960, "loss": 0.2723, "lr": 1.2798718069387005e-05, "epoch": 13.921517671517671, "percentage": 69.61, "elapsed_time": "1:17:44", "remaining_time": "0:33:56", "throughput": 1034.28, "total_tokens": 4823968} {"current_steps": 53575, "total_steps": 76960, "loss": 0.3169, "lr": 1.279376987267386e-05, "epoch": 13.922817047817048, "percentage": 69.61, "elapsed_time": "1:17:44", "remaining_time": "0:33:56", "throughput": 1034.29, "total_tokens": 4824416} {"current_steps": 53580, "total_steps": 76960, "loss": 0.3768, "lr": 1.2788822303738829e-05, "epoch": 13.924116424116423, "percentage": 69.62, "elapsed_time": "1:17:44", "remaining_time": "0:33:55", "throughput": 1034.3, "total_tokens": 4824896} {"current_steps": 53585, "total_steps": 76960, "loss": 0.2192, "lr": 1.2783875362836373e-05, "epoch": 13.9254158004158, "percentage": 69.63, "elapsed_time": "1:17:45", "remaining_time": "0:33:55", "throughput": 1034.31, "total_tokens": 4825360} {"current_steps": 53590, "total_steps": 76960, "loss": 0.5854, "lr": 1.2778929050220905e-05, "epoch": 13.926715176715177, "percentage": 69.63, "elapsed_time": "1:17:45", "remaining_time": "0:33:54", "throughput": 1034.31, "total_tokens": 4825824} {"current_steps": 53595, "total_steps": 76960, "loss": 0.2095, "lr": 1.2773983366146832e-05, "epoch": 13.928014553014552, "percentage": 69.64, "elapsed_time": "1:17:46", "remaining_time": "0:33:54", "throughput": 1034.31, "total_tokens": 4826240} {"current_steps": 53600, "total_steps": 76960, "loss": 0.0802, "lr": 1.2769038310868503e-05, "epoch": 13.92931392931393, "percentage": 69.65, "elapsed_time": "1:17:46", "remaining_time": "0:33:53", "throughput": 1034.32, "total_tokens": 4826704} {"current_steps": 53605, "total_steps": 76960, "loss": 0.2067, "lr": 1.2764093884640261e-05, "epoch": 13.930613305613306, "percentage": 69.65, "elapsed_time": "1:17:46", "remaining_time": "0:33:53", "throughput": 1034.32, "total_tokens": 4827136} {"current_steps": 53610, "total_steps": 76960, "loss": 0.1587, "lr": 1.2759150087716384e-05, "epoch": 13.931912681912682, "percentage": 69.66, "elapsed_time": "1:17:47", "remaining_time": "0:33:52", "throughput": 1034.33, "total_tokens": 4827616} {"current_steps": 53615, "total_steps": 76960, "loss": 0.2918, "lr": 1.2754206920351147e-05, "epoch": 13.933212058212058, "percentage": 69.67, "elapsed_time": "1:17:47", "remaining_time": "0:33:52", "throughput": 1034.34, "total_tokens": 4828080} {"current_steps": 53620, "total_steps": 76960, "loss": 0.2461, "lr": 1.2749264382798782e-05, "epoch": 13.934511434511435, "percentage": 69.67, "elapsed_time": "1:17:48", "remaining_time": "0:33:52", "throughput": 1034.34, "total_tokens": 4828512} {"current_steps": 53625, "total_steps": 76960, "loss": 0.2353, "lr": 1.2744322475313497e-05, "epoch": 13.93581081081081, "percentage": 69.68, "elapsed_time": "1:17:48", "remaining_time": "0:33:51", "throughput": 1034.34, "total_tokens": 4828960} {"current_steps": 53630, "total_steps": 76960, "loss": 0.3194, "lr": 1.2739381198149453e-05, "epoch": 13.937110187110187, "percentage": 69.69, "elapsed_time": "1:17:49", "remaining_time": "0:33:51", "throughput": 1034.36, "total_tokens": 4829472} {"current_steps": 53635, "total_steps": 76960, "loss": 0.3524, "lr": 1.2734440551560766e-05, "epoch": 13.938409563409563, "percentage": 69.69, "elapsed_time": "1:17:49", "remaining_time": "0:33:50", "throughput": 1034.36, "total_tokens": 4829920} {"current_steps": 53640, "total_steps": 76960, "loss": 0.221, "lr": 1.2729500535801569e-05, "epoch": 13.93970893970894, "percentage": 69.7, "elapsed_time": "1:17:49", "remaining_time": "0:33:50", "throughput": 1034.36, "total_tokens": 4830352} {"current_steps": 53645, "total_steps": 76960, "loss": 0.1734, "lr": 1.2724561151125902e-05, "epoch": 13.941008316008316, "percentage": 69.71, "elapsed_time": "1:17:50", "remaining_time": "0:33:49", "throughput": 1034.36, "total_tokens": 4830768} {"current_steps": 53650, "total_steps": 76960, "loss": 0.3678, "lr": 1.271962239778782e-05, "epoch": 13.942307692307692, "percentage": 69.71, "elapsed_time": "1:17:50", "remaining_time": "0:33:49", "throughput": 1034.36, "total_tokens": 4831216} {"current_steps": 53655, "total_steps": 76960, "loss": 0.1702, "lr": 1.2714684276041322e-05, "epoch": 13.943607068607069, "percentage": 69.72, "elapsed_time": "1:17:51", "remaining_time": "0:33:48", "throughput": 1034.36, "total_tokens": 4831648} {"current_steps": 53660, "total_steps": 76960, "loss": 0.2588, "lr": 1.2709746786140398e-05, "epoch": 13.944906444906445, "percentage": 69.72, "elapsed_time": "1:17:51", "remaining_time": "0:33:48", "throughput": 1034.36, "total_tokens": 4832080} {"current_steps": 53665, "total_steps": 76960, "loss": 0.1726, "lr": 1.2704809928338956e-05, "epoch": 13.94620582120582, "percentage": 69.73, "elapsed_time": "1:17:51", "remaining_time": "0:33:48", "throughput": 1034.38, "total_tokens": 4832576} {"current_steps": 53670, "total_steps": 76960, "loss": 0.225, "lr": 1.2699873702890936e-05, "epoch": 13.947505197505198, "percentage": 69.74, "elapsed_time": "1:17:52", "remaining_time": "0:33:47", "throughput": 1034.38, "total_tokens": 4833008} {"current_steps": 53675, "total_steps": 76960, "loss": 0.2133, "lr": 1.2694938110050181e-05, "epoch": 13.948804573804575, "percentage": 69.74, "elapsed_time": "1:17:52", "remaining_time": "0:33:47", "throughput": 1034.38, "total_tokens": 4833440} {"current_steps": 53680, "total_steps": 76960, "loss": 0.0997, "lr": 1.2690003150070562e-05, "epoch": 13.95010395010395, "percentage": 69.75, "elapsed_time": "1:17:53", "remaining_time": "0:33:46", "throughput": 1034.37, "total_tokens": 4833856} {"current_steps": 53685, "total_steps": 76960, "loss": 0.0485, "lr": 1.2685068823205867e-05, "epoch": 13.951403326403327, "percentage": 69.76, "elapsed_time": "1:17:53", "remaining_time": "0:33:46", "throughput": 1034.38, "total_tokens": 4834336} {"current_steps": 53690, "total_steps": 76960, "loss": 0.1882, "lr": 1.268013512970988e-05, "epoch": 13.952702702702704, "percentage": 69.76, "elapsed_time": "1:17:54", "remaining_time": "0:33:45", "throughput": 1034.39, "total_tokens": 4834784} {"current_steps": 53695, "total_steps": 76960, "loss": 0.2542, "lr": 1.2675202069836361e-05, "epoch": 13.954002079002079, "percentage": 69.77, "elapsed_time": "1:17:54", "remaining_time": "0:33:45", "throughput": 1034.39, "total_tokens": 4835216} {"current_steps": 53700, "total_steps": 76960, "loss": 0.1034, "lr": 1.2670269643838994e-05, "epoch": 13.955301455301456, "percentage": 69.78, "elapsed_time": "1:17:54", "remaining_time": "0:33:44", "throughput": 1034.39, "total_tokens": 4835680} {"current_steps": 53705, "total_steps": 76960, "loss": 0.1561, "lr": 1.2665337851971487e-05, "epoch": 13.95660083160083, "percentage": 69.78, "elapsed_time": "1:17:55", "remaining_time": "0:33:44", "throughput": 1034.4, "total_tokens": 4836112} {"current_steps": 53710, "total_steps": 76960, "loss": 0.2781, "lr": 1.2660406694487461e-05, "epoch": 13.957900207900208, "percentage": 69.79, "elapsed_time": "1:17:55", "remaining_time": "0:33:44", "throughput": 1034.4, "total_tokens": 4836576} {"current_steps": 53715, "total_steps": 76960, "loss": 0.3758, "lr": 1.2655476171640551e-05, "epoch": 13.959199584199585, "percentage": 69.8, "elapsed_time": "1:17:56", "remaining_time": "0:33:43", "throughput": 1034.4, "total_tokens": 4837008} {"current_steps": 53720, "total_steps": 76960, "loss": 0.2313, "lr": 1.2650546283684322e-05, "epoch": 13.96049896049896, "percentage": 69.8, "elapsed_time": "1:17:56", "remaining_time": "0:33:43", "throughput": 1034.41, "total_tokens": 4837472} {"current_steps": 53725, "total_steps": 76960, "loss": 0.3444, "lr": 1.2645617030872328e-05, "epoch": 13.961798336798337, "percentage": 69.81, "elapsed_time": "1:17:56", "remaining_time": "0:33:42", "throughput": 1034.41, "total_tokens": 4837888} {"current_steps": 53730, "total_steps": 76960, "loss": 0.1373, "lr": 1.264068841345809e-05, "epoch": 13.963097713097714, "percentage": 69.82, "elapsed_time": "1:17:57", "remaining_time": "0:33:42", "throughput": 1034.41, "total_tokens": 4838352} {"current_steps": 53735, "total_steps": 76960, "loss": 0.2464, "lr": 1.2635760431695098e-05, "epoch": 13.964397089397089, "percentage": 69.82, "elapsed_time": "1:17:57", "remaining_time": "0:33:41", "throughput": 1034.41, "total_tokens": 4838784} {"current_steps": 53740, "total_steps": 76960, "loss": 0.0433, "lr": 1.263083308583678e-05, "epoch": 13.965696465696466, "percentage": 69.83, "elapsed_time": "1:17:58", "remaining_time": "0:33:41", "throughput": 1034.41, "total_tokens": 4839200} {"current_steps": 53745, "total_steps": 76960, "loss": 0.3958, "lr": 1.2625906376136581e-05, "epoch": 13.966995841995843, "percentage": 69.83, "elapsed_time": "1:17:58", "remaining_time": "0:33:40", "throughput": 1034.41, "total_tokens": 4839632} {"current_steps": 53750, "total_steps": 76960, "loss": 0.1842, "lr": 1.2620980302847865e-05, "epoch": 13.968295218295218, "percentage": 69.84, "elapsed_time": "1:17:59", "remaining_time": "0:33:40", "throughput": 1034.41, "total_tokens": 4840064} {"current_steps": 53755, "total_steps": 76960, "loss": 0.1005, "lr": 1.2616054866223992e-05, "epoch": 13.969594594594595, "percentage": 69.85, "elapsed_time": "1:17:59", "remaining_time": "0:33:40", "throughput": 1034.42, "total_tokens": 4840512} {"current_steps": 53760, "total_steps": 76960, "loss": 0.1667, "lr": 1.2611130066518293e-05, "epoch": 13.970893970893972, "percentage": 69.85, "elapsed_time": "1:17:59", "remaining_time": "0:33:39", "throughput": 1034.42, "total_tokens": 4840976} {"current_steps": 53765, "total_steps": 76960, "loss": 0.1512, "lr": 1.2606205903984034e-05, "epoch": 13.972193347193347, "percentage": 69.86, "elapsed_time": "1:18:00", "remaining_time": "0:33:39", "throughput": 1034.43, "total_tokens": 4841424} {"current_steps": 53770, "total_steps": 76960, "loss": 0.0242, "lr": 1.260128237887449e-05, "epoch": 13.973492723492724, "percentage": 69.87, "elapsed_time": "1:18:00", "remaining_time": "0:33:38", "throughput": 1034.43, "total_tokens": 4841856} {"current_steps": 53775, "total_steps": 76960, "loss": 0.4485, "lr": 1.2596359491442866e-05, "epoch": 13.9747920997921, "percentage": 69.87, "elapsed_time": "1:18:01", "remaining_time": "0:33:38", "throughput": 1034.44, "total_tokens": 4842368} {"current_steps": 53780, "total_steps": 76960, "loss": 0.2662, "lr": 1.2591437241942367e-05, "epoch": 13.976091476091476, "percentage": 69.88, "elapsed_time": "1:18:01", "remaining_time": "0:33:37", "throughput": 1034.44, "total_tokens": 4842784} {"current_steps": 53785, "total_steps": 76960, "loss": 0.1712, "lr": 1.2586515630626127e-05, "epoch": 13.977390852390853, "percentage": 69.89, "elapsed_time": "1:18:01", "remaining_time": "0:33:37", "throughput": 1034.45, "total_tokens": 4843248} {"current_steps": 53790, "total_steps": 76960, "loss": 0.2249, "lr": 1.2581594657747286e-05, "epoch": 13.978690228690228, "percentage": 69.89, "elapsed_time": "1:18:02", "remaining_time": "0:33:36", "throughput": 1034.45, "total_tokens": 4843696} {"current_steps": 53795, "total_steps": 76960, "loss": 0.2211, "lr": 1.2576674323558929e-05, "epoch": 13.979989604989605, "percentage": 69.9, "elapsed_time": "1:18:02", "remaining_time": "0:33:36", "throughput": 1034.45, "total_tokens": 4844144} {"current_steps": 53800, "total_steps": 76960, "loss": 0.3639, "lr": 1.2571754628314122e-05, "epoch": 13.981288981288982, "percentage": 69.91, "elapsed_time": "1:18:03", "remaining_time": "0:33:36", "throughput": 1034.46, "total_tokens": 4844576} {"current_steps": 53805, "total_steps": 76960, "loss": 0.2579, "lr": 1.2566835572265878e-05, "epoch": 13.982588357588357, "percentage": 69.91, "elapsed_time": "1:18:03", "remaining_time": "0:33:35", "throughput": 1034.46, "total_tokens": 4845040} {"current_steps": 53810, "total_steps": 76960, "loss": 0.6379, "lr": 1.2561917155667199e-05, "epoch": 13.983887733887734, "percentage": 69.92, "elapsed_time": "1:18:04", "remaining_time": "0:33:35", "throughput": 1034.46, "total_tokens": 4845472} {"current_steps": 53815, "total_steps": 76960, "loss": 0.5323, "lr": 1.255699937877103e-05, "epoch": 13.98518711018711, "percentage": 69.93, "elapsed_time": "1:18:04", "remaining_time": "0:33:34", "throughput": 1034.46, "total_tokens": 4845888} {"current_steps": 53820, "total_steps": 76960, "loss": 0.0547, "lr": 1.2552082241830316e-05, "epoch": 13.986486486486486, "percentage": 69.93, "elapsed_time": "1:18:04", "remaining_time": "0:33:34", "throughput": 1034.46, "total_tokens": 4846320} {"current_steps": 53825, "total_steps": 76960, "loss": 0.3538, "lr": 1.2547165745097928e-05, "epoch": 13.987785862785863, "percentage": 69.94, "elapsed_time": "1:18:05", "remaining_time": "0:33:33", "throughput": 1034.47, "total_tokens": 4846816} {"current_steps": 53830, "total_steps": 76960, "loss": 0.0431, "lr": 1.2542249888826741e-05, "epoch": 13.98908523908524, "percentage": 69.95, "elapsed_time": "1:18:05", "remaining_time": "0:33:33", "throughput": 1034.47, "total_tokens": 4847216} {"current_steps": 53835, "total_steps": 76960, "loss": 0.0813, "lr": 1.2537334673269585e-05, "epoch": 13.990384615384615, "percentage": 69.95, "elapsed_time": "1:18:06", "remaining_time": "0:33:32", "throughput": 1034.47, "total_tokens": 4847648} {"current_steps": 53840, "total_steps": 76960, "loss": 0.2704, "lr": 1.2532420098679237e-05, "epoch": 13.991683991683992, "percentage": 69.96, "elapsed_time": "1:18:06", "remaining_time": "0:33:32", "throughput": 1034.47, "total_tokens": 4848096} {"current_steps": 53845, "total_steps": 76960, "loss": 0.4442, "lr": 1.2527506165308481e-05, "epoch": 13.992983367983367, "percentage": 69.96, "elapsed_time": "1:18:06", "remaining_time": "0:33:32", "throughput": 1034.47, "total_tokens": 4848528} {"current_steps": 53850, "total_steps": 76960, "loss": 0.5379, "lr": 1.2522592873410022e-05, "epoch": 13.994282744282744, "percentage": 69.97, "elapsed_time": "1:18:07", "remaining_time": "0:33:31", "throughput": 1034.48, "total_tokens": 4848992} {"current_steps": 53855, "total_steps": 76960, "loss": 0.5045, "lr": 1.2517680223236578e-05, "epoch": 13.995582120582121, "percentage": 69.98, "elapsed_time": "1:18:07", "remaining_time": "0:33:31", "throughput": 1034.47, "total_tokens": 4849392} {"current_steps": 53860, "total_steps": 76960, "loss": 0.438, "lr": 1.2512768215040793e-05, "epoch": 13.996881496881496, "percentage": 69.98, "elapsed_time": "1:18:08", "remaining_time": "0:33:30", "throughput": 1034.47, "total_tokens": 4849840} {"current_steps": 53865, "total_steps": 76960, "loss": 0.3572, "lr": 1.25078568490753e-05, "epoch": 13.998180873180873, "percentage": 69.99, "elapsed_time": "1:18:08", "remaining_time": "0:33:30", "throughput": 1034.48, "total_tokens": 4850272} {"current_steps": 53870, "total_steps": 76960, "loss": 0.1854, "lr": 1.2502946125592698e-05, "epoch": 13.99948024948025, "percentage": 70.0, "elapsed_time": "1:18:09", "remaining_time": "0:33:29", "throughput": 1034.49, "total_tokens": 4850752} {"current_steps": 53872, "total_steps": 76960, "eval_loss": 0.38002052903175354, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "1:18:22", "remaining_time": "0:33:35", "throughput": 1031.56, "total_tokens": 4850888} {"current_steps": 53875, "total_steps": 76960, "loss": 0.3353, "lr": 1.2498036044845563e-05, "epoch": 14.000779625779625, "percentage": 70.0, "elapsed_time": "1:18:24", "remaining_time": "0:33:35", "throughput": 1031.2, "total_tokens": 4851176} {"current_steps": 53880, "total_steps": 76960, "loss": 0.0467, "lr": 1.2493126607086403e-05, "epoch": 14.002079002079002, "percentage": 70.01, "elapsed_time": "1:18:24", "remaining_time": "0:33:35", "throughput": 1031.2, "total_tokens": 4851576} {"current_steps": 53885, "total_steps": 76960, "loss": 0.1147, "lr": 1.2488217812567732e-05, "epoch": 14.003378378378379, "percentage": 70.02, "elapsed_time": "1:18:25", "remaining_time": "0:33:34", "throughput": 1031.19, "total_tokens": 4852024} {"current_steps": 53890, "total_steps": 76960, "loss": 0.3185, "lr": 1.2483309661542001e-05, "epoch": 14.004677754677754, "percentage": 70.02, "elapsed_time": "1:18:25", "remaining_time": "0:33:34", "throughput": 1031.21, "total_tokens": 4852520} {"current_steps": 53895, "total_steps": 76960, "loss": 0.128, "lr": 1.2478402154261653e-05, "epoch": 14.005977130977131, "percentage": 70.03, "elapsed_time": "1:18:26", "remaining_time": "0:33:34", "throughput": 1031.21, "total_tokens": 4852968} {"current_steps": 53900, "total_steps": 76960, "loss": 0.1943, "lr": 1.2473495290979073e-05, "epoch": 14.007276507276508, "percentage": 70.04, "elapsed_time": "1:18:26", "remaining_time": "0:33:33", "throughput": 1031.21, "total_tokens": 4853384} {"current_steps": 53905, "total_steps": 76960, "loss": 0.1906, "lr": 1.2468589071946632e-05, "epoch": 14.008575883575883, "percentage": 70.04, "elapsed_time": "1:18:26", "remaining_time": "0:33:33", "throughput": 1031.21, "total_tokens": 4853848} {"current_steps": 53910, "total_steps": 76960, "loss": 0.1348, "lr": 1.2463683497416672e-05, "epoch": 14.00987525987526, "percentage": 70.05, "elapsed_time": "1:18:27", "remaining_time": "0:33:32", "throughput": 1031.21, "total_tokens": 4854296} {"current_steps": 53915, "total_steps": 76960, "loss": 0.2186, "lr": 1.245877856764147e-05, "epoch": 14.011174636174637, "percentage": 70.06, "elapsed_time": "1:18:27", "remaining_time": "0:33:32", "throughput": 1031.21, "total_tokens": 4854712} {"current_steps": 53920, "total_steps": 76960, "loss": 0.2042, "lr": 1.2453874282873316e-05, "epoch": 14.012474012474012, "percentage": 70.06, "elapsed_time": "1:18:28", "remaining_time": "0:33:31", "throughput": 1031.21, "total_tokens": 4855160} {"current_steps": 53925, "total_steps": 76960, "loss": 0.1079, "lr": 1.2448970643364416e-05, "epoch": 14.013773388773389, "percentage": 70.07, "elapsed_time": "1:18:28", "remaining_time": "0:33:31", "throughput": 1031.22, "total_tokens": 4855640} {"current_steps": 53930, "total_steps": 76960, "loss": 0.272, "lr": 1.2444067649366992e-05, "epoch": 14.015072765072764, "percentage": 70.08, "elapsed_time": "1:18:29", "remaining_time": "0:33:30", "throughput": 1031.23, "total_tokens": 4856088} {"current_steps": 53935, "total_steps": 76960, "loss": 0.0849, "lr": 1.243916530113319e-05, "epoch": 14.016372141372141, "percentage": 70.08, "elapsed_time": "1:18:29", "remaining_time": "0:33:30", "throughput": 1031.23, "total_tokens": 4856536} {"current_steps": 53940, "total_steps": 76960, "loss": 0.2413, "lr": 1.2434263598915153e-05, "epoch": 14.017671517671518, "percentage": 70.09, "elapsed_time": "1:18:29", "remaining_time": "0:33:30", "throughput": 1031.23, "total_tokens": 4856968} {"current_steps": 53945, "total_steps": 76960, "loss": 0.1245, "lr": 1.2429362542964976e-05, "epoch": 14.018970893970893, "percentage": 70.09, "elapsed_time": "1:18:30", "remaining_time": "0:33:29", "throughput": 1031.23, "total_tokens": 4857400} {"current_steps": 53950, "total_steps": 76960, "loss": 0.1912, "lr": 1.242446213353474e-05, "epoch": 14.02027027027027, "percentage": 70.1, "elapsed_time": "1:18:30", "remaining_time": "0:33:29", "throughput": 1031.23, "total_tokens": 4857848} {"current_steps": 53955, "total_steps": 76960, "loss": 0.156, "lr": 1.2419562370876456e-05, "epoch": 14.021569646569647, "percentage": 70.11, "elapsed_time": "1:18:31", "remaining_time": "0:33:28", "throughput": 1031.24, "total_tokens": 4858312} {"current_steps": 53960, "total_steps": 76960, "loss": 0.2786, "lr": 1.241466325524214e-05, "epoch": 14.022869022869022, "percentage": 70.11, "elapsed_time": "1:18:31", "remaining_time": "0:33:28", "throughput": 1031.24, "total_tokens": 4858760} {"current_steps": 53965, "total_steps": 76960, "loss": 0.0379, "lr": 1.2409764786883754e-05, "epoch": 14.0241683991684, "percentage": 70.12, "elapsed_time": "1:18:31", "remaining_time": "0:33:27", "throughput": 1031.25, "total_tokens": 4859208} {"current_steps": 53970, "total_steps": 76960, "loss": 0.3601, "lr": 1.2404866966053218e-05, "epoch": 14.025467775467776, "percentage": 70.13, "elapsed_time": "1:18:32", "remaining_time": "0:33:27", "throughput": 1031.25, "total_tokens": 4859640} {"current_steps": 53975, "total_steps": 76960, "loss": 0.117, "lr": 1.2399969793002445e-05, "epoch": 14.026767151767151, "percentage": 70.13, "elapsed_time": "1:18:32", "remaining_time": "0:33:26", "throughput": 1031.26, "total_tokens": 4860136} {"current_steps": 53980, "total_steps": 76960, "loss": 0.1646, "lr": 1.2395073267983295e-05, "epoch": 14.028066528066528, "percentage": 70.14, "elapsed_time": "1:18:33", "remaining_time": "0:33:26", "throughput": 1031.26, "total_tokens": 4860536} {"current_steps": 53985, "total_steps": 76960, "loss": 0.0751, "lr": 1.2390177391247614e-05, "epoch": 14.029365904365905, "percentage": 70.15, "elapsed_time": "1:18:33", "remaining_time": "0:33:26", "throughput": 1031.26, "total_tokens": 4861000} {"current_steps": 53990, "total_steps": 76960, "loss": 0.3616, "lr": 1.2385282163047182e-05, "epoch": 14.03066528066528, "percentage": 70.15, "elapsed_time": "1:18:34", "remaining_time": "0:33:25", "throughput": 1031.27, "total_tokens": 4861464} {"current_steps": 53995, "total_steps": 76960, "loss": 0.0934, "lr": 1.2380387583633787e-05, "epoch": 14.031964656964657, "percentage": 70.16, "elapsed_time": "1:18:34", "remaining_time": "0:33:25", "throughput": 1031.27, "total_tokens": 4861912} {"current_steps": 54000, "total_steps": 76960, "loss": 0.0813, "lr": 1.237549365325914e-05, "epoch": 14.033264033264032, "percentage": 70.17, "elapsed_time": "1:18:34", "remaining_time": "0:33:24", "throughput": 1031.28, "total_tokens": 4862376} {"current_steps": 54005, "total_steps": 76960, "loss": 0.2254, "lr": 1.2370600372174949e-05, "epoch": 14.03456340956341, "percentage": 70.17, "elapsed_time": "1:18:35", "remaining_time": "0:33:24", "throughput": 1031.29, "total_tokens": 4862824} {"current_steps": 54010, "total_steps": 76960, "loss": 0.1288, "lr": 1.2365707740632882e-05, "epoch": 14.035862785862786, "percentage": 70.18, "elapsed_time": "1:18:35", "remaining_time": "0:33:23", "throughput": 1031.29, "total_tokens": 4863288} {"current_steps": 54015, "total_steps": 76960, "loss": 0.2121, "lr": 1.2360815758884583e-05, "epoch": 14.037162162162161, "percentage": 70.19, "elapsed_time": "1:18:36", "remaining_time": "0:33:23", "throughput": 1031.29, "total_tokens": 4863720} {"current_steps": 54020, "total_steps": 76960, "loss": 0.3636, "lr": 1.2355924427181628e-05, "epoch": 14.038461538461538, "percentage": 70.19, "elapsed_time": "1:18:36", "remaining_time": "0:33:22", "throughput": 1031.3, "total_tokens": 4864184} {"current_steps": 54025, "total_steps": 76960, "loss": 0.1657, "lr": 1.2351033745775606e-05, "epoch": 14.039760914760915, "percentage": 70.2, "elapsed_time": "1:18:36", "remaining_time": "0:33:22", "throughput": 1031.31, "total_tokens": 4864680} {"current_steps": 54030, "total_steps": 76960, "loss": 0.1428, "lr": 1.2346143714918038e-05, "epoch": 14.04106029106029, "percentage": 70.21, "elapsed_time": "1:18:37", "remaining_time": "0:33:22", "throughput": 1031.34, "total_tokens": 4865208} {"current_steps": 54035, "total_steps": 76960, "loss": 0.3363, "lr": 1.234125433486041e-05, "epoch": 14.042359667359667, "percentage": 70.21, "elapsed_time": "1:18:37", "remaining_time": "0:33:21", "throughput": 1031.33, "total_tokens": 4865608} {"current_steps": 54040, "total_steps": 76960, "loss": 0.2118, "lr": 1.2336365605854205e-05, "epoch": 14.043659043659044, "percentage": 70.22, "elapsed_time": "1:18:38", "remaining_time": "0:33:21", "throughput": 1031.33, "total_tokens": 4866040} {"current_steps": 54045, "total_steps": 76960, "loss": 0.2227, "lr": 1.2331477528150851e-05, "epoch": 14.04495841995842, "percentage": 70.22, "elapsed_time": "1:18:38", "remaining_time": "0:33:20", "throughput": 1031.33, "total_tokens": 4866456} {"current_steps": 54050, "total_steps": 76960, "loss": 0.1541, "lr": 1.2326590102001753e-05, "epoch": 14.046257796257796, "percentage": 70.23, "elapsed_time": "1:18:39", "remaining_time": "0:33:20", "throughput": 1031.33, "total_tokens": 4866920} {"current_steps": 54055, "total_steps": 76960, "loss": 0.3082, "lr": 1.232170332765826e-05, "epoch": 14.047557172557173, "percentage": 70.24, "elapsed_time": "1:18:39", "remaining_time": "0:33:19", "throughput": 1031.34, "total_tokens": 4867368} {"current_steps": 54060, "total_steps": 76960, "loss": 0.0639, "lr": 1.2316817205371722e-05, "epoch": 14.048856548856548, "percentage": 70.24, "elapsed_time": "1:18:39", "remaining_time": "0:33:19", "throughput": 1031.34, "total_tokens": 4867816} {"current_steps": 54065, "total_steps": 76960, "loss": 0.0308, "lr": 1.2311931735393417e-05, "epoch": 14.050155925155925, "percentage": 70.25, "elapsed_time": "1:18:40", "remaining_time": "0:33:18", "throughput": 1031.35, "total_tokens": 4868264} {"current_steps": 54070, "total_steps": 76960, "loss": 0.1428, "lr": 1.2307046917974632e-05, "epoch": 14.051455301455302, "percentage": 70.26, "elapsed_time": "1:18:40", "remaining_time": "0:33:18", "throughput": 1031.35, "total_tokens": 4868680} {"current_steps": 54075, "total_steps": 76960, "loss": 0.3188, "lr": 1.2302162753366575e-05, "epoch": 14.052754677754677, "percentage": 70.26, "elapsed_time": "1:18:41", "remaining_time": "0:33:18", "throughput": 1031.35, "total_tokens": 4869112} {"current_steps": 54080, "total_steps": 76960, "loss": 0.2976, "lr": 1.2297279241820455e-05, "epoch": 14.054054054054054, "percentage": 70.27, "elapsed_time": "1:18:41", "remaining_time": "0:33:17", "throughput": 1031.35, "total_tokens": 4869560} {"current_steps": 54085, "total_steps": 76960, "loss": 0.002, "lr": 1.2292396383587434e-05, "epoch": 14.05535343035343, "percentage": 70.28, "elapsed_time": "1:18:41", "remaining_time": "0:33:17", "throughput": 1031.35, "total_tokens": 4870008} {"current_steps": 54090, "total_steps": 76960, "loss": 0.0775, "lr": 1.2287514178918651e-05, "epoch": 14.056652806652806, "percentage": 70.28, "elapsed_time": "1:18:42", "remaining_time": "0:33:16", "throughput": 1031.35, "total_tokens": 4870424} {"current_steps": 54095, "total_steps": 76960, "loss": 0.0047, "lr": 1.2282632628065197e-05, "epoch": 14.057952182952183, "percentage": 70.29, "elapsed_time": "1:18:42", "remaining_time": "0:33:16", "throughput": 1031.36, "total_tokens": 4870872} {"current_steps": 54100, "total_steps": 76960, "loss": 0.4385, "lr": 1.2277751731278123e-05, "epoch": 14.059251559251559, "percentage": 70.3, "elapsed_time": "1:18:43", "remaining_time": "0:33:15", "throughput": 1031.37, "total_tokens": 4871352} {"current_steps": 54105, "total_steps": 76960, "loss": 0.3143, "lr": 1.2272871488808473e-05, "epoch": 14.060550935550935, "percentage": 70.3, "elapsed_time": "1:18:43", "remaining_time": "0:33:15", "throughput": 1031.37, "total_tokens": 4871800} {"current_steps": 54110, "total_steps": 76960, "loss": 0.3432, "lr": 1.226799190090723e-05, "epoch": 14.061850311850312, "percentage": 70.31, "elapsed_time": "1:18:44", "remaining_time": "0:33:14", "throughput": 1031.38, "total_tokens": 4872264} {"current_steps": 54115, "total_steps": 76960, "loss": 0.1115, "lr": 1.2263112967825364e-05, "epoch": 14.063149688149688, "percentage": 70.32, "elapsed_time": "1:18:44", "remaining_time": "0:33:14", "throughput": 1031.38, "total_tokens": 4872680} {"current_steps": 54120, "total_steps": 76960, "loss": 0.0722, "lr": 1.22582346898138e-05, "epoch": 14.064449064449065, "percentage": 70.32, "elapsed_time": "1:18:44", "remaining_time": "0:33:14", "throughput": 1031.39, "total_tokens": 4873160} {"current_steps": 54125, "total_steps": 76960, "loss": 0.1309, "lr": 1.2253357067123444e-05, "epoch": 14.065748440748441, "percentage": 70.33, "elapsed_time": "1:18:45", "remaining_time": "0:33:13", "throughput": 1031.38, "total_tokens": 4873576} {"current_steps": 54130, "total_steps": 76960, "loss": 0.3798, "lr": 1.2248480100005138e-05, "epoch": 14.067047817047817, "percentage": 70.34, "elapsed_time": "1:18:45", "remaining_time": "0:33:13", "throughput": 1031.39, "total_tokens": 4874040} {"current_steps": 54135, "total_steps": 76960, "loss": 0.5191, "lr": 1.2243603788709725e-05, "epoch": 14.068347193347194, "percentage": 70.34, "elapsed_time": "1:18:46", "remaining_time": "0:33:12", "throughput": 1031.39, "total_tokens": 4874472} {"current_steps": 54140, "total_steps": 76960, "loss": 0.2301, "lr": 1.2238728133487986e-05, "epoch": 14.06964656964657, "percentage": 70.35, "elapsed_time": "1:18:46", "remaining_time": "0:33:12", "throughput": 1031.4, "total_tokens": 4874920} {"current_steps": 54145, "total_steps": 76960, "loss": 0.0979, "lr": 1.2233853134590697e-05, "epoch": 14.070945945945946, "percentage": 70.35, "elapsed_time": "1:18:46", "remaining_time": "0:33:11", "throughput": 1031.4, "total_tokens": 4875384} {"current_steps": 54150, "total_steps": 76960, "loss": 0.0917, "lr": 1.2228978792268561e-05, "epoch": 14.072245322245323, "percentage": 70.36, "elapsed_time": "1:18:47", "remaining_time": "0:33:11", "throughput": 1031.4, "total_tokens": 4875800} {"current_steps": 54155, "total_steps": 76960, "loss": 0.373, "lr": 1.2224105106772282e-05, "epoch": 14.073544698544698, "percentage": 70.37, "elapsed_time": "1:18:47", "remaining_time": "0:33:10", "throughput": 1031.41, "total_tokens": 4876248} {"current_steps": 54160, "total_steps": 76960, "loss": 0.1949, "lr": 1.221923207835253e-05, "epoch": 14.074844074844075, "percentage": 70.37, "elapsed_time": "1:18:48", "remaining_time": "0:33:10", "throughput": 1031.41, "total_tokens": 4876712} {"current_steps": 54165, "total_steps": 76960, "loss": 0.1749, "lr": 1.221435970725991e-05, "epoch": 14.076143451143452, "percentage": 70.38, "elapsed_time": "1:18:48", "remaining_time": "0:33:10", "throughput": 1031.42, "total_tokens": 4877160} {"current_steps": 54170, "total_steps": 76960, "loss": 0.0194, "lr": 1.2209487993745025e-05, "epoch": 14.077442827442827, "percentage": 70.39, "elapsed_time": "1:18:49", "remaining_time": "0:33:09", "throughput": 1031.41, "total_tokens": 4877560} {"current_steps": 54175, "total_steps": 76960, "loss": 0.3709, "lr": 1.2204616938058422e-05, "epoch": 14.078742203742204, "percentage": 70.39, "elapsed_time": "1:18:49", "remaining_time": "0:33:09", "throughput": 1031.41, "total_tokens": 4877976} {"current_steps": 54180, "total_steps": 76960, "loss": 0.0126, "lr": 1.2199746540450641e-05, "epoch": 14.08004158004158, "percentage": 70.4, "elapsed_time": "1:18:49", "remaining_time": "0:33:08", "throughput": 1031.41, "total_tokens": 4878408} {"current_steps": 54185, "total_steps": 76960, "loss": 0.4351, "lr": 1.2194876801172148e-05, "epoch": 14.081340956340956, "percentage": 70.41, "elapsed_time": "1:18:50", "remaining_time": "0:33:08", "throughput": 1031.41, "total_tokens": 4878824} {"current_steps": 54190, "total_steps": 76960, "loss": 0.3283, "lr": 1.2190007720473409e-05, "epoch": 14.082640332640333, "percentage": 70.41, "elapsed_time": "1:18:50", "remaining_time": "0:33:07", "throughput": 1031.41, "total_tokens": 4879288} {"current_steps": 54195, "total_steps": 76960, "loss": 0.1149, "lr": 1.218513929860485e-05, "epoch": 14.08393970893971, "percentage": 70.42, "elapsed_time": "1:18:51", "remaining_time": "0:33:07", "throughput": 1031.42, "total_tokens": 4879736} {"current_steps": 54200, "total_steps": 76960, "loss": 0.3026, "lr": 1.2180271535816862e-05, "epoch": 14.085239085239085, "percentage": 70.43, "elapsed_time": "1:18:51", "remaining_time": "0:33:06", "throughput": 1031.42, "total_tokens": 4880184} {"current_steps": 54205, "total_steps": 76960, "loss": 0.3486, "lr": 1.2175404432359785e-05, "epoch": 14.086538461538462, "percentage": 70.43, "elapsed_time": "1:18:51", "remaining_time": "0:33:06", "throughput": 1031.42, "total_tokens": 4880616} {"current_steps": 54210, "total_steps": 76960, "loss": 0.1371, "lr": 1.2170537988483954e-05, "epoch": 14.087837837837839, "percentage": 70.44, "elapsed_time": "1:18:52", "remaining_time": "0:33:05", "throughput": 1031.43, "total_tokens": 4881064} {"current_steps": 54215, "total_steps": 76960, "loss": 0.3393, "lr": 1.2165672204439638e-05, "epoch": 14.089137214137214, "percentage": 70.45, "elapsed_time": "1:18:52", "remaining_time": "0:33:05", "throughput": 1031.43, "total_tokens": 4881512} {"current_steps": 54220, "total_steps": 76960, "loss": 0.2001, "lr": 1.2160807080477108e-05, "epoch": 14.09043659043659, "percentage": 70.45, "elapsed_time": "1:18:53", "remaining_time": "0:33:05", "throughput": 1031.44, "total_tokens": 4881976} {"current_steps": 54225, "total_steps": 76960, "loss": 0.2905, "lr": 1.215594261684656e-05, "epoch": 14.091735966735968, "percentage": 70.46, "elapsed_time": "1:18:53", "remaining_time": "0:33:04", "throughput": 1031.44, "total_tokens": 4882424} {"current_steps": 54230, "total_steps": 76960, "loss": 0.0686, "lr": 1.2151078813798194e-05, "epoch": 14.093035343035343, "percentage": 70.47, "elapsed_time": "1:18:53", "remaining_time": "0:33:04", "throughput": 1031.45, "total_tokens": 4882856} {"current_steps": 54235, "total_steps": 76960, "loss": 0.2296, "lr": 1.2146215671582161e-05, "epoch": 14.09433471933472, "percentage": 70.47, "elapsed_time": "1:18:54", "remaining_time": "0:33:03", "throughput": 1031.45, "total_tokens": 4883304} {"current_steps": 54240, "total_steps": 76960, "loss": 0.1054, "lr": 1.2141353190448565e-05, "epoch": 14.095634095634095, "percentage": 70.48, "elapsed_time": "1:18:54", "remaining_time": "0:33:03", "throughput": 1031.45, "total_tokens": 4883736} {"current_steps": 54245, "total_steps": 76960, "loss": 0.0091, "lr": 1.2136491370647505e-05, "epoch": 14.096933471933472, "percentage": 70.48, "elapsed_time": "1:18:55", "remaining_time": "0:33:02", "throughput": 1031.46, "total_tokens": 4884216} {"current_steps": 54250, "total_steps": 76960, "loss": 0.0374, "lr": 1.2131630212429007e-05, "epoch": 14.098232848232849, "percentage": 70.49, "elapsed_time": "1:18:55", "remaining_time": "0:33:02", "throughput": 1031.47, "total_tokens": 4884664} {"current_steps": 54255, "total_steps": 76960, "loss": 0.064, "lr": 1.2126769716043099e-05, "epoch": 14.099532224532224, "percentage": 70.5, "elapsed_time": "1:18:56", "remaining_time": "0:33:01", "throughput": 1031.46, "total_tokens": 4885080} {"current_steps": 54260, "total_steps": 76960, "loss": 0.3594, "lr": 1.2121909881739758e-05, "epoch": 14.1008316008316, "percentage": 70.5, "elapsed_time": "1:18:56", "remaining_time": "0:33:01", "throughput": 1031.46, "total_tokens": 4885512} {"current_steps": 54265, "total_steps": 76960, "loss": 0.0451, "lr": 1.211705070976894e-05, "epoch": 14.102130977130978, "percentage": 70.51, "elapsed_time": "1:18:56", "remaining_time": "0:33:01", "throughput": 1031.47, "total_tokens": 4885976} {"current_steps": 54270, "total_steps": 76960, "loss": 0.421, "lr": 1.211219220038054e-05, "epoch": 14.103430353430353, "percentage": 70.52, "elapsed_time": "1:18:57", "remaining_time": "0:33:00", "throughput": 1031.49, "total_tokens": 4886472} {"current_steps": 54275, "total_steps": 76960, "loss": 0.0599, "lr": 1.210733435382445e-05, "epoch": 14.10472972972973, "percentage": 70.52, "elapsed_time": "1:18:57", "remaining_time": "0:33:00", "throughput": 1031.49, "total_tokens": 4886904} {"current_steps": 54280, "total_steps": 76960, "loss": 0.3187, "lr": 1.2102477170350501e-05, "epoch": 14.106029106029107, "percentage": 70.53, "elapsed_time": "1:18:58", "remaining_time": "0:32:59", "throughput": 1031.49, "total_tokens": 4887368} {"current_steps": 54285, "total_steps": 76960, "loss": 0.1591, "lr": 1.2097620650208519e-05, "epoch": 14.107328482328482, "percentage": 70.54, "elapsed_time": "1:18:58", "remaining_time": "0:32:59", "throughput": 1031.51, "total_tokens": 4887880} {"current_steps": 54290, "total_steps": 76960, "loss": 0.1652, "lr": 1.2092764793648259e-05, "epoch": 14.108627858627859, "percentage": 70.54, "elapsed_time": "1:18:58", "remaining_time": "0:32:58", "throughput": 1031.52, "total_tokens": 4888328} {"current_steps": 54295, "total_steps": 76960, "loss": 0.247, "lr": 1.208790960091947e-05, "epoch": 14.109927234927236, "percentage": 70.55, "elapsed_time": "1:18:59", "remaining_time": "0:32:58", "throughput": 1031.52, "total_tokens": 4888792} {"current_steps": 54300, "total_steps": 76960, "loss": 0.1345, "lr": 1.2083055072271876e-05, "epoch": 14.111226611226611, "percentage": 70.56, "elapsed_time": "1:18:59", "remaining_time": "0:32:57", "throughput": 1031.53, "total_tokens": 4889256} {"current_steps": 54305, "total_steps": 76960, "loss": 0.2319, "lr": 1.2078201207955123e-05, "epoch": 14.112525987525988, "percentage": 70.56, "elapsed_time": "1:19:00", "remaining_time": "0:32:57", "throughput": 1031.53, "total_tokens": 4889688} {"current_steps": 54310, "total_steps": 76960, "loss": 0.0726, "lr": 1.2073348008218874e-05, "epoch": 14.113825363825363, "percentage": 70.57, "elapsed_time": "1:19:00", "remaining_time": "0:32:57", "throughput": 1031.54, "total_tokens": 4890168} {"current_steps": 54315, "total_steps": 76960, "loss": 0.1601, "lr": 1.2068495473312713e-05, "epoch": 14.11512474012474, "percentage": 70.58, "elapsed_time": "1:19:01", "remaining_time": "0:32:56", "throughput": 1031.54, "total_tokens": 4890616} {"current_steps": 54320, "total_steps": 76960, "loss": 0.1792, "lr": 1.206364360348623e-05, "epoch": 14.116424116424117, "percentage": 70.58, "elapsed_time": "1:19:01", "remaining_time": "0:32:56", "throughput": 1031.56, "total_tokens": 4891096} {"current_steps": 54325, "total_steps": 76960, "loss": 0.0847, "lr": 1.205879239898894e-05, "epoch": 14.117723492723492, "percentage": 70.59, "elapsed_time": "1:19:01", "remaining_time": "0:32:55", "throughput": 1031.56, "total_tokens": 4891544} {"current_steps": 54330, "total_steps": 76960, "loss": 0.1422, "lr": 1.2053941860070359e-05, "epoch": 14.119022869022869, "percentage": 70.6, "elapsed_time": "1:19:02", "remaining_time": "0:32:55", "throughput": 1031.56, "total_tokens": 4891976} {"current_steps": 54335, "total_steps": 76960, "loss": 0.2331, "lr": 1.2049091986979951e-05, "epoch": 14.120322245322246, "percentage": 70.6, "elapsed_time": "1:19:02", "remaining_time": "0:32:54", "throughput": 1031.56, "total_tokens": 4892408} {"current_steps": 54340, "total_steps": 76960, "loss": 0.3091, "lr": 1.2044242779967163e-05, "epoch": 14.121621621621621, "percentage": 70.61, "elapsed_time": "1:19:03", "remaining_time": "0:32:54", "throughput": 1031.56, "total_tokens": 4892856} {"current_steps": 54345, "total_steps": 76960, "loss": 0.154, "lr": 1.203939423928137e-05, "epoch": 14.122920997920998, "percentage": 70.61, "elapsed_time": "1:19:03", "remaining_time": "0:32:53", "throughput": 1031.57, "total_tokens": 4893320} {"current_steps": 54350, "total_steps": 76960, "loss": 0.0866, "lr": 1.2034546365171959e-05, "epoch": 14.124220374220375, "percentage": 70.62, "elapsed_time": "1:19:03", "remaining_time": "0:32:53", "throughput": 1031.58, "total_tokens": 4893784} {"current_steps": 54355, "total_steps": 76960, "loss": 0.2029, "lr": 1.2029699157888253e-05, "epoch": 14.12551975051975, "percentage": 70.63, "elapsed_time": "1:19:04", "remaining_time": "0:32:53", "throughput": 1031.58, "total_tokens": 4894232} {"current_steps": 54360, "total_steps": 76960, "loss": 0.2178, "lr": 1.2024852617679538e-05, "epoch": 14.126819126819127, "percentage": 70.63, "elapsed_time": "1:19:04", "remaining_time": "0:32:52", "throughput": 1031.6, "total_tokens": 4894712} {"current_steps": 54365, "total_steps": 76960, "loss": 0.0716, "lr": 1.2020006744795084e-05, "epoch": 14.128118503118504, "percentage": 70.64, "elapsed_time": "1:19:05", "remaining_time": "0:32:52", "throughput": 1031.61, "total_tokens": 4895192} {"current_steps": 54370, "total_steps": 76960, "loss": 0.0689, "lr": 1.2015161539484118e-05, "epoch": 14.129417879417879, "percentage": 70.65, "elapsed_time": "1:19:05", "remaining_time": "0:32:51", "throughput": 1031.62, "total_tokens": 4895672} {"current_steps": 54375, "total_steps": 76960, "loss": 0.1683, "lr": 1.2010317001995846e-05, "epoch": 14.130717255717256, "percentage": 70.65, "elapsed_time": "1:19:06", "remaining_time": "0:32:51", "throughput": 1031.63, "total_tokens": 4896152} {"current_steps": 54380, "total_steps": 76960, "loss": 0.3482, "lr": 1.200547313257941e-05, "epoch": 14.132016632016631, "percentage": 70.66, "elapsed_time": "1:19:06", "remaining_time": "0:32:50", "throughput": 1031.63, "total_tokens": 4896584} {"current_steps": 54385, "total_steps": 76960, "loss": 0.0137, "lr": 1.2000629931483947e-05, "epoch": 14.133316008316008, "percentage": 70.67, "elapsed_time": "1:19:06", "remaining_time": "0:32:50", "throughput": 1031.62, "total_tokens": 4896984} {"current_steps": 54390, "total_steps": 76960, "loss": 0.1266, "lr": 1.1995787398958536e-05, "epoch": 14.134615384615385, "percentage": 70.67, "elapsed_time": "1:19:07", "remaining_time": "0:32:49", "throughput": 1031.62, "total_tokens": 4897400} {"current_steps": 54395, "total_steps": 76960, "loss": 0.0311, "lr": 1.199094553525225e-05, "epoch": 14.13591476091476, "percentage": 70.68, "elapsed_time": "1:19:07", "remaining_time": "0:32:49", "throughput": 1031.62, "total_tokens": 4897848} {"current_steps": 54400, "total_steps": 76960, "loss": 0.0999, "lr": 1.1986104340614086e-05, "epoch": 14.137214137214137, "percentage": 70.69, "elapsed_time": "1:19:08", "remaining_time": "0:32:49", "throughput": 1031.62, "total_tokens": 4898280} {"current_steps": 54405, "total_steps": 76960, "loss": 0.3163, "lr": 1.1981263815293044e-05, "epoch": 14.138513513513514, "percentage": 70.69, "elapsed_time": "1:19:08", "remaining_time": "0:32:48", "throughput": 1031.63, "total_tokens": 4898728} {"current_steps": 54410, "total_steps": 76960, "loss": 0.0146, "lr": 1.1976423959538083e-05, "epoch": 14.13981288981289, "percentage": 70.7, "elapsed_time": "1:19:08", "remaining_time": "0:32:48", "throughput": 1031.64, "total_tokens": 4899192} {"current_steps": 54415, "total_steps": 76960, "loss": 0.3132, "lr": 1.1971584773598122e-05, "epoch": 14.141112266112266, "percentage": 70.71, "elapsed_time": "1:19:09", "remaining_time": "0:32:47", "throughput": 1031.64, "total_tokens": 4899624} {"current_steps": 54420, "total_steps": 76960, "loss": 0.1545, "lr": 1.1966746257722042e-05, "epoch": 14.142411642411643, "percentage": 70.71, "elapsed_time": "1:19:09", "remaining_time": "0:32:47", "throughput": 1031.64, "total_tokens": 4900072} {"current_steps": 54425, "total_steps": 76960, "loss": 0.3527, "lr": 1.1961908412158678e-05, "epoch": 14.143711018711018, "percentage": 70.72, "elapsed_time": "1:19:10", "remaining_time": "0:32:46", "throughput": 1031.65, "total_tokens": 4900520} {"current_steps": 54430, "total_steps": 76960, "loss": 0.1277, "lr": 1.1957071237156867e-05, "epoch": 14.145010395010395, "percentage": 70.73, "elapsed_time": "1:19:10", "remaining_time": "0:32:46", "throughput": 1031.66, "total_tokens": 4901000} {"current_steps": 54435, "total_steps": 76960, "loss": 0.1707, "lr": 1.195223473296537e-05, "epoch": 14.146309771309772, "percentage": 70.73, "elapsed_time": "1:19:11", "remaining_time": "0:32:45", "throughput": 1031.66, "total_tokens": 4901432} {"current_steps": 54440, "total_steps": 76960, "loss": 0.2763, "lr": 1.1947398899832942e-05, "epoch": 14.147609147609147, "percentage": 70.74, "elapsed_time": "1:19:11", "remaining_time": "0:32:45", "throughput": 1031.66, "total_tokens": 4901880} {"current_steps": 54445, "total_steps": 76960, "loss": 0.0382, "lr": 1.1942563738008298e-05, "epoch": 14.148908523908524, "percentage": 70.74, "elapsed_time": "1:19:11", "remaining_time": "0:32:45", "throughput": 1031.66, "total_tokens": 4902312} {"current_steps": 54450, "total_steps": 76960, "loss": 0.5015, "lr": 1.1937729247740117e-05, "epoch": 14.1502079002079, "percentage": 70.75, "elapsed_time": "1:19:12", "remaining_time": "0:32:44", "throughput": 1031.66, "total_tokens": 4902744} {"current_steps": 54455, "total_steps": 76960, "loss": 0.192, "lr": 1.193289542927703e-05, "epoch": 14.151507276507276, "percentage": 70.76, "elapsed_time": "1:19:12", "remaining_time": "0:32:44", "throughput": 1031.67, "total_tokens": 4903192} {"current_steps": 54460, "total_steps": 76960, "loss": 0.0833, "lr": 1.192806228286766e-05, "epoch": 14.152806652806653, "percentage": 70.76, "elapsed_time": "1:19:13", "remaining_time": "0:32:43", "throughput": 1031.67, "total_tokens": 4903624} {"current_steps": 54465, "total_steps": 76960, "loss": 0.1691, "lr": 1.1923229808760564e-05, "epoch": 14.154106029106028, "percentage": 70.77, "elapsed_time": "1:19:13", "remaining_time": "0:32:43", "throughput": 1031.68, "total_tokens": 4904104} {"current_steps": 54470, "total_steps": 76960, "loss": 0.2275, "lr": 1.1918398007204295e-05, "epoch": 14.155405405405405, "percentage": 70.78, "elapsed_time": "1:19:13", "remaining_time": "0:32:42", "throughput": 1031.69, "total_tokens": 4904584} {"current_steps": 54475, "total_steps": 76960, "loss": 0.1759, "lr": 1.1913566878447332e-05, "epoch": 14.156704781704782, "percentage": 70.78, "elapsed_time": "1:19:14", "remaining_time": "0:32:42", "throughput": 1031.69, "total_tokens": 4905016} {"current_steps": 54480, "total_steps": 76960, "loss": 0.4742, "lr": 1.1908736422738184e-05, "epoch": 14.158004158004157, "percentage": 70.79, "elapsed_time": "1:19:14", "remaining_time": "0:32:41", "throughput": 1031.7, "total_tokens": 4905496} {"current_steps": 54485, "total_steps": 76960, "loss": 0.1621, "lr": 1.1903906640325262e-05, "epoch": 14.159303534303534, "percentage": 70.8, "elapsed_time": "1:19:15", "remaining_time": "0:32:41", "throughput": 1031.7, "total_tokens": 4905912} {"current_steps": 54490, "total_steps": 76960, "loss": 0.1456, "lr": 1.1899077531456965e-05, "epoch": 14.160602910602911, "percentage": 70.8, "elapsed_time": "1:19:15", "remaining_time": "0:32:41", "throughput": 1031.7, "total_tokens": 4906344} {"current_steps": 54495, "total_steps": 76960, "loss": 0.173, "lr": 1.1894249096381668e-05, "epoch": 14.161902286902286, "percentage": 70.81, "elapsed_time": "1:19:16", "remaining_time": "0:32:40", "throughput": 1031.7, "total_tokens": 4906792} {"current_steps": 54500, "total_steps": 76960, "loss": 0.1825, "lr": 1.1889421335347692e-05, "epoch": 14.163201663201663, "percentage": 70.82, "elapsed_time": "1:19:16", "remaining_time": "0:32:40", "throughput": 1031.71, "total_tokens": 4907256} {"current_steps": 54505, "total_steps": 76960, "loss": 0.2729, "lr": 1.1884594248603336e-05, "epoch": 14.16450103950104, "percentage": 70.82, "elapsed_time": "1:19:16", "remaining_time": "0:32:39", "throughput": 1031.72, "total_tokens": 4907736} {"current_steps": 54510, "total_steps": 76960, "loss": 0.2532, "lr": 1.1879767836396865e-05, "epoch": 14.165800415800415, "percentage": 70.83, "elapsed_time": "1:19:17", "remaining_time": "0:32:39", "throughput": 1031.73, "total_tokens": 4908200} {"current_steps": 54515, "total_steps": 76960, "loss": 0.3775, "lr": 1.1874942098976515e-05, "epoch": 14.167099792099792, "percentage": 70.84, "elapsed_time": "1:19:17", "remaining_time": "0:32:38", "throughput": 1031.72, "total_tokens": 4908616} {"current_steps": 54520, "total_steps": 76960, "loss": 0.0945, "lr": 1.1870117036590458e-05, "epoch": 14.16839916839917, "percentage": 70.84, "elapsed_time": "1:19:18", "remaining_time": "0:32:38", "throughput": 1031.73, "total_tokens": 4909064} {"current_steps": 54525, "total_steps": 76960, "loss": 0.1807, "lr": 1.1865292649486872e-05, "epoch": 14.169698544698544, "percentage": 70.85, "elapsed_time": "1:19:18", "remaining_time": "0:32:37", "throughput": 1031.73, "total_tokens": 4909496} {"current_steps": 54530, "total_steps": 76960, "loss": 0.0055, "lr": 1.1860468937913863e-05, "epoch": 14.170997920997921, "percentage": 70.85, "elapsed_time": "1:19:18", "remaining_time": "0:32:37", "throughput": 1031.74, "total_tokens": 4909960} {"current_steps": 54535, "total_steps": 76960, "loss": 0.1734, "lr": 1.1855645902119534e-05, "epoch": 14.172297297297296, "percentage": 70.86, "elapsed_time": "1:19:19", "remaining_time": "0:32:37", "throughput": 1031.74, "total_tokens": 4910408} {"current_steps": 54540, "total_steps": 76960, "loss": 0.1748, "lr": 1.1850823542351921e-05, "epoch": 14.173596673596673, "percentage": 70.87, "elapsed_time": "1:19:19", "remaining_time": "0:32:36", "throughput": 1031.74, "total_tokens": 4910840} {"current_steps": 54545, "total_steps": 76960, "loss": 0.2456, "lr": 1.1846001858859054e-05, "epoch": 14.17489604989605, "percentage": 70.87, "elapsed_time": "1:19:20", "remaining_time": "0:32:36", "throughput": 1031.76, "total_tokens": 4911336} {"current_steps": 54550, "total_steps": 76960, "loss": 0.2503, "lr": 1.1841180851888922e-05, "epoch": 14.176195426195425, "percentage": 70.88, "elapsed_time": "1:19:20", "remaining_time": "0:32:35", "throughput": 1031.76, "total_tokens": 4911768} {"current_steps": 54555, "total_steps": 76960, "loss": 0.0746, "lr": 1.1836360521689457e-05, "epoch": 14.177494802494802, "percentage": 70.89, "elapsed_time": "1:19:21", "remaining_time": "0:32:35", "throughput": 1031.76, "total_tokens": 4912200} {"current_steps": 54560, "total_steps": 76960, "loss": 0.2983, "lr": 1.1831540868508595e-05, "epoch": 14.17879417879418, "percentage": 70.89, "elapsed_time": "1:19:21", "remaining_time": "0:32:34", "throughput": 1031.76, "total_tokens": 4912648} {"current_steps": 54565, "total_steps": 76960, "loss": 0.0044, "lr": 1.1826721892594193e-05, "epoch": 14.180093555093555, "percentage": 70.9, "elapsed_time": "1:19:21", "remaining_time": "0:32:34", "throughput": 1031.77, "total_tokens": 4913112} {"current_steps": 54570, "total_steps": 76960, "loss": 0.7243, "lr": 1.1821903594194115e-05, "epoch": 14.181392931392931, "percentage": 70.91, "elapsed_time": "1:19:22", "remaining_time": "0:32:33", "throughput": 1031.77, "total_tokens": 4913528} {"current_steps": 54575, "total_steps": 76960, "loss": 0.1812, "lr": 1.1817085973556152e-05, "epoch": 14.182692307692308, "percentage": 70.91, "elapsed_time": "1:19:22", "remaining_time": "0:32:33", "throughput": 1031.77, "total_tokens": 4913976} {"current_steps": 54580, "total_steps": 76960, "loss": 0.2728, "lr": 1.181226903092809e-05, "epoch": 14.183991683991684, "percentage": 70.92, "elapsed_time": "1:19:23", "remaining_time": "0:32:33", "throughput": 1031.77, "total_tokens": 4914408} {"current_steps": 54585, "total_steps": 76960, "loss": 0.0398, "lr": 1.1807452766557667e-05, "epoch": 14.18529106029106, "percentage": 70.93, "elapsed_time": "1:19:23", "remaining_time": "0:32:32", "throughput": 1031.78, "total_tokens": 4914888} {"current_steps": 54590, "total_steps": 76960, "loss": 0.1489, "lr": 1.18026371806926e-05, "epoch": 14.186590436590437, "percentage": 70.93, "elapsed_time": "1:19:23", "remaining_time": "0:32:32", "throughput": 1031.79, "total_tokens": 4915368} {"current_steps": 54595, "total_steps": 76960, "loss": 0.2344, "lr": 1.1797822273580537e-05, "epoch": 14.187889812889813, "percentage": 70.94, "elapsed_time": "1:19:24", "remaining_time": "0:32:31", "throughput": 1031.8, "total_tokens": 4915848} {"current_steps": 54600, "total_steps": 76960, "loss": 0.0106, "lr": 1.179300804546913e-05, "epoch": 14.18918918918919, "percentage": 70.95, "elapsed_time": "1:19:24", "remaining_time": "0:32:31", "throughput": 1031.8, "total_tokens": 4916280} {"current_steps": 54605, "total_steps": 76960, "loss": 0.4316, "lr": 1.178819449660597e-05, "epoch": 14.190488565488565, "percentage": 70.95, "elapsed_time": "1:19:25", "remaining_time": "0:32:30", "throughput": 1031.8, "total_tokens": 4916696} {"current_steps": 54610, "total_steps": 76960, "loss": 0.0835, "lr": 1.1783381627238632e-05, "epoch": 14.191787941787942, "percentage": 70.96, "elapsed_time": "1:19:25", "remaining_time": "0:32:30", "throughput": 1031.8, "total_tokens": 4917144} {"current_steps": 54615, "total_steps": 76960, "loss": 0.1009, "lr": 1.1778569437614634e-05, "epoch": 14.193087318087318, "percentage": 70.97, "elapsed_time": "1:19:25", "remaining_time": "0:32:29", "throughput": 1031.82, "total_tokens": 4917624} {"current_steps": 54620, "total_steps": 76960, "loss": 0.0134, "lr": 1.1773757927981473e-05, "epoch": 14.194386694386694, "percentage": 70.97, "elapsed_time": "1:19:26", "remaining_time": "0:32:29", "throughput": 1031.81, "total_tokens": 4918040} {"current_steps": 54625, "total_steps": 76960, "loss": 0.4459, "lr": 1.1768947098586628e-05, "epoch": 14.19568607068607, "percentage": 70.98, "elapsed_time": "1:19:26", "remaining_time": "0:32:29", "throughput": 1031.82, "total_tokens": 4918488} {"current_steps": 54630, "total_steps": 76960, "loss": 0.078, "lr": 1.17641369496775e-05, "epoch": 14.196985446985448, "percentage": 70.98, "elapsed_time": "1:19:27", "remaining_time": "0:32:28", "throughput": 1031.83, "total_tokens": 4918984} {"current_steps": 54635, "total_steps": 76960, "loss": 0.0706, "lr": 1.17593274815015e-05, "epoch": 14.198284823284823, "percentage": 70.99, "elapsed_time": "1:19:27", "remaining_time": "0:32:28", "throughput": 1031.83, "total_tokens": 4919416} {"current_steps": 54640, "total_steps": 76960, "loss": 0.2187, "lr": 1.1754518694305966e-05, "epoch": 14.1995841995842, "percentage": 71.0, "elapsed_time": "1:19:28", "remaining_time": "0:32:27", "throughput": 1031.83, "total_tokens": 4919832} {"current_steps": 54645, "total_steps": 76960, "loss": 0.1561, "lr": 1.1749710588338236e-05, "epoch": 14.200883575883577, "percentage": 71.0, "elapsed_time": "1:19:28", "remaining_time": "0:32:27", "throughput": 1031.84, "total_tokens": 4920296} {"current_steps": 54650, "total_steps": 76960, "loss": 0.3276, "lr": 1.1744903163845577e-05, "epoch": 14.202182952182952, "percentage": 71.01, "elapsed_time": "1:19:28", "remaining_time": "0:32:26", "throughput": 1031.84, "total_tokens": 4920728} {"current_steps": 54655, "total_steps": 76960, "loss": 0.0545, "lr": 1.1740096421075247e-05, "epoch": 14.203482328482329, "percentage": 71.02, "elapsed_time": "1:19:29", "remaining_time": "0:32:26", "throughput": 1031.84, "total_tokens": 4921192} {"current_steps": 54660, "total_steps": 76960, "loss": 0.3165, "lr": 1.1735290360274465e-05, "epoch": 14.204781704781706, "percentage": 71.02, "elapsed_time": "1:19:29", "remaining_time": "0:32:25", "throughput": 1031.85, "total_tokens": 4921656} {"current_steps": 54665, "total_steps": 76960, "loss": 0.0789, "lr": 1.1730484981690418e-05, "epoch": 14.20608108108108, "percentage": 71.03, "elapsed_time": "1:19:30", "remaining_time": "0:32:25", "throughput": 1031.87, "total_tokens": 4922152} {"current_steps": 54670, "total_steps": 76960, "loss": 0.3325, "lr": 1.1725680285570233e-05, "epoch": 14.207380457380458, "percentage": 71.04, "elapsed_time": "1:19:30", "remaining_time": "0:32:25", "throughput": 1031.88, "total_tokens": 4922632} {"current_steps": 54675, "total_steps": 76960, "loss": 0.0926, "lr": 1.1720876272161041e-05, "epoch": 14.208679833679835, "percentage": 71.04, "elapsed_time": "1:19:30", "remaining_time": "0:32:24", "throughput": 1031.87, "total_tokens": 4923032} {"current_steps": 54680, "total_steps": 76960, "loss": 0.2985, "lr": 1.1716072941709905e-05, "epoch": 14.20997920997921, "percentage": 71.05, "elapsed_time": "1:19:31", "remaining_time": "0:32:24", "throughput": 1031.88, "total_tokens": 4923496} {"current_steps": 54685, "total_steps": 76960, "loss": 0.2845, "lr": 1.1711270294463856e-05, "epoch": 14.211278586278587, "percentage": 71.06, "elapsed_time": "1:19:31", "remaining_time": "0:32:23", "throughput": 1031.88, "total_tokens": 4923960} {"current_steps": 54690, "total_steps": 76960, "loss": 0.1599, "lr": 1.1706468330669907e-05, "epoch": 14.212577962577962, "percentage": 71.06, "elapsed_time": "1:19:32", "remaining_time": "0:32:23", "throughput": 1031.9, "total_tokens": 4924456} {"current_steps": 54695, "total_steps": 76960, "loss": 0.2869, "lr": 1.170166705057503e-05, "epoch": 14.213877338877339, "percentage": 71.07, "elapsed_time": "1:19:32", "remaining_time": "0:32:22", "throughput": 1031.9, "total_tokens": 4924888} {"current_steps": 54700, "total_steps": 76960, "loss": 0.5704, "lr": 1.1696866454426166e-05, "epoch": 14.215176715176716, "percentage": 71.08, "elapsed_time": "1:19:33", "remaining_time": "0:32:22", "throughput": 1031.9, "total_tokens": 4925320} {"current_steps": 54705, "total_steps": 76960, "loss": 0.1949, "lr": 1.1692066542470201e-05, "epoch": 14.21647609147609, "percentage": 71.08, "elapsed_time": "1:19:33", "remaining_time": "0:32:21", "throughput": 1031.91, "total_tokens": 4925816} {"current_steps": 54710, "total_steps": 76960, "loss": 0.0762, "lr": 1.1687267314954011e-05, "epoch": 14.217775467775468, "percentage": 71.09, "elapsed_time": "1:19:33", "remaining_time": "0:32:21", "throughput": 1031.91, "total_tokens": 4926248} {"current_steps": 54715, "total_steps": 76960, "loss": 0.1632, "lr": 1.168246877212441e-05, "epoch": 14.219074844074845, "percentage": 71.1, "elapsed_time": "1:19:34", "remaining_time": "0:32:21", "throughput": 1031.91, "total_tokens": 4926680} {"current_steps": 54720, "total_steps": 76960, "loss": 0.1252, "lr": 1.1677670914228211e-05, "epoch": 14.22037422037422, "percentage": 71.1, "elapsed_time": "1:19:34", "remaining_time": "0:32:20", "throughput": 1031.92, "total_tokens": 4927128} {"current_steps": 54725, "total_steps": 76960, "loss": 0.0562, "lr": 1.1672873741512142e-05, "epoch": 14.221673596673597, "percentage": 71.11, "elapsed_time": "1:19:35", "remaining_time": "0:32:20", "throughput": 1031.92, "total_tokens": 4927592} {"current_steps": 54730, "total_steps": 76960, "loss": 0.3424, "lr": 1.1668077254222964e-05, "epoch": 14.222972972972974, "percentage": 71.11, "elapsed_time": "1:19:35", "remaining_time": "0:32:19", "throughput": 1031.92, "total_tokens": 4928008} {"current_steps": 54735, "total_steps": 76960, "loss": 0.1506, "lr": 1.166328145260734e-05, "epoch": 14.224272349272349, "percentage": 71.12, "elapsed_time": "1:19:35", "remaining_time": "0:32:19", "throughput": 1031.93, "total_tokens": 4928456} {"current_steps": 54740, "total_steps": 76960, "loss": 0.2104, "lr": 1.1658486336911936e-05, "epoch": 14.225571725571726, "percentage": 71.13, "elapsed_time": "1:19:36", "remaining_time": "0:32:18", "throughput": 1031.93, "total_tokens": 4928904} {"current_steps": 54745, "total_steps": 76960, "loss": 0.2187, "lr": 1.1653691907383362e-05, "epoch": 14.226871101871103, "percentage": 71.13, "elapsed_time": "1:19:36", "remaining_time": "0:32:18", "throughput": 1031.93, "total_tokens": 4929352} {"current_steps": 54750, "total_steps": 76960, "loss": 0.29, "lr": 1.1648898164268195e-05, "epoch": 14.228170478170478, "percentage": 71.14, "elapsed_time": "1:19:37", "remaining_time": "0:32:17", "throughput": 1031.94, "total_tokens": 4929832} {"current_steps": 54755, "total_steps": 76960, "loss": 0.3011, "lr": 1.1644105107812986e-05, "epoch": 14.229469854469855, "percentage": 71.15, "elapsed_time": "1:19:37", "remaining_time": "0:32:17", "throughput": 1031.95, "total_tokens": 4930296} {"current_steps": 54760, "total_steps": 76960, "loss": 0.2057, "lr": 1.1639312738264249e-05, "epoch": 14.23076923076923, "percentage": 71.15, "elapsed_time": "1:19:38", "remaining_time": "0:32:17", "throughput": 1031.95, "total_tokens": 4930728} {"current_steps": 54765, "total_steps": 76960, "loss": 0.3294, "lr": 1.163452105586847e-05, "epoch": 14.232068607068607, "percentage": 71.16, "elapsed_time": "1:19:38", "remaining_time": "0:32:16", "throughput": 1031.96, "total_tokens": 4931176} {"current_steps": 54770, "total_steps": 76960, "loss": 0.3236, "lr": 1.1629730060872069e-05, "epoch": 14.233367983367984, "percentage": 71.17, "elapsed_time": "1:19:38", "remaining_time": "0:32:16", "throughput": 1031.95, "total_tokens": 4931592} {"current_steps": 54775, "total_steps": 76960, "loss": 0.207, "lr": 1.1624939753521468e-05, "epoch": 14.234667359667359, "percentage": 71.17, "elapsed_time": "1:19:39", "remaining_time": "0:32:15", "throughput": 1031.97, "total_tokens": 4932088} {"current_steps": 54780, "total_steps": 76960, "loss": 0.1053, "lr": 1.1620150134063026e-05, "epoch": 14.235966735966736, "percentage": 71.18, "elapsed_time": "1:19:39", "remaining_time": "0:32:15", "throughput": 1031.97, "total_tokens": 4932552} {"current_steps": 54785, "total_steps": 76960, "loss": 0.0152, "lr": 1.1615361202743088e-05, "epoch": 14.237266112266113, "percentage": 71.19, "elapsed_time": "1:19:40", "remaining_time": "0:32:14", "throughput": 1031.98, "total_tokens": 4933000} {"current_steps": 54790, "total_steps": 76960, "loss": 0.5301, "lr": 1.161057295980794e-05, "epoch": 14.238565488565488, "percentage": 71.19, "elapsed_time": "1:19:40", "remaining_time": "0:32:14", "throughput": 1031.98, "total_tokens": 4933448} {"current_steps": 54795, "total_steps": 76960, "loss": 0.3307, "lr": 1.1605785405503854e-05, "epoch": 14.239864864864865, "percentage": 71.2, "elapsed_time": "1:19:40", "remaining_time": "0:32:13", "throughput": 1031.99, "total_tokens": 4933912} {"current_steps": 54800, "total_steps": 76960, "loss": 0.1542, "lr": 1.160099854007706e-05, "epoch": 14.241164241164242, "percentage": 71.21, "elapsed_time": "1:19:41", "remaining_time": "0:32:13", "throughput": 1032.0, "total_tokens": 4934376} {"current_steps": 54805, "total_steps": 76960, "loss": 0.1316, "lr": 1.159621236377376e-05, "epoch": 14.242463617463617, "percentage": 71.21, "elapsed_time": "1:19:41", "remaining_time": "0:32:13", "throughput": 1032.0, "total_tokens": 4934824} {"current_steps": 54810, "total_steps": 76960, "loss": 0.2234, "lr": 1.1591426876840098e-05, "epoch": 14.243762993762994, "percentage": 71.22, "elapsed_time": "1:19:42", "remaining_time": "0:32:12", "throughput": 1032.0, "total_tokens": 4935272} {"current_steps": 54815, "total_steps": 76960, "loss": 0.1276, "lr": 1.1586642079522189e-05, "epoch": 14.24506237006237, "percentage": 71.23, "elapsed_time": "1:19:42", "remaining_time": "0:32:12", "throughput": 1032.02, "total_tokens": 4935752} {"current_steps": 54820, "total_steps": 76960, "loss": 0.0753, "lr": 1.1581857972066141e-05, "epoch": 14.246361746361746, "percentage": 71.23, "elapsed_time": "1:19:43", "remaining_time": "0:32:11", "throughput": 1032.03, "total_tokens": 4936248} {"current_steps": 54825, "total_steps": 76960, "loss": 0.1669, "lr": 1.1577074554717984e-05, "epoch": 14.247661122661123, "percentage": 71.24, "elapsed_time": "1:19:43", "remaining_time": "0:32:11", "throughput": 1032.04, "total_tokens": 4936712} {"current_steps": 54830, "total_steps": 76960, "loss": 0.1252, "lr": 1.1572291827723743e-05, "epoch": 14.248960498960498, "percentage": 71.24, "elapsed_time": "1:19:43", "remaining_time": "0:32:10", "throughput": 1032.04, "total_tokens": 4937160} {"current_steps": 54835, "total_steps": 76960, "loss": 0.0419, "lr": 1.1567509791329401e-05, "epoch": 14.250259875259875, "percentage": 71.25, "elapsed_time": "1:19:44", "remaining_time": "0:32:10", "throughput": 1032.04, "total_tokens": 4937608} {"current_steps": 54840, "total_steps": 76960, "loss": 0.1525, "lr": 1.156272844578091e-05, "epoch": 14.251559251559252, "percentage": 71.26, "elapsed_time": "1:19:44", "remaining_time": "0:32:09", "throughput": 1032.05, "total_tokens": 4938072} {"current_steps": 54845, "total_steps": 76960, "loss": 0.0556, "lr": 1.1557947791324161e-05, "epoch": 14.252858627858627, "percentage": 71.26, "elapsed_time": "1:19:45", "remaining_time": "0:32:09", "throughput": 1032.06, "total_tokens": 4938520} {"current_steps": 54850, "total_steps": 76960, "loss": 0.241, "lr": 1.1553167828205044e-05, "epoch": 14.254158004158004, "percentage": 71.27, "elapsed_time": "1:19:45", "remaining_time": "0:32:09", "throughput": 1032.07, "total_tokens": 4939000} {"current_steps": 54855, "total_steps": 76960, "loss": 0.2495, "lr": 1.1548388556669382e-05, "epoch": 14.255457380457381, "percentage": 71.28, "elapsed_time": "1:19:45", "remaining_time": "0:32:08", "throughput": 1032.07, "total_tokens": 4939448} {"current_steps": 54860, "total_steps": 76960, "loss": 0.1978, "lr": 1.1543609976962994e-05, "epoch": 14.256756756756756, "percentage": 71.28, "elapsed_time": "1:19:46", "remaining_time": "0:32:08", "throughput": 1032.07, "total_tokens": 4939896} {"current_steps": 54865, "total_steps": 76960, "loss": 0.2739, "lr": 1.1538832089331628e-05, "epoch": 14.258056133056133, "percentage": 71.29, "elapsed_time": "1:19:46", "remaining_time": "0:32:07", "throughput": 1032.08, "total_tokens": 4940344} {"current_steps": 54870, "total_steps": 76960, "loss": 0.2601, "lr": 1.1534054894021027e-05, "epoch": 14.25935550935551, "percentage": 71.3, "elapsed_time": "1:19:47", "remaining_time": "0:32:07", "throughput": 1032.08, "total_tokens": 4940776} {"current_steps": 54875, "total_steps": 76960, "loss": 0.0485, "lr": 1.1529278391276893e-05, "epoch": 14.260654885654885, "percentage": 71.3, "elapsed_time": "1:19:47", "remaining_time": "0:32:06", "throughput": 1032.07, "total_tokens": 4941192} {"current_steps": 54880, "total_steps": 76960, "loss": 0.1894, "lr": 1.152450258134487e-05, "epoch": 14.261954261954262, "percentage": 71.31, "elapsed_time": "1:19:48", "remaining_time": "0:32:06", "throughput": 1032.08, "total_tokens": 4941624} {"current_steps": 54885, "total_steps": 76960, "loss": 0.0925, "lr": 1.1519727464470601e-05, "epoch": 14.263253638253639, "percentage": 71.32, "elapsed_time": "1:19:48", "remaining_time": "0:32:05", "throughput": 1032.08, "total_tokens": 4942072} {"current_steps": 54890, "total_steps": 76960, "loss": 0.0347, "lr": 1.1514953040899657e-05, "epoch": 14.264553014553014, "percentage": 71.32, "elapsed_time": "1:19:48", "remaining_time": "0:32:05", "throughput": 1032.08, "total_tokens": 4942520} {"current_steps": 54895, "total_steps": 76960, "loss": 0.3623, "lr": 1.1510179310877603e-05, "epoch": 14.265852390852391, "percentage": 71.33, "elapsed_time": "1:19:49", "remaining_time": "0:32:05", "throughput": 1032.09, "total_tokens": 4942984} {"current_steps": 54900, "total_steps": 76960, "loss": 0.2599, "lr": 1.1505406274649947e-05, "epoch": 14.267151767151766, "percentage": 71.34, "elapsed_time": "1:19:49", "remaining_time": "0:32:04", "throughput": 1032.09, "total_tokens": 4943432} {"current_steps": 54905, "total_steps": 76960, "loss": 0.0215, "lr": 1.1500633932462175e-05, "epoch": 14.268451143451143, "percentage": 71.34, "elapsed_time": "1:19:50", "remaining_time": "0:32:04", "throughput": 1032.1, "total_tokens": 4943880} {"current_steps": 54910, "total_steps": 76960, "loss": 0.1273, "lr": 1.1495862284559733e-05, "epoch": 14.26975051975052, "percentage": 71.35, "elapsed_time": "1:19:50", "remaining_time": "0:32:03", "throughput": 1032.1, "total_tokens": 4944328} {"current_steps": 54915, "total_steps": 76960, "loss": 0.0784, "lr": 1.1491091331188046e-05, "epoch": 14.271049896049895, "percentage": 71.36, "elapsed_time": "1:19:50", "remaining_time": "0:32:03", "throughput": 1032.11, "total_tokens": 4944776} {"current_steps": 54920, "total_steps": 76960, "loss": 0.2035, "lr": 1.1486321072592463e-05, "epoch": 14.272349272349272, "percentage": 71.36, "elapsed_time": "1:19:51", "remaining_time": "0:32:02", "throughput": 1032.11, "total_tokens": 4945224} {"current_steps": 54925, "total_steps": 76960, "loss": 0.39, "lr": 1.1481551509018346e-05, "epoch": 14.27364864864865, "percentage": 71.37, "elapsed_time": "1:19:51", "remaining_time": "0:32:02", "throughput": 1032.11, "total_tokens": 4945672} {"current_steps": 54930, "total_steps": 76960, "loss": 0.3978, "lr": 1.1476782640710975e-05, "epoch": 14.274948024948024, "percentage": 71.37, "elapsed_time": "1:19:52", "remaining_time": "0:32:01", "throughput": 1032.11, "total_tokens": 4946088} {"current_steps": 54935, "total_steps": 76960, "loss": 0.4211, "lr": 1.1472014467915643e-05, "epoch": 14.276247401247401, "percentage": 71.38, "elapsed_time": "1:19:52", "remaining_time": "0:32:01", "throughput": 1032.12, "total_tokens": 4946552} {"current_steps": 54940, "total_steps": 76960, "loss": 0.0947, "lr": 1.1467246990877558e-05, "epoch": 14.277546777546778, "percentage": 71.39, "elapsed_time": "1:19:53", "remaining_time": "0:32:01", "throughput": 1032.12, "total_tokens": 4946984} {"current_steps": 54945, "total_steps": 76960, "loss": 0.1477, "lr": 1.1462480209841928e-05, "epoch": 14.278846153846153, "percentage": 71.39, "elapsed_time": "1:19:53", "remaining_time": "0:32:00", "throughput": 1032.14, "total_tokens": 4947496} {"current_steps": 54950, "total_steps": 76960, "loss": 0.4159, "lr": 1.145771412505392e-05, "epoch": 14.28014553014553, "percentage": 71.4, "elapsed_time": "1:19:53", "remaining_time": "0:32:00", "throughput": 1032.14, "total_tokens": 4947944} {"current_steps": 54955, "total_steps": 76960, "loss": 0.1696, "lr": 1.1452948736758642e-05, "epoch": 14.281444906444907, "percentage": 71.41, "elapsed_time": "1:19:54", "remaining_time": "0:31:59", "throughput": 1032.15, "total_tokens": 4948408} {"current_steps": 54960, "total_steps": 76960, "loss": 0.1276, "lr": 1.14481840452012e-05, "epoch": 14.282744282744282, "percentage": 71.41, "elapsed_time": "1:19:54", "remaining_time": "0:31:59", "throughput": 1032.15, "total_tokens": 4948856} {"current_steps": 54965, "total_steps": 76960, "loss": 0.3439, "lr": 1.1443420050626625e-05, "epoch": 14.28404365904366, "percentage": 71.42, "elapsed_time": "1:19:55", "remaining_time": "0:31:58", "throughput": 1032.15, "total_tokens": 4949288} {"current_steps": 54970, "total_steps": 76960, "loss": 0.2791, "lr": 1.1438656753279958e-05, "epoch": 14.285343035343036, "percentage": 71.43, "elapsed_time": "1:19:55", "remaining_time": "0:31:58", "throughput": 1032.16, "total_tokens": 4949768} {"current_steps": 54975, "total_steps": 76960, "loss": 0.2949, "lr": 1.143389415340615e-05, "epoch": 14.286642411642411, "percentage": 71.43, "elapsed_time": "1:19:55", "remaining_time": "0:31:57", "throughput": 1032.16, "total_tokens": 4950200} {"current_steps": 54980, "total_steps": 76960, "loss": 0.0291, "lr": 1.142913225125018e-05, "epoch": 14.287941787941788, "percentage": 71.44, "elapsed_time": "1:19:56", "remaining_time": "0:31:57", "throughput": 1032.17, "total_tokens": 4950664} {"current_steps": 54985, "total_steps": 76960, "loss": 0.044, "lr": 1.1424371047056933e-05, "epoch": 14.289241164241163, "percentage": 71.45, "elapsed_time": "1:19:56", "remaining_time": "0:31:57", "throughput": 1032.17, "total_tokens": 4951096} {"current_steps": 54990, "total_steps": 76960, "loss": 0.0805, "lr": 1.1419610541071301e-05, "epoch": 14.29054054054054, "percentage": 71.45, "elapsed_time": "1:19:57", "remaining_time": "0:31:56", "throughput": 1032.17, "total_tokens": 4951528} {"current_steps": 54995, "total_steps": 76960, "loss": 0.1336, "lr": 1.1414850733538101e-05, "epoch": 14.291839916839917, "percentage": 71.46, "elapsed_time": "1:19:57", "remaining_time": "0:31:56", "throughput": 1032.17, "total_tokens": 4951960} {"current_steps": 55000, "total_steps": 76960, "loss": 0.2438, "lr": 1.1410091624702155e-05, "epoch": 14.293139293139292, "percentage": 71.47, "elapsed_time": "1:19:58", "remaining_time": "0:31:55", "throughput": 1032.18, "total_tokens": 4952424} {"current_steps": 55005, "total_steps": 76960, "loss": 0.2543, "lr": 1.1405333214808209e-05, "epoch": 14.29443866943867, "percentage": 71.47, "elapsed_time": "1:19:58", "remaining_time": "0:31:55", "throughput": 1032.18, "total_tokens": 4952840} {"current_steps": 55010, "total_steps": 76960, "loss": 0.0309, "lr": 1.1400575504101e-05, "epoch": 14.295738045738046, "percentage": 71.48, "elapsed_time": "1:19:58", "remaining_time": "0:31:54", "throughput": 1032.18, "total_tokens": 4953288} {"current_steps": 55015, "total_steps": 76960, "loss": 0.4379, "lr": 1.139581849282523e-05, "epoch": 14.297037422037421, "percentage": 71.49, "elapsed_time": "1:19:59", "remaining_time": "0:31:54", "throughput": 1032.18, "total_tokens": 4953704} {"current_steps": 55020, "total_steps": 76960, "loss": 0.2113, "lr": 1.1391062181225545e-05, "epoch": 14.298336798336798, "percentage": 71.49, "elapsed_time": "1:19:59", "remaining_time": "0:31:53", "throughput": 1032.19, "total_tokens": 4954200} {"current_steps": 55025, "total_steps": 76960, "loss": 0.108, "lr": 1.138630656954658e-05, "epoch": 14.299636174636175, "percentage": 71.5, "elapsed_time": "1:20:00", "remaining_time": "0:31:53", "throughput": 1032.2, "total_tokens": 4954664} {"current_steps": 55030, "total_steps": 76960, "loss": 0.1815, "lr": 1.1381551658032899e-05, "epoch": 14.30093555093555, "percentage": 71.5, "elapsed_time": "1:20:00", "remaining_time": "0:31:53", "throughput": 1032.2, "total_tokens": 4955080} {"current_steps": 55035, "total_steps": 76960, "loss": 0.0256, "lr": 1.1376797446929077e-05, "epoch": 14.302234927234927, "percentage": 71.51, "elapsed_time": "1:20:00", "remaining_time": "0:31:52", "throughput": 1032.2, "total_tokens": 4955528} {"current_steps": 55040, "total_steps": 76960, "loss": 0.1845, "lr": 1.1372043936479606e-05, "epoch": 14.303534303534304, "percentage": 71.52, "elapsed_time": "1:20:01", "remaining_time": "0:31:52", "throughput": 1032.2, "total_tokens": 4955960} {"current_steps": 55045, "total_steps": 76960, "loss": 0.1956, "lr": 1.1367291126928976e-05, "epoch": 14.30483367983368, "percentage": 71.52, "elapsed_time": "1:20:01", "remaining_time": "0:31:51", "throughput": 1032.21, "total_tokens": 4956424} {"current_steps": 55050, "total_steps": 76960, "loss": 0.0178, "lr": 1.136253901852162e-05, "epoch": 14.306133056133056, "percentage": 71.53, "elapsed_time": "1:20:02", "remaining_time": "0:31:51", "throughput": 1032.21, "total_tokens": 4956840} {"current_steps": 55055, "total_steps": 76960, "loss": 0.1978, "lr": 1.1357787611501961e-05, "epoch": 14.307432432432432, "percentage": 71.54, "elapsed_time": "1:20:02", "remaining_time": "0:31:50", "throughput": 1032.21, "total_tokens": 4957272} {"current_steps": 55060, "total_steps": 76960, "loss": 0.3809, "lr": 1.1353036906114347e-05, "epoch": 14.308731808731808, "percentage": 71.54, "elapsed_time": "1:20:03", "remaining_time": "0:31:50", "throughput": 1032.21, "total_tokens": 4957720} {"current_steps": 55065, "total_steps": 76960, "loss": 0.3269, "lr": 1.1348286902603131e-05, "epoch": 14.310031185031185, "percentage": 71.55, "elapsed_time": "1:20:03", "remaining_time": "0:31:49", "throughput": 1032.21, "total_tokens": 4958152} {"current_steps": 55070, "total_steps": 76960, "loss": 0.1651, "lr": 1.1343537601212597e-05, "epoch": 14.31133056133056, "percentage": 71.56, "elapsed_time": "1:20:03", "remaining_time": "0:31:49", "throughput": 1032.21, "total_tokens": 4958584} {"current_steps": 55075, "total_steps": 76960, "loss": 0.0814, "lr": 1.1338789002187002e-05, "epoch": 14.312629937629938, "percentage": 71.56, "elapsed_time": "1:20:04", "remaining_time": "0:31:49", "throughput": 1032.22, "total_tokens": 4959048} {"current_steps": 55080, "total_steps": 76960, "loss": 0.3224, "lr": 1.1334041105770579e-05, "epoch": 14.313929313929314, "percentage": 71.57, "elapsed_time": "1:20:04", "remaining_time": "0:31:48", "throughput": 1032.22, "total_tokens": 4959480} {"current_steps": 55085, "total_steps": 76960, "loss": 0.1216, "lr": 1.1329293912207517e-05, "epoch": 14.31522869022869, "percentage": 71.58, "elapsed_time": "1:20:05", "remaining_time": "0:31:48", "throughput": 1032.23, "total_tokens": 4959928} {"current_steps": 55090, "total_steps": 76960, "loss": 0.0708, "lr": 1.1324547421741973e-05, "epoch": 14.316528066528067, "percentage": 71.58, "elapsed_time": "1:20:05", "remaining_time": "0:31:47", "throughput": 1032.24, "total_tokens": 4960408} {"current_steps": 55095, "total_steps": 76960, "loss": 0.0768, "lr": 1.1319801634618052e-05, "epoch": 14.317827442827443, "percentage": 71.59, "elapsed_time": "1:20:05", "remaining_time": "0:31:47", "throughput": 1032.24, "total_tokens": 4960840} {"current_steps": 55100, "total_steps": 76960, "loss": 0.1543, "lr": 1.131505655107985e-05, "epoch": 14.319126819126819, "percentage": 71.6, "elapsed_time": "1:20:06", "remaining_time": "0:31:46", "throughput": 1032.24, "total_tokens": 4961256} {"current_steps": 55105, "total_steps": 76960, "loss": 0.1519, "lr": 1.1310312171371393e-05, "epoch": 14.320426195426196, "percentage": 71.6, "elapsed_time": "1:20:06", "remaining_time": "0:31:46", "throughput": 1032.24, "total_tokens": 4961688} {"current_steps": 55110, "total_steps": 76960, "loss": 0.127, "lr": 1.1305568495736705e-05, "epoch": 14.321725571725572, "percentage": 71.61, "elapsed_time": "1:20:07", "remaining_time": "0:31:45", "throughput": 1032.24, "total_tokens": 4962152} {"current_steps": 55115, "total_steps": 76960, "loss": 0.0613, "lr": 1.1300825524419741e-05, "epoch": 14.323024948024948, "percentage": 71.62, "elapsed_time": "1:20:07", "remaining_time": "0:31:45", "throughput": 1032.25, "total_tokens": 4962600} {"current_steps": 55120, "total_steps": 76960, "loss": 0.0473, "lr": 1.129608325766445e-05, "epoch": 14.324324324324325, "percentage": 71.62, "elapsed_time": "1:20:07", "remaining_time": "0:31:45", "throughput": 1032.24, "total_tokens": 4963016} {"current_steps": 55125, "total_steps": 76960, "loss": 0.1422, "lr": 1.1291341695714725e-05, "epoch": 14.325623700623701, "percentage": 71.63, "elapsed_time": "1:20:08", "remaining_time": "0:31:44", "throughput": 1032.24, "total_tokens": 4963432} {"current_steps": 55130, "total_steps": 76960, "loss": 0.0015, "lr": 1.128660083881444e-05, "epoch": 14.326923076923077, "percentage": 71.63, "elapsed_time": "1:20:08", "remaining_time": "0:31:44", "throughput": 1032.24, "total_tokens": 4963864} {"current_steps": 55135, "total_steps": 76960, "loss": 0.0503, "lr": 1.1281860687207414e-05, "epoch": 14.328222453222454, "percentage": 71.64, "elapsed_time": "1:20:09", "remaining_time": "0:31:43", "throughput": 1032.25, "total_tokens": 4964328} {"current_steps": 55140, "total_steps": 76960, "loss": 0.241, "lr": 1.1277121241137429e-05, "epoch": 14.329521829521829, "percentage": 71.65, "elapsed_time": "1:20:09", "remaining_time": "0:31:43", "throughput": 1032.25, "total_tokens": 4964776} {"current_steps": 55145, "total_steps": 76960, "loss": 0.1562, "lr": 1.1272382500848256e-05, "epoch": 14.330821205821206, "percentage": 71.65, "elapsed_time": "1:20:10", "remaining_time": "0:31:42", "throughput": 1032.26, "total_tokens": 4965224} {"current_steps": 55150, "total_steps": 76960, "loss": 0.032, "lr": 1.1267644466583593e-05, "epoch": 14.332120582120583, "percentage": 71.66, "elapsed_time": "1:20:10", "remaining_time": "0:31:42", "throughput": 1032.26, "total_tokens": 4965656} {"current_steps": 55155, "total_steps": 76960, "loss": 0.1622, "lr": 1.1262907138587134e-05, "epoch": 14.333419958419958, "percentage": 71.67, "elapsed_time": "1:20:10", "remaining_time": "0:31:41", "throughput": 1032.26, "total_tokens": 4966088} {"current_steps": 55160, "total_steps": 76960, "loss": 0.1592, "lr": 1.1258170517102523e-05, "epoch": 14.334719334719335, "percentage": 71.67, "elapsed_time": "1:20:11", "remaining_time": "0:31:41", "throughput": 1032.27, "total_tokens": 4966552} {"current_steps": 55165, "total_steps": 76960, "loss": 0.4322, "lr": 1.1253434602373379e-05, "epoch": 14.336018711018712, "percentage": 71.68, "elapsed_time": "1:20:11", "remaining_time": "0:31:41", "throughput": 1032.28, "total_tokens": 4967032} {"current_steps": 55170, "total_steps": 76960, "loss": 0.2444, "lr": 1.1248699394643255e-05, "epoch": 14.337318087318087, "percentage": 71.69, "elapsed_time": "1:20:12", "remaining_time": "0:31:40", "throughput": 1032.28, "total_tokens": 4967496} {"current_steps": 55175, "total_steps": 76960, "loss": 0.2453, "lr": 1.1243964894155707e-05, "epoch": 14.338617463617464, "percentage": 71.69, "elapsed_time": "1:20:12", "remaining_time": "0:31:40", "throughput": 1032.29, "total_tokens": 4967928} {"current_steps": 55180, "total_steps": 76960, "loss": 0.3627, "lr": 1.1239231101154213e-05, "epoch": 14.33991683991684, "percentage": 71.7, "elapsed_time": "1:20:12", "remaining_time": "0:31:39", "throughput": 1032.3, "total_tokens": 4968424} {"current_steps": 55185, "total_steps": 76960, "loss": 0.3512, "lr": 1.1234498015882261e-05, "epoch": 14.341216216216216, "percentage": 71.71, "elapsed_time": "1:20:13", "remaining_time": "0:31:39", "throughput": 1032.3, "total_tokens": 4968872} {"current_steps": 55190, "total_steps": 76960, "loss": 0.0748, "lr": 1.1229765638583253e-05, "epoch": 14.342515592515593, "percentage": 71.71, "elapsed_time": "1:20:13", "remaining_time": "0:31:38", "throughput": 1032.3, "total_tokens": 4969304} {"current_steps": 55195, "total_steps": 76960, "loss": 0.1231, "lr": 1.1225033969500595e-05, "epoch": 14.34381496881497, "percentage": 71.72, "elapsed_time": "1:20:14", "remaining_time": "0:31:38", "throughput": 1032.3, "total_tokens": 4969720} {"current_steps": 55200, "total_steps": 76960, "loss": 0.1625, "lr": 1.1220303008877647e-05, "epoch": 14.345114345114345, "percentage": 71.73, "elapsed_time": "1:20:14", "remaining_time": "0:31:37", "throughput": 1032.31, "total_tokens": 4970184} {"current_steps": 55205, "total_steps": 76960, "loss": 0.039, "lr": 1.121557275695771e-05, "epoch": 14.346413721413722, "percentage": 71.73, "elapsed_time": "1:20:15", "remaining_time": "0:31:37", "throughput": 1032.3, "total_tokens": 4970600} {"current_steps": 55210, "total_steps": 76960, "loss": 0.0419, "lr": 1.1210843213984082e-05, "epoch": 14.347713097713097, "percentage": 71.74, "elapsed_time": "1:20:15", "remaining_time": "0:31:37", "throughput": 1032.31, "total_tokens": 4971048} {"current_steps": 55215, "total_steps": 76960, "loss": 0.2134, "lr": 1.1206114380199989e-05, "epoch": 14.349012474012474, "percentage": 71.75, "elapsed_time": "1:20:15", "remaining_time": "0:31:36", "throughput": 1032.31, "total_tokens": 4971496} {"current_steps": 55220, "total_steps": 76960, "loss": 0.0575, "lr": 1.120138625584866e-05, "epoch": 14.35031185031185, "percentage": 71.75, "elapsed_time": "1:20:16", "remaining_time": "0:31:36", "throughput": 1032.32, "total_tokens": 4971960} {"current_steps": 55225, "total_steps": 76960, "loss": 0.2924, "lr": 1.119665884117324e-05, "epoch": 14.351611226611226, "percentage": 71.76, "elapsed_time": "1:20:16", "remaining_time": "0:31:35", "throughput": 1032.32, "total_tokens": 4972392} {"current_steps": 55230, "total_steps": 76960, "loss": 0.4533, "lr": 1.1191932136416899e-05, "epoch": 14.352910602910603, "percentage": 71.76, "elapsed_time": "1:20:17", "remaining_time": "0:31:35", "throughput": 1032.32, "total_tokens": 4972824} {"current_steps": 55235, "total_steps": 76960, "loss": 0.4946, "lr": 1.1187206141822709e-05, "epoch": 14.35420997920998, "percentage": 71.77, "elapsed_time": "1:20:17", "remaining_time": "0:31:34", "throughput": 1032.32, "total_tokens": 4973272} {"current_steps": 55240, "total_steps": 76960, "loss": 0.1285, "lr": 1.1182480857633751e-05, "epoch": 14.355509355509355, "percentage": 71.78, "elapsed_time": "1:20:17", "remaining_time": "0:31:34", "throughput": 1032.33, "total_tokens": 4973720} {"current_steps": 55245, "total_steps": 76960, "loss": 0.2292, "lr": 1.1177756284093032e-05, "epoch": 14.356808731808732, "percentage": 71.78, "elapsed_time": "1:20:18", "remaining_time": "0:31:33", "throughput": 1032.33, "total_tokens": 4974168} {"current_steps": 55250, "total_steps": 76960, "loss": 0.3128, "lr": 1.1173032421443563e-05, "epoch": 14.358108108108109, "percentage": 71.79, "elapsed_time": "1:20:18", "remaining_time": "0:31:33", "throughput": 1032.33, "total_tokens": 4974584} {"current_steps": 55255, "total_steps": 76960, "loss": 0.4611, "lr": 1.1168309269928276e-05, "epoch": 14.359407484407484, "percentage": 71.8, "elapsed_time": "1:20:19", "remaining_time": "0:31:33", "throughput": 1032.34, "total_tokens": 4975048} {"current_steps": 55260, "total_steps": 76960, "loss": 0.0431, "lr": 1.1163586829790093e-05, "epoch": 14.36070686070686, "percentage": 71.8, "elapsed_time": "1:20:19", "remaining_time": "0:31:32", "throughput": 1032.34, "total_tokens": 4975512} {"current_steps": 55265, "total_steps": 76960, "loss": 0.0238, "lr": 1.1158865101271906e-05, "epoch": 14.362006237006238, "percentage": 71.81, "elapsed_time": "1:20:20", "remaining_time": "0:31:32", "throughput": 1032.35, "total_tokens": 4975976} {"current_steps": 55270, "total_steps": 76960, "loss": 0.1331, "lr": 1.115414408461654e-05, "epoch": 14.363305613305613, "percentage": 71.82, "elapsed_time": "1:20:20", "remaining_time": "0:31:31", "throughput": 1032.36, "total_tokens": 4976424} {"current_steps": 55275, "total_steps": 76960, "loss": 0.4267, "lr": 1.1149423780066822e-05, "epoch": 14.36460498960499, "percentage": 71.82, "elapsed_time": "1:20:20", "remaining_time": "0:31:31", "throughput": 1032.36, "total_tokens": 4976888} {"current_steps": 55280, "total_steps": 76960, "loss": 0.0857, "lr": 1.1144704187865499e-05, "epoch": 14.365904365904367, "percentage": 71.83, "elapsed_time": "1:20:21", "remaining_time": "0:31:30", "throughput": 1032.36, "total_tokens": 4977320} {"current_steps": 55285, "total_steps": 76960, "loss": 0.0111, "lr": 1.1139985308255324e-05, "epoch": 14.367203742203742, "percentage": 71.84, "elapsed_time": "1:20:21", "remaining_time": "0:31:30", "throughput": 1032.37, "total_tokens": 4977800} {"current_steps": 55290, "total_steps": 76960, "loss": 0.1091, "lr": 1.1135267141478974e-05, "epoch": 14.368503118503119, "percentage": 71.84, "elapsed_time": "1:20:22", "remaining_time": "0:31:29", "throughput": 1032.38, "total_tokens": 4978232} {"current_steps": 55295, "total_steps": 76960, "loss": 0.0786, "lr": 1.1130549687779124e-05, "epoch": 14.369802494802494, "percentage": 71.85, "elapsed_time": "1:20:22", "remaining_time": "0:31:29", "throughput": 1032.37, "total_tokens": 4978648} {"current_steps": 55300, "total_steps": 76960, "loss": 0.0096, "lr": 1.112583294739839e-05, "epoch": 14.371101871101871, "percentage": 71.86, "elapsed_time": "1:20:22", "remaining_time": "0:31:29", "throughput": 1032.37, "total_tokens": 4979064} {"current_steps": 55305, "total_steps": 76960, "loss": 0.5474, "lr": 1.112111692057937e-05, "epoch": 14.372401247401248, "percentage": 71.86, "elapsed_time": "1:20:23", "remaining_time": "0:31:28", "throughput": 1032.37, "total_tokens": 4979512} {"current_steps": 55310, "total_steps": 76960, "loss": 0.1518, "lr": 1.1116401607564594e-05, "epoch": 14.373700623700623, "percentage": 71.87, "elapsed_time": "1:20:23", "remaining_time": "0:31:28", "throughput": 1032.38, "total_tokens": 4979976} {"current_steps": 55315, "total_steps": 76960, "loss": 0.294, "lr": 1.1111687008596597e-05, "epoch": 14.375, "percentage": 71.88, "elapsed_time": "1:20:24", "remaining_time": "0:31:27", "throughput": 1032.39, "total_tokens": 4980424} {"current_steps": 55320, "total_steps": 76960, "loss": 0.3171, "lr": 1.1106973123917835e-05, "epoch": 14.376299376299377, "percentage": 71.88, "elapsed_time": "1:20:24", "remaining_time": "0:31:27", "throughput": 1032.39, "total_tokens": 4980872} {"current_steps": 55325, "total_steps": 76960, "loss": 0.2647, "lr": 1.1102259953770766e-05, "epoch": 14.377598752598752, "percentage": 71.89, "elapsed_time": "1:20:25", "remaining_time": "0:31:26", "throughput": 1032.39, "total_tokens": 4981320} {"current_steps": 55330, "total_steps": 76960, "loss": 0.1358, "lr": 1.1097547498397776e-05, "epoch": 14.378898128898129, "percentage": 71.89, "elapsed_time": "1:20:25", "remaining_time": "0:31:26", "throughput": 1032.4, "total_tokens": 4981768} {"current_steps": 55335, "total_steps": 76960, "loss": 0.0567, "lr": 1.1092835758041237e-05, "epoch": 14.380197505197506, "percentage": 71.9, "elapsed_time": "1:20:25", "remaining_time": "0:31:25", "throughput": 1032.4, "total_tokens": 4982216} {"current_steps": 55340, "total_steps": 76960, "loss": 0.3454, "lr": 1.108812473294349e-05, "epoch": 14.381496881496881, "percentage": 71.91, "elapsed_time": "1:20:26", "remaining_time": "0:31:25", "throughput": 1032.4, "total_tokens": 4982664} {"current_steps": 55345, "total_steps": 76960, "loss": 0.0383, "lr": 1.1083414423346807e-05, "epoch": 14.382796257796258, "percentage": 71.91, "elapsed_time": "1:20:26", "remaining_time": "0:31:25", "throughput": 1032.41, "total_tokens": 4983128} {"current_steps": 55350, "total_steps": 76960, "loss": 0.1641, "lr": 1.1078704829493467e-05, "epoch": 14.384095634095633, "percentage": 71.92, "elapsed_time": "1:20:27", "remaining_time": "0:31:24", "throughput": 1032.41, "total_tokens": 4983544} {"current_steps": 55355, "total_steps": 76960, "loss": 0.0304, "lr": 1.1073995951625666e-05, "epoch": 14.38539501039501, "percentage": 71.93, "elapsed_time": "1:20:27", "remaining_time": "0:31:24", "throughput": 1032.43, "total_tokens": 4984056} {"current_steps": 55360, "total_steps": 76960, "loss": 0.2913, "lr": 1.1069287789985606e-05, "epoch": 14.386694386694387, "percentage": 71.93, "elapsed_time": "1:20:27", "remaining_time": "0:31:23", "throughput": 1032.43, "total_tokens": 4984504} {"current_steps": 55365, "total_steps": 76960, "loss": 0.1154, "lr": 1.106458034481541e-05, "epoch": 14.387993762993762, "percentage": 71.94, "elapsed_time": "1:20:28", "remaining_time": "0:31:23", "throughput": 1032.43, "total_tokens": 4984920} {"current_steps": 55370, "total_steps": 76960, "loss": 0.0724, "lr": 1.1059873616357202e-05, "epoch": 14.38929313929314, "percentage": 71.95, "elapsed_time": "1:20:28", "remaining_time": "0:31:22", "throughput": 1032.43, "total_tokens": 4985384} {"current_steps": 55375, "total_steps": 76960, "loss": 0.2418, "lr": 1.1055167604853051e-05, "epoch": 14.390592515592516, "percentage": 71.95, "elapsed_time": "1:20:29", "remaining_time": "0:31:22", "throughput": 1032.43, "total_tokens": 4985800} {"current_steps": 55380, "total_steps": 76960, "loss": 0.1878, "lr": 1.1050462310544999e-05, "epoch": 14.391891891891891, "percentage": 71.96, "elapsed_time": "1:20:29", "remaining_time": "0:31:21", "throughput": 1032.44, "total_tokens": 4986248} {"current_steps": 55385, "total_steps": 76960, "loss": 0.2274, "lr": 1.1045757733675027e-05, "epoch": 14.393191268191268, "percentage": 71.97, "elapsed_time": "1:20:30", "remaining_time": "0:31:21", "throughput": 1032.44, "total_tokens": 4986696} {"current_steps": 55390, "total_steps": 76960, "loss": 0.4848, "lr": 1.1041053874485115e-05, "epoch": 14.394490644490645, "percentage": 71.97, "elapsed_time": "1:20:30", "remaining_time": "0:31:21", "throughput": 1032.45, "total_tokens": 4987160} {"current_steps": 55395, "total_steps": 76960, "loss": 0.3148, "lr": 1.1036350733217177e-05, "epoch": 14.39579002079002, "percentage": 71.98, "elapsed_time": "1:20:30", "remaining_time": "0:31:20", "throughput": 1032.45, "total_tokens": 4987592} {"current_steps": 55400, "total_steps": 76960, "loss": 0.1364, "lr": 1.1031648310113091e-05, "epoch": 14.397089397089397, "percentage": 71.99, "elapsed_time": "1:20:31", "remaining_time": "0:31:20", "throughput": 1032.45, "total_tokens": 4988040} {"current_steps": 55405, "total_steps": 76960, "loss": 0.1558, "lr": 1.1026946605414717e-05, "epoch": 14.398388773388774, "percentage": 71.99, "elapsed_time": "1:20:31", "remaining_time": "0:31:19", "throughput": 1032.46, "total_tokens": 4988488} {"current_steps": 55410, "total_steps": 76960, "loss": 0.1221, "lr": 1.1022245619363866e-05, "epoch": 14.39968814968815, "percentage": 72.0, "elapsed_time": "1:20:32", "remaining_time": "0:31:19", "throughput": 1032.46, "total_tokens": 4988936} {"current_steps": 55415, "total_steps": 76960, "loss": 0.2673, "lr": 1.1017545352202328e-05, "epoch": 14.400987525987526, "percentage": 72.0, "elapsed_time": "1:20:32", "remaining_time": "0:31:18", "throughput": 1032.46, "total_tokens": 4989384} {"current_steps": 55420, "total_steps": 76960, "loss": 0.6079, "lr": 1.1012845804171815e-05, "epoch": 14.402286902286903, "percentage": 72.01, "elapsed_time": "1:20:32", "remaining_time": "0:31:18", "throughput": 1032.47, "total_tokens": 4989832} {"current_steps": 55425, "total_steps": 76960, "loss": 0.0182, "lr": 1.1008146975514059e-05, "epoch": 14.403586278586278, "percentage": 72.02, "elapsed_time": "1:20:33", "remaining_time": "0:31:17", "throughput": 1032.48, "total_tokens": 4990296} {"current_steps": 55430, "total_steps": 76960, "loss": 0.414, "lr": 1.1003448866470698e-05, "epoch": 14.404885654885655, "percentage": 72.02, "elapsed_time": "1:20:33", "remaining_time": "0:31:17", "throughput": 1032.48, "total_tokens": 4990728} {"current_steps": 55435, "total_steps": 76960, "loss": 0.0835, "lr": 1.099875147728338e-05, "epoch": 14.40618503118503, "percentage": 72.03, "elapsed_time": "1:20:34", "remaining_time": "0:31:17", "throughput": 1032.48, "total_tokens": 4991176} {"current_steps": 55440, "total_steps": 76960, "loss": 0.0813, "lr": 1.0994054808193686e-05, "epoch": 14.407484407484407, "percentage": 72.04, "elapsed_time": "1:20:34", "remaining_time": "0:31:16", "throughput": 1032.48, "total_tokens": 4991592} {"current_steps": 55445, "total_steps": 76960, "loss": 0.3687, "lr": 1.0989358859443166e-05, "epoch": 14.408783783783784, "percentage": 72.04, "elapsed_time": "1:20:34", "remaining_time": "0:31:16", "throughput": 1032.49, "total_tokens": 4992072} {"current_steps": 55450, "total_steps": 76960, "loss": 0.217, "lr": 1.0984663631273348e-05, "epoch": 14.41008316008316, "percentage": 72.05, "elapsed_time": "1:20:35", "remaining_time": "0:31:15", "throughput": 1032.49, "total_tokens": 4992488} {"current_steps": 55455, "total_steps": 76960, "loss": 0.0434, "lr": 1.0979969123925718e-05, "epoch": 14.411382536382536, "percentage": 72.06, "elapsed_time": "1:20:35", "remaining_time": "0:31:15", "throughput": 1032.5, "total_tokens": 4992968} {"current_steps": 55460, "total_steps": 76960, "loss": 0.2729, "lr": 1.0975275337641708e-05, "epoch": 14.412681912681913, "percentage": 72.06, "elapsed_time": "1:20:36", "remaining_time": "0:31:14", "throughput": 1032.5, "total_tokens": 4993432} {"current_steps": 55465, "total_steps": 76960, "loss": 0.5102, "lr": 1.0970582272662717e-05, "epoch": 14.413981288981288, "percentage": 72.07, "elapsed_time": "1:20:36", "remaining_time": "0:31:14", "throughput": 1032.53, "total_tokens": 4994008} {"current_steps": 55470, "total_steps": 76960, "loss": 0.2532, "lr": 1.096588992923013e-05, "epoch": 14.415280665280665, "percentage": 72.08, "elapsed_time": "1:20:37", "remaining_time": "0:31:13", "throughput": 1032.54, "total_tokens": 4994472} {"current_steps": 55475, "total_steps": 76960, "loss": 0.4475, "lr": 1.0961198307585252e-05, "epoch": 14.416580041580042, "percentage": 72.08, "elapsed_time": "1:20:37", "remaining_time": "0:31:13", "throughput": 1032.55, "total_tokens": 4994920} {"current_steps": 55480, "total_steps": 76960, "loss": 0.211, "lr": 1.0956507407969416e-05, "epoch": 14.417879417879417, "percentage": 72.09, "elapsed_time": "1:20:37", "remaining_time": "0:31:13", "throughput": 1032.56, "total_tokens": 4995400} {"current_steps": 55485, "total_steps": 76960, "loss": 0.0929, "lr": 1.0951817230623852e-05, "epoch": 14.419178794178794, "percentage": 72.1, "elapsed_time": "1:20:38", "remaining_time": "0:31:12", "throughput": 1032.56, "total_tokens": 4995864} {"current_steps": 55490, "total_steps": 76960, "loss": 0.1206, "lr": 1.0947127775789795e-05, "epoch": 14.420478170478171, "percentage": 72.1, "elapsed_time": "1:20:38", "remaining_time": "0:31:12", "throughput": 1032.57, "total_tokens": 4996312} {"current_steps": 55495, "total_steps": 76960, "loss": 0.2718, "lr": 1.0942439043708413e-05, "epoch": 14.421777546777546, "percentage": 72.11, "elapsed_time": "1:20:39", "remaining_time": "0:31:11", "throughput": 1032.57, "total_tokens": 4996760} {"current_steps": 55500, "total_steps": 76960, "loss": 0.1129, "lr": 1.0937751034620869e-05, "epoch": 14.423076923076923, "percentage": 72.12, "elapsed_time": "1:20:39", "remaining_time": "0:31:11", "throughput": 1032.58, "total_tokens": 4997224} {"current_steps": 55505, "total_steps": 76960, "loss": 0.2952, "lr": 1.0933063748768254e-05, "epoch": 14.424376299376299, "percentage": 72.12, "elapsed_time": "1:20:39", "remaining_time": "0:31:10", "throughput": 1032.59, "total_tokens": 4997688} {"current_steps": 55510, "total_steps": 76960, "loss": 0.4714, "lr": 1.0928377186391647e-05, "epoch": 14.425675675675675, "percentage": 72.13, "elapsed_time": "1:20:40", "remaining_time": "0:31:10", "throughput": 1032.59, "total_tokens": 4998120} {"current_steps": 55515, "total_steps": 76960, "loss": 0.0084, "lr": 1.0923691347732087e-05, "epoch": 14.426975051975052, "percentage": 72.13, "elapsed_time": "1:20:40", "remaining_time": "0:31:09", "throughput": 1032.59, "total_tokens": 4998584} {"current_steps": 55520, "total_steps": 76960, "loss": 0.2081, "lr": 1.0919006233030576e-05, "epoch": 14.428274428274428, "percentage": 72.14, "elapsed_time": "1:20:41", "remaining_time": "0:31:09", "throughput": 1032.6, "total_tokens": 4999048} {"current_steps": 55525, "total_steps": 76960, "loss": 0.0358, "lr": 1.0914321842528057e-05, "epoch": 14.429573804573804, "percentage": 72.15, "elapsed_time": "1:20:41", "remaining_time": "0:31:09", "throughput": 1032.6, "total_tokens": 4999496} {"current_steps": 55530, "total_steps": 76960, "loss": 0.1483, "lr": 1.0909638176465473e-05, "epoch": 14.430873180873181, "percentage": 72.15, "elapsed_time": "1:20:42", "remaining_time": "0:31:08", "throughput": 1032.6, "total_tokens": 4999912} {"current_steps": 55535, "total_steps": 76960, "loss": 0.3365, "lr": 1.0904955235083696e-05, "epoch": 14.432172557172557, "percentage": 72.16, "elapsed_time": "1:20:42", "remaining_time": "0:31:08", "throughput": 1032.6, "total_tokens": 5000328} {"current_steps": 55540, "total_steps": 76960, "loss": 0.1237, "lr": 1.0900273018623569e-05, "epoch": 14.433471933471933, "percentage": 72.17, "elapsed_time": "1:20:42", "remaining_time": "0:31:07", "throughput": 1032.6, "total_tokens": 5000760} {"current_steps": 55545, "total_steps": 76960, "loss": 0.2263, "lr": 1.0895591527325911e-05, "epoch": 14.43477130977131, "percentage": 72.17, "elapsed_time": "1:20:43", "remaining_time": "0:31:07", "throughput": 1032.61, "total_tokens": 5001224} {"current_steps": 55550, "total_steps": 76960, "loss": 0.0689, "lr": 1.0890910761431491e-05, "epoch": 14.436070686070686, "percentage": 72.18, "elapsed_time": "1:20:43", "remaining_time": "0:31:06", "throughput": 1032.61, "total_tokens": 5001688} {"current_steps": 55555, "total_steps": 76960, "loss": 0.2176, "lr": 1.0886230721181063e-05, "epoch": 14.437370062370062, "percentage": 72.19, "elapsed_time": "1:20:44", "remaining_time": "0:31:06", "throughput": 1032.61, "total_tokens": 5002104} {"current_steps": 55560, "total_steps": 76960, "loss": 0.3273, "lr": 1.0881551406815298e-05, "epoch": 14.43866943866944, "percentage": 72.19, "elapsed_time": "1:20:44", "remaining_time": "0:31:05", "throughput": 1032.62, "total_tokens": 5002584} {"current_steps": 55565, "total_steps": 76960, "loss": 0.1421, "lr": 1.0876872818574884e-05, "epoch": 14.439968814968815, "percentage": 72.2, "elapsed_time": "1:20:44", "remaining_time": "0:31:05", "throughput": 1032.62, "total_tokens": 5003000} {"current_steps": 55570, "total_steps": 76960, "loss": 0.1529, "lr": 1.0872194956700423e-05, "epoch": 14.441268191268192, "percentage": 72.21, "elapsed_time": "1:20:45", "remaining_time": "0:31:05", "throughput": 1032.62, "total_tokens": 5003448} {"current_steps": 55575, "total_steps": 76960, "loss": 0.0786, "lr": 1.0867517821432524e-05, "epoch": 14.442567567567568, "percentage": 72.21, "elapsed_time": "1:20:45", "remaining_time": "0:31:04", "throughput": 1032.62, "total_tokens": 5003880} {"current_steps": 55580, "total_steps": 76960, "loss": 0.1559, "lr": 1.0862841413011713e-05, "epoch": 14.443866943866944, "percentage": 72.22, "elapsed_time": "1:20:46", "remaining_time": "0:31:04", "throughput": 1032.63, "total_tokens": 5004328} {"current_steps": 55585, "total_steps": 76960, "loss": 0.0967, "lr": 1.0858165731678513e-05, "epoch": 14.44516632016632, "percentage": 72.23, "elapsed_time": "1:20:46", "remaining_time": "0:31:03", "throughput": 1032.63, "total_tokens": 5004760} {"current_steps": 55590, "total_steps": 76960, "loss": 0.1884, "lr": 1.08534907776734e-05, "epoch": 14.446465696465696, "percentage": 72.23, "elapsed_time": "1:20:47", "remaining_time": "0:31:03", "throughput": 1032.64, "total_tokens": 5005240} {"current_steps": 55595, "total_steps": 76960, "loss": 0.1965, "lr": 1.084881655123682e-05, "epoch": 14.447765072765073, "percentage": 72.24, "elapsed_time": "1:20:47", "remaining_time": "0:31:02", "throughput": 1032.64, "total_tokens": 5005672} {"current_steps": 55600, "total_steps": 76960, "loss": 0.612, "lr": 1.0844143052609165e-05, "epoch": 14.44906444906445, "percentage": 72.25, "elapsed_time": "1:20:47", "remaining_time": "0:31:02", "throughput": 1032.64, "total_tokens": 5006104} {"current_steps": 55605, "total_steps": 76960, "loss": 0.2932, "lr": 1.0839470282030787e-05, "epoch": 14.450363825363825, "percentage": 72.25, "elapsed_time": "1:20:48", "remaining_time": "0:31:01", "throughput": 1032.63, "total_tokens": 5006520} {"current_steps": 55610, "total_steps": 76960, "loss": 0.0482, "lr": 1.0834798239742028e-05, "epoch": 14.451663201663202, "percentage": 72.26, "elapsed_time": "1:20:48", "remaining_time": "0:31:01", "throughput": 1032.64, "total_tokens": 5006968} {"current_steps": 55615, "total_steps": 76960, "loss": 0.1943, "lr": 1.0830126925983158e-05, "epoch": 14.452962577962579, "percentage": 72.26, "elapsed_time": "1:20:49", "remaining_time": "0:31:01", "throughput": 1032.64, "total_tokens": 5007416} {"current_steps": 55620, "total_steps": 76960, "loss": 0.1614, "lr": 1.082545634099444e-05, "epoch": 14.454261954261954, "percentage": 72.27, "elapsed_time": "1:20:49", "remaining_time": "0:31:00", "throughput": 1032.64, "total_tokens": 5007848} {"current_steps": 55625, "total_steps": 76960, "loss": 0.1556, "lr": 1.0820786485016082e-05, "epoch": 14.45556133056133, "percentage": 72.28, "elapsed_time": "1:20:49", "remaining_time": "0:31:00", "throughput": 1032.65, "total_tokens": 5008312} {"current_steps": 55630, "total_steps": 76960, "loss": 0.472, "lr": 1.0816117358288272e-05, "epoch": 14.456860706860708, "percentage": 72.28, "elapsed_time": "1:20:50", "remaining_time": "0:30:59", "throughput": 1032.66, "total_tokens": 5008792} {"current_steps": 55635, "total_steps": 76960, "loss": 0.0923, "lr": 1.0811448961051123e-05, "epoch": 14.458160083160083, "percentage": 72.29, "elapsed_time": "1:20:50", "remaining_time": "0:30:59", "throughput": 1032.66, "total_tokens": 5009208} {"current_steps": 55640, "total_steps": 76960, "loss": 0.0187, "lr": 1.0806781293544763e-05, "epoch": 14.45945945945946, "percentage": 72.3, "elapsed_time": "1:20:51", "remaining_time": "0:30:58", "throughput": 1032.66, "total_tokens": 5009640} {"current_steps": 55645, "total_steps": 76960, "loss": 0.1256, "lr": 1.080211435600923e-05, "epoch": 14.460758835758837, "percentage": 72.3, "elapsed_time": "1:20:51", "remaining_time": "0:30:58", "throughput": 1032.66, "total_tokens": 5010072} {"current_steps": 55650, "total_steps": 76960, "loss": 0.1538, "lr": 1.0797448148684566e-05, "epoch": 14.462058212058212, "percentage": 72.31, "elapsed_time": "1:20:52", "remaining_time": "0:30:57", "throughput": 1032.67, "total_tokens": 5010568} {"current_steps": 55655, "total_steps": 76960, "loss": 0.1975, "lr": 1.0792782671810745e-05, "epoch": 14.463357588357589, "percentage": 72.32, "elapsed_time": "1:20:52", "remaining_time": "0:30:57", "throughput": 1032.68, "total_tokens": 5011048} {"current_steps": 55660, "total_steps": 76960, "loss": 0.0198, "lr": 1.0788117925627724e-05, "epoch": 14.464656964656964, "percentage": 72.32, "elapsed_time": "1:20:52", "remaining_time": "0:30:57", "throughput": 1032.68, "total_tokens": 5011480} {"current_steps": 55665, "total_steps": 76960, "loss": 0.1834, "lr": 1.0783453910375424e-05, "epoch": 14.46595634095634, "percentage": 72.33, "elapsed_time": "1:20:53", "remaining_time": "0:30:56", "throughput": 1032.69, "total_tokens": 5011928} {"current_steps": 55670, "total_steps": 76960, "loss": 0.3127, "lr": 1.07787906262937e-05, "epoch": 14.467255717255718, "percentage": 72.34, "elapsed_time": "1:20:53", "remaining_time": "0:30:56", "throughput": 1032.69, "total_tokens": 5012360} {"current_steps": 55675, "total_steps": 76960, "loss": 0.2066, "lr": 1.077412807362241e-05, "epoch": 14.468555093555093, "percentage": 72.34, "elapsed_time": "1:20:54", "remaining_time": "0:30:55", "throughput": 1032.69, "total_tokens": 5012792} {"current_steps": 55680, "total_steps": 76960, "loss": 0.5146, "lr": 1.0769466252601337e-05, "epoch": 14.46985446985447, "percentage": 72.35, "elapsed_time": "1:20:54", "remaining_time": "0:30:55", "throughput": 1032.69, "total_tokens": 5013224} {"current_steps": 55685, "total_steps": 76960, "loss": 0.6988, "lr": 1.076480516347026e-05, "epoch": 14.471153846153847, "percentage": 72.36, "elapsed_time": "1:20:54", "remaining_time": "0:30:54", "throughput": 1032.7, "total_tokens": 5013704} {"current_steps": 55690, "total_steps": 76960, "loss": 0.1649, "lr": 1.076014480646888e-05, "epoch": 14.472453222453222, "percentage": 72.36, "elapsed_time": "1:20:55", "remaining_time": "0:30:54", "throughput": 1032.7, "total_tokens": 5014136} {"current_steps": 55695, "total_steps": 76960, "loss": 0.0616, "lr": 1.0755485181836897e-05, "epoch": 14.473752598752599, "percentage": 72.37, "elapsed_time": "1:20:55", "remaining_time": "0:30:53", "throughput": 1032.7, "total_tokens": 5014568} {"current_steps": 55700, "total_steps": 76960, "loss": 0.3179, "lr": 1.0750826289813961e-05, "epoch": 14.475051975051976, "percentage": 72.38, "elapsed_time": "1:20:56", "remaining_time": "0:30:53", "throughput": 1032.7, "total_tokens": 5015000} {"current_steps": 55705, "total_steps": 76960, "loss": 0.2943, "lr": 1.0746168130639689e-05, "epoch": 14.47635135135135, "percentage": 72.38, "elapsed_time": "1:20:56", "remaining_time": "0:30:53", "throughput": 1032.71, "total_tokens": 5015464} {"current_steps": 55710, "total_steps": 76960, "loss": 0.2997, "lr": 1.074151070455364e-05, "epoch": 14.477650727650728, "percentage": 72.39, "elapsed_time": "1:20:57", "remaining_time": "0:30:52", "throughput": 1032.71, "total_tokens": 5015912} {"current_steps": 55715, "total_steps": 76960, "loss": 0.1018, "lr": 1.0736854011795367e-05, "epoch": 14.478950103950105, "percentage": 72.39, "elapsed_time": "1:20:57", "remaining_time": "0:30:52", "throughput": 1032.72, "total_tokens": 5016344} {"current_steps": 55720, "total_steps": 76960, "loss": 0.237, "lr": 1.0732198052604347e-05, "epoch": 14.48024948024948, "percentage": 72.4, "elapsed_time": "1:20:57", "remaining_time": "0:30:51", "throughput": 1032.72, "total_tokens": 5016808} {"current_steps": 55725, "total_steps": 76960, "loss": 0.1277, "lr": 1.0727542827220056e-05, "epoch": 14.481548856548857, "percentage": 72.41, "elapsed_time": "1:20:58", "remaining_time": "0:30:51", "throughput": 1032.73, "total_tokens": 5017256} {"current_steps": 55730, "total_steps": 76960, "loss": 0.5393, "lr": 1.0722888335881917e-05, "epoch": 14.482848232848234, "percentage": 72.41, "elapsed_time": "1:20:58", "remaining_time": "0:30:50", "throughput": 1032.73, "total_tokens": 5017704} {"current_steps": 55735, "total_steps": 76960, "loss": 0.1758, "lr": 1.0718234578829304e-05, "epoch": 14.484147609147609, "percentage": 72.42, "elapsed_time": "1:20:59", "remaining_time": "0:30:50", "throughput": 1032.73, "total_tokens": 5018152} {"current_steps": 55740, "total_steps": 76960, "loss": 0.0448, "lr": 1.0713581556301577e-05, "epoch": 14.485446985446986, "percentage": 72.43, "elapsed_time": "1:20:59", "remaining_time": "0:30:49", "throughput": 1032.74, "total_tokens": 5018600} {"current_steps": 55745, "total_steps": 76960, "loss": 0.1862, "lr": 1.0708929268538034e-05, "epoch": 14.486746361746361, "percentage": 72.43, "elapsed_time": "1:20:59", "remaining_time": "0:30:49", "throughput": 1032.75, "total_tokens": 5019080} {"current_steps": 55750, "total_steps": 76960, "loss": 0.2869, "lr": 1.0704277715777957e-05, "epoch": 14.488045738045738, "percentage": 72.44, "elapsed_time": "1:21:00", "remaining_time": "0:30:49", "throughput": 1032.76, "total_tokens": 5019560} {"current_steps": 55755, "total_steps": 76960, "loss": 0.2389, "lr": 1.0699626898260571e-05, "epoch": 14.489345114345115, "percentage": 72.45, "elapsed_time": "1:21:00", "remaining_time": "0:30:48", "throughput": 1032.76, "total_tokens": 5020008} {"current_steps": 55760, "total_steps": 76960, "loss": 0.165, "lr": 1.0694976816225073e-05, "epoch": 14.49064449064449, "percentage": 72.45, "elapsed_time": "1:21:01", "remaining_time": "0:30:48", "throughput": 1032.76, "total_tokens": 5020440} {"current_steps": 55765, "total_steps": 76960, "loss": 0.1858, "lr": 1.0690327469910622e-05, "epoch": 14.491943866943867, "percentage": 72.46, "elapsed_time": "1:21:01", "remaining_time": "0:30:47", "throughput": 1032.77, "total_tokens": 5020920} {"current_steps": 55770, "total_steps": 76960, "loss": 0.2386, "lr": 1.0685678859556348e-05, "epoch": 14.493243243243244, "percentage": 72.47, "elapsed_time": "1:21:02", "remaining_time": "0:30:47", "throughput": 1032.78, "total_tokens": 5021384} {"current_steps": 55775, "total_steps": 76960, "loss": 0.1355, "lr": 1.0681030985401319e-05, "epoch": 14.494542619542619, "percentage": 72.47, "elapsed_time": "1:21:02", "remaining_time": "0:30:46", "throughput": 1032.78, "total_tokens": 5021800} {"current_steps": 55780, "total_steps": 76960, "loss": 0.0208, "lr": 1.0676383847684595e-05, "epoch": 14.495841995841996, "percentage": 72.48, "elapsed_time": "1:21:02", "remaining_time": "0:30:46", "throughput": 1032.79, "total_tokens": 5022280} {"current_steps": 55785, "total_steps": 76960, "loss": 0.031, "lr": 1.0671737446645163e-05, "epoch": 14.497141372141373, "percentage": 72.49, "elapsed_time": "1:21:03", "remaining_time": "0:30:46", "throughput": 1032.79, "total_tokens": 5022712} {"current_steps": 55790, "total_steps": 76960, "loss": 0.1267, "lr": 1.0667091782522015e-05, "epoch": 14.498440748440748, "percentage": 72.49, "elapsed_time": "1:21:03", "remaining_time": "0:30:45", "throughput": 1032.79, "total_tokens": 5023128} {"current_steps": 55795, "total_steps": 76960, "loss": 0.1494, "lr": 1.0662446855554059e-05, "epoch": 14.499740124740125, "percentage": 72.5, "elapsed_time": "1:21:04", "remaining_time": "0:30:45", "throughput": 1032.79, "total_tokens": 5023592} {"current_steps": 55800, "total_steps": 76960, "loss": 0.3456, "lr": 1.0657802665980199e-05, "epoch": 14.5010395010395, "percentage": 72.51, "elapsed_time": "1:21:04", "remaining_time": "0:30:44", "throughput": 1032.8, "total_tokens": 5024040} {"current_steps": 55805, "total_steps": 76960, "loss": 0.1242, "lr": 1.06531592140393e-05, "epoch": 14.502338877338877, "percentage": 72.51, "elapsed_time": "1:21:04", "remaining_time": "0:30:44", "throughput": 1032.8, "total_tokens": 5024456} {"current_steps": 55810, "total_steps": 76960, "loss": 0.4919, "lr": 1.0648516499970159e-05, "epoch": 14.503638253638254, "percentage": 72.52, "elapsed_time": "1:21:05", "remaining_time": "0:30:43", "throughput": 1032.81, "total_tokens": 5024952} {"current_steps": 55815, "total_steps": 76960, "loss": 0.0573, "lr": 1.0643874524011573e-05, "epoch": 14.50493762993763, "percentage": 72.52, "elapsed_time": "1:21:05", "remaining_time": "0:30:43", "throughput": 1032.82, "total_tokens": 5025448} {"current_steps": 55820, "total_steps": 76960, "loss": 0.2609, "lr": 1.063923328640227e-05, "epoch": 14.506237006237006, "percentage": 72.53, "elapsed_time": "1:21:06", "remaining_time": "0:30:42", "throughput": 1032.83, "total_tokens": 5025912} {"current_steps": 55825, "total_steps": 76960, "loss": 0.029, "lr": 1.0634592787380965e-05, "epoch": 14.507536382536383, "percentage": 72.54, "elapsed_time": "1:21:06", "remaining_time": "0:30:42", "throughput": 1032.83, "total_tokens": 5026328} {"current_steps": 55830, "total_steps": 76960, "loss": 0.3407, "lr": 1.062995302718631e-05, "epoch": 14.508835758835758, "percentage": 72.54, "elapsed_time": "1:21:06", "remaining_time": "0:30:42", "throughput": 1032.83, "total_tokens": 5026776} {"current_steps": 55835, "total_steps": 76960, "loss": 0.2351, "lr": 1.062531400605694e-05, "epoch": 14.510135135135135, "percentage": 72.55, "elapsed_time": "1:21:07", "remaining_time": "0:30:41", "throughput": 1032.83, "total_tokens": 5027192} {"current_steps": 55840, "total_steps": 76960, "loss": 0.4485, "lr": 1.062067572423144e-05, "epoch": 14.511434511434512, "percentage": 72.56, "elapsed_time": "1:21:07", "remaining_time": "0:30:41", "throughput": 1032.84, "total_tokens": 5027656} {"current_steps": 55845, "total_steps": 76960, "loss": 0.4607, "lr": 1.061603818194838e-05, "epoch": 14.512733887733887, "percentage": 72.56, "elapsed_time": "1:21:08", "remaining_time": "0:30:40", "throughput": 1032.85, "total_tokens": 5028152} {"current_steps": 55850, "total_steps": 76960, "loss": 0.0057, "lr": 1.0611401379446245e-05, "epoch": 14.514033264033264, "percentage": 72.57, "elapsed_time": "1:21:08", "remaining_time": "0:30:40", "throughput": 1032.86, "total_tokens": 5028632} {"current_steps": 55855, "total_steps": 76960, "loss": 0.166, "lr": 1.0606765316963533e-05, "epoch": 14.515332640332641, "percentage": 72.58, "elapsed_time": "1:21:09", "remaining_time": "0:30:39", "throughput": 1032.85, "total_tokens": 5029032} {"current_steps": 55860, "total_steps": 76960, "loss": 0.2294, "lr": 1.0602129994738672e-05, "epoch": 14.516632016632016, "percentage": 72.58, "elapsed_time": "1:21:09", "remaining_time": "0:30:39", "throughput": 1032.87, "total_tokens": 5029512} {"current_steps": 55865, "total_steps": 76960, "loss": 0.104, "lr": 1.0597495413010053e-05, "epoch": 14.517931392931393, "percentage": 72.59, "elapsed_time": "1:21:09", "remaining_time": "0:30:38", "throughput": 1032.88, "total_tokens": 5029992} {"current_steps": 55870, "total_steps": 76960, "loss": 0.5741, "lr": 1.0592861572016042e-05, "epoch": 14.51923076923077, "percentage": 72.6, "elapsed_time": "1:21:10", "remaining_time": "0:30:38", "throughput": 1032.89, "total_tokens": 5030472} {"current_steps": 55875, "total_steps": 76960, "loss": 0.2206, "lr": 1.0588228471994966e-05, "epoch": 14.520530145530145, "percentage": 72.6, "elapsed_time": "1:21:10", "remaining_time": "0:30:38", "throughput": 1032.89, "total_tokens": 5030888} {"current_steps": 55880, "total_steps": 76960, "loss": 0.0834, "lr": 1.0583596113185119e-05, "epoch": 14.521829521829522, "percentage": 72.61, "elapsed_time": "1:21:11", "remaining_time": "0:30:37", "throughput": 1032.9, "total_tokens": 5031368} {"current_steps": 55885, "total_steps": 76960, "loss": 0.4676, "lr": 1.0578964495824725e-05, "epoch": 14.523128898128899, "percentage": 72.62, "elapsed_time": "1:21:11", "remaining_time": "0:30:37", "throughput": 1032.91, "total_tokens": 5031864} {"current_steps": 55890, "total_steps": 76960, "loss": 0.3727, "lr": 1.0574333620152016e-05, "epoch": 14.524428274428274, "percentage": 72.62, "elapsed_time": "1:21:11", "remaining_time": "0:30:36", "throughput": 1032.92, "total_tokens": 5032328} {"current_steps": 55895, "total_steps": 76960, "loss": 0.0385, "lr": 1.0569703486405141e-05, "epoch": 14.525727650727651, "percentage": 72.63, "elapsed_time": "1:21:12", "remaining_time": "0:30:36", "throughput": 1032.93, "total_tokens": 5032792} {"current_steps": 55900, "total_steps": 76960, "loss": 0.3582, "lr": 1.0565074094822252e-05, "epoch": 14.527027027027026, "percentage": 72.64, "elapsed_time": "1:21:12", "remaining_time": "0:30:35", "throughput": 1032.93, "total_tokens": 5033240} {"current_steps": 55905, "total_steps": 76960, "loss": 0.2226, "lr": 1.0560445445641423e-05, "epoch": 14.528326403326403, "percentage": 72.64, "elapsed_time": "1:21:13", "remaining_time": "0:30:35", "throughput": 1032.93, "total_tokens": 5033656} {"current_steps": 55910, "total_steps": 76960, "loss": 0.4209, "lr": 1.055581753910072e-05, "epoch": 14.52962577962578, "percentage": 72.65, "elapsed_time": "1:21:13", "remaining_time": "0:30:34", "throughput": 1032.93, "total_tokens": 5034120} {"current_steps": 55915, "total_steps": 76960, "loss": 0.6899, "lr": 1.0551190375438163e-05, "epoch": 14.530925155925155, "percentage": 72.65, "elapsed_time": "1:21:14", "remaining_time": "0:30:34", "throughput": 1032.94, "total_tokens": 5034568} {"current_steps": 55920, "total_steps": 76960, "loss": 0.344, "lr": 1.0546563954891736e-05, "epoch": 14.532224532224532, "percentage": 72.66, "elapsed_time": "1:21:14", "remaining_time": "0:30:34", "throughput": 1032.94, "total_tokens": 5035016} {"current_steps": 55925, "total_steps": 76960, "loss": 0.4807, "lr": 1.0541938277699373e-05, "epoch": 14.53352390852391, "percentage": 72.67, "elapsed_time": "1:21:14", "remaining_time": "0:30:33", "throughput": 1032.95, "total_tokens": 5035480} {"current_steps": 55930, "total_steps": 76960, "loss": 0.1715, "lr": 1.053731334409897e-05, "epoch": 14.534823284823284, "percentage": 72.67, "elapsed_time": "1:21:15", "remaining_time": "0:30:33", "throughput": 1032.95, "total_tokens": 5035912} {"current_steps": 55935, "total_steps": 76960, "loss": 0.0143, "lr": 1.0532689154328407e-05, "epoch": 14.536122661122661, "percentage": 72.68, "elapsed_time": "1:21:15", "remaining_time": "0:30:32", "throughput": 1032.95, "total_tokens": 5036360} {"current_steps": 55940, "total_steps": 76960, "loss": 0.1324, "lr": 1.0528065708625495e-05, "epoch": 14.537422037422038, "percentage": 72.69, "elapsed_time": "1:21:16", "remaining_time": "0:30:32", "throughput": 1032.96, "total_tokens": 5036824} {"current_steps": 55945, "total_steps": 76960, "loss": 0.2786, "lr": 1.052344300722803e-05, "epoch": 14.538721413721413, "percentage": 72.69, "elapsed_time": "1:21:16", "remaining_time": "0:30:31", "throughput": 1032.97, "total_tokens": 5037288} {"current_steps": 55950, "total_steps": 76960, "loss": 0.0081, "lr": 1.0518821050373758e-05, "epoch": 14.54002079002079, "percentage": 72.7, "elapsed_time": "1:21:16", "remaining_time": "0:30:31", "throughput": 1032.97, "total_tokens": 5037720} {"current_steps": 55955, "total_steps": 76960, "loss": 0.2565, "lr": 1.051419983830041e-05, "epoch": 14.541320166320165, "percentage": 72.71, "elapsed_time": "1:21:17", "remaining_time": "0:30:30", "throughput": 1032.97, "total_tokens": 5038168} {"current_steps": 55960, "total_steps": 76960, "loss": 0.0573, "lr": 1.050957937124563e-05, "epoch": 14.542619542619542, "percentage": 72.71, "elapsed_time": "1:21:17", "remaining_time": "0:30:30", "throughput": 1032.98, "total_tokens": 5038632} {"current_steps": 55965, "total_steps": 76960, "loss": 0.1509, "lr": 1.0504959649447077e-05, "epoch": 14.54391891891892, "percentage": 72.72, "elapsed_time": "1:21:18", "remaining_time": "0:30:30", "throughput": 1032.98, "total_tokens": 5039064} {"current_steps": 55970, "total_steps": 76960, "loss": 0.7151, "lr": 1.0500340673142331e-05, "epoch": 14.545218295218294, "percentage": 72.73, "elapsed_time": "1:21:18", "remaining_time": "0:30:29", "throughput": 1032.98, "total_tokens": 5039528} {"current_steps": 55975, "total_steps": 76960, "loss": 0.1398, "lr": 1.0495722442568954e-05, "epoch": 14.546517671517671, "percentage": 72.73, "elapsed_time": "1:21:19", "remaining_time": "0:30:29", "throughput": 1032.99, "total_tokens": 5039992} {"current_steps": 55980, "total_steps": 76960, "loss": 0.4608, "lr": 1.0491104957964471e-05, "epoch": 14.547817047817048, "percentage": 72.74, "elapsed_time": "1:21:19", "remaining_time": "0:30:28", "throughput": 1033.0, "total_tokens": 5040472} {"current_steps": 55985, "total_steps": 76960, "loss": 0.1565, "lr": 1.048648821956637e-05, "epoch": 14.549116424116423, "percentage": 72.75, "elapsed_time": "1:21:19", "remaining_time": "0:30:28", "throughput": 1033.01, "total_tokens": 5040920} {"current_steps": 55990, "total_steps": 76960, "loss": 0.1774, "lr": 1.0481872227612085e-05, "epoch": 14.5504158004158, "percentage": 72.75, "elapsed_time": "1:21:20", "remaining_time": "0:30:27", "throughput": 1033.01, "total_tokens": 5041384} {"current_steps": 55995, "total_steps": 76960, "loss": 0.0062, "lr": 1.0477256982339015e-05, "epoch": 14.551715176715177, "percentage": 72.76, "elapsed_time": "1:21:20", "remaining_time": "0:30:27", "throughput": 1033.02, "total_tokens": 5041864} {"current_steps": 56000, "total_steps": 76960, "loss": 0.2707, "lr": 1.047264248398454e-05, "epoch": 14.553014553014552, "percentage": 72.77, "elapsed_time": "1:21:21", "remaining_time": "0:30:26", "throughput": 1033.03, "total_tokens": 5042344} {"current_steps": 56005, "total_steps": 76960, "loss": 0.1264, "lr": 1.0468028732785975e-05, "epoch": 14.55431392931393, "percentage": 72.77, "elapsed_time": "1:21:21", "remaining_time": "0:30:26", "throughput": 1033.03, "total_tokens": 5042776} {"current_steps": 56010, "total_steps": 76960, "loss": 0.3057, "lr": 1.0463415728980617e-05, "epoch": 14.555613305613306, "percentage": 72.78, "elapsed_time": "1:21:21", "remaining_time": "0:30:26", "throughput": 1033.04, "total_tokens": 5043256} {"current_steps": 56015, "total_steps": 76960, "loss": 0.1803, "lr": 1.0458803472805714e-05, "epoch": 14.556912681912682, "percentage": 72.78, "elapsed_time": "1:21:22", "remaining_time": "0:30:25", "throughput": 1033.06, "total_tokens": 5043752} {"current_steps": 56020, "total_steps": 76960, "loss": 0.4252, "lr": 1.0454191964498491e-05, "epoch": 14.558212058212058, "percentage": 72.79, "elapsed_time": "1:21:22", "remaining_time": "0:30:25", "throughput": 1033.07, "total_tokens": 5044232} {"current_steps": 56025, "total_steps": 76960, "loss": 0.2892, "lr": 1.0449581204296102e-05, "epoch": 14.559511434511435, "percentage": 72.8, "elapsed_time": "1:21:23", "remaining_time": "0:30:24", "throughput": 1033.07, "total_tokens": 5044664} {"current_steps": 56030, "total_steps": 76960, "loss": 0.314, "lr": 1.0444971192435704e-05, "epoch": 14.56081081081081, "percentage": 72.8, "elapsed_time": "1:21:23", "remaining_time": "0:30:24", "throughput": 1033.08, "total_tokens": 5045128} {"current_steps": 56035, "total_steps": 76960, "loss": 0.1217, "lr": 1.0440361929154375e-05, "epoch": 14.562110187110187, "percentage": 72.81, "elapsed_time": "1:21:24", "remaining_time": "0:30:23", "throughput": 1033.09, "total_tokens": 5045640} {"current_steps": 56040, "total_steps": 76960, "loss": 0.3951, "lr": 1.043575341468919e-05, "epoch": 14.563409563409563, "percentage": 72.82, "elapsed_time": "1:21:24", "remaining_time": "0:30:23", "throughput": 1033.11, "total_tokens": 5046136} {"current_steps": 56045, "total_steps": 76960, "loss": 0.1322, "lr": 1.0431145649277152e-05, "epoch": 14.56470893970894, "percentage": 72.82, "elapsed_time": "1:21:24", "remaining_time": "0:30:22", "throughput": 1033.11, "total_tokens": 5046584} {"current_steps": 56050, "total_steps": 76960, "loss": 0.2128, "lr": 1.0426538633155253e-05, "epoch": 14.566008316008316, "percentage": 72.83, "elapsed_time": "1:21:25", "remaining_time": "0:30:22", "throughput": 1033.12, "total_tokens": 5047064} {"current_steps": 56055, "total_steps": 76960, "loss": 0.2824, "lr": 1.0421932366560444e-05, "epoch": 14.567307692307692, "percentage": 72.84, "elapsed_time": "1:21:25", "remaining_time": "0:30:22", "throughput": 1033.13, "total_tokens": 5047544} {"current_steps": 56060, "total_steps": 76960, "loss": 0.0328, "lr": 1.0417326849729614e-05, "epoch": 14.568607068607069, "percentage": 72.84, "elapsed_time": "1:21:26", "remaining_time": "0:30:21", "throughput": 1033.14, "total_tokens": 5048008} {"current_steps": 56065, "total_steps": 76960, "loss": 0.1581, "lr": 1.0412722082899644e-05, "epoch": 14.569906444906445, "percentage": 72.85, "elapsed_time": "1:21:26", "remaining_time": "0:30:21", "throughput": 1033.15, "total_tokens": 5048488} {"current_steps": 56070, "total_steps": 76960, "loss": 0.0818, "lr": 1.0408118066307346e-05, "epoch": 14.57120582120582, "percentage": 72.86, "elapsed_time": "1:21:26", "remaining_time": "0:30:20", "throughput": 1033.16, "total_tokens": 5048952} {"current_steps": 56075, "total_steps": 76960, "loss": 0.1948, "lr": 1.0403514800189526e-05, "epoch": 14.572505197505198, "percentage": 72.86, "elapsed_time": "1:21:27", "remaining_time": "0:30:20", "throughput": 1033.17, "total_tokens": 5049432} {"current_steps": 56080, "total_steps": 76960, "loss": 0.0292, "lr": 1.0398912284782918e-05, "epoch": 14.573804573804575, "percentage": 72.87, "elapsed_time": "1:21:27", "remaining_time": "0:30:19", "throughput": 1033.17, "total_tokens": 5049864} {"current_steps": 56085, "total_steps": 76960, "loss": 0.1627, "lr": 1.039431052032424e-05, "epoch": 14.57510395010395, "percentage": 72.88, "elapsed_time": "1:21:28", "remaining_time": "0:30:19", "throughput": 1033.18, "total_tokens": 5050360} {"current_steps": 56090, "total_steps": 76960, "loss": 0.3826, "lr": 1.0389709507050166e-05, "epoch": 14.576403326403327, "percentage": 72.88, "elapsed_time": "1:21:28", "remaining_time": "0:30:18", "throughput": 1033.19, "total_tokens": 5050824} {"current_steps": 56095, "total_steps": 76960, "loss": 0.0568, "lr": 1.0385109245197342e-05, "epoch": 14.577702702702704, "percentage": 72.89, "elapsed_time": "1:21:28", "remaining_time": "0:30:18", "throughput": 1033.19, "total_tokens": 5051256} {"current_steps": 56100, "total_steps": 76960, "loss": 0.4059, "lr": 1.0380509735002341e-05, "epoch": 14.579002079002079, "percentage": 72.9, "elapsed_time": "1:21:29", "remaining_time": "0:30:18", "throughput": 1033.19, "total_tokens": 5051688} {"current_steps": 56105, "total_steps": 76960, "loss": 0.3131, "lr": 1.0375910976701742e-05, "epoch": 14.580301455301456, "percentage": 72.9, "elapsed_time": "1:21:29", "remaining_time": "0:30:17", "throughput": 1033.19, "total_tokens": 5052120} {"current_steps": 56110, "total_steps": 76960, "loss": 0.0385, "lr": 1.0371312970532046e-05, "epoch": 14.58160083160083, "percentage": 72.91, "elapsed_time": "1:21:30", "remaining_time": "0:30:17", "throughput": 1033.19, "total_tokens": 5052536} {"current_steps": 56115, "total_steps": 76960, "loss": 0.1695, "lr": 1.0366715716729747e-05, "epoch": 14.582900207900208, "percentage": 72.91, "elapsed_time": "1:21:30", "remaining_time": "0:30:16", "throughput": 1033.19, "total_tokens": 5052968} {"current_steps": 56120, "total_steps": 76960, "loss": 0.0811, "lr": 1.0362119215531271e-05, "epoch": 14.584199584199585, "percentage": 72.92, "elapsed_time": "1:21:31", "remaining_time": "0:30:16", "throughput": 1033.19, "total_tokens": 5053416} {"current_steps": 56125, "total_steps": 76960, "loss": 0.2961, "lr": 1.0357523467173031e-05, "epoch": 14.58549896049896, "percentage": 72.93, "elapsed_time": "1:21:31", "remaining_time": "0:30:15", "throughput": 1033.2, "total_tokens": 5053896} {"current_steps": 56130, "total_steps": 76960, "loss": 0.1364, "lr": 1.0352928471891396e-05, "epoch": 14.586798336798337, "percentage": 72.93, "elapsed_time": "1:21:31", "remaining_time": "0:30:15", "throughput": 1033.21, "total_tokens": 5054344} {"current_steps": 56135, "total_steps": 76960, "loss": 0.2544, "lr": 1.0348334229922677e-05, "epoch": 14.588097713097714, "percentage": 72.94, "elapsed_time": "1:21:32", "remaining_time": "0:30:14", "throughput": 1033.22, "total_tokens": 5054824} {"current_steps": 56140, "total_steps": 76960, "loss": 0.551, "lr": 1.0343740741503174e-05, "epoch": 14.589397089397089, "percentage": 72.95, "elapsed_time": "1:21:32", "remaining_time": "0:30:14", "throughput": 1033.23, "total_tokens": 5055304} {"current_steps": 56145, "total_steps": 76960, "loss": 0.2396, "lr": 1.033914800686912e-05, "epoch": 14.590696465696466, "percentage": 72.95, "elapsed_time": "1:21:33", "remaining_time": "0:30:14", "throughput": 1033.24, "total_tokens": 5055784} {"current_steps": 56150, "total_steps": 76960, "loss": 0.0248, "lr": 1.033455602625674e-05, "epoch": 14.591995841995843, "percentage": 72.96, "elapsed_time": "1:21:33", "remaining_time": "0:30:13", "throughput": 1033.24, "total_tokens": 5056216} {"current_steps": 56155, "total_steps": 76960, "loss": 0.2877, "lr": 1.0329964799902187e-05, "epoch": 14.593295218295218, "percentage": 72.97, "elapsed_time": "1:21:33", "remaining_time": "0:30:13", "throughput": 1033.24, "total_tokens": 5056680} {"current_steps": 56160, "total_steps": 76960, "loss": 0.1791, "lr": 1.0325374328041598e-05, "epoch": 14.594594594594595, "percentage": 72.97, "elapsed_time": "1:21:34", "remaining_time": "0:30:12", "throughput": 1033.24, "total_tokens": 5057112} {"current_steps": 56165, "total_steps": 76960, "loss": 0.3164, "lr": 1.0320784610911069e-05, "epoch": 14.595893970893972, "percentage": 72.98, "elapsed_time": "1:21:34", "remaining_time": "0:30:12", "throughput": 1033.25, "total_tokens": 5057544} {"current_steps": 56170, "total_steps": 76960, "loss": 0.0656, "lr": 1.0316195648746662e-05, "epoch": 14.597193347193347, "percentage": 72.99, "elapsed_time": "1:21:35", "remaining_time": "0:30:11", "throughput": 1033.26, "total_tokens": 5058024} {"current_steps": 56175, "total_steps": 76960, "loss": 0.196, "lr": 1.0311607441784374e-05, "epoch": 14.598492723492724, "percentage": 72.99, "elapsed_time": "1:21:35", "remaining_time": "0:30:11", "throughput": 1033.26, "total_tokens": 5058472} {"current_steps": 56180, "total_steps": 76960, "loss": 0.0341, "lr": 1.0307019990260198e-05, "epoch": 14.5997920997921, "percentage": 73.0, "elapsed_time": "1:21:36", "remaining_time": "0:30:10", "throughput": 1033.26, "total_tokens": 5058920} {"current_steps": 56185, "total_steps": 76960, "loss": 0.0457, "lr": 1.030243329441006e-05, "epoch": 14.601091476091476, "percentage": 73.01, "elapsed_time": "1:21:36", "remaining_time": "0:30:10", "throughput": 1033.27, "total_tokens": 5059368} {"current_steps": 56190, "total_steps": 76960, "loss": 0.2158, "lr": 1.0297847354469853e-05, "epoch": 14.602390852390853, "percentage": 73.01, "elapsed_time": "1:21:36", "remaining_time": "0:30:10", "throughput": 1033.27, "total_tokens": 5059816} {"current_steps": 56195, "total_steps": 76960, "loss": 0.2533, "lr": 1.0293262170675441e-05, "epoch": 14.603690228690228, "percentage": 73.02, "elapsed_time": "1:21:37", "remaining_time": "0:30:09", "throughput": 1033.27, "total_tokens": 5060264} {"current_steps": 56200, "total_steps": 76960, "loss": 0.6392, "lr": 1.028867774326265e-05, "epoch": 14.604989604989605, "percentage": 73.02, "elapsed_time": "1:21:37", "remaining_time": "0:30:09", "throughput": 1033.27, "total_tokens": 5060680} {"current_steps": 56205, "total_steps": 76960, "loss": 0.3625, "lr": 1.0284094072467266e-05, "epoch": 14.606288981288982, "percentage": 73.03, "elapsed_time": "1:21:38", "remaining_time": "0:30:08", "throughput": 1033.27, "total_tokens": 5061128} {"current_steps": 56210, "total_steps": 76960, "loss": 0.4392, "lr": 1.0279511158525015e-05, "epoch": 14.607588357588357, "percentage": 73.04, "elapsed_time": "1:21:38", "remaining_time": "0:30:08", "throughput": 1033.28, "total_tokens": 5061560} {"current_steps": 56215, "total_steps": 76960, "loss": 0.1443, "lr": 1.0274929001671618e-05, "epoch": 14.608887733887734, "percentage": 73.04, "elapsed_time": "1:21:38", "remaining_time": "0:30:07", "throughput": 1033.27, "total_tokens": 5061976} {"current_steps": 56220, "total_steps": 76960, "loss": 0.4014, "lr": 1.0270347602142724e-05, "epoch": 14.61018711018711, "percentage": 73.05, "elapsed_time": "1:21:39", "remaining_time": "0:30:07", "throughput": 1033.28, "total_tokens": 5062440} {"current_steps": 56225, "total_steps": 76960, "loss": 0.0718, "lr": 1.0265766960173965e-05, "epoch": 14.611486486486486, "percentage": 73.06, "elapsed_time": "1:21:39", "remaining_time": "0:30:06", "throughput": 1033.28, "total_tokens": 5062872} {"current_steps": 56230, "total_steps": 76960, "loss": 0.1201, "lr": 1.0261187076000928e-05, "epoch": 14.612785862785863, "percentage": 73.06, "elapsed_time": "1:21:40", "remaining_time": "0:30:06", "throughput": 1033.29, "total_tokens": 5063352} {"current_steps": 56235, "total_steps": 76960, "loss": 0.2814, "lr": 1.0256607949859171e-05, "epoch": 14.61408523908524, "percentage": 73.07, "elapsed_time": "1:21:40", "remaining_time": "0:30:06", "throughput": 1033.3, "total_tokens": 5063816} {"current_steps": 56240, "total_steps": 76960, "loss": 0.1734, "lr": 1.0252029581984185e-05, "epoch": 14.615384615384615, "percentage": 73.08, "elapsed_time": "1:21:41", "remaining_time": "0:30:05", "throughput": 1033.3, "total_tokens": 5064280} {"current_steps": 56245, "total_steps": 76960, "loss": 0.1256, "lr": 1.0247451972611457e-05, "epoch": 14.616683991683992, "percentage": 73.08, "elapsed_time": "1:21:41", "remaining_time": "0:30:05", "throughput": 1033.32, "total_tokens": 5064760} {"current_steps": 56250, "total_steps": 76960, "loss": 0.1245, "lr": 1.0242875121976412e-05, "epoch": 14.617983367983367, "percentage": 73.09, "elapsed_time": "1:21:41", "remaining_time": "0:30:04", "throughput": 1033.31, "total_tokens": 5065176} {"current_steps": 56255, "total_steps": 76960, "loss": 0.2777, "lr": 1.0238299030314427e-05, "epoch": 14.619282744282744, "percentage": 73.1, "elapsed_time": "1:21:42", "remaining_time": "0:30:04", "throughput": 1033.32, "total_tokens": 5065624} {"current_steps": 56260, "total_steps": 76960, "loss": 0.5409, "lr": 1.0233723697860867e-05, "epoch": 14.620582120582121, "percentage": 73.1, "elapsed_time": "1:21:42", "remaining_time": "0:30:03", "throughput": 1033.32, "total_tokens": 5066088} {"current_steps": 56265, "total_steps": 76960, "loss": 0.2883, "lr": 1.0229149124851048e-05, "epoch": 14.621881496881496, "percentage": 73.11, "elapsed_time": "1:21:43", "remaining_time": "0:30:03", "throughput": 1033.32, "total_tokens": 5066520} {"current_steps": 56270, "total_steps": 76960, "loss": 0.2412, "lr": 1.0224575311520248e-05, "epoch": 14.623180873180873, "percentage": 73.12, "elapsed_time": "1:21:43", "remaining_time": "0:30:02", "throughput": 1033.33, "total_tokens": 5067000} {"current_steps": 56275, "total_steps": 76960, "loss": 0.79, "lr": 1.022000225810369e-05, "epoch": 14.62448024948025, "percentage": 73.12, "elapsed_time": "1:21:43", "remaining_time": "0:30:02", "throughput": 1033.34, "total_tokens": 5067448} {"current_steps": 56280, "total_steps": 76960, "loss": 0.3056, "lr": 1.0215429964836587e-05, "epoch": 14.625779625779625, "percentage": 73.13, "elapsed_time": "1:21:44", "remaining_time": "0:30:02", "throughput": 1033.34, "total_tokens": 5067880} {"current_steps": 56285, "total_steps": 76960, "loss": 0.2332, "lr": 1.0210858431954076e-05, "epoch": 14.627079002079002, "percentage": 73.14, "elapsed_time": "1:21:44", "remaining_time": "0:30:01", "throughput": 1033.35, "total_tokens": 5068360} {"current_steps": 56290, "total_steps": 76960, "loss": 0.4399, "lr": 1.0206287659691294e-05, "epoch": 14.628378378378379, "percentage": 73.14, "elapsed_time": "1:21:45", "remaining_time": "0:30:01", "throughput": 1033.36, "total_tokens": 5068840} {"current_steps": 56295, "total_steps": 76960, "loss": 0.3133, "lr": 1.0201717648283308e-05, "epoch": 14.629677754677754, "percentage": 73.15, "elapsed_time": "1:21:45", "remaining_time": "0:30:00", "throughput": 1033.35, "total_tokens": 5069256} {"current_steps": 56300, "total_steps": 76960, "loss": 0.0802, "lr": 1.019714839796516e-05, "epoch": 14.630977130977131, "percentage": 73.15, "elapsed_time": "1:21:46", "remaining_time": "0:30:00", "throughput": 1033.36, "total_tokens": 5069704} {"current_steps": 56305, "total_steps": 76960, "loss": 0.0229, "lr": 1.019257990897185e-05, "epoch": 14.632276507276508, "percentage": 73.16, "elapsed_time": "1:21:46", "remaining_time": "0:29:59", "throughput": 1033.36, "total_tokens": 5070136} {"current_steps": 56310, "total_steps": 76960, "loss": 0.0801, "lr": 1.0188012181538357e-05, "epoch": 14.633575883575883, "percentage": 73.17, "elapsed_time": "1:21:46", "remaining_time": "0:29:59", "throughput": 1033.36, "total_tokens": 5070552} {"current_steps": 56315, "total_steps": 76960, "loss": 0.0858, "lr": 1.0183445215899584e-05, "epoch": 14.63487525987526, "percentage": 73.17, "elapsed_time": "1:21:47", "remaining_time": "0:29:59", "throughput": 1033.36, "total_tokens": 5071000} {"current_steps": 56320, "total_steps": 76960, "loss": 0.2504, "lr": 1.0178879012290415e-05, "epoch": 14.636174636174637, "percentage": 73.18, "elapsed_time": "1:21:47", "remaining_time": "0:29:58", "throughput": 1033.37, "total_tokens": 5071480} {"current_steps": 56325, "total_steps": 76960, "loss": 0.4397, "lr": 1.017431357094571e-05, "epoch": 14.637474012474012, "percentage": 73.19, "elapsed_time": "1:21:48", "remaining_time": "0:29:58", "throughput": 1033.38, "total_tokens": 5071976} {"current_steps": 56330, "total_steps": 76960, "loss": 0.1834, "lr": 1.016974889210025e-05, "epoch": 14.638773388773389, "percentage": 73.19, "elapsed_time": "1:21:48", "remaining_time": "0:29:57", "throughput": 1033.39, "total_tokens": 5072424} {"current_steps": 56335, "total_steps": 76960, "loss": 0.0802, "lr": 1.0165184975988818e-05, "epoch": 14.640072765072766, "percentage": 73.2, "elapsed_time": "1:21:48", "remaining_time": "0:29:57", "throughput": 1033.39, "total_tokens": 5072856} {"current_steps": 56340, "total_steps": 76960, "loss": 0.1423, "lr": 1.0160621822846133e-05, "epoch": 14.641372141372141, "percentage": 73.21, "elapsed_time": "1:21:49", "remaining_time": "0:29:56", "throughput": 1033.39, "total_tokens": 5073304} {"current_steps": 56345, "total_steps": 76960, "loss": 0.1923, "lr": 1.0156059432906898e-05, "epoch": 14.642671517671518, "percentage": 73.21, "elapsed_time": "1:21:49", "remaining_time": "0:29:56", "throughput": 1033.39, "total_tokens": 5073736} {"current_steps": 56350, "total_steps": 76960, "loss": 0.0498, "lr": 1.0151497806405741e-05, "epoch": 14.643970893970893, "percentage": 73.22, "elapsed_time": "1:21:50", "remaining_time": "0:29:55", "throughput": 1033.4, "total_tokens": 5074184} {"current_steps": 56355, "total_steps": 76960, "loss": 0.1317, "lr": 1.0146936943577284e-05, "epoch": 14.64527027027027, "percentage": 73.23, "elapsed_time": "1:21:50", "remaining_time": "0:29:55", "throughput": 1033.4, "total_tokens": 5074632} {"current_steps": 56360, "total_steps": 76960, "loss": 0.6031, "lr": 1.0142376844656085e-05, "epoch": 14.646569646569647, "percentage": 73.23, "elapsed_time": "1:21:51", "remaining_time": "0:29:55", "throughput": 1033.41, "total_tokens": 5075096} {"current_steps": 56365, "total_steps": 76960, "loss": 0.0935, "lr": 1.013781750987669e-05, "epoch": 14.647869022869022, "percentage": 73.24, "elapsed_time": "1:21:51", "remaining_time": "0:29:54", "throughput": 1033.42, "total_tokens": 5075608} {"current_steps": 56370, "total_steps": 76960, "loss": 0.0449, "lr": 1.0133258939473573e-05, "epoch": 14.6491683991684, "percentage": 73.25, "elapsed_time": "1:21:51", "remaining_time": "0:29:54", "throughput": 1033.43, "total_tokens": 5076056} {"current_steps": 56375, "total_steps": 76960, "loss": 0.1765, "lr": 1.012870113368119e-05, "epoch": 14.650467775467776, "percentage": 73.25, "elapsed_time": "1:21:52", "remaining_time": "0:29:53", "throughput": 1033.43, "total_tokens": 5076504} {"current_steps": 56380, "total_steps": 76960, "loss": 0.0291, "lr": 1.0124144092733967e-05, "epoch": 14.651767151767151, "percentage": 73.26, "elapsed_time": "1:21:52", "remaining_time": "0:29:53", "throughput": 1033.43, "total_tokens": 5076920} {"current_steps": 56385, "total_steps": 76960, "loss": 0.4955, "lr": 1.0119587816866258e-05, "epoch": 14.653066528066528, "percentage": 73.27, "elapsed_time": "1:21:53", "remaining_time": "0:29:52", "throughput": 1033.43, "total_tokens": 5077352} {"current_steps": 56390, "total_steps": 76960, "loss": 0.3668, "lr": 1.0115032306312414e-05, "epoch": 14.654365904365905, "percentage": 73.27, "elapsed_time": "1:21:53", "remaining_time": "0:29:52", "throughput": 1033.43, "total_tokens": 5077800} {"current_steps": 56395, "total_steps": 76960, "loss": 0.0197, "lr": 1.0110477561306714e-05, "epoch": 14.65566528066528, "percentage": 73.28, "elapsed_time": "1:21:53", "remaining_time": "0:29:51", "throughput": 1033.44, "total_tokens": 5078280} {"current_steps": 56400, "total_steps": 76960, "loss": 0.4855, "lr": 1.0105923582083424e-05, "epoch": 14.656964656964657, "percentage": 73.28, "elapsed_time": "1:21:54", "remaining_time": "0:29:51", "throughput": 1033.46, "total_tokens": 5078792} {"current_steps": 56405, "total_steps": 76960, "loss": 0.1063, "lr": 1.010137036887675e-05, "epoch": 14.658264033264032, "percentage": 73.29, "elapsed_time": "1:21:54", "remaining_time": "0:29:51", "throughput": 1033.47, "total_tokens": 5079272} {"current_steps": 56410, "total_steps": 76960, "loss": 0.2078, "lr": 1.0096817921920871e-05, "epoch": 14.65956340956341, "percentage": 73.3, "elapsed_time": "1:21:55", "remaining_time": "0:29:50", "throughput": 1033.47, "total_tokens": 5079720} {"current_steps": 56415, "total_steps": 76960, "loss": 0.1141, "lr": 1.0092266241449927e-05, "epoch": 14.660862785862786, "percentage": 73.3, "elapsed_time": "1:21:55", "remaining_time": "0:29:50", "throughput": 1033.48, "total_tokens": 5080184} {"current_steps": 56420, "total_steps": 76960, "loss": 0.2343, "lr": 1.0087715327698022e-05, "epoch": 14.662162162162161, "percentage": 73.31, "elapsed_time": "1:21:56", "remaining_time": "0:29:49", "throughput": 1033.49, "total_tokens": 5080664} {"current_steps": 56425, "total_steps": 76960, "loss": 0.0606, "lr": 1.0083165180899196e-05, "epoch": 14.663461538461538, "percentage": 73.32, "elapsed_time": "1:21:56", "remaining_time": "0:29:49", "throughput": 1033.5, "total_tokens": 5081128} {"current_steps": 56430, "total_steps": 76960, "loss": 0.0972, "lr": 1.007861580128749e-05, "epoch": 14.664760914760915, "percentage": 73.32, "elapsed_time": "1:21:56", "remaining_time": "0:29:48", "throughput": 1033.51, "total_tokens": 5081624} {"current_steps": 56435, "total_steps": 76960, "loss": 0.3593, "lr": 1.0074067189096855e-05, "epoch": 14.66606029106029, "percentage": 73.33, "elapsed_time": "1:21:57", "remaining_time": "0:29:48", "throughput": 1033.51, "total_tokens": 5082040} {"current_steps": 56440, "total_steps": 76960, "loss": 0.2447, "lr": 1.0069519344561259e-05, "epoch": 14.667359667359667, "percentage": 73.34, "elapsed_time": "1:21:57", "remaining_time": "0:29:47", "throughput": 1033.51, "total_tokens": 5082472} {"current_steps": 56445, "total_steps": 76960, "loss": 0.0606, "lr": 1.0064972267914583e-05, "epoch": 14.668659043659044, "percentage": 73.34, "elapsed_time": "1:21:58", "remaining_time": "0:29:47", "throughput": 1033.51, "total_tokens": 5082936} {"current_steps": 56450, "total_steps": 76960, "loss": 0.0602, "lr": 1.0060425959390688e-05, "epoch": 14.66995841995842, "percentage": 73.35, "elapsed_time": "1:21:58", "remaining_time": "0:29:47", "throughput": 1033.52, "total_tokens": 5083384} {"current_steps": 56455, "total_steps": 76960, "loss": 0.0527, "lr": 1.0055880419223413e-05, "epoch": 14.671257796257796, "percentage": 73.36, "elapsed_time": "1:21:58", "remaining_time": "0:29:46", "throughput": 1033.52, "total_tokens": 5083832} {"current_steps": 56460, "total_steps": 76960, "loss": 0.0277, "lr": 1.0051335647646515e-05, "epoch": 14.672557172557173, "percentage": 73.36, "elapsed_time": "1:21:59", "remaining_time": "0:29:46", "throughput": 1033.52, "total_tokens": 5084264} {"current_steps": 56465, "total_steps": 76960, "loss": 0.3496, "lr": 1.0046791644893758e-05, "epoch": 14.673856548856548, "percentage": 73.37, "elapsed_time": "1:21:59", "remaining_time": "0:29:45", "throughput": 1033.53, "total_tokens": 5084712} {"current_steps": 56470, "total_steps": 76960, "loss": 0.1425, "lr": 1.0042248411198824e-05, "epoch": 14.675155925155925, "percentage": 73.38, "elapsed_time": "1:22:00", "remaining_time": "0:29:45", "throughput": 1033.53, "total_tokens": 5085144} {"current_steps": 56475, "total_steps": 76960, "loss": 0.4932, "lr": 1.0037705946795386e-05, "epoch": 14.676455301455302, "percentage": 73.38, "elapsed_time": "1:22:00", "remaining_time": "0:29:44", "throughput": 1033.53, "total_tokens": 5085592} {"current_steps": 56480, "total_steps": 76960, "loss": 0.0346, "lr": 1.0033164251917069e-05, "epoch": 14.677754677754677, "percentage": 73.39, "elapsed_time": "1:22:01", "remaining_time": "0:29:44", "throughput": 1033.53, "total_tokens": 5086008} {"current_steps": 56485, "total_steps": 76960, "loss": 0.3661, "lr": 1.0028623326797465e-05, "epoch": 14.679054054054054, "percentage": 73.4, "elapsed_time": "1:22:01", "remaining_time": "0:29:43", "throughput": 1033.53, "total_tokens": 5086472} {"current_steps": 56490, "total_steps": 76960, "loss": 0.3175, "lr": 1.0024083171670095e-05, "epoch": 14.68035343035343, "percentage": 73.4, "elapsed_time": "1:22:01", "remaining_time": "0:29:43", "throughput": 1033.54, "total_tokens": 5086952} {"current_steps": 56495, "total_steps": 76960, "loss": 0.1338, "lr": 1.001954378676849e-05, "epoch": 14.681652806652806, "percentage": 73.41, "elapsed_time": "1:22:02", "remaining_time": "0:29:43", "throughput": 1033.54, "total_tokens": 5087384} {"current_steps": 56500, "total_steps": 76960, "loss": 0.1729, "lr": 1.0015005172326092e-05, "epoch": 14.682952182952183, "percentage": 73.41, "elapsed_time": "1:22:02", "remaining_time": "0:29:42", "throughput": 1033.55, "total_tokens": 5087832} {"current_steps": 56505, "total_steps": 76960, "loss": 0.3185, "lr": 1.0010467328576342e-05, "epoch": 14.684251559251559, "percentage": 73.42, "elapsed_time": "1:22:03", "remaining_time": "0:29:42", "throughput": 1033.55, "total_tokens": 5088280} {"current_steps": 56510, "total_steps": 76960, "loss": 0.2067, "lr": 1.0005930255752614e-05, "epoch": 14.685550935550935, "percentage": 73.43, "elapsed_time": "1:22:03", "remaining_time": "0:29:41", "throughput": 1033.56, "total_tokens": 5088744} {"current_steps": 56515, "total_steps": 76960, "loss": 0.1591, "lr": 1.0001393954088257e-05, "epoch": 14.686850311850312, "percentage": 73.43, "elapsed_time": "1:22:03", "remaining_time": "0:29:41", "throughput": 1033.56, "total_tokens": 5089192} {"current_steps": 56520, "total_steps": 76960, "loss": 0.0412, "lr": 9.99685842381659e-06, "epoch": 14.688149688149688, "percentage": 73.44, "elapsed_time": "1:22:04", "remaining_time": "0:29:40", "throughput": 1033.56, "total_tokens": 5089624} {"current_steps": 56525, "total_steps": 76960, "loss": 0.1596, "lr": 9.99232366517086e-06, "epoch": 14.689449064449065, "percentage": 73.45, "elapsed_time": "1:22:04", "remaining_time": "0:29:40", "throughput": 1033.57, "total_tokens": 5090072} {"current_steps": 56530, "total_steps": 76960, "loss": 0.1974, "lr": 9.987789678384313e-06, "epoch": 14.690748440748441, "percentage": 73.45, "elapsed_time": "1:22:05", "remaining_time": "0:29:39", "throughput": 1033.57, "total_tokens": 5090536} {"current_steps": 56535, "total_steps": 76960, "loss": 0.1003, "lr": 9.98325646369012e-06, "epoch": 14.692047817047817, "percentage": 73.46, "elapsed_time": "1:22:05", "remaining_time": "0:29:39", "throughput": 1033.58, "total_tokens": 5090984} {"current_steps": 56540, "total_steps": 76960, "loss": 0.141, "lr": 9.97872402132144e-06, "epoch": 14.693347193347194, "percentage": 73.47, "elapsed_time": "1:22:06", "remaining_time": "0:29:39", "throughput": 1033.58, "total_tokens": 5091400} {"current_steps": 56545, "total_steps": 76960, "loss": 0.0333, "lr": 9.974192351511368e-06, "epoch": 14.69464656964657, "percentage": 73.47, "elapsed_time": "1:22:06", "remaining_time": "0:29:38", "throughput": 1033.58, "total_tokens": 5091864} {"current_steps": 56550, "total_steps": 76960, "loss": 0.2326, "lr": 9.969661454492984e-06, "epoch": 14.695945945945946, "percentage": 73.48, "elapsed_time": "1:22:06", "remaining_time": "0:29:38", "throughput": 1033.6, "total_tokens": 5092360} {"current_steps": 56555, "total_steps": 76960, "loss": 0.5713, "lr": 9.96513133049931e-06, "epoch": 14.697245322245323, "percentage": 73.49, "elapsed_time": "1:22:07", "remaining_time": "0:29:37", "throughput": 1033.6, "total_tokens": 5092824} {"current_steps": 56560, "total_steps": 76960, "loss": 0.3776, "lr": 9.960601979763347e-06, "epoch": 14.698544698544698, "percentage": 73.49, "elapsed_time": "1:22:07", "remaining_time": "0:29:37", "throughput": 1033.61, "total_tokens": 5093288} {"current_steps": 56565, "total_steps": 76960, "loss": 0.157, "lr": 9.956073402518026e-06, "epoch": 14.699844074844075, "percentage": 73.5, "elapsed_time": "1:22:08", "remaining_time": "0:29:36", "throughput": 1033.62, "total_tokens": 5093768} {"current_steps": 56570, "total_steps": 76960, "loss": 0.047, "lr": 9.951545598996273e-06, "epoch": 14.701143451143452, "percentage": 73.51, "elapsed_time": "1:22:08", "remaining_time": "0:29:36", "throughput": 1033.62, "total_tokens": 5094216} {"current_steps": 56575, "total_steps": 76960, "loss": 0.4323, "lr": 9.947018569430947e-06, "epoch": 14.702442827442827, "percentage": 73.51, "elapsed_time": "1:22:08", "remaining_time": "0:29:35", "throughput": 1033.63, "total_tokens": 5094680} {"current_steps": 56580, "total_steps": 76960, "loss": 0.5396, "lr": 9.942492314054872e-06, "epoch": 14.703742203742204, "percentage": 73.52, "elapsed_time": "1:22:09", "remaining_time": "0:29:35", "throughput": 1033.64, "total_tokens": 5095128} {"current_steps": 56585, "total_steps": 76960, "loss": 0.2913, "lr": 9.937966833100845e-06, "epoch": 14.70504158004158, "percentage": 73.53, "elapsed_time": "1:22:09", "remaining_time": "0:29:35", "throughput": 1033.64, "total_tokens": 5095592} {"current_steps": 56590, "total_steps": 76960, "loss": 0.1507, "lr": 9.933442126801615e-06, "epoch": 14.706340956340956, "percentage": 73.53, "elapsed_time": "1:22:10", "remaining_time": "0:29:34", "throughput": 1033.65, "total_tokens": 5096072} {"current_steps": 56595, "total_steps": 76960, "loss": 0.2953, "lr": 9.9289181953899e-06, "epoch": 14.707640332640333, "percentage": 73.54, "elapsed_time": "1:22:10", "remaining_time": "0:29:34", "throughput": 1033.65, "total_tokens": 5096488} {"current_steps": 56600, "total_steps": 76960, "loss": 0.5229, "lr": 9.924395039098355e-06, "epoch": 14.70893970893971, "percentage": 73.54, "elapsed_time": "1:22:10", "remaining_time": "0:29:33", "throughput": 1033.66, "total_tokens": 5096952} {"current_steps": 56605, "total_steps": 76960, "loss": 0.0461, "lr": 9.919872658159626e-06, "epoch": 14.710239085239085, "percentage": 73.55, "elapsed_time": "1:22:11", "remaining_time": "0:29:33", "throughput": 1033.66, "total_tokens": 5097384} {"current_steps": 56610, "total_steps": 76960, "loss": 0.0221, "lr": 9.915351052806288e-06, "epoch": 14.711538461538462, "percentage": 73.56, "elapsed_time": "1:22:11", "remaining_time": "0:29:32", "throughput": 1033.66, "total_tokens": 5097848} {"current_steps": 56615, "total_steps": 76960, "loss": 0.175, "lr": 9.910830223270906e-06, "epoch": 14.712837837837839, "percentage": 73.56, "elapsed_time": "1:22:12", "remaining_time": "0:29:32", "throughput": 1033.67, "total_tokens": 5098296} {"current_steps": 56620, "total_steps": 76960, "loss": 0.0898, "lr": 9.906310169785973e-06, "epoch": 14.714137214137214, "percentage": 73.57, "elapsed_time": "1:22:12", "remaining_time": "0:29:31", "throughput": 1033.67, "total_tokens": 5098744} {"current_steps": 56625, "total_steps": 76960, "loss": 0.1751, "lr": 9.901790892583974e-06, "epoch": 14.71543659043659, "percentage": 73.58, "elapsed_time": "1:22:13", "remaining_time": "0:29:31", "throughput": 1033.67, "total_tokens": 5099176} {"current_steps": 56630, "total_steps": 76960, "loss": 0.3654, "lr": 9.897272391897333e-06, "epoch": 14.716735966735968, "percentage": 73.58, "elapsed_time": "1:22:13", "remaining_time": "0:29:31", "throughput": 1033.68, "total_tokens": 5099656} {"current_steps": 56635, "total_steps": 76960, "loss": 0.0992, "lr": 9.892754667958455e-06, "epoch": 14.718035343035343, "percentage": 73.59, "elapsed_time": "1:22:13", "remaining_time": "0:29:30", "throughput": 1033.69, "total_tokens": 5100120} {"current_steps": 56640, "total_steps": 76960, "loss": 0.2204, "lr": 9.888237720999677e-06, "epoch": 14.71933471933472, "percentage": 73.6, "elapsed_time": "1:22:14", "remaining_time": "0:29:30", "throughput": 1033.71, "total_tokens": 5100632} {"current_steps": 56645, "total_steps": 76960, "loss": 0.2338, "lr": 9.883721551253303e-06, "epoch": 14.720634095634095, "percentage": 73.6, "elapsed_time": "1:22:14", "remaining_time": "0:29:29", "throughput": 1033.71, "total_tokens": 5101080} {"current_steps": 56650, "total_steps": 76960, "loss": 0.2709, "lr": 9.879206158951623e-06, "epoch": 14.721933471933472, "percentage": 73.61, "elapsed_time": "1:22:15", "remaining_time": "0:29:29", "throughput": 1033.71, "total_tokens": 5101528} {"current_steps": 56655, "total_steps": 76960, "loss": 0.1897, "lr": 9.874691544326851e-06, "epoch": 14.723232848232849, "percentage": 73.62, "elapsed_time": "1:22:15", "remaining_time": "0:29:28", "throughput": 1033.72, "total_tokens": 5101976} {"current_steps": 56660, "total_steps": 76960, "loss": 0.2669, "lr": 9.870177707611183e-06, "epoch": 14.724532224532224, "percentage": 73.62, "elapsed_time": "1:22:15", "remaining_time": "0:29:28", "throughput": 1033.73, "total_tokens": 5102456} {"current_steps": 56665, "total_steps": 76960, "loss": 0.2851, "lr": 9.865664649036774e-06, "epoch": 14.7258316008316, "percentage": 73.63, "elapsed_time": "1:22:16", "remaining_time": "0:29:28", "throughput": 1033.73, "total_tokens": 5102920} {"current_steps": 56670, "total_steps": 76960, "loss": 0.5248, "lr": 9.861152368835742e-06, "epoch": 14.727130977130978, "percentage": 73.64, "elapsed_time": "1:22:16", "remaining_time": "0:29:27", "throughput": 1033.74, "total_tokens": 5103384} {"current_steps": 56675, "total_steps": 76960, "loss": 0.2172, "lr": 9.856640867240139e-06, "epoch": 14.728430353430353, "percentage": 73.64, "elapsed_time": "1:22:17", "remaining_time": "0:29:27", "throughput": 1033.74, "total_tokens": 5103832} {"current_steps": 56680, "total_steps": 76960, "loss": 0.4755, "lr": 9.852130144482017e-06, "epoch": 14.72972972972973, "percentage": 73.65, "elapsed_time": "1:22:17", "remaining_time": "0:29:26", "throughput": 1033.74, "total_tokens": 5104248} {"current_steps": 56685, "total_steps": 76960, "loss": 0.2965, "lr": 9.847620200793343e-06, "epoch": 14.731029106029107, "percentage": 73.66, "elapsed_time": "1:22:18", "remaining_time": "0:29:26", "throughput": 1033.74, "total_tokens": 5104680} {"current_steps": 56690, "total_steps": 76960, "loss": 0.439, "lr": 9.843111036406092e-06, "epoch": 14.732328482328482, "percentage": 73.66, "elapsed_time": "1:22:18", "remaining_time": "0:29:25", "throughput": 1033.75, "total_tokens": 5105160} {"current_steps": 56695, "total_steps": 76960, "loss": 0.363, "lr": 9.838602651552146e-06, "epoch": 14.733627858627859, "percentage": 73.67, "elapsed_time": "1:22:18", "remaining_time": "0:29:25", "throughput": 1033.75, "total_tokens": 5105576} {"current_steps": 56700, "total_steps": 76960, "loss": 0.1218, "lr": 9.834095046463407e-06, "epoch": 14.734927234927234, "percentage": 73.67, "elapsed_time": "1:22:19", "remaining_time": "0:29:24", "throughput": 1033.75, "total_tokens": 5105992} {"current_steps": 56705, "total_steps": 76960, "loss": 0.1828, "lr": 9.829588221371694e-06, "epoch": 14.736226611226611, "percentage": 73.68, "elapsed_time": "1:22:19", "remaining_time": "0:29:24", "throughput": 1033.75, "total_tokens": 5106456} {"current_steps": 56710, "total_steps": 76960, "loss": 0.0612, "lr": 9.825082176508782e-06, "epoch": 14.737525987525988, "percentage": 73.69, "elapsed_time": "1:22:20", "remaining_time": "0:29:24", "throughput": 1033.76, "total_tokens": 5106904} {"current_steps": 56715, "total_steps": 76960, "loss": 0.0765, "lr": 9.820576912106446e-06, "epoch": 14.738825363825363, "percentage": 73.69, "elapsed_time": "1:22:20", "remaining_time": "0:29:23", "throughput": 1033.76, "total_tokens": 5107336} {"current_steps": 56720, "total_steps": 76960, "loss": 0.0217, "lr": 9.816072428396375e-06, "epoch": 14.74012474012474, "percentage": 73.7, "elapsed_time": "1:22:20", "remaining_time": "0:29:23", "throughput": 1033.76, "total_tokens": 5107768} {"current_steps": 56725, "total_steps": 76960, "loss": 0.44, "lr": 9.811568725610246e-06, "epoch": 14.741424116424117, "percentage": 73.71, "elapsed_time": "1:22:21", "remaining_time": "0:29:22", "throughput": 1033.77, "total_tokens": 5108232} {"current_steps": 56730, "total_steps": 76960, "loss": 0.2378, "lr": 9.80706580397969e-06, "epoch": 14.742723492723492, "percentage": 73.71, "elapsed_time": "1:22:21", "remaining_time": "0:29:22", "throughput": 1033.77, "total_tokens": 5108696} {"current_steps": 56735, "total_steps": 76960, "loss": 0.1031, "lr": 9.802563663736305e-06, "epoch": 14.744022869022869, "percentage": 73.72, "elapsed_time": "1:22:22", "remaining_time": "0:29:21", "throughput": 1033.78, "total_tokens": 5109176} {"current_steps": 56740, "total_steps": 76960, "loss": 0.2068, "lr": 9.798062305111625e-06, "epoch": 14.745322245322246, "percentage": 73.73, "elapsed_time": "1:22:22", "remaining_time": "0:29:21", "throughput": 1033.79, "total_tokens": 5109640} {"current_steps": 56745, "total_steps": 76960, "loss": 0.2716, "lr": 9.793561728337176e-06, "epoch": 14.746621621621621, "percentage": 73.73, "elapsed_time": "1:22:23", "remaining_time": "0:29:20", "throughput": 1033.79, "total_tokens": 5110072} {"current_steps": 56750, "total_steps": 76960, "loss": 0.0837, "lr": 9.789061933644405e-06, "epoch": 14.747920997920998, "percentage": 73.74, "elapsed_time": "1:22:23", "remaining_time": "0:29:20", "throughput": 1033.79, "total_tokens": 5110504} {"current_steps": 56755, "total_steps": 76960, "loss": 0.206, "lr": 9.784562921264767e-06, "epoch": 14.749220374220375, "percentage": 73.75, "elapsed_time": "1:22:23", "remaining_time": "0:29:20", "throughput": 1033.79, "total_tokens": 5110920} {"current_steps": 56760, "total_steps": 76960, "loss": 0.1526, "lr": 9.780064691429625e-06, "epoch": 14.75051975051975, "percentage": 73.75, "elapsed_time": "1:22:24", "remaining_time": "0:29:19", "throughput": 1033.79, "total_tokens": 5111368} {"current_steps": 56765, "total_steps": 76960, "loss": 0.0821, "lr": 9.77556724437034e-06, "epoch": 14.751819126819127, "percentage": 73.76, "elapsed_time": "1:22:24", "remaining_time": "0:29:19", "throughput": 1033.79, "total_tokens": 5111800} {"current_steps": 56770, "total_steps": 76960, "loss": 0.4993, "lr": 9.771070580318225e-06, "epoch": 14.753118503118504, "percentage": 73.77, "elapsed_time": "1:22:25", "remaining_time": "0:29:18", "throughput": 1033.79, "total_tokens": 5112216} {"current_steps": 56775, "total_steps": 76960, "loss": 0.1857, "lr": 9.766574699504536e-06, "epoch": 14.754417879417879, "percentage": 73.77, "elapsed_time": "1:22:25", "remaining_time": "0:29:18", "throughput": 1033.79, "total_tokens": 5112648} {"current_steps": 56780, "total_steps": 76960, "loss": 0.1992, "lr": 9.762079602160515e-06, "epoch": 14.755717255717256, "percentage": 73.78, "elapsed_time": "1:22:25", "remaining_time": "0:29:17", "throughput": 1033.8, "total_tokens": 5113128} {"current_steps": 56785, "total_steps": 76960, "loss": 0.2569, "lr": 9.757585288517328e-06, "epoch": 14.757016632016633, "percentage": 73.79, "elapsed_time": "1:22:26", "remaining_time": "0:29:17", "throughput": 1033.81, "total_tokens": 5113624} {"current_steps": 56790, "total_steps": 76960, "loss": 0.0655, "lr": 9.753091758806146e-06, "epoch": 14.758316008316008, "percentage": 73.79, "elapsed_time": "1:22:26", "remaining_time": "0:29:16", "throughput": 1033.81, "total_tokens": 5114056} {"current_steps": 56795, "total_steps": 76960, "loss": 0.3811, "lr": 9.748599013258055e-06, "epoch": 14.759615384615385, "percentage": 73.8, "elapsed_time": "1:22:27", "remaining_time": "0:29:16", "throughput": 1033.82, "total_tokens": 5114488} {"current_steps": 56800, "total_steps": 76960, "loss": 0.3044, "lr": 9.744107052104128e-06, "epoch": 14.76091476091476, "percentage": 73.8, "elapsed_time": "1:22:27", "remaining_time": "0:29:16", "throughput": 1033.81, "total_tokens": 5114904} {"current_steps": 56805, "total_steps": 76960, "loss": 0.3865, "lr": 9.739615875575395e-06, "epoch": 14.762214137214137, "percentage": 73.81, "elapsed_time": "1:22:28", "remaining_time": "0:29:15", "throughput": 1033.81, "total_tokens": 5115336} {"current_steps": 56810, "total_steps": 76960, "loss": 0.3577, "lr": 9.73512548390285e-06, "epoch": 14.763513513513514, "percentage": 73.82, "elapsed_time": "1:22:28", "remaining_time": "0:29:15", "throughput": 1033.82, "total_tokens": 5115784} {"current_steps": 56815, "total_steps": 76960, "loss": 0.2436, "lr": 9.730635877317415e-06, "epoch": 14.76481288981289, "percentage": 73.82, "elapsed_time": "1:22:28", "remaining_time": "0:29:14", "throughput": 1033.82, "total_tokens": 5116248} {"current_steps": 56820, "total_steps": 76960, "loss": 0.0493, "lr": 9.726147056050017e-06, "epoch": 14.766112266112266, "percentage": 73.83, "elapsed_time": "1:22:29", "remaining_time": "0:29:14", "throughput": 1033.83, "total_tokens": 5116696} {"current_steps": 56825, "total_steps": 76960, "loss": 0.0068, "lr": 9.7216590203315e-06, "epoch": 14.767411642411643, "percentage": 73.84, "elapsed_time": "1:22:29", "remaining_time": "0:29:13", "throughput": 1033.84, "total_tokens": 5117176} {"current_steps": 56830, "total_steps": 76960, "loss": 0.2938, "lr": 9.717171770392711e-06, "epoch": 14.768711018711018, "percentage": 73.84, "elapsed_time": "1:22:30", "remaining_time": "0:29:13", "throughput": 1033.84, "total_tokens": 5117624} {"current_steps": 56835, "total_steps": 76960, "loss": 0.5362, "lr": 9.712685306464408e-06, "epoch": 14.770010395010395, "percentage": 73.85, "elapsed_time": "1:22:30", "remaining_time": "0:29:12", "throughput": 1033.84, "total_tokens": 5118040} {"current_steps": 56840, "total_steps": 76960, "loss": 0.4679, "lr": 9.708199628777351e-06, "epoch": 14.771309771309772, "percentage": 73.86, "elapsed_time": "1:22:30", "remaining_time": "0:29:12", "throughput": 1033.84, "total_tokens": 5118472} {"current_steps": 56845, "total_steps": 76960, "loss": 0.1284, "lr": 9.703714737562246e-06, "epoch": 14.772609147609147, "percentage": 73.86, "elapsed_time": "1:22:31", "remaining_time": "0:29:12", "throughput": 1033.84, "total_tokens": 5118904} {"current_steps": 56850, "total_steps": 76960, "loss": 0.1066, "lr": 9.699230633049742e-06, "epoch": 14.773908523908524, "percentage": 73.87, "elapsed_time": "1:22:31", "remaining_time": "0:29:11", "throughput": 1033.84, "total_tokens": 5119336} {"current_steps": 56855, "total_steps": 76960, "loss": 0.0086, "lr": 9.694747315470473e-06, "epoch": 14.7752079002079, "percentage": 73.88, "elapsed_time": "1:22:32", "remaining_time": "0:29:11", "throughput": 1033.85, "total_tokens": 5119816} {"current_steps": 56860, "total_steps": 76960, "loss": 0.2941, "lr": 9.690264785055005e-06, "epoch": 14.776507276507276, "percentage": 73.88, "elapsed_time": "1:22:32", "remaining_time": "0:29:10", "throughput": 1033.85, "total_tokens": 5120232} {"current_steps": 56865, "total_steps": 76960, "loss": 0.1049, "lr": 9.6857830420339e-06, "epoch": 14.777806652806653, "percentage": 73.89, "elapsed_time": "1:22:33", "remaining_time": "0:29:10", "throughput": 1033.85, "total_tokens": 5120680} {"current_steps": 56870, "total_steps": 76960, "loss": 0.2883, "lr": 9.681302086637634e-06, "epoch": 14.779106029106028, "percentage": 73.9, "elapsed_time": "1:22:33", "remaining_time": "0:29:09", "throughput": 1033.85, "total_tokens": 5121112} {"current_steps": 56875, "total_steps": 76960, "loss": 0.1042, "lr": 9.676821919096682e-06, "epoch": 14.780405405405405, "percentage": 73.9, "elapsed_time": "1:22:33", "remaining_time": "0:29:09", "throughput": 1033.85, "total_tokens": 5121544} {"current_steps": 56880, "total_steps": 76960, "loss": 0.2307, "lr": 9.67234253964146e-06, "epoch": 14.781704781704782, "percentage": 73.91, "elapsed_time": "1:22:34", "remaining_time": "0:29:08", "throughput": 1033.86, "total_tokens": 5122008} {"current_steps": 56885, "total_steps": 76960, "loss": 0.2571, "lr": 9.667863948502356e-06, "epoch": 14.783004158004157, "percentage": 73.92, "elapsed_time": "1:22:34", "remaining_time": "0:29:08", "throughput": 1033.85, "total_tokens": 5122408} {"current_steps": 56890, "total_steps": 76960, "loss": 0.327, "lr": 9.663386145909692e-06, "epoch": 14.784303534303534, "percentage": 73.92, "elapsed_time": "1:22:35", "remaining_time": "0:29:08", "throughput": 1033.86, "total_tokens": 5122856} {"current_steps": 56895, "total_steps": 76960, "loss": 0.2943, "lr": 9.658909132093783e-06, "epoch": 14.785602910602911, "percentage": 73.93, "elapsed_time": "1:22:35", "remaining_time": "0:29:07", "throughput": 1033.87, "total_tokens": 5123320} {"current_steps": 56900, "total_steps": 76960, "loss": 0.0877, "lr": 9.654432907284874e-06, "epoch": 14.786902286902286, "percentage": 73.93, "elapsed_time": "1:22:35", "remaining_time": "0:29:07", "throughput": 1033.87, "total_tokens": 5123768} {"current_steps": 56905, "total_steps": 76960, "loss": 0.2036, "lr": 9.649957471713175e-06, "epoch": 14.788201663201663, "percentage": 73.94, "elapsed_time": "1:22:36", "remaining_time": "0:29:06", "throughput": 1033.87, "total_tokens": 5124216} {"current_steps": 56910, "total_steps": 76960, "loss": 0.3053, "lr": 9.645482825608874e-06, "epoch": 14.78950103950104, "percentage": 73.95, "elapsed_time": "1:22:36", "remaining_time": "0:29:06", "throughput": 1033.87, "total_tokens": 5124648} {"current_steps": 56915, "total_steps": 76960, "loss": 0.3598, "lr": 9.6410089692021e-06, "epoch": 14.790800415800415, "percentage": 73.95, "elapsed_time": "1:22:37", "remaining_time": "0:29:05", "throughput": 1033.88, "total_tokens": 5125112} {"current_steps": 56920, "total_steps": 76960, "loss": 0.2448, "lr": 9.63653590272296e-06, "epoch": 14.792099792099792, "percentage": 73.96, "elapsed_time": "1:22:37", "remaining_time": "0:29:05", "throughput": 1033.88, "total_tokens": 5125528} {"current_steps": 56925, "total_steps": 76960, "loss": 0.2822, "lr": 9.63206362640149e-06, "epoch": 14.79339916839917, "percentage": 73.97, "elapsed_time": "1:22:37", "remaining_time": "0:29:04", "throughput": 1033.89, "total_tokens": 5126008} {"current_steps": 56930, "total_steps": 76960, "loss": 0.6206, "lr": 9.627592140467726e-06, "epoch": 14.794698544698544, "percentage": 73.97, "elapsed_time": "1:22:38", "remaining_time": "0:29:04", "throughput": 1033.89, "total_tokens": 5126424} {"current_steps": 56935, "total_steps": 76960, "loss": 0.2163, "lr": 9.623121445151615e-06, "epoch": 14.795997920997921, "percentage": 73.98, "elapsed_time": "1:22:38", "remaining_time": "0:29:04", "throughput": 1033.9, "total_tokens": 5126904} {"current_steps": 56940, "total_steps": 76960, "loss": 0.3183, "lr": 9.61865154068311e-06, "epoch": 14.797297297297296, "percentage": 73.99, "elapsed_time": "1:22:39", "remaining_time": "0:29:03", "throughput": 1033.9, "total_tokens": 5127352} {"current_steps": 56945, "total_steps": 76960, "loss": 0.0772, "lr": 9.614182427292077e-06, "epoch": 14.798596673596673, "percentage": 73.99, "elapsed_time": "1:22:39", "remaining_time": "0:29:03", "throughput": 1033.91, "total_tokens": 5127832} {"current_steps": 56950, "total_steps": 76960, "loss": 0.2595, "lr": 9.609714105208401e-06, "epoch": 14.79989604989605, "percentage": 74.0, "elapsed_time": "1:22:40", "remaining_time": "0:29:02", "throughput": 1033.91, "total_tokens": 5128280} {"current_steps": 56955, "total_steps": 76960, "loss": 0.205, "lr": 9.605246574661866e-06, "epoch": 14.801195426195425, "percentage": 74.01, "elapsed_time": "1:22:40", "remaining_time": "0:29:02", "throughput": 1033.91, "total_tokens": 5128696} {"current_steps": 56960, "total_steps": 76960, "loss": 0.5041, "lr": 9.600779835882259e-06, "epoch": 14.802494802494802, "percentage": 74.01, "elapsed_time": "1:22:40", "remaining_time": "0:29:01", "throughput": 1033.91, "total_tokens": 5129112} {"current_steps": 56965, "total_steps": 76960, "loss": 0.26, "lr": 9.596313889099297e-06, "epoch": 14.80379417879418, "percentage": 74.02, "elapsed_time": "1:22:41", "remaining_time": "0:29:01", "throughput": 1033.92, "total_tokens": 5129576} {"current_steps": 56970, "total_steps": 76960, "loss": 0.3966, "lr": 9.591848734542665e-06, "epoch": 14.805093555093555, "percentage": 74.03, "elapsed_time": "1:22:41", "remaining_time": "0:29:01", "throughput": 1033.91, "total_tokens": 5129976} {"current_steps": 56975, "total_steps": 76960, "loss": 0.257, "lr": 9.587384372442019e-06, "epoch": 14.806392931392931, "percentage": 74.03, "elapsed_time": "1:22:42", "remaining_time": "0:29:00", "throughput": 1033.92, "total_tokens": 5130440} {"current_steps": 56980, "total_steps": 76960, "loss": 0.2723, "lr": 9.582920803026959e-06, "epoch": 14.807692307692308, "percentage": 74.04, "elapsed_time": "1:22:42", "remaining_time": "0:29:00", "throughput": 1033.92, "total_tokens": 5130904} {"current_steps": 56985, "total_steps": 76960, "loss": 0.1515, "lr": 9.578458026527063e-06, "epoch": 14.808991683991684, "percentage": 74.04, "elapsed_time": "1:22:42", "remaining_time": "0:28:59", "throughput": 1033.93, "total_tokens": 5131352} {"current_steps": 56990, "total_steps": 76960, "loss": 0.2466, "lr": 9.573996043171837e-06, "epoch": 14.81029106029106, "percentage": 74.05, "elapsed_time": "1:22:43", "remaining_time": "0:28:59", "throughput": 1033.93, "total_tokens": 5131784} {"current_steps": 56995, "total_steps": 76960, "loss": 0.0974, "lr": 9.569534853190787e-06, "epoch": 14.811590436590437, "percentage": 74.06, "elapsed_time": "1:22:43", "remaining_time": "0:28:58", "throughput": 1033.93, "total_tokens": 5132200} {"current_steps": 57000, "total_steps": 76960, "loss": 0.1137, "lr": 9.565074456813334e-06, "epoch": 14.812889812889813, "percentage": 74.06, "elapsed_time": "1:22:44", "remaining_time": "0:28:58", "throughput": 1033.94, "total_tokens": 5132680} {"current_steps": 57005, "total_steps": 76960, "loss": 0.1601, "lr": 9.560614854268899e-06, "epoch": 14.81418918918919, "percentage": 74.07, "elapsed_time": "1:22:44", "remaining_time": "0:28:57", "throughput": 1033.94, "total_tokens": 5133144} {"current_steps": 57010, "total_steps": 76960, "loss": 0.1585, "lr": 9.556156045786826e-06, "epoch": 14.815488565488565, "percentage": 74.08, "elapsed_time": "1:22:45", "remaining_time": "0:28:57", "throughput": 1033.95, "total_tokens": 5133592} {"current_steps": 57015, "total_steps": 76960, "loss": 0.0485, "lr": 9.551698031596445e-06, "epoch": 14.816787941787942, "percentage": 74.08, "elapsed_time": "1:22:45", "remaining_time": "0:28:57", "throughput": 1033.95, "total_tokens": 5134024} {"current_steps": 57020, "total_steps": 76960, "loss": 0.0636, "lr": 9.547240811927038e-06, "epoch": 14.818087318087318, "percentage": 74.09, "elapsed_time": "1:22:45", "remaining_time": "0:28:56", "throughput": 1033.95, "total_tokens": 5134456} {"current_steps": 57025, "total_steps": 76960, "loss": 0.0899, "lr": 9.54278438700785e-06, "epoch": 14.819386694386694, "percentage": 74.1, "elapsed_time": "1:22:46", "remaining_time": "0:28:56", "throughput": 1033.95, "total_tokens": 5134904} {"current_steps": 57030, "total_steps": 76960, "loss": 0.075, "lr": 9.538328757068072e-06, "epoch": 14.82068607068607, "percentage": 74.1, "elapsed_time": "1:22:46", "remaining_time": "0:28:55", "throughput": 1033.95, "total_tokens": 5135352} {"current_steps": 57035, "total_steps": 76960, "loss": 0.3818, "lr": 9.53387392233685e-06, "epoch": 14.821985446985448, "percentage": 74.11, "elapsed_time": "1:22:47", "remaining_time": "0:28:55", "throughput": 1033.96, "total_tokens": 5135800} {"current_steps": 57040, "total_steps": 76960, "loss": 0.1275, "lr": 9.529419883043319e-06, "epoch": 14.823284823284823, "percentage": 74.12, "elapsed_time": "1:22:47", "remaining_time": "0:28:54", "throughput": 1033.96, "total_tokens": 5136264} {"current_steps": 57045, "total_steps": 76960, "loss": 0.2601, "lr": 9.52496663941654e-06, "epoch": 14.8245841995842, "percentage": 74.12, "elapsed_time": "1:22:47", "remaining_time": "0:28:54", "throughput": 1033.97, "total_tokens": 5136696} {"current_steps": 57050, "total_steps": 76960, "loss": 0.5499, "lr": 9.520514191685556e-06, "epoch": 14.825883575883577, "percentage": 74.13, "elapsed_time": "1:22:48", "remaining_time": "0:28:53", "throughput": 1033.97, "total_tokens": 5137128} {"current_steps": 57055, "total_steps": 76960, "loss": 0.1026, "lr": 9.516062540079357e-06, "epoch": 14.827182952182952, "percentage": 74.14, "elapsed_time": "1:22:48", "remaining_time": "0:28:53", "throughput": 1033.97, "total_tokens": 5137560} {"current_steps": 57060, "total_steps": 76960, "loss": 0.3878, "lr": 9.511611684826904e-06, "epoch": 14.828482328482329, "percentage": 74.14, "elapsed_time": "1:22:49", "remaining_time": "0:28:53", "throughput": 1033.96, "total_tokens": 5137976} {"current_steps": 57065, "total_steps": 76960, "loss": 0.0371, "lr": 9.507161626157096e-06, "epoch": 14.829781704781706, "percentage": 74.15, "elapsed_time": "1:22:49", "remaining_time": "0:28:52", "throughput": 1033.97, "total_tokens": 5138456} {"current_steps": 57070, "total_steps": 76960, "loss": 0.3668, "lr": 9.502712364298819e-06, "epoch": 14.83108108108108, "percentage": 74.16, "elapsed_time": "1:22:50", "remaining_time": "0:28:52", "throughput": 1033.98, "total_tokens": 5138904} {"current_steps": 57075, "total_steps": 76960, "loss": 0.5623, "lr": 9.498263899480886e-06, "epoch": 14.832380457380458, "percentage": 74.16, "elapsed_time": "1:22:50", "remaining_time": "0:28:51", "throughput": 1033.99, "total_tokens": 5139400} {"current_steps": 57080, "total_steps": 76960, "loss": 0.1253, "lr": 9.493816231932101e-06, "epoch": 14.833679833679835, "percentage": 74.17, "elapsed_time": "1:22:50", "remaining_time": "0:28:51", "throughput": 1034.0, "total_tokens": 5139864} {"current_steps": 57085, "total_steps": 76960, "loss": 0.365, "lr": 9.489369361881196e-06, "epoch": 14.83497920997921, "percentage": 74.17, "elapsed_time": "1:22:51", "remaining_time": "0:28:50", "throughput": 1034.01, "total_tokens": 5140344} {"current_steps": 57090, "total_steps": 76960, "loss": 0.3826, "lr": 9.484923289556886e-06, "epoch": 14.836278586278587, "percentage": 74.18, "elapsed_time": "1:22:51", "remaining_time": "0:28:50", "throughput": 1034.02, "total_tokens": 5140824} {"current_steps": 57095, "total_steps": 76960, "loss": 0.2276, "lr": 9.480478015187846e-06, "epoch": 14.837577962577962, "percentage": 74.19, "elapsed_time": "1:22:52", "remaining_time": "0:28:49", "throughput": 1034.04, "total_tokens": 5141336} {"current_steps": 57100, "total_steps": 76960, "loss": 0.2233, "lr": 9.476033539002683e-06, "epoch": 14.838877338877339, "percentage": 74.19, "elapsed_time": "1:22:52", "remaining_time": "0:28:49", "throughput": 1034.03, "total_tokens": 5141752} {"current_steps": 57105, "total_steps": 76960, "loss": 0.1674, "lr": 9.471589861229998e-06, "epoch": 14.840176715176716, "percentage": 74.2, "elapsed_time": "1:22:52", "remaining_time": "0:28:49", "throughput": 1034.04, "total_tokens": 5142216} {"current_steps": 57110, "total_steps": 76960, "loss": 0.0891, "lr": 9.467146982098316e-06, "epoch": 14.84147609147609, "percentage": 74.21, "elapsed_time": "1:22:53", "remaining_time": "0:28:48", "throughput": 1034.04, "total_tokens": 5142664} {"current_steps": 57115, "total_steps": 76960, "loss": 0.0125, "lr": 9.462704901836156e-06, "epoch": 14.842775467775468, "percentage": 74.21, "elapsed_time": "1:22:53", "remaining_time": "0:28:48", "throughput": 1034.05, "total_tokens": 5143128} {"current_steps": 57120, "total_steps": 76960, "loss": 0.086, "lr": 9.458263620671965e-06, "epoch": 14.844074844074845, "percentage": 74.22, "elapsed_time": "1:22:54", "remaining_time": "0:28:47", "throughput": 1034.05, "total_tokens": 5143544} {"current_steps": 57125, "total_steps": 76960, "loss": 0.0857, "lr": 9.453823138834162e-06, "epoch": 14.84537422037422, "percentage": 74.23, "elapsed_time": "1:22:54", "remaining_time": "0:28:47", "throughput": 1034.06, "total_tokens": 5144008} {"current_steps": 57130, "total_steps": 76960, "loss": 0.306, "lr": 9.449383456551133e-06, "epoch": 14.846673596673597, "percentage": 74.23, "elapsed_time": "1:22:55", "remaining_time": "0:28:46", "throughput": 1034.06, "total_tokens": 5144456} {"current_steps": 57135, "total_steps": 76960, "loss": 0.4236, "lr": 9.444944574051224e-06, "epoch": 14.847972972972974, "percentage": 74.24, "elapsed_time": "1:22:55", "remaining_time": "0:28:46", "throughput": 1034.07, "total_tokens": 5144920} {"current_steps": 57140, "total_steps": 76960, "loss": 0.3757, "lr": 9.440506491562706e-06, "epoch": 14.849272349272349, "percentage": 74.25, "elapsed_time": "1:22:55", "remaining_time": "0:28:45", "throughput": 1034.07, "total_tokens": 5145368} {"current_steps": 57145, "total_steps": 76960, "loss": 0.099, "lr": 9.436069209313858e-06, "epoch": 14.850571725571726, "percentage": 74.25, "elapsed_time": "1:22:56", "remaining_time": "0:28:45", "throughput": 1034.07, "total_tokens": 5145784} {"current_steps": 57150, "total_steps": 76960, "loss": 0.0274, "lr": 9.431632727532877e-06, "epoch": 14.851871101871101, "percentage": 74.26, "elapsed_time": "1:22:56", "remaining_time": "0:28:45", "throughput": 1034.07, "total_tokens": 5146216} {"current_steps": 57155, "total_steps": 76960, "loss": 0.4167, "lr": 9.427197046447946e-06, "epoch": 14.853170478170478, "percentage": 74.27, "elapsed_time": "1:22:57", "remaining_time": "0:28:44", "throughput": 1034.08, "total_tokens": 5146696} {"current_steps": 57160, "total_steps": 76960, "loss": 0.0323, "lr": 9.422762166287189e-06, "epoch": 14.854469854469855, "percentage": 74.27, "elapsed_time": "1:22:57", "remaining_time": "0:28:44", "throughput": 1034.07, "total_tokens": 5147096} {"current_steps": 57165, "total_steps": 76960, "loss": 0.1878, "lr": 9.418328087278694e-06, "epoch": 14.85576923076923, "percentage": 74.28, "elapsed_time": "1:22:57", "remaining_time": "0:28:43", "throughput": 1034.07, "total_tokens": 5147528} {"current_steps": 57170, "total_steps": 76960, "loss": 0.1861, "lr": 9.413894809650529e-06, "epoch": 14.857068607068607, "percentage": 74.29, "elapsed_time": "1:22:58", "remaining_time": "0:28:43", "throughput": 1034.07, "total_tokens": 5147944} {"current_steps": 57175, "total_steps": 76960, "loss": 0.4534, "lr": 9.409462333630675e-06, "epoch": 14.858367983367984, "percentage": 74.29, "elapsed_time": "1:22:58", "remaining_time": "0:28:42", "throughput": 1034.08, "total_tokens": 5148408} {"current_steps": 57180, "total_steps": 76960, "loss": 0.0924, "lr": 9.405030659447119e-06, "epoch": 14.859667359667359, "percentage": 74.3, "elapsed_time": "1:22:59", "remaining_time": "0:28:42", "throughput": 1034.08, "total_tokens": 5148840} {"current_steps": 57185, "total_steps": 76960, "loss": 0.2173, "lr": 9.400599787327773e-06, "epoch": 14.860966735966736, "percentage": 74.3, "elapsed_time": "1:22:59", "remaining_time": "0:28:41", "throughput": 1034.08, "total_tokens": 5149272} {"current_steps": 57190, "total_steps": 76960, "loss": 0.5637, "lr": 9.396169717500534e-06, "epoch": 14.862266112266113, "percentage": 74.31, "elapsed_time": "1:22:59", "remaining_time": "0:28:41", "throughput": 1034.09, "total_tokens": 5149752} {"current_steps": 57195, "total_steps": 76960, "loss": 0.3292, "lr": 9.39174045019322e-06, "epoch": 14.863565488565488, "percentage": 74.32, "elapsed_time": "1:23:00", "remaining_time": "0:28:41", "throughput": 1034.09, "total_tokens": 5150200} {"current_steps": 57200, "total_steps": 76960, "loss": 0.0735, "lr": 9.387311985633668e-06, "epoch": 14.864864864864865, "percentage": 74.32, "elapsed_time": "1:23:00", "remaining_time": "0:28:40", "throughput": 1034.1, "total_tokens": 5150648} {"current_steps": 57205, "total_steps": 76960, "loss": 0.0904, "lr": 9.382884324049609e-06, "epoch": 14.866164241164242, "percentage": 74.33, "elapsed_time": "1:23:01", "remaining_time": "0:28:40", "throughput": 1034.1, "total_tokens": 5151112} {"current_steps": 57210, "total_steps": 76960, "loss": 0.3344, "lr": 9.378457465668783e-06, "epoch": 14.867463617463617, "percentage": 74.34, "elapsed_time": "1:23:01", "remaining_time": "0:28:39", "throughput": 1034.11, "total_tokens": 5151560} {"current_steps": 57215, "total_steps": 76960, "loss": 0.5246, "lr": 9.374031410718851e-06, "epoch": 14.868762993762994, "percentage": 74.34, "elapsed_time": "1:23:02", "remaining_time": "0:28:39", "throughput": 1034.12, "total_tokens": 5152040} {"current_steps": 57220, "total_steps": 76960, "loss": 0.092, "lr": 9.369606159427461e-06, "epoch": 14.87006237006237, "percentage": 74.35, "elapsed_time": "1:23:02", "remaining_time": "0:28:38", "throughput": 1034.13, "total_tokens": 5152520} {"current_steps": 57225, "total_steps": 76960, "loss": 0.0779, "lr": 9.365181712022195e-06, "epoch": 14.871361746361746, "percentage": 74.36, "elapsed_time": "1:23:02", "remaining_time": "0:28:38", "throughput": 1034.13, "total_tokens": 5152968} {"current_steps": 57230, "total_steps": 76960, "loss": 0.343, "lr": 9.360758068730614e-06, "epoch": 14.872661122661123, "percentage": 74.36, "elapsed_time": "1:23:03", "remaining_time": "0:28:37", "throughput": 1034.13, "total_tokens": 5153416} {"current_steps": 57235, "total_steps": 76960, "loss": 0.0801, "lr": 9.356335229780238e-06, "epoch": 14.8739604989605, "percentage": 74.37, "elapsed_time": "1:23:03", "remaining_time": "0:28:37", "throughput": 1034.14, "total_tokens": 5153864} {"current_steps": 57240, "total_steps": 76960, "loss": 0.2187, "lr": 9.351913195398524e-06, "epoch": 14.875259875259875, "percentage": 74.38, "elapsed_time": "1:23:04", "remaining_time": "0:28:37", "throughput": 1034.14, "total_tokens": 5154328} {"current_steps": 57245, "total_steps": 76960, "loss": 0.12, "lr": 9.347491965812913e-06, "epoch": 14.876559251559252, "percentage": 74.38, "elapsed_time": "1:23:04", "remaining_time": "0:28:36", "throughput": 1034.15, "total_tokens": 5154776} {"current_steps": 57250, "total_steps": 76960, "loss": 0.1281, "lr": 9.343071541250781e-06, "epoch": 14.877858627858627, "percentage": 74.39, "elapsed_time": "1:23:04", "remaining_time": "0:28:36", "throughput": 1034.16, "total_tokens": 5155256} {"current_steps": 57255, "total_steps": 76960, "loss": 0.3211, "lr": 9.33865192193949e-06, "epoch": 14.879158004158004, "percentage": 74.4, "elapsed_time": "1:23:05", "remaining_time": "0:28:35", "throughput": 1034.16, "total_tokens": 5155720} {"current_steps": 57260, "total_steps": 76960, "loss": 0.1087, "lr": 9.334233108106327e-06, "epoch": 14.880457380457381, "percentage": 74.4, "elapsed_time": "1:23:05", "remaining_time": "0:28:35", "throughput": 1034.17, "total_tokens": 5156168} {"current_steps": 57265, "total_steps": 76960, "loss": 0.2749, "lr": 9.329815099978568e-06, "epoch": 14.881756756756756, "percentage": 74.41, "elapsed_time": "1:23:06", "remaining_time": "0:28:34", "throughput": 1034.17, "total_tokens": 5156616} {"current_steps": 57270, "total_steps": 76960, "loss": 0.3566, "lr": 9.32539789778343e-06, "epoch": 14.883056133056133, "percentage": 74.42, "elapsed_time": "1:23:06", "remaining_time": "0:28:34", "throughput": 1034.18, "total_tokens": 5157096} {"current_steps": 57275, "total_steps": 76960, "loss": 0.2448, "lr": 9.320981501748107e-06, "epoch": 14.88435550935551, "percentage": 74.42, "elapsed_time": "1:23:07", "remaining_time": "0:28:34", "throughput": 1034.19, "total_tokens": 5157560} {"current_steps": 57280, "total_steps": 76960, "loss": 0.048, "lr": 9.31656591209972e-06, "epoch": 14.885654885654885, "percentage": 74.43, "elapsed_time": "1:23:07", "remaining_time": "0:28:33", "throughput": 1034.2, "total_tokens": 5158024} {"current_steps": 57285, "total_steps": 76960, "loss": 0.2819, "lr": 9.312151129065383e-06, "epoch": 14.886954261954262, "percentage": 74.43, "elapsed_time": "1:23:07", "remaining_time": "0:28:33", "throughput": 1034.2, "total_tokens": 5158456} {"current_steps": 57290, "total_steps": 76960, "loss": 0.0667, "lr": 9.307737152872137e-06, "epoch": 14.888253638253639, "percentage": 74.44, "elapsed_time": "1:23:08", "remaining_time": "0:28:32", "throughput": 1034.2, "total_tokens": 5158888} {"current_steps": 57295, "total_steps": 76960, "loss": 0.1203, "lr": 9.303323983747012e-06, "epoch": 14.889553014553014, "percentage": 74.45, "elapsed_time": "1:23:08", "remaining_time": "0:28:32", "throughput": 1034.21, "total_tokens": 5159352} {"current_steps": 57300, "total_steps": 76960, "loss": 0.1441, "lr": 9.298911621916967e-06, "epoch": 14.890852390852391, "percentage": 74.45, "elapsed_time": "1:23:09", "remaining_time": "0:28:31", "throughput": 1034.22, "total_tokens": 5159848} {"current_steps": 57305, "total_steps": 76960, "loss": 0.0863, "lr": 9.29450006760894e-06, "epoch": 14.892151767151766, "percentage": 74.46, "elapsed_time": "1:23:09", "remaining_time": "0:28:31", "throughput": 1034.22, "total_tokens": 5160296} {"current_steps": 57310, "total_steps": 76960, "loss": 0.19, "lr": 9.290089321049833e-06, "epoch": 14.893451143451143, "percentage": 74.47, "elapsed_time": "1:23:09", "remaining_time": "0:28:30", "throughput": 1034.23, "total_tokens": 5160760} {"current_steps": 57315, "total_steps": 76960, "loss": 0.1426, "lr": 9.285679382466474e-06, "epoch": 14.89475051975052, "percentage": 74.47, "elapsed_time": "1:23:10", "remaining_time": "0:28:30", "throughput": 1034.24, "total_tokens": 5161224} {"current_steps": 57320, "total_steps": 76960, "loss": 0.2619, "lr": 9.281270252085692e-06, "epoch": 14.896049896049895, "percentage": 74.48, "elapsed_time": "1:23:10", "remaining_time": "0:28:30", "throughput": 1034.24, "total_tokens": 5161672} {"current_steps": 57325, "total_steps": 76960, "loss": 0.3689, "lr": 9.27686193013423e-06, "epoch": 14.897349272349272, "percentage": 74.49, "elapsed_time": "1:23:11", "remaining_time": "0:28:29", "throughput": 1034.24, "total_tokens": 5162104} {"current_steps": 57330, "total_steps": 76960, "loss": 0.0451, "lr": 9.272454416838839e-06, "epoch": 14.89864864864865, "percentage": 74.49, "elapsed_time": "1:23:11", "remaining_time": "0:28:29", "throughput": 1034.24, "total_tokens": 5162552} {"current_steps": 57335, "total_steps": 76960, "loss": 0.1291, "lr": 9.268047712426173e-06, "epoch": 14.899948024948024, "percentage": 74.5, "elapsed_time": "1:23:12", "remaining_time": "0:28:28", "throughput": 1034.25, "total_tokens": 5163000} {"current_steps": 57340, "total_steps": 76960, "loss": 0.2747, "lr": 9.263641817122887e-06, "epoch": 14.901247401247401, "percentage": 74.51, "elapsed_time": "1:23:12", "remaining_time": "0:28:28", "throughput": 1034.25, "total_tokens": 5163432} {"current_steps": 57345, "total_steps": 76960, "loss": 0.3616, "lr": 9.259236731155582e-06, "epoch": 14.902546777546778, "percentage": 74.51, "elapsed_time": "1:23:12", "remaining_time": "0:28:27", "throughput": 1034.25, "total_tokens": 5163896} {"current_steps": 57350, "total_steps": 76960, "loss": 0.1327, "lr": 9.254832454750823e-06, "epoch": 14.903846153846153, "percentage": 74.52, "elapsed_time": "1:23:13", "remaining_time": "0:28:27", "throughput": 1034.25, "total_tokens": 5164312} {"current_steps": 57355, "total_steps": 76960, "loss": 0.2214, "lr": 9.250428988135108e-06, "epoch": 14.90514553014553, "percentage": 74.53, "elapsed_time": "1:23:13", "remaining_time": "0:28:26", "throughput": 1034.25, "total_tokens": 5164728} {"current_steps": 57360, "total_steps": 76960, "loss": 0.1198, "lr": 9.246026331534927e-06, "epoch": 14.906444906444907, "percentage": 74.53, "elapsed_time": "1:23:14", "remaining_time": "0:28:26", "throughput": 1034.25, "total_tokens": 5165144} {"current_steps": 57365, "total_steps": 76960, "loss": 0.032, "lr": 9.241624485176708e-06, "epoch": 14.907744282744282, "percentage": 74.54, "elapsed_time": "1:23:14", "remaining_time": "0:28:26", "throughput": 1034.25, "total_tokens": 5165576} {"current_steps": 57370, "total_steps": 76960, "loss": 0.5921, "lr": 9.237223449286833e-06, "epoch": 14.90904365904366, "percentage": 74.55, "elapsed_time": "1:23:14", "remaining_time": "0:28:25", "throughput": 1034.24, "total_tokens": 5165992} {"current_steps": 57375, "total_steps": 76960, "loss": 0.3006, "lr": 9.232823224091659e-06, "epoch": 14.910343035343036, "percentage": 74.55, "elapsed_time": "1:23:15", "remaining_time": "0:28:25", "throughput": 1034.24, "total_tokens": 5166424} {"current_steps": 57380, "total_steps": 76960, "loss": 0.309, "lr": 9.22842380981749e-06, "epoch": 14.911642411642411, "percentage": 74.56, "elapsed_time": "1:23:15", "remaining_time": "0:28:24", "throughput": 1034.25, "total_tokens": 5166872} {"current_steps": 57385, "total_steps": 76960, "loss": 0.313, "lr": 9.224025206690608e-06, "epoch": 14.912941787941788, "percentage": 74.56, "elapsed_time": "1:23:16", "remaining_time": "0:28:24", "throughput": 1034.25, "total_tokens": 5167304} {"current_steps": 57390, "total_steps": 76960, "loss": 0.1987, "lr": 9.219627414937219e-06, "epoch": 14.914241164241163, "percentage": 74.57, "elapsed_time": "1:23:16", "remaining_time": "0:28:23", "throughput": 1034.25, "total_tokens": 5167768} {"current_steps": 57395, "total_steps": 76960, "loss": 0.0622, "lr": 9.215230434783518e-06, "epoch": 14.91554054054054, "percentage": 74.58, "elapsed_time": "1:23:17", "remaining_time": "0:28:23", "throughput": 1034.26, "total_tokens": 5168216} {"current_steps": 57400, "total_steps": 76960, "loss": 0.245, "lr": 9.210834266455631e-06, "epoch": 14.916839916839917, "percentage": 74.58, "elapsed_time": "1:23:17", "remaining_time": "0:28:22", "throughput": 1034.26, "total_tokens": 5168648} {"current_steps": 57405, "total_steps": 76960, "loss": 0.1716, "lr": 9.206438910179676e-06, "epoch": 14.918139293139292, "percentage": 74.59, "elapsed_time": "1:23:17", "remaining_time": "0:28:22", "throughput": 1034.26, "total_tokens": 5169080} {"current_steps": 57410, "total_steps": 76960, "loss": 0.2592, "lr": 9.202044366181692e-06, "epoch": 14.91943866943867, "percentage": 74.6, "elapsed_time": "1:23:18", "remaining_time": "0:28:22", "throughput": 1034.26, "total_tokens": 5169512} {"current_steps": 57415, "total_steps": 76960, "loss": 0.0943, "lr": 9.197650634687701e-06, "epoch": 14.920738045738046, "percentage": 74.6, "elapsed_time": "1:23:18", "remaining_time": "0:28:21", "throughput": 1034.26, "total_tokens": 5169960} {"current_steps": 57420, "total_steps": 76960, "loss": 0.1865, "lr": 9.193257715923682e-06, "epoch": 14.922037422037421, "percentage": 74.61, "elapsed_time": "1:23:19", "remaining_time": "0:28:21", "throughput": 1034.27, "total_tokens": 5170424} {"current_steps": 57425, "total_steps": 76960, "loss": 0.3776, "lr": 9.18886561011557e-06, "epoch": 14.923336798336798, "percentage": 74.62, "elapsed_time": "1:23:19", "remaining_time": "0:28:20", "throughput": 1034.27, "total_tokens": 5170872} {"current_steps": 57430, "total_steps": 76960, "loss": 0.422, "lr": 9.18447431748925e-06, "epoch": 14.924636174636175, "percentage": 74.62, "elapsed_time": "1:23:19", "remaining_time": "0:28:20", "throughput": 1034.28, "total_tokens": 5171304} {"current_steps": 57435, "total_steps": 76960, "loss": 0.2778, "lr": 9.180083838270561e-06, "epoch": 14.92593555093555, "percentage": 74.63, "elapsed_time": "1:23:20", "remaining_time": "0:28:19", "throughput": 1034.28, "total_tokens": 5171736} {"current_steps": 57440, "total_steps": 76960, "loss": 0.3159, "lr": 9.175694172685328e-06, "epoch": 14.927234927234927, "percentage": 74.64, "elapsed_time": "1:23:20", "remaining_time": "0:28:19", "throughput": 1034.28, "total_tokens": 5172200} {"current_steps": 57445, "total_steps": 76960, "loss": 0.1382, "lr": 9.17130532095929e-06, "epoch": 14.928534303534304, "percentage": 74.64, "elapsed_time": "1:23:21", "remaining_time": "0:28:18", "throughput": 1034.29, "total_tokens": 5172664} {"current_steps": 57450, "total_steps": 76960, "loss": 0.1102, "lr": 9.1669172833182e-06, "epoch": 14.92983367983368, "percentage": 74.65, "elapsed_time": "1:23:21", "remaining_time": "0:28:18", "throughput": 1034.3, "total_tokens": 5173112} {"current_steps": 57455, "total_steps": 76960, "loss": 0.0976, "lr": 9.162530059987715e-06, "epoch": 14.931133056133056, "percentage": 74.66, "elapsed_time": "1:23:21", "remaining_time": "0:28:18", "throughput": 1034.3, "total_tokens": 5173560} {"current_steps": 57460, "total_steps": 76960, "loss": 0.0949, "lr": 9.158143651193492e-06, "epoch": 14.932432432432432, "percentage": 74.66, "elapsed_time": "1:23:22", "remaining_time": "0:28:17", "throughput": 1034.3, "total_tokens": 5173976} {"current_steps": 57465, "total_steps": 76960, "loss": 0.0462, "lr": 9.153758057161116e-06, "epoch": 14.933731808731808, "percentage": 74.67, "elapsed_time": "1:23:22", "remaining_time": "0:28:17", "throughput": 1034.31, "total_tokens": 5174456} {"current_steps": 57470, "total_steps": 76960, "loss": 0.178, "lr": 9.14937327811615e-06, "epoch": 14.935031185031185, "percentage": 74.68, "elapsed_time": "1:23:23", "remaining_time": "0:28:16", "throughput": 1034.3, "total_tokens": 5174856} {"current_steps": 57475, "total_steps": 76960, "loss": 0.341, "lr": 9.144989314284097e-06, "epoch": 14.93633056133056, "percentage": 74.68, "elapsed_time": "1:23:23", "remaining_time": "0:28:16", "throughput": 1034.3, "total_tokens": 5175288} {"current_steps": 57480, "total_steps": 76960, "loss": 0.6557, "lr": 9.140606165890437e-06, "epoch": 14.937629937629938, "percentage": 74.69, "elapsed_time": "1:23:24", "remaining_time": "0:28:15", "throughput": 1034.31, "total_tokens": 5175736} {"current_steps": 57485, "total_steps": 76960, "loss": 0.2924, "lr": 9.136223833160596e-06, "epoch": 14.938929313929314, "percentage": 74.69, "elapsed_time": "1:23:24", "remaining_time": "0:28:15", "throughput": 1034.31, "total_tokens": 5176168} {"current_steps": 57490, "total_steps": 76960, "loss": 0.2292, "lr": 9.131842316319971e-06, "epoch": 14.94022869022869, "percentage": 74.7, "elapsed_time": "1:23:24", "remaining_time": "0:28:14", "throughput": 1034.31, "total_tokens": 5176600} {"current_steps": 57495, "total_steps": 76960, "loss": 0.5003, "lr": 9.127461615593898e-06, "epoch": 14.941528066528067, "percentage": 74.71, "elapsed_time": "1:23:25", "remaining_time": "0:28:14", "throughput": 1034.31, "total_tokens": 5177032} {"current_steps": 57500, "total_steps": 76960, "loss": 0.0269, "lr": 9.123081731207677e-06, "epoch": 14.942827442827443, "percentage": 74.71, "elapsed_time": "1:23:25", "remaining_time": "0:28:14", "throughput": 1034.31, "total_tokens": 5177480} {"current_steps": 57505, "total_steps": 76960, "loss": 0.3543, "lr": 9.118702663386584e-06, "epoch": 14.944126819126819, "percentage": 74.72, "elapsed_time": "1:23:26", "remaining_time": "0:28:13", "throughput": 1034.32, "total_tokens": 5177960} {"current_steps": 57510, "total_steps": 76960, "loss": 0.124, "lr": 9.114324412355821e-06, "epoch": 14.945426195426196, "percentage": 74.73, "elapsed_time": "1:23:26", "remaining_time": "0:28:13", "throughput": 1034.33, "total_tokens": 5178440} {"current_steps": 57515, "total_steps": 76960, "loss": 0.214, "lr": 9.109946978340572e-06, "epoch": 14.946725571725572, "percentage": 74.73, "elapsed_time": "1:23:26", "remaining_time": "0:28:12", "throughput": 1034.34, "total_tokens": 5178920} {"current_steps": 57520, "total_steps": 76960, "loss": 0.0828, "lr": 9.105570361565977e-06, "epoch": 14.948024948024948, "percentage": 74.74, "elapsed_time": "1:23:27", "remaining_time": "0:28:12", "throughput": 1034.35, "total_tokens": 5179384} {"current_steps": 57525, "total_steps": 76960, "loss": 0.1667, "lr": 9.101194562257137e-06, "epoch": 14.949324324324325, "percentage": 74.75, "elapsed_time": "1:23:27", "remaining_time": "0:28:11", "throughput": 1034.34, "total_tokens": 5179784} {"current_steps": 57530, "total_steps": 76960, "loss": 0.2497, "lr": 9.096819580639082e-06, "epoch": 14.950623700623701, "percentage": 74.75, "elapsed_time": "1:23:28", "remaining_time": "0:28:11", "throughput": 1034.34, "total_tokens": 5180216} {"current_steps": 57535, "total_steps": 76960, "loss": 0.0036, "lr": 9.092445416936846e-06, "epoch": 14.951923076923077, "percentage": 74.76, "elapsed_time": "1:23:28", "remaining_time": "0:28:11", "throughput": 1034.36, "total_tokens": 5180712} {"current_steps": 57540, "total_steps": 76960, "loss": 0.1558, "lr": 9.088072071375372e-06, "epoch": 14.953222453222454, "percentage": 74.77, "elapsed_time": "1:23:29", "remaining_time": "0:28:10", "throughput": 1034.36, "total_tokens": 5181144} {"current_steps": 57545, "total_steps": 76960, "loss": 0.0943, "lr": 9.08369954417961e-06, "epoch": 14.954521829521829, "percentage": 74.77, "elapsed_time": "1:23:29", "remaining_time": "0:28:10", "throughput": 1034.37, "total_tokens": 5181624} {"current_steps": 57550, "total_steps": 76960, "loss": 0.2462, "lr": 9.07932783557442e-06, "epoch": 14.955821205821206, "percentage": 74.78, "elapsed_time": "1:23:29", "remaining_time": "0:28:09", "throughput": 1034.37, "total_tokens": 5182056} {"current_steps": 57555, "total_steps": 76960, "loss": 0.1258, "lr": 9.074956945784654e-06, "epoch": 14.957120582120583, "percentage": 74.79, "elapsed_time": "1:23:30", "remaining_time": "0:28:09", "throughput": 1034.37, "total_tokens": 5182488} {"current_steps": 57560, "total_steps": 76960, "loss": 0.399, "lr": 9.07058687503512e-06, "epoch": 14.958419958419958, "percentage": 74.79, "elapsed_time": "1:23:30", "remaining_time": "0:28:08", "throughput": 1034.37, "total_tokens": 5182936} {"current_steps": 57565, "total_steps": 76960, "loss": 0.1074, "lr": 9.066217623550558e-06, "epoch": 14.959719334719335, "percentage": 74.8, "elapsed_time": "1:23:31", "remaining_time": "0:28:08", "throughput": 1034.37, "total_tokens": 5183368} {"current_steps": 57570, "total_steps": 76960, "loss": 0.4162, "lr": 9.061849191555696e-06, "epoch": 14.961018711018712, "percentage": 74.81, "elapsed_time": "1:23:31", "remaining_time": "0:28:07", "throughput": 1034.38, "total_tokens": 5183848} {"current_steps": 57575, "total_steps": 76960, "loss": 0.3631, "lr": 9.057481579275196e-06, "epoch": 14.962318087318087, "percentage": 74.81, "elapsed_time": "1:23:31", "remaining_time": "0:28:07", "throughput": 1034.39, "total_tokens": 5184312} {"current_steps": 57580, "total_steps": 76960, "loss": 0.3032, "lr": 9.0531147869337e-06, "epoch": 14.963617463617464, "percentage": 74.82, "elapsed_time": "1:23:32", "remaining_time": "0:28:07", "throughput": 1034.38, "total_tokens": 5184728} {"current_steps": 57585, "total_steps": 76960, "loss": 0.1397, "lr": 9.048748814755784e-06, "epoch": 14.96491683991684, "percentage": 74.82, "elapsed_time": "1:23:32", "remaining_time": "0:28:06", "throughput": 1034.39, "total_tokens": 5185192} {"current_steps": 57590, "total_steps": 76960, "loss": 0.1938, "lr": 9.044383662965997e-06, "epoch": 14.966216216216216, "percentage": 74.83, "elapsed_time": "1:23:33", "remaining_time": "0:28:06", "throughput": 1034.39, "total_tokens": 5185640} {"current_steps": 57595, "total_steps": 76960, "loss": 0.1579, "lr": 9.040019331788848e-06, "epoch": 14.967515592515593, "percentage": 74.84, "elapsed_time": "1:23:33", "remaining_time": "0:28:05", "throughput": 1034.4, "total_tokens": 5186120} {"current_steps": 57600, "total_steps": 76960, "loss": 0.0682, "lr": 9.035655821448804e-06, "epoch": 14.96881496881497, "percentage": 74.84, "elapsed_time": "1:23:34", "remaining_time": "0:28:05", "throughput": 1034.41, "total_tokens": 5186552} {"current_steps": 57605, "total_steps": 76960, "loss": 0.0501, "lr": 9.031293132170271e-06, "epoch": 14.970114345114345, "percentage": 74.85, "elapsed_time": "1:23:34", "remaining_time": "0:28:04", "throughput": 1034.41, "total_tokens": 5187016} {"current_steps": 57610, "total_steps": 76960, "loss": 0.2572, "lr": 9.026931264177641e-06, "epoch": 14.971413721413722, "percentage": 74.86, "elapsed_time": "1:23:34", "remaining_time": "0:28:04", "throughput": 1034.42, "total_tokens": 5187496} {"current_steps": 57615, "total_steps": 76960, "loss": 0.1268, "lr": 9.022570217695232e-06, "epoch": 14.972713097713097, "percentage": 74.86, "elapsed_time": "1:23:35", "remaining_time": "0:28:03", "throughput": 1034.43, "total_tokens": 5187960} {"current_steps": 57620, "total_steps": 76960, "loss": 0.2509, "lr": 9.018209992947355e-06, "epoch": 14.974012474012474, "percentage": 74.87, "elapsed_time": "1:23:35", "remaining_time": "0:28:03", "throughput": 1034.44, "total_tokens": 5188456} {"current_steps": 57625, "total_steps": 76960, "loss": 0.1874, "lr": 9.013850590158241e-06, "epoch": 14.97531185031185, "percentage": 74.88, "elapsed_time": "1:23:36", "remaining_time": "0:28:03", "throughput": 1034.44, "total_tokens": 5188888} {"current_steps": 57630, "total_steps": 76960, "loss": 0.3324, "lr": 9.00949200955211e-06, "epoch": 14.976611226611226, "percentage": 74.88, "elapsed_time": "1:23:36", "remaining_time": "0:28:02", "throughput": 1034.45, "total_tokens": 5189336} {"current_steps": 57635, "total_steps": 76960, "loss": 0.1809, "lr": 9.005134251353132e-06, "epoch": 14.977910602910603, "percentage": 74.89, "elapsed_time": "1:23:36", "remaining_time": "0:28:02", "throughput": 1034.45, "total_tokens": 5189784} {"current_steps": 57640, "total_steps": 76960, "loss": 0.0764, "lr": 9.000777315785417e-06, "epoch": 14.97920997920998, "percentage": 74.9, "elapsed_time": "1:23:37", "remaining_time": "0:28:01", "throughput": 1034.45, "total_tokens": 5190232} {"current_steps": 57645, "total_steps": 76960, "loss": 0.2416, "lr": 8.996421203073062e-06, "epoch": 14.980509355509355, "percentage": 74.9, "elapsed_time": "1:23:37", "remaining_time": "0:28:01", "throughput": 1034.46, "total_tokens": 5190680} {"current_steps": 57650, "total_steps": 76960, "loss": 0.3782, "lr": 8.992065913440092e-06, "epoch": 14.981808731808732, "percentage": 74.91, "elapsed_time": "1:23:38", "remaining_time": "0:28:00", "throughput": 1034.47, "total_tokens": 5191160} {"current_steps": 57655, "total_steps": 76960, "loss": 0.1997, "lr": 8.98771144711052e-06, "epoch": 14.983108108108109, "percentage": 74.92, "elapsed_time": "1:23:38", "remaining_time": "0:28:00", "throughput": 1034.47, "total_tokens": 5191592} {"current_steps": 57660, "total_steps": 76960, "loss": 0.2299, "lr": 8.983357804308282e-06, "epoch": 14.984407484407484, "percentage": 74.92, "elapsed_time": "1:23:39", "remaining_time": "0:27:59", "throughput": 1034.47, "total_tokens": 5192024} {"current_steps": 57665, "total_steps": 76960, "loss": 0.297, "lr": 8.979004985257294e-06, "epoch": 14.98570686070686, "percentage": 74.93, "elapsed_time": "1:23:39", "remaining_time": "0:27:59", "throughput": 1034.47, "total_tokens": 5192488} {"current_steps": 57670, "total_steps": 76960, "loss": 0.3161, "lr": 8.974652990181433e-06, "epoch": 14.987006237006238, "percentage": 74.94, "elapsed_time": "1:23:39", "remaining_time": "0:27:59", "throughput": 1034.48, "total_tokens": 5192936} {"current_steps": 57675, "total_steps": 76960, "loss": 0.2871, "lr": 8.970301819304533e-06, "epoch": 14.988305613305613, "percentage": 74.94, "elapsed_time": "1:23:40", "remaining_time": "0:27:58", "throughput": 1034.48, "total_tokens": 5193400} {"current_steps": 57680, "total_steps": 76960, "loss": 0.1583, "lr": 8.965951472850359e-06, "epoch": 14.98960498960499, "percentage": 74.95, "elapsed_time": "1:23:40", "remaining_time": "0:27:58", "throughput": 1034.49, "total_tokens": 5193880} {"current_steps": 57685, "total_steps": 76960, "loss": 0.3764, "lr": 8.961601951042676e-06, "epoch": 14.990904365904367, "percentage": 74.95, "elapsed_time": "1:23:41", "remaining_time": "0:27:57", "throughput": 1034.5, "total_tokens": 5194344} {"current_steps": 57690, "total_steps": 76960, "loss": 0.085, "lr": 8.957253254105166e-06, "epoch": 14.992203742203742, "percentage": 74.96, "elapsed_time": "1:23:41", "remaining_time": "0:27:57", "throughput": 1034.5, "total_tokens": 5194792} {"current_steps": 57695, "total_steps": 76960, "loss": 0.0548, "lr": 8.95290538226148e-06, "epoch": 14.993503118503119, "percentage": 74.97, "elapsed_time": "1:23:41", "remaining_time": "0:27:56", "throughput": 1034.51, "total_tokens": 5195240} {"current_steps": 57700, "total_steps": 76960, "loss": 0.1236, "lr": 8.948558335735264e-06, "epoch": 14.994802494802494, "percentage": 74.97, "elapsed_time": "1:23:42", "remaining_time": "0:27:56", "throughput": 1034.51, "total_tokens": 5195704} {"current_steps": 57705, "total_steps": 76960, "loss": 0.5874, "lr": 8.944212114750058e-06, "epoch": 14.996101871101871, "percentage": 74.98, "elapsed_time": "1:23:42", "remaining_time": "0:27:55", "throughput": 1034.52, "total_tokens": 5196152} {"current_steps": 57710, "total_steps": 76960, "loss": 0.2108, "lr": 8.939866719529419e-06, "epoch": 14.997401247401248, "percentage": 74.99, "elapsed_time": "1:23:43", "remaining_time": "0:27:55", "throughput": 1034.53, "total_tokens": 5196632} {"current_steps": 57715, "total_steps": 76960, "loss": 0.7135, "lr": 8.935522150296816e-06, "epoch": 14.998700623700623, "percentage": 74.99, "elapsed_time": "1:23:43", "remaining_time": "0:27:55", "throughput": 1034.53, "total_tokens": 5197048} {"current_steps": 57720, "total_steps": 76960, "loss": 0.1511, "lr": 8.931178407275706e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "1:23:44", "remaining_time": "0:27:54", "throughput": 1034.51, "total_tokens": 5197456} {"current_steps": 57720, "total_steps": 76960, "eval_loss": 0.44215071201324463, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "1:23:57", "remaining_time": "0:27:59", "throughput": 1031.79, "total_tokens": 5197456} {"current_steps": 57725, "total_steps": 76960, "loss": 0.0129, "lr": 8.926835490689481e-06, "epoch": 15.001299376299377, "percentage": 75.01, "elapsed_time": "1:23:59", "remaining_time": "0:27:59", "throughput": 1031.45, "total_tokens": 5197920} {"current_steps": 57730, "total_steps": 76960, "loss": 0.2508, "lr": 8.922493400761505e-06, "epoch": 15.002598752598752, "percentage": 75.01, "elapsed_time": "1:23:59", "remaining_time": "0:27:58", "throughput": 1031.45, "total_tokens": 5198400} {"current_steps": 57735, "total_steps": 76960, "loss": 0.13, "lr": 8.9181521377151e-06, "epoch": 15.003898128898129, "percentage": 75.02, "elapsed_time": "1:24:00", "remaining_time": "0:27:58", "throughput": 1031.46, "total_tokens": 5198864} {"current_steps": 57740, "total_steps": 76960, "loss": 0.0789, "lr": 8.913811701773547e-06, "epoch": 15.005197505197506, "percentage": 75.03, "elapsed_time": "1:24:00", "remaining_time": "0:27:57", "throughput": 1031.46, "total_tokens": 5199312} {"current_steps": 57745, "total_steps": 76960, "loss": 0.0676, "lr": 8.909472093160065e-06, "epoch": 15.006496881496881, "percentage": 75.03, "elapsed_time": "1:24:01", "remaining_time": "0:27:57", "throughput": 1031.45, "total_tokens": 5199728} {"current_steps": 57750, "total_steps": 76960, "loss": 0.1472, "lr": 8.905133312097855e-06, "epoch": 15.007796257796258, "percentage": 75.04, "elapsed_time": "1:24:01", "remaining_time": "0:27:57", "throughput": 1031.47, "total_tokens": 5200256} {"current_steps": 57755, "total_steps": 76960, "loss": 0.0733, "lr": 8.900795358810062e-06, "epoch": 15.009095634095635, "percentage": 75.05, "elapsed_time": "1:24:02", "remaining_time": "0:27:56", "throughput": 1031.48, "total_tokens": 5200720} {"current_steps": 57760, "total_steps": 76960, "loss": 0.034, "lr": 8.896458233519782e-06, "epoch": 15.01039501039501, "percentage": 75.05, "elapsed_time": "1:24:02", "remaining_time": "0:27:56", "throughput": 1031.48, "total_tokens": 5201168} {"current_steps": 57765, "total_steps": 76960, "loss": 0.1427, "lr": 8.892121936450085e-06, "epoch": 15.011694386694387, "percentage": 75.06, "elapsed_time": "1:24:02", "remaining_time": "0:27:55", "throughput": 1031.48, "total_tokens": 5201584} {"current_steps": 57770, "total_steps": 76960, "loss": 0.037, "lr": 8.88778646782399e-06, "epoch": 15.012993762993762, "percentage": 75.06, "elapsed_time": "1:24:03", "remaining_time": "0:27:55", "throughput": 1031.49, "total_tokens": 5202080} {"current_steps": 57775, "total_steps": 76960, "loss": 0.1082, "lr": 8.883451827864481e-06, "epoch": 15.01429313929314, "percentage": 75.07, "elapsed_time": "1:24:03", "remaining_time": "0:27:54", "throughput": 1031.49, "total_tokens": 5202496} {"current_steps": 57780, "total_steps": 76960, "loss": 0.3493, "lr": 8.87911801679448e-06, "epoch": 15.015592515592516, "percentage": 75.08, "elapsed_time": "1:24:04", "remaining_time": "0:27:54", "throughput": 1031.49, "total_tokens": 5202960} {"current_steps": 57785, "total_steps": 76960, "loss": 0.2364, "lr": 8.874785034836894e-06, "epoch": 15.016891891891891, "percentage": 75.08, "elapsed_time": "1:24:04", "remaining_time": "0:27:53", "throughput": 1031.5, "total_tokens": 5203408} {"current_steps": 57790, "total_steps": 76960, "loss": 0.0614, "lr": 8.870452882214555e-06, "epoch": 15.018191268191268, "percentage": 75.09, "elapsed_time": "1:24:04", "remaining_time": "0:27:53", "throughput": 1031.51, "total_tokens": 5203920} {"current_steps": 57795, "total_steps": 76960, "loss": 0.0513, "lr": 8.866121559150286e-06, "epoch": 15.019490644490645, "percentage": 75.1, "elapsed_time": "1:24:05", "remaining_time": "0:27:53", "throughput": 1031.52, "total_tokens": 5204384} {"current_steps": 57800, "total_steps": 76960, "loss": 0.0064, "lr": 8.86179106586684e-06, "epoch": 15.02079002079002, "percentage": 75.1, "elapsed_time": "1:24:05", "remaining_time": "0:27:52", "throughput": 1031.52, "total_tokens": 5204816} {"current_steps": 57805, "total_steps": 76960, "loss": 0.062, "lr": 8.85746140258694e-06, "epoch": 15.022089397089397, "percentage": 75.11, "elapsed_time": "1:24:06", "remaining_time": "0:27:52", "throughput": 1031.52, "total_tokens": 5205264} {"current_steps": 57810, "total_steps": 76960, "loss": 0.3645, "lr": 8.853132569533266e-06, "epoch": 15.023388773388774, "percentage": 75.12, "elapsed_time": "1:24:06", "remaining_time": "0:27:51", "throughput": 1031.52, "total_tokens": 5205696} {"current_steps": 57815, "total_steps": 76960, "loss": 0.3993, "lr": 8.848804566928464e-06, "epoch": 15.02468814968815, "percentage": 75.12, "elapsed_time": "1:24:07", "remaining_time": "0:27:51", "throughput": 1031.52, "total_tokens": 5206128} {"current_steps": 57820, "total_steps": 76960, "loss": 0.1134, "lr": 8.844477394995118e-06, "epoch": 15.025987525987526, "percentage": 75.13, "elapsed_time": "1:24:07", "remaining_time": "0:27:50", "throughput": 1031.54, "total_tokens": 5206624} {"current_steps": 57825, "total_steps": 76960, "loss": 0.0429, "lr": 8.840151053955773e-06, "epoch": 15.027286902286903, "percentage": 75.14, "elapsed_time": "1:24:07", "remaining_time": "0:27:50", "throughput": 1031.54, "total_tokens": 5207088} {"current_steps": 57830, "total_steps": 76960, "loss": 0.2407, "lr": 8.83582554403295e-06, "epoch": 15.028586278586278, "percentage": 75.14, "elapsed_time": "1:24:08", "remaining_time": "0:27:49", "throughput": 1031.54, "total_tokens": 5207520} {"current_steps": 57835, "total_steps": 76960, "loss": 0.2191, "lr": 8.831500865449097e-06, "epoch": 15.029885654885655, "percentage": 75.15, "elapsed_time": "1:24:08", "remaining_time": "0:27:49", "throughput": 1031.54, "total_tokens": 5207936} {"current_steps": 57840, "total_steps": 76960, "loss": 0.1575, "lr": 8.827177018426649e-06, "epoch": 15.03118503118503, "percentage": 75.16, "elapsed_time": "1:24:09", "remaining_time": "0:27:49", "throughput": 1031.55, "total_tokens": 5208432} {"current_steps": 57845, "total_steps": 76960, "loss": 0.1273, "lr": 8.82285400318798e-06, "epoch": 15.032484407484407, "percentage": 75.16, "elapsed_time": "1:24:09", "remaining_time": "0:27:48", "throughput": 1031.56, "total_tokens": 5208912} {"current_steps": 57850, "total_steps": 76960, "loss": 0.2945, "lr": 8.818531819955442e-06, "epoch": 15.033783783783784, "percentage": 75.17, "elapsed_time": "1:24:09", "remaining_time": "0:27:48", "throughput": 1031.57, "total_tokens": 5209360} {"current_steps": 57855, "total_steps": 76960, "loss": 0.0957, "lr": 8.814210468951306e-06, "epoch": 15.03508316008316, "percentage": 75.18, "elapsed_time": "1:24:10", "remaining_time": "0:27:47", "throughput": 1031.57, "total_tokens": 5209808} {"current_steps": 57860, "total_steps": 76960, "loss": 0.1701, "lr": 8.809889950397843e-06, "epoch": 15.036382536382536, "percentage": 75.18, "elapsed_time": "1:24:10", "remaining_time": "0:27:47", "throughput": 1031.56, "total_tokens": 5210208} {"current_steps": 57865, "total_steps": 76960, "loss": 0.3419, "lr": 8.805570264517243e-06, "epoch": 15.037681912681913, "percentage": 75.19, "elapsed_time": "1:24:11", "remaining_time": "0:27:46", "throughput": 1031.57, "total_tokens": 5210688} {"current_steps": 57870, "total_steps": 76960, "loss": 0.0806, "lr": 8.801251411531692e-06, "epoch": 15.038981288981288, "percentage": 75.19, "elapsed_time": "1:24:11", "remaining_time": "0:27:46", "throughput": 1031.58, "total_tokens": 5211136} {"current_steps": 57875, "total_steps": 76960, "loss": 0.3244, "lr": 8.796933391663292e-06, "epoch": 15.040280665280665, "percentage": 75.2, "elapsed_time": "1:24:12", "remaining_time": "0:27:45", "throughput": 1031.58, "total_tokens": 5211568} {"current_steps": 57880, "total_steps": 76960, "loss": 0.2663, "lr": 8.792616205134132e-06, "epoch": 15.041580041580042, "percentage": 75.21, "elapsed_time": "1:24:12", "remaining_time": "0:27:45", "throughput": 1031.58, "total_tokens": 5212000} {"current_steps": 57885, "total_steps": 76960, "loss": 0.3698, "lr": 8.788299852166257e-06, "epoch": 15.042879417879417, "percentage": 75.21, "elapsed_time": "1:24:12", "remaining_time": "0:27:45", "throughput": 1031.58, "total_tokens": 5212448} {"current_steps": 57890, "total_steps": 76960, "loss": 0.5582, "lr": 8.783984332981649e-06, "epoch": 15.044178794178794, "percentage": 75.22, "elapsed_time": "1:24:13", "remaining_time": "0:27:44", "throughput": 1031.59, "total_tokens": 5212896} {"current_steps": 57895, "total_steps": 76960, "loss": 0.004, "lr": 8.779669647802269e-06, "epoch": 15.045478170478171, "percentage": 75.23, "elapsed_time": "1:24:13", "remaining_time": "0:27:44", "throughput": 1031.59, "total_tokens": 5213328} {"current_steps": 57900, "total_steps": 76960, "loss": 0.0268, "lr": 8.775355796850015e-06, "epoch": 15.046777546777546, "percentage": 75.23, "elapsed_time": "1:24:14", "remaining_time": "0:27:43", "throughput": 1031.58, "total_tokens": 5213744} {"current_steps": 57905, "total_steps": 76960, "loss": 0.0696, "lr": 8.771042780346766e-06, "epoch": 15.048076923076923, "percentage": 75.24, "elapsed_time": "1:24:14", "remaining_time": "0:27:43", "throughput": 1031.59, "total_tokens": 5214192} {"current_steps": 57910, "total_steps": 76960, "loss": 0.0203, "lr": 8.766730598514328e-06, "epoch": 15.049376299376299, "percentage": 75.25, "elapsed_time": "1:24:14", "remaining_time": "0:27:42", "throughput": 1031.59, "total_tokens": 5214640} {"current_steps": 57915, "total_steps": 76960, "loss": 0.1381, "lr": 8.762419251574489e-06, "epoch": 15.050675675675675, "percentage": 75.25, "elapsed_time": "1:24:15", "remaining_time": "0:27:42", "throughput": 1031.59, "total_tokens": 5215072} {"current_steps": 57920, "total_steps": 76960, "loss": 0.2395, "lr": 8.758108739748986e-06, "epoch": 15.051975051975052, "percentage": 75.26, "elapsed_time": "1:24:15", "remaining_time": "0:27:41", "throughput": 1031.6, "total_tokens": 5215536} {"current_steps": 57925, "total_steps": 76960, "loss": 0.3358, "lr": 8.753799063259522e-06, "epoch": 15.053274428274428, "percentage": 75.27, "elapsed_time": "1:24:16", "remaining_time": "0:27:41", "throughput": 1031.61, "total_tokens": 5216000} {"current_steps": 57930, "total_steps": 76960, "loss": 0.0516, "lr": 8.749490222327728e-06, "epoch": 15.054573804573804, "percentage": 75.27, "elapsed_time": "1:24:16", "remaining_time": "0:27:41", "throughput": 1031.61, "total_tokens": 5216432} {"current_steps": 57935, "total_steps": 76960, "loss": 0.0823, "lr": 8.745182217175232e-06, "epoch": 15.055873180873181, "percentage": 75.28, "elapsed_time": "1:24:17", "remaining_time": "0:27:40", "throughput": 1031.61, "total_tokens": 5216912} {"current_steps": 57940, "total_steps": 76960, "loss": 0.0226, "lr": 8.740875048023581e-06, "epoch": 15.057172557172557, "percentage": 75.29, "elapsed_time": "1:24:17", "remaining_time": "0:27:40", "throughput": 1031.63, "total_tokens": 5217392} {"current_steps": 57945, "total_steps": 76960, "loss": 0.506, "lr": 8.736568715094304e-06, "epoch": 15.058471933471933, "percentage": 75.29, "elapsed_time": "1:24:17", "remaining_time": "0:27:39", "throughput": 1031.64, "total_tokens": 5217904} {"current_steps": 57950, "total_steps": 76960, "loss": 0.0559, "lr": 8.732263218608892e-06, "epoch": 15.05977130977131, "percentage": 75.3, "elapsed_time": "1:24:18", "remaining_time": "0:27:39", "throughput": 1031.65, "total_tokens": 5218368} {"current_steps": 57955, "total_steps": 76960, "loss": 0.0365, "lr": 8.727958558788757e-06, "epoch": 15.061070686070686, "percentage": 75.31, "elapsed_time": "1:24:18", "remaining_time": "0:27:38", "throughput": 1031.65, "total_tokens": 5218784} {"current_steps": 57960, "total_steps": 76960, "loss": 0.0524, "lr": 8.723654735855316e-06, "epoch": 15.062370062370062, "percentage": 75.31, "elapsed_time": "1:24:19", "remaining_time": "0:27:38", "throughput": 1031.64, "total_tokens": 5219184} {"current_steps": 57965, "total_steps": 76960, "loss": 0.0119, "lr": 8.719351750029896e-06, "epoch": 15.06366943866944, "percentage": 75.32, "elapsed_time": "1:24:19", "remaining_time": "0:27:37", "throughput": 1031.64, "total_tokens": 5219600} {"current_steps": 57970, "total_steps": 76960, "loss": 0.3308, "lr": 8.715049601533825e-06, "epoch": 15.064968814968815, "percentage": 75.32, "elapsed_time": "1:24:19", "remaining_time": "0:27:37", "throughput": 1031.65, "total_tokens": 5220080} {"current_steps": 57975, "total_steps": 76960, "loss": 0.0641, "lr": 8.71074829058835e-06, "epoch": 15.066268191268192, "percentage": 75.33, "elapsed_time": "1:24:20", "remaining_time": "0:27:37", "throughput": 1031.64, "total_tokens": 5220480} {"current_steps": 57980, "total_steps": 76960, "loss": 0.0258, "lr": 8.706447817414696e-06, "epoch": 15.067567567567568, "percentage": 75.34, "elapsed_time": "1:24:20", "remaining_time": "0:27:36", "throughput": 1031.65, "total_tokens": 5220960} {"current_steps": 57985, "total_steps": 76960, "loss": 0.1456, "lr": 8.702148182234043e-06, "epoch": 15.068866943866944, "percentage": 75.34, "elapsed_time": "1:24:21", "remaining_time": "0:27:36", "throughput": 1031.65, "total_tokens": 5221392} {"current_steps": 57990, "total_steps": 76960, "loss": 0.1872, "lr": 8.697849385267534e-06, "epoch": 15.07016632016632, "percentage": 75.35, "elapsed_time": "1:24:21", "remaining_time": "0:27:35", "throughput": 1031.66, "total_tokens": 5221856} {"current_steps": 57995, "total_steps": 76960, "loss": 0.1447, "lr": 8.693551426736241e-06, "epoch": 15.071465696465696, "percentage": 75.36, "elapsed_time": "1:24:22", "remaining_time": "0:27:35", "throughput": 1031.66, "total_tokens": 5222304} {"current_steps": 58000, "total_steps": 76960, "loss": 0.12, "lr": 8.68925430686123e-06, "epoch": 15.072765072765073, "percentage": 75.36, "elapsed_time": "1:24:22", "remaining_time": "0:27:34", "throughput": 1031.66, "total_tokens": 5222736} {"current_steps": 58005, "total_steps": 76960, "loss": 0.2272, "lr": 8.684958025863493e-06, "epoch": 15.07406444906445, "percentage": 75.37, "elapsed_time": "1:24:22", "remaining_time": "0:27:34", "throughput": 1031.66, "total_tokens": 5223168} {"current_steps": 58010, "total_steps": 76960, "loss": 0.1566, "lr": 8.680662583964003e-06, "epoch": 15.075363825363825, "percentage": 75.38, "elapsed_time": "1:24:23", "remaining_time": "0:27:34", "throughput": 1031.67, "total_tokens": 5223616} {"current_steps": 58015, "total_steps": 76960, "loss": 0.4895, "lr": 8.676367981383666e-06, "epoch": 15.076663201663202, "percentage": 75.38, "elapsed_time": "1:24:23", "remaining_time": "0:27:33", "throughput": 1031.67, "total_tokens": 5224048} {"current_steps": 58020, "total_steps": 76960, "loss": 0.1516, "lr": 8.672074218343362e-06, "epoch": 15.077962577962579, "percentage": 75.39, "elapsed_time": "1:24:24", "remaining_time": "0:27:33", "throughput": 1031.67, "total_tokens": 5224496} {"current_steps": 58025, "total_steps": 76960, "loss": 0.3732, "lr": 8.667781295063934e-06, "epoch": 15.079261954261954, "percentage": 75.4, "elapsed_time": "1:24:24", "remaining_time": "0:27:32", "throughput": 1031.68, "total_tokens": 5224960} {"current_steps": 58030, "total_steps": 76960, "loss": 0.3605, "lr": 8.663489211766157e-06, "epoch": 15.08056133056133, "percentage": 75.4, "elapsed_time": "1:24:24", "remaining_time": "0:27:32", "throughput": 1031.68, "total_tokens": 5225392} {"current_steps": 58035, "total_steps": 76960, "loss": 0.221, "lr": 8.65919796867079e-06, "epoch": 15.081860706860708, "percentage": 75.41, "elapsed_time": "1:24:25", "remaining_time": "0:27:31", "throughput": 1031.67, "total_tokens": 5225792} {"current_steps": 58040, "total_steps": 76960, "loss": 0.0031, "lr": 8.654907565998518e-06, "epoch": 15.083160083160083, "percentage": 75.42, "elapsed_time": "1:24:25", "remaining_time": "0:27:31", "throughput": 1031.69, "total_tokens": 5226272} {"current_steps": 58045, "total_steps": 76960, "loss": 0.0427, "lr": 8.65061800397002e-06, "epoch": 15.08445945945946, "percentage": 75.42, "elapsed_time": "1:24:26", "remaining_time": "0:27:30", "throughput": 1031.7, "total_tokens": 5226752} {"current_steps": 58050, "total_steps": 76960, "loss": 0.1977, "lr": 8.646329282805898e-06, "epoch": 15.085758835758837, "percentage": 75.43, "elapsed_time": "1:24:26", "remaining_time": "0:27:30", "throughput": 1031.7, "total_tokens": 5227184} {"current_steps": 58055, "total_steps": 76960, "loss": 0.0448, "lr": 8.642041402726728e-06, "epoch": 15.087058212058212, "percentage": 75.44, "elapsed_time": "1:24:27", "remaining_time": "0:27:30", "throughput": 1031.7, "total_tokens": 5227616} {"current_steps": 58060, "total_steps": 76960, "loss": 0.0965, "lr": 8.637754363953044e-06, "epoch": 15.088357588357589, "percentage": 75.44, "elapsed_time": "1:24:27", "remaining_time": "0:27:29", "throughput": 1031.7, "total_tokens": 5228080} {"current_steps": 58065, "total_steps": 76960, "loss": 0.0271, "lr": 8.633468166705336e-06, "epoch": 15.089656964656964, "percentage": 75.45, "elapsed_time": "1:24:27", "remaining_time": "0:27:29", "throughput": 1031.71, "total_tokens": 5228560} {"current_steps": 58070, "total_steps": 76960, "loss": 0.0215, "lr": 8.629182811204034e-06, "epoch": 15.09095634095634, "percentage": 75.45, "elapsed_time": "1:24:28", "remaining_time": "0:27:28", "throughput": 1031.73, "total_tokens": 5229056} {"current_steps": 58075, "total_steps": 76960, "loss": 0.096, "lr": 8.624898297669557e-06, "epoch": 15.092255717255718, "percentage": 75.46, "elapsed_time": "1:24:28", "remaining_time": "0:27:28", "throughput": 1031.74, "total_tokens": 5229536} {"current_steps": 58080, "total_steps": 76960, "loss": 0.3286, "lr": 8.620614626322248e-06, "epoch": 15.093555093555093, "percentage": 75.47, "elapsed_time": "1:24:29", "remaining_time": "0:27:27", "throughput": 1031.74, "total_tokens": 5229968} {"current_steps": 58085, "total_steps": 76960, "loss": 0.0358, "lr": 8.616331797382416e-06, "epoch": 15.09485446985447, "percentage": 75.47, "elapsed_time": "1:24:29", "remaining_time": "0:27:27", "throughput": 1031.74, "total_tokens": 5230432} {"current_steps": 58090, "total_steps": 76960, "loss": 0.0156, "lr": 8.612049811070336e-06, "epoch": 15.096153846153847, "percentage": 75.48, "elapsed_time": "1:24:29", "remaining_time": "0:27:26", "throughput": 1031.74, "total_tokens": 5230864} {"current_steps": 58095, "total_steps": 76960, "loss": 0.2279, "lr": 8.607768667606236e-06, "epoch": 15.097453222453222, "percentage": 75.49, "elapsed_time": "1:24:30", "remaining_time": "0:27:26", "throughput": 1031.74, "total_tokens": 5231280} {"current_steps": 58100, "total_steps": 76960, "loss": 0.2224, "lr": 8.603488367210308e-06, "epoch": 15.098752598752599, "percentage": 75.49, "elapsed_time": "1:24:30", "remaining_time": "0:27:26", "throughput": 1031.74, "total_tokens": 5231712} {"current_steps": 58105, "total_steps": 76960, "loss": 0.0974, "lr": 8.599208910102677e-06, "epoch": 15.100051975051976, "percentage": 75.5, "elapsed_time": "1:24:31", "remaining_time": "0:27:25", "throughput": 1031.75, "total_tokens": 5232160} {"current_steps": 58110, "total_steps": 76960, "loss": 0.1672, "lr": 8.594930296503453e-06, "epoch": 15.10135135135135, "percentage": 75.51, "elapsed_time": "1:24:31", "remaining_time": "0:27:25", "throughput": 1031.75, "total_tokens": 5232624} {"current_steps": 58115, "total_steps": 76960, "loss": 0.0314, "lr": 8.590652526632675e-06, "epoch": 15.102650727650728, "percentage": 75.51, "elapsed_time": "1:24:32", "remaining_time": "0:27:24", "throughput": 1031.75, "total_tokens": 5233056} {"current_steps": 58120, "total_steps": 76960, "loss": 0.0633, "lr": 8.58637560071037e-06, "epoch": 15.103950103950105, "percentage": 75.52, "elapsed_time": "1:24:32", "remaining_time": "0:27:24", "throughput": 1031.75, "total_tokens": 5233488} {"current_steps": 58125, "total_steps": 76960, "loss": 0.234, "lr": 8.582099518956485e-06, "epoch": 15.10524948024948, "percentage": 75.53, "elapsed_time": "1:24:32", "remaining_time": "0:27:23", "throughput": 1031.75, "total_tokens": 5233920} {"current_steps": 58130, "total_steps": 76960, "loss": 0.0973, "lr": 8.577824281590952e-06, "epoch": 15.106548856548857, "percentage": 75.53, "elapsed_time": "1:24:33", "remaining_time": "0:27:23", "throughput": 1031.77, "total_tokens": 5234432} {"current_steps": 58135, "total_steps": 76960, "loss": 0.0498, "lr": 8.573549888833651e-06, "epoch": 15.107848232848232, "percentage": 75.54, "elapsed_time": "1:24:33", "remaining_time": "0:27:22", "throughput": 1031.78, "total_tokens": 5234912} {"current_steps": 58140, "total_steps": 76960, "loss": 0.2158, "lr": 8.569276340904427e-06, "epoch": 15.109147609147609, "percentage": 75.55, "elapsed_time": "1:24:34", "remaining_time": "0:27:22", "throughput": 1031.79, "total_tokens": 5235392} {"current_steps": 58145, "total_steps": 76960, "loss": 0.1449, "lr": 8.565003638023065e-06, "epoch": 15.110446985446986, "percentage": 75.55, "elapsed_time": "1:24:34", "remaining_time": "0:27:22", "throughput": 1031.8, "total_tokens": 5235856} {"current_steps": 58150, "total_steps": 76960, "loss": 0.0838, "lr": 8.560731780409304e-06, "epoch": 15.111746361746361, "percentage": 75.56, "elapsed_time": "1:24:34", "remaining_time": "0:27:21", "throughput": 1031.8, "total_tokens": 5236304} {"current_steps": 58155, "total_steps": 76960, "loss": 0.0919, "lr": 8.556460768282867e-06, "epoch": 15.113045738045738, "percentage": 75.57, "elapsed_time": "1:24:35", "remaining_time": "0:27:21", "throughput": 1031.81, "total_tokens": 5236752} {"current_steps": 58160, "total_steps": 76960, "loss": 0.3617, "lr": 8.5521906018634e-06, "epoch": 15.114345114345115, "percentage": 75.57, "elapsed_time": "1:24:35", "remaining_time": "0:27:20", "throughput": 1031.8, "total_tokens": 5237152} {"current_steps": 58165, "total_steps": 76960, "loss": 0.0921, "lr": 8.54792128137053e-06, "epoch": 15.11564449064449, "percentage": 75.58, "elapsed_time": "1:24:36", "remaining_time": "0:27:20", "throughput": 1031.8, "total_tokens": 5237600} {"current_steps": 58170, "total_steps": 76960, "loss": 0.0093, "lr": 8.543652807023833e-06, "epoch": 15.116943866943867, "percentage": 75.58, "elapsed_time": "1:24:36", "remaining_time": "0:27:19", "throughput": 1031.81, "total_tokens": 5238048} {"current_steps": 58175, "total_steps": 76960, "loss": 0.0398, "lr": 8.539385179042847e-06, "epoch": 15.118243243243244, "percentage": 75.59, "elapsed_time": "1:24:36", "remaining_time": "0:27:19", "throughput": 1031.81, "total_tokens": 5238480} {"current_steps": 58180, "total_steps": 76960, "loss": 0.3144, "lr": 8.535118397647044e-06, "epoch": 15.119542619542619, "percentage": 75.6, "elapsed_time": "1:24:37", "remaining_time": "0:27:18", "throughput": 1031.81, "total_tokens": 5238928} {"current_steps": 58185, "total_steps": 76960, "loss": 0.0314, "lr": 8.530852463055889e-06, "epoch": 15.120841995841996, "percentage": 75.6, "elapsed_time": "1:24:37", "remaining_time": "0:27:18", "throughput": 1031.81, "total_tokens": 5239344} {"current_steps": 58190, "total_steps": 76960, "loss": 0.4338, "lr": 8.526587375488759e-06, "epoch": 15.122141372141373, "percentage": 75.61, "elapsed_time": "1:24:38", "remaining_time": "0:27:18", "throughput": 1031.82, "total_tokens": 5239824} {"current_steps": 58195, "total_steps": 76960, "loss": 0.0519, "lr": 8.522323135165028e-06, "epoch": 15.123440748440748, "percentage": 75.62, "elapsed_time": "1:24:38", "remaining_time": "0:27:17", "throughput": 1031.83, "total_tokens": 5240320} {"current_steps": 58200, "total_steps": 76960, "loss": 0.3879, "lr": 8.518059742304005e-06, "epoch": 15.124740124740125, "percentage": 75.62, "elapsed_time": "1:24:39", "remaining_time": "0:27:17", "throughput": 1031.84, "total_tokens": 5240800} {"current_steps": 58205, "total_steps": 76960, "loss": 0.0725, "lr": 8.51379719712497e-06, "epoch": 15.126039501039502, "percentage": 75.63, "elapsed_time": "1:24:39", "remaining_time": "0:27:16", "throughput": 1031.85, "total_tokens": 5241248} {"current_steps": 58210, "total_steps": 76960, "loss": 0.2127, "lr": 8.50953549984714e-06, "epoch": 15.127338877338877, "percentage": 75.64, "elapsed_time": "1:24:39", "remaining_time": "0:27:16", "throughput": 1031.85, "total_tokens": 5241696} {"current_steps": 58215, "total_steps": 76960, "loss": 0.0616, "lr": 8.505274650689692e-06, "epoch": 15.128638253638254, "percentage": 75.64, "elapsed_time": "1:24:40", "remaining_time": "0:27:15", "throughput": 1031.85, "total_tokens": 5242144} {"current_steps": 58220, "total_steps": 76960, "loss": 0.2573, "lr": 8.501014649871785e-06, "epoch": 15.12993762993763, "percentage": 75.65, "elapsed_time": "1:24:40", "remaining_time": "0:27:15", "throughput": 1031.86, "total_tokens": 5242608} {"current_steps": 58225, "total_steps": 76960, "loss": 0.1974, "lr": 8.496755497612492e-06, "epoch": 15.131237006237006, "percentage": 75.66, "elapsed_time": "1:24:41", "remaining_time": "0:27:14", "throughput": 1031.86, "total_tokens": 5243040} {"current_steps": 58230, "total_steps": 76960, "loss": 0.0501, "lr": 8.492497194130877e-06, "epoch": 15.132536382536383, "percentage": 75.66, "elapsed_time": "1:24:41", "remaining_time": "0:27:14", "throughput": 1031.87, "total_tokens": 5243504} {"current_steps": 58235, "total_steps": 76960, "loss": 0.4174, "lr": 8.488239739645947e-06, "epoch": 15.133835758835758, "percentage": 75.67, "elapsed_time": "1:24:41", "remaining_time": "0:27:14", "throughput": 1031.87, "total_tokens": 5243952} {"current_steps": 58240, "total_steps": 76960, "loss": 0.0613, "lr": 8.483983134376677e-06, "epoch": 15.135135135135135, "percentage": 75.68, "elapsed_time": "1:24:42", "remaining_time": "0:27:13", "throughput": 1031.88, "total_tokens": 5244400} {"current_steps": 58245, "total_steps": 76960, "loss": 0.0087, "lr": 8.479727378541972e-06, "epoch": 15.136434511434512, "percentage": 75.68, "elapsed_time": "1:24:42", "remaining_time": "0:27:13", "throughput": 1031.88, "total_tokens": 5244864} {"current_steps": 58250, "total_steps": 76960, "loss": 0.0412, "lr": 8.475472472360724e-06, "epoch": 15.137733887733887, "percentage": 75.69, "elapsed_time": "1:24:43", "remaining_time": "0:27:12", "throughput": 1031.88, "total_tokens": 5245296} {"current_steps": 58255, "total_steps": 76960, "loss": 0.0392, "lr": 8.471218416051752e-06, "epoch": 15.139033264033264, "percentage": 75.7, "elapsed_time": "1:24:43", "remaining_time": "0:27:12", "throughput": 1031.89, "total_tokens": 5245744} {"current_steps": 58260, "total_steps": 76960, "loss": 0.2831, "lr": 8.46696520983386e-06, "epoch": 15.140332640332641, "percentage": 75.7, "elapsed_time": "1:24:44", "remaining_time": "0:27:11", "throughput": 1031.89, "total_tokens": 5246208} {"current_steps": 58265, "total_steps": 76960, "loss": 0.3931, "lr": 8.462712853925784e-06, "epoch": 15.141632016632016, "percentage": 75.71, "elapsed_time": "1:24:44", "remaining_time": "0:27:11", "throughput": 1031.9, "total_tokens": 5246640} {"current_steps": 58270, "total_steps": 76960, "loss": 0.094, "lr": 8.458461348546228e-06, "epoch": 15.142931392931393, "percentage": 75.71, "elapsed_time": "1:24:44", "remaining_time": "0:27:10", "throughput": 1031.9, "total_tokens": 5247088} {"current_steps": 58275, "total_steps": 76960, "loss": 0.2881, "lr": 8.454210693913863e-06, "epoch": 15.14423076923077, "percentage": 75.72, "elapsed_time": "1:24:45", "remaining_time": "0:27:10", "throughput": 1031.9, "total_tokens": 5247536} {"current_steps": 58280, "total_steps": 76960, "loss": 0.2718, "lr": 8.449960890247289e-06, "epoch": 15.145530145530145, "percentage": 75.73, "elapsed_time": "1:24:45", "remaining_time": "0:27:10", "throughput": 1031.9, "total_tokens": 5247968} {"current_steps": 58285, "total_steps": 76960, "loss": 0.301, "lr": 8.445711937765092e-06, "epoch": 15.146829521829522, "percentage": 75.73, "elapsed_time": "1:24:46", "remaining_time": "0:27:09", "throughput": 1031.9, "total_tokens": 5248400} {"current_steps": 58290, "total_steps": 76960, "loss": 0.3355, "lr": 8.441463836685782e-06, "epoch": 15.148128898128897, "percentage": 75.74, "elapsed_time": "1:24:46", "remaining_time": "0:27:09", "throughput": 1031.91, "total_tokens": 5248848} {"current_steps": 58295, "total_steps": 76960, "loss": 0.0611, "lr": 8.437216587227859e-06, "epoch": 15.149428274428274, "percentage": 75.75, "elapsed_time": "1:24:46", "remaining_time": "0:27:08", "throughput": 1031.91, "total_tokens": 5249296} {"current_steps": 58300, "total_steps": 76960, "loss": 0.113, "lr": 8.432970189609752e-06, "epoch": 15.150727650727651, "percentage": 75.75, "elapsed_time": "1:24:47", "remaining_time": "0:27:08", "throughput": 1031.91, "total_tokens": 5249696} {"current_steps": 58305, "total_steps": 76960, "loss": 0.0122, "lr": 8.42872464404986e-06, "epoch": 15.152027027027026, "percentage": 75.76, "elapsed_time": "1:24:47", "remaining_time": "0:27:07", "throughput": 1031.9, "total_tokens": 5250112} {"current_steps": 58310, "total_steps": 76960, "loss": 0.1212, "lr": 8.424479950766536e-06, "epoch": 15.153326403326403, "percentage": 75.77, "elapsed_time": "1:24:48", "remaining_time": "0:27:07", "throughput": 1031.91, "total_tokens": 5250560} {"current_steps": 58315, "total_steps": 76960, "loss": 0.1484, "lr": 8.420236109978102e-06, "epoch": 15.15462577962578, "percentage": 75.77, "elapsed_time": "1:24:48", "remaining_time": "0:27:06", "throughput": 1031.91, "total_tokens": 5250992} {"current_steps": 58320, "total_steps": 76960, "loss": 0.3207, "lr": 8.4159931219028e-06, "epoch": 15.155925155925155, "percentage": 75.78, "elapsed_time": "1:24:49", "remaining_time": "0:27:06", "throughput": 1031.92, "total_tokens": 5251472} {"current_steps": 58325, "total_steps": 76960, "loss": 0.737, "lr": 8.41175098675887e-06, "epoch": 15.157224532224532, "percentage": 75.79, "elapsed_time": "1:24:49", "remaining_time": "0:27:06", "throughput": 1031.91, "total_tokens": 5251888} {"current_steps": 58330, "total_steps": 76960, "loss": 0.0489, "lr": 8.407509704764474e-06, "epoch": 15.15852390852391, "percentage": 75.79, "elapsed_time": "1:24:49", "remaining_time": "0:27:05", "throughput": 1031.92, "total_tokens": 5252336} {"current_steps": 58335, "total_steps": 76960, "loss": 0.2089, "lr": 8.40326927613776e-06, "epoch": 15.159823284823284, "percentage": 75.8, "elapsed_time": "1:24:50", "remaining_time": "0:27:05", "throughput": 1031.92, "total_tokens": 5252768} {"current_steps": 58340, "total_steps": 76960, "loss": 0.1145, "lr": 8.3990297010968e-06, "epoch": 15.161122661122661, "percentage": 75.81, "elapsed_time": "1:24:50", "remaining_time": "0:27:04", "throughput": 1031.92, "total_tokens": 5253184} {"current_steps": 58345, "total_steps": 76960, "loss": 0.0025, "lr": 8.394790979859649e-06, "epoch": 15.162422037422038, "percentage": 75.81, "elapsed_time": "1:24:51", "remaining_time": "0:27:04", "throughput": 1031.92, "total_tokens": 5253632} {"current_steps": 58350, "total_steps": 76960, "loss": 0.2862, "lr": 8.390553112644317e-06, "epoch": 15.163721413721413, "percentage": 75.82, "elapsed_time": "1:24:51", "remaining_time": "0:27:03", "throughput": 1031.93, "total_tokens": 5254096} {"current_steps": 58355, "total_steps": 76960, "loss": 0.1001, "lr": 8.386316099668746e-06, "epoch": 15.16502079002079, "percentage": 75.83, "elapsed_time": "1:24:51", "remaining_time": "0:27:03", "throughput": 1031.93, "total_tokens": 5254544} {"current_steps": 58360, "total_steps": 76960, "loss": 0.5264, "lr": 8.38207994115086e-06, "epoch": 15.166320166320165, "percentage": 75.83, "elapsed_time": "1:24:52", "remaining_time": "0:27:02", "throughput": 1031.94, "total_tokens": 5255040} {"current_steps": 58365, "total_steps": 76960, "loss": 0.0175, "lr": 8.377844637308521e-06, "epoch": 15.167619542619542, "percentage": 75.84, "elapsed_time": "1:24:52", "remaining_time": "0:27:02", "throughput": 1031.94, "total_tokens": 5255472} {"current_steps": 58370, "total_steps": 76960, "loss": 0.0143, "lr": 8.373610188359565e-06, "epoch": 15.16891891891892, "percentage": 75.84, "elapsed_time": "1:24:53", "remaining_time": "0:27:02", "throughput": 1031.95, "total_tokens": 5255952} {"current_steps": 58375, "total_steps": 76960, "loss": 0.066, "lr": 8.369376594521764e-06, "epoch": 15.170218295218294, "percentage": 75.85, "elapsed_time": "1:24:53", "remaining_time": "0:27:01", "throughput": 1031.96, "total_tokens": 5256416} {"current_steps": 58380, "total_steps": 76960, "loss": 0.1134, "lr": 8.365143856012855e-06, "epoch": 15.171517671517671, "percentage": 75.86, "elapsed_time": "1:24:54", "remaining_time": "0:27:01", "throughput": 1031.97, "total_tokens": 5256896} {"current_steps": 58385, "total_steps": 76960, "loss": 0.0098, "lr": 8.360911973050537e-06, "epoch": 15.172817047817048, "percentage": 75.86, "elapsed_time": "1:24:54", "remaining_time": "0:27:00", "throughput": 1031.98, "total_tokens": 5257376} {"current_steps": 58390, "total_steps": 76960, "loss": 0.2507, "lr": 8.356680945852466e-06, "epoch": 15.174116424116423, "percentage": 75.87, "elapsed_time": "1:24:54", "remaining_time": "0:27:00", "throughput": 1031.99, "total_tokens": 5257824} {"current_steps": 58395, "total_steps": 76960, "loss": 0.2459, "lr": 8.352450774636237e-06, "epoch": 15.1754158004158, "percentage": 75.88, "elapsed_time": "1:24:55", "remaining_time": "0:26:59", "throughput": 1031.99, "total_tokens": 5258272} {"current_steps": 58400, "total_steps": 76960, "loss": 0.3586, "lr": 8.348221459619418e-06, "epoch": 15.176715176715177, "percentage": 75.88, "elapsed_time": "1:24:55", "remaining_time": "0:26:59", "throughput": 1031.99, "total_tokens": 5258704} {"current_steps": 58405, "total_steps": 76960, "loss": 0.373, "lr": 8.343993001019529e-06, "epoch": 15.178014553014552, "percentage": 75.89, "elapsed_time": "1:24:56", "remaining_time": "0:26:59", "throughput": 1031.99, "total_tokens": 5259136} {"current_steps": 58410, "total_steps": 76960, "loss": 0.3202, "lr": 8.339765399054029e-06, "epoch": 15.17931392931393, "percentage": 75.9, "elapsed_time": "1:24:56", "remaining_time": "0:26:58", "throughput": 1032.0, "total_tokens": 5259600} {"current_steps": 58415, "total_steps": 76960, "loss": 0.0634, "lr": 8.335538653940356e-06, "epoch": 15.180613305613306, "percentage": 75.9, "elapsed_time": "1:24:56", "remaining_time": "0:26:58", "throughput": 1032.0, "total_tokens": 5260048} {"current_steps": 58420, "total_steps": 76960, "loss": 0.4044, "lr": 8.331312765895899e-06, "epoch": 15.181912681912682, "percentage": 75.91, "elapsed_time": "1:24:57", "remaining_time": "0:26:57", "throughput": 1032.01, "total_tokens": 5260496} {"current_steps": 58425, "total_steps": 76960, "loss": 0.3778, "lr": 8.327087735138006e-06, "epoch": 15.183212058212058, "percentage": 75.92, "elapsed_time": "1:24:57", "remaining_time": "0:26:57", "throughput": 1032.01, "total_tokens": 5260944} {"current_steps": 58430, "total_steps": 76960, "loss": 0.295, "lr": 8.322863561883956e-06, "epoch": 15.184511434511435, "percentage": 75.92, "elapsed_time": "1:24:58", "remaining_time": "0:26:56", "throughput": 1032.02, "total_tokens": 5261408} {"current_steps": 58435, "total_steps": 76960, "loss": 0.0299, "lr": 8.318640246351023e-06, "epoch": 15.18581081081081, "percentage": 75.93, "elapsed_time": "1:24:58", "remaining_time": "0:26:56", "throughput": 1032.02, "total_tokens": 5261840} {"current_steps": 58440, "total_steps": 76960, "loss": 0.1376, "lr": 8.314417788756395e-06, "epoch": 15.187110187110187, "percentage": 75.94, "elapsed_time": "1:24:59", "remaining_time": "0:26:55", "throughput": 1032.02, "total_tokens": 5262272} {"current_steps": 58445, "total_steps": 76960, "loss": 0.0272, "lr": 8.310196189317249e-06, "epoch": 15.188409563409563, "percentage": 75.94, "elapsed_time": "1:24:59", "remaining_time": "0:26:55", "throughput": 1032.02, "total_tokens": 5262704} {"current_steps": 58450, "total_steps": 76960, "loss": 0.0251, "lr": 8.305975448250704e-06, "epoch": 15.18970893970894, "percentage": 75.95, "elapsed_time": "1:24:59", "remaining_time": "0:26:55", "throughput": 1032.02, "total_tokens": 5263136} {"current_steps": 58455, "total_steps": 76960, "loss": 0.0154, "lr": 8.301755565773844e-06, "epoch": 15.191008316008316, "percentage": 75.96, "elapsed_time": "1:25:00", "remaining_time": "0:26:54", "throughput": 1032.02, "total_tokens": 5263600} {"current_steps": 58460, "total_steps": 76960, "loss": 0.1001, "lr": 8.29753654210369e-06, "epoch": 15.192307692307692, "percentage": 75.96, "elapsed_time": "1:25:00", "remaining_time": "0:26:54", "throughput": 1032.04, "total_tokens": 5264096} {"current_steps": 58465, "total_steps": 76960, "loss": 0.4887, "lr": 8.293318377457241e-06, "epoch": 15.193607068607069, "percentage": 75.97, "elapsed_time": "1:25:01", "remaining_time": "0:26:53", "throughput": 1032.03, "total_tokens": 5264512} {"current_steps": 58470, "total_steps": 76960, "loss": 0.1994, "lr": 8.289101072051434e-06, "epoch": 15.194906444906445, "percentage": 75.97, "elapsed_time": "1:25:01", "remaining_time": "0:26:53", "throughput": 1032.04, "total_tokens": 5264976} {"current_steps": 58475, "total_steps": 76960, "loss": 0.3758, "lr": 8.284884626103165e-06, "epoch": 15.19620582120582, "percentage": 75.98, "elapsed_time": "1:25:01", "remaining_time": "0:26:52", "throughput": 1032.05, "total_tokens": 5265456} {"current_steps": 58480, "total_steps": 76960, "loss": 0.4941, "lr": 8.280669039829295e-06, "epoch": 15.197505197505198, "percentage": 75.99, "elapsed_time": "1:25:02", "remaining_time": "0:26:52", "throughput": 1032.05, "total_tokens": 5265904} {"current_steps": 58485, "total_steps": 76960, "loss": 0.6957, "lr": 8.276454313446633e-06, "epoch": 15.198804573804575, "percentage": 75.99, "elapsed_time": "1:25:02", "remaining_time": "0:26:51", "throughput": 1032.05, "total_tokens": 5266336} {"current_steps": 58490, "total_steps": 76960, "loss": 0.0481, "lr": 8.27224044717196e-06, "epoch": 15.20010395010395, "percentage": 76.0, "elapsed_time": "1:25:03", "remaining_time": "0:26:51", "throughput": 1032.05, "total_tokens": 5266752} {"current_steps": 58495, "total_steps": 76960, "loss": 0.1386, "lr": 8.268027441221981e-06, "epoch": 15.201403326403327, "percentage": 76.01, "elapsed_time": "1:25:03", "remaining_time": "0:26:51", "throughput": 1032.05, "total_tokens": 5267200} {"current_steps": 58500, "total_steps": 76960, "loss": 0.1465, "lr": 8.26381529581339e-06, "epoch": 15.202702702702704, "percentage": 76.01, "elapsed_time": "1:25:04", "remaining_time": "0:26:50", "throughput": 1032.06, "total_tokens": 5267648} {"current_steps": 58505, "total_steps": 76960, "loss": 0.14, "lr": 8.259604011162806e-06, "epoch": 15.204002079002079, "percentage": 76.02, "elapsed_time": "1:25:04", "remaining_time": "0:26:50", "throughput": 1032.07, "total_tokens": 5268144} {"current_steps": 58510, "total_steps": 76960, "loss": 0.1831, "lr": 8.255393587486834e-06, "epoch": 15.205301455301456, "percentage": 76.03, "elapsed_time": "1:25:04", "remaining_time": "0:26:49", "throughput": 1032.07, "total_tokens": 5268560} {"current_steps": 58515, "total_steps": 76960, "loss": 0.2121, "lr": 8.251184025002006e-06, "epoch": 15.20660083160083, "percentage": 76.03, "elapsed_time": "1:25:05", "remaining_time": "0:26:49", "throughput": 1032.07, "total_tokens": 5268976} {"current_steps": 58520, "total_steps": 76960, "loss": 0.0217, "lr": 8.246975323924832e-06, "epoch": 15.207900207900208, "percentage": 76.04, "elapsed_time": "1:25:05", "remaining_time": "0:26:48", "throughput": 1032.07, "total_tokens": 5269408} {"current_steps": 58525, "total_steps": 76960, "loss": 0.0197, "lr": 8.242767484471773e-06, "epoch": 15.209199584199585, "percentage": 76.05, "elapsed_time": "1:25:06", "remaining_time": "0:26:48", "throughput": 1032.06, "total_tokens": 5269808} {"current_steps": 58530, "total_steps": 76960, "loss": 0.2097, "lr": 8.238560506859242e-06, "epoch": 15.21049896049896, "percentage": 76.05, "elapsed_time": "1:25:06", "remaining_time": "0:26:47", "throughput": 1032.06, "total_tokens": 5270240} {"current_steps": 58535, "total_steps": 76960, "loss": 0.5185, "lr": 8.234354391303605e-06, "epoch": 15.211798336798337, "percentage": 76.06, "elapsed_time": "1:25:06", "remaining_time": "0:26:47", "throughput": 1032.07, "total_tokens": 5270720} {"current_steps": 58540, "total_steps": 76960, "loss": 0.0913, "lr": 8.230149138021178e-06, "epoch": 15.213097713097714, "percentage": 76.07, "elapsed_time": "1:25:07", "remaining_time": "0:26:47", "throughput": 1032.08, "total_tokens": 5271184} {"current_steps": 58545, "total_steps": 76960, "loss": 0.0804, "lr": 8.225944747228257e-06, "epoch": 15.214397089397089, "percentage": 76.07, "elapsed_time": "1:25:07", "remaining_time": "0:26:46", "throughput": 1032.07, "total_tokens": 5271600} {"current_steps": 58550, "total_steps": 76960, "loss": 0.299, "lr": 8.22174121914106e-06, "epoch": 15.215696465696466, "percentage": 76.08, "elapsed_time": "1:25:08", "remaining_time": "0:26:46", "throughput": 1032.07, "total_tokens": 5272016} {"current_steps": 58555, "total_steps": 76960, "loss": 0.0932, "lr": 8.21753855397579e-06, "epoch": 15.216995841995843, "percentage": 76.08, "elapsed_time": "1:25:08", "remaining_time": "0:26:45", "throughput": 1032.07, "total_tokens": 5272464} {"current_steps": 58560, "total_steps": 76960, "loss": 0.1633, "lr": 8.213336751948595e-06, "epoch": 15.218295218295218, "percentage": 76.09, "elapsed_time": "1:25:09", "remaining_time": "0:26:45", "throughput": 1032.08, "total_tokens": 5272928} {"current_steps": 58565, "total_steps": 76960, "loss": 0.4308, "lr": 8.209135813275579e-06, "epoch": 15.219594594594595, "percentage": 76.1, "elapsed_time": "1:25:09", "remaining_time": "0:26:44", "throughput": 1032.08, "total_tokens": 5273376} {"current_steps": 58570, "total_steps": 76960, "loss": 0.4548, "lr": 8.204935738172789e-06, "epoch": 15.220893970893972, "percentage": 76.1, "elapsed_time": "1:25:09", "remaining_time": "0:26:44", "throughput": 1032.09, "total_tokens": 5273808} {"current_steps": 58575, "total_steps": 76960, "loss": 0.1463, "lr": 8.200736526856254e-06, "epoch": 15.222193347193347, "percentage": 76.11, "elapsed_time": "1:25:10", "remaining_time": "0:26:43", "throughput": 1032.1, "total_tokens": 5274288} {"current_steps": 58580, "total_steps": 76960, "loss": 0.2632, "lr": 8.196538179541929e-06, "epoch": 15.223492723492724, "percentage": 76.12, "elapsed_time": "1:25:10", "remaining_time": "0:26:43", "throughput": 1032.1, "total_tokens": 5274736} {"current_steps": 58585, "total_steps": 76960, "loss": 0.3313, "lr": 8.192340696445755e-06, "epoch": 15.2247920997921, "percentage": 76.12, "elapsed_time": "1:25:11", "remaining_time": "0:26:43", "throughput": 1032.1, "total_tokens": 5275184} {"current_steps": 58590, "total_steps": 76960, "loss": 0.3263, "lr": 8.18814407778359e-06, "epoch": 15.226091476091476, "percentage": 76.13, "elapsed_time": "1:25:11", "remaining_time": "0:26:42", "throughput": 1032.11, "total_tokens": 5275632} {"current_steps": 58595, "total_steps": 76960, "loss": 0.3286, "lr": 8.18394832377129e-06, "epoch": 15.227390852390853, "percentage": 76.14, "elapsed_time": "1:25:11", "remaining_time": "0:26:42", "throughput": 1032.12, "total_tokens": 5276112} {"current_steps": 58600, "total_steps": 76960, "loss": 0.0121, "lr": 8.179753434624642e-06, "epoch": 15.228690228690228, "percentage": 76.14, "elapsed_time": "1:25:12", "remaining_time": "0:26:41", "throughput": 1032.12, "total_tokens": 5276544} {"current_steps": 58605, "total_steps": 76960, "loss": 0.0132, "lr": 8.175559410559388e-06, "epoch": 15.229989604989605, "percentage": 76.15, "elapsed_time": "1:25:12", "remaining_time": "0:26:41", "throughput": 1032.12, "total_tokens": 5276992} {"current_steps": 58610, "total_steps": 76960, "loss": 0.0635, "lr": 8.17136625179124e-06, "epoch": 15.231288981288982, "percentage": 76.16, "elapsed_time": "1:25:13", "remaining_time": "0:26:40", "throughput": 1032.13, "total_tokens": 5277456} {"current_steps": 58615, "total_steps": 76960, "loss": 0.056, "lr": 8.167173958535842e-06, "epoch": 15.232588357588357, "percentage": 76.16, "elapsed_time": "1:25:13", "remaining_time": "0:26:40", "throughput": 1032.13, "total_tokens": 5277888} {"current_steps": 58620, "total_steps": 76960, "loss": 0.0241, "lr": 8.162982531008826e-06, "epoch": 15.233887733887734, "percentage": 76.17, "elapsed_time": "1:25:14", "remaining_time": "0:26:39", "throughput": 1032.15, "total_tokens": 5278416} {"current_steps": 58625, "total_steps": 76960, "loss": 0.1649, "lr": 8.158791969425738e-06, "epoch": 15.23518711018711, "percentage": 76.18, "elapsed_time": "1:25:14", "remaining_time": "0:26:39", "throughput": 1032.15, "total_tokens": 5278880} {"current_steps": 58630, "total_steps": 76960, "loss": 0.1238, "lr": 8.154602274002121e-06, "epoch": 15.236486486486486, "percentage": 76.18, "elapsed_time": "1:25:14", "remaining_time": "0:26:39", "throughput": 1032.16, "total_tokens": 5279344} {"current_steps": 58635, "total_steps": 76960, "loss": 0.0263, "lr": 8.150413444953447e-06, "epoch": 15.237785862785863, "percentage": 76.19, "elapsed_time": "1:25:15", "remaining_time": "0:26:38", "throughput": 1032.16, "total_tokens": 5279760} {"current_steps": 58640, "total_steps": 76960, "loss": 0.0704, "lr": 8.146225482495163e-06, "epoch": 15.23908523908524, "percentage": 76.2, "elapsed_time": "1:25:15", "remaining_time": "0:26:38", "throughput": 1032.16, "total_tokens": 5280192} {"current_steps": 58645, "total_steps": 76960, "loss": 0.3631, "lr": 8.14203838684264e-06, "epoch": 15.240384615384615, "percentage": 76.2, "elapsed_time": "1:25:16", "remaining_time": "0:26:37", "throughput": 1032.16, "total_tokens": 5280640} {"current_steps": 58650, "total_steps": 76960, "loss": 0.3011, "lr": 8.137852158211246e-06, "epoch": 15.241683991683992, "percentage": 76.21, "elapsed_time": "1:25:16", "remaining_time": "0:26:37", "throughput": 1032.16, "total_tokens": 5281072} {"current_steps": 58655, "total_steps": 76960, "loss": 0.2786, "lr": 8.133666796816264e-06, "epoch": 15.242983367983369, "percentage": 76.21, "elapsed_time": "1:25:16", "remaining_time": "0:26:36", "throughput": 1032.17, "total_tokens": 5281536} {"current_steps": 58660, "total_steps": 76960, "loss": 0.0543, "lr": 8.129482302872964e-06, "epoch": 15.244282744282744, "percentage": 76.22, "elapsed_time": "1:25:17", "remaining_time": "0:26:36", "throughput": 1032.18, "total_tokens": 5282016} {"current_steps": 58665, "total_steps": 76960, "loss": 0.1226, "lr": 8.125298676596548e-06, "epoch": 15.245582120582121, "percentage": 76.23, "elapsed_time": "1:25:17", "remaining_time": "0:26:35", "throughput": 1032.19, "total_tokens": 5282480} {"current_steps": 58670, "total_steps": 76960, "loss": 0.3489, "lr": 8.12111591820219e-06, "epoch": 15.246881496881496, "percentage": 76.23, "elapsed_time": "1:25:18", "remaining_time": "0:26:35", "throughput": 1032.19, "total_tokens": 5282928} {"current_steps": 58675, "total_steps": 76960, "loss": 0.1497, "lr": 8.116934027905021e-06, "epoch": 15.248180873180873, "percentage": 76.24, "elapsed_time": "1:25:18", "remaining_time": "0:26:35", "throughput": 1032.2, "total_tokens": 5283408} {"current_steps": 58680, "total_steps": 76960, "loss": 0.2471, "lr": 8.112753005920104e-06, "epoch": 15.24948024948025, "percentage": 76.25, "elapsed_time": "1:25:18", "remaining_time": "0:26:34", "throughput": 1032.2, "total_tokens": 5283840} {"current_steps": 58685, "total_steps": 76960, "loss": 0.2387, "lr": 8.108572852462487e-06, "epoch": 15.250779625779625, "percentage": 76.25, "elapsed_time": "1:25:19", "remaining_time": "0:26:34", "throughput": 1032.2, "total_tokens": 5284272} {"current_steps": 58690, "total_steps": 76960, "loss": 0.1359, "lr": 8.104393567747146e-06, "epoch": 15.252079002079002, "percentage": 76.26, "elapsed_time": "1:25:19", "remaining_time": "0:26:33", "throughput": 1032.21, "total_tokens": 5284720} {"current_steps": 58695, "total_steps": 76960, "loss": 0.0053, "lr": 8.100215151989032e-06, "epoch": 15.253378378378379, "percentage": 76.27, "elapsed_time": "1:25:20", "remaining_time": "0:26:33", "throughput": 1032.21, "total_tokens": 5285152} {"current_steps": 58700, "total_steps": 76960, "loss": 0.0845, "lr": 8.096037605403045e-06, "epoch": 15.254677754677754, "percentage": 76.27, "elapsed_time": "1:25:20", "remaining_time": "0:26:32", "throughput": 1032.21, "total_tokens": 5285584} {"current_steps": 58705, "total_steps": 76960, "loss": 0.2386, "lr": 8.091860928204049e-06, "epoch": 15.255977130977131, "percentage": 76.28, "elapsed_time": "1:25:21", "remaining_time": "0:26:32", "throughput": 1032.21, "total_tokens": 5286032} {"current_steps": 58710, "total_steps": 76960, "loss": 0.1192, "lr": 8.087685120606835e-06, "epoch": 15.257276507276508, "percentage": 76.29, "elapsed_time": "1:25:21", "remaining_time": "0:26:32", "throughput": 1032.22, "total_tokens": 5286480} {"current_steps": 58715, "total_steps": 76960, "loss": 0.2836, "lr": 8.083510182826192e-06, "epoch": 15.258575883575883, "percentage": 76.29, "elapsed_time": "1:25:21", "remaining_time": "0:26:31", "throughput": 1032.23, "total_tokens": 5286960} {"current_steps": 58720, "total_steps": 76960, "loss": 0.3334, "lr": 8.079336115076818e-06, "epoch": 15.25987525987526, "percentage": 76.3, "elapsed_time": "1:25:22", "remaining_time": "0:26:31", "throughput": 1032.23, "total_tokens": 5287408} {"current_steps": 58725, "total_steps": 76960, "loss": 0.1352, "lr": 8.075162917573412e-06, "epoch": 15.261174636174637, "percentage": 76.31, "elapsed_time": "1:25:22", "remaining_time": "0:26:30", "throughput": 1032.23, "total_tokens": 5287856} {"current_steps": 58730, "total_steps": 76960, "loss": 0.251, "lr": 8.070990590530583e-06, "epoch": 15.262474012474012, "percentage": 76.31, "elapsed_time": "1:25:23", "remaining_time": "0:26:30", "throughput": 1032.24, "total_tokens": 5288304} {"current_steps": 58735, "total_steps": 76960, "loss": 0.0206, "lr": 8.066819134162928e-06, "epoch": 15.263773388773389, "percentage": 76.32, "elapsed_time": "1:25:23", "remaining_time": "0:26:29", "throughput": 1032.23, "total_tokens": 5288720} {"current_steps": 58740, "total_steps": 76960, "loss": 0.3217, "lr": 8.062648548685e-06, "epoch": 15.265072765072764, "percentage": 76.33, "elapsed_time": "1:25:23", "remaining_time": "0:26:29", "throughput": 1032.24, "total_tokens": 5289184} {"current_steps": 58745, "total_steps": 76960, "loss": 0.6124, "lr": 8.058478834311275e-06, "epoch": 15.266372141372141, "percentage": 76.33, "elapsed_time": "1:25:24", "remaining_time": "0:26:28", "throughput": 1032.25, "total_tokens": 5289648} {"current_steps": 58750, "total_steps": 76960, "loss": 0.1711, "lr": 8.054309991256225e-06, "epoch": 15.267671517671518, "percentage": 76.34, "elapsed_time": "1:25:24", "remaining_time": "0:26:28", "throughput": 1032.24, "total_tokens": 5290064} {"current_steps": 58755, "total_steps": 76960, "loss": 0.0953, "lr": 8.05014201973424e-06, "epoch": 15.268970893970893, "percentage": 76.34, "elapsed_time": "1:25:25", "remaining_time": "0:26:28", "throughput": 1032.25, "total_tokens": 5290496} {"current_steps": 58760, "total_steps": 76960, "loss": 0.0564, "lr": 8.045974919959703e-06, "epoch": 15.27027027027027, "percentage": 76.35, "elapsed_time": "1:25:25", "remaining_time": "0:26:27", "throughput": 1032.25, "total_tokens": 5290960} {"current_steps": 58765, "total_steps": 76960, "loss": 0.222, "lr": 8.04180869214691e-06, "epoch": 15.271569646569647, "percentage": 76.36, "elapsed_time": "1:25:26", "remaining_time": "0:26:27", "throughput": 1032.27, "total_tokens": 5291472} {"current_steps": 58770, "total_steps": 76960, "loss": 0.0295, "lr": 8.037643336510145e-06, "epoch": 15.272869022869022, "percentage": 76.36, "elapsed_time": "1:25:26", "remaining_time": "0:26:26", "throughput": 1032.27, "total_tokens": 5291904} {"current_steps": 58775, "total_steps": 76960, "loss": 0.4509, "lr": 8.033478853263635e-06, "epoch": 15.2741683991684, "percentage": 76.37, "elapsed_time": "1:25:26", "remaining_time": "0:26:26", "throughput": 1032.28, "total_tokens": 5292368} {"current_steps": 58780, "total_steps": 76960, "loss": 0.0178, "lr": 8.029315242621572e-06, "epoch": 15.275467775467776, "percentage": 76.38, "elapsed_time": "1:25:27", "remaining_time": "0:26:25", "throughput": 1032.29, "total_tokens": 5292848} {"current_steps": 58785, "total_steps": 76960, "loss": 0.345, "lr": 8.025152504798078e-06, "epoch": 15.276767151767151, "percentage": 76.38, "elapsed_time": "1:25:27", "remaining_time": "0:26:25", "throughput": 1032.29, "total_tokens": 5293312} {"current_steps": 58790, "total_steps": 76960, "loss": 0.0728, "lr": 8.020990640007264e-06, "epoch": 15.278066528066528, "percentage": 76.39, "elapsed_time": "1:25:28", "remaining_time": "0:26:24", "throughput": 1032.3, "total_tokens": 5293760} {"current_steps": 58795, "total_steps": 76960, "loss": 0.0938, "lr": 8.016829648463173e-06, "epoch": 15.279365904365905, "percentage": 76.4, "elapsed_time": "1:25:28", "remaining_time": "0:26:24", "throughput": 1032.3, "total_tokens": 5294208} {"current_steps": 58800, "total_steps": 76960, "loss": 0.0891, "lr": 8.012669530379794e-06, "epoch": 15.28066528066528, "percentage": 76.4, "elapsed_time": "1:25:28", "remaining_time": "0:26:24", "throughput": 1032.3, "total_tokens": 5294640} {"current_steps": 58805, "total_steps": 76960, "loss": 0.096, "lr": 8.008510285971097e-06, "epoch": 15.281964656964657, "percentage": 76.41, "elapsed_time": "1:25:29", "remaining_time": "0:26:23", "throughput": 1032.3, "total_tokens": 5295072} {"current_steps": 58810, "total_steps": 76960, "loss": 0.3655, "lr": 8.004351915450997e-06, "epoch": 15.283264033264032, "percentage": 76.42, "elapsed_time": "1:25:29", "remaining_time": "0:26:23", "throughput": 1032.31, "total_tokens": 5295536} {"current_steps": 58815, "total_steps": 76960, "loss": 0.285, "lr": 8.00019441903337e-06, "epoch": 15.28456340956341, "percentage": 76.42, "elapsed_time": "1:25:30", "remaining_time": "0:26:22", "throughput": 1032.32, "total_tokens": 5296000} {"current_steps": 58820, "total_steps": 76960, "loss": 0.0316, "lr": 7.996037796932026e-06, "epoch": 15.285862785862786, "percentage": 76.43, "elapsed_time": "1:25:30", "remaining_time": "0:26:22", "throughput": 1032.32, "total_tokens": 5296448} {"current_steps": 58825, "total_steps": 76960, "loss": 0.0063, "lr": 7.99188204936076e-06, "epoch": 15.287162162162161, "percentage": 76.44, "elapsed_time": "1:25:31", "remaining_time": "0:26:21", "throughput": 1032.34, "total_tokens": 5296960} {"current_steps": 58830, "total_steps": 76960, "loss": 0.1938, "lr": 7.987727176533286e-06, "epoch": 15.288461538461538, "percentage": 76.44, "elapsed_time": "1:25:31", "remaining_time": "0:26:21", "throughput": 1032.34, "total_tokens": 5297392} {"current_steps": 58835, "total_steps": 76960, "loss": 0.0082, "lr": 7.983573178663315e-06, "epoch": 15.289760914760915, "percentage": 76.45, "elapsed_time": "1:25:31", "remaining_time": "0:26:20", "throughput": 1032.35, "total_tokens": 5297872} {"current_steps": 58840, "total_steps": 76960, "loss": 0.3721, "lr": 7.979420055964468e-06, "epoch": 15.29106029106029, "percentage": 76.46, "elapsed_time": "1:25:32", "remaining_time": "0:26:20", "throughput": 1032.35, "total_tokens": 5298304} {"current_steps": 58845, "total_steps": 76960, "loss": 0.2544, "lr": 7.975267808650355e-06, "epoch": 15.292359667359667, "percentage": 76.46, "elapsed_time": "1:25:32", "remaining_time": "0:26:20", "throughput": 1032.35, "total_tokens": 5298768} {"current_steps": 58850, "total_steps": 76960, "loss": 0.3302, "lr": 7.971116436934534e-06, "epoch": 15.293659043659044, "percentage": 76.47, "elapsed_time": "1:25:33", "remaining_time": "0:26:19", "throughput": 1032.36, "total_tokens": 5299232} {"current_steps": 58855, "total_steps": 76960, "loss": 0.0538, "lr": 7.966965941030519e-06, "epoch": 15.29495841995842, "percentage": 76.47, "elapsed_time": "1:25:33", "remaining_time": "0:26:19", "throughput": 1032.37, "total_tokens": 5299712} {"current_steps": 58860, "total_steps": 76960, "loss": 0.15, "lr": 7.962816321151756e-06, "epoch": 15.296257796257796, "percentage": 76.48, "elapsed_time": "1:25:33", "remaining_time": "0:26:18", "throughput": 1032.38, "total_tokens": 5300160} {"current_steps": 58865, "total_steps": 76960, "loss": 0.0156, "lr": 7.958667577511683e-06, "epoch": 15.297557172557173, "percentage": 76.49, "elapsed_time": "1:25:34", "remaining_time": "0:26:18", "throughput": 1032.38, "total_tokens": 5300608} {"current_steps": 58870, "total_steps": 76960, "loss": 0.1875, "lr": 7.954519710323663e-06, "epoch": 15.298856548856548, "percentage": 76.49, "elapsed_time": "1:25:34", "remaining_time": "0:26:17", "throughput": 1032.38, "total_tokens": 5301040} {"current_steps": 58875, "total_steps": 76960, "loss": 0.0221, "lr": 7.950372719801022e-06, "epoch": 15.300155925155925, "percentage": 76.5, "elapsed_time": "1:25:35", "remaining_time": "0:26:17", "throughput": 1032.38, "total_tokens": 5301488} {"current_steps": 58880, "total_steps": 76960, "loss": 0.2094, "lr": 7.946226606157045e-06, "epoch": 15.301455301455302, "percentage": 76.51, "elapsed_time": "1:25:35", "remaining_time": "0:26:16", "throughput": 1032.39, "total_tokens": 5301936} {"current_steps": 58885, "total_steps": 76960, "loss": 0.0641, "lr": 7.942081369604976e-06, "epoch": 15.302754677754677, "percentage": 76.51, "elapsed_time": "1:25:36", "remaining_time": "0:26:16", "throughput": 1032.4, "total_tokens": 5302448} {"current_steps": 58890, "total_steps": 76960, "loss": 0.1726, "lr": 7.937937010358012e-06, "epoch": 15.304054054054054, "percentage": 76.52, "elapsed_time": "1:25:36", "remaining_time": "0:26:16", "throughput": 1032.41, "total_tokens": 5302896} {"current_steps": 58895, "total_steps": 76960, "loss": 0.3349, "lr": 7.933793528629287e-06, "epoch": 15.30535343035343, "percentage": 76.53, "elapsed_time": "1:25:36", "remaining_time": "0:26:15", "throughput": 1032.41, "total_tokens": 5303344} {"current_steps": 58900, "total_steps": 76960, "loss": 0.2737, "lr": 7.929650924631924e-06, "epoch": 15.306652806652806, "percentage": 76.53, "elapsed_time": "1:25:37", "remaining_time": "0:26:15", "throughput": 1032.41, "total_tokens": 5303776} {"current_steps": 58905, "total_steps": 76960, "loss": 0.1025, "lr": 7.92550919857896e-06, "epoch": 15.307952182952183, "percentage": 76.54, "elapsed_time": "1:25:37", "remaining_time": "0:26:14", "throughput": 1032.41, "total_tokens": 5304208} {"current_steps": 58910, "total_steps": 76960, "loss": 0.1947, "lr": 7.921368350683428e-06, "epoch": 15.309251559251559, "percentage": 76.55, "elapsed_time": "1:25:38", "remaining_time": "0:26:14", "throughput": 1032.41, "total_tokens": 5304624} {"current_steps": 58915, "total_steps": 76960, "loss": 0.2584, "lr": 7.917228381158268e-06, "epoch": 15.310550935550935, "percentage": 76.55, "elapsed_time": "1:25:38", "remaining_time": "0:26:13", "throughput": 1032.42, "total_tokens": 5305104} {"current_steps": 58920, "total_steps": 76960, "loss": 0.2472, "lr": 7.913089290216436e-06, "epoch": 15.311850311850312, "percentage": 76.56, "elapsed_time": "1:25:38", "remaining_time": "0:26:13", "throughput": 1032.42, "total_tokens": 5305552} {"current_steps": 58925, "total_steps": 76960, "loss": 0.0915, "lr": 7.908951078070787e-06, "epoch": 15.313149688149688, "percentage": 76.57, "elapsed_time": "1:25:39", "remaining_time": "0:26:12", "throughput": 1032.42, "total_tokens": 5305984} {"current_steps": 58930, "total_steps": 76960, "loss": 0.1444, "lr": 7.904813744934164e-06, "epoch": 15.314449064449065, "percentage": 76.57, "elapsed_time": "1:25:39", "remaining_time": "0:26:12", "throughput": 1032.43, "total_tokens": 5306416} {"current_steps": 58935, "total_steps": 76960, "loss": 0.1777, "lr": 7.900677291019354e-06, "epoch": 15.315748440748441, "percentage": 76.58, "elapsed_time": "1:25:40", "remaining_time": "0:26:12", "throughput": 1032.43, "total_tokens": 5306848} {"current_steps": 58940, "total_steps": 76960, "loss": 0.3291, "lr": 7.896541716539085e-06, "epoch": 15.317047817047817, "percentage": 76.59, "elapsed_time": "1:25:40", "remaining_time": "0:26:11", "throughput": 1032.43, "total_tokens": 5307280} {"current_steps": 58945, "total_steps": 76960, "loss": 0.2962, "lr": 7.892407021706063e-06, "epoch": 15.318347193347194, "percentage": 76.59, "elapsed_time": "1:25:41", "remaining_time": "0:26:11", "throughput": 1032.44, "total_tokens": 5307776} {"current_steps": 58950, "total_steps": 76960, "loss": 0.0668, "lr": 7.888273206732943e-06, "epoch": 15.31964656964657, "percentage": 76.6, "elapsed_time": "1:25:41", "remaining_time": "0:26:10", "throughput": 1032.45, "total_tokens": 5308240} {"current_steps": 58955, "total_steps": 76960, "loss": 0.0363, "lr": 7.884140271832333e-06, "epoch": 15.320945945945946, "percentage": 76.6, "elapsed_time": "1:25:41", "remaining_time": "0:26:10", "throughput": 1032.45, "total_tokens": 5308688} {"current_steps": 58960, "total_steps": 76960, "loss": 0.3493, "lr": 7.88000821721678e-06, "epoch": 15.322245322245323, "percentage": 76.61, "elapsed_time": "1:25:42", "remaining_time": "0:26:09", "throughput": 1032.47, "total_tokens": 5309200} {"current_steps": 58965, "total_steps": 76960, "loss": 0.032, "lr": 7.875877043098818e-06, "epoch": 15.323544698544698, "percentage": 76.62, "elapsed_time": "1:25:42", "remaining_time": "0:26:09", "throughput": 1032.47, "total_tokens": 5309632} {"current_steps": 58970, "total_steps": 76960, "loss": 0.144, "lr": 7.871746749690898e-06, "epoch": 15.324844074844075, "percentage": 76.62, "elapsed_time": "1:25:43", "remaining_time": "0:26:09", "throughput": 1032.47, "total_tokens": 5310080} {"current_steps": 58975, "total_steps": 76960, "loss": 0.0804, "lr": 7.86761733720546e-06, "epoch": 15.326143451143452, "percentage": 76.63, "elapsed_time": "1:25:43", "remaining_time": "0:26:08", "throughput": 1032.47, "total_tokens": 5310528} {"current_steps": 58980, "total_steps": 76960, "loss": 0.2184, "lr": 7.863488805854872e-06, "epoch": 15.327442827442827, "percentage": 76.64, "elapsed_time": "1:25:43", "remaining_time": "0:26:08", "throughput": 1032.48, "total_tokens": 5310992} {"current_steps": 58985, "total_steps": 76960, "loss": 0.1599, "lr": 7.859361155851475e-06, "epoch": 15.328742203742204, "percentage": 76.64, "elapsed_time": "1:25:44", "remaining_time": "0:26:07", "throughput": 1032.48, "total_tokens": 5311440} {"current_steps": 58990, "total_steps": 76960, "loss": 0.2218, "lr": 7.855234387407554e-06, "epoch": 15.33004158004158, "percentage": 76.65, "elapsed_time": "1:25:44", "remaining_time": "0:26:07", "throughput": 1032.49, "total_tokens": 5311888} {"current_steps": 58995, "total_steps": 76960, "loss": 0.3278, "lr": 7.851108500735365e-06, "epoch": 15.331340956340956, "percentage": 76.66, "elapsed_time": "1:25:45", "remaining_time": "0:26:06", "throughput": 1032.49, "total_tokens": 5312320} {"current_steps": 59000, "total_steps": 76960, "loss": 0.0059, "lr": 7.8469834960471e-06, "epoch": 15.332640332640333, "percentage": 76.66, "elapsed_time": "1:25:45", "remaining_time": "0:26:06", "throughput": 1032.5, "total_tokens": 5312800} {"current_steps": 59005, "total_steps": 76960, "loss": 0.0574, "lr": 7.842859373554898e-06, "epoch": 15.33393970893971, "percentage": 76.67, "elapsed_time": "1:25:45", "remaining_time": "0:26:05", "throughput": 1032.5, "total_tokens": 5313232} {"current_steps": 59010, "total_steps": 76960, "loss": 0.3267, "lr": 7.838736133470886e-06, "epoch": 15.335239085239085, "percentage": 76.68, "elapsed_time": "1:25:46", "remaining_time": "0:26:05", "throughput": 1032.51, "total_tokens": 5313696} {"current_steps": 59015, "total_steps": 76960, "loss": 0.079, "lr": 7.83461377600711e-06, "epoch": 15.336538461538462, "percentage": 76.68, "elapsed_time": "1:25:46", "remaining_time": "0:26:05", "throughput": 1032.51, "total_tokens": 5314128} {"current_steps": 59020, "total_steps": 76960, "loss": 0.1634, "lr": 7.830492301375597e-06, "epoch": 15.337837837837839, "percentage": 76.69, "elapsed_time": "1:25:47", "remaining_time": "0:26:04", "throughput": 1032.51, "total_tokens": 5314592} {"current_steps": 59025, "total_steps": 76960, "loss": 0.0572, "lr": 7.826371709788313e-06, "epoch": 15.339137214137214, "percentage": 76.7, "elapsed_time": "1:25:47", "remaining_time": "0:26:04", "throughput": 1032.52, "total_tokens": 5315040} {"current_steps": 59030, "total_steps": 76960, "loss": 0.5196, "lr": 7.822252001457195e-06, "epoch": 15.34043659043659, "percentage": 76.7, "elapsed_time": "1:25:48", "remaining_time": "0:26:03", "throughput": 1032.52, "total_tokens": 5315472} {"current_steps": 59035, "total_steps": 76960, "loss": 0.3889, "lr": 7.818133176594109e-06, "epoch": 15.341735966735968, "percentage": 76.71, "elapsed_time": "1:25:48", "remaining_time": "0:26:03", "throughput": 1032.52, "total_tokens": 5315936} {"current_steps": 59040, "total_steps": 76960, "loss": 0.7989, "lr": 7.814015235410905e-06, "epoch": 15.343035343035343, "percentage": 76.72, "elapsed_time": "1:25:48", "remaining_time": "0:26:02", "throughput": 1032.54, "total_tokens": 5316448} {"current_steps": 59045, "total_steps": 76960, "loss": 0.3395, "lr": 7.809898178119354e-06, "epoch": 15.34433471933472, "percentage": 76.72, "elapsed_time": "1:25:49", "remaining_time": "0:26:02", "throughput": 1032.54, "total_tokens": 5316896} {"current_steps": 59050, "total_steps": 76960, "loss": 0.3282, "lr": 7.805782004931219e-06, "epoch": 15.345634095634095, "percentage": 76.73, "elapsed_time": "1:25:49", "remaining_time": "0:26:01", "throughput": 1032.56, "total_tokens": 5317392} {"current_steps": 59055, "total_steps": 76960, "loss": 0.1832, "lr": 7.801666716058185e-06, "epoch": 15.346933471933472, "percentage": 76.73, "elapsed_time": "1:25:50", "remaining_time": "0:26:01", "throughput": 1032.57, "total_tokens": 5317872} {"current_steps": 59060, "total_steps": 76960, "loss": 0.104, "lr": 7.797552311711906e-06, "epoch": 15.348232848232849, "percentage": 76.74, "elapsed_time": "1:25:50", "remaining_time": "0:26:01", "throughput": 1032.58, "total_tokens": 5318368} {"current_steps": 59065, "total_steps": 76960, "loss": 0.024, "lr": 7.793438792104005e-06, "epoch": 15.349532224532224, "percentage": 76.75, "elapsed_time": "1:25:50", "remaining_time": "0:26:00", "throughput": 1032.58, "total_tokens": 5318816} {"current_steps": 59070, "total_steps": 76960, "loss": 0.1074, "lr": 7.789326157446025e-06, "epoch": 15.3508316008316, "percentage": 76.75, "elapsed_time": "1:25:51", "remaining_time": "0:26:00", "throughput": 1032.58, "total_tokens": 5319232} {"current_steps": 59075, "total_steps": 76960, "loss": 0.0279, "lr": 7.785214407949498e-06, "epoch": 15.352130977130978, "percentage": 76.76, "elapsed_time": "1:25:51", "remaining_time": "0:25:59", "throughput": 1032.58, "total_tokens": 5319648} {"current_steps": 59080, "total_steps": 76960, "loss": 0.0101, "lr": 7.781103543825881e-06, "epoch": 15.353430353430353, "percentage": 76.77, "elapsed_time": "1:25:52", "remaining_time": "0:25:59", "throughput": 1032.58, "total_tokens": 5320064} {"current_steps": 59085, "total_steps": 76960, "loss": 0.1295, "lr": 7.776993565286617e-06, "epoch": 15.35472972972973, "percentage": 76.77, "elapsed_time": "1:25:52", "remaining_time": "0:25:58", "throughput": 1032.58, "total_tokens": 5320512} {"current_steps": 59090, "total_steps": 76960, "loss": 0.4173, "lr": 7.772884472543065e-06, "epoch": 15.356029106029107, "percentage": 76.78, "elapsed_time": "1:25:53", "remaining_time": "0:25:58", "throughput": 1032.59, "total_tokens": 5320976} {"current_steps": 59095, "total_steps": 76960, "loss": 0.103, "lr": 7.768776265806574e-06, "epoch": 15.357328482328482, "percentage": 76.79, "elapsed_time": "1:25:53", "remaining_time": "0:25:57", "throughput": 1032.59, "total_tokens": 5321424} {"current_steps": 59100, "total_steps": 76960, "loss": 0.3236, "lr": 7.764668945288428e-06, "epoch": 15.358627858627859, "percentage": 76.79, "elapsed_time": "1:25:53", "remaining_time": "0:25:57", "throughput": 1032.59, "total_tokens": 5321856} {"current_steps": 59105, "total_steps": 76960, "loss": 0.194, "lr": 7.760562511199882e-06, "epoch": 15.359927234927236, "percentage": 76.8, "elapsed_time": "1:25:54", "remaining_time": "0:25:57", "throughput": 1032.59, "total_tokens": 5322288} {"current_steps": 59110, "total_steps": 76960, "loss": 0.1027, "lr": 7.756456963752113e-06, "epoch": 15.361226611226611, "percentage": 76.81, "elapsed_time": "1:25:54", "remaining_time": "0:25:56", "throughput": 1032.59, "total_tokens": 5322736} {"current_steps": 59115, "total_steps": 76960, "loss": 0.1777, "lr": 7.752352303156293e-06, "epoch": 15.362525987525988, "percentage": 76.81, "elapsed_time": "1:25:55", "remaining_time": "0:25:56", "throughput": 1032.6, "total_tokens": 5323184} {"current_steps": 59120, "total_steps": 76960, "loss": 0.3531, "lr": 7.748248529623514e-06, "epoch": 15.363825363825363, "percentage": 76.82, "elapsed_time": "1:25:55", "remaining_time": "0:25:55", "throughput": 1032.6, "total_tokens": 5323600} {"current_steps": 59125, "total_steps": 76960, "loss": 0.0998, "lr": 7.74414564336485e-06, "epoch": 15.36512474012474, "percentage": 76.83, "elapsed_time": "1:25:55", "remaining_time": "0:25:55", "throughput": 1032.61, "total_tokens": 5324080} {"current_steps": 59130, "total_steps": 76960, "loss": 0.4085, "lr": 7.740043644591302e-06, "epoch": 15.366424116424117, "percentage": 76.83, "elapsed_time": "1:25:56", "remaining_time": "0:25:54", "throughput": 1032.61, "total_tokens": 5324544} {"current_steps": 59135, "total_steps": 76960, "loss": 0.0961, "lr": 7.735942533513846e-06, "epoch": 15.367723492723492, "percentage": 76.84, "elapsed_time": "1:25:56", "remaining_time": "0:25:54", "throughput": 1032.62, "total_tokens": 5325024} {"current_steps": 59140, "total_steps": 76960, "loss": 0.0336, "lr": 7.731842310343415e-06, "epoch": 15.369022869022869, "percentage": 76.85, "elapsed_time": "1:25:57", "remaining_time": "0:25:53", "throughput": 1032.63, "total_tokens": 5325472} {"current_steps": 59145, "total_steps": 76960, "loss": 0.1819, "lr": 7.727742975290871e-06, "epoch": 15.370322245322246, "percentage": 76.85, "elapsed_time": "1:25:57", "remaining_time": "0:25:53", "throughput": 1032.63, "total_tokens": 5325936} {"current_steps": 59150, "total_steps": 76960, "loss": 0.0037, "lr": 7.723644528567064e-06, "epoch": 15.371621621621621, "percentage": 76.86, "elapsed_time": "1:25:58", "remaining_time": "0:25:53", "throughput": 1032.64, "total_tokens": 5326384} {"current_steps": 59155, "total_steps": 76960, "loss": 0.0894, "lr": 7.719546970382766e-06, "epoch": 15.372920997920998, "percentage": 76.86, "elapsed_time": "1:25:58", "remaining_time": "0:25:52", "throughput": 1032.63, "total_tokens": 5326800} {"current_steps": 59160, "total_steps": 76960, "loss": 0.5277, "lr": 7.715450300948732e-06, "epoch": 15.374220374220375, "percentage": 76.87, "elapsed_time": "1:25:58", "remaining_time": "0:25:52", "throughput": 1032.63, "total_tokens": 5327232} {"current_steps": 59165, "total_steps": 76960, "loss": 0.2478, "lr": 7.711354520475633e-06, "epoch": 15.37551975051975, "percentage": 76.88, "elapsed_time": "1:25:59", "remaining_time": "0:25:51", "throughput": 1032.63, "total_tokens": 5327664} {"current_steps": 59170, "total_steps": 76960, "loss": 0.1397, "lr": 7.707259629174152e-06, "epoch": 15.376819126819127, "percentage": 76.88, "elapsed_time": "1:25:59", "remaining_time": "0:25:51", "throughput": 1032.64, "total_tokens": 5328128} {"current_steps": 59175, "total_steps": 76960, "loss": 0.1292, "lr": 7.703165627254869e-06, "epoch": 15.378118503118504, "percentage": 76.89, "elapsed_time": "1:26:00", "remaining_time": "0:25:50", "throughput": 1032.64, "total_tokens": 5328576} {"current_steps": 59180, "total_steps": 76960, "loss": 0.0065, "lr": 7.69907251492836e-06, "epoch": 15.379417879417879, "percentage": 76.9, "elapsed_time": "1:26:00", "remaining_time": "0:25:50", "throughput": 1032.65, "total_tokens": 5329056} {"current_steps": 59185, "total_steps": 76960, "loss": 0.5131, "lr": 7.694980292405122e-06, "epoch": 15.380717255717256, "percentage": 76.9, "elapsed_time": "1:26:00", "remaining_time": "0:25:49", "throughput": 1032.66, "total_tokens": 5329504} {"current_steps": 59190, "total_steps": 76960, "loss": 0.3909, "lr": 7.690888959895634e-06, "epoch": 15.382016632016631, "percentage": 76.91, "elapsed_time": "1:26:01", "remaining_time": "0:25:49", "throughput": 1032.66, "total_tokens": 5329952} {"current_steps": 59195, "total_steps": 76960, "loss": 0.0557, "lr": 7.686798517610304e-06, "epoch": 15.383316008316008, "percentage": 76.92, "elapsed_time": "1:26:01", "remaining_time": "0:25:49", "throughput": 1032.66, "total_tokens": 5330400} {"current_steps": 59200, "total_steps": 76960, "loss": 0.2147, "lr": 7.682708965759516e-06, "epoch": 15.384615384615385, "percentage": 76.92, "elapsed_time": "1:26:02", "remaining_time": "0:25:48", "throughput": 1032.66, "total_tokens": 5330832} {"current_steps": 59205, "total_steps": 76960, "loss": 0.0562, "lr": 7.678620304553604e-06, "epoch": 15.38591476091476, "percentage": 76.93, "elapsed_time": "1:26:02", "remaining_time": "0:25:48", "throughput": 1032.66, "total_tokens": 5331264} {"current_steps": 59210, "total_steps": 76960, "loss": 0.4563, "lr": 7.674532534202841e-06, "epoch": 15.387214137214137, "percentage": 76.94, "elapsed_time": "1:26:03", "remaining_time": "0:25:47", "throughput": 1032.67, "total_tokens": 5331712} {"current_steps": 59215, "total_steps": 76960, "loss": 0.1182, "lr": 7.670445654917477e-06, "epoch": 15.388513513513514, "percentage": 76.94, "elapsed_time": "1:26:03", "remaining_time": "0:25:47", "throughput": 1032.67, "total_tokens": 5332160} {"current_steps": 59220, "total_steps": 76960, "loss": 0.394, "lr": 7.66635966690769e-06, "epoch": 15.38981288981289, "percentage": 76.95, "elapsed_time": "1:26:03", "remaining_time": "0:25:46", "throughput": 1032.67, "total_tokens": 5332608} {"current_steps": 59225, "total_steps": 76960, "loss": 0.255, "lr": 7.66227457038364e-06, "epoch": 15.391112266112266, "percentage": 76.96, "elapsed_time": "1:26:04", "remaining_time": "0:25:46", "throughput": 1032.68, "total_tokens": 5333056} {"current_steps": 59230, "total_steps": 76960, "loss": 0.0213, "lr": 7.658190365555415e-06, "epoch": 15.392411642411643, "percentage": 76.96, "elapsed_time": "1:26:04", "remaining_time": "0:25:46", "throughput": 1032.68, "total_tokens": 5333488} {"current_steps": 59235, "total_steps": 76960, "loss": 0.225, "lr": 7.654107052633075e-06, "epoch": 15.393711018711018, "percentage": 76.97, "elapsed_time": "1:26:05", "remaining_time": "0:25:45", "throughput": 1032.68, "total_tokens": 5333920} {"current_steps": 59240, "total_steps": 76960, "loss": 0.1993, "lr": 7.65002463182663e-06, "epoch": 15.395010395010395, "percentage": 76.98, "elapsed_time": "1:26:05", "remaining_time": "0:25:45", "throughput": 1032.68, "total_tokens": 5334352} {"current_steps": 59245, "total_steps": 76960, "loss": 0.0045, "lr": 7.645943103346048e-06, "epoch": 15.396309771309772, "percentage": 76.98, "elapsed_time": "1:26:05", "remaining_time": "0:25:44", "throughput": 1032.68, "total_tokens": 5334784} {"current_steps": 59250, "total_steps": 76960, "loss": 0.0634, "lr": 7.641862467401234e-06, "epoch": 15.397609147609147, "percentage": 76.99, "elapsed_time": "1:26:06", "remaining_time": "0:25:44", "throughput": 1032.69, "total_tokens": 5335248} {"current_steps": 59255, "total_steps": 76960, "loss": 0.4031, "lr": 7.637782724202073e-06, "epoch": 15.398908523908524, "percentage": 76.99, "elapsed_time": "1:26:06", "remaining_time": "0:25:43", "throughput": 1032.69, "total_tokens": 5335680} {"current_steps": 59260, "total_steps": 76960, "loss": 0.3599, "lr": 7.63370387395838e-06, "epoch": 15.4002079002079, "percentage": 77.0, "elapsed_time": "1:26:07", "remaining_time": "0:25:43", "throughput": 1032.69, "total_tokens": 5336128} {"current_steps": 59265, "total_steps": 76960, "loss": 0.2858, "lr": 7.629625916879932e-06, "epoch": 15.401507276507276, "percentage": 77.01, "elapsed_time": "1:26:07", "remaining_time": "0:25:42", "throughput": 1032.7, "total_tokens": 5336576} {"current_steps": 59270, "total_steps": 76960, "loss": 0.1563, "lr": 7.625548853176464e-06, "epoch": 15.402806652806653, "percentage": 77.01, "elapsed_time": "1:26:08", "remaining_time": "0:25:42", "throughput": 1032.7, "total_tokens": 5337040} {"current_steps": 59275, "total_steps": 76960, "loss": 0.0348, "lr": 7.621472683057668e-06, "epoch": 15.404106029106028, "percentage": 77.02, "elapsed_time": "1:26:08", "remaining_time": "0:25:42", "throughput": 1032.71, "total_tokens": 5337488} {"current_steps": 59280, "total_steps": 76960, "loss": 0.24, "lr": 7.61739740673319e-06, "epoch": 15.405405405405405, "percentage": 77.03, "elapsed_time": "1:26:08", "remaining_time": "0:25:41", "throughput": 1032.72, "total_tokens": 5337968} {"current_steps": 59285, "total_steps": 76960, "loss": 0.1575, "lr": 7.613323024412608e-06, "epoch": 15.406704781704782, "percentage": 77.03, "elapsed_time": "1:26:09", "remaining_time": "0:25:41", "throughput": 1032.73, "total_tokens": 5338448} {"current_steps": 59290, "total_steps": 76960, "loss": 0.4993, "lr": 7.6092495363054935e-06, "epoch": 15.408004158004157, "percentage": 77.04, "elapsed_time": "1:26:09", "remaining_time": "0:25:40", "throughput": 1032.73, "total_tokens": 5338912} {"current_steps": 59295, "total_steps": 76960, "loss": 0.2333, "lr": 7.605176942621328e-06, "epoch": 15.409303534303534, "percentage": 77.05, "elapsed_time": "1:26:10", "remaining_time": "0:25:40", "throughput": 1032.74, "total_tokens": 5339376} {"current_steps": 59300, "total_steps": 76960, "loss": 0.3877, "lr": 7.6011052435695894e-06, "epoch": 15.410602910602911, "percentage": 77.05, "elapsed_time": "1:26:10", "remaining_time": "0:25:39", "throughput": 1032.75, "total_tokens": 5339840} {"current_steps": 59305, "total_steps": 76960, "loss": 0.047, "lr": 7.597034439359671e-06, "epoch": 15.411902286902286, "percentage": 77.06, "elapsed_time": "1:26:10", "remaining_time": "0:25:39", "throughput": 1032.75, "total_tokens": 5340304} {"current_steps": 59310, "total_steps": 76960, "loss": 0.7074, "lr": 7.592964530200944e-06, "epoch": 15.413201663201663, "percentage": 77.07, "elapsed_time": "1:26:11", "remaining_time": "0:25:38", "throughput": 1032.76, "total_tokens": 5340752} {"current_steps": 59315, "total_steps": 76960, "loss": 0.0574, "lr": 7.58889551630273e-06, "epoch": 15.41450103950104, "percentage": 77.07, "elapsed_time": "1:26:11", "remaining_time": "0:25:38", "throughput": 1032.77, "total_tokens": 5341232} {"current_steps": 59320, "total_steps": 76960, "loss": 0.0324, "lr": 7.584827397874312e-06, "epoch": 15.415800415800415, "percentage": 77.08, "elapsed_time": "1:26:12", "remaining_time": "0:25:38", "throughput": 1032.77, "total_tokens": 5341696} {"current_steps": 59325, "total_steps": 76960, "loss": 0.4524, "lr": 7.580760175124907e-06, "epoch": 15.417099792099792, "percentage": 77.09, "elapsed_time": "1:26:12", "remaining_time": "0:25:37", "throughput": 1032.78, "total_tokens": 5342160} {"current_steps": 59330, "total_steps": 76960, "loss": 0.4458, "lr": 7.576693848263686e-06, "epoch": 15.41839916839917, "percentage": 77.09, "elapsed_time": "1:26:13", "remaining_time": "0:25:37", "throughput": 1032.79, "total_tokens": 5342624} {"current_steps": 59335, "total_steps": 76960, "loss": 0.2364, "lr": 7.5726284174998055e-06, "epoch": 15.419698544698544, "percentage": 77.1, "elapsed_time": "1:26:13", "remaining_time": "0:25:36", "throughput": 1032.79, "total_tokens": 5343072} {"current_steps": 59340, "total_steps": 76960, "loss": 0.0093, "lr": 7.568563883042334e-06, "epoch": 15.420997920997921, "percentage": 77.1, "elapsed_time": "1:26:13", "remaining_time": "0:25:36", "throughput": 1032.79, "total_tokens": 5343488} {"current_steps": 59345, "total_steps": 76960, "loss": 0.1557, "lr": 7.564500245100325e-06, "epoch": 15.422297297297296, "percentage": 77.11, "elapsed_time": "1:26:14", "remaining_time": "0:25:35", "throughput": 1032.78, "total_tokens": 5343904} {"current_steps": 59350, "total_steps": 76960, "loss": 0.0768, "lr": 7.5604375038827725e-06, "epoch": 15.423596673596673, "percentage": 77.12, "elapsed_time": "1:26:14", "remaining_time": "0:25:35", "throughput": 1032.79, "total_tokens": 5344352} {"current_steps": 59355, "total_steps": 76960, "loss": 0.061, "lr": 7.556375659598638e-06, "epoch": 15.42489604989605, "percentage": 77.12, "elapsed_time": "1:26:15", "remaining_time": "0:25:34", "throughput": 1032.8, "total_tokens": 5344864} {"current_steps": 59360, "total_steps": 76960, "loss": 0.2177, "lr": 7.55231471245681e-06, "epoch": 15.426195426195425, "percentage": 77.13, "elapsed_time": "1:26:15", "remaining_time": "0:25:34", "throughput": 1032.81, "total_tokens": 5345312} {"current_steps": 59365, "total_steps": 76960, "loss": 0.0942, "lr": 7.548254662666163e-06, "epoch": 15.427494802494802, "percentage": 77.14, "elapsed_time": "1:26:15", "remaining_time": "0:25:34", "throughput": 1032.81, "total_tokens": 5345760} {"current_steps": 59370, "total_steps": 76960, "loss": 0.004, "lr": 7.54419551043549e-06, "epoch": 15.42879417879418, "percentage": 77.14, "elapsed_time": "1:26:16", "remaining_time": "0:25:33", "throughput": 1032.81, "total_tokens": 5346208} {"current_steps": 59375, "total_steps": 76960, "loss": 0.4131, "lr": 7.540137255973576e-06, "epoch": 15.430093555093555, "percentage": 77.15, "elapsed_time": "1:26:16", "remaining_time": "0:25:33", "throughput": 1032.82, "total_tokens": 5346656} {"current_steps": 59380, "total_steps": 76960, "loss": 0.1917, "lr": 7.536079899489121e-06, "epoch": 15.431392931392931, "percentage": 77.16, "elapsed_time": "1:26:17", "remaining_time": "0:25:32", "throughput": 1032.82, "total_tokens": 5347120} {"current_steps": 59385, "total_steps": 76960, "loss": 0.0656, "lr": 7.5320234411908135e-06, "epoch": 15.432692307692308, "percentage": 77.16, "elapsed_time": "1:26:17", "remaining_time": "0:25:32", "throughput": 1032.83, "total_tokens": 5347600} {"current_steps": 59390, "total_steps": 76960, "loss": 0.2473, "lr": 7.527967881287284e-06, "epoch": 15.433991683991684, "percentage": 77.17, "elapsed_time": "1:26:18", "remaining_time": "0:25:31", "throughput": 1032.83, "total_tokens": 5348016} {"current_steps": 59395, "total_steps": 76960, "loss": 0.1941, "lr": 7.5239132199871e-06, "epoch": 15.43529106029106, "percentage": 77.18, "elapsed_time": "1:26:18", "remaining_time": "0:25:31", "throughput": 1032.83, "total_tokens": 5348448} {"current_steps": 59400, "total_steps": 76960, "loss": 0.0012, "lr": 7.519859457498812e-06, "epoch": 15.436590436590437, "percentage": 77.18, "elapsed_time": "1:26:18", "remaining_time": "0:25:30", "throughput": 1032.83, "total_tokens": 5348864} {"current_steps": 59405, "total_steps": 76960, "loss": 0.0916, "lr": 7.515806594030891e-06, "epoch": 15.437889812889813, "percentage": 77.19, "elapsed_time": "1:26:19", "remaining_time": "0:25:30", "throughput": 1032.83, "total_tokens": 5349312} {"current_steps": 59410, "total_steps": 76960, "loss": 0.2505, "lr": 7.511754629791792e-06, "epoch": 15.43918918918919, "percentage": 77.2, "elapsed_time": "1:26:19", "remaining_time": "0:25:30", "throughput": 1032.83, "total_tokens": 5349760} {"current_steps": 59415, "total_steps": 76960, "loss": 0.2208, "lr": 7.507703564989907e-06, "epoch": 15.440488565488565, "percentage": 77.2, "elapsed_time": "1:26:20", "remaining_time": "0:25:29", "throughput": 1032.84, "total_tokens": 5350208} {"current_steps": 59420, "total_steps": 76960, "loss": 0.024, "lr": 7.503653399833596e-06, "epoch": 15.441787941787942, "percentage": 77.21, "elapsed_time": "1:26:20", "remaining_time": "0:25:29", "throughput": 1032.84, "total_tokens": 5350640} {"current_steps": 59425, "total_steps": 76960, "loss": 0.1648, "lr": 7.499604134531149e-06, "epoch": 15.443087318087318, "percentage": 77.22, "elapsed_time": "1:26:20", "remaining_time": "0:25:28", "throughput": 1032.84, "total_tokens": 5351056} {"current_steps": 59430, "total_steps": 76960, "loss": 0.2868, "lr": 7.495555769290835e-06, "epoch": 15.444386694386694, "percentage": 77.22, "elapsed_time": "1:26:21", "remaining_time": "0:25:28", "throughput": 1032.84, "total_tokens": 5351504} {"current_steps": 59435, "total_steps": 76960, "loss": 0.0444, "lr": 7.491508304320854e-06, "epoch": 15.44568607068607, "percentage": 77.23, "elapsed_time": "1:26:21", "remaining_time": "0:25:27", "throughput": 1032.84, "total_tokens": 5351952} {"current_steps": 59440, "total_steps": 76960, "loss": 0.0406, "lr": 7.487461739829383e-06, "epoch": 15.446985446985448, "percentage": 77.23, "elapsed_time": "1:26:22", "remaining_time": "0:25:27", "throughput": 1032.85, "total_tokens": 5352400} {"current_steps": 59445, "total_steps": 76960, "loss": 0.2685, "lr": 7.483416076024527e-06, "epoch": 15.448284823284823, "percentage": 77.24, "elapsed_time": "1:26:22", "remaining_time": "0:25:27", "throughput": 1032.85, "total_tokens": 5352848} {"current_steps": 59450, "total_steps": 76960, "loss": 0.0675, "lr": 7.479371313114364e-06, "epoch": 15.4495841995842, "percentage": 77.25, "elapsed_time": "1:26:23", "remaining_time": "0:25:26", "throughput": 1032.85, "total_tokens": 5353296} {"current_steps": 59455, "total_steps": 76960, "loss": 0.1838, "lr": 7.4753274513069325e-06, "epoch": 15.450883575883577, "percentage": 77.25, "elapsed_time": "1:26:23", "remaining_time": "0:25:26", "throughput": 1032.86, "total_tokens": 5353744} {"current_steps": 59460, "total_steps": 76960, "loss": 0.2388, "lr": 7.471284490810193e-06, "epoch": 15.452182952182952, "percentage": 77.26, "elapsed_time": "1:26:23", "remaining_time": "0:25:25", "throughput": 1032.87, "total_tokens": 5354208} {"current_steps": 59465, "total_steps": 76960, "loss": 0.1004, "lr": 7.467242431832094e-06, "epoch": 15.453482328482329, "percentage": 77.27, "elapsed_time": "1:26:24", "remaining_time": "0:25:25", "throughput": 1032.87, "total_tokens": 5354672} {"current_steps": 59470, "total_steps": 76960, "loss": 0.4127, "lr": 7.463201274580508e-06, "epoch": 15.454781704781706, "percentage": 77.27, "elapsed_time": "1:26:24", "remaining_time": "0:25:24", "throughput": 1032.89, "total_tokens": 5355184} {"current_steps": 59475, "total_steps": 76960, "loss": 0.1839, "lr": 7.4591610192632915e-06, "epoch": 15.45608108108108, "percentage": 77.28, "elapsed_time": "1:26:25", "remaining_time": "0:25:24", "throughput": 1032.9, "total_tokens": 5355664} {"current_steps": 59480, "total_steps": 76960, "loss": 0.1557, "lr": 7.455121666088225e-06, "epoch": 15.457380457380458, "percentage": 77.29, "elapsed_time": "1:26:25", "remaining_time": "0:25:23", "throughput": 1032.9, "total_tokens": 5356112} {"current_steps": 59485, "total_steps": 76960, "loss": 0.0168, "lr": 7.451083215263057e-06, "epoch": 15.458679833679835, "percentage": 77.29, "elapsed_time": "1:26:25", "remaining_time": "0:25:23", "throughput": 1032.9, "total_tokens": 5356544} {"current_steps": 59490, "total_steps": 76960, "loss": 0.0143, "lr": 7.447045666995498e-06, "epoch": 15.45997920997921, "percentage": 77.3, "elapsed_time": "1:26:26", "remaining_time": "0:25:23", "throughput": 1032.91, "total_tokens": 5357024} {"current_steps": 59495, "total_steps": 76960, "loss": 0.2459, "lr": 7.443009021493205e-06, "epoch": 15.461278586278587, "percentage": 77.31, "elapsed_time": "1:26:26", "remaining_time": "0:25:22", "throughput": 1032.91, "total_tokens": 5357456} {"current_steps": 59500, "total_steps": 76960, "loss": 0.2085, "lr": 7.438973278963774e-06, "epoch": 15.462577962577962, "percentage": 77.31, "elapsed_time": "1:26:27", "remaining_time": "0:25:22", "throughput": 1032.92, "total_tokens": 5357904} {"current_steps": 59505, "total_steps": 76960, "loss": 0.0078, "lr": 7.434938439614781e-06, "epoch": 15.463877338877339, "percentage": 77.32, "elapsed_time": "1:26:27", "remaining_time": "0:25:21", "throughput": 1032.92, "total_tokens": 5358352} {"current_steps": 59510, "total_steps": 76960, "loss": 0.0109, "lr": 7.430904503653724e-06, "epoch": 15.465176715176716, "percentage": 77.33, "elapsed_time": "1:26:27", "remaining_time": "0:25:21", "throughput": 1032.93, "total_tokens": 5358816} {"current_steps": 59515, "total_steps": 76960, "loss": 0.2046, "lr": 7.426871471288091e-06, "epoch": 15.46647609147609, "percentage": 77.33, "elapsed_time": "1:26:28", "remaining_time": "0:25:20", "throughput": 1032.93, "total_tokens": 5359264} {"current_steps": 59520, "total_steps": 76960, "loss": 0.0594, "lr": 7.422839342725291e-06, "epoch": 15.467775467775468, "percentage": 77.34, "elapsed_time": "1:26:28", "remaining_time": "0:25:20", "throughput": 1032.93, "total_tokens": 5359696} {"current_steps": 59525, "total_steps": 76960, "loss": 0.0844, "lr": 7.418808118172702e-06, "epoch": 15.469074844074845, "percentage": 77.35, "elapsed_time": "1:26:29", "remaining_time": "0:25:19", "throughput": 1032.94, "total_tokens": 5360176} {"current_steps": 59530, "total_steps": 76960, "loss": 0.1604, "lr": 7.414777797837666e-06, "epoch": 15.47037422037422, "percentage": 77.35, "elapsed_time": "1:26:29", "remaining_time": "0:25:19", "throughput": 1032.95, "total_tokens": 5360640} {"current_steps": 59535, "total_steps": 76960, "loss": 0.207, "lr": 7.410748381927449e-06, "epoch": 15.471673596673597, "percentage": 77.36, "elapsed_time": "1:26:30", "remaining_time": "0:25:19", "throughput": 1032.95, "total_tokens": 5361072} {"current_steps": 59540, "total_steps": 76960, "loss": 0.1078, "lr": 7.406719870649303e-06, "epoch": 15.472972972972974, "percentage": 77.36, "elapsed_time": "1:26:30", "remaining_time": "0:25:18", "throughput": 1032.95, "total_tokens": 5361504} {"current_steps": 59545, "total_steps": 76960, "loss": 0.1522, "lr": 7.402692264210403e-06, "epoch": 15.474272349272349, "percentage": 77.37, "elapsed_time": "1:26:30", "remaining_time": "0:25:18", "throughput": 1032.95, "total_tokens": 5361936} {"current_steps": 59550, "total_steps": 76960, "loss": 0.1473, "lr": 7.3986655628179105e-06, "epoch": 15.475571725571726, "percentage": 77.38, "elapsed_time": "1:26:31", "remaining_time": "0:25:17", "throughput": 1032.95, "total_tokens": 5362368} {"current_steps": 59555, "total_steps": 76960, "loss": 0.0386, "lr": 7.3946397666789045e-06, "epoch": 15.476871101871103, "percentage": 77.38, "elapsed_time": "1:26:31", "remaining_time": "0:25:17", "throughput": 1032.96, "total_tokens": 5362832} {"current_steps": 59560, "total_steps": 76960, "loss": 0.4307, "lr": 7.390614876000443e-06, "epoch": 15.478170478170478, "percentage": 77.39, "elapsed_time": "1:26:32", "remaining_time": "0:25:16", "throughput": 1032.96, "total_tokens": 5363280} {"current_steps": 59565, "total_steps": 76960, "loss": 0.096, "lr": 7.386590890989534e-06, "epoch": 15.479469854469855, "percentage": 77.4, "elapsed_time": "1:26:32", "remaining_time": "0:25:16", "throughput": 1032.96, "total_tokens": 5363712} {"current_steps": 59570, "total_steps": 76960, "loss": 0.0164, "lr": 7.382567811853136e-06, "epoch": 15.48076923076923, "percentage": 77.4, "elapsed_time": "1:26:32", "remaining_time": "0:25:15", "throughput": 1032.97, "total_tokens": 5364176} {"current_steps": 59575, "total_steps": 76960, "loss": 0.0579, "lr": 7.3785456387981485e-06, "epoch": 15.482068607068607, "percentage": 77.41, "elapsed_time": "1:26:33", "remaining_time": "0:25:15", "throughput": 1032.97, "total_tokens": 5364624} {"current_steps": 59580, "total_steps": 76960, "loss": 0.0849, "lr": 7.374524372031452e-06, "epoch": 15.483367983367984, "percentage": 77.42, "elapsed_time": "1:26:33", "remaining_time": "0:25:15", "throughput": 1032.97, "total_tokens": 5365056} {"current_steps": 59585, "total_steps": 76960, "loss": 0.0161, "lr": 7.370504011759855e-06, "epoch": 15.484667359667359, "percentage": 77.42, "elapsed_time": "1:26:34", "remaining_time": "0:25:14", "throughput": 1032.97, "total_tokens": 5365488} {"current_steps": 59590, "total_steps": 76960, "loss": 0.286, "lr": 7.3664845581901206e-06, "epoch": 15.485966735966736, "percentage": 77.43, "elapsed_time": "1:26:34", "remaining_time": "0:25:14", "throughput": 1032.98, "total_tokens": 5365936} {"current_steps": 59595, "total_steps": 76960, "loss": 0.126, "lr": 7.362466011528979e-06, "epoch": 15.487266112266113, "percentage": 77.44, "elapsed_time": "1:26:35", "remaining_time": "0:25:13", "throughput": 1032.99, "total_tokens": 5366416} {"current_steps": 59600, "total_steps": 76960, "loss": 0.1699, "lr": 7.358448371983112e-06, "epoch": 15.488565488565488, "percentage": 77.44, "elapsed_time": "1:26:35", "remaining_time": "0:25:13", "throughput": 1033.0, "total_tokens": 5366896} {"current_steps": 59605, "total_steps": 76960, "loss": 0.3404, "lr": 7.3544316397591545e-06, "epoch": 15.489864864864865, "percentage": 77.45, "elapsed_time": "1:26:35", "remaining_time": "0:25:12", "throughput": 1033.0, "total_tokens": 5367328} {"current_steps": 59610, "total_steps": 76960, "loss": 0.1177, "lr": 7.350415815063677e-06, "epoch": 15.491164241164242, "percentage": 77.46, "elapsed_time": "1:26:36", "remaining_time": "0:25:12", "throughput": 1032.99, "total_tokens": 5367744} {"current_steps": 59615, "total_steps": 76960, "loss": 0.1, "lr": 7.3464008981032365e-06, "epoch": 15.492463617463617, "percentage": 77.46, "elapsed_time": "1:26:36", "remaining_time": "0:25:11", "throughput": 1033.0, "total_tokens": 5368192} {"current_steps": 59620, "total_steps": 76960, "loss": 0.0827, "lr": 7.342386889084301e-06, "epoch": 15.493762993762994, "percentage": 77.47, "elapsed_time": "1:26:37", "remaining_time": "0:25:11", "throughput": 1033.0, "total_tokens": 5368640} {"current_steps": 59625, "total_steps": 76960, "loss": 0.2329, "lr": 7.338373788213337e-06, "epoch": 15.49506237006237, "percentage": 77.48, "elapsed_time": "1:26:37", "remaining_time": "0:25:11", "throughput": 1033.01, "total_tokens": 5369104} {"current_steps": 59630, "total_steps": 76960, "loss": 0.1217, "lr": 7.334361595696723e-06, "epoch": 15.496361746361746, "percentage": 77.48, "elapsed_time": "1:26:37", "remaining_time": "0:25:10", "throughput": 1033.01, "total_tokens": 5369552} {"current_steps": 59635, "total_steps": 76960, "loss": 0.199, "lr": 7.330350311740816e-06, "epoch": 15.497661122661123, "percentage": 77.49, "elapsed_time": "1:26:38", "remaining_time": "0:25:10", "throughput": 1033.01, "total_tokens": 5370000} {"current_steps": 59640, "total_steps": 76960, "loss": 0.0693, "lr": 7.326339936551926e-06, "epoch": 15.4989604989605, "percentage": 77.49, "elapsed_time": "1:26:38", "remaining_time": "0:25:09", "throughput": 1033.02, "total_tokens": 5370448} {"current_steps": 59645, "total_steps": 76960, "loss": 0.2959, "lr": 7.3223304703363135e-06, "epoch": 15.500259875259875, "percentage": 77.5, "elapsed_time": "1:26:39", "remaining_time": "0:25:09", "throughput": 1033.02, "total_tokens": 5370896} {"current_steps": 59650, "total_steps": 76960, "loss": 0.0497, "lr": 7.318321913300183e-06, "epoch": 15.501559251559252, "percentage": 77.51, "elapsed_time": "1:26:39", "remaining_time": "0:25:08", "throughput": 1033.02, "total_tokens": 5371344} {"current_steps": 59655, "total_steps": 76960, "loss": 0.0514, "lr": 7.314314265649691e-06, "epoch": 15.502858627858627, "percentage": 77.51, "elapsed_time": "1:26:40", "remaining_time": "0:25:08", "throughput": 1033.03, "total_tokens": 5371808} {"current_steps": 59660, "total_steps": 76960, "loss": 0.3617, "lr": 7.310307527590962e-06, "epoch": 15.504158004158004, "percentage": 77.52, "elapsed_time": "1:26:40", "remaining_time": "0:25:08", "throughput": 1033.04, "total_tokens": 5372256} {"current_steps": 59665, "total_steps": 76960, "loss": 0.3767, "lr": 7.306301699330065e-06, "epoch": 15.505457380457381, "percentage": 77.53, "elapsed_time": "1:26:40", "remaining_time": "0:25:07", "throughput": 1033.04, "total_tokens": 5372704} {"current_steps": 59670, "total_steps": 76960, "loss": 0.1564, "lr": 7.302296781073034e-06, "epoch": 15.506756756756756, "percentage": 77.53, "elapsed_time": "1:26:41", "remaining_time": "0:25:07", "throughput": 1033.05, "total_tokens": 5373168} {"current_steps": 59675, "total_steps": 76960, "loss": 0.2044, "lr": 7.298292773025828e-06, "epoch": 15.508056133056133, "percentage": 77.54, "elapsed_time": "1:26:41", "remaining_time": "0:25:06", "throughput": 1033.06, "total_tokens": 5373648} {"current_steps": 59680, "total_steps": 76960, "loss": 0.0101, "lr": 7.294289675394394e-06, "epoch": 15.50935550935551, "percentage": 77.55, "elapsed_time": "1:26:42", "remaining_time": "0:25:06", "throughput": 1033.06, "total_tokens": 5374080} {"current_steps": 59685, "total_steps": 76960, "loss": 0.1135, "lr": 7.290287488384598e-06, "epoch": 15.510654885654885, "percentage": 77.55, "elapsed_time": "1:26:42", "remaining_time": "0:25:05", "throughput": 1033.06, "total_tokens": 5374512} {"current_steps": 59690, "total_steps": 76960, "loss": 0.1658, "lr": 7.286286212202295e-06, "epoch": 15.511954261954262, "percentage": 77.56, "elapsed_time": "1:26:42", "remaining_time": "0:25:05", "throughput": 1033.07, "total_tokens": 5374992} {"current_steps": 59695, "total_steps": 76960, "loss": 0.0969, "lr": 7.282285847053255e-06, "epoch": 15.513253638253639, "percentage": 77.57, "elapsed_time": "1:26:43", "remaining_time": "0:25:04", "throughput": 1033.08, "total_tokens": 5375472} {"current_steps": 59700, "total_steps": 76960, "loss": 0.3203, "lr": 7.27828639314323e-06, "epoch": 15.514553014553014, "percentage": 77.57, "elapsed_time": "1:26:43", "remaining_time": "0:25:04", "throughput": 1033.08, "total_tokens": 5375920} {"current_steps": 59705, "total_steps": 76960, "loss": 0.4822, "lr": 7.274287850677919e-06, "epoch": 15.515852390852391, "percentage": 77.58, "elapsed_time": "1:26:44", "remaining_time": "0:25:04", "throughput": 1033.1, "total_tokens": 5376432} {"current_steps": 59710, "total_steps": 76960, "loss": 0.1963, "lr": 7.2702902198629714e-06, "epoch": 15.517151767151766, "percentage": 77.59, "elapsed_time": "1:26:44", "remaining_time": "0:25:03", "throughput": 1033.1, "total_tokens": 5376880} {"current_steps": 59715, "total_steps": 76960, "loss": 0.0537, "lr": 7.2662935009039865e-06, "epoch": 15.518451143451143, "percentage": 77.59, "elapsed_time": "1:26:45", "remaining_time": "0:25:03", "throughput": 1033.1, "total_tokens": 5377328} {"current_steps": 59720, "total_steps": 76960, "loss": 0.1525, "lr": 7.262297694006512e-06, "epoch": 15.51975051975052, "percentage": 77.6, "elapsed_time": "1:26:45", "remaining_time": "0:25:02", "throughput": 1033.1, "total_tokens": 5377744} {"current_steps": 59725, "total_steps": 76960, "loss": 0.0679, "lr": 7.258302799376071e-06, "epoch": 15.521049896049895, "percentage": 77.61, "elapsed_time": "1:26:45", "remaining_time": "0:25:02", "throughput": 1033.11, "total_tokens": 5378224} {"current_steps": 59730, "total_steps": 76960, "loss": 0.2097, "lr": 7.254308817218109e-06, "epoch": 15.522349272349272, "percentage": 77.61, "elapsed_time": "1:26:46", "remaining_time": "0:25:01", "throughput": 1033.11, "total_tokens": 5378672} {"current_steps": 59735, "total_steps": 76960, "loss": 0.3075, "lr": 7.2503157477380455e-06, "epoch": 15.52364864864865, "percentage": 77.62, "elapsed_time": "1:26:46", "remaining_time": "0:25:01", "throughput": 1033.12, "total_tokens": 5379136} {"current_steps": 59740, "total_steps": 76960, "loss": 0.0965, "lr": 7.246323591141249e-06, "epoch": 15.524948024948024, "percentage": 77.62, "elapsed_time": "1:26:47", "remaining_time": "0:25:00", "throughput": 1033.12, "total_tokens": 5379568} {"current_steps": 59745, "total_steps": 76960, "loss": 0.0199, "lr": 7.242332347633052e-06, "epoch": 15.526247401247401, "percentage": 77.63, "elapsed_time": "1:26:47", "remaining_time": "0:25:00", "throughput": 1033.12, "total_tokens": 5379984} {"current_steps": 59750, "total_steps": 76960, "loss": 0.2721, "lr": 7.238342017418706e-06, "epoch": 15.527546777546778, "percentage": 77.64, "elapsed_time": "1:26:47", "remaining_time": "0:25:00", "throughput": 1033.12, "total_tokens": 5380448} {"current_steps": 59755, "total_steps": 76960, "loss": 0.0163, "lr": 7.234352600703459e-06, "epoch": 15.528846153846153, "percentage": 77.64, "elapsed_time": "1:26:48", "remaining_time": "0:24:59", "throughput": 1033.13, "total_tokens": 5380912} {"current_steps": 59760, "total_steps": 76960, "loss": 0.3408, "lr": 7.230364097692469e-06, "epoch": 15.53014553014553, "percentage": 77.65, "elapsed_time": "1:26:48", "remaining_time": "0:24:59", "throughput": 1033.14, "total_tokens": 5381408} {"current_steps": 59765, "total_steps": 76960, "loss": 0.6972, "lr": 7.22637650859089e-06, "epoch": 15.531444906444907, "percentage": 77.66, "elapsed_time": "1:26:49", "remaining_time": "0:24:58", "throughput": 1033.14, "total_tokens": 5381840} {"current_steps": 59770, "total_steps": 76960, "loss": 0.1528, "lr": 7.2223898336037875e-06, "epoch": 15.532744282744282, "percentage": 77.66, "elapsed_time": "1:26:49", "remaining_time": "0:24:58", "throughput": 1033.15, "total_tokens": 5382304} {"current_steps": 59775, "total_steps": 76960, "loss": 0.2966, "lr": 7.218404072936211e-06, "epoch": 15.53404365904366, "percentage": 77.67, "elapsed_time": "1:26:50", "remaining_time": "0:24:57", "throughput": 1033.15, "total_tokens": 5382736} {"current_steps": 59780, "total_steps": 76960, "loss": 0.018, "lr": 7.214419226793159e-06, "epoch": 15.535343035343036, "percentage": 77.68, "elapsed_time": "1:26:50", "remaining_time": "0:24:57", "throughput": 1033.16, "total_tokens": 5383216} {"current_steps": 59785, "total_steps": 76960, "loss": 0.0046, "lr": 7.210435295379558e-06, "epoch": 15.536642411642411, "percentage": 77.68, "elapsed_time": "1:26:50", "remaining_time": "0:24:56", "throughput": 1033.16, "total_tokens": 5383648} {"current_steps": 59790, "total_steps": 76960, "loss": 0.3823, "lr": 7.206452278900322e-06, "epoch": 15.537941787941788, "percentage": 77.69, "elapsed_time": "1:26:51", "remaining_time": "0:24:56", "throughput": 1033.17, "total_tokens": 5384096} {"current_steps": 59795, "total_steps": 76960, "loss": 0.0656, "lr": 7.202470177560288e-06, "epoch": 15.539241164241163, "percentage": 77.7, "elapsed_time": "1:26:51", "remaining_time": "0:24:56", "throughput": 1033.18, "total_tokens": 5384592} {"current_steps": 59800, "total_steps": 76960, "loss": 0.4488, "lr": 7.198488991564273e-06, "epoch": 15.54054054054054, "percentage": 77.7, "elapsed_time": "1:26:52", "remaining_time": "0:24:55", "throughput": 1033.18, "total_tokens": 5385040} {"current_steps": 59805, "total_steps": 76960, "loss": 0.1433, "lr": 7.1945087211170185e-06, "epoch": 15.541839916839917, "percentage": 77.71, "elapsed_time": "1:26:52", "remaining_time": "0:24:55", "throughput": 1033.19, "total_tokens": 5385488} {"current_steps": 59810, "total_steps": 76960, "loss": 0.0155, "lr": 7.19052936642324e-06, "epoch": 15.543139293139292, "percentage": 77.72, "elapsed_time": "1:26:52", "remaining_time": "0:24:54", "throughput": 1033.19, "total_tokens": 5385920} {"current_steps": 59815, "total_steps": 76960, "loss": 0.0481, "lr": 7.186550927687602e-06, "epoch": 15.54443866943867, "percentage": 77.72, "elapsed_time": "1:26:53", "remaining_time": "0:24:54", "throughput": 1033.2, "total_tokens": 5386400} {"current_steps": 59820, "total_steps": 76960, "loss": 0.1404, "lr": 7.1825734051147235e-06, "epoch": 15.545738045738046, "percentage": 77.73, "elapsed_time": "1:26:53", "remaining_time": "0:24:53", "throughput": 1033.2, "total_tokens": 5386864} {"current_steps": 59825, "total_steps": 76960, "loss": 0.5213, "lr": 7.178596798909159e-06, "epoch": 15.547037422037421, "percentage": 77.74, "elapsed_time": "1:26:54", "remaining_time": "0:24:53", "throughput": 1033.21, "total_tokens": 5387328} {"current_steps": 59830, "total_steps": 76960, "loss": 0.216, "lr": 7.174621109275445e-06, "epoch": 15.548336798336798, "percentage": 77.74, "elapsed_time": "1:26:54", "remaining_time": "0:24:52", "throughput": 1033.22, "total_tokens": 5387808} {"current_steps": 59835, "total_steps": 76960, "loss": 0.0222, "lr": 7.170646336418038e-06, "epoch": 15.549636174636175, "percentage": 77.75, "elapsed_time": "1:26:54", "remaining_time": "0:24:52", "throughput": 1033.22, "total_tokens": 5388256} {"current_steps": 59840, "total_steps": 76960, "loss": 0.1181, "lr": 7.166672480541384e-06, "epoch": 15.55093555093555, "percentage": 77.75, "elapsed_time": "1:26:55", "remaining_time": "0:24:52", "throughput": 1033.22, "total_tokens": 5388688} {"current_steps": 59845, "total_steps": 76960, "loss": 0.0404, "lr": 7.162699541849841e-06, "epoch": 15.552234927234927, "percentage": 77.76, "elapsed_time": "1:26:55", "remaining_time": "0:24:51", "throughput": 1033.23, "total_tokens": 5389152} {"current_steps": 59850, "total_steps": 76960, "loss": 0.0426, "lr": 7.158727520547753e-06, "epoch": 15.553534303534304, "percentage": 77.77, "elapsed_time": "1:26:56", "remaining_time": "0:24:51", "throughput": 1033.23, "total_tokens": 5389600} {"current_steps": 59855, "total_steps": 76960, "loss": 0.1908, "lr": 7.154756416839409e-06, "epoch": 15.55483367983368, "percentage": 77.77, "elapsed_time": "1:26:56", "remaining_time": "0:24:50", "throughput": 1033.23, "total_tokens": 5390016} {"current_steps": 59860, "total_steps": 76960, "loss": 0.3752, "lr": 7.1507862309290355e-06, "epoch": 15.556133056133056, "percentage": 77.78, "elapsed_time": "1:26:57", "remaining_time": "0:24:50", "throughput": 1033.23, "total_tokens": 5390448} {"current_steps": 59865, "total_steps": 76960, "loss": 0.267, "lr": 7.146816963020836e-06, "epoch": 15.557432432432432, "percentage": 77.79, "elapsed_time": "1:26:57", "remaining_time": "0:24:49", "throughput": 1033.24, "total_tokens": 5390896} {"current_steps": 59870, "total_steps": 76960, "loss": 0.0762, "lr": 7.142848613318936e-06, "epoch": 15.558731808731808, "percentage": 77.79, "elapsed_time": "1:26:57", "remaining_time": "0:24:49", "throughput": 1033.24, "total_tokens": 5391360} {"current_steps": 59875, "total_steps": 76960, "loss": 0.1159, "lr": 7.138881182027452e-06, "epoch": 15.560031185031185, "percentage": 77.8, "elapsed_time": "1:26:58", "remaining_time": "0:24:49", "throughput": 1033.25, "total_tokens": 5391808} {"current_steps": 59880, "total_steps": 76960, "loss": 0.0036, "lr": 7.134914669350415e-06, "epoch": 15.56133056133056, "percentage": 77.81, "elapsed_time": "1:26:58", "remaining_time": "0:24:48", "throughput": 1033.25, "total_tokens": 5392240} {"current_steps": 59885, "total_steps": 76960, "loss": 0.4278, "lr": 7.13094907549183e-06, "epoch": 15.562629937629938, "percentage": 77.81, "elapsed_time": "1:26:59", "remaining_time": "0:24:48", "throughput": 1033.25, "total_tokens": 5392688} {"current_steps": 59890, "total_steps": 76960, "loss": 0.3426, "lr": 7.126984400655659e-06, "epoch": 15.563929313929314, "percentage": 77.82, "elapsed_time": "1:26:59", "remaining_time": "0:24:47", "throughput": 1033.25, "total_tokens": 5393136} {"current_steps": 59895, "total_steps": 76960, "loss": 0.0922, "lr": 7.123020645045814e-06, "epoch": 15.56522869022869, "percentage": 77.83, "elapsed_time": "1:26:59", "remaining_time": "0:24:47", "throughput": 1033.25, "total_tokens": 5393568} {"current_steps": 59900, "total_steps": 76960, "loss": 0.4157, "lr": 7.1190578088661365e-06, "epoch": 15.566528066528067, "percentage": 77.83, "elapsed_time": "1:27:00", "remaining_time": "0:24:46", "throughput": 1033.26, "total_tokens": 5394048} {"current_steps": 59905, "total_steps": 76960, "loss": 0.0946, "lr": 7.115095892320456e-06, "epoch": 15.567827442827443, "percentage": 77.84, "elapsed_time": "1:27:00", "remaining_time": "0:24:46", "throughput": 1033.27, "total_tokens": 5394512} {"current_steps": 59910, "total_steps": 76960, "loss": 0.147, "lr": 7.111134895612523e-06, "epoch": 15.569126819126819, "percentage": 77.85, "elapsed_time": "1:27:01", "remaining_time": "0:24:45", "throughput": 1033.27, "total_tokens": 5394944} {"current_steps": 59915, "total_steps": 76960, "loss": 0.0666, "lr": 7.107174818946063e-06, "epoch": 15.570426195426196, "percentage": 77.85, "elapsed_time": "1:27:01", "remaining_time": "0:24:45", "throughput": 1033.27, "total_tokens": 5395360} {"current_steps": 59920, "total_steps": 76960, "loss": 0.2015, "lr": 7.103215662524753e-06, "epoch": 15.571725571725572, "percentage": 77.86, "elapsed_time": "1:27:02", "remaining_time": "0:24:45", "throughput": 1033.27, "total_tokens": 5395824} {"current_steps": 59925, "total_steps": 76960, "loss": 0.4476, "lr": 7.099257426552203e-06, "epoch": 15.573024948024948, "percentage": 77.87, "elapsed_time": "1:27:02", "remaining_time": "0:24:44", "throughput": 1033.27, "total_tokens": 5396256} {"current_steps": 59930, "total_steps": 76960, "loss": 0.048, "lr": 7.095300111232e-06, "epoch": 15.574324324324325, "percentage": 77.87, "elapsed_time": "1:27:02", "remaining_time": "0:24:44", "throughput": 1033.28, "total_tokens": 5396704} {"current_steps": 59935, "total_steps": 76960, "loss": 0.1969, "lr": 7.0913437167676625e-06, "epoch": 15.575623700623701, "percentage": 77.88, "elapsed_time": "1:27:03", "remaining_time": "0:24:43", "throughput": 1033.28, "total_tokens": 5397136} {"current_steps": 59940, "total_steps": 76960, "loss": 0.1786, "lr": 7.087388243362686e-06, "epoch": 15.576923076923077, "percentage": 77.88, "elapsed_time": "1:27:03", "remaining_time": "0:24:43", "throughput": 1033.28, "total_tokens": 5397600} {"current_steps": 59945, "total_steps": 76960, "loss": 0.2152, "lr": 7.083433691220484e-06, "epoch": 15.578222453222454, "percentage": 77.89, "elapsed_time": "1:27:04", "remaining_time": "0:24:42", "throughput": 1033.28, "total_tokens": 5398016} {"current_steps": 59950, "total_steps": 76960, "loss": 0.0485, "lr": 7.079480060544458e-06, "epoch": 15.579521829521829, "percentage": 77.9, "elapsed_time": "1:27:04", "remaining_time": "0:24:42", "throughput": 1033.29, "total_tokens": 5398480} {"current_steps": 59955, "total_steps": 76960, "loss": 0.1834, "lr": 7.075527351537939e-06, "epoch": 15.580821205821206, "percentage": 77.9, "elapsed_time": "1:27:04", "remaining_time": "0:24:41", "throughput": 1033.29, "total_tokens": 5398944} {"current_steps": 59960, "total_steps": 76960, "loss": 0.199, "lr": 7.071575564404231e-06, "epoch": 15.582120582120583, "percentage": 77.91, "elapsed_time": "1:27:05", "remaining_time": "0:24:41", "throughput": 1033.3, "total_tokens": 5399408} {"current_steps": 59965, "total_steps": 76960, "loss": 0.0605, "lr": 7.067624699346564e-06, "epoch": 15.583419958419958, "percentage": 77.92, "elapsed_time": "1:27:05", "remaining_time": "0:24:41", "throughput": 1033.3, "total_tokens": 5399840} {"current_steps": 59970, "total_steps": 76960, "loss": 0.1678, "lr": 7.0636747565681475e-06, "epoch": 15.584719334719335, "percentage": 77.92, "elapsed_time": "1:27:06", "remaining_time": "0:24:40", "throughput": 1033.3, "total_tokens": 5400240} {"current_steps": 59975, "total_steps": 76960, "loss": 0.159, "lr": 7.059725736272127e-06, "epoch": 15.586018711018712, "percentage": 77.93, "elapsed_time": "1:27:06", "remaining_time": "0:24:40", "throughput": 1033.29, "total_tokens": 5400656} {"current_steps": 59980, "total_steps": 76960, "loss": 0.287, "lr": 7.05577763866159e-06, "epoch": 15.587318087318087, "percentage": 77.94, "elapsed_time": "1:27:07", "remaining_time": "0:24:39", "throughput": 1033.31, "total_tokens": 5401152} {"current_steps": 59985, "total_steps": 76960, "loss": 0.0907, "lr": 7.051830463939604e-06, "epoch": 15.588617463617464, "percentage": 77.94, "elapsed_time": "1:27:07", "remaining_time": "0:24:39", "throughput": 1033.31, "total_tokens": 5401584} {"current_steps": 59990, "total_steps": 76960, "loss": 0.1495, "lr": 7.047884212309172e-06, "epoch": 15.58991683991684, "percentage": 77.95, "elapsed_time": "1:27:07", "remaining_time": "0:24:38", "throughput": 1033.31, "total_tokens": 5402016} {"current_steps": 59995, "total_steps": 76960, "loss": 0.2163, "lr": 7.043938883973266e-06, "epoch": 15.591216216216216, "percentage": 77.96, "elapsed_time": "1:27:08", "remaining_time": "0:24:38", "throughput": 1033.31, "total_tokens": 5402464} {"current_steps": 60000, "total_steps": 76960, "loss": 0.1329, "lr": 7.039994479134782e-06, "epoch": 15.592515592515593, "percentage": 77.96, "elapsed_time": "1:27:08", "remaining_time": "0:24:37", "throughput": 1033.32, "total_tokens": 5402928} {"current_steps": 60005, "total_steps": 76960, "loss": 0.3039, "lr": 7.036050997996593e-06, "epoch": 15.59381496881497, "percentage": 77.97, "elapsed_time": "1:27:09", "remaining_time": "0:24:37", "throughput": 1033.32, "total_tokens": 5403360} {"current_steps": 60010, "total_steps": 76960, "loss": 0.0021, "lr": 7.032108440761509e-06, "epoch": 15.595114345114345, "percentage": 77.98, "elapsed_time": "1:27:09", "remaining_time": "0:24:37", "throughput": 1033.33, "total_tokens": 5403856} {"current_steps": 60015, "total_steps": 76960, "loss": 0.0633, "lr": 7.028166807632311e-06, "epoch": 15.596413721413722, "percentage": 77.98, "elapsed_time": "1:27:09", "remaining_time": "0:24:36", "throughput": 1033.33, "total_tokens": 5404288} {"current_steps": 60020, "total_steps": 76960, "loss": 0.3378, "lr": 7.024226098811707e-06, "epoch": 15.597713097713097, "percentage": 77.99, "elapsed_time": "1:27:10", "remaining_time": "0:24:36", "throughput": 1033.33, "total_tokens": 5404720} {"current_steps": 60025, "total_steps": 76960, "loss": 0.0867, "lr": 7.020286314502377e-06, "epoch": 15.599012474012474, "percentage": 78.0, "elapsed_time": "1:27:10", "remaining_time": "0:24:35", "throughput": 1033.34, "total_tokens": 5405184} {"current_steps": 60030, "total_steps": 76960, "loss": 0.0592, "lr": 7.016347454906949e-06, "epoch": 15.60031185031185, "percentage": 78.0, "elapsed_time": "1:27:11", "remaining_time": "0:24:35", "throughput": 1033.34, "total_tokens": 5405616} {"current_steps": 60035, "total_steps": 76960, "loss": 0.2469, "lr": 7.012409520228011e-06, "epoch": 15.601611226611226, "percentage": 78.01, "elapsed_time": "1:27:11", "remaining_time": "0:24:34", "throughput": 1033.34, "total_tokens": 5406048} {"current_steps": 60040, "total_steps": 76960, "loss": 0.0048, "lr": 7.008472510668085e-06, "epoch": 15.602910602910603, "percentage": 78.01, "elapsed_time": "1:27:12", "remaining_time": "0:24:34", "throughput": 1033.34, "total_tokens": 5406480} {"current_steps": 60045, "total_steps": 76960, "loss": 0.3294, "lr": 7.00453642642965e-06, "epoch": 15.60420997920998, "percentage": 78.02, "elapsed_time": "1:27:12", "remaining_time": "0:24:34", "throughput": 1033.34, "total_tokens": 5406928} {"current_steps": 60050, "total_steps": 76960, "loss": 0.4861, "lr": 7.000601267715157e-06, "epoch": 15.605509355509355, "percentage": 78.03, "elapsed_time": "1:27:12", "remaining_time": "0:24:33", "throughput": 1033.35, "total_tokens": 5407408} {"current_steps": 60055, "total_steps": 76960, "loss": 0.155, "lr": 6.996667034726978e-06, "epoch": 15.606808731808732, "percentage": 78.03, "elapsed_time": "1:27:13", "remaining_time": "0:24:33", "throughput": 1033.36, "total_tokens": 5407872} {"current_steps": 60060, "total_steps": 76960, "loss": 0.2482, "lr": 6.992733727667466e-06, "epoch": 15.608108108108109, "percentage": 78.04, "elapsed_time": "1:27:13", "remaining_time": "0:24:32", "throughput": 1033.36, "total_tokens": 5408336} {"current_steps": 60065, "total_steps": 76960, "loss": 0.2877, "lr": 6.98880134673891e-06, "epoch": 15.609407484407484, "percentage": 78.05, "elapsed_time": "1:27:14", "remaining_time": "0:24:32", "throughput": 1033.36, "total_tokens": 5408768} {"current_steps": 60070, "total_steps": 76960, "loss": 0.2292, "lr": 6.9848698921435664e-06, "epoch": 15.61070686070686, "percentage": 78.05, "elapsed_time": "1:27:14", "remaining_time": "0:24:31", "throughput": 1033.37, "total_tokens": 5409200} {"current_steps": 60075, "total_steps": 76960, "loss": 0.3558, "lr": 6.980939364083616e-06, "epoch": 15.612006237006238, "percentage": 78.06, "elapsed_time": "1:27:14", "remaining_time": "0:24:31", "throughput": 1033.37, "total_tokens": 5409680} {"current_steps": 60080, "total_steps": 76960, "loss": 0.0934, "lr": 6.97700976276123e-06, "epoch": 15.613305613305613, "percentage": 78.07, "elapsed_time": "1:27:15", "remaining_time": "0:24:30", "throughput": 1033.38, "total_tokens": 5410160} {"current_steps": 60085, "total_steps": 76960, "loss": 0.0021, "lr": 6.973081088378492e-06, "epoch": 15.61460498960499, "percentage": 78.07, "elapsed_time": "1:27:15", "remaining_time": "0:24:30", "throughput": 1033.39, "total_tokens": 5410608} {"current_steps": 60090, "total_steps": 76960, "loss": 0.2715, "lr": 6.969153341137472e-06, "epoch": 15.615904365904367, "percentage": 78.08, "elapsed_time": "1:27:16", "remaining_time": "0:24:30", "throughput": 1033.39, "total_tokens": 5411072} {"current_steps": 60095, "total_steps": 76960, "loss": 0.032, "lr": 6.965226521240165e-06, "epoch": 15.617203742203742, "percentage": 78.09, "elapsed_time": "1:27:16", "remaining_time": "0:24:29", "throughput": 1033.39, "total_tokens": 5411472} {"current_steps": 60100, "total_steps": 76960, "loss": 0.1175, "lr": 6.96130062888854e-06, "epoch": 15.618503118503119, "percentage": 78.09, "elapsed_time": "1:27:17", "remaining_time": "0:24:29", "throughput": 1033.4, "total_tokens": 5411968} {"current_steps": 60105, "total_steps": 76960, "loss": 0.0603, "lr": 6.957375664284513e-06, "epoch": 15.619802494802494, "percentage": 78.1, "elapsed_time": "1:27:17", "remaining_time": "0:24:28", "throughput": 1033.4, "total_tokens": 5412400} {"current_steps": 60110, "total_steps": 76960, "loss": 0.2344, "lr": 6.953451627629936e-06, "epoch": 15.621101871101871, "percentage": 78.11, "elapsed_time": "1:27:17", "remaining_time": "0:24:28", "throughput": 1033.41, "total_tokens": 5412880} {"current_steps": 60115, "total_steps": 76960, "loss": 0.0514, "lr": 6.9495285191266415e-06, "epoch": 15.622401247401248, "percentage": 78.11, "elapsed_time": "1:27:18", "remaining_time": "0:24:27", "throughput": 1033.41, "total_tokens": 5413312} {"current_steps": 60120, "total_steps": 76960, "loss": 0.0855, "lr": 6.945606338976382e-06, "epoch": 15.623700623700623, "percentage": 78.12, "elapsed_time": "1:27:18", "remaining_time": "0:24:27", "throughput": 1033.42, "total_tokens": 5413776} {"current_steps": 60125, "total_steps": 76960, "loss": 0.5685, "lr": 6.941685087380898e-06, "epoch": 15.625, "percentage": 78.12, "elapsed_time": "1:27:19", "remaining_time": "0:24:26", "throughput": 1033.43, "total_tokens": 5414256} {"current_steps": 60130, "total_steps": 76960, "loss": 0.004, "lr": 6.937764764541832e-06, "epoch": 15.626299376299377, "percentage": 78.13, "elapsed_time": "1:27:19", "remaining_time": "0:24:26", "throughput": 1033.43, "total_tokens": 5414688} {"current_steps": 60135, "total_steps": 76960, "loss": 0.0154, "lr": 6.933845370660849e-06, "epoch": 15.627598752598752, "percentage": 78.14, "elapsed_time": "1:27:19", "remaining_time": "0:24:26", "throughput": 1033.43, "total_tokens": 5415120} {"current_steps": 60140, "total_steps": 76960, "loss": 0.1943, "lr": 6.929926905939502e-06, "epoch": 15.628898128898129, "percentage": 78.14, "elapsed_time": "1:27:20", "remaining_time": "0:24:25", "throughput": 1033.43, "total_tokens": 5415552} {"current_steps": 60145, "total_steps": 76960, "loss": 0.132, "lr": 6.926009370579334e-06, "epoch": 15.630197505197506, "percentage": 78.15, "elapsed_time": "1:27:20", "remaining_time": "0:24:25", "throughput": 1033.44, "total_tokens": 5416032} {"current_steps": 60150, "total_steps": 76960, "loss": 0.6707, "lr": 6.922092764781815e-06, "epoch": 15.631496881496881, "percentage": 78.16, "elapsed_time": "1:27:21", "remaining_time": "0:24:24", "throughput": 1033.44, "total_tokens": 5416480} {"current_steps": 60155, "total_steps": 76960, "loss": 0.0909, "lr": 6.9181770887483926e-06, "epoch": 15.632796257796258, "percentage": 78.16, "elapsed_time": "1:27:21", "remaining_time": "0:24:24", "throughput": 1033.44, "total_tokens": 5416912} {"current_steps": 60160, "total_steps": 76960, "loss": 0.0779, "lr": 6.914262342680442e-06, "epoch": 15.634095634095633, "percentage": 78.17, "elapsed_time": "1:27:22", "remaining_time": "0:24:23", "throughput": 1033.44, "total_tokens": 5417328} {"current_steps": 60165, "total_steps": 76960, "loss": 0.6061, "lr": 6.9103485267793065e-06, "epoch": 15.63539501039501, "percentage": 78.18, "elapsed_time": "1:27:22", "remaining_time": "0:24:23", "throughput": 1033.45, "total_tokens": 5417792} {"current_steps": 60170, "total_steps": 76960, "loss": 0.2182, "lr": 6.90643564124629e-06, "epoch": 15.636694386694387, "percentage": 78.18, "elapsed_time": "1:27:22", "remaining_time": "0:24:22", "throughput": 1033.45, "total_tokens": 5418240} {"current_steps": 60175, "total_steps": 76960, "loss": 0.3687, "lr": 6.9025236862826135e-06, "epoch": 15.637993762993762, "percentage": 78.19, "elapsed_time": "1:27:23", "remaining_time": "0:24:22", "throughput": 1033.45, "total_tokens": 5418672} {"current_steps": 60180, "total_steps": 76960, "loss": 0.1839, "lr": 6.898612662089493e-06, "epoch": 15.63929313929314, "percentage": 78.2, "elapsed_time": "1:27:23", "remaining_time": "0:24:22", "throughput": 1033.45, "total_tokens": 5419120} {"current_steps": 60185, "total_steps": 76960, "loss": 0.1921, "lr": 6.894702568868058e-06, "epoch": 15.640592515592516, "percentage": 78.2, "elapsed_time": "1:27:24", "remaining_time": "0:24:21", "throughput": 1033.46, "total_tokens": 5419584} {"current_steps": 60190, "total_steps": 76960, "loss": 0.1223, "lr": 6.890793406819427e-06, "epoch": 15.641891891891891, "percentage": 78.21, "elapsed_time": "1:27:24", "remaining_time": "0:24:21", "throughput": 1033.47, "total_tokens": 5420032} {"current_steps": 60195, "total_steps": 76960, "loss": 0.139, "lr": 6.886885176144633e-06, "epoch": 15.643191268191268, "percentage": 78.22, "elapsed_time": "1:27:24", "remaining_time": "0:24:20", "throughput": 1033.47, "total_tokens": 5420496} {"current_steps": 60200, "total_steps": 76960, "loss": 0.3027, "lr": 6.882977877044691e-06, "epoch": 15.644490644490645, "percentage": 78.22, "elapsed_time": "1:27:25", "remaining_time": "0:24:20", "throughput": 1033.47, "total_tokens": 5420928} {"current_steps": 60205, "total_steps": 76960, "loss": 0.0359, "lr": 6.8790715097205555e-06, "epoch": 15.64579002079002, "percentage": 78.23, "elapsed_time": "1:27:25", "remaining_time": "0:24:19", "throughput": 1033.47, "total_tokens": 5421360} {"current_steps": 60210, "total_steps": 76960, "loss": 0.3591, "lr": 6.875166074373144e-06, "epoch": 15.647089397089397, "percentage": 78.24, "elapsed_time": "1:27:26", "remaining_time": "0:24:19", "throughput": 1033.48, "total_tokens": 5421808} {"current_steps": 60215, "total_steps": 76960, "loss": 0.0494, "lr": 6.871261571203297e-06, "epoch": 15.648388773388774, "percentage": 78.24, "elapsed_time": "1:27:26", "remaining_time": "0:24:19", "throughput": 1033.48, "total_tokens": 5422240} {"current_steps": 60220, "total_steps": 76960, "loss": 0.0861, "lr": 6.867358000411847e-06, "epoch": 15.64968814968815, "percentage": 78.25, "elapsed_time": "1:27:27", "remaining_time": "0:24:18", "throughput": 1033.48, "total_tokens": 5422688} {"current_steps": 60225, "total_steps": 76960, "loss": 0.2202, "lr": 6.8634553621995416e-06, "epoch": 15.650987525987526, "percentage": 78.25, "elapsed_time": "1:27:27", "remaining_time": "0:24:18", "throughput": 1033.48, "total_tokens": 5423136} {"current_steps": 60230, "total_steps": 76960, "loss": 0.0943, "lr": 6.859553656767112e-06, "epoch": 15.652286902286903, "percentage": 78.26, "elapsed_time": "1:27:27", "remaining_time": "0:24:17", "throughput": 1033.48, "total_tokens": 5423568} {"current_steps": 60235, "total_steps": 76960, "loss": 0.1333, "lr": 6.8556528843152115e-06, "epoch": 15.653586278586278, "percentage": 78.27, "elapsed_time": "1:27:28", "remaining_time": "0:24:17", "throughput": 1033.48, "total_tokens": 5424000} {"current_steps": 60240, "total_steps": 76960, "loss": 0.4845, "lr": 6.8517530450444676e-06, "epoch": 15.654885654885655, "percentage": 78.27, "elapsed_time": "1:27:28", "remaining_time": "0:24:16", "throughput": 1033.49, "total_tokens": 5424432} {"current_steps": 60245, "total_steps": 76960, "loss": 0.0077, "lr": 6.84785413915546e-06, "epoch": 15.65618503118503, "percentage": 78.28, "elapsed_time": "1:27:29", "remaining_time": "0:24:16", "throughput": 1033.48, "total_tokens": 5424848} {"current_steps": 60250, "total_steps": 76960, "loss": 0.379, "lr": 6.8439561668487e-06, "epoch": 15.657484407484407, "percentage": 78.29, "elapsed_time": "1:27:29", "remaining_time": "0:24:15", "throughput": 1033.49, "total_tokens": 5425296} {"current_steps": 60255, "total_steps": 76960, "loss": 0.096, "lr": 6.84005912832468e-06, "epoch": 15.658783783783784, "percentage": 78.29, "elapsed_time": "1:27:29", "remaining_time": "0:24:15", "throughput": 1033.49, "total_tokens": 5425744} {"current_steps": 60260, "total_steps": 76960, "loss": 0.0389, "lr": 6.83616302378381e-06, "epoch": 15.66008316008316, "percentage": 78.3, "elapsed_time": "1:27:30", "remaining_time": "0:24:15", "throughput": 1033.49, "total_tokens": 5426192} {"current_steps": 60265, "total_steps": 76960, "loss": 0.111, "lr": 6.832267853426485e-06, "epoch": 15.661382536382536, "percentage": 78.31, "elapsed_time": "1:27:30", "remaining_time": "0:24:14", "throughput": 1033.5, "total_tokens": 5426656} {"current_steps": 60270, "total_steps": 76960, "loss": 0.1927, "lr": 6.828373617453026e-06, "epoch": 15.662681912681913, "percentage": 78.31, "elapsed_time": "1:27:31", "remaining_time": "0:24:14", "throughput": 1033.51, "total_tokens": 5427120} {"current_steps": 60275, "total_steps": 76960, "loss": 0.0821, "lr": 6.824480316063725e-06, "epoch": 15.663981288981288, "percentage": 78.32, "elapsed_time": "1:27:31", "remaining_time": "0:24:13", "throughput": 1033.51, "total_tokens": 5427552} {"current_steps": 60280, "total_steps": 76960, "loss": 0.1016, "lr": 6.820587949458815e-06, "epoch": 15.665280665280665, "percentage": 78.33, "elapsed_time": "1:27:32", "remaining_time": "0:24:13", "throughput": 1033.5, "total_tokens": 5427968} {"current_steps": 60285, "total_steps": 76960, "loss": 0.1689, "lr": 6.816696517838492e-06, "epoch": 15.666580041580042, "percentage": 78.33, "elapsed_time": "1:27:32", "remaining_time": "0:24:12", "throughput": 1033.5, "total_tokens": 5428400} {"current_steps": 60290, "total_steps": 76960, "loss": 0.0384, "lr": 6.812806021402882e-06, "epoch": 15.667879417879417, "percentage": 78.34, "elapsed_time": "1:27:32", "remaining_time": "0:24:12", "throughput": 1033.51, "total_tokens": 5428880} {"current_steps": 60295, "total_steps": 76960, "loss": 0.3975, "lr": 6.808916460352091e-06, "epoch": 15.669178794178794, "percentage": 78.35, "elapsed_time": "1:27:33", "remaining_time": "0:24:11", "throughput": 1033.52, "total_tokens": 5429360} {"current_steps": 60300, "total_steps": 76960, "loss": 0.077, "lr": 6.80502783488616e-06, "epoch": 15.670478170478171, "percentage": 78.35, "elapsed_time": "1:27:33", "remaining_time": "0:24:11", "throughput": 1033.53, "total_tokens": 5429824} {"current_steps": 60305, "total_steps": 76960, "loss": 0.1098, "lr": 6.80114014520507e-06, "epoch": 15.671777546777546, "percentage": 78.36, "elapsed_time": "1:27:34", "remaining_time": "0:24:11", "throughput": 1033.53, "total_tokens": 5430256} {"current_steps": 60310, "total_steps": 76960, "loss": 0.4109, "lr": 6.7972533915087815e-06, "epoch": 15.673076923076923, "percentage": 78.37, "elapsed_time": "1:27:34", "remaining_time": "0:24:10", "throughput": 1033.54, "total_tokens": 5430720} {"current_steps": 60315, "total_steps": 76960, "loss": 0.086, "lr": 6.793367573997192e-06, "epoch": 15.674376299376299, "percentage": 78.37, "elapsed_time": "1:27:34", "remaining_time": "0:24:10", "throughput": 1033.54, "total_tokens": 5431184} {"current_steps": 60320, "total_steps": 76960, "loss": 0.0257, "lr": 6.789482692870158e-06, "epoch": 15.675675675675675, "percentage": 78.38, "elapsed_time": "1:27:35", "remaining_time": "0:24:09", "throughput": 1033.55, "total_tokens": 5431664} {"current_steps": 60325, "total_steps": 76960, "loss": 0.2225, "lr": 6.785598748327474e-06, "epoch": 15.676975051975052, "percentage": 78.38, "elapsed_time": "1:27:35", "remaining_time": "0:24:09", "throughput": 1033.55, "total_tokens": 5432096} {"current_steps": 60330, "total_steps": 76960, "loss": 0.2055, "lr": 6.781715740568903e-06, "epoch": 15.678274428274428, "percentage": 78.39, "elapsed_time": "1:27:36", "remaining_time": "0:24:08", "throughput": 1033.55, "total_tokens": 5432512} {"current_steps": 60335, "total_steps": 76960, "loss": 0.0125, "lr": 6.77783366979414e-06, "epoch": 15.679573804573804, "percentage": 78.4, "elapsed_time": "1:27:36", "remaining_time": "0:24:08", "throughput": 1033.56, "total_tokens": 5432992} {"current_steps": 60340, "total_steps": 76960, "loss": 0.1522, "lr": 6.77395253620286e-06, "epoch": 15.680873180873181, "percentage": 78.4, "elapsed_time": "1:27:36", "remaining_time": "0:24:07", "throughput": 1033.56, "total_tokens": 5433408} {"current_steps": 60345, "total_steps": 76960, "loss": 0.2124, "lr": 6.770072339994657e-06, "epoch": 15.682172557172557, "percentage": 78.41, "elapsed_time": "1:27:37", "remaining_time": "0:24:07", "throughput": 1033.57, "total_tokens": 5433904} {"current_steps": 60350, "total_steps": 76960, "loss": 0.3169, "lr": 6.766193081369099e-06, "epoch": 15.683471933471933, "percentage": 78.42, "elapsed_time": "1:27:37", "remaining_time": "0:24:07", "throughput": 1033.57, "total_tokens": 5434336} {"current_steps": 60355, "total_steps": 76960, "loss": 0.0211, "lr": 6.762314760525704e-06, "epoch": 15.68477130977131, "percentage": 78.42, "elapsed_time": "1:27:38", "remaining_time": "0:24:06", "throughput": 1033.57, "total_tokens": 5434768} {"current_steps": 60360, "total_steps": 76960, "loss": 0.024, "lr": 6.75843737766394e-06, "epoch": 15.686070686070686, "percentage": 78.43, "elapsed_time": "1:27:38", "remaining_time": "0:24:06", "throughput": 1033.59, "total_tokens": 5435280} {"current_steps": 60365, "total_steps": 76960, "loss": 0.6248, "lr": 6.754560932983223e-06, "epoch": 15.687370062370062, "percentage": 78.44, "elapsed_time": "1:27:39", "remaining_time": "0:24:05", "throughput": 1033.6, "total_tokens": 5435776} {"current_steps": 60370, "total_steps": 76960, "loss": 0.4857, "lr": 6.750685426682909e-06, "epoch": 15.68866943866944, "percentage": 78.44, "elapsed_time": "1:27:39", "remaining_time": "0:24:05", "throughput": 1033.6, "total_tokens": 5436224} {"current_steps": 60375, "total_steps": 76960, "loss": 0.2416, "lr": 6.746810858962338e-06, "epoch": 15.689968814968815, "percentage": 78.45, "elapsed_time": "1:27:39", "remaining_time": "0:24:04", "throughput": 1033.61, "total_tokens": 5436672} {"current_steps": 60380, "total_steps": 76960, "loss": 0.2761, "lr": 6.742937230020757e-06, "epoch": 15.691268191268192, "percentage": 78.46, "elapsed_time": "1:27:40", "remaining_time": "0:24:04", "throughput": 1033.62, "total_tokens": 5437152} {"current_steps": 60385, "total_steps": 76960, "loss": 0.1713, "lr": 6.739064540057424e-06, "epoch": 15.692567567567568, "percentage": 78.46, "elapsed_time": "1:27:40", "remaining_time": "0:24:04", "throughput": 1033.62, "total_tokens": 5437616} {"current_steps": 60390, "total_steps": 76960, "loss": 0.0082, "lr": 6.735192789271491e-06, "epoch": 15.693866943866944, "percentage": 78.47, "elapsed_time": "1:27:41", "remaining_time": "0:24:03", "throughput": 1033.62, "total_tokens": 5438048} {"current_steps": 60395, "total_steps": 76960, "loss": 0.2082, "lr": 6.7313219778621015e-06, "epoch": 15.69516632016632, "percentage": 78.48, "elapsed_time": "1:27:41", "remaining_time": "0:24:03", "throughput": 1033.62, "total_tokens": 5438464} {"current_steps": 60400, "total_steps": 76960, "loss": 0.0297, "lr": 6.727452106028317e-06, "epoch": 15.696465696465696, "percentage": 78.48, "elapsed_time": "1:27:41", "remaining_time": "0:24:02", "throughput": 1033.63, "total_tokens": 5438928} {"current_steps": 60405, "total_steps": 76960, "loss": 0.2224, "lr": 6.723583173969189e-06, "epoch": 15.697765072765073, "percentage": 78.49, "elapsed_time": "1:27:42", "remaining_time": "0:24:02", "throughput": 1033.63, "total_tokens": 5439376} {"current_steps": 60410, "total_steps": 76960, "loss": 0.254, "lr": 6.719715181883682e-06, "epoch": 15.69906444906445, "percentage": 78.5, "elapsed_time": "1:27:42", "remaining_time": "0:24:01", "throughput": 1033.63, "total_tokens": 5439808} {"current_steps": 60415, "total_steps": 76960, "loss": 0.1477, "lr": 6.715848129970737e-06, "epoch": 15.700363825363825, "percentage": 78.5, "elapsed_time": "1:27:43", "remaining_time": "0:24:01", "throughput": 1033.64, "total_tokens": 5440304} {"current_steps": 60420, "total_steps": 76960, "loss": 0.1855, "lr": 6.711982018429242e-06, "epoch": 15.701663201663202, "percentage": 78.51, "elapsed_time": "1:27:43", "remaining_time": "0:24:00", "throughput": 1033.65, "total_tokens": 5440752} {"current_steps": 60425, "total_steps": 76960, "loss": 0.1574, "lr": 6.708116847458043e-06, "epoch": 15.702962577962579, "percentage": 78.51, "elapsed_time": "1:27:44", "remaining_time": "0:24:00", "throughput": 1033.64, "total_tokens": 5441168} {"current_steps": 60430, "total_steps": 76960, "loss": 0.2309, "lr": 6.704252617255918e-06, "epoch": 15.704261954261954, "percentage": 78.52, "elapsed_time": "1:27:44", "remaining_time": "0:24:00", "throughput": 1033.65, "total_tokens": 5441648} {"current_steps": 60435, "total_steps": 76960, "loss": 0.3464, "lr": 6.700389328021608e-06, "epoch": 15.70556133056133, "percentage": 78.53, "elapsed_time": "1:27:44", "remaining_time": "0:23:59", "throughput": 1033.66, "total_tokens": 5442112} {"current_steps": 60440, "total_steps": 76960, "loss": 0.0569, "lr": 6.696526979953812e-06, "epoch": 15.706860706860708, "percentage": 78.53, "elapsed_time": "1:27:45", "remaining_time": "0:23:59", "throughput": 1033.66, "total_tokens": 5442560} {"current_steps": 60445, "total_steps": 76960, "loss": 0.4986, "lr": 6.692665573251167e-06, "epoch": 15.708160083160083, "percentage": 78.54, "elapsed_time": "1:27:45", "remaining_time": "0:23:58", "throughput": 1033.66, "total_tokens": 5442992} {"current_steps": 60450, "total_steps": 76960, "loss": 0.0888, "lr": 6.688805108112273e-06, "epoch": 15.70945945945946, "percentage": 78.55, "elapsed_time": "1:27:46", "remaining_time": "0:23:58", "throughput": 1033.67, "total_tokens": 5443456} {"current_steps": 60455, "total_steps": 76960, "loss": 0.1443, "lr": 6.684945584735675e-06, "epoch": 15.710758835758837, "percentage": 78.55, "elapsed_time": "1:27:46", "remaining_time": "0:23:57", "throughput": 1033.67, "total_tokens": 5443904} {"current_steps": 60460, "total_steps": 76960, "loss": 0.0441, "lr": 6.68108700331988e-06, "epoch": 15.712058212058212, "percentage": 78.56, "elapsed_time": "1:27:46", "remaining_time": "0:23:57", "throughput": 1033.68, "total_tokens": 5444352} {"current_steps": 60465, "total_steps": 76960, "loss": 0.0081, "lr": 6.677229364063328e-06, "epoch": 15.713357588357589, "percentage": 78.57, "elapsed_time": "1:27:47", "remaining_time": "0:23:56", "throughput": 1033.68, "total_tokens": 5444800} {"current_steps": 60470, "total_steps": 76960, "loss": 0.3573, "lr": 6.673372667164435e-06, "epoch": 15.714656964656964, "percentage": 78.57, "elapsed_time": "1:27:47", "remaining_time": "0:23:56", "throughput": 1033.69, "total_tokens": 5445280} {"current_steps": 60475, "total_steps": 76960, "loss": 0.0977, "lr": 6.669516912821535e-06, "epoch": 15.71595634095634, "percentage": 78.58, "elapsed_time": "1:27:48", "remaining_time": "0:23:56", "throughput": 1033.69, "total_tokens": 5445712} {"current_steps": 60480, "total_steps": 76960, "loss": 0.5308, "lr": 6.665662101232953e-06, "epoch": 15.717255717255718, "percentage": 78.59, "elapsed_time": "1:27:48", "remaining_time": "0:23:55", "throughput": 1033.7, "total_tokens": 5446176} {"current_steps": 60485, "total_steps": 76960, "loss": 0.1599, "lr": 6.6618082325969275e-06, "epoch": 15.718555093555093, "percentage": 78.59, "elapsed_time": "1:27:49", "remaining_time": "0:23:55", "throughput": 1033.7, "total_tokens": 5446640} {"current_steps": 60490, "total_steps": 76960, "loss": 0.2964, "lr": 6.657955307111674e-06, "epoch": 15.71985446985447, "percentage": 78.6, "elapsed_time": "1:27:49", "remaining_time": "0:23:54", "throughput": 1033.7, "total_tokens": 5447056} {"current_steps": 60495, "total_steps": 76960, "loss": 0.4231, "lr": 6.654103324975355e-06, "epoch": 15.721153846153847, "percentage": 78.61, "elapsed_time": "1:27:49", "remaining_time": "0:23:54", "throughput": 1033.7, "total_tokens": 5447472} {"current_steps": 60500, "total_steps": 76960, "loss": 0.2765, "lr": 6.650252286386088e-06, "epoch": 15.722453222453222, "percentage": 78.61, "elapsed_time": "1:27:50", "remaining_time": "0:23:53", "throughput": 1033.7, "total_tokens": 5447920} {"current_steps": 60505, "total_steps": 76960, "loss": 0.0672, "lr": 6.646402191541929e-06, "epoch": 15.723752598752599, "percentage": 78.62, "elapsed_time": "1:27:50", "remaining_time": "0:23:53", "throughput": 1033.71, "total_tokens": 5448384} {"current_steps": 60510, "total_steps": 76960, "loss": 0.0167, "lr": 6.642553040640881e-06, "epoch": 15.725051975051976, "percentage": 78.63, "elapsed_time": "1:27:51", "remaining_time": "0:23:52", "throughput": 1033.71, "total_tokens": 5448800} {"current_steps": 60515, "total_steps": 76960, "loss": 0.2582, "lr": 6.638704833880929e-06, "epoch": 15.72635135135135, "percentage": 78.63, "elapsed_time": "1:27:51", "remaining_time": "0:23:52", "throughput": 1033.71, "total_tokens": 5449232} {"current_steps": 60520, "total_steps": 76960, "loss": 0.2891, "lr": 6.634857571459971e-06, "epoch": 15.727650727650728, "percentage": 78.64, "elapsed_time": "1:27:51", "remaining_time": "0:23:52", "throughput": 1033.71, "total_tokens": 5449696} {"current_steps": 60525, "total_steps": 76960, "loss": 0.0235, "lr": 6.6310112535758864e-06, "epoch": 15.728950103950105, "percentage": 78.64, "elapsed_time": "1:27:52", "remaining_time": "0:23:51", "throughput": 1033.73, "total_tokens": 5450192} {"current_steps": 60530, "total_steps": 76960, "loss": 0.1812, "lr": 6.627165880426492e-06, "epoch": 15.73024948024948, "percentage": 78.65, "elapsed_time": "1:27:52", "remaining_time": "0:23:51", "throughput": 1033.73, "total_tokens": 5450656} {"current_steps": 60535, "total_steps": 76960, "loss": 0.0368, "lr": 6.623321452209569e-06, "epoch": 15.731548856548857, "percentage": 78.66, "elapsed_time": "1:27:53", "remaining_time": "0:23:50", "throughput": 1033.73, "total_tokens": 5451072} {"current_steps": 60540, "total_steps": 76960, "loss": 0.1653, "lr": 6.619477969122822e-06, "epoch": 15.732848232848234, "percentage": 78.66, "elapsed_time": "1:27:53", "remaining_time": "0:23:50", "throughput": 1033.74, "total_tokens": 5451552} {"current_steps": 60545, "total_steps": 76960, "loss": 0.115, "lr": 6.615635431363942e-06, "epoch": 15.734147609147609, "percentage": 78.67, "elapsed_time": "1:27:54", "remaining_time": "0:23:49", "throughput": 1033.74, "total_tokens": 5451984} {"current_steps": 60550, "total_steps": 76960, "loss": 0.2887, "lr": 6.611793839130542e-06, "epoch": 15.735446985446986, "percentage": 78.68, "elapsed_time": "1:27:54", "remaining_time": "0:23:49", "throughput": 1033.74, "total_tokens": 5452432} {"current_steps": 60555, "total_steps": 76960, "loss": 0.0323, "lr": 6.607953192620209e-06, "epoch": 15.736746361746361, "percentage": 78.68, "elapsed_time": "1:27:54", "remaining_time": "0:23:49", "throughput": 1033.74, "total_tokens": 5452864} {"current_steps": 60560, "total_steps": 76960, "loss": 0.3132, "lr": 6.604113492030459e-06, "epoch": 15.738045738045738, "percentage": 78.69, "elapsed_time": "1:27:55", "remaining_time": "0:23:48", "throughput": 1033.76, "total_tokens": 5453360} {"current_steps": 60565, "total_steps": 76960, "loss": 0.3767, "lr": 6.600274737558779e-06, "epoch": 15.739345114345115, "percentage": 78.7, "elapsed_time": "1:27:55", "remaining_time": "0:23:48", "throughput": 1033.76, "total_tokens": 5453808} {"current_steps": 60570, "total_steps": 76960, "loss": 0.2029, "lr": 6.5964369294026054e-06, "epoch": 15.74064449064449, "percentage": 78.7, "elapsed_time": "1:27:56", "remaining_time": "0:23:47", "throughput": 1033.76, "total_tokens": 5454272} {"current_steps": 60575, "total_steps": 76960, "loss": 0.2818, "lr": 6.5926000677593055e-06, "epoch": 15.741943866943867, "percentage": 78.71, "elapsed_time": "1:27:56", "remaining_time": "0:23:47", "throughput": 1033.77, "total_tokens": 5454720} {"current_steps": 60580, "total_steps": 76960, "loss": 0.1771, "lr": 6.58876415282623e-06, "epoch": 15.743243243243244, "percentage": 78.72, "elapsed_time": "1:27:56", "remaining_time": "0:23:46", "throughput": 1033.77, "total_tokens": 5455168} {"current_steps": 60585, "total_steps": 76960, "loss": 0.1381, "lr": 6.5849291848006454e-06, "epoch": 15.744542619542619, "percentage": 78.72, "elapsed_time": "1:27:57", "remaining_time": "0:23:46", "throughput": 1033.77, "total_tokens": 5455568} {"current_steps": 60590, "total_steps": 76960, "loss": 0.2072, "lr": 6.581095163879808e-06, "epoch": 15.745841995841996, "percentage": 78.73, "elapsed_time": "1:27:57", "remaining_time": "0:23:45", "throughput": 1033.77, "total_tokens": 5456016} {"current_steps": 60595, "total_steps": 76960, "loss": 0.0209, "lr": 6.577262090260885e-06, "epoch": 15.747141372141373, "percentage": 78.74, "elapsed_time": "1:27:58", "remaining_time": "0:23:45", "throughput": 1033.77, "total_tokens": 5456432} {"current_steps": 60600, "total_steps": 76960, "loss": 0.4554, "lr": 6.573429964141025e-06, "epoch": 15.748440748440748, "percentage": 78.74, "elapsed_time": "1:27:58", "remaining_time": "0:23:45", "throughput": 1033.77, "total_tokens": 5456864} {"current_steps": 60605, "total_steps": 76960, "loss": 0.0561, "lr": 6.569598785717318e-06, "epoch": 15.749740124740125, "percentage": 78.75, "elapsed_time": "1:27:59", "remaining_time": "0:23:44", "throughput": 1033.77, "total_tokens": 5457296} {"current_steps": 60610, "total_steps": 76960, "loss": 0.1262, "lr": 6.56576855518681e-06, "epoch": 15.7510395010395, "percentage": 78.76, "elapsed_time": "1:27:59", "remaining_time": "0:23:44", "throughput": 1033.77, "total_tokens": 5457760} {"current_steps": 60615, "total_steps": 76960, "loss": 0.1916, "lr": 6.561939272746484e-06, "epoch": 15.752338877338877, "percentage": 78.76, "elapsed_time": "1:27:59", "remaining_time": "0:23:43", "throughput": 1033.78, "total_tokens": 5458224} {"current_steps": 60620, "total_steps": 76960, "loss": 0.2302, "lr": 6.558110938593293e-06, "epoch": 15.753638253638254, "percentage": 78.77, "elapsed_time": "1:28:00", "remaining_time": "0:23:43", "throughput": 1033.78, "total_tokens": 5458656} {"current_steps": 60625, "total_steps": 76960, "loss": 0.6017, "lr": 6.554283552924118e-06, "epoch": 15.75493762993763, "percentage": 78.77, "elapsed_time": "1:28:00", "remaining_time": "0:23:42", "throughput": 1033.78, "total_tokens": 5459104} {"current_steps": 60630, "total_steps": 76960, "loss": 0.1722, "lr": 6.550457115935815e-06, "epoch": 15.756237006237006, "percentage": 78.78, "elapsed_time": "1:28:01", "remaining_time": "0:23:42", "throughput": 1033.8, "total_tokens": 5459616} {"current_steps": 60635, "total_steps": 76960, "loss": 0.105, "lr": 6.5466316278251894e-06, "epoch": 15.757536382536383, "percentage": 78.79, "elapsed_time": "1:28:01", "remaining_time": "0:23:41", "throughput": 1033.8, "total_tokens": 5460048} {"current_steps": 60640, "total_steps": 76960, "loss": 0.0573, "lr": 6.5428070887889686e-06, "epoch": 15.758835758835758, "percentage": 78.79, "elapsed_time": "1:28:01", "remaining_time": "0:23:41", "throughput": 1033.8, "total_tokens": 5460496} {"current_steps": 60645, "total_steps": 76960, "loss": 0.197, "lr": 6.538983499023876e-06, "epoch": 15.760135135135135, "percentage": 78.8, "elapsed_time": "1:28:02", "remaining_time": "0:23:41", "throughput": 1033.8, "total_tokens": 5460928} {"current_steps": 60650, "total_steps": 76960, "loss": 0.0019, "lr": 6.5351608587265415e-06, "epoch": 15.761434511434512, "percentage": 78.81, "elapsed_time": "1:28:02", "remaining_time": "0:23:40", "throughput": 1033.8, "total_tokens": 5461376} {"current_steps": 60655, "total_steps": 76960, "loss": 0.0518, "lr": 6.531339168093581e-06, "epoch": 15.762733887733887, "percentage": 78.81, "elapsed_time": "1:28:03", "remaining_time": "0:23:40", "throughput": 1033.8, "total_tokens": 5461792} {"current_steps": 60660, "total_steps": 76960, "loss": 0.0234, "lr": 6.527518427321539e-06, "epoch": 15.764033264033264, "percentage": 78.82, "elapsed_time": "1:28:03", "remaining_time": "0:23:39", "throughput": 1033.8, "total_tokens": 5462208} {"current_steps": 60665, "total_steps": 76960, "loss": 0.1827, "lr": 6.523698636606923e-06, "epoch": 15.765332640332641, "percentage": 78.83, "elapsed_time": "1:28:04", "remaining_time": "0:23:39", "throughput": 1033.81, "total_tokens": 5462672} {"current_steps": 60670, "total_steps": 76960, "loss": 0.0514, "lr": 6.519879796146189e-06, "epoch": 15.766632016632016, "percentage": 78.83, "elapsed_time": "1:28:04", "remaining_time": "0:23:38", "throughput": 1033.81, "total_tokens": 5463136} {"current_steps": 60675, "total_steps": 76960, "loss": 0.0595, "lr": 6.5160619061357504e-06, "epoch": 15.767931392931393, "percentage": 78.84, "elapsed_time": "1:28:04", "remaining_time": "0:23:38", "throughput": 1033.81, "total_tokens": 5463568} {"current_steps": 60680, "total_steps": 76960, "loss": 0.1215, "lr": 6.512244966771952e-06, "epoch": 15.76923076923077, "percentage": 78.85, "elapsed_time": "1:28:05", "remaining_time": "0:23:38", "throughput": 1033.82, "total_tokens": 5464032} {"current_steps": 60685, "total_steps": 76960, "loss": 0.4947, "lr": 6.508428978251116e-06, "epoch": 15.770530145530145, "percentage": 78.85, "elapsed_time": "1:28:05", "remaining_time": "0:23:37", "throughput": 1033.82, "total_tokens": 5464496} {"current_steps": 60690, "total_steps": 76960, "loss": 0.3005, "lr": 6.504613940769486e-06, "epoch": 15.771829521829522, "percentage": 78.86, "elapsed_time": "1:28:06", "remaining_time": "0:23:37", "throughput": 1033.83, "total_tokens": 5464976} {"current_steps": 60695, "total_steps": 76960, "loss": 0.1659, "lr": 6.500799854523293e-06, "epoch": 15.773128898128899, "percentage": 78.87, "elapsed_time": "1:28:06", "remaining_time": "0:23:36", "throughput": 1033.84, "total_tokens": 5465456} {"current_steps": 60700, "total_steps": 76960, "loss": 0.0112, "lr": 6.496986719708681e-06, "epoch": 15.774428274428274, "percentage": 78.87, "elapsed_time": "1:28:06", "remaining_time": "0:23:36", "throughput": 1033.84, "total_tokens": 5465872} {"current_steps": 60705, "total_steps": 76960, "loss": 0.6038, "lr": 6.493174536521768e-06, "epoch": 15.775727650727651, "percentage": 78.88, "elapsed_time": "1:28:07", "remaining_time": "0:23:35", "throughput": 1033.84, "total_tokens": 5466320} {"current_steps": 60710, "total_steps": 76960, "loss": 0.1257, "lr": 6.48936330515863e-06, "epoch": 15.777027027027026, "percentage": 78.89, "elapsed_time": "1:28:07", "remaining_time": "0:23:35", "throughput": 1033.84, "total_tokens": 5466736} {"current_steps": 60715, "total_steps": 76960, "loss": 0.0064, "lr": 6.485553025815266e-06, "epoch": 15.778326403326403, "percentage": 78.89, "elapsed_time": "1:28:08", "remaining_time": "0:23:34", "throughput": 1033.85, "total_tokens": 5467216} {"current_steps": 60720, "total_steps": 76960, "loss": 0.2134, "lr": 6.481743698687659e-06, "epoch": 15.77962577962578, "percentage": 78.9, "elapsed_time": "1:28:08", "remaining_time": "0:23:34", "throughput": 1033.85, "total_tokens": 5467648} {"current_steps": 60725, "total_steps": 76960, "loss": 0.4616, "lr": 6.477935323971707e-06, "epoch": 15.780925155925155, "percentage": 78.9, "elapsed_time": "1:28:09", "remaining_time": "0:23:34", "throughput": 1033.85, "total_tokens": 5468080} {"current_steps": 60730, "total_steps": 76960, "loss": 0.3035, "lr": 6.4741279018632975e-06, "epoch": 15.782224532224532, "percentage": 78.91, "elapsed_time": "1:28:09", "remaining_time": "0:23:33", "throughput": 1033.86, "total_tokens": 5468544} {"current_steps": 60735, "total_steps": 76960, "loss": 0.195, "lr": 6.47032143255823e-06, "epoch": 15.78352390852391, "percentage": 78.92, "elapsed_time": "1:28:09", "remaining_time": "0:23:33", "throughput": 1033.86, "total_tokens": 5468976} {"current_steps": 60740, "total_steps": 76960, "loss": 0.0472, "lr": 6.466515916252288e-06, "epoch": 15.784823284823284, "percentage": 78.92, "elapsed_time": "1:28:10", "remaining_time": "0:23:32", "throughput": 1033.86, "total_tokens": 5469408} {"current_steps": 60745, "total_steps": 76960, "loss": 0.2767, "lr": 6.46271135314119e-06, "epoch": 15.786122661122661, "percentage": 78.93, "elapsed_time": "1:28:10", "remaining_time": "0:23:32", "throughput": 1033.86, "total_tokens": 5469856} {"current_steps": 60750, "total_steps": 76960, "loss": 0.0909, "lr": 6.4589077434206145e-06, "epoch": 15.787422037422038, "percentage": 78.94, "elapsed_time": "1:28:11", "remaining_time": "0:23:31", "throughput": 1033.86, "total_tokens": 5470288} {"current_steps": 60755, "total_steps": 76960, "loss": 0.3099, "lr": 6.455105087286173e-06, "epoch": 15.788721413721413, "percentage": 78.94, "elapsed_time": "1:28:11", "remaining_time": "0:23:31", "throughput": 1033.86, "total_tokens": 5470720} {"current_steps": 60760, "total_steps": 76960, "loss": 0.0991, "lr": 6.451303384933455e-06, "epoch": 15.79002079002079, "percentage": 78.95, "elapsed_time": "1:28:11", "remaining_time": "0:23:30", "throughput": 1033.87, "total_tokens": 5471184} {"current_steps": 60765, "total_steps": 76960, "loss": 0.0472, "lr": 6.447502636557972e-06, "epoch": 15.791320166320165, "percentage": 78.96, "elapsed_time": "1:28:12", "remaining_time": "0:23:30", "throughput": 1033.86, "total_tokens": 5471584} {"current_steps": 60770, "total_steps": 76960, "loss": 0.3414, "lr": 6.443702842355201e-06, "epoch": 15.792619542619542, "percentage": 78.96, "elapsed_time": "1:28:12", "remaining_time": "0:23:30", "throughput": 1033.86, "total_tokens": 5472016} {"current_steps": 60775, "total_steps": 76960, "loss": 0.0364, "lr": 6.439904002520572e-06, "epoch": 15.79391891891892, "percentage": 78.97, "elapsed_time": "1:28:13", "remaining_time": "0:23:29", "throughput": 1033.88, "total_tokens": 5472528} {"current_steps": 60780, "total_steps": 76960, "loss": 0.0847, "lr": 6.436106117249463e-06, "epoch": 15.795218295218294, "percentage": 78.98, "elapsed_time": "1:28:13", "remaining_time": "0:23:29", "throughput": 1033.89, "total_tokens": 5472992} {"current_steps": 60785, "total_steps": 76960, "loss": 0.3298, "lr": 6.4323091867372095e-06, "epoch": 15.796517671517671, "percentage": 78.98, "elapsed_time": "1:28:14", "remaining_time": "0:23:28", "throughput": 1033.9, "total_tokens": 5473472} {"current_steps": 60790, "total_steps": 76960, "loss": 0.0603, "lr": 6.42851321117908e-06, "epoch": 15.797817047817048, "percentage": 78.99, "elapsed_time": "1:28:14", "remaining_time": "0:23:28", "throughput": 1033.91, "total_tokens": 5473952} {"current_steps": 60795, "total_steps": 76960, "loss": 0.2234, "lr": 6.424718190770315e-06, "epoch": 15.799116424116423, "percentage": 79.0, "elapsed_time": "1:28:14", "remaining_time": "0:23:27", "throughput": 1033.9, "total_tokens": 5474368} {"current_steps": 60800, "total_steps": 76960, "loss": 0.123, "lr": 6.4209241257060875e-06, "epoch": 15.8004158004158, "percentage": 79.0, "elapsed_time": "1:28:15", "remaining_time": "0:23:27", "throughput": 1033.9, "total_tokens": 5474768} {"current_steps": 60805, "total_steps": 76960, "loss": 0.3482, "lr": 6.417131016181538e-06, "epoch": 15.801715176715177, "percentage": 79.01, "elapsed_time": "1:28:15", "remaining_time": "0:23:26", "throughput": 1033.9, "total_tokens": 5475216} {"current_steps": 60810, "total_steps": 76960, "loss": 0.2091, "lr": 6.413338862391741e-06, "epoch": 15.803014553014552, "percentage": 79.02, "elapsed_time": "1:28:16", "remaining_time": "0:23:26", "throughput": 1033.89, "total_tokens": 5475616} {"current_steps": 60815, "total_steps": 76960, "loss": 0.3753, "lr": 6.4095476645317346e-06, "epoch": 15.80431392931393, "percentage": 79.02, "elapsed_time": "1:28:16", "remaining_time": "0:23:26", "throughput": 1033.89, "total_tokens": 5476048} {"current_steps": 60820, "total_steps": 76960, "loss": 0.1982, "lr": 6.405757422796502e-06, "epoch": 15.805613305613306, "percentage": 79.03, "elapsed_time": "1:28:16", "remaining_time": "0:23:25", "throughput": 1033.9, "total_tokens": 5476496} {"current_steps": 60825, "total_steps": 76960, "loss": 0.1753, "lr": 6.401968137380993e-06, "epoch": 15.806912681912682, "percentage": 79.03, "elapsed_time": "1:28:17", "remaining_time": "0:23:25", "throughput": 1033.9, "total_tokens": 5476960} {"current_steps": 60830, "total_steps": 76960, "loss": 0.2261, "lr": 6.398179808480078e-06, "epoch": 15.808212058212058, "percentage": 79.04, "elapsed_time": "1:28:17", "remaining_time": "0:23:24", "throughput": 1033.9, "total_tokens": 5477392} {"current_steps": 60835, "total_steps": 76960, "loss": 0.3363, "lr": 6.394392436288593e-06, "epoch": 15.809511434511435, "percentage": 79.05, "elapsed_time": "1:28:18", "remaining_time": "0:23:24", "throughput": 1033.91, "total_tokens": 5477856} {"current_steps": 60840, "total_steps": 76960, "loss": 0.378, "lr": 6.390606021001342e-06, "epoch": 15.81081081081081, "percentage": 79.05, "elapsed_time": "1:28:18", "remaining_time": "0:23:23", "throughput": 1033.92, "total_tokens": 5478320} {"current_steps": 60845, "total_steps": 76960, "loss": 0.3512, "lr": 6.386820562813043e-06, "epoch": 15.812110187110187, "percentage": 79.06, "elapsed_time": "1:28:19", "remaining_time": "0:23:23", "throughput": 1033.91, "total_tokens": 5478736} {"current_steps": 60850, "total_steps": 76960, "loss": 0.1263, "lr": 6.383036061918399e-06, "epoch": 15.813409563409563, "percentage": 79.07, "elapsed_time": "1:28:19", "remaining_time": "0:23:23", "throughput": 1033.91, "total_tokens": 5479168} {"current_steps": 60855, "total_steps": 76960, "loss": 0.2623, "lr": 6.379252518512047e-06, "epoch": 15.81470893970894, "percentage": 79.07, "elapsed_time": "1:28:19", "remaining_time": "0:23:22", "throughput": 1033.92, "total_tokens": 5479632} {"current_steps": 60860, "total_steps": 76960, "loss": 0.2011, "lr": 6.375469932788586e-06, "epoch": 15.816008316008316, "percentage": 79.08, "elapsed_time": "1:28:20", "remaining_time": "0:23:22", "throughput": 1033.92, "total_tokens": 5480080} {"current_steps": 60865, "total_steps": 76960, "loss": 0.2483, "lr": 6.371688304942544e-06, "epoch": 15.817307692307692, "percentage": 79.09, "elapsed_time": "1:28:20", "remaining_time": "0:23:21", "throughput": 1033.94, "total_tokens": 5480576} {"current_steps": 60870, "total_steps": 76960, "loss": 0.2404, "lr": 6.367907635168433e-06, "epoch": 15.818607068607069, "percentage": 79.09, "elapsed_time": "1:28:21", "remaining_time": "0:23:21", "throughput": 1033.94, "total_tokens": 5481040} {"current_steps": 60875, "total_steps": 76960, "loss": 0.0525, "lr": 6.364127923660673e-06, "epoch": 15.819906444906445, "percentage": 79.1, "elapsed_time": "1:28:21", "remaining_time": "0:23:20", "throughput": 1033.95, "total_tokens": 5481488} {"current_steps": 60880, "total_steps": 76960, "loss": 0.1589, "lr": 6.360349170613672e-06, "epoch": 15.82120582120582, "percentage": 79.11, "elapsed_time": "1:28:21", "remaining_time": "0:23:20", "throughput": 1033.95, "total_tokens": 5481952} {"current_steps": 60885, "total_steps": 76960, "loss": 0.0781, "lr": 6.356571376221771e-06, "epoch": 15.822505197505198, "percentage": 79.11, "elapsed_time": "1:28:22", "remaining_time": "0:23:19", "throughput": 1033.96, "total_tokens": 5482432} {"current_steps": 60890, "total_steps": 76960, "loss": 0.1667, "lr": 6.352794540679274e-06, "epoch": 15.823804573804575, "percentage": 79.12, "elapsed_time": "1:28:22", "remaining_time": "0:23:19", "throughput": 1033.97, "total_tokens": 5482880} {"current_steps": 60895, "total_steps": 76960, "loss": 0.2294, "lr": 6.349018664180425e-06, "epoch": 15.82510395010395, "percentage": 79.13, "elapsed_time": "1:28:23", "remaining_time": "0:23:19", "throughput": 1033.97, "total_tokens": 5483344} {"current_steps": 60900, "total_steps": 76960, "loss": 0.0202, "lr": 6.345243746919405e-06, "epoch": 15.826403326403327, "percentage": 79.13, "elapsed_time": "1:28:23", "remaining_time": "0:23:18", "throughput": 1033.99, "total_tokens": 5483840} {"current_steps": 60905, "total_steps": 76960, "loss": 0.0044, "lr": 6.341469789090385e-06, "epoch": 15.827702702702704, "percentage": 79.14, "elapsed_time": "1:28:24", "remaining_time": "0:23:18", "throughput": 1034.0, "total_tokens": 5484336} {"current_steps": 60910, "total_steps": 76960, "loss": 0.5615, "lr": 6.3376967908874406e-06, "epoch": 15.829002079002079, "percentage": 79.15, "elapsed_time": "1:28:24", "remaining_time": "0:23:17", "throughput": 1034.0, "total_tokens": 5484784} {"current_steps": 60915, "total_steps": 76960, "loss": 0.1194, "lr": 6.3339247525046305e-06, "epoch": 15.830301455301456, "percentage": 79.15, "elapsed_time": "1:28:24", "remaining_time": "0:23:17", "throughput": 1034.01, "total_tokens": 5485248} {"current_steps": 60920, "total_steps": 76960, "loss": 0.6774, "lr": 6.3301536741359575e-06, "epoch": 15.83160083160083, "percentage": 79.16, "elapsed_time": "1:28:25", "remaining_time": "0:23:16", "throughput": 1034.02, "total_tokens": 5485728} {"current_steps": 60925, "total_steps": 76960, "loss": 0.0709, "lr": 6.326383555975376e-06, "epoch": 15.832900207900208, "percentage": 79.16, "elapsed_time": "1:28:25", "remaining_time": "0:23:16", "throughput": 1034.02, "total_tokens": 5486192} {"current_steps": 60930, "total_steps": 76960, "loss": 0.2718, "lr": 6.322614398216775e-06, "epoch": 15.834199584199585, "percentage": 79.17, "elapsed_time": "1:28:26", "remaining_time": "0:23:15", "throughput": 1034.03, "total_tokens": 5486640} {"current_steps": 60935, "total_steps": 76960, "loss": 0.2159, "lr": 6.318846201054018e-06, "epoch": 15.83549896049896, "percentage": 79.18, "elapsed_time": "1:28:26", "remaining_time": "0:23:15", "throughput": 1034.03, "total_tokens": 5487104} {"current_steps": 60940, "total_steps": 76960, "loss": 0.3473, "lr": 6.315078964680893e-06, "epoch": 15.836798336798337, "percentage": 79.18, "elapsed_time": "1:28:26", "remaining_time": "0:23:15", "throughput": 1034.04, "total_tokens": 5487568} {"current_steps": 60945, "total_steps": 76960, "loss": 0.1447, "lr": 6.311312689291166e-06, "epoch": 15.838097713097714, "percentage": 79.19, "elapsed_time": "1:28:27", "remaining_time": "0:23:14", "throughput": 1034.04, "total_tokens": 5488016} {"current_steps": 60950, "total_steps": 76960, "loss": 0.4063, "lr": 6.3075473750785265e-06, "epoch": 15.839397089397089, "percentage": 79.2, "elapsed_time": "1:28:27", "remaining_time": "0:23:14", "throughput": 1034.05, "total_tokens": 5488464} {"current_steps": 60955, "total_steps": 76960, "loss": 0.1675, "lr": 6.303783022236637e-06, "epoch": 15.840696465696466, "percentage": 79.2, "elapsed_time": "1:28:28", "remaining_time": "0:23:13", "throughput": 1034.05, "total_tokens": 5488896} {"current_steps": 60960, "total_steps": 76960, "loss": 0.3327, "lr": 6.300019630959109e-06, "epoch": 15.841995841995843, "percentage": 79.21, "elapsed_time": "1:28:28", "remaining_time": "0:23:13", "throughput": 1034.05, "total_tokens": 5489328} {"current_steps": 60965, "total_steps": 76960, "loss": 0.4821, "lr": 6.296257201439479e-06, "epoch": 15.843295218295218, "percentage": 79.22, "elapsed_time": "1:28:29", "remaining_time": "0:23:12", "throughput": 1034.05, "total_tokens": 5489760} {"current_steps": 60970, "total_steps": 76960, "loss": 0.2778, "lr": 6.29249573387127e-06, "epoch": 15.844594594594595, "percentage": 79.22, "elapsed_time": "1:28:29", "remaining_time": "0:23:12", "throughput": 1034.05, "total_tokens": 5490224} {"current_steps": 60975, "total_steps": 76960, "loss": 0.179, "lr": 6.288735228447923e-06, "epoch": 15.845893970893972, "percentage": 79.23, "elapsed_time": "1:28:29", "remaining_time": "0:23:12", "throughput": 1034.05, "total_tokens": 5490640} {"current_steps": 60980, "total_steps": 76960, "loss": 0.0079, "lr": 6.284975685362859e-06, "epoch": 15.847193347193347, "percentage": 79.24, "elapsed_time": "1:28:30", "remaining_time": "0:23:11", "throughput": 1034.05, "total_tokens": 5491088} {"current_steps": 60985, "total_steps": 76960, "loss": 0.0471, "lr": 6.28121710480942e-06, "epoch": 15.848492723492724, "percentage": 79.24, "elapsed_time": "1:28:30", "remaining_time": "0:23:11", "throughput": 1034.07, "total_tokens": 5491584} {"current_steps": 60990, "total_steps": 76960, "loss": 0.2728, "lr": 6.277459486980922e-06, "epoch": 15.8497920997921, "percentage": 79.25, "elapsed_time": "1:28:31", "remaining_time": "0:23:10", "throughput": 1034.08, "total_tokens": 5492064} {"current_steps": 60995, "total_steps": 76960, "loss": 0.1715, "lr": 6.273702832070621e-06, "epoch": 15.851091476091476, "percentage": 79.26, "elapsed_time": "1:28:31", "remaining_time": "0:23:10", "throughput": 1034.08, "total_tokens": 5492512} {"current_steps": 61000, "total_steps": 76960, "loss": 0.2081, "lr": 6.269947140271732e-06, "epoch": 15.852390852390853, "percentage": 79.26, "elapsed_time": "1:28:31", "remaining_time": "0:23:09", "throughput": 1034.08, "total_tokens": 5492944} {"current_steps": 61005, "total_steps": 76960, "loss": 0.1405, "lr": 6.2661924117774025e-06, "epoch": 15.853690228690228, "percentage": 79.27, "elapsed_time": "1:28:32", "remaining_time": "0:23:09", "throughput": 1034.09, "total_tokens": 5493408} {"current_steps": 61010, "total_steps": 76960, "loss": 0.1611, "lr": 6.262438646780752e-06, "epoch": 15.854989604989605, "percentage": 79.27, "elapsed_time": "1:28:32", "remaining_time": "0:23:08", "throughput": 1034.09, "total_tokens": 5493872} {"current_steps": 61015, "total_steps": 76960, "loss": 0.1351, "lr": 6.258685845474829e-06, "epoch": 15.856288981288982, "percentage": 79.28, "elapsed_time": "1:28:33", "remaining_time": "0:23:08", "throughput": 1034.09, "total_tokens": 5494272} {"current_steps": 61020, "total_steps": 76960, "loss": 0.1455, "lr": 6.254934008052657e-06, "epoch": 15.857588357588357, "percentage": 79.29, "elapsed_time": "1:28:33", "remaining_time": "0:23:08", "throughput": 1034.09, "total_tokens": 5494704} {"current_steps": 61025, "total_steps": 76960, "loss": 0.0082, "lr": 6.251183134707184e-06, "epoch": 15.858887733887734, "percentage": 79.29, "elapsed_time": "1:28:33", "remaining_time": "0:23:07", "throughput": 1034.09, "total_tokens": 5495152} {"current_steps": 61030, "total_steps": 76960, "loss": 0.1566, "lr": 6.247433225631324e-06, "epoch": 15.86018711018711, "percentage": 79.3, "elapsed_time": "1:28:34", "remaining_time": "0:23:07", "throughput": 1034.09, "total_tokens": 5495600} {"current_steps": 61035, "total_steps": 76960, "loss": 0.0877, "lr": 6.243684281017953e-06, "epoch": 15.861486486486486, "percentage": 79.31, "elapsed_time": "1:28:34", "remaining_time": "0:23:06", "throughput": 1034.09, "total_tokens": 5496032} {"current_steps": 61040, "total_steps": 76960, "loss": 0.1372, "lr": 6.2399363010598594e-06, "epoch": 15.862785862785863, "percentage": 79.31, "elapsed_time": "1:28:35", "remaining_time": "0:23:06", "throughput": 1034.09, "total_tokens": 5496448} {"current_steps": 61045, "total_steps": 76960, "loss": 0.003, "lr": 6.236189285949825e-06, "epoch": 15.86408523908524, "percentage": 79.32, "elapsed_time": "1:28:35", "remaining_time": "0:23:05", "throughput": 1034.1, "total_tokens": 5496944} {"current_steps": 61050, "total_steps": 76960, "loss": 0.0497, "lr": 6.2324432358805476e-06, "epoch": 15.865384615384615, "percentage": 79.33, "elapsed_time": "1:28:36", "remaining_time": "0:23:05", "throughput": 1034.11, "total_tokens": 5497424} {"current_steps": 61055, "total_steps": 76960, "loss": 0.0086, "lr": 6.228698151044704e-06, "epoch": 15.866683991683992, "percentage": 79.33, "elapsed_time": "1:28:36", "remaining_time": "0:23:04", "throughput": 1034.12, "total_tokens": 5497872} {"current_steps": 61060, "total_steps": 76960, "loss": 0.3511, "lr": 6.224954031634891e-06, "epoch": 15.867983367983367, "percentage": 79.34, "elapsed_time": "1:28:36", "remaining_time": "0:23:04", "throughput": 1034.12, "total_tokens": 5498320} {"current_steps": 61065, "total_steps": 76960, "loss": 0.0081, "lr": 6.221210877843683e-06, "epoch": 15.869282744282744, "percentage": 79.35, "elapsed_time": "1:28:37", "remaining_time": "0:23:04", "throughput": 1034.12, "total_tokens": 5498752} {"current_steps": 61070, "total_steps": 76960, "loss": 0.4165, "lr": 6.217468689863595e-06, "epoch": 15.870582120582121, "percentage": 79.35, "elapsed_time": "1:28:37", "remaining_time": "0:23:03", "throughput": 1034.12, "total_tokens": 5499200} {"current_steps": 61075, "total_steps": 76960, "loss": 0.1193, "lr": 6.213727467887093e-06, "epoch": 15.871881496881496, "percentage": 79.36, "elapsed_time": "1:28:38", "remaining_time": "0:23:03", "throughput": 1034.12, "total_tokens": 5499616} {"current_steps": 61080, "total_steps": 76960, "loss": 0.3027, "lr": 6.209987212106583e-06, "epoch": 15.873180873180873, "percentage": 79.37, "elapsed_time": "1:28:38", "remaining_time": "0:23:02", "throughput": 1034.12, "total_tokens": 5500048} {"current_steps": 61085, "total_steps": 76960, "loss": 0.2803, "lr": 6.206247922714439e-06, "epoch": 15.87448024948025, "percentage": 79.37, "elapsed_time": "1:28:38", "remaining_time": "0:23:02", "throughput": 1034.13, "total_tokens": 5500512} {"current_steps": 61090, "total_steps": 76960, "loss": 0.1877, "lr": 6.202509599902973e-06, "epoch": 15.875779625779625, "percentage": 79.38, "elapsed_time": "1:28:39", "remaining_time": "0:23:01", "throughput": 1034.13, "total_tokens": 5500960} {"current_steps": 61095, "total_steps": 76960, "loss": 0.163, "lr": 6.1987722438644395e-06, "epoch": 15.877079002079002, "percentage": 79.39, "elapsed_time": "1:28:39", "remaining_time": "0:23:01", "throughput": 1034.13, "total_tokens": 5501408} {"current_steps": 61100, "total_steps": 76960, "loss": 0.4732, "lr": 6.195035854791068e-06, "epoch": 15.878378378378379, "percentage": 79.39, "elapsed_time": "1:28:40", "remaining_time": "0:23:00", "throughput": 1034.14, "total_tokens": 5501872} {"current_steps": 61105, "total_steps": 76960, "loss": 0.0437, "lr": 6.191300432875017e-06, "epoch": 15.879677754677754, "percentage": 79.4, "elapsed_time": "1:28:40", "remaining_time": "0:23:00", "throughput": 1034.14, "total_tokens": 5502320} {"current_steps": 61110, "total_steps": 76960, "loss": 0.0796, "lr": 6.187565978308416e-06, "epoch": 15.880977130977131, "percentage": 79.4, "elapsed_time": "1:28:41", "remaining_time": "0:23:00", "throughput": 1034.15, "total_tokens": 5502768} {"current_steps": 61115, "total_steps": 76960, "loss": 0.0548, "lr": 6.1838324912833116e-06, "epoch": 15.882276507276508, "percentage": 79.41, "elapsed_time": "1:28:41", "remaining_time": "0:22:59", "throughput": 1034.15, "total_tokens": 5503216} {"current_steps": 61120, "total_steps": 76960, "loss": 0.2152, "lr": 6.18009997199174e-06, "epoch": 15.883575883575883, "percentage": 79.42, "elapsed_time": "1:28:41", "remaining_time": "0:22:59", "throughput": 1034.16, "total_tokens": 5503664} {"current_steps": 61125, "total_steps": 76960, "loss": 0.3157, "lr": 6.1763684206256525e-06, "epoch": 15.88487525987526, "percentage": 79.42, "elapsed_time": "1:28:42", "remaining_time": "0:22:58", "throughput": 1034.16, "total_tokens": 5504096} {"current_steps": 61130, "total_steps": 76960, "loss": 0.2509, "lr": 6.172637837376974e-06, "epoch": 15.886174636174637, "percentage": 79.43, "elapsed_time": "1:28:42", "remaining_time": "0:22:58", "throughput": 1034.16, "total_tokens": 5504544} {"current_steps": 61135, "total_steps": 76960, "loss": 0.1476, "lr": 6.1689082224375695e-06, "epoch": 15.887474012474012, "percentage": 79.44, "elapsed_time": "1:28:43", "remaining_time": "0:22:57", "throughput": 1034.16, "total_tokens": 5504992} {"current_steps": 61140, "total_steps": 76960, "loss": 0.4312, "lr": 6.165179575999267e-06, "epoch": 15.888773388773389, "percentage": 79.44, "elapsed_time": "1:28:43", "remaining_time": "0:22:57", "throughput": 1034.17, "total_tokens": 5505440} {"current_steps": 61145, "total_steps": 76960, "loss": 0.1767, "lr": 6.161451898253814e-06, "epoch": 15.890072765072766, "percentage": 79.45, "elapsed_time": "1:28:43", "remaining_time": "0:22:57", "throughput": 1034.17, "total_tokens": 5505904} {"current_steps": 61150, "total_steps": 76960, "loss": 0.0598, "lr": 6.1577251893929514e-06, "epoch": 15.891372141372141, "percentage": 79.46, "elapsed_time": "1:28:44", "remaining_time": "0:22:56", "throughput": 1034.17, "total_tokens": 5506336} {"current_steps": 61155, "total_steps": 76960, "loss": 0.2181, "lr": 6.1539994496083356e-06, "epoch": 15.892671517671518, "percentage": 79.46, "elapsed_time": "1:28:44", "remaining_time": "0:22:56", "throughput": 1034.18, "total_tokens": 5506784} {"current_steps": 61160, "total_steps": 76960, "loss": 0.1275, "lr": 6.150274679091577e-06, "epoch": 15.893970893970893, "percentage": 79.47, "elapsed_time": "1:28:45", "remaining_time": "0:22:55", "throughput": 1034.19, "total_tokens": 5507264} {"current_steps": 61165, "total_steps": 76960, "loss": 0.1502, "lr": 6.1465508780342545e-06, "epoch": 15.89527027027027, "percentage": 79.48, "elapsed_time": "1:28:45", "remaining_time": "0:22:55", "throughput": 1034.18, "total_tokens": 5507680} {"current_steps": 61170, "total_steps": 76960, "loss": 0.2048, "lr": 6.142828046627883e-06, "epoch": 15.896569646569647, "percentage": 79.48, "elapsed_time": "1:28:46", "remaining_time": "0:22:54", "throughput": 1034.18, "total_tokens": 5508096} {"current_steps": 61175, "total_steps": 76960, "loss": 0.0553, "lr": 6.139106185063942e-06, "epoch": 15.897869022869022, "percentage": 79.49, "elapsed_time": "1:28:46", "remaining_time": "0:22:54", "throughput": 1034.18, "total_tokens": 5508544} {"current_steps": 61180, "total_steps": 76960, "loss": 0.072, "lr": 6.135385293533832e-06, "epoch": 15.8991683991684, "percentage": 79.5, "elapsed_time": "1:28:46", "remaining_time": "0:22:53", "throughput": 1034.19, "total_tokens": 5508992} {"current_steps": 61185, "total_steps": 76960, "loss": 0.1321, "lr": 6.13166537222894e-06, "epoch": 15.900467775467776, "percentage": 79.5, "elapsed_time": "1:28:47", "remaining_time": "0:22:53", "throughput": 1034.19, "total_tokens": 5509424} {"current_steps": 61190, "total_steps": 76960, "loss": 0.2455, "lr": 6.127946421340569e-06, "epoch": 15.901767151767151, "percentage": 79.51, "elapsed_time": "1:28:47", "remaining_time": "0:22:53", "throughput": 1034.19, "total_tokens": 5509872} {"current_steps": 61195, "total_steps": 76960, "loss": 0.1078, "lr": 6.124228441060004e-06, "epoch": 15.903066528066528, "percentage": 79.52, "elapsed_time": "1:28:48", "remaining_time": "0:22:52", "throughput": 1034.19, "total_tokens": 5510288} {"current_steps": 61200, "total_steps": 76960, "loss": 0.0241, "lr": 6.120511431578449e-06, "epoch": 15.904365904365905, "percentage": 79.52, "elapsed_time": "1:28:48", "remaining_time": "0:22:52", "throughput": 1034.19, "total_tokens": 5510752} {"current_steps": 61205, "total_steps": 76960, "loss": 0.255, "lr": 6.116795393087079e-06, "epoch": 15.90566528066528, "percentage": 79.53, "elapsed_time": "1:28:48", "remaining_time": "0:22:51", "throughput": 1034.19, "total_tokens": 5511168} {"current_steps": 61210, "total_steps": 76960, "loss": 0.0007, "lr": 6.113080325777018e-06, "epoch": 15.906964656964657, "percentage": 79.53, "elapsed_time": "1:28:49", "remaining_time": "0:22:51", "throughput": 1034.2, "total_tokens": 5511632} {"current_steps": 61215, "total_steps": 76960, "loss": 0.0271, "lr": 6.1093662298393365e-06, "epoch": 15.908264033264032, "percentage": 79.54, "elapsed_time": "1:28:49", "remaining_time": "0:22:50", "throughput": 1034.2, "total_tokens": 5512064} {"current_steps": 61220, "total_steps": 76960, "loss": 0.1721, "lr": 6.105653105465051e-06, "epoch": 15.90956340956341, "percentage": 79.55, "elapsed_time": "1:28:50", "remaining_time": "0:22:50", "throughput": 1034.2, "total_tokens": 5512496} {"current_steps": 61225, "total_steps": 76960, "loss": 0.0028, "lr": 6.101940952845122e-06, "epoch": 15.910862785862786, "percentage": 79.55, "elapsed_time": "1:28:50", "remaining_time": "0:22:49", "throughput": 1034.2, "total_tokens": 5512912} {"current_steps": 61230, "total_steps": 76960, "loss": 0.0403, "lr": 6.098229772170486e-06, "epoch": 15.912162162162161, "percentage": 79.56, "elapsed_time": "1:28:51", "remaining_time": "0:22:49", "throughput": 1034.2, "total_tokens": 5513360} {"current_steps": 61235, "total_steps": 76960, "loss": 0.5086, "lr": 6.094519563631995e-06, "epoch": 15.913461538461538, "percentage": 79.57, "elapsed_time": "1:28:51", "remaining_time": "0:22:49", "throughput": 1034.21, "total_tokens": 5513824} {"current_steps": 61240, "total_steps": 76960, "loss": 0.2181, "lr": 6.090810327420479e-06, "epoch": 15.914760914760915, "percentage": 79.57, "elapsed_time": "1:28:51", "remaining_time": "0:22:48", "throughput": 1034.21, "total_tokens": 5514272} {"current_steps": 61245, "total_steps": 76960, "loss": 0.0035, "lr": 6.087102063726704e-06, "epoch": 15.91606029106029, "percentage": 79.58, "elapsed_time": "1:28:52", "remaining_time": "0:22:48", "throughput": 1034.21, "total_tokens": 5514720} {"current_steps": 61250, "total_steps": 76960, "loss": 0.32, "lr": 6.0833947727414e-06, "epoch": 15.917359667359667, "percentage": 79.59, "elapsed_time": "1:28:52", "remaining_time": "0:22:47", "throughput": 1034.22, "total_tokens": 5515184} {"current_steps": 61255, "total_steps": 76960, "loss": 0.0012, "lr": 6.079688454655219e-06, "epoch": 15.918659043659044, "percentage": 79.59, "elapsed_time": "1:28:53", "remaining_time": "0:22:47", "throughput": 1034.22, "total_tokens": 5515616} {"current_steps": 61260, "total_steps": 76960, "loss": 0.0156, "lr": 6.075983109658798e-06, "epoch": 15.91995841995842, "percentage": 79.6, "elapsed_time": "1:28:53", "remaining_time": "0:22:46", "throughput": 1034.22, "total_tokens": 5516064} {"current_steps": 61265, "total_steps": 76960, "loss": 0.2773, "lr": 6.072278737942691e-06, "epoch": 15.921257796257796, "percentage": 79.61, "elapsed_time": "1:28:53", "remaining_time": "0:22:46", "throughput": 1034.23, "total_tokens": 5516512} {"current_steps": 61270, "total_steps": 76960, "loss": 0.1713, "lr": 6.06857533969743e-06, "epoch": 15.922557172557173, "percentage": 79.61, "elapsed_time": "1:28:54", "remaining_time": "0:22:46", "throughput": 1034.23, "total_tokens": 5516976} {"current_steps": 61275, "total_steps": 76960, "loss": 0.48, "lr": 6.0648729151134705e-06, "epoch": 15.923856548856548, "percentage": 79.62, "elapsed_time": "1:28:54", "remaining_time": "0:22:45", "throughput": 1034.23, "total_tokens": 5517392} {"current_steps": 61280, "total_steps": 76960, "loss": 0.116, "lr": 6.0611714643812406e-06, "epoch": 15.925155925155925, "percentage": 79.63, "elapsed_time": "1:28:55", "remaining_time": "0:22:45", "throughput": 1034.23, "total_tokens": 5517824} {"current_steps": 61285, "total_steps": 76960, "loss": 0.0353, "lr": 6.057470987691116e-06, "epoch": 15.926455301455302, "percentage": 79.63, "elapsed_time": "1:28:55", "remaining_time": "0:22:44", "throughput": 1034.24, "total_tokens": 5518288} {"current_steps": 61290, "total_steps": 76960, "loss": 0.0556, "lr": 6.0537714852334e-06, "epoch": 15.927754677754677, "percentage": 79.64, "elapsed_time": "1:28:56", "remaining_time": "0:22:44", "throughput": 1034.24, "total_tokens": 5518736} {"current_steps": 61295, "total_steps": 76960, "loss": 0.5915, "lr": 6.05007295719838e-06, "epoch": 15.929054054054054, "percentage": 79.65, "elapsed_time": "1:28:56", "remaining_time": "0:22:43", "throughput": 1034.24, "total_tokens": 5519184} {"current_steps": 61300, "total_steps": 76960, "loss": 0.1303, "lr": 6.046375403776256e-06, "epoch": 15.93035343035343, "percentage": 79.65, "elapsed_time": "1:28:56", "remaining_time": "0:22:43", "throughput": 1034.26, "total_tokens": 5519680} {"current_steps": 61305, "total_steps": 76960, "loss": 0.2512, "lr": 6.0426788251572105e-06, "epoch": 15.931652806652806, "percentage": 79.66, "elapsed_time": "1:28:57", "remaining_time": "0:22:42", "throughput": 1034.26, "total_tokens": 5520112} {"current_steps": 61310, "total_steps": 76960, "loss": 0.0418, "lr": 6.038983221531352e-06, "epoch": 15.932952182952183, "percentage": 79.66, "elapsed_time": "1:28:57", "remaining_time": "0:22:42", "throughput": 1034.25, "total_tokens": 5520528} {"current_steps": 61315, "total_steps": 76960, "loss": 0.3272, "lr": 6.0352885930887556e-06, "epoch": 15.934251559251559, "percentage": 79.67, "elapsed_time": "1:28:58", "remaining_time": "0:22:42", "throughput": 1034.25, "total_tokens": 5520944} {"current_steps": 61320, "total_steps": 76960, "loss": 0.1446, "lr": 6.031594940019436e-06, "epoch": 15.935550935550935, "percentage": 79.68, "elapsed_time": "1:28:58", "remaining_time": "0:22:41", "throughput": 1034.25, "total_tokens": 5521392} {"current_steps": 61325, "total_steps": 76960, "loss": 0.3093, "lr": 6.027902262513372e-06, "epoch": 15.936850311850312, "percentage": 79.68, "elapsed_time": "1:28:58", "remaining_time": "0:22:41", "throughput": 1034.26, "total_tokens": 5521840} {"current_steps": 61330, "total_steps": 76960, "loss": 0.1018, "lr": 6.024210560760463e-06, "epoch": 15.938149688149688, "percentage": 79.69, "elapsed_time": "1:28:59", "remaining_time": "0:22:40", "throughput": 1034.26, "total_tokens": 5522304} {"current_steps": 61335, "total_steps": 76960, "loss": 0.2205, "lr": 6.0205198349505945e-06, "epoch": 15.939449064449065, "percentage": 79.7, "elapsed_time": "1:28:59", "remaining_time": "0:22:40", "throughput": 1034.26, "total_tokens": 5522736} {"current_steps": 61340, "total_steps": 76960, "loss": 0.1567, "lr": 6.01683008527357e-06, "epoch": 15.940748440748441, "percentage": 79.7, "elapsed_time": "1:29:00", "remaining_time": "0:22:39", "throughput": 1034.27, "total_tokens": 5523184} {"current_steps": 61345, "total_steps": 76960, "loss": 0.4664, "lr": 6.0131413119191685e-06, "epoch": 15.942047817047817, "percentage": 79.71, "elapsed_time": "1:29:00", "remaining_time": "0:22:39", "throughput": 1034.27, "total_tokens": 5523648} {"current_steps": 61350, "total_steps": 76960, "loss": 0.1767, "lr": 6.009453515077096e-06, "epoch": 15.943347193347194, "percentage": 79.72, "elapsed_time": "1:29:01", "remaining_time": "0:22:38", "throughput": 1034.27, "total_tokens": 5524048} {"current_steps": 61355, "total_steps": 76960, "loss": 0.2421, "lr": 6.005766694937026e-06, "epoch": 15.94464656964657, "percentage": 79.72, "elapsed_time": "1:29:01", "remaining_time": "0:22:38", "throughput": 1034.27, "total_tokens": 5524480} {"current_steps": 61360, "total_steps": 76960, "loss": 0.1481, "lr": 6.00208085168858e-06, "epoch": 15.945945945945946, "percentage": 79.73, "elapsed_time": "1:29:01", "remaining_time": "0:22:38", "throughput": 1034.27, "total_tokens": 5524912} {"current_steps": 61365, "total_steps": 76960, "loss": 0.2174, "lr": 5.99839598552131e-06, "epoch": 15.947245322245323, "percentage": 79.74, "elapsed_time": "1:29:02", "remaining_time": "0:22:37", "throughput": 1034.28, "total_tokens": 5525376} {"current_steps": 61370, "total_steps": 76960, "loss": 0.4563, "lr": 5.994712096624752e-06, "epoch": 15.948544698544698, "percentage": 79.74, "elapsed_time": "1:29:02", "remaining_time": "0:22:37", "throughput": 1034.28, "total_tokens": 5525808} {"current_steps": 61375, "total_steps": 76960, "loss": 0.1669, "lr": 5.9910291851883515e-06, "epoch": 15.949844074844075, "percentage": 79.75, "elapsed_time": "1:29:03", "remaining_time": "0:22:36", "throughput": 1034.28, "total_tokens": 5526240} {"current_steps": 61380, "total_steps": 76960, "loss": 0.0315, "lr": 5.9873472514015316e-06, "epoch": 15.951143451143452, "percentage": 79.76, "elapsed_time": "1:29:03", "remaining_time": "0:22:36", "throughput": 1034.29, "total_tokens": 5526736} {"current_steps": 61385, "total_steps": 76960, "loss": 0.3249, "lr": 5.9836662954536634e-06, "epoch": 15.952442827442827, "percentage": 79.76, "elapsed_time": "1:29:03", "remaining_time": "0:22:35", "throughput": 1034.3, "total_tokens": 5527216} {"current_steps": 61390, "total_steps": 76960, "loss": 0.5066, "lr": 5.979986317534064e-06, "epoch": 15.953742203742204, "percentage": 79.77, "elapsed_time": "1:29:04", "remaining_time": "0:22:35", "throughput": 1034.3, "total_tokens": 5527664} {"current_steps": 61395, "total_steps": 76960, "loss": 0.3528, "lr": 5.976307317831984e-06, "epoch": 15.95504158004158, "percentage": 79.78, "elapsed_time": "1:29:04", "remaining_time": "0:22:35", "throughput": 1034.31, "total_tokens": 5528144} {"current_steps": 61400, "total_steps": 76960, "loss": 0.1066, "lr": 5.972629296536655e-06, "epoch": 15.956340956340956, "percentage": 79.78, "elapsed_time": "1:29:05", "remaining_time": "0:22:34", "throughput": 1034.32, "total_tokens": 5528624} {"current_steps": 61405, "total_steps": 76960, "loss": 0.0228, "lr": 5.968952253837224e-06, "epoch": 15.957640332640333, "percentage": 79.79, "elapsed_time": "1:29:05", "remaining_time": "0:22:34", "throughput": 1034.32, "total_tokens": 5529088} {"current_steps": 61410, "total_steps": 76960, "loss": 0.0443, "lr": 5.96527618992282e-06, "epoch": 15.95893970893971, "percentage": 79.79, "elapsed_time": "1:29:06", "remaining_time": "0:22:33", "throughput": 1034.33, "total_tokens": 5529536} {"current_steps": 61415, "total_steps": 76960, "loss": 0.003, "lr": 5.961601104982495e-06, "epoch": 15.960239085239085, "percentage": 79.8, "elapsed_time": "1:29:06", "remaining_time": "0:22:33", "throughput": 1034.33, "total_tokens": 5530000} {"current_steps": 61420, "total_steps": 76960, "loss": 0.0028, "lr": 5.957926999205265e-06, "epoch": 15.961538461538462, "percentage": 79.81, "elapsed_time": "1:29:06", "remaining_time": "0:22:32", "throughput": 1034.34, "total_tokens": 5530448} {"current_steps": 61425, "total_steps": 76960, "loss": 0.4672, "lr": 5.954253872780102e-06, "epoch": 15.962837837837839, "percentage": 79.81, "elapsed_time": "1:29:07", "remaining_time": "0:22:32", "throughput": 1034.34, "total_tokens": 5530912} {"current_steps": 61430, "total_steps": 76960, "loss": 0.081, "lr": 5.950581725895904e-06, "epoch": 15.964137214137214, "percentage": 79.82, "elapsed_time": "1:29:07", "remaining_time": "0:22:31", "throughput": 1034.35, "total_tokens": 5531392} {"current_steps": 61435, "total_steps": 76960, "loss": 0.1934, "lr": 5.946910558741548e-06, "epoch": 15.96543659043659, "percentage": 79.83, "elapsed_time": "1:29:08", "remaining_time": "0:22:31", "throughput": 1034.37, "total_tokens": 5531904} {"current_steps": 61440, "total_steps": 76960, "loss": 0.4011, "lr": 5.943240371505829e-06, "epoch": 15.966735966735968, "percentage": 79.83, "elapsed_time": "1:29:08", "remaining_time": "0:22:31", "throughput": 1034.37, "total_tokens": 5532336} {"current_steps": 61445, "total_steps": 76960, "loss": 0.0333, "lr": 5.939571164377525e-06, "epoch": 15.968035343035343, "percentage": 79.84, "elapsed_time": "1:29:08", "remaining_time": "0:22:30", "throughput": 1034.38, "total_tokens": 5532832} {"current_steps": 61450, "total_steps": 76960, "loss": 0.1428, "lr": 5.935902937545332e-06, "epoch": 15.96933471933472, "percentage": 79.85, "elapsed_time": "1:29:09", "remaining_time": "0:22:30", "throughput": 1034.38, "total_tokens": 5533264} {"current_steps": 61455, "total_steps": 76960, "loss": 0.0814, "lr": 5.932235691197918e-06, "epoch": 15.970634095634095, "percentage": 79.85, "elapsed_time": "1:29:09", "remaining_time": "0:22:29", "throughput": 1034.38, "total_tokens": 5533712} {"current_steps": 61460, "total_steps": 76960, "loss": 0.2925, "lr": 5.928569425523891e-06, "epoch": 15.971933471933472, "percentage": 79.86, "elapsed_time": "1:29:10", "remaining_time": "0:22:29", "throughput": 1034.38, "total_tokens": 5534144} {"current_steps": 61465, "total_steps": 76960, "loss": 0.0375, "lr": 5.924904140711818e-06, "epoch": 15.973232848232849, "percentage": 79.87, "elapsed_time": "1:29:10", "remaining_time": "0:22:28", "throughput": 1034.38, "total_tokens": 5534576} {"current_steps": 61470, "total_steps": 76960, "loss": 0.2036, "lr": 5.921239836950196e-06, "epoch": 15.974532224532224, "percentage": 79.87, "elapsed_time": "1:29:11", "remaining_time": "0:22:28", "throughput": 1034.39, "total_tokens": 5535024} {"current_steps": 61475, "total_steps": 76960, "loss": 0.0862, "lr": 5.9175765144274976e-06, "epoch": 15.9758316008316, "percentage": 79.88, "elapsed_time": "1:29:11", "remaining_time": "0:22:27", "throughput": 1034.39, "total_tokens": 5535456} {"current_steps": 61480, "total_steps": 76960, "loss": 0.4148, "lr": 5.9139141733321215e-06, "epoch": 15.977130977130978, "percentage": 79.89, "elapsed_time": "1:29:11", "remaining_time": "0:22:27", "throughput": 1034.4, "total_tokens": 5535952} {"current_steps": 61485, "total_steps": 76960, "loss": 0.6204, "lr": 5.910252813852421e-06, "epoch": 15.978430353430353, "percentage": 79.89, "elapsed_time": "1:29:12", "remaining_time": "0:22:27", "throughput": 1034.41, "total_tokens": 5536448} {"current_steps": 61490, "total_steps": 76960, "loss": 0.0959, "lr": 5.9065924361767084e-06, "epoch": 15.97972972972973, "percentage": 79.9, "elapsed_time": "1:29:12", "remaining_time": "0:22:26", "throughput": 1034.41, "total_tokens": 5536880} {"current_steps": 61495, "total_steps": 76960, "loss": 0.4261, "lr": 5.902933040493241e-06, "epoch": 15.981029106029107, "percentage": 79.91, "elapsed_time": "1:29:13", "remaining_time": "0:22:26", "throughput": 1034.42, "total_tokens": 5537328} {"current_steps": 61500, "total_steps": 76960, "loss": 0.6419, "lr": 5.899274626990234e-06, "epoch": 15.982328482328482, "percentage": 79.91, "elapsed_time": "1:29:13", "remaining_time": "0:22:25", "throughput": 1034.41, "total_tokens": 5537744} {"current_steps": 61505, "total_steps": 76960, "loss": 0.0026, "lr": 5.8956171958558266e-06, "epoch": 15.983627858627859, "percentage": 79.92, "elapsed_time": "1:29:13", "remaining_time": "0:22:25", "throughput": 1034.42, "total_tokens": 5538208} {"current_steps": 61510, "total_steps": 76960, "loss": 0.1278, "lr": 5.891960747278136e-06, "epoch": 15.984927234927234, "percentage": 79.92, "elapsed_time": "1:29:14", "remaining_time": "0:22:24", "throughput": 1034.42, "total_tokens": 5538672} {"current_steps": 61515, "total_steps": 76960, "loss": 0.5197, "lr": 5.888305281445208e-06, "epoch": 15.986226611226611, "percentage": 79.93, "elapsed_time": "1:29:14", "remaining_time": "0:22:24", "throughput": 1034.42, "total_tokens": 5539088} {"current_steps": 61520, "total_steps": 76960, "loss": 0.2758, "lr": 5.8846507985450574e-06, "epoch": 15.987525987525988, "percentage": 79.94, "elapsed_time": "1:29:15", "remaining_time": "0:22:24", "throughput": 1034.42, "total_tokens": 5539504} {"current_steps": 61525, "total_steps": 76960, "loss": 0.1798, "lr": 5.880997298765628e-06, "epoch": 15.988825363825363, "percentage": 79.94, "elapsed_time": "1:29:15", "remaining_time": "0:22:23", "throughput": 1034.43, "total_tokens": 5539984} {"current_steps": 61530, "total_steps": 76960, "loss": 0.2156, "lr": 5.877344782294822e-06, "epoch": 15.99012474012474, "percentage": 79.95, "elapsed_time": "1:29:16", "remaining_time": "0:22:23", "throughput": 1034.43, "total_tokens": 5540448} {"current_steps": 61535, "total_steps": 76960, "loss": 0.0133, "lr": 5.8736932493205e-06, "epoch": 15.991424116424117, "percentage": 79.96, "elapsed_time": "1:29:16", "remaining_time": "0:22:22", "throughput": 1034.43, "total_tokens": 5540864} {"current_steps": 61540, "total_steps": 76960, "loss": 0.1135, "lr": 5.870042700030464e-06, "epoch": 15.992723492723492, "percentage": 79.96, "elapsed_time": "1:29:16", "remaining_time": "0:22:22", "throughput": 1034.43, "total_tokens": 5541296} {"current_steps": 61545, "total_steps": 76960, "loss": 0.0742, "lr": 5.866393134612463e-06, "epoch": 15.994022869022869, "percentage": 79.97, "elapsed_time": "1:29:17", "remaining_time": "0:22:21", "throughput": 1034.44, "total_tokens": 5541760} {"current_steps": 61550, "total_steps": 76960, "loss": 0.0814, "lr": 5.862744553254188e-06, "epoch": 15.995322245322246, "percentage": 79.98, "elapsed_time": "1:29:17", "remaining_time": "0:22:21", "throughput": 1034.45, "total_tokens": 5542256} {"current_steps": 61555, "total_steps": 76960, "loss": 0.1648, "lr": 5.859096956143306e-06, "epoch": 15.996621621621621, "percentage": 79.98, "elapsed_time": "1:29:18", "remaining_time": "0:22:20", "throughput": 1034.45, "total_tokens": 5542688} {"current_steps": 61560, "total_steps": 76960, "loss": 0.207, "lr": 5.855450343467397e-06, "epoch": 15.997920997920998, "percentage": 79.99, "elapsed_time": "1:29:18", "remaining_time": "0:22:20", "throughput": 1034.45, "total_tokens": 5543120} {"current_steps": 61565, "total_steps": 76960, "loss": 0.0483, "lr": 5.8518047154140245e-06, "epoch": 15.999220374220375, "percentage": 80.0, "elapsed_time": "1:29:18", "remaining_time": "0:22:20", "throughput": 1034.47, "total_tokens": 5543648} {"current_steps": 61568, "total_steps": 76960, "eval_loss": 0.5153894424438477, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "1:29:32", "remaining_time": "0:22:23", "throughput": 1031.9, "total_tokens": 5543848} {"current_steps": 61570, "total_steps": 76960, "loss": 0.0529, "lr": 5.848160072170681e-06, "epoch": 16.00051975051975, "percentage": 80.0, "elapsed_time": "1:29:34", "remaining_time": "0:22:23", "throughput": 1031.58, "total_tokens": 5544056} {"current_steps": 61575, "total_steps": 76960, "loss": 0.0845, "lr": 5.844516413924822e-06, "epoch": 16.001819126819125, "percentage": 80.01, "elapsed_time": "1:29:34", "remaining_time": "0:22:22", "throughput": 1031.59, "total_tokens": 5544504} {"current_steps": 61580, "total_steps": 76960, "loss": 0.0725, "lr": 5.840873740863828e-06, "epoch": 16.003118503118504, "percentage": 80.02, "elapsed_time": "1:29:35", "remaining_time": "0:22:22", "throughput": 1031.58, "total_tokens": 5544936} {"current_steps": 61585, "total_steps": 76960, "loss": 0.1973, "lr": 5.8372320531750655e-06, "epoch": 16.00441787941788, "percentage": 80.02, "elapsed_time": "1:29:35", "remaining_time": "0:22:22", "throughput": 1031.58, "total_tokens": 5545368} {"current_steps": 61590, "total_steps": 76960, "loss": 0.0468, "lr": 5.833591351045811e-06, "epoch": 16.005717255717254, "percentage": 80.03, "elapsed_time": "1:29:36", "remaining_time": "0:22:21", "throughput": 1031.59, "total_tokens": 5545848} {"current_steps": 61595, "total_steps": 76960, "loss": 0.0644, "lr": 5.829951634663325e-06, "epoch": 16.007016632016633, "percentage": 80.04, "elapsed_time": "1:29:36", "remaining_time": "0:22:21", "throughput": 1031.59, "total_tokens": 5546264} {"current_steps": 61600, "total_steps": 76960, "loss": 0.3802, "lr": 5.826312904214781e-06, "epoch": 16.008316008316008, "percentage": 80.04, "elapsed_time": "1:29:36", "remaining_time": "0:22:20", "throughput": 1031.59, "total_tokens": 5546728} {"current_steps": 61605, "total_steps": 76960, "loss": 0.0114, "lr": 5.82267515988735e-06, "epoch": 16.009615384615383, "percentage": 80.05, "elapsed_time": "1:29:37", "remaining_time": "0:22:20", "throughput": 1031.6, "total_tokens": 5547256} {"current_steps": 61610, "total_steps": 76960, "loss": 0.1976, "lr": 5.8190384018681075e-06, "epoch": 16.010914760914762, "percentage": 80.05, "elapsed_time": "1:29:37", "remaining_time": "0:22:19", "throughput": 1031.61, "total_tokens": 5547720} {"current_steps": 61615, "total_steps": 76960, "loss": 0.3996, "lr": 5.815402630344094e-06, "epoch": 16.012214137214137, "percentage": 80.06, "elapsed_time": "1:29:38", "remaining_time": "0:22:19", "throughput": 1031.62, "total_tokens": 5548200} {"current_steps": 61620, "total_steps": 76960, "loss": 0.0358, "lr": 5.811767845502311e-06, "epoch": 16.013513513513512, "percentage": 80.07, "elapsed_time": "1:29:38", "remaining_time": "0:22:18", "throughput": 1031.63, "total_tokens": 5548680} {"current_steps": 61625, "total_steps": 76960, "loss": 0.0799, "lr": 5.808134047529687e-06, "epoch": 16.01481288981289, "percentage": 80.07, "elapsed_time": "1:29:38", "remaining_time": "0:22:18", "throughput": 1031.63, "total_tokens": 5549128} {"current_steps": 61630, "total_steps": 76960, "loss": 0.0412, "lr": 5.804501236613116e-06, "epoch": 16.016112266112266, "percentage": 80.08, "elapsed_time": "1:29:39", "remaining_time": "0:22:18", "throughput": 1031.64, "total_tokens": 5549608} {"current_steps": 61635, "total_steps": 76960, "loss": 0.0843, "lr": 5.8008694129394385e-06, "epoch": 16.01741164241164, "percentage": 80.09, "elapsed_time": "1:29:39", "remaining_time": "0:22:17", "throughput": 1031.65, "total_tokens": 5550072} {"current_steps": 61640, "total_steps": 76960, "loss": 0.2191, "lr": 5.797238576695452e-06, "epoch": 16.01871101871102, "percentage": 80.09, "elapsed_time": "1:29:40", "remaining_time": "0:22:17", "throughput": 1031.65, "total_tokens": 5550536} {"current_steps": 61645, "total_steps": 76960, "loss": 0.065, "lr": 5.7936087280678755e-06, "epoch": 16.020010395010395, "percentage": 80.1, "elapsed_time": "1:29:40", "remaining_time": "0:22:16", "throughput": 1031.65, "total_tokens": 5550952} {"current_steps": 61650, "total_steps": 76960, "loss": 0.0426, "lr": 5.789979867243414e-06, "epoch": 16.02130977130977, "percentage": 80.11, "elapsed_time": "1:29:41", "remaining_time": "0:22:16", "throughput": 1031.65, "total_tokens": 5551384} {"current_steps": 61655, "total_steps": 76960, "loss": 0.0086, "lr": 5.786351994408684e-06, "epoch": 16.02260914760915, "percentage": 80.11, "elapsed_time": "1:29:41", "remaining_time": "0:22:15", "throughput": 1031.67, "total_tokens": 5551896} {"current_steps": 61660, "total_steps": 76960, "loss": 0.0033, "lr": 5.782725109750289e-06, "epoch": 16.023908523908524, "percentage": 80.12, "elapsed_time": "1:29:41", "remaining_time": "0:22:15", "throughput": 1031.67, "total_tokens": 5552344} {"current_steps": 61665, "total_steps": 76960, "loss": 0.0346, "lr": 5.77909921345475e-06, "epoch": 16.0252079002079, "percentage": 80.13, "elapsed_time": "1:29:42", "remaining_time": "0:22:14", "throughput": 1031.67, "total_tokens": 5552792} {"current_steps": 61670, "total_steps": 76960, "loss": 0.0014, "lr": 5.775474305708553e-06, "epoch": 16.026507276507278, "percentage": 80.13, "elapsed_time": "1:29:42", "remaining_time": "0:22:14", "throughput": 1031.68, "total_tokens": 5553272} {"current_steps": 61675, "total_steps": 76960, "loss": 0.1733, "lr": 5.771850386698138e-06, "epoch": 16.027806652806653, "percentage": 80.14, "elapsed_time": "1:29:43", "remaining_time": "0:22:14", "throughput": 1031.69, "total_tokens": 5553752} {"current_steps": 61680, "total_steps": 76960, "loss": 0.0158, "lr": 5.768227456609879e-06, "epoch": 16.02910602910603, "percentage": 80.15, "elapsed_time": "1:29:43", "remaining_time": "0:22:13", "throughput": 1031.69, "total_tokens": 5554184} {"current_steps": 61685, "total_steps": 76960, "loss": 0.2692, "lr": 5.764605515630112e-06, "epoch": 16.030405405405407, "percentage": 80.15, "elapsed_time": "1:29:43", "remaining_time": "0:22:13", "throughput": 1031.69, "total_tokens": 5554616} {"current_steps": 61690, "total_steps": 76960, "loss": 0.0946, "lr": 5.760984563945107e-06, "epoch": 16.031704781704782, "percentage": 80.16, "elapsed_time": "1:29:44", "remaining_time": "0:22:12", "throughput": 1031.69, "total_tokens": 5555048} {"current_steps": 61695, "total_steps": 76960, "loss": 0.0399, "lr": 5.757364601741108e-06, "epoch": 16.033004158004157, "percentage": 80.17, "elapsed_time": "1:29:44", "remaining_time": "0:22:12", "throughput": 1031.7, "total_tokens": 5555496} {"current_steps": 61700, "total_steps": 76960, "loss": 0.1247, "lr": 5.753745629204277e-06, "epoch": 16.034303534303536, "percentage": 80.17, "elapsed_time": "1:29:45", "remaining_time": "0:22:11", "throughput": 1031.69, "total_tokens": 5555912} {"current_steps": 61705, "total_steps": 76960, "loss": 0.3687, "lr": 5.750127646520747e-06, "epoch": 16.03560291060291, "percentage": 80.18, "elapsed_time": "1:29:45", "remaining_time": "0:22:11", "throughput": 1031.7, "total_tokens": 5556360} {"current_steps": 61710, "total_steps": 76960, "loss": 0.1106, "lr": 5.7465106538766e-06, "epoch": 16.036902286902286, "percentage": 80.18, "elapsed_time": "1:29:46", "remaining_time": "0:22:11", "throughput": 1031.7, "total_tokens": 5556824} {"current_steps": 61715, "total_steps": 76960, "loss": 0.1496, "lr": 5.742894651457864e-06, "epoch": 16.03820166320166, "percentage": 80.19, "elapsed_time": "1:29:46", "remaining_time": "0:22:10", "throughput": 1031.7, "total_tokens": 5557256} {"current_steps": 61720, "total_steps": 76960, "loss": 0.0013, "lr": 5.739279639450501e-06, "epoch": 16.03950103950104, "percentage": 80.2, "elapsed_time": "1:29:46", "remaining_time": "0:22:10", "throughput": 1031.71, "total_tokens": 5557704} {"current_steps": 61725, "total_steps": 76960, "loss": 0.0648, "lr": 5.735665618040445e-06, "epoch": 16.040800415800415, "percentage": 80.2, "elapsed_time": "1:29:47", "remaining_time": "0:22:09", "throughput": 1031.71, "total_tokens": 5558136} {"current_steps": 61730, "total_steps": 76960, "loss": 0.0396, "lr": 5.732052587413561e-06, "epoch": 16.04209979209979, "percentage": 80.21, "elapsed_time": "1:29:47", "remaining_time": "0:22:09", "throughput": 1031.71, "total_tokens": 5558568} {"current_steps": 61735, "total_steps": 76960, "loss": 0.0882, "lr": 5.728440547755679e-06, "epoch": 16.04339916839917, "percentage": 80.22, "elapsed_time": "1:29:48", "remaining_time": "0:22:08", "throughput": 1031.71, "total_tokens": 5559000} {"current_steps": 61740, "total_steps": 76960, "loss": 0.0542, "lr": 5.72482949925256e-06, "epoch": 16.044698544698544, "percentage": 80.22, "elapsed_time": "1:29:48", "remaining_time": "0:22:08", "throughput": 1031.72, "total_tokens": 5559512} {"current_steps": 61745, "total_steps": 76960, "loss": 0.2196, "lr": 5.721219442089926e-06, "epoch": 16.04599792099792, "percentage": 80.23, "elapsed_time": "1:29:48", "remaining_time": "0:22:07", "throughput": 1031.73, "total_tokens": 5559976} {"current_steps": 61750, "total_steps": 76960, "loss": 0.2915, "lr": 5.717610376453455e-06, "epoch": 16.0472972972973, "percentage": 80.24, "elapsed_time": "1:29:49", "remaining_time": "0:22:07", "throughput": 1031.72, "total_tokens": 5560376} {"current_steps": 61755, "total_steps": 76960, "loss": 0.1446, "lr": 5.714002302528751e-06, "epoch": 16.048596673596673, "percentage": 80.24, "elapsed_time": "1:29:49", "remaining_time": "0:22:07", "throughput": 1031.73, "total_tokens": 5560840} {"current_steps": 61760, "total_steps": 76960, "loss": 0.1512, "lr": 5.7103952205013965e-06, "epoch": 16.04989604989605, "percentage": 80.25, "elapsed_time": "1:29:50", "remaining_time": "0:22:06", "throughput": 1031.73, "total_tokens": 5561272} {"current_steps": 61765, "total_steps": 76960, "loss": 0.3052, "lr": 5.706789130556889e-06, "epoch": 16.051195426195427, "percentage": 80.26, "elapsed_time": "1:29:50", "remaining_time": "0:22:06", "throughput": 1031.73, "total_tokens": 5561688} {"current_steps": 61770, "total_steps": 76960, "loss": 0.2178, "lr": 5.70318403288071e-06, "epoch": 16.052494802494802, "percentage": 80.26, "elapsed_time": "1:29:51", "remaining_time": "0:22:05", "throughput": 1031.74, "total_tokens": 5562152} {"current_steps": 61775, "total_steps": 76960, "loss": 0.4226, "lr": 5.699579927658258e-06, "epoch": 16.053794178794178, "percentage": 80.27, "elapsed_time": "1:29:51", "remaining_time": "0:22:05", "throughput": 1031.74, "total_tokens": 5562600} {"current_steps": 61780, "total_steps": 76960, "loss": 0.3369, "lr": 5.695976815074905e-06, "epoch": 16.055093555093556, "percentage": 80.28, "elapsed_time": "1:29:51", "remaining_time": "0:22:04", "throughput": 1031.74, "total_tokens": 5563048} {"current_steps": 61785, "total_steps": 76960, "loss": 0.0256, "lr": 5.69237469531596e-06, "epoch": 16.05639293139293, "percentage": 80.28, "elapsed_time": "1:29:52", "remaining_time": "0:22:04", "throughput": 1031.75, "total_tokens": 5563496} {"current_steps": 61790, "total_steps": 76960, "loss": 0.0064, "lr": 5.688773568566691e-06, "epoch": 16.057692307692307, "percentage": 80.29, "elapsed_time": "1:29:52", "remaining_time": "0:22:03", "throughput": 1031.75, "total_tokens": 5563944} {"current_steps": 61795, "total_steps": 76960, "loss": 0.2657, "lr": 5.685173435012292e-06, "epoch": 16.058991683991685, "percentage": 80.29, "elapsed_time": "1:29:53", "remaining_time": "0:22:03", "throughput": 1031.76, "total_tokens": 5564424} {"current_steps": 61800, "total_steps": 76960, "loss": 0.0026, "lr": 5.6815742948379384e-06, "epoch": 16.06029106029106, "percentage": 80.3, "elapsed_time": "1:29:53", "remaining_time": "0:22:03", "throughput": 1031.76, "total_tokens": 5564872} {"current_steps": 61805, "total_steps": 76960, "loss": 0.0614, "lr": 5.677976148228728e-06, "epoch": 16.061590436590436, "percentage": 80.31, "elapsed_time": "1:29:53", "remaining_time": "0:22:02", "throughput": 1031.77, "total_tokens": 5565320} {"current_steps": 61810, "total_steps": 76960, "loss": 0.4103, "lr": 5.674378995369712e-06, "epoch": 16.062889812889814, "percentage": 80.31, "elapsed_time": "1:29:54", "remaining_time": "0:22:02", "throughput": 1031.77, "total_tokens": 5565768} {"current_steps": 61815, "total_steps": 76960, "loss": 0.2209, "lr": 5.670782836445901e-06, "epoch": 16.06418918918919, "percentage": 80.32, "elapsed_time": "1:29:54", "remaining_time": "0:22:01", "throughput": 1031.78, "total_tokens": 5566232} {"current_steps": 61820, "total_steps": 76960, "loss": 0.0788, "lr": 5.667187671642246e-06, "epoch": 16.065488565488565, "percentage": 80.33, "elapsed_time": "1:29:55", "remaining_time": "0:22:01", "throughput": 1031.78, "total_tokens": 5566664} {"current_steps": 61825, "total_steps": 76960, "loss": 0.1011, "lr": 5.663593501143663e-06, "epoch": 16.066787941787943, "percentage": 80.33, "elapsed_time": "1:29:55", "remaining_time": "0:22:00", "throughput": 1031.77, "total_tokens": 5567080} {"current_steps": 61830, "total_steps": 76960, "loss": 0.0026, "lr": 5.660000325134987e-06, "epoch": 16.06808731808732, "percentage": 80.34, "elapsed_time": "1:29:56", "remaining_time": "0:22:00", "throughput": 1031.78, "total_tokens": 5567560} {"current_steps": 61835, "total_steps": 76960, "loss": 0.1381, "lr": 5.656408143801028e-06, "epoch": 16.069386694386694, "percentage": 80.35, "elapsed_time": "1:29:56", "remaining_time": "0:21:59", "throughput": 1031.79, "total_tokens": 5568024} {"current_steps": 61840, "total_steps": 76960, "loss": 0.2278, "lr": 5.6528169573265286e-06, "epoch": 16.070686070686072, "percentage": 80.35, "elapsed_time": "1:29:56", "remaining_time": "0:21:59", "throughput": 1031.79, "total_tokens": 5568472} {"current_steps": 61845, "total_steps": 76960, "loss": 0.2744, "lr": 5.649226765896199e-06, "epoch": 16.071985446985448, "percentage": 80.36, "elapsed_time": "1:29:57", "remaining_time": "0:21:59", "throughput": 1031.8, "total_tokens": 5568920} {"current_steps": 61850, "total_steps": 76960, "loss": 0.0367, "lr": 5.645637569694662e-06, "epoch": 16.073284823284823, "percentage": 80.37, "elapsed_time": "1:29:57", "remaining_time": "0:21:58", "throughput": 1031.81, "total_tokens": 5569400} {"current_steps": 61855, "total_steps": 76960, "loss": 0.3891, "lr": 5.642049368906544e-06, "epoch": 16.074584199584198, "percentage": 80.37, "elapsed_time": "1:29:58", "remaining_time": "0:21:58", "throughput": 1031.81, "total_tokens": 5569864} {"current_steps": 61860, "total_steps": 76960, "loss": 0.0055, "lr": 5.638462163716366e-06, "epoch": 16.075883575883577, "percentage": 80.38, "elapsed_time": "1:29:58", "remaining_time": "0:21:57", "throughput": 1031.81, "total_tokens": 5570296} {"current_steps": 61865, "total_steps": 76960, "loss": 0.0483, "lr": 5.634875954308638e-06, "epoch": 16.07718295218295, "percentage": 80.39, "elapsed_time": "1:29:58", "remaining_time": "0:21:57", "throughput": 1031.81, "total_tokens": 5570728} {"current_steps": 61870, "total_steps": 76960, "loss": 0.2142, "lr": 5.631290740867795e-06, "epoch": 16.078482328482327, "percentage": 80.39, "elapsed_time": "1:29:59", "remaining_time": "0:21:56", "throughput": 1031.82, "total_tokens": 5571192} {"current_steps": 61875, "total_steps": 76960, "loss": 0.0361, "lr": 5.627706523578219e-06, "epoch": 16.079781704781706, "percentage": 80.4, "elapsed_time": "1:29:59", "remaining_time": "0:21:56", "throughput": 1031.82, "total_tokens": 5571640} {"current_steps": 61880, "total_steps": 76960, "loss": 0.0209, "lr": 5.624123302624259e-06, "epoch": 16.08108108108108, "percentage": 80.41, "elapsed_time": "1:30:00", "remaining_time": "0:21:56", "throughput": 1031.83, "total_tokens": 5572104} {"current_steps": 61885, "total_steps": 76960, "loss": 0.049, "lr": 5.620541078190203e-06, "epoch": 16.082380457380456, "percentage": 80.41, "elapsed_time": "1:30:00", "remaining_time": "0:21:55", "throughput": 1031.83, "total_tokens": 5572536} {"current_steps": 61890, "total_steps": 76960, "loss": 0.0437, "lr": 5.616959850460296e-06, "epoch": 16.083679833679835, "percentage": 80.42, "elapsed_time": "1:30:01", "remaining_time": "0:21:55", "throughput": 1031.83, "total_tokens": 5572984} {"current_steps": 61895, "total_steps": 76960, "loss": 0.2189, "lr": 5.613379619618705e-06, "epoch": 16.08497920997921, "percentage": 80.42, "elapsed_time": "1:30:01", "remaining_time": "0:21:54", "throughput": 1031.83, "total_tokens": 5573400} {"current_steps": 61900, "total_steps": 76960, "loss": 0.2685, "lr": 5.609800385849587e-06, "epoch": 16.086278586278585, "percentage": 80.43, "elapsed_time": "1:30:01", "remaining_time": "0:21:54", "throughput": 1031.83, "total_tokens": 5573832} {"current_steps": 61905, "total_steps": 76960, "loss": 0.0158, "lr": 5.6062221493370035e-06, "epoch": 16.087577962577964, "percentage": 80.44, "elapsed_time": "1:30:02", "remaining_time": "0:21:53", "throughput": 1031.84, "total_tokens": 5574296} {"current_steps": 61910, "total_steps": 76960, "loss": 0.1095, "lr": 5.602644910265006e-06, "epoch": 16.08887733887734, "percentage": 80.44, "elapsed_time": "1:30:02", "remaining_time": "0:21:53", "throughput": 1031.84, "total_tokens": 5574728} {"current_steps": 61915, "total_steps": 76960, "loss": 0.022, "lr": 5.5990686688175585e-06, "epoch": 16.090176715176714, "percentage": 80.45, "elapsed_time": "1:30:03", "remaining_time": "0:21:52", "throughput": 1031.84, "total_tokens": 5575160} {"current_steps": 61920, "total_steps": 76960, "loss": 0.0108, "lr": 5.5954934251786e-06, "epoch": 16.091476091476093, "percentage": 80.46, "elapsed_time": "1:30:03", "remaining_time": "0:21:52", "throughput": 1031.84, "total_tokens": 5575592} {"current_steps": 61925, "total_steps": 76960, "loss": 0.2747, "lr": 5.591919179532007e-06, "epoch": 16.092775467775468, "percentage": 80.46, "elapsed_time": "1:30:03", "remaining_time": "0:21:52", "throughput": 1031.84, "total_tokens": 5576008} {"current_steps": 61930, "total_steps": 76960, "loss": 0.067, "lr": 5.588345932061612e-06, "epoch": 16.094074844074843, "percentage": 80.47, "elapsed_time": "1:30:04", "remaining_time": "0:21:51", "throughput": 1031.85, "total_tokens": 5576488} {"current_steps": 61935, "total_steps": 76960, "loss": 0.0114, "lr": 5.584773682951186e-06, "epoch": 16.09537422037422, "percentage": 80.48, "elapsed_time": "1:30:04", "remaining_time": "0:21:51", "throughput": 1031.85, "total_tokens": 5576936} {"current_steps": 61940, "total_steps": 76960, "loss": 0.1113, "lr": 5.581202432384444e-06, "epoch": 16.096673596673597, "percentage": 80.48, "elapsed_time": "1:30:05", "remaining_time": "0:21:50", "throughput": 1031.86, "total_tokens": 5577400} {"current_steps": 61945, "total_steps": 76960, "loss": 0.395, "lr": 5.577632180545075e-06, "epoch": 16.097972972972972, "percentage": 80.49, "elapsed_time": "1:30:05", "remaining_time": "0:21:50", "throughput": 1031.86, "total_tokens": 5577848} {"current_steps": 61950, "total_steps": 76960, "loss": 0.1271, "lr": 5.574062927616685e-06, "epoch": 16.09927234927235, "percentage": 80.5, "elapsed_time": "1:30:06", "remaining_time": "0:21:49", "throughput": 1031.87, "total_tokens": 5578312} {"current_steps": 61955, "total_steps": 76960, "loss": 0.333, "lr": 5.570494673782853e-06, "epoch": 16.100571725571726, "percentage": 80.5, "elapsed_time": "1:30:06", "remaining_time": "0:21:49", "throughput": 1031.87, "total_tokens": 5578776} {"current_steps": 61960, "total_steps": 76960, "loss": 0.0423, "lr": 5.566927419227094e-06, "epoch": 16.1018711018711, "percentage": 80.51, "elapsed_time": "1:30:06", "remaining_time": "0:21:48", "throughput": 1031.88, "total_tokens": 5579224} {"current_steps": 61965, "total_steps": 76960, "loss": 0.054, "lr": 5.563361164132888e-06, "epoch": 16.10317047817048, "percentage": 80.52, "elapsed_time": "1:30:07", "remaining_time": "0:21:48", "throughput": 1031.89, "total_tokens": 5579688} {"current_steps": 61970, "total_steps": 76960, "loss": 0.1279, "lr": 5.559795908683632e-06, "epoch": 16.104469854469855, "percentage": 80.52, "elapsed_time": "1:30:07", "remaining_time": "0:21:48", "throughput": 1031.89, "total_tokens": 5580152} {"current_steps": 61975, "total_steps": 76960, "loss": 0.2499, "lr": 5.556231653062705e-06, "epoch": 16.10576923076923, "percentage": 80.53, "elapsed_time": "1:30:08", "remaining_time": "0:21:47", "throughput": 1031.9, "total_tokens": 5580600} {"current_steps": 61980, "total_steps": 76960, "loss": 0.0712, "lr": 5.552668397453409e-06, "epoch": 16.10706860706861, "percentage": 80.54, "elapsed_time": "1:30:08", "remaining_time": "0:21:47", "throughput": 1031.9, "total_tokens": 5581048} {"current_steps": 61985, "total_steps": 76960, "loss": 0.3326, "lr": 5.549106142039018e-06, "epoch": 16.108367983367984, "percentage": 80.54, "elapsed_time": "1:30:08", "remaining_time": "0:21:46", "throughput": 1031.9, "total_tokens": 5581480} {"current_steps": 61990, "total_steps": 76960, "loss": 0.0065, "lr": 5.545544887002726e-06, "epoch": 16.10966735966736, "percentage": 80.55, "elapsed_time": "1:30:09", "remaining_time": "0:21:46", "throughput": 1031.9, "total_tokens": 5581928} {"current_steps": 61995, "total_steps": 76960, "loss": 0.0026, "lr": 5.541984632527702e-06, "epoch": 16.110966735966738, "percentage": 80.55, "elapsed_time": "1:30:09", "remaining_time": "0:21:45", "throughput": 1031.9, "total_tokens": 5582344} {"current_steps": 62000, "total_steps": 76960, "loss": 0.0029, "lr": 5.53842537879706e-06, "epoch": 16.112266112266113, "percentage": 80.56, "elapsed_time": "1:30:10", "remaining_time": "0:21:45", "throughput": 1031.9, "total_tokens": 5582776} {"current_steps": 62005, "total_steps": 76960, "loss": 0.0264, "lr": 5.534867125993839e-06, "epoch": 16.113565488565488, "percentage": 80.57, "elapsed_time": "1:30:10", "remaining_time": "0:21:44", "throughput": 1031.9, "total_tokens": 5583208} {"current_steps": 62010, "total_steps": 76960, "loss": 0.4728, "lr": 5.531309874301061e-06, "epoch": 16.114864864864863, "percentage": 80.57, "elapsed_time": "1:30:11", "remaining_time": "0:21:44", "throughput": 1031.91, "total_tokens": 5583688} {"current_steps": 62015, "total_steps": 76960, "loss": 0.0027, "lr": 5.527753623901663e-06, "epoch": 16.116164241164242, "percentage": 80.58, "elapsed_time": "1:30:11", "remaining_time": "0:21:44", "throughput": 1031.9, "total_tokens": 5584088} {"current_steps": 62020, "total_steps": 76960, "loss": 0.5481, "lr": 5.524198374978559e-06, "epoch": 16.117463617463617, "percentage": 80.59, "elapsed_time": "1:30:11", "remaining_time": "0:21:43", "throughput": 1031.91, "total_tokens": 5584520} {"current_steps": 62025, "total_steps": 76960, "loss": 0.1163, "lr": 5.520644127714589e-06, "epoch": 16.118762993762992, "percentage": 80.59, "elapsed_time": "1:30:12", "remaining_time": "0:21:43", "throughput": 1031.91, "total_tokens": 5584968} {"current_steps": 62030, "total_steps": 76960, "loss": 0.0265, "lr": 5.517090882292552e-06, "epoch": 16.12006237006237, "percentage": 80.6, "elapsed_time": "1:30:12", "remaining_time": "0:21:42", "throughput": 1031.91, "total_tokens": 5585416} {"current_steps": 62035, "total_steps": 76960, "loss": 0.0034, "lr": 5.5135386388952024e-06, "epoch": 16.121361746361746, "percentage": 80.61, "elapsed_time": "1:30:13", "remaining_time": "0:21:42", "throughput": 1031.92, "total_tokens": 5585880} {"current_steps": 62040, "total_steps": 76960, "loss": 0.0381, "lr": 5.509987397705238e-06, "epoch": 16.12266112266112, "percentage": 80.61, "elapsed_time": "1:30:13", "remaining_time": "0:21:41", "throughput": 1031.92, "total_tokens": 5586312} {"current_steps": 62045, "total_steps": 76960, "loss": 0.1397, "lr": 5.506437158905287e-06, "epoch": 16.1239604989605, "percentage": 80.62, "elapsed_time": "1:30:13", "remaining_time": "0:21:41", "throughput": 1031.91, "total_tokens": 5586712} {"current_steps": 62050, "total_steps": 76960, "loss": 0.0687, "lr": 5.50288792267796e-06, "epoch": 16.125259875259875, "percentage": 80.63, "elapsed_time": "1:30:14", "remaining_time": "0:21:41", "throughput": 1031.92, "total_tokens": 5587160} {"current_steps": 62055, "total_steps": 76960, "loss": 0.0609, "lr": 5.499339689205779e-06, "epoch": 16.12655925155925, "percentage": 80.63, "elapsed_time": "1:30:14", "remaining_time": "0:21:40", "throughput": 1031.93, "total_tokens": 5587640} {"current_steps": 62060, "total_steps": 76960, "loss": 0.0166, "lr": 5.49579245867125e-06, "epoch": 16.12785862785863, "percentage": 80.64, "elapsed_time": "1:30:15", "remaining_time": "0:21:40", "throughput": 1031.93, "total_tokens": 5588104} {"current_steps": 62065, "total_steps": 76960, "loss": 0.3359, "lr": 5.492246231256798e-06, "epoch": 16.129158004158004, "percentage": 80.65, "elapsed_time": "1:30:15", "remaining_time": "0:21:39", "throughput": 1031.94, "total_tokens": 5588552} {"current_steps": 62070, "total_steps": 76960, "loss": 0.3418, "lr": 5.488701007144812e-06, "epoch": 16.13045738045738, "percentage": 80.65, "elapsed_time": "1:30:16", "remaining_time": "0:21:39", "throughput": 1031.94, "total_tokens": 5589000} {"current_steps": 62075, "total_steps": 76960, "loss": 0.1266, "lr": 5.485156786517634e-06, "epoch": 16.131756756756758, "percentage": 80.66, "elapsed_time": "1:30:16", "remaining_time": "0:21:38", "throughput": 1031.94, "total_tokens": 5589432} {"current_steps": 62080, "total_steps": 76960, "loss": 0.0336, "lr": 5.481613569557536e-06, "epoch": 16.133056133056133, "percentage": 80.67, "elapsed_time": "1:30:16", "remaining_time": "0:21:38", "throughput": 1031.94, "total_tokens": 5589880} {"current_steps": 62085, "total_steps": 76960, "loss": 0.0014, "lr": 5.47807135644676e-06, "epoch": 16.134355509355508, "percentage": 80.67, "elapsed_time": "1:30:17", "remaining_time": "0:21:37", "throughput": 1031.95, "total_tokens": 5590344} {"current_steps": 62090, "total_steps": 76960, "loss": 0.2497, "lr": 5.474530147367471e-06, "epoch": 16.135654885654887, "percentage": 80.68, "elapsed_time": "1:30:17", "remaining_time": "0:21:37", "throughput": 1031.96, "total_tokens": 5590808} {"current_steps": 62095, "total_steps": 76960, "loss": 0.3827, "lr": 5.4709899425018144e-06, "epoch": 16.136954261954262, "percentage": 80.68, "elapsed_time": "1:30:18", "remaining_time": "0:21:37", "throughput": 1031.96, "total_tokens": 5591240} {"current_steps": 62100, "total_steps": 76960, "loss": 0.2393, "lr": 5.467450742031841e-06, "epoch": 16.138253638253637, "percentage": 80.69, "elapsed_time": "1:30:18", "remaining_time": "0:21:36", "throughput": 1031.96, "total_tokens": 5591672} {"current_steps": 62105, "total_steps": 76960, "loss": 0.1931, "lr": 5.4639125461396045e-06, "epoch": 16.139553014553016, "percentage": 80.7, "elapsed_time": "1:30:18", "remaining_time": "0:21:36", "throughput": 1031.97, "total_tokens": 5592152} {"current_steps": 62110, "total_steps": 76960, "loss": 0.4683, "lr": 5.460375355007058e-06, "epoch": 16.14085239085239, "percentage": 80.7, "elapsed_time": "1:30:19", "remaining_time": "0:21:35", "throughput": 1031.97, "total_tokens": 5592600} {"current_steps": 62115, "total_steps": 76960, "loss": 0.0614, "lr": 5.4568391688161355e-06, "epoch": 16.142151767151766, "percentage": 80.71, "elapsed_time": "1:30:19", "remaining_time": "0:21:35", "throughput": 1031.98, "total_tokens": 5593080} {"current_steps": 62120, "total_steps": 76960, "loss": 0.0033, "lr": 5.453303987748695e-06, "epoch": 16.143451143451145, "percentage": 80.72, "elapsed_time": "1:30:20", "remaining_time": "0:21:34", "throughput": 1031.98, "total_tokens": 5593512} {"current_steps": 62125, "total_steps": 76960, "loss": 0.0792, "lr": 5.449769811986563e-06, "epoch": 16.14475051975052, "percentage": 80.72, "elapsed_time": "1:30:20", "remaining_time": "0:21:34", "throughput": 1031.98, "total_tokens": 5593944} {"current_steps": 62130, "total_steps": 76960, "loss": 0.2419, "lr": 5.4462366417114965e-06, "epoch": 16.146049896049895, "percentage": 80.73, "elapsed_time": "1:30:21", "remaining_time": "0:21:33", "throughput": 1031.99, "total_tokens": 5594424} {"current_steps": 62135, "total_steps": 76960, "loss": 0.2128, "lr": 5.442704477105215e-06, "epoch": 16.147349272349274, "percentage": 80.74, "elapsed_time": "1:30:21", "remaining_time": "0:21:33", "throughput": 1031.99, "total_tokens": 5594856} {"current_steps": 62140, "total_steps": 76960, "loss": 0.3004, "lr": 5.439173318349389e-06, "epoch": 16.14864864864865, "percentage": 80.74, "elapsed_time": "1:30:21", "remaining_time": "0:21:33", "throughput": 1031.99, "total_tokens": 5595272} {"current_steps": 62145, "total_steps": 76960, "loss": 0.0326, "lr": 5.435643165625614e-06, "epoch": 16.149948024948024, "percentage": 80.75, "elapsed_time": "1:30:22", "remaining_time": "0:21:32", "throughput": 1031.99, "total_tokens": 5595736} {"current_steps": 62150, "total_steps": 76960, "loss": 0.004, "lr": 5.432114019115464e-06, "epoch": 16.151247401247403, "percentage": 80.76, "elapsed_time": "1:30:22", "remaining_time": "0:21:32", "throughput": 1032.0, "total_tokens": 5596184} {"current_steps": 62155, "total_steps": 76960, "loss": 0.2203, "lr": 5.42858587900043e-06, "epoch": 16.152546777546778, "percentage": 80.76, "elapsed_time": "1:30:23", "remaining_time": "0:21:31", "throughput": 1032.01, "total_tokens": 5596648} {"current_steps": 62160, "total_steps": 76960, "loss": 0.1263, "lr": 5.425058745461986e-06, "epoch": 16.153846153846153, "percentage": 80.77, "elapsed_time": "1:30:23", "remaining_time": "0:21:31", "throughput": 1032.01, "total_tokens": 5597112} {"current_steps": 62165, "total_steps": 76960, "loss": 0.2394, "lr": 5.4215326186815185e-06, "epoch": 16.15514553014553, "percentage": 80.78, "elapsed_time": "1:30:23", "remaining_time": "0:21:30", "throughput": 1032.01, "total_tokens": 5597544} {"current_steps": 62170, "total_steps": 76960, "loss": 0.2502, "lr": 5.418007498840388e-06, "epoch": 16.156444906444907, "percentage": 80.78, "elapsed_time": "1:30:24", "remaining_time": "0:21:30", "throughput": 1032.02, "total_tokens": 5597992} {"current_steps": 62175, "total_steps": 76960, "loss": 0.276, "lr": 5.4144833861198925e-06, "epoch": 16.157744282744282, "percentage": 80.79, "elapsed_time": "1:30:24", "remaining_time": "0:21:29", "throughput": 1032.02, "total_tokens": 5598456} {"current_steps": 62180, "total_steps": 76960, "loss": 0.4008, "lr": 5.410960280701291e-06, "epoch": 16.159043659043657, "percentage": 80.8, "elapsed_time": "1:30:25", "remaining_time": "0:21:29", "throughput": 1032.03, "total_tokens": 5598904} {"current_steps": 62185, "total_steps": 76960, "loss": 0.0006, "lr": 5.407438182765764e-06, "epoch": 16.160343035343036, "percentage": 80.8, "elapsed_time": "1:30:25", "remaining_time": "0:21:29", "throughput": 1032.03, "total_tokens": 5599352} {"current_steps": 62190, "total_steps": 76960, "loss": 0.0296, "lr": 5.403917092494473e-06, "epoch": 16.16164241164241, "percentage": 80.81, "elapsed_time": "1:30:25", "remaining_time": "0:21:28", "throughput": 1032.03, "total_tokens": 5599800} {"current_steps": 62195, "total_steps": 76960, "loss": 0.0169, "lr": 5.400397010068492e-06, "epoch": 16.162941787941786, "percentage": 80.81, "elapsed_time": "1:30:26", "remaining_time": "0:21:28", "throughput": 1032.04, "total_tokens": 5600264} {"current_steps": 62200, "total_steps": 76960, "loss": 0.0861, "lr": 5.396877935668882e-06, "epoch": 16.164241164241165, "percentage": 80.82, "elapsed_time": "1:30:26", "remaining_time": "0:21:27", "throughput": 1032.04, "total_tokens": 5600712} {"current_steps": 62205, "total_steps": 76960, "loss": 0.0046, "lr": 5.3933598694766135e-06, "epoch": 16.16554054054054, "percentage": 80.83, "elapsed_time": "1:30:27", "remaining_time": "0:21:27", "throughput": 1032.04, "total_tokens": 5601144} {"current_steps": 62210, "total_steps": 76960, "loss": 0.3716, "lr": 5.389842811672635e-06, "epoch": 16.166839916839916, "percentage": 80.83, "elapsed_time": "1:30:27", "remaining_time": "0:21:26", "throughput": 1032.04, "total_tokens": 5601576} {"current_steps": 62215, "total_steps": 76960, "loss": 0.231, "lr": 5.386326762437835e-06, "epoch": 16.168139293139294, "percentage": 80.84, "elapsed_time": "1:30:28", "remaining_time": "0:21:26", "throughput": 1032.05, "total_tokens": 5602040} {"current_steps": 62220, "total_steps": 76960, "loss": 0.1764, "lr": 5.3828117219530374e-06, "epoch": 16.16943866943867, "percentage": 80.85, "elapsed_time": "1:30:28", "remaining_time": "0:21:26", "throughput": 1032.06, "total_tokens": 5602520} {"current_steps": 62225, "total_steps": 76960, "loss": 0.3579, "lr": 5.379297690399035e-06, "epoch": 16.170738045738045, "percentage": 80.85, "elapsed_time": "1:30:28", "remaining_time": "0:21:25", "throughput": 1032.06, "total_tokens": 5602952} {"current_steps": 62230, "total_steps": 76960, "loss": 0.2631, "lr": 5.375784667956546e-06, "epoch": 16.172037422037423, "percentage": 80.86, "elapsed_time": "1:30:29", "remaining_time": "0:21:25", "throughput": 1032.07, "total_tokens": 5603432} {"current_steps": 62235, "total_steps": 76960, "loss": 0.0255, "lr": 5.37227265480626e-06, "epoch": 16.1733367983368, "percentage": 80.87, "elapsed_time": "1:30:29", "remaining_time": "0:21:24", "throughput": 1032.08, "total_tokens": 5603896} {"current_steps": 62240, "total_steps": 76960, "loss": 0.1957, "lr": 5.368761651128792e-06, "epoch": 16.174636174636174, "percentage": 80.87, "elapsed_time": "1:30:30", "remaining_time": "0:21:24", "throughput": 1032.08, "total_tokens": 5604344} {"current_steps": 62245, "total_steps": 76960, "loss": 0.2416, "lr": 5.3652516571047225e-06, "epoch": 16.175935550935552, "percentage": 80.88, "elapsed_time": "1:30:30", "remaining_time": "0:21:23", "throughput": 1032.08, "total_tokens": 5604792} {"current_steps": 62250, "total_steps": 76960, "loss": 0.003, "lr": 5.361742672914572e-06, "epoch": 16.177234927234927, "percentage": 80.89, "elapsed_time": "1:30:30", "remaining_time": "0:21:23", "throughput": 1032.09, "total_tokens": 5605272} {"current_steps": 62255, "total_steps": 76960, "loss": 0.0378, "lr": 5.35823469873882e-06, "epoch": 16.178534303534303, "percentage": 80.89, "elapsed_time": "1:30:31", "remaining_time": "0:21:22", "throughput": 1032.1, "total_tokens": 5605752} {"current_steps": 62260, "total_steps": 76960, "loss": 0.1449, "lr": 5.35472773475787e-06, "epoch": 16.17983367983368, "percentage": 80.9, "elapsed_time": "1:30:31", "remaining_time": "0:21:22", "throughput": 1032.11, "total_tokens": 5606200} {"current_steps": 62265, "total_steps": 76960, "loss": 0.0058, "lr": 5.351221781152102e-06, "epoch": 16.181133056133056, "percentage": 80.91, "elapsed_time": "1:30:32", "remaining_time": "0:21:22", "throughput": 1032.11, "total_tokens": 5606664} {"current_steps": 62270, "total_steps": 76960, "loss": 0.1172, "lr": 5.347716838101827e-06, "epoch": 16.18243243243243, "percentage": 80.91, "elapsed_time": "1:30:32", "remaining_time": "0:21:21", "throughput": 1032.12, "total_tokens": 5607144} {"current_steps": 62275, "total_steps": 76960, "loss": 0.4716, "lr": 5.344212905787296e-06, "epoch": 16.18373180873181, "percentage": 80.92, "elapsed_time": "1:30:33", "remaining_time": "0:21:21", "throughput": 1032.13, "total_tokens": 5607624} {"current_steps": 62280, "total_steps": 76960, "loss": 0.1473, "lr": 5.340709984388728e-06, "epoch": 16.185031185031185, "percentage": 80.93, "elapsed_time": "1:30:33", "remaining_time": "0:21:20", "throughput": 1032.13, "total_tokens": 5608056} {"current_steps": 62285, "total_steps": 76960, "loss": 0.4677, "lr": 5.337208074086284e-06, "epoch": 16.18633056133056, "percentage": 80.93, "elapsed_time": "1:30:33", "remaining_time": "0:21:20", "throughput": 1032.13, "total_tokens": 5608488} {"current_steps": 62290, "total_steps": 76960, "loss": 0.2707, "lr": 5.333707175060074e-06, "epoch": 16.18762993762994, "percentage": 80.94, "elapsed_time": "1:30:34", "remaining_time": "0:21:19", "throughput": 1032.14, "total_tokens": 5608936} {"current_steps": 62295, "total_steps": 76960, "loss": 0.1694, "lr": 5.330207287490141e-06, "epoch": 16.188929313929314, "percentage": 80.94, "elapsed_time": "1:30:34", "remaining_time": "0:21:19", "throughput": 1032.14, "total_tokens": 5609384} {"current_steps": 62300, "total_steps": 76960, "loss": 0.1264, "lr": 5.3267084115565e-06, "epoch": 16.19022869022869, "percentage": 80.95, "elapsed_time": "1:30:35", "remaining_time": "0:21:18", "throughput": 1032.14, "total_tokens": 5609816} {"current_steps": 62305, "total_steps": 76960, "loss": 0.1514, "lr": 5.3232105474390895e-06, "epoch": 16.191528066528065, "percentage": 80.96, "elapsed_time": "1:30:35", "remaining_time": "0:21:18", "throughput": 1032.14, "total_tokens": 5610248} {"current_steps": 62310, "total_steps": 76960, "loss": 0.0093, "lr": 5.3197136953178215e-06, "epoch": 16.192827442827443, "percentage": 80.96, "elapsed_time": "1:30:35", "remaining_time": "0:21:18", "throughput": 1032.14, "total_tokens": 5610696} {"current_steps": 62315, "total_steps": 76960, "loss": 0.1019, "lr": 5.316217855372527e-06, "epoch": 16.19412681912682, "percentage": 80.97, "elapsed_time": "1:30:36", "remaining_time": "0:21:17", "throughput": 1032.15, "total_tokens": 5611176} {"current_steps": 62320, "total_steps": 76960, "loss": 0.1287, "lr": 5.312723027783006e-06, "epoch": 16.195426195426194, "percentage": 80.98, "elapsed_time": "1:30:36", "remaining_time": "0:21:17", "throughput": 1032.15, "total_tokens": 5611608} {"current_steps": 62325, "total_steps": 76960, "loss": 0.0069, "lr": 5.309229212729009e-06, "epoch": 16.196725571725572, "percentage": 80.98, "elapsed_time": "1:30:37", "remaining_time": "0:21:16", "throughput": 1032.16, "total_tokens": 5612072} {"current_steps": 62330, "total_steps": 76960, "loss": 0.2817, "lr": 5.305736410390222e-06, "epoch": 16.198024948024948, "percentage": 80.99, "elapsed_time": "1:30:37", "remaining_time": "0:21:16", "throughput": 1032.17, "total_tokens": 5612552} {"current_steps": 62335, "total_steps": 76960, "loss": 0.3366, "lr": 5.302244620946284e-06, "epoch": 16.199324324324323, "percentage": 81.0, "elapsed_time": "1:30:38", "remaining_time": "0:21:15", "throughput": 1032.18, "total_tokens": 5613032} {"current_steps": 62340, "total_steps": 76960, "loss": 0.0158, "lr": 5.29875384457677e-06, "epoch": 16.2006237006237, "percentage": 81.0, "elapsed_time": "1:30:38", "remaining_time": "0:21:15", "throughput": 1032.18, "total_tokens": 5613464} {"current_steps": 62345, "total_steps": 76960, "loss": 0.1085, "lr": 5.295264081461232e-06, "epoch": 16.201923076923077, "percentage": 81.01, "elapsed_time": "1:30:38", "remaining_time": "0:21:14", "throughput": 1032.18, "total_tokens": 5613896} {"current_steps": 62350, "total_steps": 76960, "loss": 0.5694, "lr": 5.291775331779125e-06, "epoch": 16.203222453222452, "percentage": 81.02, "elapsed_time": "1:30:39", "remaining_time": "0:21:14", "throughput": 1032.18, "total_tokens": 5614328} {"current_steps": 62355, "total_steps": 76960, "loss": 0.0388, "lr": 5.288287595709915e-06, "epoch": 16.20452182952183, "percentage": 81.02, "elapsed_time": "1:30:39", "remaining_time": "0:21:14", "throughput": 1032.19, "total_tokens": 5614792} {"current_steps": 62360, "total_steps": 76960, "loss": 0.572, "lr": 5.284800873432949e-06, "epoch": 16.205821205821206, "percentage": 81.03, "elapsed_time": "1:30:40", "remaining_time": "0:21:13", "throughput": 1032.2, "total_tokens": 5615256} {"current_steps": 62365, "total_steps": 76960, "loss": 0.0035, "lr": 5.281315165127573e-06, "epoch": 16.20712058212058, "percentage": 81.04, "elapsed_time": "1:30:40", "remaining_time": "0:21:13", "throughput": 1032.2, "total_tokens": 5615736} {"current_steps": 62370, "total_steps": 76960, "loss": 0.0651, "lr": 5.277830470973047e-06, "epoch": 16.20841995841996, "percentage": 81.04, "elapsed_time": "1:30:40", "remaining_time": "0:21:12", "throughput": 1032.21, "total_tokens": 5616184} {"current_steps": 62375, "total_steps": 76960, "loss": 0.1839, "lr": 5.274346791148601e-06, "epoch": 16.209719334719335, "percentage": 81.05, "elapsed_time": "1:30:41", "remaining_time": "0:21:12", "throughput": 1032.21, "total_tokens": 5616600} {"current_steps": 62380, "total_steps": 76960, "loss": 0.0152, "lr": 5.270864125833394e-06, "epoch": 16.21101871101871, "percentage": 81.06, "elapsed_time": "1:30:41", "remaining_time": "0:21:11", "throughput": 1032.21, "total_tokens": 5617048} {"current_steps": 62385, "total_steps": 76960, "loss": 0.2868, "lr": 5.267382475206548e-06, "epoch": 16.21231808731809, "percentage": 81.06, "elapsed_time": "1:30:42", "remaining_time": "0:21:11", "throughput": 1032.22, "total_tokens": 5617512} {"current_steps": 62390, "total_steps": 76960, "loss": 0.1518, "lr": 5.263901839447128e-06, "epoch": 16.213617463617464, "percentage": 81.07, "elapsed_time": "1:30:42", "remaining_time": "0:21:11", "throughput": 1032.23, "total_tokens": 5618024} {"current_steps": 62395, "total_steps": 76960, "loss": 0.0247, "lr": 5.260422218734154e-06, "epoch": 16.21491683991684, "percentage": 81.07, "elapsed_time": "1:30:43", "remaining_time": "0:21:10", "throughput": 1032.23, "total_tokens": 5618456} {"current_steps": 62400, "total_steps": 76960, "loss": 0.1508, "lr": 5.256943613246579e-06, "epoch": 16.216216216216218, "percentage": 81.08, "elapsed_time": "1:30:43", "remaining_time": "0:21:10", "throughput": 1032.23, "total_tokens": 5618904} {"current_steps": 62405, "total_steps": 76960, "loss": 0.0227, "lr": 5.2534660231633036e-06, "epoch": 16.217515592515593, "percentage": 81.09, "elapsed_time": "1:30:43", "remaining_time": "0:21:09", "throughput": 1032.24, "total_tokens": 5619368} {"current_steps": 62410, "total_steps": 76960, "loss": 0.0037, "lr": 5.249989448663195e-06, "epoch": 16.218814968814968, "percentage": 81.09, "elapsed_time": "1:30:44", "remaining_time": "0:21:09", "throughput": 1032.25, "total_tokens": 5619864} {"current_steps": 62415, "total_steps": 76960, "loss": 0.1025, "lr": 5.24651388992505e-06, "epoch": 16.220114345114347, "percentage": 81.1, "elapsed_time": "1:30:44", "remaining_time": "0:21:08", "throughput": 1032.25, "total_tokens": 5620296} {"current_steps": 62420, "total_steps": 76960, "loss": 0.0464, "lr": 5.243039347127621e-06, "epoch": 16.22141372141372, "percentage": 81.11, "elapsed_time": "1:30:45", "remaining_time": "0:21:08", "throughput": 1032.26, "total_tokens": 5620744} {"current_steps": 62425, "total_steps": 76960, "loss": 0.022, "lr": 5.2395658204496075e-06, "epoch": 16.222713097713097, "percentage": 81.11, "elapsed_time": "1:30:45", "remaining_time": "0:21:07", "throughput": 1032.27, "total_tokens": 5621224} {"current_steps": 62430, "total_steps": 76960, "loss": 0.2409, "lr": 5.236093310069667e-06, "epoch": 16.224012474012476, "percentage": 81.12, "elapsed_time": "1:30:45", "remaining_time": "0:21:07", "throughput": 1032.27, "total_tokens": 5621688} {"current_steps": 62435, "total_steps": 76960, "loss": 0.0497, "lr": 5.232621816166375e-06, "epoch": 16.22531185031185, "percentage": 81.13, "elapsed_time": "1:30:46", "remaining_time": "0:21:07", "throughput": 1032.28, "total_tokens": 5622152} {"current_steps": 62440, "total_steps": 76960, "loss": 0.1787, "lr": 5.22915133891829e-06, "epoch": 16.226611226611226, "percentage": 81.13, "elapsed_time": "1:30:46", "remaining_time": "0:21:06", "throughput": 1032.29, "total_tokens": 5622632} {"current_steps": 62445, "total_steps": 76960, "loss": 0.0833, "lr": 5.225681878503891e-06, "epoch": 16.227910602910605, "percentage": 81.14, "elapsed_time": "1:30:47", "remaining_time": "0:21:06", "throughput": 1032.29, "total_tokens": 5623048} {"current_steps": 62450, "total_steps": 76960, "loss": 0.2311, "lr": 5.222213435101625e-06, "epoch": 16.22920997920998, "percentage": 81.15, "elapsed_time": "1:30:47", "remaining_time": "0:21:05", "throughput": 1032.29, "total_tokens": 5623512} {"current_steps": 62455, "total_steps": 76960, "loss": 0.3602, "lr": 5.218746008889863e-06, "epoch": 16.230509355509355, "percentage": 81.15, "elapsed_time": "1:30:48", "remaining_time": "0:21:05", "throughput": 1032.3, "total_tokens": 5623976} {"current_steps": 62460, "total_steps": 76960, "loss": 0.0008, "lr": 5.2152796000469514e-06, "epoch": 16.23180873180873, "percentage": 81.16, "elapsed_time": "1:30:48", "remaining_time": "0:21:04", "throughput": 1032.3, "total_tokens": 5624392} {"current_steps": 62465, "total_steps": 76960, "loss": 0.1238, "lr": 5.2118142087511705e-06, "epoch": 16.23310810810811, "percentage": 81.17, "elapsed_time": "1:30:48", "remaining_time": "0:21:04", "throughput": 1032.3, "total_tokens": 5624856} {"current_steps": 62470, "total_steps": 76960, "loss": 0.0064, "lr": 5.20834983518074e-06, "epoch": 16.234407484407484, "percentage": 81.17, "elapsed_time": "1:30:49", "remaining_time": "0:21:03", "throughput": 1032.31, "total_tokens": 5625336} {"current_steps": 62475, "total_steps": 76960, "loss": 0.1582, "lr": 5.2048864795138454e-06, "epoch": 16.23570686070686, "percentage": 81.18, "elapsed_time": "1:30:49", "remaining_time": "0:21:03", "throughput": 1032.31, "total_tokens": 5625768} {"current_steps": 62480, "total_steps": 76960, "loss": 0.4492, "lr": 5.2014241419286015e-06, "epoch": 16.237006237006238, "percentage": 81.19, "elapsed_time": "1:30:50", "remaining_time": "0:21:03", "throughput": 1032.31, "total_tokens": 5626184} {"current_steps": 62485, "total_steps": 76960, "loss": 0.2503, "lr": 5.197962822603092e-06, "epoch": 16.238305613305613, "percentage": 81.19, "elapsed_time": "1:30:50", "remaining_time": "0:21:02", "throughput": 1032.31, "total_tokens": 5626616} {"current_steps": 62490, "total_steps": 76960, "loss": 0.0588, "lr": 5.194502521715316e-06, "epoch": 16.239604989604988, "percentage": 81.2, "elapsed_time": "1:30:50", "remaining_time": "0:21:02", "throughput": 1032.33, "total_tokens": 5627128} {"current_steps": 62495, "total_steps": 76960, "loss": 0.3872, "lr": 5.191043239443258e-06, "epoch": 16.240904365904367, "percentage": 81.2, "elapsed_time": "1:30:51", "remaining_time": "0:21:01", "throughput": 1032.34, "total_tokens": 5627624} {"current_steps": 62500, "total_steps": 76960, "loss": 0.1534, "lr": 5.187584975964823e-06, "epoch": 16.242203742203742, "percentage": 81.21, "elapsed_time": "1:30:51", "remaining_time": "0:21:01", "throughput": 1032.34, "total_tokens": 5628088} {"current_steps": 62505, "total_steps": 76960, "loss": 0.0217, "lr": 5.184127731457883e-06, "epoch": 16.243503118503117, "percentage": 81.22, "elapsed_time": "1:30:52", "remaining_time": "0:21:00", "throughput": 1032.34, "total_tokens": 5628520} {"current_steps": 62510, "total_steps": 76960, "loss": 0.038, "lr": 5.1806715061002345e-06, "epoch": 16.244802494802496, "percentage": 81.22, "elapsed_time": "1:30:52", "remaining_time": "0:21:00", "throughput": 1032.34, "total_tokens": 5628952} {"current_steps": 62515, "total_steps": 76960, "loss": 0.1199, "lr": 5.177216300069645e-06, "epoch": 16.24610187110187, "percentage": 81.23, "elapsed_time": "1:30:53", "remaining_time": "0:20:59", "throughput": 1032.34, "total_tokens": 5629368} {"current_steps": 62520, "total_steps": 76960, "loss": 0.0927, "lr": 5.173762113543809e-06, "epoch": 16.247401247401246, "percentage": 81.24, "elapsed_time": "1:30:53", "remaining_time": "0:20:59", "throughput": 1032.35, "total_tokens": 5629832} {"current_steps": 62525, "total_steps": 76960, "loss": 0.0896, "lr": 5.1703089467003916e-06, "epoch": 16.248700623700625, "percentage": 81.24, "elapsed_time": "1:30:53", "remaining_time": "0:20:59", "throughput": 1032.35, "total_tokens": 5630280} {"current_steps": 62530, "total_steps": 76960, "loss": 0.1097, "lr": 5.16685679971698e-06, "epoch": 16.25, "percentage": 81.25, "elapsed_time": "1:30:54", "remaining_time": "0:20:58", "throughput": 1032.36, "total_tokens": 5630744} {"current_steps": 62535, "total_steps": 76960, "loss": 0.1063, "lr": 5.163405672771124e-06, "epoch": 16.251299376299375, "percentage": 81.26, "elapsed_time": "1:30:54", "remaining_time": "0:20:58", "throughput": 1032.37, "total_tokens": 5631208} {"current_steps": 62540, "total_steps": 76960, "loss": 0.3471, "lr": 5.159955566040325e-06, "epoch": 16.252598752598754, "percentage": 81.26, "elapsed_time": "1:30:55", "remaining_time": "0:20:57", "throughput": 1032.37, "total_tokens": 5631656} {"current_steps": 62545, "total_steps": 76960, "loss": 0.0205, "lr": 5.156506479702019e-06, "epoch": 16.25389812889813, "percentage": 81.27, "elapsed_time": "1:30:55", "remaining_time": "0:20:57", "throughput": 1032.37, "total_tokens": 5632104} {"current_steps": 62550, "total_steps": 76960, "loss": 0.1964, "lr": 5.153058413933601e-06, "epoch": 16.255197505197504, "percentage": 81.28, "elapsed_time": "1:30:55", "remaining_time": "0:20:56", "throughput": 1032.38, "total_tokens": 5632568} {"current_steps": 62555, "total_steps": 76960, "loss": 0.0453, "lr": 5.149611368912402e-06, "epoch": 16.256496881496883, "percentage": 81.28, "elapsed_time": "1:30:56", "remaining_time": "0:20:56", "throughput": 1032.38, "total_tokens": 5632984} {"current_steps": 62560, "total_steps": 76960, "loss": 0.7743, "lr": 5.146165344815715e-06, "epoch": 16.257796257796258, "percentage": 81.29, "elapsed_time": "1:30:56", "remaining_time": "0:20:56", "throughput": 1032.37, "total_tokens": 5633400} {"current_steps": 62565, "total_steps": 76960, "loss": 0.1814, "lr": 5.142720341820759e-06, "epoch": 16.259095634095633, "percentage": 81.3, "elapsed_time": "1:30:57", "remaining_time": "0:20:55", "throughput": 1032.39, "total_tokens": 5633896} {"current_steps": 62570, "total_steps": 76960, "loss": 0.1644, "lr": 5.139276360104725e-06, "epoch": 16.260395010395012, "percentage": 81.3, "elapsed_time": "1:30:57", "remaining_time": "0:20:55", "throughput": 1032.39, "total_tokens": 5634328} {"current_steps": 62575, "total_steps": 76960, "loss": 0.1145, "lr": 5.135833399844736e-06, "epoch": 16.261694386694387, "percentage": 81.31, "elapsed_time": "1:30:57", "remaining_time": "0:20:54", "throughput": 1032.39, "total_tokens": 5634792} {"current_steps": 62580, "total_steps": 76960, "loss": 0.1745, "lr": 5.1323914612178726e-06, "epoch": 16.262993762993762, "percentage": 81.31, "elapsed_time": "1:30:58", "remaining_time": "0:20:54", "throughput": 1032.4, "total_tokens": 5635240} {"current_steps": 62585, "total_steps": 76960, "loss": 0.1018, "lr": 5.1289505444011486e-06, "epoch": 16.26429313929314, "percentage": 81.32, "elapsed_time": "1:30:58", "remaining_time": "0:20:53", "throughput": 1032.4, "total_tokens": 5635704} {"current_steps": 62590, "total_steps": 76960, "loss": 0.0137, "lr": 5.125510649571543e-06, "epoch": 16.265592515592516, "percentage": 81.33, "elapsed_time": "1:30:59", "remaining_time": "0:20:53", "throughput": 1032.4, "total_tokens": 5636136} {"current_steps": 62595, "total_steps": 76960, "loss": 0.0805, "lr": 5.122071776905971e-06, "epoch": 16.26689189189189, "percentage": 81.33, "elapsed_time": "1:30:59", "remaining_time": "0:20:52", "throughput": 1032.41, "total_tokens": 5636600} {"current_steps": 62600, "total_steps": 76960, "loss": 0.0758, "lr": 5.118633926581276e-06, "epoch": 16.26819126819127, "percentage": 81.34, "elapsed_time": "1:31:00", "remaining_time": "0:20:52", "throughput": 1032.41, "total_tokens": 5637048} {"current_steps": 62605, "total_steps": 76960, "loss": 0.004, "lr": 5.115197098774302e-06, "epoch": 16.269490644490645, "percentage": 81.35, "elapsed_time": "1:31:00", "remaining_time": "0:20:52", "throughput": 1032.41, "total_tokens": 5637480} {"current_steps": 62610, "total_steps": 76960, "loss": 0.1915, "lr": 5.111761293661788e-06, "epoch": 16.27079002079002, "percentage": 81.35, "elapsed_time": "1:31:00", "remaining_time": "0:20:51", "throughput": 1032.42, "total_tokens": 5637960} {"current_steps": 62615, "total_steps": 76960, "loss": 0.2673, "lr": 5.108326511420453e-06, "epoch": 16.272089397089395, "percentage": 81.36, "elapsed_time": "1:31:01", "remaining_time": "0:20:51", "throughput": 1032.43, "total_tokens": 5638424} {"current_steps": 62620, "total_steps": 76960, "loss": 0.1631, "lr": 5.104892752226939e-06, "epoch": 16.273388773388774, "percentage": 81.37, "elapsed_time": "1:31:01", "remaining_time": "0:20:50", "throughput": 1032.43, "total_tokens": 5638872} {"current_steps": 62625, "total_steps": 76960, "loss": 0.3169, "lr": 5.101460016257859e-06, "epoch": 16.27468814968815, "percentage": 81.37, "elapsed_time": "1:31:02", "remaining_time": "0:20:50", "throughput": 1032.44, "total_tokens": 5639352} {"current_steps": 62630, "total_steps": 76960, "loss": 0.011, "lr": 5.09802830368975e-06, "epoch": 16.275987525987524, "percentage": 81.38, "elapsed_time": "1:31:02", "remaining_time": "0:20:49", "throughput": 1032.45, "total_tokens": 5639816} {"current_steps": 62635, "total_steps": 76960, "loss": 0.3361, "lr": 5.094597614699115e-06, "epoch": 16.277286902286903, "percentage": 81.39, "elapsed_time": "1:31:02", "remaining_time": "0:20:49", "throughput": 1032.45, "total_tokens": 5640280} {"current_steps": 62640, "total_steps": 76960, "loss": 0.2119, "lr": 5.091167949462397e-06, "epoch": 16.27858627858628, "percentage": 81.39, "elapsed_time": "1:31:03", "remaining_time": "0:20:48", "throughput": 1032.46, "total_tokens": 5640744} {"current_steps": 62645, "total_steps": 76960, "loss": 0.1133, "lr": 5.0877393081559924e-06, "epoch": 16.279885654885653, "percentage": 81.4, "elapsed_time": "1:31:03", "remaining_time": "0:20:48", "throughput": 1032.46, "total_tokens": 5641192} {"current_steps": 62650, "total_steps": 76960, "loss": 0.3325, "lr": 5.084311690956229e-06, "epoch": 16.281185031185032, "percentage": 81.41, "elapsed_time": "1:31:04", "remaining_time": "0:20:48", "throughput": 1032.46, "total_tokens": 5641624} {"current_steps": 62655, "total_steps": 76960, "loss": 0.4661, "lr": 5.080885098039404e-06, "epoch": 16.282484407484407, "percentage": 81.41, "elapsed_time": "1:31:04", "remaining_time": "0:20:47", "throughput": 1032.48, "total_tokens": 5642120} {"current_steps": 62660, "total_steps": 76960, "loss": 0.0423, "lr": 5.077459529581741e-06, "epoch": 16.283783783783782, "percentage": 81.42, "elapsed_time": "1:31:05", "remaining_time": "0:20:47", "throughput": 1032.48, "total_tokens": 5642584} {"current_steps": 62665, "total_steps": 76960, "loss": 0.1889, "lr": 5.074034985759421e-06, "epoch": 16.28508316008316, "percentage": 81.43, "elapsed_time": "1:31:05", "remaining_time": "0:20:46", "throughput": 1032.5, "total_tokens": 5643080} {"current_steps": 62670, "total_steps": 76960, "loss": 0.0206, "lr": 5.0706114667485705e-06, "epoch": 16.286382536382536, "percentage": 81.43, "elapsed_time": "1:31:05", "remaining_time": "0:20:46", "throughput": 1032.5, "total_tokens": 5643512} {"current_steps": 62675, "total_steps": 76960, "loss": 0.1885, "lr": 5.06718897272527e-06, "epoch": 16.28768191268191, "percentage": 81.44, "elapsed_time": "1:31:06", "remaining_time": "0:20:45", "throughput": 1032.49, "total_tokens": 5643928} {"current_steps": 62680, "total_steps": 76960, "loss": 0.042, "lr": 5.063767503865543e-06, "epoch": 16.28898128898129, "percentage": 81.44, "elapsed_time": "1:31:06", "remaining_time": "0:20:45", "throughput": 1032.5, "total_tokens": 5644392} {"current_steps": 62685, "total_steps": 76960, "loss": 0.0125, "lr": 5.060347060345352e-06, "epoch": 16.290280665280665, "percentage": 81.45, "elapsed_time": "1:31:07", "remaining_time": "0:20:45", "throughput": 1032.51, "total_tokens": 5644856} {"current_steps": 62690, "total_steps": 76960, "loss": 0.1287, "lr": 5.056927642340622e-06, "epoch": 16.29158004158004, "percentage": 81.46, "elapsed_time": "1:31:07", "remaining_time": "0:20:44", "throughput": 1032.51, "total_tokens": 5645304} {"current_steps": 62695, "total_steps": 76960, "loss": 0.1318, "lr": 5.053509250027205e-06, "epoch": 16.29287941787942, "percentage": 81.46, "elapsed_time": "1:31:07", "remaining_time": "0:20:44", "throughput": 1032.51, "total_tokens": 5645752} {"current_steps": 62700, "total_steps": 76960, "loss": 0.1484, "lr": 5.050091883580926e-06, "epoch": 16.294178794178794, "percentage": 81.47, "elapsed_time": "1:31:08", "remaining_time": "0:20:43", "throughput": 1032.52, "total_tokens": 5646216} {"current_steps": 62705, "total_steps": 76960, "loss": 0.3182, "lr": 5.0466755431775316e-06, "epoch": 16.29547817047817, "percentage": 81.48, "elapsed_time": "1:31:08", "remaining_time": "0:20:43", "throughput": 1032.52, "total_tokens": 5646664} {"current_steps": 62710, "total_steps": 76960, "loss": 0.0547, "lr": 5.04326022899273e-06, "epoch": 16.296777546777548, "percentage": 81.48, "elapsed_time": "1:31:09", "remaining_time": "0:20:42", "throughput": 1032.54, "total_tokens": 5647160} {"current_steps": 62715, "total_steps": 76960, "loss": 0.7436, "lr": 5.039845941202178e-06, "epoch": 16.298076923076923, "percentage": 81.49, "elapsed_time": "1:31:09", "remaining_time": "0:20:42", "throughput": 1032.54, "total_tokens": 5647592} {"current_steps": 62720, "total_steps": 76960, "loss": 0.0959, "lr": 5.036432679981482e-06, "epoch": 16.2993762993763, "percentage": 81.5, "elapsed_time": "1:31:10", "remaining_time": "0:20:41", "throughput": 1032.55, "total_tokens": 5648072} {"current_steps": 62725, "total_steps": 76960, "loss": 0.0057, "lr": 5.033020445506179e-06, "epoch": 16.300675675675677, "percentage": 81.5, "elapsed_time": "1:31:10", "remaining_time": "0:20:41", "throughput": 1032.56, "total_tokens": 5648584} {"current_steps": 62730, "total_steps": 76960, "loss": 0.1378, "lr": 5.02960923795176e-06, "epoch": 16.301975051975052, "percentage": 81.51, "elapsed_time": "1:31:10", "remaining_time": "0:20:41", "throughput": 1032.56, "total_tokens": 5649032} {"current_steps": 62735, "total_steps": 76960, "loss": 0.2636, "lr": 5.026199057493678e-06, "epoch": 16.303274428274428, "percentage": 81.52, "elapsed_time": "1:31:11", "remaining_time": "0:20:40", "throughput": 1032.56, "total_tokens": 5649448} {"current_steps": 62740, "total_steps": 76960, "loss": 0.3114, "lr": 5.022789904307312e-06, "epoch": 16.304573804573806, "percentage": 81.52, "elapsed_time": "1:31:11", "remaining_time": "0:20:40", "throughput": 1032.56, "total_tokens": 5649880} {"current_steps": 62745, "total_steps": 76960, "loss": 0.2308, "lr": 5.0193817785679995e-06, "epoch": 16.30587318087318, "percentage": 81.53, "elapsed_time": "1:31:12", "remaining_time": "0:20:39", "throughput": 1032.56, "total_tokens": 5650312} {"current_steps": 62750, "total_steps": 76960, "loss": 0.0036, "lr": 5.01597468045103e-06, "epoch": 16.307172557172557, "percentage": 81.54, "elapsed_time": "1:31:12", "remaining_time": "0:20:39", "throughput": 1032.56, "total_tokens": 5650712} {"current_steps": 62755, "total_steps": 76960, "loss": 0.0884, "lr": 5.012568610131635e-06, "epoch": 16.308471933471935, "percentage": 81.54, "elapsed_time": "1:31:12", "remaining_time": "0:20:38", "throughput": 1032.55, "total_tokens": 5651128} {"current_steps": 62760, "total_steps": 76960, "loss": 0.0255, "lr": 5.00916356778498e-06, "epoch": 16.30977130977131, "percentage": 81.55, "elapsed_time": "1:31:13", "remaining_time": "0:20:38", "throughput": 1032.55, "total_tokens": 5651560} {"current_steps": 62765, "total_steps": 76960, "loss": 0.0611, "lr": 5.005759553586206e-06, "epoch": 16.311070686070686, "percentage": 81.56, "elapsed_time": "1:31:13", "remaining_time": "0:20:37", "throughput": 1032.56, "total_tokens": 5652024} {"current_steps": 62770, "total_steps": 76960, "loss": 0.1438, "lr": 5.002356567710367e-06, "epoch": 16.31237006237006, "percentage": 81.56, "elapsed_time": "1:31:14", "remaining_time": "0:20:37", "throughput": 1032.56, "total_tokens": 5652472} {"current_steps": 62775, "total_steps": 76960, "loss": 0.0497, "lr": 4.998954610332499e-06, "epoch": 16.31366943866944, "percentage": 81.57, "elapsed_time": "1:31:14", "remaining_time": "0:20:37", "throughput": 1032.56, "total_tokens": 5652888} {"current_steps": 62780, "total_steps": 76960, "loss": 0.0323, "lr": 4.9955536816275516e-06, "epoch": 16.314968814968815, "percentage": 81.57, "elapsed_time": "1:31:15", "remaining_time": "0:20:36", "throughput": 1032.57, "total_tokens": 5653352} {"current_steps": 62785, "total_steps": 76960, "loss": 0.3066, "lr": 4.992153781770448e-06, "epoch": 16.31626819126819, "percentage": 81.58, "elapsed_time": "1:31:15", "remaining_time": "0:20:36", "throughput": 1032.57, "total_tokens": 5653800} {"current_steps": 62790, "total_steps": 76960, "loss": 0.0049, "lr": 4.98875491093605e-06, "epoch": 16.31756756756757, "percentage": 81.59, "elapsed_time": "1:31:15", "remaining_time": "0:20:35", "throughput": 1032.58, "total_tokens": 5654264} {"current_steps": 62795, "total_steps": 76960, "loss": 0.0112, "lr": 4.985357069299154e-06, "epoch": 16.318866943866944, "percentage": 81.59, "elapsed_time": "1:31:16", "remaining_time": "0:20:35", "throughput": 1032.58, "total_tokens": 5654728} {"current_steps": 62800, "total_steps": 76960, "loss": 0.2416, "lr": 4.981960257034529e-06, "epoch": 16.32016632016632, "percentage": 81.6, "elapsed_time": "1:31:16", "remaining_time": "0:20:34", "throughput": 1032.59, "total_tokens": 5655208} {"current_steps": 62805, "total_steps": 76960, "loss": 0.0014, "lr": 4.978564474316863e-06, "epoch": 16.321465696465697, "percentage": 81.61, "elapsed_time": "1:31:17", "remaining_time": "0:20:34", "throughput": 1032.6, "total_tokens": 5655656} {"current_steps": 62810, "total_steps": 76960, "loss": 0.1727, "lr": 4.975169721320813e-06, "epoch": 16.322765072765073, "percentage": 81.61, "elapsed_time": "1:31:17", "remaining_time": "0:20:33", "throughput": 1032.6, "total_tokens": 5656120} {"current_steps": 62815, "total_steps": 76960, "loss": 0.1057, "lr": 4.971775998220968e-06, "epoch": 16.324064449064448, "percentage": 81.62, "elapsed_time": "1:31:17", "remaining_time": "0:20:33", "throughput": 1032.61, "total_tokens": 5656584} {"current_steps": 62820, "total_steps": 76960, "loss": 0.2941, "lr": 4.96838330519187e-06, "epoch": 16.325363825363826, "percentage": 81.63, "elapsed_time": "1:31:18", "remaining_time": "0:20:33", "throughput": 1032.61, "total_tokens": 5657032} {"current_steps": 62825, "total_steps": 76960, "loss": 0.0112, "lr": 4.964991642408015e-06, "epoch": 16.3266632016632, "percentage": 81.63, "elapsed_time": "1:31:18", "remaining_time": "0:20:32", "throughput": 1032.61, "total_tokens": 5657464} {"current_steps": 62830, "total_steps": 76960, "loss": 0.1594, "lr": 4.96160101004384e-06, "epoch": 16.327962577962577, "percentage": 81.64, "elapsed_time": "1:31:19", "remaining_time": "0:20:32", "throughput": 1032.62, "total_tokens": 5657912} {"current_steps": 62835, "total_steps": 76960, "loss": 0.003, "lr": 4.958211408273722e-06, "epoch": 16.329261954261955, "percentage": 81.65, "elapsed_time": "1:31:19", "remaining_time": "0:20:31", "throughput": 1032.62, "total_tokens": 5658344} {"current_steps": 62840, "total_steps": 76960, "loss": 0.0497, "lr": 4.954822837271997e-06, "epoch": 16.33056133056133, "percentage": 81.65, "elapsed_time": "1:31:20", "remaining_time": "0:20:31", "throughput": 1032.62, "total_tokens": 5658792} {"current_steps": 62845, "total_steps": 76960, "loss": 0.2971, "lr": 4.951435297212937e-06, "epoch": 16.331860706860706, "percentage": 81.66, "elapsed_time": "1:31:20", "remaining_time": "0:20:30", "throughput": 1032.62, "total_tokens": 5659224} {"current_steps": 62850, "total_steps": 76960, "loss": 0.0394, "lr": 4.948048788270768e-06, "epoch": 16.333160083160084, "percentage": 81.67, "elapsed_time": "1:31:20", "remaining_time": "0:20:30", "throughput": 1032.63, "total_tokens": 5659688} {"current_steps": 62855, "total_steps": 76960, "loss": 0.2711, "lr": 4.9446633106196685e-06, "epoch": 16.33445945945946, "percentage": 81.67, "elapsed_time": "1:31:21", "remaining_time": "0:20:30", "throughput": 1032.63, "total_tokens": 5660152} {"current_steps": 62860, "total_steps": 76960, "loss": 0.0248, "lr": 4.9412788644337436e-06, "epoch": 16.335758835758835, "percentage": 81.68, "elapsed_time": "1:31:21", "remaining_time": "0:20:29", "throughput": 1032.63, "total_tokens": 5660584} {"current_steps": 62865, "total_steps": 76960, "loss": 0.1686, "lr": 4.937895449887075e-06, "epoch": 16.337058212058214, "percentage": 81.69, "elapsed_time": "1:31:22", "remaining_time": "0:20:29", "throughput": 1032.64, "total_tokens": 5661048} {"current_steps": 62870, "total_steps": 76960, "loss": 0.0628, "lr": 4.934513067153657e-06, "epoch": 16.33835758835759, "percentage": 81.69, "elapsed_time": "1:31:22", "remaining_time": "0:20:28", "throughput": 1032.64, "total_tokens": 5661464} {"current_steps": 62875, "total_steps": 76960, "loss": 0.0769, "lr": 4.9311317164074664e-06, "epoch": 16.339656964656964, "percentage": 81.7, "elapsed_time": "1:31:22", "remaining_time": "0:20:28", "throughput": 1032.65, "total_tokens": 5661944} {"current_steps": 62880, "total_steps": 76960, "loss": 0.0054, "lr": 4.927751397822391e-06, "epoch": 16.340956340956343, "percentage": 81.7, "elapsed_time": "1:31:23", "remaining_time": "0:20:27", "throughput": 1032.65, "total_tokens": 5662408} {"current_steps": 62885, "total_steps": 76960, "loss": 0.0036, "lr": 4.924372111572298e-06, "epoch": 16.342255717255718, "percentage": 81.71, "elapsed_time": "1:31:23", "remaining_time": "0:20:27", "throughput": 1032.66, "total_tokens": 5662856} {"current_steps": 62890, "total_steps": 76960, "loss": 0.0333, "lr": 4.92099385783098e-06, "epoch": 16.343555093555093, "percentage": 81.72, "elapsed_time": "1:31:24", "remaining_time": "0:20:26", "throughput": 1032.65, "total_tokens": 5663256} {"current_steps": 62895, "total_steps": 76960, "loss": 0.1852, "lr": 4.917616636772193e-06, "epoch": 16.34485446985447, "percentage": 81.72, "elapsed_time": "1:31:24", "remaining_time": "0:20:26", "throughput": 1032.65, "total_tokens": 5663688} {"current_steps": 62900, "total_steps": 76960, "loss": 0.2484, "lr": 4.914240448569621e-06, "epoch": 16.346153846153847, "percentage": 81.73, "elapsed_time": "1:31:25", "remaining_time": "0:20:26", "throughput": 1032.66, "total_tokens": 5664136} {"current_steps": 62905, "total_steps": 76960, "loss": 0.3928, "lr": 4.91086529339691e-06, "epoch": 16.347453222453222, "percentage": 81.74, "elapsed_time": "1:31:25", "remaining_time": "0:20:25", "throughput": 1032.66, "total_tokens": 5664584} {"current_steps": 62910, "total_steps": 76960, "loss": 0.0796, "lr": 4.907491171427642e-06, "epoch": 16.348752598752597, "percentage": 81.74, "elapsed_time": "1:31:25", "remaining_time": "0:20:25", "throughput": 1032.66, "total_tokens": 5665032} {"current_steps": 62915, "total_steps": 76960, "loss": 0.0692, "lr": 4.90411808283536e-06, "epoch": 16.350051975051976, "percentage": 81.75, "elapsed_time": "1:31:26", "remaining_time": "0:20:24", "throughput": 1032.67, "total_tokens": 5665528} {"current_steps": 62920, "total_steps": 76960, "loss": 0.0827, "lr": 4.900746027793535e-06, "epoch": 16.35135135135135, "percentage": 81.76, "elapsed_time": "1:31:26", "remaining_time": "0:20:24", "throughput": 1032.68, "total_tokens": 5666008} {"current_steps": 62925, "total_steps": 76960, "loss": 0.1277, "lr": 4.897375006475599e-06, "epoch": 16.352650727650726, "percentage": 81.76, "elapsed_time": "1:31:27", "remaining_time": "0:20:23", "throughput": 1032.68, "total_tokens": 5666440} {"current_steps": 62930, "total_steps": 76960, "loss": 0.4905, "lr": 4.894005019054934e-06, "epoch": 16.353950103950105, "percentage": 81.77, "elapsed_time": "1:31:27", "remaining_time": "0:20:23", "throughput": 1032.68, "total_tokens": 5666840} {"current_steps": 62935, "total_steps": 76960, "loss": 0.412, "lr": 4.890636065704848e-06, "epoch": 16.35524948024948, "percentage": 81.78, "elapsed_time": "1:31:27", "remaining_time": "0:20:22", "throughput": 1032.69, "total_tokens": 5667320} {"current_steps": 62940, "total_steps": 76960, "loss": 0.3717, "lr": 4.887268146598625e-06, "epoch": 16.356548856548855, "percentage": 81.78, "elapsed_time": "1:31:28", "remaining_time": "0:20:22", "throughput": 1032.69, "total_tokens": 5667736} {"current_steps": 62945, "total_steps": 76960, "loss": 0.0091, "lr": 4.883901261909465e-06, "epoch": 16.357848232848234, "percentage": 81.79, "elapsed_time": "1:31:28", "remaining_time": "0:20:22", "throughput": 1032.69, "total_tokens": 5668184} {"current_steps": 62950, "total_steps": 76960, "loss": 0.7774, "lr": 4.880535411810544e-06, "epoch": 16.35914760914761, "percentage": 81.8, "elapsed_time": "1:31:29", "remaining_time": "0:20:21", "throughput": 1032.7, "total_tokens": 5668664} {"current_steps": 62955, "total_steps": 76960, "loss": 0.3548, "lr": 4.877170596474959e-06, "epoch": 16.360446985446984, "percentage": 81.8, "elapsed_time": "1:31:29", "remaining_time": "0:20:21", "throughput": 1032.71, "total_tokens": 5669128} {"current_steps": 62960, "total_steps": 76960, "loss": 0.0564, "lr": 4.873806816075771e-06, "epoch": 16.361746361746363, "percentage": 81.81, "elapsed_time": "1:31:30", "remaining_time": "0:20:20", "throughput": 1032.71, "total_tokens": 5669608} {"current_steps": 62965, "total_steps": 76960, "loss": 0.2137, "lr": 4.870444070785981e-06, "epoch": 16.363045738045738, "percentage": 81.82, "elapsed_time": "1:31:30", "remaining_time": "0:20:20", "throughput": 1032.72, "total_tokens": 5670088} {"current_steps": 62970, "total_steps": 76960, "loss": 0.1001, "lr": 4.867082360778547e-06, "epoch": 16.364345114345113, "percentage": 81.82, "elapsed_time": "1:31:30", "remaining_time": "0:20:19", "throughput": 1032.73, "total_tokens": 5670552} {"current_steps": 62975, "total_steps": 76960, "loss": 0.1077, "lr": 4.86372168622635e-06, "epoch": 16.365644490644492, "percentage": 81.83, "elapsed_time": "1:31:31", "remaining_time": "0:20:19", "throughput": 1032.73, "total_tokens": 5670984} {"current_steps": 62980, "total_steps": 76960, "loss": 0.3849, "lr": 4.860362047302247e-06, "epoch": 16.366943866943867, "percentage": 81.83, "elapsed_time": "1:31:31", "remaining_time": "0:20:19", "throughput": 1032.74, "total_tokens": 5671480} {"current_steps": 62985, "total_steps": 76960, "loss": 0.156, "lr": 4.8570034441790226e-06, "epoch": 16.368243243243242, "percentage": 81.84, "elapsed_time": "1:31:32", "remaining_time": "0:20:18", "throughput": 1032.74, "total_tokens": 5671912} {"current_steps": 62990, "total_steps": 76960, "loss": 0.2336, "lr": 4.853645877029403e-06, "epoch": 16.36954261954262, "percentage": 81.85, "elapsed_time": "1:31:32", "remaining_time": "0:20:18", "throughput": 1032.75, "total_tokens": 5672360} {"current_steps": 62995, "total_steps": 76960, "loss": 0.0562, "lr": 4.850289346026079e-06, "epoch": 16.370841995841996, "percentage": 81.85, "elapsed_time": "1:31:32", "remaining_time": "0:20:17", "throughput": 1032.75, "total_tokens": 5672792} {"current_steps": 63000, "total_steps": 76960, "loss": 0.1142, "lr": 4.8469338513416814e-06, "epoch": 16.37214137214137, "percentage": 81.86, "elapsed_time": "1:31:33", "remaining_time": "0:20:17", "throughput": 1032.76, "total_tokens": 5673272} {"current_steps": 63005, "total_steps": 76960, "loss": 0.27, "lr": 4.843579393148792e-06, "epoch": 16.37344074844075, "percentage": 81.87, "elapsed_time": "1:31:33", "remaining_time": "0:20:16", "throughput": 1032.77, "total_tokens": 5673752} {"current_steps": 63010, "total_steps": 76960, "loss": 0.0926, "lr": 4.8402259716199215e-06, "epoch": 16.374740124740125, "percentage": 81.87, "elapsed_time": "1:31:34", "remaining_time": "0:20:16", "throughput": 1032.77, "total_tokens": 5674200} {"current_steps": 63015, "total_steps": 76960, "loss": 0.1036, "lr": 4.836873586927551e-06, "epoch": 16.3760395010395, "percentage": 81.88, "elapsed_time": "1:31:34", "remaining_time": "0:20:15", "throughput": 1032.77, "total_tokens": 5674648} {"current_steps": 63020, "total_steps": 76960, "loss": 0.6447, "lr": 4.833522239244085e-06, "epoch": 16.37733887733888, "percentage": 81.89, "elapsed_time": "1:31:34", "remaining_time": "0:20:15", "throughput": 1032.77, "total_tokens": 5675080} {"current_steps": 63025, "total_steps": 76960, "loss": 0.1313, "lr": 4.8301719287419e-06, "epoch": 16.378638253638254, "percentage": 81.89, "elapsed_time": "1:31:35", "remaining_time": "0:20:15", "throughput": 1032.78, "total_tokens": 5675544} {"current_steps": 63030, "total_steps": 76960, "loss": 0.2226, "lr": 4.826822655593291e-06, "epoch": 16.37993762993763, "percentage": 81.9, "elapsed_time": "1:31:35", "remaining_time": "0:20:14", "throughput": 1032.77, "total_tokens": 5675944} {"current_steps": 63035, "total_steps": 76960, "loss": 0.0532, "lr": 4.823474419970522e-06, "epoch": 16.381237006237008, "percentage": 81.91, "elapsed_time": "1:31:36", "remaining_time": "0:20:14", "throughput": 1032.78, "total_tokens": 5676392} {"current_steps": 63040, "total_steps": 76960, "loss": 0.2251, "lr": 4.8201272220457945e-06, "epoch": 16.382536382536383, "percentage": 81.91, "elapsed_time": "1:31:36", "remaining_time": "0:20:13", "throughput": 1032.78, "total_tokens": 5676824} {"current_steps": 63045, "total_steps": 76960, "loss": 0.0045, "lr": 4.816781061991268e-06, "epoch": 16.383835758835758, "percentage": 81.92, "elapsed_time": "1:31:37", "remaining_time": "0:20:13", "throughput": 1032.78, "total_tokens": 5677272} {"current_steps": 63050, "total_steps": 76960, "loss": 0.0731, "lr": 4.81343593997903e-06, "epoch": 16.385135135135137, "percentage": 81.93, "elapsed_time": "1:31:37", "remaining_time": "0:20:12", "throughput": 1032.78, "total_tokens": 5677672} {"current_steps": 63055, "total_steps": 76960, "loss": 0.0458, "lr": 4.810091856181118e-06, "epoch": 16.386434511434512, "percentage": 81.93, "elapsed_time": "1:31:37", "remaining_time": "0:20:12", "throughput": 1032.78, "total_tokens": 5678136} {"current_steps": 63060, "total_steps": 76960, "loss": 0.0382, "lr": 4.806748810769529e-06, "epoch": 16.387733887733887, "percentage": 81.94, "elapsed_time": "1:31:38", "remaining_time": "0:20:11", "throughput": 1032.78, "total_tokens": 5678536} {"current_steps": 63065, "total_steps": 76960, "loss": 0.1605, "lr": 4.803406803916194e-06, "epoch": 16.389033264033262, "percentage": 81.95, "elapsed_time": "1:31:38", "remaining_time": "0:20:11", "throughput": 1032.78, "total_tokens": 5678984} {"current_steps": 63070, "total_steps": 76960, "loss": 0.0611, "lr": 4.800065835792996e-06, "epoch": 16.39033264033264, "percentage": 81.95, "elapsed_time": "1:31:39", "remaining_time": "0:20:11", "throughput": 1032.78, "total_tokens": 5679416} {"current_steps": 63075, "total_steps": 76960, "loss": 0.5909, "lr": 4.796725906571769e-06, "epoch": 16.391632016632016, "percentage": 81.96, "elapsed_time": "1:31:39", "remaining_time": "0:20:10", "throughput": 1032.79, "total_tokens": 5679880} {"current_steps": 63080, "total_steps": 76960, "loss": 0.1981, "lr": 4.793387016424294e-06, "epoch": 16.39293139293139, "percentage": 81.96, "elapsed_time": "1:31:39", "remaining_time": "0:20:10", "throughput": 1032.8, "total_tokens": 5680360} {"current_steps": 63085, "total_steps": 76960, "loss": 0.0374, "lr": 4.790049165522278e-06, "epoch": 16.39423076923077, "percentage": 81.97, "elapsed_time": "1:31:40", "remaining_time": "0:20:09", "throughput": 1032.8, "total_tokens": 5680792} {"current_steps": 63090, "total_steps": 76960, "loss": 0.2965, "lr": 4.786712354037404e-06, "epoch": 16.395530145530145, "percentage": 81.98, "elapsed_time": "1:31:40", "remaining_time": "0:20:09", "throughput": 1032.8, "total_tokens": 5681240} {"current_steps": 63095, "total_steps": 76960, "loss": 0.0004, "lr": 4.783376582141275e-06, "epoch": 16.39682952182952, "percentage": 81.98, "elapsed_time": "1:31:41", "remaining_time": "0:20:08", "throughput": 1032.8, "total_tokens": 5681688} {"current_steps": 63100, "total_steps": 76960, "loss": 0.0646, "lr": 4.7800418500054565e-06, "epoch": 16.3981288981289, "percentage": 81.99, "elapsed_time": "1:31:41", "remaining_time": "0:20:08", "throughput": 1032.8, "total_tokens": 5682104} {"current_steps": 63105, "total_steps": 76960, "loss": 0.071, "lr": 4.776708157801463e-06, "epoch": 16.399428274428274, "percentage": 82.0, "elapsed_time": "1:31:42", "remaining_time": "0:20:08", "throughput": 1032.8, "total_tokens": 5682536} {"current_steps": 63110, "total_steps": 76960, "loss": 0.0016, "lr": 4.77337550570075e-06, "epoch": 16.40072765072765, "percentage": 82.0, "elapsed_time": "1:31:42", "remaining_time": "0:20:07", "throughput": 1032.81, "total_tokens": 5682984} {"current_steps": 63115, "total_steps": 76960, "loss": 0.0053, "lr": 4.770043893874715e-06, "epoch": 16.402027027027028, "percentage": 82.01, "elapsed_time": "1:31:42", "remaining_time": "0:20:07", "throughput": 1032.81, "total_tokens": 5683432} {"current_steps": 63120, "total_steps": 76960, "loss": 0.1299, "lr": 4.7667133224947006e-06, "epoch": 16.403326403326403, "percentage": 82.02, "elapsed_time": "1:31:43", "remaining_time": "0:20:06", "throughput": 1032.81, "total_tokens": 5683848} {"current_steps": 63125, "total_steps": 76960, "loss": 0.0022, "lr": 4.763383791732012e-06, "epoch": 16.40462577962578, "percentage": 82.02, "elapsed_time": "1:31:43", "remaining_time": "0:20:06", "throughput": 1032.81, "total_tokens": 5684296} {"current_steps": 63130, "total_steps": 76960, "loss": 0.045, "lr": 4.760055301757879e-06, "epoch": 16.405925155925157, "percentage": 82.03, "elapsed_time": "1:31:44", "remaining_time": "0:20:05", "throughput": 1032.81, "total_tokens": 5684728} {"current_steps": 63135, "total_steps": 76960, "loss": 0.1209, "lr": 4.756727852743495e-06, "epoch": 16.407224532224532, "percentage": 82.04, "elapsed_time": "1:31:44", "remaining_time": "0:20:05", "throughput": 1032.81, "total_tokens": 5685176} {"current_steps": 63140, "total_steps": 76960, "loss": 0.0334, "lr": 4.753401444859995e-06, "epoch": 16.408523908523907, "percentage": 82.04, "elapsed_time": "1:31:44", "remaining_time": "0:20:04", "throughput": 1032.82, "total_tokens": 5685624} {"current_steps": 63145, "total_steps": 76960, "loss": 0.3521, "lr": 4.750076078278462e-06, "epoch": 16.409823284823286, "percentage": 82.05, "elapsed_time": "1:31:45", "remaining_time": "0:20:04", "throughput": 1032.82, "total_tokens": 5686088} {"current_steps": 63150, "total_steps": 76960, "loss": 0.1048, "lr": 4.746751753169915e-06, "epoch": 16.41112266112266, "percentage": 82.06, "elapsed_time": "1:31:45", "remaining_time": "0:20:04", "throughput": 1032.83, "total_tokens": 5686568} {"current_steps": 63155, "total_steps": 76960, "loss": 0.3258, "lr": 4.743428469705335e-06, "epoch": 16.412422037422036, "percentage": 82.06, "elapsed_time": "1:31:46", "remaining_time": "0:20:03", "throughput": 1032.84, "total_tokens": 5687048} {"current_steps": 63160, "total_steps": 76960, "loss": 0.2814, "lr": 4.740106228055632e-06, "epoch": 16.413721413721415, "percentage": 82.07, "elapsed_time": "1:31:46", "remaining_time": "0:20:03", "throughput": 1032.85, "total_tokens": 5687512} {"current_steps": 63165, "total_steps": 76960, "loss": 0.209, "lr": 4.736785028391685e-06, "epoch": 16.41502079002079, "percentage": 82.08, "elapsed_time": "1:31:47", "remaining_time": "0:20:02", "throughput": 1032.85, "total_tokens": 5687960} {"current_steps": 63170, "total_steps": 76960, "loss": 0.0844, "lr": 4.733464870884291e-06, "epoch": 16.416320166320165, "percentage": 82.08, "elapsed_time": "1:31:47", "remaining_time": "0:20:02", "throughput": 1032.86, "total_tokens": 5688440} {"current_steps": 63175, "total_steps": 76960, "loss": 0.3537, "lr": 4.730145755704218e-06, "epoch": 16.417619542619544, "percentage": 82.09, "elapsed_time": "1:31:47", "remaining_time": "0:20:01", "throughput": 1032.87, "total_tokens": 5688904} {"current_steps": 63180, "total_steps": 76960, "loss": 0.4325, "lr": 4.726827683022178e-06, "epoch": 16.41891891891892, "percentage": 82.09, "elapsed_time": "1:31:48", "remaining_time": "0:20:01", "throughput": 1032.87, "total_tokens": 5689336} {"current_steps": 63185, "total_steps": 76960, "loss": 0.0496, "lr": 4.7235106530088085e-06, "epoch": 16.420218295218294, "percentage": 82.1, "elapsed_time": "1:31:48", "remaining_time": "0:20:00", "throughput": 1032.87, "total_tokens": 5689784} {"current_steps": 63190, "total_steps": 76960, "loss": 0.0028, "lr": 4.720194665834721e-06, "epoch": 16.421517671517673, "percentage": 82.11, "elapsed_time": "1:31:49", "remaining_time": "0:20:00", "throughput": 1032.87, "total_tokens": 5690200} {"current_steps": 63195, "total_steps": 76960, "loss": 0.4021, "lr": 4.7168797216704445e-06, "epoch": 16.42281704781705, "percentage": 82.11, "elapsed_time": "1:31:49", "remaining_time": "0:20:00", "throughput": 1032.88, "total_tokens": 5690664} {"current_steps": 63200, "total_steps": 76960, "loss": 0.0706, "lr": 4.713565820686486e-06, "epoch": 16.424116424116423, "percentage": 82.12, "elapsed_time": "1:31:49", "remaining_time": "0:19:59", "throughput": 1032.88, "total_tokens": 5691128} {"current_steps": 63205, "total_steps": 76960, "loss": 0.0061, "lr": 4.710252963053268e-06, "epoch": 16.4254158004158, "percentage": 82.13, "elapsed_time": "1:31:50", "remaining_time": "0:19:59", "throughput": 1032.89, "total_tokens": 5691592} {"current_steps": 63210, "total_steps": 76960, "loss": 0.0378, "lr": 4.706941148941179e-06, "epoch": 16.426715176715177, "percentage": 82.13, "elapsed_time": "1:31:50", "remaining_time": "0:19:58", "throughput": 1032.9, "total_tokens": 5692072} {"current_steps": 63215, "total_steps": 76960, "loss": 0.0779, "lr": 4.703630378520554e-06, "epoch": 16.428014553014552, "percentage": 82.14, "elapsed_time": "1:31:51", "remaining_time": "0:19:58", "throughput": 1032.89, "total_tokens": 5692472} {"current_steps": 63220, "total_steps": 76960, "loss": 0.3509, "lr": 4.7003206519616706e-06, "epoch": 16.429313929313928, "percentage": 82.15, "elapsed_time": "1:31:51", "remaining_time": "0:19:57", "throughput": 1032.9, "total_tokens": 5692936} {"current_steps": 63225, "total_steps": 76960, "loss": 0.2667, "lr": 4.6970119694347394e-06, "epoch": 16.430613305613306, "percentage": 82.15, "elapsed_time": "1:31:52", "remaining_time": "0:19:57", "throughput": 1032.91, "total_tokens": 5693448} {"current_steps": 63230, "total_steps": 76960, "loss": 0.1248, "lr": 4.693704331109943e-06, "epoch": 16.43191268191268, "percentage": 82.16, "elapsed_time": "1:31:52", "remaining_time": "0:19:56", "throughput": 1032.92, "total_tokens": 5693896} {"current_steps": 63235, "total_steps": 76960, "loss": 0.1292, "lr": 4.690397737157384e-06, "epoch": 16.433212058212057, "percentage": 82.17, "elapsed_time": "1:31:52", "remaining_time": "0:19:56", "throughput": 1032.92, "total_tokens": 5694344} {"current_steps": 63240, "total_steps": 76960, "loss": 0.1064, "lr": 4.687092187747136e-06, "epoch": 16.434511434511435, "percentage": 82.17, "elapsed_time": "1:31:53", "remaining_time": "0:19:56", "throughput": 1032.93, "total_tokens": 5694824} {"current_steps": 63245, "total_steps": 76960, "loss": 0.2106, "lr": 4.68378768304919e-06, "epoch": 16.43581081081081, "percentage": 82.18, "elapsed_time": "1:31:53", "remaining_time": "0:19:55", "throughput": 1032.93, "total_tokens": 5695256} {"current_steps": 63250, "total_steps": 76960, "loss": 0.4923, "lr": 4.680484223233511e-06, "epoch": 16.437110187110186, "percentage": 82.19, "elapsed_time": "1:31:54", "remaining_time": "0:19:55", "throughput": 1032.94, "total_tokens": 5695720} {"current_steps": 63255, "total_steps": 76960, "loss": 0.1882, "lr": 4.677181808470005e-06, "epoch": 16.438409563409564, "percentage": 82.19, "elapsed_time": "1:31:54", "remaining_time": "0:19:54", "throughput": 1032.94, "total_tokens": 5696152} {"current_steps": 63260, "total_steps": 76960, "loss": 0.0397, "lr": 4.673880438928505e-06, "epoch": 16.43970893970894, "percentage": 82.2, "elapsed_time": "1:31:54", "remaining_time": "0:19:54", "throughput": 1032.94, "total_tokens": 5696584} {"current_steps": 63265, "total_steps": 76960, "loss": 0.3442, "lr": 4.670580114778813e-06, "epoch": 16.441008316008315, "percentage": 82.21, "elapsed_time": "1:31:55", "remaining_time": "0:19:53", "throughput": 1032.94, "total_tokens": 5697032} {"current_steps": 63270, "total_steps": 76960, "loss": 0.0113, "lr": 4.66728083619066e-06, "epoch": 16.442307692307693, "percentage": 82.21, "elapsed_time": "1:31:55", "remaining_time": "0:19:53", "throughput": 1032.95, "total_tokens": 5697496} {"current_steps": 63275, "total_steps": 76960, "loss": 0.075, "lr": 4.663982603333741e-06, "epoch": 16.44360706860707, "percentage": 82.22, "elapsed_time": "1:31:56", "remaining_time": "0:19:53", "throughput": 1032.95, "total_tokens": 5697944} {"current_steps": 63280, "total_steps": 76960, "loss": 0.2732, "lr": 4.660685416377677e-06, "epoch": 16.444906444906444, "percentage": 82.22, "elapsed_time": "1:31:56", "remaining_time": "0:19:52", "throughput": 1032.95, "total_tokens": 5698376} {"current_steps": 63285, "total_steps": 76960, "loss": 0.0014, "lr": 4.65738927549205e-06, "epoch": 16.446205821205822, "percentage": 82.23, "elapsed_time": "1:31:57", "remaining_time": "0:19:52", "throughput": 1032.95, "total_tokens": 5698824} {"current_steps": 63290, "total_steps": 76960, "loss": 0.0793, "lr": 4.654094180846383e-06, "epoch": 16.447505197505198, "percentage": 82.24, "elapsed_time": "1:31:57", "remaining_time": "0:19:51", "throughput": 1032.96, "total_tokens": 5699256} {"current_steps": 63295, "total_steps": 76960, "loss": 0.2048, "lr": 4.650800132610153e-06, "epoch": 16.448804573804573, "percentage": 82.24, "elapsed_time": "1:31:57", "remaining_time": "0:19:51", "throughput": 1032.96, "total_tokens": 5699704} {"current_steps": 63300, "total_steps": 76960, "loss": 0.0772, "lr": 4.647507130952763e-06, "epoch": 16.45010395010395, "percentage": 82.25, "elapsed_time": "1:31:58", "remaining_time": "0:19:50", "throughput": 1032.96, "total_tokens": 5700152} {"current_steps": 63305, "total_steps": 76960, "loss": 0.0758, "lr": 4.6442151760435895e-06, "epoch": 16.451403326403327, "percentage": 82.26, "elapsed_time": "1:31:58", "remaining_time": "0:19:50", "throughput": 1032.97, "total_tokens": 5700632} {"current_steps": 63310, "total_steps": 76960, "loss": 0.0608, "lr": 4.640924268051933e-06, "epoch": 16.4527027027027, "percentage": 82.26, "elapsed_time": "1:31:59", "remaining_time": "0:19:49", "throughput": 1032.97, "total_tokens": 5701080} {"current_steps": 63315, "total_steps": 76960, "loss": 0.468, "lr": 4.637634407147043e-06, "epoch": 16.45400207900208, "percentage": 82.27, "elapsed_time": "1:31:59", "remaining_time": "0:19:49", "throughput": 1032.98, "total_tokens": 5701560} {"current_steps": 63320, "total_steps": 76960, "loss": 0.0735, "lr": 4.6343455934981235e-06, "epoch": 16.455301455301456, "percentage": 82.28, "elapsed_time": "1:31:59", "remaining_time": "0:19:49", "throughput": 1032.99, "total_tokens": 5702040} {"current_steps": 63325, "total_steps": 76960, "loss": 0.04, "lr": 4.631057827274327e-06, "epoch": 16.45660083160083, "percentage": 82.28, "elapsed_time": "1:32:00", "remaining_time": "0:19:48", "throughput": 1033.0, "total_tokens": 5702520} {"current_steps": 63330, "total_steps": 76960, "loss": 0.0024, "lr": 4.627771108644746e-06, "epoch": 16.45790020790021, "percentage": 82.29, "elapsed_time": "1:32:00", "remaining_time": "0:19:48", "throughput": 1033.01, "total_tokens": 5702984} {"current_steps": 63335, "total_steps": 76960, "loss": 0.3865, "lr": 4.624485437778414e-06, "epoch": 16.459199584199585, "percentage": 82.3, "elapsed_time": "1:32:01", "remaining_time": "0:19:47", "throughput": 1033.01, "total_tokens": 5703416} {"current_steps": 63340, "total_steps": 76960, "loss": 0.0022, "lr": 4.621200814844323e-06, "epoch": 16.46049896049896, "percentage": 82.3, "elapsed_time": "1:32:01", "remaining_time": "0:19:47", "throughput": 1033.02, "total_tokens": 5703896} {"current_steps": 63345, "total_steps": 76960, "loss": 0.1948, "lr": 4.617917240011394e-06, "epoch": 16.46179833679834, "percentage": 82.31, "elapsed_time": "1:32:02", "remaining_time": "0:19:46", "throughput": 1033.02, "total_tokens": 5704360} {"current_steps": 63350, "total_steps": 76960, "loss": 0.2004, "lr": 4.61463471344851e-06, "epoch": 16.463097713097714, "percentage": 82.32, "elapsed_time": "1:32:02", "remaining_time": "0:19:46", "throughput": 1033.03, "total_tokens": 5704824} {"current_steps": 63355, "total_steps": 76960, "loss": 0.2179, "lr": 4.611353235324494e-06, "epoch": 16.46439708939709, "percentage": 82.32, "elapsed_time": "1:32:02", "remaining_time": "0:19:45", "throughput": 1033.03, "total_tokens": 5705272} {"current_steps": 63360, "total_steps": 76960, "loss": 0.0005, "lr": 4.608072805808125e-06, "epoch": 16.465696465696467, "percentage": 82.33, "elapsed_time": "1:32:03", "remaining_time": "0:19:45", "throughput": 1033.05, "total_tokens": 5705768} {"current_steps": 63365, "total_steps": 76960, "loss": 0.0423, "lr": 4.604793425068102e-06, "epoch": 16.466995841995843, "percentage": 82.33, "elapsed_time": "1:32:03", "remaining_time": "0:19:45", "throughput": 1033.05, "total_tokens": 5706232} {"current_steps": 63370, "total_steps": 76960, "loss": 0.095, "lr": 4.601515093273101e-06, "epoch": 16.468295218295218, "percentage": 82.34, "elapsed_time": "1:32:04", "remaining_time": "0:19:44", "throughput": 1033.06, "total_tokens": 5706696} {"current_steps": 63375, "total_steps": 76960, "loss": 0.1, "lr": 4.598237810591727e-06, "epoch": 16.469594594594593, "percentage": 82.35, "elapsed_time": "1:32:04", "remaining_time": "0:19:44", "throughput": 1033.05, "total_tokens": 5707096} {"current_steps": 63380, "total_steps": 76960, "loss": 0.0043, "lr": 4.594961577192522e-06, "epoch": 16.47089397089397, "percentage": 82.35, "elapsed_time": "1:32:04", "remaining_time": "0:19:43", "throughput": 1033.06, "total_tokens": 5707560} {"current_steps": 63385, "total_steps": 76960, "loss": 0.0881, "lr": 4.5916863932439934e-06, "epoch": 16.472193347193347, "percentage": 82.36, "elapsed_time": "1:32:05", "remaining_time": "0:19:43", "throughput": 1033.06, "total_tokens": 5708008} {"current_steps": 63390, "total_steps": 76960, "loss": 0.1298, "lr": 4.58841225891459e-06, "epoch": 16.473492723492722, "percentage": 82.37, "elapsed_time": "1:32:05", "remaining_time": "0:19:42", "throughput": 1033.06, "total_tokens": 5708440} {"current_steps": 63395, "total_steps": 76960, "loss": 0.0024, "lr": 4.585139174372704e-06, "epoch": 16.4747920997921, "percentage": 82.37, "elapsed_time": "1:32:06", "remaining_time": "0:19:42", "throughput": 1033.07, "total_tokens": 5708888} {"current_steps": 63400, "total_steps": 76960, "loss": 0.2526, "lr": 4.581867139786669e-06, "epoch": 16.476091476091476, "percentage": 82.38, "elapsed_time": "1:32:06", "remaining_time": "0:19:42", "throughput": 1033.07, "total_tokens": 5709336} {"current_steps": 63405, "total_steps": 76960, "loss": 0.0083, "lr": 4.578596155324774e-06, "epoch": 16.47739085239085, "percentage": 82.39, "elapsed_time": "1:32:06", "remaining_time": "0:19:41", "throughput": 1033.07, "total_tokens": 5709784} {"current_steps": 63410, "total_steps": 76960, "loss": 0.1108, "lr": 4.57532622115524e-06, "epoch": 16.47869022869023, "percentage": 82.39, "elapsed_time": "1:32:07", "remaining_time": "0:19:41", "throughput": 1033.08, "total_tokens": 5710264} {"current_steps": 63415, "total_steps": 76960, "loss": 0.0289, "lr": 4.572057337446256e-06, "epoch": 16.479989604989605, "percentage": 82.4, "elapsed_time": "1:32:07", "remaining_time": "0:19:40", "throughput": 1033.08, "total_tokens": 5710680} {"current_steps": 63420, "total_steps": 76960, "loss": 0.0197, "lr": 4.56878950436593e-06, "epoch": 16.48128898128898, "percentage": 82.41, "elapsed_time": "1:32:08", "remaining_time": "0:19:40", "throughput": 1033.08, "total_tokens": 5711112} {"current_steps": 63425, "total_steps": 76960, "loss": 0.17, "lr": 4.565522722082336e-06, "epoch": 16.48258835758836, "percentage": 82.41, "elapsed_time": "1:32:08", "remaining_time": "0:19:39", "throughput": 1033.08, "total_tokens": 5711544} {"current_steps": 63430, "total_steps": 76960, "loss": 0.0026, "lr": 4.562256990763486e-06, "epoch": 16.483887733887734, "percentage": 82.42, "elapsed_time": "1:32:09", "remaining_time": "0:19:39", "throughput": 1033.08, "total_tokens": 5711976} {"current_steps": 63435, "total_steps": 76960, "loss": 0.1468, "lr": 4.558992310577348e-06, "epoch": 16.48518711018711, "percentage": 82.43, "elapsed_time": "1:32:09", "remaining_time": "0:19:38", "throughput": 1033.08, "total_tokens": 5712408} {"current_steps": 63440, "total_steps": 76960, "loss": 0.1573, "lr": 4.5557286816918205e-06, "epoch": 16.486486486486488, "percentage": 82.43, "elapsed_time": "1:32:09", "remaining_time": "0:19:38", "throughput": 1033.08, "total_tokens": 5712840} {"current_steps": 63445, "total_steps": 76960, "loss": 0.2124, "lr": 4.552466104274752e-06, "epoch": 16.487785862785863, "percentage": 82.44, "elapsed_time": "1:32:10", "remaining_time": "0:19:38", "throughput": 1033.08, "total_tokens": 5713288} {"current_steps": 63450, "total_steps": 76960, "loss": 0.0039, "lr": 4.549204578493949e-06, "epoch": 16.489085239085238, "percentage": 82.45, "elapsed_time": "1:32:10", "remaining_time": "0:19:37", "throughput": 1033.1, "total_tokens": 5713816} {"current_steps": 63455, "total_steps": 76960, "loss": 0.3131, "lr": 4.5459441045171414e-06, "epoch": 16.490384615384617, "percentage": 82.45, "elapsed_time": "1:32:11", "remaining_time": "0:19:37", "throughput": 1033.11, "total_tokens": 5714280} {"current_steps": 63460, "total_steps": 76960, "loss": 0.2739, "lr": 4.54268468251203e-06, "epoch": 16.491683991683992, "percentage": 82.46, "elapsed_time": "1:32:11", "remaining_time": "0:19:36", "throughput": 1033.11, "total_tokens": 5714712} {"current_steps": 63465, "total_steps": 76960, "loss": 0.1132, "lr": 4.5394263126462445e-06, "epoch": 16.492983367983367, "percentage": 82.46, "elapsed_time": "1:32:11", "remaining_time": "0:19:36", "throughput": 1033.11, "total_tokens": 5715128} {"current_steps": 63470, "total_steps": 76960, "loss": 0.2139, "lr": 4.5361689950873725e-06, "epoch": 16.494282744282746, "percentage": 82.47, "elapsed_time": "1:32:12", "remaining_time": "0:19:35", "throughput": 1033.12, "total_tokens": 5715624} {"current_steps": 63475, "total_steps": 76960, "loss": 0.0977, "lr": 4.532912730002934e-06, "epoch": 16.49558212058212, "percentage": 82.48, "elapsed_time": "1:32:12", "remaining_time": "0:19:35", "throughput": 1033.13, "total_tokens": 5716104} {"current_steps": 63480, "total_steps": 76960, "loss": 0.19, "lr": 4.52965751756041e-06, "epoch": 16.496881496881496, "percentage": 82.48, "elapsed_time": "1:32:13", "remaining_time": "0:19:34", "throughput": 1033.13, "total_tokens": 5716536} {"current_steps": 63485, "total_steps": 76960, "loss": 0.0311, "lr": 4.526403357927206e-06, "epoch": 16.498180873180875, "percentage": 82.49, "elapsed_time": "1:32:13", "remaining_time": "0:19:34", "throughput": 1033.13, "total_tokens": 5716984} {"current_steps": 63490, "total_steps": 76960, "loss": 0.0987, "lr": 4.5231502512707e-06, "epoch": 16.49948024948025, "percentage": 82.5, "elapsed_time": "1:32:14", "remaining_time": "0:19:34", "throughput": 1033.14, "total_tokens": 5717432} {"current_steps": 63495, "total_steps": 76960, "loss": 0.1421, "lr": 4.519898197758191e-06, "epoch": 16.500779625779625, "percentage": 82.5, "elapsed_time": "1:32:14", "remaining_time": "0:19:33", "throughput": 1033.14, "total_tokens": 5717864} {"current_steps": 63500, "total_steps": 76960, "loss": 0.3501, "lr": 4.516647197556942e-06, "epoch": 16.502079002079, "percentage": 82.51, "elapsed_time": "1:32:14", "remaining_time": "0:19:33", "throughput": 1033.14, "total_tokens": 5718296} {"current_steps": 63505, "total_steps": 76960, "loss": 0.0529, "lr": 4.513397250834159e-06, "epoch": 16.50337837837838, "percentage": 82.52, "elapsed_time": "1:32:15", "remaining_time": "0:19:32", "throughput": 1033.15, "total_tokens": 5718792} {"current_steps": 63510, "total_steps": 76960, "loss": 0.0846, "lr": 4.510148357756977e-06, "epoch": 16.504677754677754, "percentage": 82.52, "elapsed_time": "1:32:15", "remaining_time": "0:19:32", "throughput": 1033.15, "total_tokens": 5719240} {"current_steps": 63515, "total_steps": 76960, "loss": 0.2783, "lr": 4.506900518492504e-06, "epoch": 16.50597713097713, "percentage": 82.53, "elapsed_time": "1:32:16", "remaining_time": "0:19:31", "throughput": 1033.15, "total_tokens": 5719672} {"current_steps": 63520, "total_steps": 76960, "loss": 0.4086, "lr": 4.503653733207769e-06, "epoch": 16.507276507276508, "percentage": 82.54, "elapsed_time": "1:32:16", "remaining_time": "0:19:31", "throughput": 1033.15, "total_tokens": 5720088} {"current_steps": 63525, "total_steps": 76960, "loss": 0.1553, "lr": 4.500408002069767e-06, "epoch": 16.508575883575883, "percentage": 82.54, "elapsed_time": "1:32:16", "remaining_time": "0:19:31", "throughput": 1033.16, "total_tokens": 5720568} {"current_steps": 63530, "total_steps": 76960, "loss": 0.0046, "lr": 4.497163325245416e-06, "epoch": 16.50987525987526, "percentage": 82.55, "elapsed_time": "1:32:17", "remaining_time": "0:19:30", "throughput": 1033.16, "total_tokens": 5721000} {"current_steps": 63535, "total_steps": 76960, "loss": 0.0725, "lr": 4.4939197029016e-06, "epoch": 16.511174636174637, "percentage": 82.56, "elapsed_time": "1:32:17", "remaining_time": "0:19:30", "throughput": 1033.16, "total_tokens": 5721448} {"current_steps": 63540, "total_steps": 76960, "loss": 0.1489, "lr": 4.49067713520514e-06, "epoch": 16.512474012474012, "percentage": 82.56, "elapsed_time": "1:32:18", "remaining_time": "0:19:29", "throughput": 1033.17, "total_tokens": 5721912} {"current_steps": 63545, "total_steps": 76960, "loss": 0.0434, "lr": 4.487435622322814e-06, "epoch": 16.513773388773387, "percentage": 82.57, "elapsed_time": "1:32:18", "remaining_time": "0:19:29", "throughput": 1033.17, "total_tokens": 5722360} {"current_steps": 63550, "total_steps": 76960, "loss": 0.3692, "lr": 4.4841951644213235e-06, "epoch": 16.515072765072766, "percentage": 82.58, "elapsed_time": "1:32:19", "remaining_time": "0:19:28", "throughput": 1033.17, "total_tokens": 5722776} {"current_steps": 63555, "total_steps": 76960, "loss": 0.3027, "lr": 4.480955761667338e-06, "epoch": 16.51637214137214, "percentage": 82.58, "elapsed_time": "1:32:19", "remaining_time": "0:19:28", "throughput": 1033.17, "total_tokens": 5723224} {"current_steps": 63560, "total_steps": 76960, "loss": 0.0005, "lr": 4.4777174142274506e-06, "epoch": 16.517671517671516, "percentage": 82.59, "elapsed_time": "1:32:19", "remaining_time": "0:19:27", "throughput": 1033.18, "total_tokens": 5723704} {"current_steps": 63565, "total_steps": 76960, "loss": 0.0339, "lr": 4.474480122268226e-06, "epoch": 16.518970893970895, "percentage": 82.59, "elapsed_time": "1:32:20", "remaining_time": "0:19:27", "throughput": 1033.18, "total_tokens": 5724152} {"current_steps": 63570, "total_steps": 76960, "loss": 0.0009, "lr": 4.47124388595615e-06, "epoch": 16.52027027027027, "percentage": 82.6, "elapsed_time": "1:32:20", "remaining_time": "0:19:27", "throughput": 1033.19, "total_tokens": 5724584} {"current_steps": 63575, "total_steps": 76960, "loss": 0.1711, "lr": 4.468008705457671e-06, "epoch": 16.521569646569645, "percentage": 82.61, "elapsed_time": "1:32:21", "remaining_time": "0:19:26", "throughput": 1033.19, "total_tokens": 5725032} {"current_steps": 63580, "total_steps": 76960, "loss": 0.0182, "lr": 4.464774580939185e-06, "epoch": 16.522869022869024, "percentage": 82.61, "elapsed_time": "1:32:21", "remaining_time": "0:19:26", "throughput": 1033.19, "total_tokens": 5725480} {"current_steps": 63585, "total_steps": 76960, "loss": 0.046, "lr": 4.461541512567011e-06, "epoch": 16.5241683991684, "percentage": 82.62, "elapsed_time": "1:32:21", "remaining_time": "0:19:25", "throughput": 1033.19, "total_tokens": 5725896} {"current_steps": 63590, "total_steps": 76960, "loss": 0.3027, "lr": 4.458309500507441e-06, "epoch": 16.525467775467774, "percentage": 82.63, "elapsed_time": "1:32:22", "remaining_time": "0:19:25", "throughput": 1033.19, "total_tokens": 5726344} {"current_steps": 63595, "total_steps": 76960, "loss": 0.0151, "lr": 4.455078544926689e-06, "epoch": 16.526767151767153, "percentage": 82.63, "elapsed_time": "1:32:22", "remaining_time": "0:19:24", "throughput": 1033.2, "total_tokens": 5726792} {"current_steps": 63600, "total_steps": 76960, "loss": 0.0018, "lr": 4.451848645990933e-06, "epoch": 16.528066528066528, "percentage": 82.64, "elapsed_time": "1:32:23", "remaining_time": "0:19:24", "throughput": 1033.2, "total_tokens": 5727240} {"current_steps": 63605, "total_steps": 76960, "loss": 0.2227, "lr": 4.448619803866291e-06, "epoch": 16.529365904365903, "percentage": 82.65, "elapsed_time": "1:32:23", "remaining_time": "0:19:23", "throughput": 1033.2, "total_tokens": 5727672} {"current_steps": 63610, "total_steps": 76960, "loss": 0.0023, "lr": 4.445392018718827e-06, "epoch": 16.530665280665282, "percentage": 82.65, "elapsed_time": "1:32:24", "remaining_time": "0:19:23", "throughput": 1033.2, "total_tokens": 5728104} {"current_steps": 63615, "total_steps": 76960, "loss": 0.1803, "lr": 4.442165290714542e-06, "epoch": 16.531964656964657, "percentage": 82.66, "elapsed_time": "1:32:24", "remaining_time": "0:19:23", "throughput": 1033.2, "total_tokens": 5728536} {"current_steps": 63620, "total_steps": 76960, "loss": 0.0221, "lr": 4.4389396200194e-06, "epoch": 16.533264033264032, "percentage": 82.67, "elapsed_time": "1:32:24", "remaining_time": "0:19:22", "throughput": 1033.2, "total_tokens": 5728984} {"current_steps": 63625, "total_steps": 76960, "loss": 0.3164, "lr": 4.4357150067992876e-06, "epoch": 16.53456340956341, "percentage": 82.67, "elapsed_time": "1:32:25", "remaining_time": "0:19:22", "throughput": 1033.21, "total_tokens": 5729432} {"current_steps": 63630, "total_steps": 76960, "loss": 0.0366, "lr": 4.432491451220061e-06, "epoch": 16.535862785862786, "percentage": 82.68, "elapsed_time": "1:32:25", "remaining_time": "0:19:21", "throughput": 1033.21, "total_tokens": 5729880} {"current_steps": 63635, "total_steps": 76960, "loss": 0.2312, "lr": 4.4292689534475015e-06, "epoch": 16.53716216216216, "percentage": 82.69, "elapsed_time": "1:32:26", "remaining_time": "0:19:21", "throughput": 1033.21, "total_tokens": 5730296} {"current_steps": 63640, "total_steps": 76960, "loss": 0.3312, "lr": 4.4260475136473495e-06, "epoch": 16.53846153846154, "percentage": 82.69, "elapsed_time": "1:32:26", "remaining_time": "0:19:20", "throughput": 1033.21, "total_tokens": 5730744} {"current_steps": 63645, "total_steps": 76960, "loss": 0.1494, "lr": 4.422827131985291e-06, "epoch": 16.539760914760915, "percentage": 82.7, "elapsed_time": "1:32:26", "remaining_time": "0:19:20", "throughput": 1033.21, "total_tokens": 5731176} {"current_steps": 63650, "total_steps": 76960, "loss": 0.0012, "lr": 4.419607808626946e-06, "epoch": 16.54106029106029, "percentage": 82.71, "elapsed_time": "1:32:27", "remaining_time": "0:19:20", "throughput": 1033.21, "total_tokens": 5731608} {"current_steps": 63655, "total_steps": 76960, "loss": 0.2854, "lr": 4.416389543737895e-06, "epoch": 16.54235966735967, "percentage": 82.71, "elapsed_time": "1:32:27", "remaining_time": "0:19:19", "throughput": 1033.21, "total_tokens": 5732040} {"current_steps": 63660, "total_steps": 76960, "loss": 0.2896, "lr": 4.413172337483645e-06, "epoch": 16.543659043659044, "percentage": 82.72, "elapsed_time": "1:32:28", "remaining_time": "0:19:19", "throughput": 1033.22, "total_tokens": 5732488} {"current_steps": 63665, "total_steps": 76960, "loss": 0.3917, "lr": 4.409956190029674e-06, "epoch": 16.54495841995842, "percentage": 82.72, "elapsed_time": "1:32:28", "remaining_time": "0:19:18", "throughput": 1033.22, "total_tokens": 5732952} {"current_steps": 63670, "total_steps": 76960, "loss": 0.5075, "lr": 4.406741101541378e-06, "epoch": 16.546257796257795, "percentage": 82.73, "elapsed_time": "1:32:29", "remaining_time": "0:19:18", "throughput": 1033.22, "total_tokens": 5733384} {"current_steps": 63675, "total_steps": 76960, "loss": 0.2384, "lr": 4.4035270721841215e-06, "epoch": 16.547557172557173, "percentage": 82.74, "elapsed_time": "1:32:29", "remaining_time": "0:19:17", "throughput": 1033.22, "total_tokens": 5733800} {"current_steps": 63680, "total_steps": 76960, "loss": 0.086, "lr": 4.400314102123199e-06, "epoch": 16.54885654885655, "percentage": 82.74, "elapsed_time": "1:32:29", "remaining_time": "0:19:17", "throughput": 1033.23, "total_tokens": 5734280} {"current_steps": 63685, "total_steps": 76960, "loss": 0.1984, "lr": 4.397102191523869e-06, "epoch": 16.550155925155924, "percentage": 82.75, "elapsed_time": "1:32:30", "remaining_time": "0:19:16", "throughput": 1033.23, "total_tokens": 5734712} {"current_steps": 63690, "total_steps": 76960, "loss": 0.003, "lr": 4.393891340551304e-06, "epoch": 16.551455301455302, "percentage": 82.76, "elapsed_time": "1:32:30", "remaining_time": "0:19:16", "throughput": 1033.23, "total_tokens": 5735160} {"current_steps": 63695, "total_steps": 76960, "loss": 0.2289, "lr": 4.390681549370659e-06, "epoch": 16.552754677754677, "percentage": 82.76, "elapsed_time": "1:32:31", "remaining_time": "0:19:16", "throughput": 1033.23, "total_tokens": 5735576} {"current_steps": 63700, "total_steps": 76960, "loss": 0.0191, "lr": 4.387472818147012e-06, "epoch": 16.554054054054053, "percentage": 82.77, "elapsed_time": "1:32:31", "remaining_time": "0:19:15", "throughput": 1033.23, "total_tokens": 5736008} {"current_steps": 63705, "total_steps": 76960, "loss": 0.139, "lr": 4.384265147045377e-06, "epoch": 16.55535343035343, "percentage": 82.78, "elapsed_time": "1:32:31", "remaining_time": "0:19:15", "throughput": 1033.24, "total_tokens": 5736472} {"current_steps": 63710, "total_steps": 76960, "loss": 0.0027, "lr": 4.381058536230742e-06, "epoch": 16.556652806652806, "percentage": 82.78, "elapsed_time": "1:32:32", "remaining_time": "0:19:14", "throughput": 1033.23, "total_tokens": 5736888} {"current_steps": 63715, "total_steps": 76960, "loss": 0.2227, "lr": 4.377852985868019e-06, "epoch": 16.55795218295218, "percentage": 82.79, "elapsed_time": "1:32:32", "remaining_time": "0:19:14", "throughput": 1033.24, "total_tokens": 5737352} {"current_steps": 63720, "total_steps": 76960, "loss": 0.0154, "lr": 4.3746484961220856e-06, "epoch": 16.55925155925156, "percentage": 82.8, "elapsed_time": "1:32:33", "remaining_time": "0:19:13", "throughput": 1033.25, "total_tokens": 5737816} {"current_steps": 63725, "total_steps": 76960, "loss": 0.358, "lr": 4.371445067157734e-06, "epoch": 16.560550935550935, "percentage": 82.8, "elapsed_time": "1:32:33", "remaining_time": "0:19:13", "throughput": 1033.25, "total_tokens": 5738264} {"current_steps": 63730, "total_steps": 76960, "loss": 0.2505, "lr": 4.368242699139735e-06, "epoch": 16.56185031185031, "percentage": 82.81, "elapsed_time": "1:32:34", "remaining_time": "0:19:12", "throughput": 1033.26, "total_tokens": 5738728} {"current_steps": 63735, "total_steps": 76960, "loss": 0.485, "lr": 4.365041392232777e-06, "epoch": 16.56314968814969, "percentage": 82.82, "elapsed_time": "1:32:34", "remaining_time": "0:19:12", "throughput": 1033.26, "total_tokens": 5739160} {"current_steps": 63740, "total_steps": 76960, "loss": 0.0838, "lr": 4.3618411466015165e-06, "epoch": 16.564449064449065, "percentage": 82.82, "elapsed_time": "1:32:34", "remaining_time": "0:19:12", "throughput": 1033.26, "total_tokens": 5739624} {"current_steps": 63745, "total_steps": 76960, "loss": 0.4147, "lr": 4.358641962410537e-06, "epoch": 16.56574844074844, "percentage": 82.83, "elapsed_time": "1:32:35", "remaining_time": "0:19:11", "throughput": 1033.27, "total_tokens": 5740072} {"current_steps": 63750, "total_steps": 76960, "loss": 0.3537, "lr": 4.355443839824375e-06, "epoch": 16.56704781704782, "percentage": 82.84, "elapsed_time": "1:32:35", "remaining_time": "0:19:11", "throughput": 1033.26, "total_tokens": 5740488} {"current_steps": 63755, "total_steps": 76960, "loss": 0.368, "lr": 4.352246779007518e-06, "epoch": 16.568347193347194, "percentage": 82.84, "elapsed_time": "1:32:36", "remaining_time": "0:19:10", "throughput": 1033.27, "total_tokens": 5740952} {"current_steps": 63760, "total_steps": 76960, "loss": 0.0397, "lr": 4.3490507801244005e-06, "epoch": 16.56964656964657, "percentage": 82.85, "elapsed_time": "1:32:36", "remaining_time": "0:19:10", "throughput": 1033.28, "total_tokens": 5741416} {"current_steps": 63765, "total_steps": 76960, "loss": 0.064, "lr": 4.3458558433393885e-06, "epoch": 16.570945945945947, "percentage": 82.85, "elapsed_time": "1:32:36", "remaining_time": "0:19:09", "throughput": 1033.28, "total_tokens": 5741880} {"current_steps": 63770, "total_steps": 76960, "loss": 0.0024, "lr": 4.342661968816791e-06, "epoch": 16.572245322245323, "percentage": 82.86, "elapsed_time": "1:32:37", "remaining_time": "0:19:09", "throughput": 1033.29, "total_tokens": 5742328} {"current_steps": 63775, "total_steps": 76960, "loss": 0.1757, "lr": 4.33946915672089e-06, "epoch": 16.573544698544698, "percentage": 82.87, "elapsed_time": "1:32:37", "remaining_time": "0:19:09", "throughput": 1033.29, "total_tokens": 5742792} {"current_steps": 63780, "total_steps": 76960, "loss": 0.0251, "lr": 4.33627740721588e-06, "epoch": 16.574844074844076, "percentage": 82.87, "elapsed_time": "1:32:38", "remaining_time": "0:19:08", "throughput": 1033.3, "total_tokens": 5743256} {"current_steps": 63785, "total_steps": 76960, "loss": 0.0049, "lr": 4.333086720465923e-06, "epoch": 16.57614345114345, "percentage": 82.88, "elapsed_time": "1:32:38", "remaining_time": "0:19:08", "throughput": 1033.3, "total_tokens": 5743688} {"current_steps": 63790, "total_steps": 76960, "loss": 0.0138, "lr": 4.329897096635116e-06, "epoch": 16.577442827442827, "percentage": 82.89, "elapsed_time": "1:32:39", "remaining_time": "0:19:07", "throughput": 1033.3, "total_tokens": 5744136} {"current_steps": 63795, "total_steps": 76960, "loss": 0.138, "lr": 4.326708535887514e-06, "epoch": 16.578742203742205, "percentage": 82.89, "elapsed_time": "1:32:39", "remaining_time": "0:19:07", "throughput": 1033.31, "total_tokens": 5744600} {"current_steps": 63800, "total_steps": 76960, "loss": 0.2138, "lr": 4.323521038387094e-06, "epoch": 16.58004158004158, "percentage": 82.9, "elapsed_time": "1:32:39", "remaining_time": "0:19:06", "throughput": 1033.32, "total_tokens": 5745064} {"current_steps": 63805, "total_steps": 76960, "loss": 0.0093, "lr": 4.320334604297801e-06, "epoch": 16.581340956340956, "percentage": 82.91, "elapsed_time": "1:32:40", "remaining_time": "0:19:06", "throughput": 1033.32, "total_tokens": 5745512} {"current_steps": 63810, "total_steps": 76960, "loss": 0.0064, "lr": 4.3171492337835105e-06, "epoch": 16.58264033264033, "percentage": 82.91, "elapsed_time": "1:32:40", "remaining_time": "0:19:05", "throughput": 1033.33, "total_tokens": 5746008} {"current_steps": 63815, "total_steps": 76960, "loss": 0.0411, "lr": 4.31396492700806e-06, "epoch": 16.58393970893971, "percentage": 82.92, "elapsed_time": "1:32:41", "remaining_time": "0:19:05", "throughput": 1033.34, "total_tokens": 5746456} {"current_steps": 63820, "total_steps": 76960, "loss": 0.0022, "lr": 4.310781684135199e-06, "epoch": 16.585239085239085, "percentage": 82.93, "elapsed_time": "1:32:41", "remaining_time": "0:19:05", "throughput": 1033.34, "total_tokens": 5746904} {"current_steps": 63825, "total_steps": 76960, "loss": 0.382, "lr": 4.307599505328672e-06, "epoch": 16.58653846153846, "percentage": 82.93, "elapsed_time": "1:32:41", "remaining_time": "0:19:04", "throughput": 1033.34, "total_tokens": 5747352} {"current_steps": 63830, "total_steps": 76960, "loss": 0.0051, "lr": 4.3044183907521244e-06, "epoch": 16.58783783783784, "percentage": 82.94, "elapsed_time": "1:32:42", "remaining_time": "0:19:04", "throughput": 1033.34, "total_tokens": 5747768} {"current_steps": 63835, "total_steps": 76960, "loss": 0.003, "lr": 4.301238340569172e-06, "epoch": 16.589137214137214, "percentage": 82.95, "elapsed_time": "1:32:42", "remaining_time": "0:19:03", "throughput": 1033.35, "total_tokens": 5748248} {"current_steps": 63840, "total_steps": 76960, "loss": 0.0061, "lr": 4.298059354943365e-06, "epoch": 16.59043659043659, "percentage": 82.95, "elapsed_time": "1:32:43", "remaining_time": "0:19:03", "throughput": 1033.36, "total_tokens": 5748760} {"current_steps": 63845, "total_steps": 76960, "loss": 0.0947, "lr": 4.294881434038195e-06, "epoch": 16.591735966735968, "percentage": 82.96, "elapsed_time": "1:32:43", "remaining_time": "0:19:02", "throughput": 1033.37, "total_tokens": 5749208} {"current_steps": 63850, "total_steps": 76960, "loss": 0.283, "lr": 4.291704578017114e-06, "epoch": 16.593035343035343, "percentage": 82.97, "elapsed_time": "1:32:43", "remaining_time": "0:19:02", "throughput": 1033.37, "total_tokens": 5749640} {"current_steps": 63855, "total_steps": 76960, "loss": 0.0887, "lr": 4.288528787043505e-06, "epoch": 16.594334719334718, "percentage": 82.97, "elapsed_time": "1:32:44", "remaining_time": "0:19:01", "throughput": 1033.37, "total_tokens": 5750088} {"current_steps": 63860, "total_steps": 76960, "loss": 0.061, "lr": 4.285354061280713e-06, "epoch": 16.595634095634097, "percentage": 82.98, "elapsed_time": "1:32:44", "remaining_time": "0:19:01", "throughput": 1033.37, "total_tokens": 5750536} {"current_steps": 63865, "total_steps": 76960, "loss": 0.1868, "lr": 4.282180400892002e-06, "epoch": 16.596933471933472, "percentage": 82.98, "elapsed_time": "1:32:45", "remaining_time": "0:19:01", "throughput": 1033.37, "total_tokens": 5750968} {"current_steps": 63870, "total_steps": 76960, "loss": 0.061, "lr": 4.279007806040611e-06, "epoch": 16.598232848232847, "percentage": 82.99, "elapsed_time": "1:32:45", "remaining_time": "0:19:00", "throughput": 1033.38, "total_tokens": 5751416} {"current_steps": 63875, "total_steps": 76960, "loss": 0.0069, "lr": 4.275836276889697e-06, "epoch": 16.599532224532226, "percentage": 83.0, "elapsed_time": "1:32:46", "remaining_time": "0:19:00", "throughput": 1033.38, "total_tokens": 5751848} {"current_steps": 63880, "total_steps": 76960, "loss": 0.1081, "lr": 4.272665813602386e-06, "epoch": 16.6008316008316, "percentage": 83.0, "elapsed_time": "1:32:46", "remaining_time": "0:18:59", "throughput": 1033.38, "total_tokens": 5752280} {"current_steps": 63885, "total_steps": 76960, "loss": 0.2366, "lr": 4.269496416341725e-06, "epoch": 16.602130977130976, "percentage": 83.01, "elapsed_time": "1:32:46", "remaining_time": "0:18:59", "throughput": 1033.39, "total_tokens": 5752776} {"current_steps": 63890, "total_steps": 76960, "loss": 0.4635, "lr": 4.266328085270726e-06, "epoch": 16.603430353430355, "percentage": 83.02, "elapsed_time": "1:32:47", "remaining_time": "0:18:58", "throughput": 1033.39, "total_tokens": 5753192} {"current_steps": 63895, "total_steps": 76960, "loss": 0.4052, "lr": 4.2631608205523424e-06, "epoch": 16.60472972972973, "percentage": 83.02, "elapsed_time": "1:32:47", "remaining_time": "0:18:58", "throughput": 1033.39, "total_tokens": 5753640} {"current_steps": 63900, "total_steps": 76960, "loss": 0.0466, "lr": 4.25999462234947e-06, "epoch": 16.606029106029105, "percentage": 83.03, "elapsed_time": "1:32:48", "remaining_time": "0:18:58", "throughput": 1033.4, "total_tokens": 5754136} {"current_steps": 63905, "total_steps": 76960, "loss": 0.0091, "lr": 4.256829490824949e-06, "epoch": 16.607328482328484, "percentage": 83.04, "elapsed_time": "1:32:48", "remaining_time": "0:18:57", "throughput": 1033.41, "total_tokens": 5754584} {"current_steps": 63910, "total_steps": 76960, "loss": 0.0162, "lr": 4.253665426141554e-06, "epoch": 16.60862785862786, "percentage": 83.04, "elapsed_time": "1:32:48", "remaining_time": "0:18:57", "throughput": 1033.41, "total_tokens": 5755016} {"current_steps": 63915, "total_steps": 76960, "loss": 0.0266, "lr": 4.25050242846203e-06, "epoch": 16.609927234927234, "percentage": 83.05, "elapsed_time": "1:32:49", "remaining_time": "0:18:56", "throughput": 1033.4, "total_tokens": 5755432} {"current_steps": 63920, "total_steps": 76960, "loss": 0.1579, "lr": 4.247340497949043e-06, "epoch": 16.611226611226613, "percentage": 83.06, "elapsed_time": "1:32:49", "remaining_time": "0:18:56", "throughput": 1033.41, "total_tokens": 5755880} {"current_steps": 63925, "total_steps": 76960, "loss": 0.2973, "lr": 4.244179634765219e-06, "epoch": 16.612525987525988, "percentage": 83.06, "elapsed_time": "1:32:50", "remaining_time": "0:18:55", "throughput": 1033.41, "total_tokens": 5756312} {"current_steps": 63930, "total_steps": 76960, "loss": 0.2091, "lr": 4.241019839073124e-06, "epoch": 16.613825363825363, "percentage": 83.07, "elapsed_time": "1:32:50", "remaining_time": "0:18:55", "throughput": 1033.41, "total_tokens": 5756760} {"current_steps": 63935, "total_steps": 76960, "loss": 0.0008, "lr": 4.237861111035271e-06, "epoch": 16.61512474012474, "percentage": 83.08, "elapsed_time": "1:32:51", "remaining_time": "0:18:54", "throughput": 1033.42, "total_tokens": 5757224} {"current_steps": 63940, "total_steps": 76960, "loss": 0.2696, "lr": 4.234703450814112e-06, "epoch": 16.616424116424117, "percentage": 83.08, "elapsed_time": "1:32:51", "remaining_time": "0:18:54", "throughput": 1033.42, "total_tokens": 5757656} {"current_steps": 63945, "total_steps": 76960, "loss": 0.0037, "lr": 4.231546858572055e-06, "epoch": 16.617723492723492, "percentage": 83.09, "elapsed_time": "1:32:51", "remaining_time": "0:18:54", "throughput": 1033.42, "total_tokens": 5758120} {"current_steps": 63950, "total_steps": 76960, "loss": 0.1343, "lr": 4.2283913344714375e-06, "epoch": 16.61902286902287, "percentage": 83.1, "elapsed_time": "1:32:52", "remaining_time": "0:18:53", "throughput": 1033.44, "total_tokens": 5758616} {"current_steps": 63955, "total_steps": 76960, "loss": 0.2552, "lr": 4.225236878674563e-06, "epoch": 16.620322245322246, "percentage": 83.1, "elapsed_time": "1:32:52", "remaining_time": "0:18:53", "throughput": 1033.44, "total_tokens": 5759064} {"current_steps": 63960, "total_steps": 76960, "loss": 0.4554, "lr": 4.222083491343653e-06, "epoch": 16.62162162162162, "percentage": 83.11, "elapsed_time": "1:32:53", "remaining_time": "0:18:52", "throughput": 1033.45, "total_tokens": 5759528} {"current_steps": 63965, "total_steps": 76960, "loss": 0.0059, "lr": 4.218931172640899e-06, "epoch": 16.622920997921, "percentage": 83.11, "elapsed_time": "1:32:53", "remaining_time": "0:18:52", "throughput": 1033.44, "total_tokens": 5759928} {"current_steps": 63970, "total_steps": 76960, "loss": 0.1869, "lr": 4.215779922728432e-06, "epoch": 16.624220374220375, "percentage": 83.12, "elapsed_time": "1:32:53", "remaining_time": "0:18:51", "throughput": 1033.45, "total_tokens": 5760392} {"current_steps": 63975, "total_steps": 76960, "loss": 0.2195, "lr": 4.212629741768312e-06, "epoch": 16.62551975051975, "percentage": 83.13, "elapsed_time": "1:32:54", "remaining_time": "0:18:51", "throughput": 1033.44, "total_tokens": 5760808} {"current_steps": 63980, "total_steps": 76960, "loss": 0.1657, "lr": 4.209480629922569e-06, "epoch": 16.626819126819125, "percentage": 83.13, "elapsed_time": "1:32:54", "remaining_time": "0:18:50", "throughput": 1033.44, "total_tokens": 5761240} {"current_steps": 63985, "total_steps": 76960, "loss": 0.2991, "lr": 4.206332587353149e-06, "epoch": 16.628118503118504, "percentage": 83.14, "elapsed_time": "1:32:55", "remaining_time": "0:18:50", "throughput": 1033.44, "total_tokens": 5761672} {"current_steps": 63990, "total_steps": 76960, "loss": 0.1599, "lr": 4.203185614221975e-06, "epoch": 16.62941787941788, "percentage": 83.15, "elapsed_time": "1:32:55", "remaining_time": "0:18:50", "throughput": 1033.45, "total_tokens": 5762104} {"current_steps": 63995, "total_steps": 76960, "loss": 0.1053, "lr": 4.2000397106908865e-06, "epoch": 16.630717255717254, "percentage": 83.15, "elapsed_time": "1:32:56", "remaining_time": "0:18:49", "throughput": 1033.45, "total_tokens": 5762584} {"current_steps": 64000, "total_steps": 76960, "loss": 0.1975, "lr": 4.196894876921684e-06, "epoch": 16.632016632016633, "percentage": 83.16, "elapsed_time": "1:32:56", "remaining_time": "0:18:49", "throughput": 1033.46, "total_tokens": 5763032} {"current_steps": 64005, "total_steps": 76960, "loss": 0.1235, "lr": 4.1937511130761106e-06, "epoch": 16.633316008316008, "percentage": 83.17, "elapsed_time": "1:32:56", "remaining_time": "0:18:48", "throughput": 1033.46, "total_tokens": 5763480} {"current_steps": 64010, "total_steps": 76960, "loss": 0.0182, "lr": 4.190608419315858e-06, "epoch": 16.634615384615383, "percentage": 83.17, "elapsed_time": "1:32:57", "remaining_time": "0:18:48", "throughput": 1033.47, "total_tokens": 5763960} {"current_steps": 64015, "total_steps": 76960, "loss": 0.0531, "lr": 4.18746679580255e-06, "epoch": 16.635914760914762, "percentage": 83.18, "elapsed_time": "1:32:57", "remaining_time": "0:18:47", "throughput": 1033.47, "total_tokens": 5764392} {"current_steps": 64020, "total_steps": 76960, "loss": 0.0155, "lr": 4.18432624269777e-06, "epoch": 16.637214137214137, "percentage": 83.19, "elapsed_time": "1:32:58", "remaining_time": "0:18:47", "throughput": 1033.47, "total_tokens": 5764840} {"current_steps": 64025, "total_steps": 76960, "loss": 0.1737, "lr": 4.18118676016303e-06, "epoch": 16.638513513513512, "percentage": 83.19, "elapsed_time": "1:32:58", "remaining_time": "0:18:47", "throughput": 1033.48, "total_tokens": 5765304} {"current_steps": 64030, "total_steps": 76960, "loss": 0.0093, "lr": 4.178048348359809e-06, "epoch": 16.63981288981289, "percentage": 83.2, "elapsed_time": "1:32:58", "remaining_time": "0:18:46", "throughput": 1033.49, "total_tokens": 5765784} {"current_steps": 64035, "total_steps": 76960, "loss": 0.265, "lr": 4.174911007449505e-06, "epoch": 16.641112266112266, "percentage": 83.21, "elapsed_time": "1:32:59", "remaining_time": "0:18:46", "throughput": 1033.5, "total_tokens": 5766264} {"current_steps": 64040, "total_steps": 76960, "loss": 0.1807, "lr": 4.171774737593484e-06, "epoch": 16.64241164241164, "percentage": 83.21, "elapsed_time": "1:32:59", "remaining_time": "0:18:45", "throughput": 1033.5, "total_tokens": 5766680} {"current_steps": 64045, "total_steps": 76960, "loss": 0.0433, "lr": 4.168639538953048e-06, "epoch": 16.64371101871102, "percentage": 83.22, "elapsed_time": "1:33:00", "remaining_time": "0:18:45", "throughput": 1033.5, "total_tokens": 5767112} {"current_steps": 64050, "total_steps": 76960, "loss": 0.0081, "lr": 4.165505411689435e-06, "epoch": 16.645010395010395, "percentage": 83.23, "elapsed_time": "1:33:00", "remaining_time": "0:18:44", "throughput": 1033.49, "total_tokens": 5767528} {"current_steps": 64055, "total_steps": 76960, "loss": 0.2891, "lr": 4.162372355963848e-06, "epoch": 16.64630977130977, "percentage": 83.23, "elapsed_time": "1:33:01", "remaining_time": "0:18:44", "throughput": 1033.51, "total_tokens": 5768040} {"current_steps": 64060, "total_steps": 76960, "loss": 0.0021, "lr": 4.159240371937412e-06, "epoch": 16.64760914760915, "percentage": 83.24, "elapsed_time": "1:33:01", "remaining_time": "0:18:43", "throughput": 1033.51, "total_tokens": 5768456} {"current_steps": 64065, "total_steps": 76960, "loss": 0.0614, "lr": 4.1561094597712155e-06, "epoch": 16.648908523908524, "percentage": 83.24, "elapsed_time": "1:33:01", "remaining_time": "0:18:43", "throughput": 1033.51, "total_tokens": 5768920} {"current_steps": 64070, "total_steps": 76960, "loss": 0.0593, "lr": 4.152979619626271e-06, "epoch": 16.6502079002079, "percentage": 83.25, "elapsed_time": "1:33:02", "remaining_time": "0:18:43", "throughput": 1033.52, "total_tokens": 5769384} {"current_steps": 64075, "total_steps": 76960, "loss": 0.0156, "lr": 4.149850851663569e-06, "epoch": 16.651507276507278, "percentage": 83.26, "elapsed_time": "1:33:02", "remaining_time": "0:18:42", "throughput": 1033.52, "total_tokens": 5769848} {"current_steps": 64080, "total_steps": 76960, "loss": 0.0018, "lr": 4.146723156044014e-06, "epoch": 16.652806652806653, "percentage": 83.26, "elapsed_time": "1:33:03", "remaining_time": "0:18:42", "throughput": 1033.52, "total_tokens": 5770280} {"current_steps": 64085, "total_steps": 76960, "loss": 0.1104, "lr": 4.143596532928468e-06, "epoch": 16.65410602910603, "percentage": 83.27, "elapsed_time": "1:33:03", "remaining_time": "0:18:41", "throughput": 1033.53, "total_tokens": 5770744} {"current_steps": 64090, "total_steps": 76960, "loss": 0.0822, "lr": 4.140470982477735e-06, "epoch": 16.655405405405407, "percentage": 83.28, "elapsed_time": "1:33:03", "remaining_time": "0:18:41", "throughput": 1033.54, "total_tokens": 5771208} {"current_steps": 64095, "total_steps": 76960, "loss": 0.0024, "lr": 4.137346504852569e-06, "epoch": 16.656704781704782, "percentage": 83.28, "elapsed_time": "1:33:04", "remaining_time": "0:18:40", "throughput": 1033.54, "total_tokens": 5771672} {"current_steps": 64100, "total_steps": 76960, "loss": 0.5043, "lr": 4.134223100213655e-06, "epoch": 16.658004158004157, "percentage": 83.29, "elapsed_time": "1:33:04", "remaining_time": "0:18:40", "throughput": 1033.54, "total_tokens": 5772104} {"current_steps": 64105, "total_steps": 76960, "loss": 0.029, "lr": 4.131100768721641e-06, "epoch": 16.659303534303533, "percentage": 83.3, "elapsed_time": "1:33:05", "remaining_time": "0:18:39", "throughput": 1033.55, "total_tokens": 5772568} {"current_steps": 64110, "total_steps": 76960, "loss": 0.4861, "lr": 4.127979510537117e-06, "epoch": 16.66060291060291, "percentage": 83.3, "elapsed_time": "1:33:05", "remaining_time": "0:18:39", "throughput": 1033.56, "total_tokens": 5773032} {"current_steps": 64115, "total_steps": 76960, "loss": 0.1072, "lr": 4.1248593258205986e-06, "epoch": 16.661902286902286, "percentage": 83.31, "elapsed_time": "1:33:06", "remaining_time": "0:18:39", "throughput": 1033.56, "total_tokens": 5773480} {"current_steps": 64120, "total_steps": 76960, "loss": 0.0341, "lr": 4.121740214732572e-06, "epoch": 16.66320166320166, "percentage": 83.32, "elapsed_time": "1:33:06", "remaining_time": "0:18:38", "throughput": 1033.56, "total_tokens": 5773928} {"current_steps": 64125, "total_steps": 76960, "loss": 0.2509, "lr": 4.1186221774334455e-06, "epoch": 16.66450103950104, "percentage": 83.32, "elapsed_time": "1:33:06", "remaining_time": "0:18:38", "throughput": 1033.57, "total_tokens": 5774392} {"current_steps": 64130, "total_steps": 76960, "loss": 0.3098, "lr": 4.115505214083596e-06, "epoch": 16.665800415800415, "percentage": 83.33, "elapsed_time": "1:33:07", "remaining_time": "0:18:37", "throughput": 1033.57, "total_tokens": 5774840} {"current_steps": 64135, "total_steps": 76960, "loss": 0.2796, "lr": 4.112389324843313e-06, "epoch": 16.66709979209979, "percentage": 83.34, "elapsed_time": "1:33:07", "remaining_time": "0:18:37", "throughput": 1033.58, "total_tokens": 5775288} {"current_steps": 64140, "total_steps": 76960, "loss": 0.0575, "lr": 4.109274509872865e-06, "epoch": 16.66839916839917, "percentage": 83.34, "elapsed_time": "1:33:08", "remaining_time": "0:18:36", "throughput": 1033.58, "total_tokens": 5775720} {"current_steps": 64145, "total_steps": 76960, "loss": 0.0337, "lr": 4.106160769332443e-06, "epoch": 16.669698544698544, "percentage": 83.35, "elapsed_time": "1:33:08", "remaining_time": "0:18:36", "throughput": 1033.58, "total_tokens": 5776184} {"current_steps": 64150, "total_steps": 76960, "loss": 0.2115, "lr": 4.103048103382198e-06, "epoch": 16.67099792099792, "percentage": 83.35, "elapsed_time": "1:33:08", "remaining_time": "0:18:36", "throughput": 1033.59, "total_tokens": 5776632} {"current_steps": 64155, "total_steps": 76960, "loss": 0.0301, "lr": 4.099936512182207e-06, "epoch": 16.6722972972973, "percentage": 83.36, "elapsed_time": "1:33:09", "remaining_time": "0:18:35", "throughput": 1033.59, "total_tokens": 5777080} {"current_steps": 64160, "total_steps": 76960, "loss": 0.4173, "lr": 4.096825995892512e-06, "epoch": 16.673596673596673, "percentage": 83.37, "elapsed_time": "1:33:09", "remaining_time": "0:18:35", "throughput": 1033.59, "total_tokens": 5777512} {"current_steps": 64165, "total_steps": 76960, "loss": 0.2993, "lr": 4.093716554673085e-06, "epoch": 16.67489604989605, "percentage": 83.37, "elapsed_time": "1:33:10", "remaining_time": "0:18:34", "throughput": 1033.59, "total_tokens": 5777928} {"current_steps": 64170, "total_steps": 76960, "loss": 0.019, "lr": 4.090608188683842e-06, "epoch": 16.676195426195427, "percentage": 83.38, "elapsed_time": "1:33:10", "remaining_time": "0:18:34", "throughput": 1033.59, "total_tokens": 5778360} {"current_steps": 64175, "total_steps": 76960, "loss": 0.7799, "lr": 4.087500898084651e-06, "epoch": 16.677494802494802, "percentage": 83.39, "elapsed_time": "1:33:11", "remaining_time": "0:18:33", "throughput": 1033.59, "total_tokens": 5778824} {"current_steps": 64180, "total_steps": 76960, "loss": 0.347, "lr": 4.084394683035328e-06, "epoch": 16.678794178794178, "percentage": 83.39, "elapsed_time": "1:33:11", "remaining_time": "0:18:33", "throughput": 1033.59, "total_tokens": 5779256} {"current_steps": 64185, "total_steps": 76960, "loss": 0.0957, "lr": 4.081289543695635e-06, "epoch": 16.680093555093556, "percentage": 83.4, "elapsed_time": "1:33:11", "remaining_time": "0:18:32", "throughput": 1033.6, "total_tokens": 5779704} {"current_steps": 64190, "total_steps": 76960, "loss": 0.027, "lr": 4.078185480225255e-06, "epoch": 16.68139293139293, "percentage": 83.41, "elapsed_time": "1:33:12", "remaining_time": "0:18:32", "throughput": 1033.6, "total_tokens": 5780136} {"current_steps": 64195, "total_steps": 76960, "loss": 0.0457, "lr": 4.075082492783849e-06, "epoch": 16.682692307692307, "percentage": 83.41, "elapsed_time": "1:33:12", "remaining_time": "0:18:32", "throughput": 1033.6, "total_tokens": 5780600} {"current_steps": 64200, "total_steps": 76960, "loss": 0.023, "lr": 4.071980581530993e-06, "epoch": 16.683991683991685, "percentage": 83.42, "elapsed_time": "1:33:13", "remaining_time": "0:18:31", "throughput": 1033.61, "total_tokens": 5781080} {"current_steps": 64205, "total_steps": 76960, "loss": 0.011, "lr": 4.068879746626236e-06, "epoch": 16.68529106029106, "percentage": 83.43, "elapsed_time": "1:33:13", "remaining_time": "0:18:31", "throughput": 1033.62, "total_tokens": 5781544} {"current_steps": 64210, "total_steps": 76960, "loss": 0.0033, "lr": 4.06577998822904e-06, "epoch": 16.686590436590436, "percentage": 83.43, "elapsed_time": "1:33:13", "remaining_time": "0:18:30", "throughput": 1033.62, "total_tokens": 5781960} {"current_steps": 64215, "total_steps": 76960, "loss": 0.1297, "lr": 4.062681306498839e-06, "epoch": 16.687889812889814, "percentage": 83.44, "elapsed_time": "1:33:14", "remaining_time": "0:18:30", "throughput": 1033.62, "total_tokens": 5782408} {"current_steps": 64220, "total_steps": 76960, "loss": 0.6254, "lr": 4.059583701595002e-06, "epoch": 16.68918918918919, "percentage": 83.45, "elapsed_time": "1:33:14", "remaining_time": "0:18:29", "throughput": 1033.62, "total_tokens": 5782824} {"current_steps": 64225, "total_steps": 76960, "loss": 0.3244, "lr": 4.056487173676843e-06, "epoch": 16.690488565488565, "percentage": 83.45, "elapsed_time": "1:33:15", "remaining_time": "0:18:29", "throughput": 1033.62, "total_tokens": 5783288} {"current_steps": 64230, "total_steps": 76960, "loss": 0.0085, "lr": 4.053391722903616e-06, "epoch": 16.691787941787943, "percentage": 83.46, "elapsed_time": "1:33:15", "remaining_time": "0:18:29", "throughput": 1033.62, "total_tokens": 5783704} {"current_steps": 64235, "total_steps": 76960, "loss": 0.0145, "lr": 4.050297349434515e-06, "epoch": 16.69308731808732, "percentage": 83.47, "elapsed_time": "1:33:15", "remaining_time": "0:18:28", "throughput": 1033.62, "total_tokens": 5784136} {"current_steps": 64240, "total_steps": 76960, "loss": 0.1321, "lr": 4.047204053428702e-06, "epoch": 16.694386694386694, "percentage": 83.47, "elapsed_time": "1:33:16", "remaining_time": "0:18:28", "throughput": 1033.62, "total_tokens": 5784552} {"current_steps": 64245, "total_steps": 76960, "loss": 0.0161, "lr": 4.044111835045256e-06, "epoch": 16.695686070686072, "percentage": 83.48, "elapsed_time": "1:33:16", "remaining_time": "0:18:27", "throughput": 1033.62, "total_tokens": 5784968} {"current_steps": 64250, "total_steps": 76960, "loss": 0.088, "lr": 4.041020694443215e-06, "epoch": 16.696985446985448, "percentage": 83.48, "elapsed_time": "1:33:17", "remaining_time": "0:18:27", "throughput": 1033.62, "total_tokens": 5785416} {"current_steps": 64255, "total_steps": 76960, "loss": 0.0802, "lr": 4.037930631781561e-06, "epoch": 16.698284823284823, "percentage": 83.49, "elapsed_time": "1:33:17", "remaining_time": "0:18:26", "throughput": 1033.62, "total_tokens": 5785864} {"current_steps": 64260, "total_steps": 76960, "loss": 0.0008, "lr": 4.0348416472192256e-06, "epoch": 16.6995841995842, "percentage": 83.5, "elapsed_time": "1:33:18", "remaining_time": "0:18:26", "throughput": 1033.63, "total_tokens": 5786328} {"current_steps": 64265, "total_steps": 76960, "loss": 0.1228, "lr": 4.031753740915067e-06, "epoch": 16.700883575883577, "percentage": 83.5, "elapsed_time": "1:33:18", "remaining_time": "0:18:25", "throughput": 1033.63, "total_tokens": 5786776} {"current_steps": 64270, "total_steps": 76960, "loss": 0.3546, "lr": 4.028666913027912e-06, "epoch": 16.70218295218295, "percentage": 83.51, "elapsed_time": "1:33:18", "remaining_time": "0:18:25", "throughput": 1033.63, "total_tokens": 5787208} {"current_steps": 64275, "total_steps": 76960, "loss": 0.0033, "lr": 4.025581163716505e-06, "epoch": 16.703482328482327, "percentage": 83.52, "elapsed_time": "1:33:19", "remaining_time": "0:18:25", "throughput": 1033.64, "total_tokens": 5787672} {"current_steps": 64280, "total_steps": 76960, "loss": 0.0689, "lr": 4.0224964931395604e-06, "epoch": 16.704781704781706, "percentage": 83.52, "elapsed_time": "1:33:19", "remaining_time": "0:18:24", "throughput": 1033.64, "total_tokens": 5788120} {"current_steps": 64285, "total_steps": 76960, "loss": 0.0225, "lr": 4.019412901455716e-06, "epoch": 16.70608108108108, "percentage": 83.53, "elapsed_time": "1:33:20", "remaining_time": "0:18:24", "throughput": 1033.66, "total_tokens": 5788632} {"current_steps": 64290, "total_steps": 76960, "loss": 0.9927, "lr": 4.0163303888235664e-06, "epoch": 16.707380457380456, "percentage": 83.54, "elapsed_time": "1:33:20", "remaining_time": "0:18:23", "throughput": 1033.66, "total_tokens": 5789064} {"current_steps": 64295, "total_steps": 76960, "loss": 0.3855, "lr": 4.013248955401658e-06, "epoch": 16.708679833679835, "percentage": 83.54, "elapsed_time": "1:33:20", "remaining_time": "0:18:23", "throughput": 1033.66, "total_tokens": 5789496} {"current_steps": 64300, "total_steps": 76960, "loss": 0.0203, "lr": 4.010168601348458e-06, "epoch": 16.70997920997921, "percentage": 83.55, "elapsed_time": "1:33:21", "remaining_time": "0:18:22", "throughput": 1033.67, "total_tokens": 5789976} {"current_steps": 64305, "total_steps": 76960, "loss": 0.0022, "lr": 4.007089326822405e-06, "epoch": 16.711278586278585, "percentage": 83.56, "elapsed_time": "1:33:21", "remaining_time": "0:18:22", "throughput": 1033.67, "total_tokens": 5790424} {"current_steps": 64310, "total_steps": 76960, "loss": 0.2371, "lr": 4.004011131981855e-06, "epoch": 16.712577962577964, "percentage": 83.56, "elapsed_time": "1:33:22", "remaining_time": "0:18:21", "throughput": 1033.67, "total_tokens": 5790856} {"current_steps": 64315, "total_steps": 76960, "loss": 0.3883, "lr": 4.000934016985136e-06, "epoch": 16.71387733887734, "percentage": 83.57, "elapsed_time": "1:33:22", "remaining_time": "0:18:21", "throughput": 1033.68, "total_tokens": 5791320} {"current_steps": 64320, "total_steps": 76960, "loss": 0.4407, "lr": 3.997857981990491e-06, "epoch": 16.715176715176714, "percentage": 83.58, "elapsed_time": "1:33:23", "remaining_time": "0:18:21", "throughput": 1033.68, "total_tokens": 5791768} {"current_steps": 64325, "total_steps": 76960, "loss": 0.2287, "lr": 3.9947830271561435e-06, "epoch": 16.716476091476093, "percentage": 83.58, "elapsed_time": "1:33:23", "remaining_time": "0:18:20", "throughput": 1033.68, "total_tokens": 5792200} {"current_steps": 64330, "total_steps": 76960, "loss": 0.2727, "lr": 3.991709152640224e-06, "epoch": 16.717775467775468, "percentage": 83.59, "elapsed_time": "1:33:23", "remaining_time": "0:18:20", "throughput": 1033.68, "total_tokens": 5792616} {"current_steps": 64335, "total_steps": 76960, "loss": 0.2047, "lr": 3.988636358600839e-06, "epoch": 16.719074844074843, "percentage": 83.6, "elapsed_time": "1:33:24", "remaining_time": "0:18:19", "throughput": 1033.69, "total_tokens": 5793112} {"current_steps": 64340, "total_steps": 76960, "loss": 0.0009, "lr": 3.9855646451960136e-06, "epoch": 16.72037422037422, "percentage": 83.6, "elapsed_time": "1:33:24", "remaining_time": "0:18:19", "throughput": 1033.7, "total_tokens": 5793592} {"current_steps": 64345, "total_steps": 76960, "loss": 0.1631, "lr": 3.982494012583737e-06, "epoch": 16.721673596673597, "percentage": 83.61, "elapsed_time": "1:33:25", "remaining_time": "0:18:18", "throughput": 1033.71, "total_tokens": 5794072} {"current_steps": 64350, "total_steps": 76960, "loss": 0.3197, "lr": 3.9794244609219265e-06, "epoch": 16.722972972972972, "percentage": 83.61, "elapsed_time": "1:33:25", "remaining_time": "0:18:18", "throughput": 1033.71, "total_tokens": 5794520} {"current_steps": 64355, "total_steps": 76960, "loss": 0.0013, "lr": 3.976355990368458e-06, "epoch": 16.72427234927235, "percentage": 83.62, "elapsed_time": "1:33:25", "remaining_time": "0:18:18", "throughput": 1033.71, "total_tokens": 5794968} {"current_steps": 64360, "total_steps": 76960, "loss": 0.0021, "lr": 3.973288601081152e-06, "epoch": 16.725571725571726, "percentage": 83.63, "elapsed_time": "1:33:26", "remaining_time": "0:18:17", "throughput": 1033.72, "total_tokens": 5795416} {"current_steps": 64365, "total_steps": 76960, "loss": 0.0013, "lr": 3.970222293217751e-06, "epoch": 16.7268711018711, "percentage": 83.63, "elapsed_time": "1:33:26", "remaining_time": "0:18:17", "throughput": 1033.73, "total_tokens": 5795896} {"current_steps": 64370, "total_steps": 76960, "loss": 0.2739, "lr": 3.9671570669359754e-06, "epoch": 16.72817047817048, "percentage": 83.64, "elapsed_time": "1:33:27", "remaining_time": "0:18:16", "throughput": 1033.73, "total_tokens": 5796360} {"current_steps": 64375, "total_steps": 76960, "loss": 0.1055, "lr": 3.9640929223934555e-06, "epoch": 16.729469854469855, "percentage": 83.65, "elapsed_time": "1:33:27", "remaining_time": "0:18:16", "throughput": 1033.73, "total_tokens": 5796776} {"current_steps": 64380, "total_steps": 76960, "loss": 0.3283, "lr": 3.9610298597478e-06, "epoch": 16.73076923076923, "percentage": 83.65, "elapsed_time": "1:33:28", "remaining_time": "0:18:15", "throughput": 1033.74, "total_tokens": 5797240} {"current_steps": 64385, "total_steps": 76960, "loss": 0.1662, "lr": 3.957967879156533e-06, "epoch": 16.73206860706861, "percentage": 83.66, "elapsed_time": "1:33:28", "remaining_time": "0:18:15", "throughput": 1033.74, "total_tokens": 5797672} {"current_steps": 64390, "total_steps": 76960, "loss": 0.5371, "lr": 3.954906980777137e-06, "epoch": 16.733367983367984, "percentage": 83.67, "elapsed_time": "1:33:28", "remaining_time": "0:18:14", "throughput": 1033.74, "total_tokens": 5798104} {"current_steps": 64395, "total_steps": 76960, "loss": 0.1411, "lr": 3.951847164767042e-06, "epoch": 16.73466735966736, "percentage": 83.67, "elapsed_time": "1:33:29", "remaining_time": "0:18:14", "throughput": 1033.74, "total_tokens": 5798568} {"current_steps": 64400, "total_steps": 76960, "loss": 0.0941, "lr": 3.948788431283617e-06, "epoch": 16.735966735966738, "percentage": 83.68, "elapsed_time": "1:33:29", "remaining_time": "0:18:14", "throughput": 1033.75, "total_tokens": 5799048} {"current_steps": 64405, "total_steps": 76960, "loss": 0.0343, "lr": 3.945730780484172e-06, "epoch": 16.737266112266113, "percentage": 83.69, "elapsed_time": "1:33:30", "remaining_time": "0:18:13", "throughput": 1033.76, "total_tokens": 5799496} {"current_steps": 64410, "total_steps": 76960, "loss": 0.1502, "lr": 3.942674212525968e-06, "epoch": 16.738565488565488, "percentage": 83.69, "elapsed_time": "1:33:30", "remaining_time": "0:18:13", "throughput": 1033.76, "total_tokens": 5799928} {"current_steps": 64415, "total_steps": 76960, "loss": 0.2627, "lr": 3.939618727566202e-06, "epoch": 16.739864864864863, "percentage": 83.7, "elapsed_time": "1:33:30", "remaining_time": "0:18:12", "throughput": 1033.76, "total_tokens": 5800360} {"current_steps": 64420, "total_steps": 76960, "loss": 0.1432, "lr": 3.93656432576203e-06, "epoch": 16.741164241164242, "percentage": 83.71, "elapsed_time": "1:33:31", "remaining_time": "0:18:12", "throughput": 1033.77, "total_tokens": 5800840} {"current_steps": 64425, "total_steps": 76960, "loss": 0.2071, "lr": 3.933511007270529e-06, "epoch": 16.742463617463617, "percentage": 83.71, "elapsed_time": "1:33:31", "remaining_time": "0:18:11", "throughput": 1033.77, "total_tokens": 5801272} {"current_steps": 64430, "total_steps": 76960, "loss": 0.1932, "lr": 3.93045877224874e-06, "epoch": 16.743762993762992, "percentage": 83.72, "elapsed_time": "1:33:32", "remaining_time": "0:18:11", "throughput": 1033.76, "total_tokens": 5801672} {"current_steps": 64435, "total_steps": 76960, "loss": 0.1737, "lr": 3.927407620853654e-06, "epoch": 16.74506237006237, "percentage": 83.73, "elapsed_time": "1:33:32", "remaining_time": "0:18:10", "throughput": 1033.76, "total_tokens": 5802104} {"current_steps": 64440, "total_steps": 76960, "loss": 0.14, "lr": 3.9243575532421775e-06, "epoch": 16.746361746361746, "percentage": 83.73, "elapsed_time": "1:33:33", "remaining_time": "0:18:10", "throughput": 1033.76, "total_tokens": 5802552} {"current_steps": 64445, "total_steps": 76960, "loss": 0.0768, "lr": 3.921308569571192e-06, "epoch": 16.74766112266112, "percentage": 83.74, "elapsed_time": "1:33:33", "remaining_time": "0:18:10", "throughput": 1033.77, "total_tokens": 5803016} {"current_steps": 64450, "total_steps": 76960, "loss": 0.1087, "lr": 3.918260669997498e-06, "epoch": 16.7489604989605, "percentage": 83.74, "elapsed_time": "1:33:33", "remaining_time": "0:18:09", "throughput": 1033.78, "total_tokens": 5803496} {"current_steps": 64455, "total_steps": 76960, "loss": 0.2305, "lr": 3.9152138546778625e-06, "epoch": 16.750259875259875, "percentage": 83.75, "elapsed_time": "1:33:34", "remaining_time": "0:18:09", "throughput": 1033.78, "total_tokens": 5803944} {"current_steps": 64460, "total_steps": 76960, "loss": 0.2428, "lr": 3.912168123768975e-06, "epoch": 16.75155925155925, "percentage": 83.76, "elapsed_time": "1:33:34", "remaining_time": "0:18:08", "throughput": 1033.79, "total_tokens": 5804408} {"current_steps": 64465, "total_steps": 76960, "loss": 0.3427, "lr": 3.909123477427487e-06, "epoch": 16.75285862785863, "percentage": 83.76, "elapsed_time": "1:33:35", "remaining_time": "0:18:08", "throughput": 1033.79, "total_tokens": 5804856} {"current_steps": 64470, "total_steps": 76960, "loss": 0.2181, "lr": 3.906079915809984e-06, "epoch": 16.754158004158004, "percentage": 83.77, "elapsed_time": "1:33:35", "remaining_time": "0:18:07", "throughput": 1033.79, "total_tokens": 5805304} {"current_steps": 64475, "total_steps": 76960, "loss": 0.1083, "lr": 3.903037439073012e-06, "epoch": 16.75545738045738, "percentage": 83.78, "elapsed_time": "1:33:35", "remaining_time": "0:18:07", "throughput": 1033.79, "total_tokens": 5805704} {"current_steps": 64480, "total_steps": 76960, "loss": 0.5238, "lr": 3.8999960473730304e-06, "epoch": 16.756756756756758, "percentage": 83.78, "elapsed_time": "1:33:36", "remaining_time": "0:18:07", "throughput": 1033.8, "total_tokens": 5806168} {"current_steps": 64485, "total_steps": 76960, "loss": 0.3985, "lr": 3.896955740866476e-06, "epoch": 16.758056133056133, "percentage": 83.79, "elapsed_time": "1:33:36", "remaining_time": "0:18:06", "throughput": 1033.81, "total_tokens": 5806648} {"current_steps": 64490, "total_steps": 76960, "loss": 0.0029, "lr": 3.8939165197097065e-06, "epoch": 16.759355509355508, "percentage": 83.8, "elapsed_time": "1:33:37", "remaining_time": "0:18:06", "throughput": 1033.81, "total_tokens": 5807112} {"current_steps": 64495, "total_steps": 76960, "loss": 0.2008, "lr": 3.8908783840590295e-06, "epoch": 16.760654885654887, "percentage": 83.8, "elapsed_time": "1:33:37", "remaining_time": "0:18:05", "throughput": 1033.82, "total_tokens": 5807576} {"current_steps": 64500, "total_steps": 76960, "loss": 0.6151, "lr": 3.887841334070702e-06, "epoch": 16.761954261954262, "percentage": 83.81, "elapsed_time": "1:33:38", "remaining_time": "0:18:05", "throughput": 1033.82, "total_tokens": 5807992} {"current_steps": 64505, "total_steps": 76960, "loss": 0.1948, "lr": 3.88480536990092e-06, "epoch": 16.763253638253637, "percentage": 83.82, "elapsed_time": "1:33:38", "remaining_time": "0:18:04", "throughput": 1033.82, "total_tokens": 5808424} {"current_steps": 64510, "total_steps": 76960, "loss": 0.0045, "lr": 3.8817704917058415e-06, "epoch": 16.764553014553016, "percentage": 83.82, "elapsed_time": "1:33:38", "remaining_time": "0:18:04", "throughput": 1033.82, "total_tokens": 5808872} {"current_steps": 64515, "total_steps": 76960, "loss": 0.089, "lr": 3.87873669964153e-06, "epoch": 16.76585239085239, "percentage": 83.83, "elapsed_time": "1:33:39", "remaining_time": "0:18:03", "throughput": 1033.82, "total_tokens": 5809304} {"current_steps": 64520, "total_steps": 76960, "loss": 0.136, "lr": 3.875703993864036e-06, "epoch": 16.767151767151766, "percentage": 83.84, "elapsed_time": "1:33:39", "remaining_time": "0:18:03", "throughput": 1033.83, "total_tokens": 5809784} {"current_steps": 64525, "total_steps": 76960, "loss": 0.2408, "lr": 3.872672374529321e-06, "epoch": 16.768451143451145, "percentage": 83.84, "elapsed_time": "1:33:40", "remaining_time": "0:18:03", "throughput": 1033.83, "total_tokens": 5810216} {"current_steps": 64530, "total_steps": 76960, "loss": 0.2021, "lr": 3.869641841793311e-06, "epoch": 16.76975051975052, "percentage": 83.85, "elapsed_time": "1:33:40", "remaining_time": "0:18:02", "throughput": 1033.83, "total_tokens": 5810648} {"current_steps": 64535, "total_steps": 76960, "loss": 0.0623, "lr": 3.866612395811864e-06, "epoch": 16.771049896049895, "percentage": 83.86, "elapsed_time": "1:33:40", "remaining_time": "0:18:02", "throughput": 1033.83, "total_tokens": 5811080} {"current_steps": 64540, "total_steps": 76960, "loss": 0.1289, "lr": 3.863584036740792e-06, "epoch": 16.772349272349274, "percentage": 83.86, "elapsed_time": "1:33:41", "remaining_time": "0:18:01", "throughput": 1033.83, "total_tokens": 5811512} {"current_steps": 64545, "total_steps": 76960, "loss": 0.1612, "lr": 3.860556764735842e-06, "epoch": 16.77364864864865, "percentage": 83.87, "elapsed_time": "1:33:41", "remaining_time": "0:18:01", "throughput": 1033.83, "total_tokens": 5811960} {"current_steps": 64550, "total_steps": 76960, "loss": 0.3919, "lr": 3.85753057995272e-06, "epoch": 16.774948024948024, "percentage": 83.87, "elapsed_time": "1:33:42", "remaining_time": "0:18:00", "throughput": 1033.83, "total_tokens": 5812376} {"current_steps": 64555, "total_steps": 76960, "loss": 0.0179, "lr": 3.854505482547057e-06, "epoch": 16.776247401247403, "percentage": 83.88, "elapsed_time": "1:33:42", "remaining_time": "0:18:00", "throughput": 1033.83, "total_tokens": 5812808} {"current_steps": 64560, "total_steps": 76960, "loss": 0.3304, "lr": 3.851481472674434e-06, "epoch": 16.777546777546778, "percentage": 83.89, "elapsed_time": "1:33:43", "remaining_time": "0:18:00", "throughput": 1033.83, "total_tokens": 5813224} {"current_steps": 64565, "total_steps": 76960, "loss": 0.0318, "lr": 3.848458550490386e-06, "epoch": 16.778846153846153, "percentage": 83.89, "elapsed_time": "1:33:43", "remaining_time": "0:17:59", "throughput": 1033.84, "total_tokens": 5813688} {"current_steps": 64570, "total_steps": 76960, "loss": 0.5241, "lr": 3.845436716150369e-06, "epoch": 16.78014553014553, "percentage": 83.9, "elapsed_time": "1:33:43", "remaining_time": "0:17:59", "throughput": 1033.84, "total_tokens": 5814152} {"current_steps": 64575, "total_steps": 76960, "loss": 0.2232, "lr": 3.842415969809823e-06, "epoch": 16.781444906444907, "percentage": 83.91, "elapsed_time": "1:33:44", "remaining_time": "0:17:58", "throughput": 1033.85, "total_tokens": 5814648} {"current_steps": 64580, "total_steps": 76960, "loss": 0.3652, "lr": 3.839396311624091e-06, "epoch": 16.782744282744282, "percentage": 83.91, "elapsed_time": "1:33:44", "remaining_time": "0:17:58", "throughput": 1033.85, "total_tokens": 5815064} {"current_steps": 64585, "total_steps": 76960, "loss": 0.0045, "lr": 3.83637774174849e-06, "epoch": 16.784043659043657, "percentage": 83.92, "elapsed_time": "1:33:45", "remaining_time": "0:17:57", "throughput": 1033.85, "total_tokens": 5815512} {"current_steps": 64590, "total_steps": 76960, "loss": 0.0492, "lr": 3.833360260338251e-06, "epoch": 16.785343035343036, "percentage": 83.93, "elapsed_time": "1:33:45", "remaining_time": "0:17:57", "throughput": 1033.86, "total_tokens": 5815960} {"current_steps": 64595, "total_steps": 76960, "loss": 0.4683, "lr": 3.8303438675485804e-06, "epoch": 16.78664241164241, "percentage": 83.93, "elapsed_time": "1:33:45", "remaining_time": "0:17:56", "throughput": 1033.87, "total_tokens": 5816440} {"current_steps": 64600, "total_steps": 76960, "loss": 0.1691, "lr": 3.827328563534602e-06, "epoch": 16.787941787941786, "percentage": 83.94, "elapsed_time": "1:33:46", "remaining_time": "0:17:56", "throughput": 1033.87, "total_tokens": 5816904} {"current_steps": 64605, "total_steps": 76960, "loss": 0.1464, "lr": 3.824314348451405e-06, "epoch": 16.789241164241165, "percentage": 83.95, "elapsed_time": "1:33:46", "remaining_time": "0:17:56", "throughput": 1033.87, "total_tokens": 5817336} {"current_steps": 64610, "total_steps": 76960, "loss": 0.3523, "lr": 3.821301222454008e-06, "epoch": 16.79054054054054, "percentage": 83.95, "elapsed_time": "1:33:47", "remaining_time": "0:17:55", "throughput": 1033.88, "total_tokens": 5817800} {"current_steps": 64615, "total_steps": 76960, "loss": 0.2818, "lr": 3.818289185697388e-06, "epoch": 16.791839916839916, "percentage": 83.96, "elapsed_time": "1:33:47", "remaining_time": "0:17:55", "throughput": 1033.89, "total_tokens": 5818264} {"current_steps": 64620, "total_steps": 76960, "loss": 0.0126, "lr": 3.8152782383364506e-06, "epoch": 16.793139293139294, "percentage": 83.97, "elapsed_time": "1:33:47", "remaining_time": "0:17:54", "throughput": 1033.89, "total_tokens": 5818728} {"current_steps": 64625, "total_steps": 76960, "loss": 0.2441, "lr": 3.812268380526046e-06, "epoch": 16.79443866943867, "percentage": 83.97, "elapsed_time": "1:33:48", "remaining_time": "0:17:54", "throughput": 1033.9, "total_tokens": 5819192} {"current_steps": 64630, "total_steps": 76960, "loss": 0.1825, "lr": 3.8092596124209874e-06, "epoch": 16.795738045738045, "percentage": 83.98, "elapsed_time": "1:33:48", "remaining_time": "0:17:53", "throughput": 1033.9, "total_tokens": 5819624} {"current_steps": 64635, "total_steps": 76960, "loss": 0.024, "lr": 3.8062519341760027e-06, "epoch": 16.797037422037423, "percentage": 83.99, "elapsed_time": "1:33:49", "remaining_time": "0:17:53", "throughput": 1033.9, "total_tokens": 5820056} {"current_steps": 64640, "total_steps": 76960, "loss": 0.0409, "lr": 3.8032453459457884e-06, "epoch": 16.7983367983368, "percentage": 83.99, "elapsed_time": "1:33:49", "remaining_time": "0:17:52", "throughput": 1033.91, "total_tokens": 5820536} {"current_steps": 64645, "total_steps": 76960, "loss": 0.2122, "lr": 3.800239847884976e-06, "epoch": 16.799636174636174, "percentage": 84.0, "elapsed_time": "1:33:50", "remaining_time": "0:17:52", "throughput": 1033.92, "total_tokens": 5821016} {"current_steps": 64650, "total_steps": 76960, "loss": 0.1127, "lr": 3.7972354401481474e-06, "epoch": 16.800935550935552, "percentage": 84.0, "elapsed_time": "1:33:50", "remaining_time": "0:17:52", "throughput": 1033.92, "total_tokens": 5821480} {"current_steps": 64655, "total_steps": 76960, "loss": 0.0649, "lr": 3.794232122889807e-06, "epoch": 16.802234927234927, "percentage": 84.01, "elapsed_time": "1:33:50", "remaining_time": "0:17:51", "throughput": 1033.92, "total_tokens": 5821912} {"current_steps": 64660, "total_steps": 76960, "loss": 0.443, "lr": 3.7912298962644367e-06, "epoch": 16.803534303534303, "percentage": 84.02, "elapsed_time": "1:33:51", "remaining_time": "0:17:51", "throughput": 1033.93, "total_tokens": 5822344} {"current_steps": 64665, "total_steps": 76960, "loss": 0.2566, "lr": 3.7882287604264236e-06, "epoch": 16.80483367983368, "percentage": 84.02, "elapsed_time": "1:33:51", "remaining_time": "0:17:50", "throughput": 1033.93, "total_tokens": 5822792} {"current_steps": 64670, "total_steps": 76960, "loss": 0.493, "lr": 3.7852287155301396e-06, "epoch": 16.806133056133056, "percentage": 84.03, "elapsed_time": "1:33:52", "remaining_time": "0:17:50", "throughput": 1033.93, "total_tokens": 5823240} {"current_steps": 64675, "total_steps": 76960, "loss": 0.2847, "lr": 3.7822297617298606e-06, "epoch": 16.80743243243243, "percentage": 84.04, "elapsed_time": "1:33:52", "remaining_time": "0:17:49", "throughput": 1033.94, "total_tokens": 5823688} {"current_steps": 64680, "total_steps": 76960, "loss": 0.3714, "lr": 3.7792318991798386e-06, "epoch": 16.80873180873181, "percentage": 84.04, "elapsed_time": "1:33:52", "remaining_time": "0:17:49", "throughput": 1033.94, "total_tokens": 5824152} {"current_steps": 64685, "total_steps": 76960, "loss": 0.1709, "lr": 3.7762351280342556e-06, "epoch": 16.810031185031185, "percentage": 84.05, "elapsed_time": "1:33:53", "remaining_time": "0:17:49", "throughput": 1033.95, "total_tokens": 5824600} {"current_steps": 64690, "total_steps": 76960, "loss": 0.0517, "lr": 3.77323944844723e-06, "epoch": 16.81133056133056, "percentage": 84.06, "elapsed_time": "1:33:53", "remaining_time": "0:17:48", "throughput": 1033.95, "total_tokens": 5825080} {"current_steps": 64695, "total_steps": 76960, "loss": 0.0328, "lr": 3.7702448605728467e-06, "epoch": 16.81262993762994, "percentage": 84.06, "elapsed_time": "1:33:54", "remaining_time": "0:17:48", "throughput": 1033.96, "total_tokens": 5825544} {"current_steps": 64700, "total_steps": 76960, "loss": 0.0242, "lr": 3.7672513645651024e-06, "epoch": 16.813929313929314, "percentage": 84.07, "elapsed_time": "1:33:54", "remaining_time": "0:17:47", "throughput": 1033.97, "total_tokens": 5826008} {"current_steps": 64705, "total_steps": 76960, "loss": 0.061, "lr": 3.764258960577971e-06, "epoch": 16.81522869022869, "percentage": 84.08, "elapsed_time": "1:33:55", "remaining_time": "0:17:47", "throughput": 1033.97, "total_tokens": 5826456} {"current_steps": 64710, "total_steps": 76960, "loss": 0.0471, "lr": 3.7612676487653432e-06, "epoch": 16.816528066528065, "percentage": 84.08, "elapsed_time": "1:33:55", "remaining_time": "0:17:46", "throughput": 1033.97, "total_tokens": 5826888} {"current_steps": 64715, "total_steps": 76960, "loss": 0.0637, "lr": 3.7582774292810708e-06, "epoch": 16.817827442827443, "percentage": 84.09, "elapsed_time": "1:33:55", "remaining_time": "0:17:46", "throughput": 1033.97, "total_tokens": 5827336} {"current_steps": 64720, "total_steps": 76960, "loss": 0.3914, "lr": 3.755288302278942e-06, "epoch": 16.81912681912682, "percentage": 84.1, "elapsed_time": "1:33:56", "remaining_time": "0:17:45", "throughput": 1033.98, "total_tokens": 5827800} {"current_steps": 64725, "total_steps": 76960, "loss": 0.2159, "lr": 3.7523002679126978e-06, "epoch": 16.820426195426194, "percentage": 84.1, "elapsed_time": "1:33:56", "remaining_time": "0:17:45", "throughput": 1033.98, "total_tokens": 5828248} {"current_steps": 64730, "total_steps": 76960, "loss": 0.0563, "lr": 3.749313326336004e-06, "epoch": 16.821725571725572, "percentage": 84.11, "elapsed_time": "1:33:57", "remaining_time": "0:17:45", "throughput": 1033.99, "total_tokens": 5828712} {"current_steps": 64735, "total_steps": 76960, "loss": 0.091, "lr": 3.7463274777024936e-06, "epoch": 16.823024948024948, "percentage": 84.12, "elapsed_time": "1:33:57", "remaining_time": "0:17:44", "throughput": 1033.99, "total_tokens": 5829144} {"current_steps": 64740, "total_steps": 76960, "loss": 0.1675, "lr": 3.7433427221657186e-06, "epoch": 16.824324324324323, "percentage": 84.12, "elapsed_time": "1:33:57", "remaining_time": "0:17:44", "throughput": 1034.0, "total_tokens": 5829624} {"current_steps": 64745, "total_steps": 76960, "loss": 0.0089, "lr": 3.7403590598792003e-06, "epoch": 16.8256237006237, "percentage": 84.13, "elapsed_time": "1:33:58", "remaining_time": "0:17:43", "throughput": 1034.01, "total_tokens": 5830104} {"current_steps": 64750, "total_steps": 76960, "loss": 0.0024, "lr": 3.7373764909963806e-06, "epoch": 16.826923076923077, "percentage": 84.13, "elapsed_time": "1:33:58", "remaining_time": "0:17:43", "throughput": 1034.01, "total_tokens": 5830552} {"current_steps": 64755, "total_steps": 76960, "loss": 0.2509, "lr": 3.7343950156706608e-06, "epoch": 16.828222453222452, "percentage": 84.14, "elapsed_time": "1:33:59", "remaining_time": "0:17:42", "throughput": 1034.01, "total_tokens": 5830968} {"current_steps": 64760, "total_steps": 76960, "loss": 0.0344, "lr": 3.7314146340553857e-06, "epoch": 16.82952182952183, "percentage": 84.15, "elapsed_time": "1:33:59", "remaining_time": "0:17:42", "throughput": 1034.01, "total_tokens": 5831432} {"current_steps": 64765, "total_steps": 76960, "loss": 0.2569, "lr": 3.7284353463038297e-06, "epoch": 16.830821205821206, "percentage": 84.15, "elapsed_time": "1:34:00", "remaining_time": "0:17:41", "throughput": 1034.01, "total_tokens": 5831864} {"current_steps": 64770, "total_steps": 76960, "loss": 0.1829, "lr": 3.7254571525692283e-06, "epoch": 16.83212058212058, "percentage": 84.16, "elapsed_time": "1:34:00", "remaining_time": "0:17:41", "throughput": 1034.01, "total_tokens": 5832264} {"current_steps": 64775, "total_steps": 76960, "loss": 0.097, "lr": 3.7224800530047484e-06, "epoch": 16.83341995841996, "percentage": 84.17, "elapsed_time": "1:34:00", "remaining_time": "0:17:41", "throughput": 1034.02, "total_tokens": 5832776} {"current_steps": 64780, "total_steps": 76960, "loss": 0.0147, "lr": 3.7195040477635084e-06, "epoch": 16.834719334719335, "percentage": 84.17, "elapsed_time": "1:34:01", "remaining_time": "0:17:40", "throughput": 1034.03, "total_tokens": 5833240} {"current_steps": 64785, "total_steps": 76960, "loss": 0.0362, "lr": 3.7165291369985618e-06, "epoch": 16.83601871101871, "percentage": 84.18, "elapsed_time": "1:34:01", "remaining_time": "0:17:40", "throughput": 1034.04, "total_tokens": 5833720} {"current_steps": 64790, "total_steps": 76960, "loss": 0.0502, "lr": 3.713555320862913e-06, "epoch": 16.83731808731809, "percentage": 84.19, "elapsed_time": "1:34:02", "remaining_time": "0:17:39", "throughput": 1034.04, "total_tokens": 5834152} {"current_steps": 64795, "total_steps": 76960, "loss": 0.1037, "lr": 3.710582599509513e-06, "epoch": 16.838617463617464, "percentage": 84.19, "elapsed_time": "1:34:02", "remaining_time": "0:17:39", "throughput": 1034.04, "total_tokens": 5834584} {"current_steps": 64800, "total_steps": 76960, "loss": 0.2036, "lr": 3.7076109730912494e-06, "epoch": 16.83991683991684, "percentage": 84.2, "elapsed_time": "1:34:02", "remaining_time": "0:17:38", "throughput": 1034.04, "total_tokens": 5835032} {"current_steps": 64805, "total_steps": 76960, "loss": 0.0932, "lr": 3.7046404417609538e-06, "epoch": 16.841216216216218, "percentage": 84.21, "elapsed_time": "1:34:03", "remaining_time": "0:17:38", "throughput": 1034.05, "total_tokens": 5835480} {"current_steps": 64810, "total_steps": 76960, "loss": 0.0041, "lr": 3.701671005671406e-06, "epoch": 16.842515592515593, "percentage": 84.21, "elapsed_time": "1:34:03", "remaining_time": "0:17:38", "throughput": 1034.04, "total_tokens": 5835896} {"current_steps": 64815, "total_steps": 76960, "loss": 0.161, "lr": 3.6987026649753286e-06, "epoch": 16.843814968814968, "percentage": 84.22, "elapsed_time": "1:34:04", "remaining_time": "0:17:37", "throughput": 1034.04, "total_tokens": 5836312} {"current_steps": 64820, "total_steps": 76960, "loss": 0.0796, "lr": 3.695735419825369e-06, "epoch": 16.845114345114347, "percentage": 84.23, "elapsed_time": "1:34:04", "remaining_time": "0:17:37", "throughput": 1034.05, "total_tokens": 5836776} {"current_steps": 64825, "total_steps": 76960, "loss": 0.4437, "lr": 3.6927692703741634e-06, "epoch": 16.84641372141372, "percentage": 84.23, "elapsed_time": "1:34:05", "remaining_time": "0:17:36", "throughput": 1034.04, "total_tokens": 5837176} {"current_steps": 64830, "total_steps": 76960, "loss": 0.1327, "lr": 3.6898042167742426e-06, "epoch": 16.847713097713097, "percentage": 84.24, "elapsed_time": "1:34:05", "remaining_time": "0:17:36", "throughput": 1034.05, "total_tokens": 5837640} {"current_steps": 64835, "total_steps": 76960, "loss": 0.139, "lr": 3.6868402591781175e-06, "epoch": 16.849012474012476, "percentage": 84.25, "elapsed_time": "1:34:05", "remaining_time": "0:17:35", "throughput": 1034.05, "total_tokens": 5838072} {"current_steps": 64840, "total_steps": 76960, "loss": 0.0237, "lr": 3.6838773977382113e-06, "epoch": 16.85031185031185, "percentage": 84.25, "elapsed_time": "1:34:06", "remaining_time": "0:17:35", "throughput": 1034.04, "total_tokens": 5838488} {"current_steps": 64845, "total_steps": 76960, "loss": 0.2425, "lr": 3.6809156326069183e-06, "epoch": 16.851611226611226, "percentage": 84.26, "elapsed_time": "1:34:06", "remaining_time": "0:17:34", "throughput": 1034.06, "total_tokens": 5838984} {"current_steps": 64850, "total_steps": 76960, "loss": 0.1394, "lr": 3.6779549639365584e-06, "epoch": 16.852910602910605, "percentage": 84.26, "elapsed_time": "1:34:07", "remaining_time": "0:17:34", "throughput": 1034.06, "total_tokens": 5839432} {"current_steps": 64855, "total_steps": 76960, "loss": 0.5607, "lr": 3.6749953918794043e-06, "epoch": 16.85420997920998, "percentage": 84.27, "elapsed_time": "1:34:07", "remaining_time": "0:17:34", "throughput": 1034.06, "total_tokens": 5839880} {"current_steps": 64860, "total_steps": 76960, "loss": 0.2382, "lr": 3.6720369165876704e-06, "epoch": 16.855509355509355, "percentage": 84.28, "elapsed_time": "1:34:07", "remaining_time": "0:17:33", "throughput": 1034.07, "total_tokens": 5840344} {"current_steps": 64865, "total_steps": 76960, "loss": 0.1683, "lr": 3.6690795382135186e-06, "epoch": 16.856808731808734, "percentage": 84.28, "elapsed_time": "1:34:08", "remaining_time": "0:17:33", "throughput": 1034.07, "total_tokens": 5840776} {"current_steps": 64870, "total_steps": 76960, "loss": 0.0949, "lr": 3.6661232569090375e-06, "epoch": 16.85810810810811, "percentage": 84.29, "elapsed_time": "1:34:08", "remaining_time": "0:17:32", "throughput": 1034.08, "total_tokens": 5841256} {"current_steps": 64875, "total_steps": 76960, "loss": 0.1441, "lr": 3.663168072826284e-06, "epoch": 16.859407484407484, "percentage": 84.3, "elapsed_time": "1:34:09", "remaining_time": "0:17:32", "throughput": 1034.08, "total_tokens": 5841704} {"current_steps": 64880, "total_steps": 76960, "loss": 0.0713, "lr": 3.660213986117242e-06, "epoch": 16.86070686070686, "percentage": 84.3, "elapsed_time": "1:34:09", "remaining_time": "0:17:31", "throughput": 1034.08, "total_tokens": 5842152} {"current_steps": 64885, "total_steps": 76960, "loss": 0.3256, "lr": 3.6572609969338365e-06, "epoch": 16.862006237006238, "percentage": 84.31, "elapsed_time": "1:34:10", "remaining_time": "0:17:31", "throughput": 1034.08, "total_tokens": 5842584} {"current_steps": 64890, "total_steps": 76960, "loss": 0.0092, "lr": 3.6543091054279445e-06, "epoch": 16.863305613305613, "percentage": 84.32, "elapsed_time": "1:34:10", "remaining_time": "0:17:31", "throughput": 1034.09, "total_tokens": 5843048} {"current_steps": 64895, "total_steps": 76960, "loss": 0.083, "lr": 3.6513583117513906e-06, "epoch": 16.864604989604988, "percentage": 84.32, "elapsed_time": "1:34:10", "remaining_time": "0:17:30", "throughput": 1034.09, "total_tokens": 5843496} {"current_steps": 64900, "total_steps": 76960, "loss": 0.0419, "lr": 3.648408616055937e-06, "epoch": 16.865904365904367, "percentage": 84.33, "elapsed_time": "1:34:11", "remaining_time": "0:17:30", "throughput": 1034.1, "total_tokens": 5843944} {"current_steps": 64905, "total_steps": 76960, "loss": 0.0729, "lr": 3.6454600184932824e-06, "epoch": 16.867203742203742, "percentage": 84.34, "elapsed_time": "1:34:11", "remaining_time": "0:17:29", "throughput": 1034.09, "total_tokens": 5844360} {"current_steps": 64910, "total_steps": 76960, "loss": 0.0477, "lr": 3.6425125192150854e-06, "epoch": 16.868503118503117, "percentage": 84.34, "elapsed_time": "1:34:12", "remaining_time": "0:17:29", "throughput": 1034.1, "total_tokens": 5844824} {"current_steps": 64915, "total_steps": 76960, "loss": 0.0927, "lr": 3.639566118372928e-06, "epoch": 16.869802494802496, "percentage": 84.35, "elapsed_time": "1:34:12", "remaining_time": "0:17:28", "throughput": 1034.11, "total_tokens": 5845288} {"current_steps": 64920, "total_steps": 76960, "loss": 0.1126, "lr": 3.6366208161183578e-06, "epoch": 16.87110187110187, "percentage": 84.36, "elapsed_time": "1:34:12", "remaining_time": "0:17:28", "throughput": 1034.1, "total_tokens": 5845704} {"current_steps": 64925, "total_steps": 76960, "loss": 0.0319, "lr": 3.633676612602843e-06, "epoch": 16.872401247401246, "percentage": 84.36, "elapsed_time": "1:34:13", "remaining_time": "0:17:27", "throughput": 1034.1, "total_tokens": 5846120} {"current_steps": 64930, "total_steps": 76960, "loss": 0.0015, "lr": 3.6307335079778097e-06, "epoch": 16.873700623700625, "percentage": 84.37, "elapsed_time": "1:34:13", "remaining_time": "0:17:27", "throughput": 1034.1, "total_tokens": 5846552} {"current_steps": 64935, "total_steps": 76960, "loss": 0.1723, "lr": 3.6277915023946285e-06, "epoch": 16.875, "percentage": 84.38, "elapsed_time": "1:34:14", "remaining_time": "0:17:27", "throughput": 1034.11, "total_tokens": 5847016} {"current_steps": 64940, "total_steps": 76960, "loss": 0.0019, "lr": 3.6248505960046144e-06, "epoch": 16.876299376299375, "percentage": 84.38, "elapsed_time": "1:34:14", "remaining_time": "0:17:26", "throughput": 1034.11, "total_tokens": 5847464} {"current_steps": 64945, "total_steps": 76960, "loss": 0.0026, "lr": 3.6219107889590155e-06, "epoch": 16.877598752598754, "percentage": 84.39, "elapsed_time": "1:34:15", "remaining_time": "0:17:26", "throughput": 1034.11, "total_tokens": 5847896} {"current_steps": 64950, "total_steps": 76960, "loss": 0.2225, "lr": 3.6189720814090223e-06, "epoch": 16.87889812889813, "percentage": 84.39, "elapsed_time": "1:34:15", "remaining_time": "0:17:25", "throughput": 1034.11, "total_tokens": 5848344} {"current_steps": 64955, "total_steps": 76960, "loss": 0.0446, "lr": 3.616034473505786e-06, "epoch": 16.880197505197504, "percentage": 84.4, "elapsed_time": "1:34:15", "remaining_time": "0:17:25", "throughput": 1034.11, "total_tokens": 5848776} {"current_steps": 64960, "total_steps": 76960, "loss": 0.288, "lr": 3.6130979654003805e-06, "epoch": 16.881496881496883, "percentage": 84.41, "elapsed_time": "1:34:16", "remaining_time": "0:17:24", "throughput": 1034.12, "total_tokens": 5849224} {"current_steps": 64965, "total_steps": 76960, "loss": 0.1574, "lr": 3.6101625572438373e-06, "epoch": 16.882796257796258, "percentage": 84.41, "elapsed_time": "1:34:16", "remaining_time": "0:17:24", "throughput": 1034.12, "total_tokens": 5849672} {"current_steps": 64970, "total_steps": 76960, "loss": 0.0321, "lr": 3.6072282491871306e-06, "epoch": 16.884095634095633, "percentage": 84.42, "elapsed_time": "1:34:17", "remaining_time": "0:17:23", "throughput": 1034.13, "total_tokens": 5850136} {"current_steps": 64975, "total_steps": 76960, "loss": 0.0232, "lr": 3.6042950413811784e-06, "epoch": 16.885395010395012, "percentage": 84.43, "elapsed_time": "1:34:17", "remaining_time": "0:17:23", "throughput": 1034.12, "total_tokens": 5850552} {"current_steps": 64980, "total_steps": 76960, "loss": 0.2433, "lr": 3.6013629339768264e-06, "epoch": 16.886694386694387, "percentage": 84.43, "elapsed_time": "1:34:17", "remaining_time": "0:17:23", "throughput": 1034.12, "total_tokens": 5850984} {"current_steps": 64985, "total_steps": 76960, "loss": 0.1442, "lr": 3.5984319271248844e-06, "epoch": 16.887993762993762, "percentage": 84.44, "elapsed_time": "1:34:18", "remaining_time": "0:17:22", "throughput": 1034.12, "total_tokens": 5851416} {"current_steps": 64990, "total_steps": 76960, "loss": 0.2432, "lr": 3.5955020209760935e-06, "epoch": 16.88929313929314, "percentage": 84.45, "elapsed_time": "1:34:18", "remaining_time": "0:17:22", "throughput": 1034.13, "total_tokens": 5851864} {"current_steps": 64995, "total_steps": 76960, "loss": 0.1679, "lr": 3.592573215681144e-06, "epoch": 16.890592515592516, "percentage": 84.45, "elapsed_time": "1:34:19", "remaining_time": "0:17:21", "throughput": 1034.13, "total_tokens": 5852296} {"current_steps": 65000, "total_steps": 76960, "loss": 0.0243, "lr": 3.589645511390663e-06, "epoch": 16.89189189189189, "percentage": 84.46, "elapsed_time": "1:34:19", "remaining_time": "0:17:21", "throughput": 1034.13, "total_tokens": 5852744} {"current_steps": 65005, "total_steps": 76960, "loss": 0.0145, "lr": 3.5867189082552266e-06, "epoch": 16.893191268191266, "percentage": 84.47, "elapsed_time": "1:34:19", "remaining_time": "0:17:20", "throughput": 1034.14, "total_tokens": 5853208} {"current_steps": 65010, "total_steps": 76960, "loss": 0.2516, "lr": 3.583793406425359e-06, "epoch": 16.894490644490645, "percentage": 84.47, "elapsed_time": "1:34:20", "remaining_time": "0:17:20", "throughput": 1034.15, "total_tokens": 5853704} {"current_steps": 65015, "total_steps": 76960, "loss": 0.034, "lr": 3.5808690060515126e-06, "epoch": 16.89579002079002, "percentage": 84.48, "elapsed_time": "1:34:20", "remaining_time": "0:17:20", "throughput": 1034.15, "total_tokens": 5854152} {"current_steps": 65020, "total_steps": 76960, "loss": 0.0013, "lr": 3.5779457072841e-06, "epoch": 16.897089397089395, "percentage": 84.49, "elapsed_time": "1:34:21", "remaining_time": "0:17:19", "throughput": 1034.16, "total_tokens": 5854632} {"current_steps": 65025, "total_steps": 76960, "loss": 0.0052, "lr": 3.575023510273462e-06, "epoch": 16.898388773388774, "percentage": 84.49, "elapsed_time": "1:34:21", "remaining_time": "0:17:19", "throughput": 1034.17, "total_tokens": 5855112} {"current_steps": 65030, "total_steps": 76960, "loss": 0.3949, "lr": 3.572102415169898e-06, "epoch": 16.89968814968815, "percentage": 84.5, "elapsed_time": "1:34:22", "remaining_time": "0:17:18", "throughput": 1034.17, "total_tokens": 5855560} {"current_steps": 65035, "total_steps": 76960, "loss": 0.0016, "lr": 3.569182422123629e-06, "epoch": 16.900987525987524, "percentage": 84.5, "elapsed_time": "1:34:22", "remaining_time": "0:17:18", "throughput": 1034.18, "total_tokens": 5856024} {"current_steps": 65040, "total_steps": 76960, "loss": 0.2809, "lr": 3.566263531284847e-06, "epoch": 16.902286902286903, "percentage": 84.51, "elapsed_time": "1:34:22", "remaining_time": "0:17:17", "throughput": 1034.18, "total_tokens": 5856472} {"current_steps": 65045, "total_steps": 76960, "loss": 0.1569, "lr": 3.5633457428036644e-06, "epoch": 16.90358627858628, "percentage": 84.52, "elapsed_time": "1:34:23", "remaining_time": "0:17:17", "throughput": 1034.19, "total_tokens": 5856920} {"current_steps": 65050, "total_steps": 76960, "loss": 0.0676, "lr": 3.5604290568301586e-06, "epoch": 16.904885654885653, "percentage": 84.52, "elapsed_time": "1:34:23", "remaining_time": "0:17:16", "throughput": 1034.2, "total_tokens": 5857416} {"current_steps": 65055, "total_steps": 76960, "loss": 0.0062, "lr": 3.557513473514321e-06, "epoch": 16.906185031185032, "percentage": 84.53, "elapsed_time": "1:34:24", "remaining_time": "0:17:16", "throughput": 1034.2, "total_tokens": 5857832} {"current_steps": 65060, "total_steps": 76960, "loss": 0.0388, "lr": 3.5545989930061167e-06, "epoch": 16.907484407484407, "percentage": 84.54, "elapsed_time": "1:34:24", "remaining_time": "0:17:16", "throughput": 1034.2, "total_tokens": 5858280} {"current_steps": 65065, "total_steps": 76960, "loss": 0.0724, "lr": 3.55168561545543e-06, "epoch": 16.908783783783782, "percentage": 84.54, "elapsed_time": "1:34:24", "remaining_time": "0:17:15", "throughput": 1034.21, "total_tokens": 5858744} {"current_steps": 65070, "total_steps": 76960, "loss": 0.6559, "lr": 3.5487733410121015e-06, "epoch": 16.91008316008316, "percentage": 84.55, "elapsed_time": "1:34:25", "remaining_time": "0:17:15", "throughput": 1034.2, "total_tokens": 5859160} {"current_steps": 65075, "total_steps": 76960, "loss": 0.1164, "lr": 3.54586216982592e-06, "epoch": 16.911382536382536, "percentage": 84.56, "elapsed_time": "1:34:25", "remaining_time": "0:17:14", "throughput": 1034.21, "total_tokens": 5859640} {"current_steps": 65080, "total_steps": 76960, "loss": 0.1065, "lr": 3.542952102046598e-06, "epoch": 16.91268191268191, "percentage": 84.56, "elapsed_time": "1:34:26", "remaining_time": "0:17:14", "throughput": 1034.22, "total_tokens": 5860104} {"current_steps": 65085, "total_steps": 76960, "loss": 0.2968, "lr": 3.540043137823812e-06, "epoch": 16.91398128898129, "percentage": 84.57, "elapsed_time": "1:34:26", "remaining_time": "0:17:13", "throughput": 1034.22, "total_tokens": 5860552} {"current_steps": 65090, "total_steps": 76960, "loss": 0.0191, "lr": 3.537135277307166e-06, "epoch": 16.915280665280665, "percentage": 84.58, "elapsed_time": "1:34:27", "remaining_time": "0:17:13", "throughput": 1034.23, "total_tokens": 5861032} {"current_steps": 65095, "total_steps": 76960, "loss": 0.0062, "lr": 3.534228520646224e-06, "epoch": 16.91658004158004, "percentage": 84.58, "elapsed_time": "1:34:27", "remaining_time": "0:17:13", "throughput": 1034.24, "total_tokens": 5861480} {"current_steps": 65100, "total_steps": 76960, "loss": 0.1118, "lr": 3.531322867990469e-06, "epoch": 16.91787941787942, "percentage": 84.59, "elapsed_time": "1:34:27", "remaining_time": "0:17:12", "throughput": 1034.24, "total_tokens": 5861912} {"current_steps": 65105, "total_steps": 76960, "loss": 0.103, "lr": 3.5284183194893488e-06, "epoch": 16.919178794178794, "percentage": 84.6, "elapsed_time": "1:34:28", "remaining_time": "0:17:12", "throughput": 1034.26, "total_tokens": 5862456} {"current_steps": 65110, "total_steps": 76960, "loss": 0.4825, "lr": 3.525514875292249e-06, "epoch": 16.92047817047817, "percentage": 84.6, "elapsed_time": "1:34:28", "remaining_time": "0:17:11", "throughput": 1034.26, "total_tokens": 5862888} {"current_steps": 65115, "total_steps": 76960, "loss": 0.0303, "lr": 3.5226125355485e-06, "epoch": 16.921777546777548, "percentage": 84.61, "elapsed_time": "1:34:29", "remaining_time": "0:17:11", "throughput": 1034.26, "total_tokens": 5863336} {"current_steps": 65120, "total_steps": 76960, "loss": 0.2614, "lr": 3.5197113004073604e-06, "epoch": 16.923076923076923, "percentage": 84.62, "elapsed_time": "1:34:29", "remaining_time": "0:17:10", "throughput": 1034.26, "total_tokens": 5863784} {"current_steps": 65125, "total_steps": 76960, "loss": 0.1515, "lr": 3.516811170018056e-06, "epoch": 16.9243762993763, "percentage": 84.62, "elapsed_time": "1:34:29", "remaining_time": "0:17:10", "throughput": 1034.27, "total_tokens": 5864232} {"current_steps": 65130, "total_steps": 76960, "loss": 0.1897, "lr": 3.5139121445297322e-06, "epoch": 16.925675675675677, "percentage": 84.63, "elapsed_time": "1:34:30", "remaining_time": "0:17:09", "throughput": 1034.28, "total_tokens": 5864744} {"current_steps": 65135, "total_steps": 76960, "loss": 0.5165, "lr": 3.5110142240914993e-06, "epoch": 16.926975051975052, "percentage": 84.63, "elapsed_time": "1:34:30", "remaining_time": "0:17:09", "throughput": 1034.28, "total_tokens": 5865160} {"current_steps": 65140, "total_steps": 76960, "loss": 0.1781, "lr": 3.5081174088523904e-06, "epoch": 16.928274428274428, "percentage": 84.64, "elapsed_time": "1:34:31", "remaining_time": "0:17:09", "throughput": 1034.28, "total_tokens": 5865624} {"current_steps": 65145, "total_steps": 76960, "loss": 0.0086, "lr": 3.5052216989613943e-06, "epoch": 16.929573804573806, "percentage": 84.65, "elapsed_time": "1:34:31", "remaining_time": "0:17:08", "throughput": 1034.28, "total_tokens": 5866024} {"current_steps": 65150, "total_steps": 76960, "loss": 0.0043, "lr": 3.502327094567448e-06, "epoch": 16.93087318087318, "percentage": 84.65, "elapsed_time": "1:34:32", "remaining_time": "0:17:08", "throughput": 1034.28, "total_tokens": 5866472} {"current_steps": 65155, "total_steps": 76960, "loss": 0.0864, "lr": 3.49943359581941e-06, "epoch": 16.932172557172557, "percentage": 84.66, "elapsed_time": "1:34:32", "remaining_time": "0:17:07", "throughput": 1034.29, "total_tokens": 5866936} {"current_steps": 65160, "total_steps": 76960, "loss": 0.0009, "lr": 3.4965412028661103e-06, "epoch": 16.933471933471935, "percentage": 84.67, "elapsed_time": "1:34:32", "remaining_time": "0:17:07", "throughput": 1034.29, "total_tokens": 5867368} {"current_steps": 65165, "total_steps": 76960, "loss": 0.0163, "lr": 3.4936499158562925e-06, "epoch": 16.93477130977131, "percentage": 84.67, "elapsed_time": "1:34:33", "remaining_time": "0:17:06", "throughput": 1034.29, "total_tokens": 5867832} {"current_steps": 65170, "total_steps": 76960, "loss": 0.1412, "lr": 3.490759734938673e-06, "epoch": 16.936070686070686, "percentage": 84.68, "elapsed_time": "1:34:33", "remaining_time": "0:17:06", "throughput": 1034.29, "total_tokens": 5868264} {"current_steps": 65175, "total_steps": 76960, "loss": 0.0067, "lr": 3.4878706602618856e-06, "epoch": 16.93737006237006, "percentage": 84.69, "elapsed_time": "1:34:34", "remaining_time": "0:17:05", "throughput": 1034.3, "total_tokens": 5868712} {"current_steps": 65180, "total_steps": 76960, "loss": 0.0073, "lr": 3.48498269197452e-06, "epoch": 16.93866943866944, "percentage": 84.69, "elapsed_time": "1:34:34", "remaining_time": "0:17:05", "throughput": 1034.3, "total_tokens": 5869160} {"current_steps": 65185, "total_steps": 76960, "loss": 0.163, "lr": 3.48209583022511e-06, "epoch": 16.939968814968815, "percentage": 84.7, "elapsed_time": "1:34:34", "remaining_time": "0:17:05", "throughput": 1034.3, "total_tokens": 5869624} {"current_steps": 65190, "total_steps": 76960, "loss": 0.0727, "lr": 3.4792100751621343e-06, "epoch": 16.94126819126819, "percentage": 84.71, "elapsed_time": "1:34:35", "remaining_time": "0:17:04", "throughput": 1034.31, "total_tokens": 5870056} {"current_steps": 65195, "total_steps": 76960, "loss": 0.2519, "lr": 3.4763254269339963e-06, "epoch": 16.94256756756757, "percentage": 84.71, "elapsed_time": "1:34:35", "remaining_time": "0:17:04", "throughput": 1034.31, "total_tokens": 5870520} {"current_steps": 65200, "total_steps": 76960, "loss": 0.6628, "lr": 3.4734418856890743e-06, "epoch": 16.943866943866944, "percentage": 84.72, "elapsed_time": "1:34:36", "remaining_time": "0:17:03", "throughput": 1034.32, "total_tokens": 5870984} {"current_steps": 65205, "total_steps": 76960, "loss": 0.1746, "lr": 3.470559451575661e-06, "epoch": 16.94516632016632, "percentage": 84.73, "elapsed_time": "1:34:36", "remaining_time": "0:17:03", "throughput": 1034.32, "total_tokens": 5871416} {"current_steps": 65210, "total_steps": 76960, "loss": 0.0071, "lr": 3.4676781247419963e-06, "epoch": 16.946465696465697, "percentage": 84.73, "elapsed_time": "1:34:37", "remaining_time": "0:17:02", "throughput": 1034.32, "total_tokens": 5871864} {"current_steps": 65215, "total_steps": 76960, "loss": 0.0069, "lr": 3.464797905336278e-06, "epoch": 16.947765072765073, "percentage": 84.74, "elapsed_time": "1:34:37", "remaining_time": "0:17:02", "throughput": 1034.32, "total_tokens": 5872312} {"current_steps": 65220, "total_steps": 76960, "loss": 0.0517, "lr": 3.461918793506638e-06, "epoch": 16.949064449064448, "percentage": 84.75, "elapsed_time": "1:34:37", "remaining_time": "0:17:02", "throughput": 1034.33, "total_tokens": 5872760} {"current_steps": 65225, "total_steps": 76960, "loss": 0.016, "lr": 3.459040789401155e-06, "epoch": 16.950363825363826, "percentage": 84.75, "elapsed_time": "1:34:38", "remaining_time": "0:17:01", "throughput": 1034.33, "total_tokens": 5873208} {"current_steps": 65230, "total_steps": 76960, "loss": 0.0007, "lr": 3.4561638931678407e-06, "epoch": 16.9516632016632, "percentage": 84.76, "elapsed_time": "1:34:38", "remaining_time": "0:17:01", "throughput": 1034.34, "total_tokens": 5873672} {"current_steps": 65235, "total_steps": 76960, "loss": 0.5887, "lr": 3.4532881049546634e-06, "epoch": 16.952962577962577, "percentage": 84.76, "elapsed_time": "1:34:39", "remaining_time": "0:17:00", "throughput": 1034.34, "total_tokens": 5874104} {"current_steps": 65240, "total_steps": 76960, "loss": 0.1313, "lr": 3.450413424909518e-06, "epoch": 16.954261954261955, "percentage": 84.77, "elapsed_time": "1:34:39", "remaining_time": "0:17:00", "throughput": 1034.34, "total_tokens": 5874568} {"current_steps": 65245, "total_steps": 76960, "loss": 0.1955, "lr": 3.4475398531802648e-06, "epoch": 16.95556133056133, "percentage": 84.78, "elapsed_time": "1:34:39", "remaining_time": "0:16:59", "throughput": 1034.35, "total_tokens": 5875016} {"current_steps": 65250, "total_steps": 76960, "loss": 0.2893, "lr": 3.4446673899146825e-06, "epoch": 16.956860706860706, "percentage": 84.78, "elapsed_time": "1:34:40", "remaining_time": "0:16:59", "throughput": 1034.35, "total_tokens": 5875496} {"current_steps": 65255, "total_steps": 76960, "loss": 0.1424, "lr": 3.4417960352605083e-06, "epoch": 16.958160083160084, "percentage": 84.79, "elapsed_time": "1:34:40", "remaining_time": "0:16:58", "throughput": 1034.35, "total_tokens": 5875912} {"current_steps": 65260, "total_steps": 76960, "loss": 0.063, "lr": 3.4389257893654186e-06, "epoch": 16.95945945945946, "percentage": 84.8, "elapsed_time": "1:34:41", "remaining_time": "0:16:58", "throughput": 1034.36, "total_tokens": 5876376} {"current_steps": 65265, "total_steps": 76960, "loss": 0.1619, "lr": 3.4360566523770426e-06, "epoch": 16.960758835758835, "percentage": 84.8, "elapsed_time": "1:34:41", "remaining_time": "0:16:58", "throughput": 1034.36, "total_tokens": 5876840} {"current_steps": 65270, "total_steps": 76960, "loss": 0.0461, "lr": 3.4331886244429345e-06, "epoch": 16.962058212058214, "percentage": 84.81, "elapsed_time": "1:34:42", "remaining_time": "0:16:57", "throughput": 1034.36, "total_tokens": 5877240} {"current_steps": 65275, "total_steps": 76960, "loss": 0.2278, "lr": 3.430321705710593e-06, "epoch": 16.96335758835759, "percentage": 84.82, "elapsed_time": "1:34:42", "remaining_time": "0:16:57", "throughput": 1034.36, "total_tokens": 5877688} {"current_steps": 65280, "total_steps": 76960, "loss": 0.1977, "lr": 3.4274558963274806e-06, "epoch": 16.964656964656964, "percentage": 84.82, "elapsed_time": "1:34:42", "remaining_time": "0:16:56", "throughput": 1034.36, "total_tokens": 5878120} {"current_steps": 65285, "total_steps": 76960, "loss": 0.393, "lr": 3.424591196440974e-06, "epoch": 16.965956340956343, "percentage": 84.83, "elapsed_time": "1:34:43", "remaining_time": "0:16:56", "throughput": 1034.37, "total_tokens": 5878600} {"current_steps": 65290, "total_steps": 76960, "loss": 0.2888, "lr": 3.421727606198416e-06, "epoch": 16.967255717255718, "percentage": 84.84, "elapsed_time": "1:34:43", "remaining_time": "0:16:55", "throughput": 1034.38, "total_tokens": 5879064} {"current_steps": 65295, "total_steps": 76960, "loss": 0.4431, "lr": 3.418865125747081e-06, "epoch": 16.968555093555093, "percentage": 84.84, "elapsed_time": "1:34:44", "remaining_time": "0:16:55", "throughput": 1034.38, "total_tokens": 5879512} {"current_steps": 65300, "total_steps": 76960, "loss": 0.0082, "lr": 3.4160037552341955e-06, "epoch": 16.96985446985447, "percentage": 84.85, "elapsed_time": "1:34:44", "remaining_time": "0:16:55", "throughput": 1034.38, "total_tokens": 5879976} {"current_steps": 65305, "total_steps": 76960, "loss": 0.2088, "lr": 3.413143494806914e-06, "epoch": 16.971153846153847, "percentage": 84.86, "elapsed_time": "1:34:44", "remaining_time": "0:16:54", "throughput": 1034.38, "total_tokens": 5880408} {"current_steps": 65310, "total_steps": 76960, "loss": 0.3515, "lr": 3.410284344612352e-06, "epoch": 16.972453222453222, "percentage": 84.86, "elapsed_time": "1:34:45", "remaining_time": "0:16:54", "throughput": 1034.39, "total_tokens": 5880856} {"current_steps": 65315, "total_steps": 76960, "loss": 0.3331, "lr": 3.4074263047975454e-06, "epoch": 16.973752598752597, "percentage": 84.87, "elapsed_time": "1:34:45", "remaining_time": "0:16:53", "throughput": 1034.4, "total_tokens": 5881336} {"current_steps": 65320, "total_steps": 76960, "loss": 0.0956, "lr": 3.404569375509492e-06, "epoch": 16.975051975051976, "percentage": 84.88, "elapsed_time": "1:34:46", "remaining_time": "0:16:53", "throughput": 1034.4, "total_tokens": 5881768} {"current_steps": 65325, "total_steps": 76960, "loss": 0.0672, "lr": 3.401713556895131e-06, "epoch": 16.97635135135135, "percentage": 84.88, "elapsed_time": "1:34:46", "remaining_time": "0:16:52", "throughput": 1034.4, "total_tokens": 5882216} {"current_steps": 65330, "total_steps": 76960, "loss": 0.0188, "lr": 3.3988588491013385e-06, "epoch": 16.977650727650726, "percentage": 84.89, "elapsed_time": "1:34:47", "remaining_time": "0:16:52", "throughput": 1034.4, "total_tokens": 5882648} {"current_steps": 65335, "total_steps": 76960, "loss": 0.0091, "lr": 3.3960052522749335e-06, "epoch": 16.978950103950105, "percentage": 84.89, "elapsed_time": "1:34:47", "remaining_time": "0:16:51", "throughput": 1034.4, "total_tokens": 5883096} {"current_steps": 65340, "total_steps": 76960, "loss": 0.1468, "lr": 3.3931527665626738e-06, "epoch": 16.98024948024948, "percentage": 84.9, "elapsed_time": "1:34:47", "remaining_time": "0:16:51", "throughput": 1034.4, "total_tokens": 5883528} {"current_steps": 65345, "total_steps": 76960, "loss": 0.0047, "lr": 3.3903013921112755e-06, "epoch": 16.981548856548855, "percentage": 84.91, "elapsed_time": "1:34:48", "remaining_time": "0:16:51", "throughput": 1034.41, "total_tokens": 5884008} {"current_steps": 65350, "total_steps": 76960, "loss": 0.108, "lr": 3.387451129067376e-06, "epoch": 16.982848232848234, "percentage": 84.91, "elapsed_time": "1:34:48", "remaining_time": "0:16:50", "throughput": 1034.42, "total_tokens": 5884488} {"current_steps": 65355, "total_steps": 76960, "loss": 0.0681, "lr": 3.3846019775775727e-06, "epoch": 16.98414760914761, "percentage": 84.92, "elapsed_time": "1:34:49", "remaining_time": "0:16:50", "throughput": 1034.42, "total_tokens": 5884936} {"current_steps": 65360, "total_steps": 76960, "loss": 0.3127, "lr": 3.381753937788401e-06, "epoch": 16.985446985446984, "percentage": 84.93, "elapsed_time": "1:34:49", "remaining_time": "0:16:49", "throughput": 1034.42, "total_tokens": 5885352} {"current_steps": 65365, "total_steps": 76960, "loss": 0.1927, "lr": 3.378907009846341e-06, "epoch": 16.986746361746363, "percentage": 84.93, "elapsed_time": "1:34:49", "remaining_time": "0:16:49", "throughput": 1034.41, "total_tokens": 5885768} {"current_steps": 65370, "total_steps": 76960, "loss": 0.0755, "lr": 3.3760611938978087e-06, "epoch": 16.988045738045738, "percentage": 84.94, "elapsed_time": "1:34:50", "remaining_time": "0:16:48", "throughput": 1034.42, "total_tokens": 5886216} {"current_steps": 65375, "total_steps": 76960, "loss": 0.2788, "lr": 3.3732164900891706e-06, "epoch": 16.989345114345113, "percentage": 84.95, "elapsed_time": "1:34:50", "remaining_time": "0:16:48", "throughput": 1034.43, "total_tokens": 5886712} {"current_steps": 65380, "total_steps": 76960, "loss": 0.2282, "lr": 3.370372898566726e-06, "epoch": 16.990644490644492, "percentage": 84.95, "elapsed_time": "1:34:51", "remaining_time": "0:16:48", "throughput": 1034.43, "total_tokens": 5887160} {"current_steps": 65385, "total_steps": 76960, "loss": 0.0867, "lr": 3.3675304194767333e-06, "epoch": 16.991943866943867, "percentage": 84.96, "elapsed_time": "1:34:51", "remaining_time": "0:16:47", "throughput": 1034.44, "total_tokens": 5887624} {"current_steps": 65390, "total_steps": 76960, "loss": 0.1309, "lr": 3.3646890529653726e-06, "epoch": 16.993243243243242, "percentage": 84.97, "elapsed_time": "1:34:52", "remaining_time": "0:16:47", "throughput": 1034.44, "total_tokens": 5888056} {"current_steps": 65395, "total_steps": 76960, "loss": 0.2752, "lr": 3.3618487991787822e-06, "epoch": 16.99454261954262, "percentage": 84.97, "elapsed_time": "1:34:52", "remaining_time": "0:16:46", "throughput": 1034.44, "total_tokens": 5888488} {"current_steps": 65400, "total_steps": 76960, "loss": 0.0545, "lr": 3.3590096582630487e-06, "epoch": 16.995841995841996, "percentage": 84.98, "elapsed_time": "1:34:52", "remaining_time": "0:16:46", "throughput": 1034.44, "total_tokens": 5888952} {"current_steps": 65405, "total_steps": 76960, "loss": 0.1622, "lr": 3.356171630364177e-06, "epoch": 16.99714137214137, "percentage": 84.99, "elapsed_time": "1:34:53", "remaining_time": "0:16:45", "throughput": 1034.44, "total_tokens": 5889368} {"current_steps": 65410, "total_steps": 76960, "loss": 0.0568, "lr": 3.3533347156281427e-06, "epoch": 16.99844074844075, "percentage": 84.99, "elapsed_time": "1:34:53", "remaining_time": "0:16:45", "throughput": 1034.45, "total_tokens": 5889832} {"current_steps": 65415, "total_steps": 76960, "loss": 0.1082, "lr": 3.350498914200839e-06, "epoch": 16.999740124740125, "percentage": 85.0, "elapsed_time": "1:34:54", "remaining_time": "0:16:44", "throughput": 1034.45, "total_tokens": 5890280} {"current_steps": 65416, "total_steps": 76960, "eval_loss": 0.6811466217041016, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "1:35:07", "remaining_time": "0:16:47", "throughput": 1032.04, "total_tokens": 5890320} {"current_steps": 65420, "total_steps": 76960, "loss": 0.0613, "lr": 3.3476642262281256e-06, "epoch": 17.0010395010395, "percentage": 85.01, "elapsed_time": "1:35:09", "remaining_time": "0:16:47", "throughput": 1031.73, "total_tokens": 5890672} {"current_steps": 65425, "total_steps": 76960, "loss": 0.1345, "lr": 3.3448306518557795e-06, "epoch": 17.00233887733888, "percentage": 85.01, "elapsed_time": "1:35:09", "remaining_time": "0:16:46", "throughput": 1031.73, "total_tokens": 5891120} {"current_steps": 65430, "total_steps": 76960, "loss": 0.1082, "lr": 3.341998191229545e-06, "epoch": 17.003638253638254, "percentage": 85.02, "elapsed_time": "1:35:10", "remaining_time": "0:16:46", "throughput": 1031.73, "total_tokens": 5891552} {"current_steps": 65435, "total_steps": 76960, "loss": 0.0773, "lr": 3.3391668444950926e-06, "epoch": 17.00493762993763, "percentage": 85.02, "elapsed_time": "1:35:10", "remaining_time": "0:16:45", "throughput": 1031.73, "total_tokens": 5892016} {"current_steps": 65440, "total_steps": 76960, "loss": 0.1759, "lr": 3.336336611798052e-06, "epoch": 17.006237006237008, "percentage": 85.03, "elapsed_time": "1:35:11", "remaining_time": "0:16:45", "throughput": 1031.73, "total_tokens": 5892448} {"current_steps": 65445, "total_steps": 76960, "loss": 0.0179, "lr": 3.333507493283969e-06, "epoch": 17.007536382536383, "percentage": 85.04, "elapsed_time": "1:35:11", "remaining_time": "0:16:44", "throughput": 1031.74, "total_tokens": 5892944} {"current_steps": 65450, "total_steps": 76960, "loss": 0.0573, "lr": 3.3306794890983623e-06, "epoch": 17.008835758835758, "percentage": 85.04, "elapsed_time": "1:35:12", "remaining_time": "0:16:44", "throughput": 1031.74, "total_tokens": 5893392} {"current_steps": 65455, "total_steps": 76960, "loss": 0.0089, "lr": 3.327852599386666e-06, "epoch": 17.010135135135137, "percentage": 85.05, "elapsed_time": "1:35:12", "remaining_time": "0:16:44", "throughput": 1031.75, "total_tokens": 5893872} {"current_steps": 65460, "total_steps": 76960, "loss": 0.0096, "lr": 3.3250268242942807e-06, "epoch": 17.011434511434512, "percentage": 85.06, "elapsed_time": "1:35:12", "remaining_time": "0:16:43", "throughput": 1031.76, "total_tokens": 5894336} {"current_steps": 65465, "total_steps": 76960, "loss": 0.0973, "lr": 3.3222021639665286e-06, "epoch": 17.012733887733887, "percentage": 85.06, "elapsed_time": "1:35:13", "remaining_time": "0:16:43", "throughput": 1031.76, "total_tokens": 5894768} {"current_steps": 65470, "total_steps": 76960, "loss": 0.0831, "lr": 3.3193786185486907e-06, "epoch": 17.014033264033262, "percentage": 85.07, "elapsed_time": "1:35:13", "remaining_time": "0:16:42", "throughput": 1031.76, "total_tokens": 5895232} {"current_steps": 65475, "total_steps": 76960, "loss": 0.0207, "lr": 3.3165561881859873e-06, "epoch": 17.01533264033264, "percentage": 85.08, "elapsed_time": "1:35:14", "remaining_time": "0:16:42", "throughput": 1031.76, "total_tokens": 5895664} {"current_steps": 65480, "total_steps": 76960, "loss": 0.2054, "lr": 3.313734873023572e-06, "epoch": 17.016632016632016, "percentage": 85.08, "elapsed_time": "1:35:14", "remaining_time": "0:16:41", "throughput": 1031.77, "total_tokens": 5896128} {"current_steps": 65485, "total_steps": 76960, "loss": 0.2095, "lr": 3.3109146732065554e-06, "epoch": 17.01793139293139, "percentage": 85.09, "elapsed_time": "1:35:15", "remaining_time": "0:16:41", "throughput": 1031.77, "total_tokens": 5896576} {"current_steps": 65490, "total_steps": 76960, "loss": 0.0786, "lr": 3.3080955888799726e-06, "epoch": 17.01923076923077, "percentage": 85.1, "elapsed_time": "1:35:15", "remaining_time": "0:16:41", "throughput": 1031.76, "total_tokens": 5896976} {"current_steps": 65495, "total_steps": 76960, "loss": 0.0015, "lr": 3.305277620188826e-06, "epoch": 17.020530145530145, "percentage": 85.1, "elapsed_time": "1:35:15", "remaining_time": "0:16:40", "throughput": 1031.77, "total_tokens": 5897456} {"current_steps": 65500, "total_steps": 76960, "loss": 0.129, "lr": 3.302460767278029e-06, "epoch": 17.02182952182952, "percentage": 85.11, "elapsed_time": "1:35:16", "remaining_time": "0:16:40", "throughput": 1031.78, "total_tokens": 5897936} {"current_steps": 65505, "total_steps": 76960, "loss": 0.3044, "lr": 3.299645030292467e-06, "epoch": 17.0231288981289, "percentage": 85.12, "elapsed_time": "1:35:16", "remaining_time": "0:16:39", "throughput": 1031.78, "total_tokens": 5898368} {"current_steps": 65510, "total_steps": 76960, "loss": 0.3475, "lr": 3.2968304093769525e-06, "epoch": 17.024428274428274, "percentage": 85.12, "elapsed_time": "1:35:17", "remaining_time": "0:16:39", "throughput": 1031.78, "total_tokens": 5898800} {"current_steps": 65515, "total_steps": 76960, "loss": 0.0234, "lr": 3.2940169046762504e-06, "epoch": 17.02572765072765, "percentage": 85.13, "elapsed_time": "1:35:17", "remaining_time": "0:16:38", "throughput": 1031.77, "total_tokens": 5899232} {"current_steps": 65520, "total_steps": 76960, "loss": 0.0699, "lr": 3.29120451633505e-06, "epoch": 17.027027027027028, "percentage": 85.14, "elapsed_time": "1:35:17", "remaining_time": "0:16:38", "throughput": 1031.78, "total_tokens": 5899680} {"current_steps": 65525, "total_steps": 76960, "loss": 0.1678, "lr": 3.2883932444980086e-06, "epoch": 17.028326403326403, "percentage": 85.14, "elapsed_time": "1:35:18", "remaining_time": "0:16:37", "throughput": 1031.77, "total_tokens": 5900112} {"current_steps": 65530, "total_steps": 76960, "loss": 0.0308, "lr": 3.285583089309702e-06, "epoch": 17.02962577962578, "percentage": 85.15, "elapsed_time": "1:35:18", "remaining_time": "0:16:37", "throughput": 1031.79, "total_tokens": 5900608} {"current_steps": 65535, "total_steps": 76960, "loss": 0.0356, "lr": 3.2827740509146667e-06, "epoch": 17.030925155925157, "percentage": 85.15, "elapsed_time": "1:35:19", "remaining_time": "0:16:37", "throughput": 1031.79, "total_tokens": 5901040} {"current_steps": 65540, "total_steps": 76960, "loss": 0.0074, "lr": 3.2799661294573624e-06, "epoch": 17.032224532224532, "percentage": 85.16, "elapsed_time": "1:35:19", "remaining_time": "0:16:36", "throughput": 1031.79, "total_tokens": 5901504} {"current_steps": 65545, "total_steps": 76960, "loss": 0.0253, "lr": 3.277159325082213e-06, "epoch": 17.033523908523907, "percentage": 85.17, "elapsed_time": "1:35:20", "remaining_time": "0:16:36", "throughput": 1031.79, "total_tokens": 5901920} {"current_steps": 65550, "total_steps": 76960, "loss": 0.3545, "lr": 3.2743536379335804e-06, "epoch": 17.034823284823286, "percentage": 85.17, "elapsed_time": "1:35:20", "remaining_time": "0:16:35", "throughput": 1031.8, "total_tokens": 5902400} {"current_steps": 65555, "total_steps": 76960, "loss": 0.0005, "lr": 3.271549068155749e-06, "epoch": 17.03612266112266, "percentage": 85.18, "elapsed_time": "1:35:20", "remaining_time": "0:16:35", "throughput": 1031.8, "total_tokens": 5902864} {"current_steps": 65560, "total_steps": 76960, "loss": 0.0016, "lr": 3.268745615892976e-06, "epoch": 17.037422037422036, "percentage": 85.19, "elapsed_time": "1:35:21", "remaining_time": "0:16:34", "throughput": 1031.8, "total_tokens": 5903296} {"current_steps": 65565, "total_steps": 76960, "loss": 0.0378, "lr": 3.2659432812894296e-06, "epoch": 17.038721413721415, "percentage": 85.19, "elapsed_time": "1:35:21", "remaining_time": "0:16:34", "throughput": 1031.8, "total_tokens": 5903728} {"current_steps": 65570, "total_steps": 76960, "loss": 0.0614, "lr": 3.263142064489247e-06, "epoch": 17.04002079002079, "percentage": 85.2, "elapsed_time": "1:35:22", "remaining_time": "0:16:33", "throughput": 1031.8, "total_tokens": 5904176} {"current_steps": 65575, "total_steps": 76960, "loss": 0.0012, "lr": 3.2603419656364957e-06, "epoch": 17.041320166320165, "percentage": 85.21, "elapsed_time": "1:35:22", "remaining_time": "0:16:33", "throughput": 1031.81, "total_tokens": 5904640} {"current_steps": 65580, "total_steps": 76960, "loss": 0.0304, "lr": 3.257542984875192e-06, "epoch": 17.042619542619544, "percentage": 85.21, "elapsed_time": "1:35:23", "remaining_time": "0:16:33", "throughput": 1031.81, "total_tokens": 5905072} {"current_steps": 65585, "total_steps": 76960, "loss": 0.1141, "lr": 3.2547451223492786e-06, "epoch": 17.04391891891892, "percentage": 85.22, "elapsed_time": "1:35:23", "remaining_time": "0:16:32", "throughput": 1031.81, "total_tokens": 5905504} {"current_steps": 65590, "total_steps": 76960, "loss": 0.3225, "lr": 3.2519483782026654e-06, "epoch": 17.045218295218294, "percentage": 85.23, "elapsed_time": "1:35:23", "remaining_time": "0:16:32", "throughput": 1031.8, "total_tokens": 5905920} {"current_steps": 65595, "total_steps": 76960, "loss": 0.6291, "lr": 3.2491527525791794e-06, "epoch": 17.046517671517673, "percentage": 85.23, "elapsed_time": "1:35:24", "remaining_time": "0:16:31", "throughput": 1031.81, "total_tokens": 5906384} {"current_steps": 65600, "total_steps": 76960, "loss": 0.0037, "lr": 3.2463582456226103e-06, "epoch": 17.04781704781705, "percentage": 85.24, "elapsed_time": "1:35:24", "remaining_time": "0:16:31", "throughput": 1031.81, "total_tokens": 5906832} {"current_steps": 65605, "total_steps": 76960, "loss": 0.0009, "lr": 3.2435648574766776e-06, "epoch": 17.049116424116423, "percentage": 85.25, "elapsed_time": "1:35:25", "remaining_time": "0:16:30", "throughput": 1031.82, "total_tokens": 5907312} {"current_steps": 65610, "total_steps": 76960, "loss": 0.2057, "lr": 3.2407725882850516e-06, "epoch": 17.050415800415802, "percentage": 85.25, "elapsed_time": "1:35:25", "remaining_time": "0:16:30", "throughput": 1031.82, "total_tokens": 5907776} {"current_steps": 65615, "total_steps": 76960, "loss": 0.4297, "lr": 3.2379814381913426e-06, "epoch": 17.051715176715177, "percentage": 85.26, "elapsed_time": "1:35:25", "remaining_time": "0:16:30", "throughput": 1031.83, "total_tokens": 5908272} {"current_steps": 65620, "total_steps": 76960, "loss": 0.0081, "lr": 3.235191407339097e-06, "epoch": 17.053014553014552, "percentage": 85.27, "elapsed_time": "1:35:26", "remaining_time": "0:16:29", "throughput": 1031.83, "total_tokens": 5908704} {"current_steps": 65625, "total_steps": 76960, "loss": 0.0015, "lr": 3.232402495871814e-06, "epoch": 17.054313929313928, "percentage": 85.27, "elapsed_time": "1:35:26", "remaining_time": "0:16:29", "throughput": 1031.83, "total_tokens": 5909120} {"current_steps": 65630, "total_steps": 76960, "loss": 0.2552, "lr": 3.2296147039329234e-06, "epoch": 17.055613305613306, "percentage": 85.28, "elapsed_time": "1:35:27", "remaining_time": "0:16:28", "throughput": 1031.83, "total_tokens": 5909568} {"current_steps": 65635, "total_steps": 76960, "loss": 0.0014, "lr": 3.2268280316658127e-06, "epoch": 17.05691268191268, "percentage": 85.28, "elapsed_time": "1:35:27", "remaining_time": "0:16:28", "throughput": 1031.84, "total_tokens": 5910016} {"current_steps": 65640, "total_steps": 76960, "loss": 0.4583, "lr": 3.224042479213793e-06, "epoch": 17.058212058212057, "percentage": 85.29, "elapsed_time": "1:35:28", "remaining_time": "0:16:27", "throughput": 1031.84, "total_tokens": 5910464} {"current_steps": 65645, "total_steps": 76960, "loss": 0.014, "lr": 3.221258046720135e-06, "epoch": 17.059511434511435, "percentage": 85.3, "elapsed_time": "1:35:28", "remaining_time": "0:16:27", "throughput": 1031.84, "total_tokens": 5910912} {"current_steps": 65650, "total_steps": 76960, "loss": 0.143, "lr": 3.218474734328042e-06, "epoch": 17.06081081081081, "percentage": 85.3, "elapsed_time": "1:35:28", "remaining_time": "0:16:26", "throughput": 1031.85, "total_tokens": 5911392} {"current_steps": 65655, "total_steps": 76960, "loss": 0.0023, "lr": 3.2156925421806677e-06, "epoch": 17.062110187110186, "percentage": 85.31, "elapsed_time": "1:35:29", "remaining_time": "0:16:26", "throughput": 1031.85, "total_tokens": 5911840} {"current_steps": 65660, "total_steps": 76960, "loss": 0.0013, "lr": 3.2129114704210957e-06, "epoch": 17.063409563409564, "percentage": 85.32, "elapsed_time": "1:35:29", "remaining_time": "0:16:26", "throughput": 1031.85, "total_tokens": 5912288} {"current_steps": 65665, "total_steps": 76960, "loss": 0.0948, "lr": 3.2101315191923663e-06, "epoch": 17.06470893970894, "percentage": 85.32, "elapsed_time": "1:35:30", "remaining_time": "0:16:25", "throughput": 1031.86, "total_tokens": 5912752} {"current_steps": 65670, "total_steps": 76960, "loss": 0.241, "lr": 3.2073526886374494e-06, "epoch": 17.066008316008315, "percentage": 85.33, "elapsed_time": "1:35:30", "remaining_time": "0:16:25", "throughput": 1031.86, "total_tokens": 5913168} {"current_steps": 65675, "total_steps": 76960, "loss": 0.0958, "lr": 3.204574978899261e-06, "epoch": 17.067307692307693, "percentage": 85.34, "elapsed_time": "1:35:31", "remaining_time": "0:16:24", "throughput": 1031.87, "total_tokens": 5913648} {"current_steps": 65680, "total_steps": 76960, "loss": 0.0012, "lr": 3.201798390120664e-06, "epoch": 17.06860706860707, "percentage": 85.34, "elapsed_time": "1:35:31", "remaining_time": "0:16:24", "throughput": 1031.86, "total_tokens": 5914064} {"current_steps": 65685, "total_steps": 76960, "loss": 0.2371, "lr": 3.199022922444461e-06, "epoch": 17.069906444906444, "percentage": 85.35, "elapsed_time": "1:35:31", "remaining_time": "0:16:23", "throughput": 1031.86, "total_tokens": 5914496} {"current_steps": 65690, "total_steps": 76960, "loss": 0.3886, "lr": 3.196248576013405e-06, "epoch": 17.071205821205822, "percentage": 85.36, "elapsed_time": "1:35:32", "remaining_time": "0:16:23", "throughput": 1031.86, "total_tokens": 5914960} {"current_steps": 65695, "total_steps": 76960, "loss": 0.0151, "lr": 3.193475350970171e-06, "epoch": 17.072505197505198, "percentage": 85.36, "elapsed_time": "1:35:32", "remaining_time": "0:16:23", "throughput": 1031.86, "total_tokens": 5915392} {"current_steps": 65700, "total_steps": 76960, "loss": 0.2606, "lr": 3.1907032474573968e-06, "epoch": 17.073804573804573, "percentage": 85.37, "elapsed_time": "1:35:33", "remaining_time": "0:16:22", "throughput": 1031.86, "total_tokens": 5915840} {"current_steps": 65705, "total_steps": 76960, "loss": 0.0078, "lr": 3.1879322656176463e-06, "epoch": 17.07510395010395, "percentage": 85.38, "elapsed_time": "1:35:33", "remaining_time": "0:16:22", "throughput": 1031.87, "total_tokens": 5916336} {"current_steps": 65710, "total_steps": 76960, "loss": 0.0102, "lr": 3.1851624055934447e-06, "epoch": 17.076403326403327, "percentage": 85.38, "elapsed_time": "1:35:34", "remaining_time": "0:16:21", "throughput": 1031.88, "total_tokens": 5916800} {"current_steps": 65715, "total_steps": 76960, "loss": 0.0278, "lr": 3.1823936675272393e-06, "epoch": 17.0777027027027, "percentage": 85.39, "elapsed_time": "1:35:34", "remaining_time": "0:16:21", "throughput": 1031.89, "total_tokens": 5917280} {"current_steps": 65720, "total_steps": 76960, "loss": 0.1659, "lr": 3.1796260515614297e-06, "epoch": 17.07900207900208, "percentage": 85.4, "elapsed_time": "1:35:34", "remaining_time": "0:16:20", "throughput": 1031.89, "total_tokens": 5917712} {"current_steps": 65725, "total_steps": 76960, "loss": 0.1277, "lr": 3.1768595578383604e-06, "epoch": 17.080301455301456, "percentage": 85.4, "elapsed_time": "1:35:35", "remaining_time": "0:16:20", "throughput": 1031.89, "total_tokens": 5918176} {"current_steps": 65730, "total_steps": 76960, "loss": 0.003, "lr": 3.1740941865003175e-06, "epoch": 17.08160083160083, "percentage": 85.41, "elapsed_time": "1:35:35", "remaining_time": "0:16:19", "throughput": 1031.89, "total_tokens": 5918592} {"current_steps": 65735, "total_steps": 76960, "loss": 0.0568, "lr": 3.171329937689524e-06, "epoch": 17.08290020790021, "percentage": 85.41, "elapsed_time": "1:35:36", "remaining_time": "0:16:19", "throughput": 1031.9, "total_tokens": 5919072} {"current_steps": 65740, "total_steps": 76960, "loss": 0.0107, "lr": 3.168566811548143e-06, "epoch": 17.084199584199585, "percentage": 85.42, "elapsed_time": "1:35:36", "remaining_time": "0:16:19", "throughput": 1031.9, "total_tokens": 5919520} {"current_steps": 65745, "total_steps": 76960, "loss": 0.0908, "lr": 3.165804808218292e-06, "epoch": 17.08549896049896, "percentage": 85.43, "elapsed_time": "1:35:36", "remaining_time": "0:16:18", "throughput": 1031.9, "total_tokens": 5919968} {"current_steps": 65750, "total_steps": 76960, "loss": 0.3735, "lr": 3.1630439278420188e-06, "epoch": 17.08679833679834, "percentage": 85.43, "elapsed_time": "1:35:37", "remaining_time": "0:16:18", "throughput": 1031.9, "total_tokens": 5920416} {"current_steps": 65755, "total_steps": 76960, "loss": 0.0055, "lr": 3.1602841705613143e-06, "epoch": 17.088097713097714, "percentage": 85.44, "elapsed_time": "1:35:37", "remaining_time": "0:16:17", "throughput": 1031.91, "total_tokens": 5920912} {"current_steps": 65760, "total_steps": 76960, "loss": 0.0286, "lr": 3.1575255365181243e-06, "epoch": 17.08939708939709, "percentage": 85.45, "elapsed_time": "1:35:38", "remaining_time": "0:16:17", "throughput": 1031.92, "total_tokens": 5921376} {"current_steps": 65765, "total_steps": 76960, "loss": 0.2513, "lr": 3.1547680258543295e-06, "epoch": 17.090696465696464, "percentage": 85.45, "elapsed_time": "1:35:38", "remaining_time": "0:16:16", "throughput": 1031.91, "total_tokens": 5921792} {"current_steps": 65770, "total_steps": 76960, "loss": 0.0171, "lr": 3.152011638711741e-06, "epoch": 17.091995841995843, "percentage": 85.46, "elapsed_time": "1:35:39", "remaining_time": "0:16:16", "throughput": 1031.91, "total_tokens": 5922224} {"current_steps": 65775, "total_steps": 76960, "loss": 0.2423, "lr": 3.149256375232132e-06, "epoch": 17.093295218295218, "percentage": 85.47, "elapsed_time": "1:35:39", "remaining_time": "0:16:16", "throughput": 1031.92, "total_tokens": 5922704} {"current_steps": 65780, "total_steps": 76960, "loss": 0.0002, "lr": 3.146502235557197e-06, "epoch": 17.094594594594593, "percentage": 85.47, "elapsed_time": "1:35:39", "remaining_time": "0:16:15", "throughput": 1031.92, "total_tokens": 5923168} {"current_steps": 65785, "total_steps": 76960, "loss": 0.0198, "lr": 3.1437492198285985e-06, "epoch": 17.09589397089397, "percentage": 85.48, "elapsed_time": "1:35:40", "remaining_time": "0:16:15", "throughput": 1031.92, "total_tokens": 5923616} {"current_steps": 65790, "total_steps": 76960, "loss": 0.0018, "lr": 3.1409973281879085e-06, "epoch": 17.097193347193347, "percentage": 85.49, "elapsed_time": "1:35:40", "remaining_time": "0:16:14", "throughput": 1031.93, "total_tokens": 5924064} {"current_steps": 65795, "total_steps": 76960, "loss": 0.6162, "lr": 3.1382465607766807e-06, "epoch": 17.098492723492722, "percentage": 85.49, "elapsed_time": "1:35:41", "remaining_time": "0:16:14", "throughput": 1031.93, "total_tokens": 5924512} {"current_steps": 65800, "total_steps": 76960, "loss": 0.0072, "lr": 3.1354969177363804e-06, "epoch": 17.0997920997921, "percentage": 85.5, "elapsed_time": "1:35:41", "remaining_time": "0:16:13", "throughput": 1031.93, "total_tokens": 5924960} {"current_steps": 65805, "total_steps": 76960, "loss": 0.0812, "lr": 3.1327483992084154e-06, "epoch": 17.101091476091476, "percentage": 85.51, "elapsed_time": "1:35:42", "remaining_time": "0:16:13", "throughput": 1031.94, "total_tokens": 5925424} {"current_steps": 65810, "total_steps": 76960, "loss": 0.3617, "lr": 3.13000100533416e-06, "epoch": 17.10239085239085, "percentage": 85.51, "elapsed_time": "1:35:42", "remaining_time": "0:16:12", "throughput": 1031.94, "total_tokens": 5925872} {"current_steps": 65815, "total_steps": 76960, "loss": 0.006, "lr": 3.1272547362549004e-06, "epoch": 17.10369022869023, "percentage": 85.52, "elapsed_time": "1:35:42", "remaining_time": "0:16:12", "throughput": 1031.94, "total_tokens": 5926304} {"current_steps": 65820, "total_steps": 76960, "loss": 0.0763, "lr": 3.124509592111888e-06, "epoch": 17.104989604989605, "percentage": 85.52, "elapsed_time": "1:35:43", "remaining_time": "0:16:12", "throughput": 1031.95, "total_tokens": 5926768} {"current_steps": 65825, "total_steps": 76960, "loss": 0.0507, "lr": 3.1217655730463093e-06, "epoch": 17.10628898128898, "percentage": 85.53, "elapsed_time": "1:35:43", "remaining_time": "0:16:11", "throughput": 1031.95, "total_tokens": 5927216} {"current_steps": 65830, "total_steps": 76960, "loss": 0.0891, "lr": 3.119022679199293e-06, "epoch": 17.10758835758836, "percentage": 85.54, "elapsed_time": "1:35:44", "remaining_time": "0:16:11", "throughput": 1031.96, "total_tokens": 5927680} {"current_steps": 65835, "total_steps": 76960, "loss": 0.2301, "lr": 3.1162809107118996e-06, "epoch": 17.108887733887734, "percentage": 85.54, "elapsed_time": "1:35:44", "remaining_time": "0:16:10", "throughput": 1031.96, "total_tokens": 5928128} {"current_steps": 65840, "total_steps": 76960, "loss": 0.0668, "lr": 3.113540267725154e-06, "epoch": 17.11018711018711, "percentage": 85.55, "elapsed_time": "1:35:44", "remaining_time": "0:16:10", "throughput": 1031.96, "total_tokens": 5928576} {"current_steps": 65845, "total_steps": 76960, "loss": 0.081, "lr": 3.1108007503799967e-06, "epoch": 17.111486486486488, "percentage": 85.56, "elapsed_time": "1:35:45", "remaining_time": "0:16:09", "throughput": 1031.97, "total_tokens": 5929040} {"current_steps": 65850, "total_steps": 76960, "loss": 0.053, "lr": 3.1080623588173372e-06, "epoch": 17.112785862785863, "percentage": 85.56, "elapsed_time": "1:35:45", "remaining_time": "0:16:09", "throughput": 1031.97, "total_tokens": 5929472} {"current_steps": 65855, "total_steps": 76960, "loss": 0.002, "lr": 3.1053250931779993e-06, "epoch": 17.114085239085238, "percentage": 85.57, "elapsed_time": "1:35:46", "remaining_time": "0:16:08", "throughput": 1031.98, "total_tokens": 5929968} {"current_steps": 65860, "total_steps": 76960, "loss": 0.1432, "lr": 3.1025889536027696e-06, "epoch": 17.115384615384617, "percentage": 85.58, "elapsed_time": "1:35:46", "remaining_time": "0:16:08", "throughput": 1031.99, "total_tokens": 5930416} {"current_steps": 65865, "total_steps": 76960, "loss": 0.1945, "lr": 3.099853940232378e-06, "epoch": 17.116683991683992, "percentage": 85.58, "elapsed_time": "1:35:47", "remaining_time": "0:16:08", "throughput": 1032.0, "total_tokens": 5930912} {"current_steps": 65870, "total_steps": 76960, "loss": 0.0033, "lr": 3.097120053207475e-06, "epoch": 17.117983367983367, "percentage": 85.59, "elapsed_time": "1:35:47", "remaining_time": "0:16:07", "throughput": 1032.01, "total_tokens": 5931392} {"current_steps": 65875, "total_steps": 76960, "loss": 0.2383, "lr": 3.094387292668682e-06, "epoch": 17.119282744282746, "percentage": 85.6, "elapsed_time": "1:35:47", "remaining_time": "0:16:07", "throughput": 1032.01, "total_tokens": 5931872} {"current_steps": 65880, "total_steps": 76960, "loss": 0.1565, "lr": 3.0916556587565316e-06, "epoch": 17.12058212058212, "percentage": 85.6, "elapsed_time": "1:35:48", "remaining_time": "0:16:06", "throughput": 1032.02, "total_tokens": 5932336} {"current_steps": 65885, "total_steps": 76960, "loss": 0.0727, "lr": 3.08892515161153e-06, "epoch": 17.121881496881496, "percentage": 85.61, "elapsed_time": "1:35:48", "remaining_time": "0:16:06", "throughput": 1032.02, "total_tokens": 5932752} {"current_steps": 65890, "total_steps": 76960, "loss": 0.0006, "lr": 3.0861957713740953e-06, "epoch": 17.123180873180875, "percentage": 85.62, "elapsed_time": "1:35:49", "remaining_time": "0:16:05", "throughput": 1032.02, "total_tokens": 5933216} {"current_steps": 65895, "total_steps": 76960, "loss": 0.0066, "lr": 3.0834675181846073e-06, "epoch": 17.12448024948025, "percentage": 85.62, "elapsed_time": "1:35:49", "remaining_time": "0:16:05", "throughput": 1032.03, "total_tokens": 5933664} {"current_steps": 65900, "total_steps": 76960, "loss": 0.0089, "lr": 3.0807403921833873e-06, "epoch": 17.125779625779625, "percentage": 85.63, "elapsed_time": "1:35:49", "remaining_time": "0:16:05", "throughput": 1032.04, "total_tokens": 5934160} {"current_steps": 65905, "total_steps": 76960, "loss": 0.0061, "lr": 3.078014393510695e-06, "epoch": 17.127079002079004, "percentage": 85.64, "elapsed_time": "1:35:50", "remaining_time": "0:16:04", "throughput": 1032.05, "total_tokens": 5934624} {"current_steps": 65910, "total_steps": 76960, "loss": 0.0008, "lr": 3.0752895223067207e-06, "epoch": 17.12837837837838, "percentage": 85.64, "elapsed_time": "1:35:50", "remaining_time": "0:16:04", "throughput": 1032.05, "total_tokens": 5935088} {"current_steps": 65915, "total_steps": 76960, "loss": 0.4002, "lr": 3.0725657787116197e-06, "epoch": 17.129677754677754, "percentage": 85.65, "elapsed_time": "1:35:51", "remaining_time": "0:16:03", "throughput": 1032.06, "total_tokens": 5935552} {"current_steps": 65920, "total_steps": 76960, "loss": 0.255, "lr": 3.0698431628654655e-06, "epoch": 17.13097713097713, "percentage": 85.65, "elapsed_time": "1:35:51", "remaining_time": "0:16:03", "throughput": 1032.06, "total_tokens": 5936000} {"current_steps": 65925, "total_steps": 76960, "loss": 0.3485, "lr": 3.0671216749082936e-06, "epoch": 17.132276507276508, "percentage": 85.66, "elapsed_time": "1:35:52", "remaining_time": "0:16:02", "throughput": 1032.06, "total_tokens": 5936432} {"current_steps": 65930, "total_steps": 76960, "loss": 0.017, "lr": 3.0644013149800672e-06, "epoch": 17.133575883575883, "percentage": 85.67, "elapsed_time": "1:35:52", "remaining_time": "0:16:02", "throughput": 1032.06, "total_tokens": 5936864} {"current_steps": 65935, "total_steps": 76960, "loss": 0.1453, "lr": 3.061682083220696e-06, "epoch": 17.13487525987526, "percentage": 85.67, "elapsed_time": "1:35:52", "remaining_time": "0:16:01", "throughput": 1032.06, "total_tokens": 5937312} {"current_steps": 65940, "total_steps": 76960, "loss": 0.0049, "lr": 3.0589639797700408e-06, "epoch": 17.136174636174637, "percentage": 85.68, "elapsed_time": "1:35:53", "remaining_time": "0:16:01", "throughput": 1032.07, "total_tokens": 5937760} {"current_steps": 65945, "total_steps": 76960, "loss": 0.018, "lr": 3.056247004767887e-06, "epoch": 17.137474012474012, "percentage": 85.69, "elapsed_time": "1:35:53", "remaining_time": "0:16:01", "throughput": 1032.08, "total_tokens": 5938256} {"current_steps": 65950, "total_steps": 76960, "loss": 0.1276, "lr": 3.0535311583539812e-06, "epoch": 17.138773388773387, "percentage": 85.69, "elapsed_time": "1:35:54", "remaining_time": "0:16:00", "throughput": 1032.09, "total_tokens": 5938720} {"current_steps": 65955, "total_steps": 76960, "loss": 0.0614, "lr": 3.050816440667989e-06, "epoch": 17.140072765072766, "percentage": 85.7, "elapsed_time": "1:35:54", "remaining_time": "0:16:00", "throughput": 1032.09, "total_tokens": 5939168} {"current_steps": 65960, "total_steps": 76960, "loss": 0.1729, "lr": 3.0481028518495435e-06, "epoch": 17.14137214137214, "percentage": 85.71, "elapsed_time": "1:35:54", "remaining_time": "0:15:59", "throughput": 1032.09, "total_tokens": 5939632} {"current_steps": 65965, "total_steps": 76960, "loss": 0.0348, "lr": 3.045390392038197e-06, "epoch": 17.142671517671516, "percentage": 85.71, "elapsed_time": "1:35:55", "remaining_time": "0:15:59", "throughput": 1032.1, "total_tokens": 5940064} {"current_steps": 65970, "total_steps": 76960, "loss": 0.1493, "lr": 3.0426790613734575e-06, "epoch": 17.143970893970895, "percentage": 85.72, "elapsed_time": "1:35:55", "remaining_time": "0:15:58", "throughput": 1032.1, "total_tokens": 5940512} {"current_steps": 65975, "total_steps": 76960, "loss": 0.012, "lr": 3.039968859994774e-06, "epoch": 17.14527027027027, "percentage": 85.73, "elapsed_time": "1:35:56", "remaining_time": "0:15:58", "throughput": 1032.1, "total_tokens": 5940944} {"current_steps": 65980, "total_steps": 76960, "loss": 0.0351, "lr": 3.0372597880415355e-06, "epoch": 17.146569646569645, "percentage": 85.73, "elapsed_time": "1:35:56", "remaining_time": "0:15:57", "throughput": 1032.1, "total_tokens": 5941376} {"current_steps": 65985, "total_steps": 76960, "loss": 0.1231, "lr": 3.0345518456530665e-06, "epoch": 17.147869022869024, "percentage": 85.74, "elapsed_time": "1:35:57", "remaining_time": "0:15:57", "throughput": 1032.11, "total_tokens": 5941856} {"current_steps": 65990, "total_steps": 76960, "loss": 0.0143, "lr": 3.031845032968647e-06, "epoch": 17.1491683991684, "percentage": 85.75, "elapsed_time": "1:35:57", "remaining_time": "0:15:57", "throughput": 1032.12, "total_tokens": 5942352} {"current_steps": 65995, "total_steps": 76960, "loss": 0.1973, "lr": 3.0291393501274884e-06, "epoch": 17.150467775467774, "percentage": 85.75, "elapsed_time": "1:35:57", "remaining_time": "0:15:56", "throughput": 1032.13, "total_tokens": 5942816} {"current_steps": 66000, "total_steps": 76960, "loss": 0.0011, "lr": 3.026434797268737e-06, "epoch": 17.151767151767153, "percentage": 85.76, "elapsed_time": "1:35:58", "remaining_time": "0:15:56", "throughput": 1032.13, "total_tokens": 5943264} {"current_steps": 66005, "total_steps": 76960, "loss": 0.3401, "lr": 3.0237313745314992e-06, "epoch": 17.153066528066528, "percentage": 85.77, "elapsed_time": "1:35:58", "remaining_time": "0:15:55", "throughput": 1032.13, "total_tokens": 5943728} {"current_steps": 66010, "total_steps": 76960, "loss": 0.6025, "lr": 3.021029082054813e-06, "epoch": 17.154365904365903, "percentage": 85.77, "elapsed_time": "1:35:59", "remaining_time": "0:15:55", "throughput": 1032.13, "total_tokens": 5944160} {"current_steps": 66015, "total_steps": 76960, "loss": 0.3436, "lr": 3.018327919977665e-06, "epoch": 17.155665280665282, "percentage": 85.78, "elapsed_time": "1:35:59", "remaining_time": "0:15:54", "throughput": 1032.14, "total_tokens": 5944608} {"current_steps": 66020, "total_steps": 76960, "loss": 0.0003, "lr": 3.015627888438971e-06, "epoch": 17.156964656964657, "percentage": 85.78, "elapsed_time": "1:35:59", "remaining_time": "0:15:54", "throughput": 1032.14, "total_tokens": 5945040} {"current_steps": 66025, "total_steps": 76960, "loss": 0.0117, "lr": 3.0129289875776013e-06, "epoch": 17.158264033264032, "percentage": 85.79, "elapsed_time": "1:36:00", "remaining_time": "0:15:54", "throughput": 1032.14, "total_tokens": 5945504} {"current_steps": 66030, "total_steps": 76960, "loss": 0.0354, "lr": 3.0102312175323556e-06, "epoch": 17.15956340956341, "percentage": 85.8, "elapsed_time": "1:36:00", "remaining_time": "0:15:53", "throughput": 1032.15, "total_tokens": 5945984} {"current_steps": 66035, "total_steps": 76960, "loss": 0.0003, "lr": 3.007534578441995e-06, "epoch": 17.160862785862786, "percentage": 85.8, "elapsed_time": "1:36:01", "remaining_time": "0:15:53", "throughput": 1032.15, "total_tokens": 5946416} {"current_steps": 66040, "total_steps": 76960, "loss": 0.1829, "lr": 3.004839070445192e-06, "epoch": 17.16216216216216, "percentage": 85.81, "elapsed_time": "1:36:01", "remaining_time": "0:15:52", "throughput": 1032.15, "total_tokens": 5946816} {"current_steps": 66045, "total_steps": 76960, "loss": 0.0535, "lr": 3.0021446936806e-06, "epoch": 17.16346153846154, "percentage": 85.82, "elapsed_time": "1:36:02", "remaining_time": "0:15:52", "throughput": 1032.15, "total_tokens": 5947280} {"current_steps": 66050, "total_steps": 76960, "loss": 0.0023, "lr": 2.9994514482867803e-06, "epoch": 17.164760914760915, "percentage": 85.82, "elapsed_time": "1:36:02", "remaining_time": "0:15:51", "throughput": 1032.16, "total_tokens": 5947744} {"current_steps": 66055, "total_steps": 76960, "loss": 0.0161, "lr": 2.9967593344022576e-06, "epoch": 17.16606029106029, "percentage": 85.83, "elapsed_time": "1:36:02", "remaining_time": "0:15:51", "throughput": 1032.17, "total_tokens": 5948224} {"current_steps": 66060, "total_steps": 76960, "loss": 0.0754, "lr": 2.994068352165483e-06, "epoch": 17.16735966735967, "percentage": 85.84, "elapsed_time": "1:36:03", "remaining_time": "0:15:50", "throughput": 1032.17, "total_tokens": 5948656} {"current_steps": 66065, "total_steps": 76960, "loss": 0.3355, "lr": 2.991378501714856e-06, "epoch": 17.168659043659044, "percentage": 85.84, "elapsed_time": "1:36:03", "remaining_time": "0:15:50", "throughput": 1032.17, "total_tokens": 5949088} {"current_steps": 66070, "total_steps": 76960, "loss": 0.2814, "lr": 2.9886897831887166e-06, "epoch": 17.16995841995842, "percentage": 85.85, "elapsed_time": "1:36:04", "remaining_time": "0:15:50", "throughput": 1032.17, "total_tokens": 5949536} {"current_steps": 66075, "total_steps": 76960, "loss": 0.0244, "lr": 2.9860021967253543e-06, "epoch": 17.171257796257795, "percentage": 85.86, "elapsed_time": "1:36:04", "remaining_time": "0:15:49", "throughput": 1032.18, "total_tokens": 5949984} {"current_steps": 66080, "total_steps": 76960, "loss": 0.161, "lr": 2.983315742462997e-06, "epoch": 17.172557172557173, "percentage": 85.86, "elapsed_time": "1:36:04", "remaining_time": "0:15:49", "throughput": 1032.19, "total_tokens": 5950464} {"current_steps": 66085, "total_steps": 76960, "loss": 0.1979, "lr": 2.9806304205397986e-06, "epoch": 17.17385654885655, "percentage": 85.87, "elapsed_time": "1:36:05", "remaining_time": "0:15:48", "throughput": 1032.19, "total_tokens": 5950944} {"current_steps": 66090, "total_steps": 76960, "loss": 0.2599, "lr": 2.977946231093884e-06, "epoch": 17.175155925155924, "percentage": 85.88, "elapsed_time": "1:36:05", "remaining_time": "0:15:48", "throughput": 1032.2, "total_tokens": 5951376} {"current_steps": 66095, "total_steps": 76960, "loss": 0.0336, "lr": 2.9752631742632876e-06, "epoch": 17.176455301455302, "percentage": 85.88, "elapsed_time": "1:36:06", "remaining_time": "0:15:47", "throughput": 1032.2, "total_tokens": 5951840} {"current_steps": 66100, "total_steps": 76960, "loss": 0.0616, "lr": 2.9725812501860157e-06, "epoch": 17.177754677754677, "percentage": 85.89, "elapsed_time": "1:36:06", "remaining_time": "0:15:47", "throughput": 1032.2, "total_tokens": 5952288} {"current_steps": 66105, "total_steps": 76960, "loss": 0.466, "lr": 2.9699004589999913e-06, "epoch": 17.179054054054053, "percentage": 85.9, "elapsed_time": "1:36:06", "remaining_time": "0:15:46", "throughput": 1032.21, "total_tokens": 5952736} {"current_steps": 66110, "total_steps": 76960, "loss": 0.0903, "lr": 2.9672208008430928e-06, "epoch": 17.18035343035343, "percentage": 85.9, "elapsed_time": "1:36:07", "remaining_time": "0:15:46", "throughput": 1032.22, "total_tokens": 5953216} {"current_steps": 66115, "total_steps": 76960, "loss": 0.0376, "lr": 2.964542275853141e-06, "epoch": 17.181652806652806, "percentage": 85.91, "elapsed_time": "1:36:07", "remaining_time": "0:15:46", "throughput": 1032.23, "total_tokens": 5953696} {"current_steps": 66120, "total_steps": 76960, "loss": 0.2829, "lr": 2.9618648841678977e-06, "epoch": 17.18295218295218, "percentage": 85.91, "elapsed_time": "1:36:08", "remaining_time": "0:15:45", "throughput": 1032.23, "total_tokens": 5954144} {"current_steps": 66125, "total_steps": 76960, "loss": 0.0054, "lr": 2.9591886259250605e-06, "epoch": 17.18425155925156, "percentage": 85.92, "elapsed_time": "1:36:08", "remaining_time": "0:15:45", "throughput": 1032.23, "total_tokens": 5954576} {"current_steps": 66130, "total_steps": 76960, "loss": 0.1577, "lr": 2.956513501262265e-06, "epoch": 17.185550935550935, "percentage": 85.93, "elapsed_time": "1:36:09", "remaining_time": "0:15:44", "throughput": 1032.23, "total_tokens": 5955024} {"current_steps": 66135, "total_steps": 76960, "loss": 0.0043, "lr": 2.953839510317105e-06, "epoch": 17.18685031185031, "percentage": 85.93, "elapsed_time": "1:36:09", "remaining_time": "0:15:44", "throughput": 1032.23, "total_tokens": 5955456} {"current_steps": 66140, "total_steps": 76960, "loss": 0.0067, "lr": 2.951166653227097e-06, "epoch": 17.18814968814969, "percentage": 85.94, "elapsed_time": "1:36:09", "remaining_time": "0:15:43", "throughput": 1032.23, "total_tokens": 5955888} {"current_steps": 66145, "total_steps": 76960, "loss": 0.1678, "lr": 2.9484949301297166e-06, "epoch": 17.189449064449065, "percentage": 85.95, "elapsed_time": "1:36:10", "remaining_time": "0:15:43", "throughput": 1032.23, "total_tokens": 5956320} {"current_steps": 66150, "total_steps": 76960, "loss": 0.0243, "lr": 2.9458243411623677e-06, "epoch": 17.19074844074844, "percentage": 85.95, "elapsed_time": "1:36:10", "remaining_time": "0:15:43", "throughput": 1032.24, "total_tokens": 5956768} {"current_steps": 66155, "total_steps": 76960, "loss": 0.0586, "lr": 2.9431548864624127e-06, "epoch": 17.19204781704782, "percentage": 85.96, "elapsed_time": "1:36:11", "remaining_time": "0:15:42", "throughput": 1032.24, "total_tokens": 5957200} {"current_steps": 66160, "total_steps": 76960, "loss": 0.3531, "lr": 2.940486566167128e-06, "epoch": 17.193347193347194, "percentage": 85.97, "elapsed_time": "1:36:11", "remaining_time": "0:15:42", "throughput": 1032.25, "total_tokens": 5957696} {"current_steps": 66165, "total_steps": 76960, "loss": 0.0778, "lr": 2.9378193804137617e-06, "epoch": 17.19464656964657, "percentage": 85.97, "elapsed_time": "1:36:11", "remaining_time": "0:15:41", "throughput": 1032.25, "total_tokens": 5958128} {"current_steps": 66170, "total_steps": 76960, "loss": 0.0023, "lr": 2.9351533293394797e-06, "epoch": 17.195945945945947, "percentage": 85.98, "elapsed_time": "1:36:12", "remaining_time": "0:15:41", "throughput": 1032.25, "total_tokens": 5958592} {"current_steps": 66175, "total_steps": 76960, "loss": 0.0769, "lr": 2.932488413081408e-06, "epoch": 17.197245322245323, "percentage": 85.99, "elapsed_time": "1:36:12", "remaining_time": "0:15:40", "throughput": 1032.26, "total_tokens": 5959056} {"current_steps": 66180, "total_steps": 76960, "loss": 0.2071, "lr": 2.9298246317765954e-06, "epoch": 17.198544698544698, "percentage": 85.99, "elapsed_time": "1:36:13", "remaining_time": "0:15:40", "throughput": 1032.26, "total_tokens": 5959504} {"current_steps": 66185, "total_steps": 76960, "loss": 0.2071, "lr": 2.9271619855620493e-06, "epoch": 17.199844074844076, "percentage": 86.0, "elapsed_time": "1:36:13", "remaining_time": "0:15:39", "throughput": 1032.27, "total_tokens": 5959952} {"current_steps": 66190, "total_steps": 76960, "loss": 0.0002, "lr": 2.924500474574715e-06, "epoch": 17.20114345114345, "percentage": 86.01, "elapsed_time": "1:36:14", "remaining_time": "0:15:39", "throughput": 1032.27, "total_tokens": 5960432} {"current_steps": 66195, "total_steps": 76960, "loss": 0.0907, "lr": 2.92184009895147e-06, "epoch": 17.202442827442827, "percentage": 86.01, "elapsed_time": "1:36:14", "remaining_time": "0:15:39", "throughput": 1032.27, "total_tokens": 5960832} {"current_steps": 66200, "total_steps": 76960, "loss": 0.018, "lr": 2.919180858829146e-06, "epoch": 17.203742203742205, "percentage": 86.02, "elapsed_time": "1:36:14", "remaining_time": "0:15:38", "throughput": 1032.28, "total_tokens": 5961312} {"current_steps": 66205, "total_steps": 76960, "loss": 0.4611, "lr": 2.916522754344503e-06, "epoch": 17.20504158004158, "percentage": 86.03, "elapsed_time": "1:36:15", "remaining_time": "0:15:38", "throughput": 1032.28, "total_tokens": 5961760} {"current_steps": 66210, "total_steps": 76960, "loss": 0.166, "lr": 2.9138657856342596e-06, "epoch": 17.206340956340956, "percentage": 86.03, "elapsed_time": "1:36:15", "remaining_time": "0:15:37", "throughput": 1032.28, "total_tokens": 5962208} {"current_steps": 66215, "total_steps": 76960, "loss": 0.0039, "lr": 2.911209952835056e-06, "epoch": 17.20764033264033, "percentage": 86.04, "elapsed_time": "1:36:16", "remaining_time": "0:15:37", "throughput": 1032.29, "total_tokens": 5962688} {"current_steps": 66220, "total_steps": 76960, "loss": 0.084, "lr": 2.9085552560834894e-06, "epoch": 17.20893970893971, "percentage": 86.04, "elapsed_time": "1:36:16", "remaining_time": "0:15:36", "throughput": 1032.3, "total_tokens": 5963136} {"current_steps": 66225, "total_steps": 76960, "loss": 0.0253, "lr": 2.9059016955160916e-06, "epoch": 17.210239085239085, "percentage": 86.05, "elapsed_time": "1:36:16", "remaining_time": "0:15:36", "throughput": 1032.3, "total_tokens": 5963568} {"current_steps": 66230, "total_steps": 76960, "loss": 0.0637, "lr": 2.9032492712693426e-06, "epoch": 17.21153846153846, "percentage": 86.06, "elapsed_time": "1:36:17", "remaining_time": "0:15:36", "throughput": 1032.3, "total_tokens": 5964048} {"current_steps": 66235, "total_steps": 76960, "loss": 0.0412, "lr": 2.9005979834796555e-06, "epoch": 17.21283783783784, "percentage": 86.06, "elapsed_time": "1:36:17", "remaining_time": "0:15:35", "throughput": 1032.31, "total_tokens": 5964512} {"current_steps": 66240, "total_steps": 76960, "loss": 0.1818, "lr": 2.8979478322833902e-06, "epoch": 17.214137214137214, "percentage": 86.07, "elapsed_time": "1:36:18", "remaining_time": "0:15:35", "throughput": 1032.31, "total_tokens": 5964960} {"current_steps": 66245, "total_steps": 76960, "loss": 0.2143, "lr": 2.895298817816841e-06, "epoch": 17.21543659043659, "percentage": 86.08, "elapsed_time": "1:36:18", "remaining_time": "0:15:34", "throughput": 1032.31, "total_tokens": 5965392} {"current_steps": 66250, "total_steps": 76960, "loss": 0.1141, "lr": 2.892650940216257e-06, "epoch": 17.216735966735968, "percentage": 86.08, "elapsed_time": "1:36:19", "remaining_time": "0:15:34", "throughput": 1032.32, "total_tokens": 5965856} {"current_steps": 66255, "total_steps": 76960, "loss": 0.0093, "lr": 2.890004199617813e-06, "epoch": 17.218035343035343, "percentage": 86.09, "elapsed_time": "1:36:19", "remaining_time": "0:15:33", "throughput": 1032.32, "total_tokens": 5966288} {"current_steps": 66260, "total_steps": 76960, "loss": 0.1819, "lr": 2.887358596157638e-06, "epoch": 17.219334719334718, "percentage": 86.1, "elapsed_time": "1:36:19", "remaining_time": "0:15:33", "throughput": 1032.32, "total_tokens": 5966704} {"current_steps": 66265, "total_steps": 76960, "loss": 0.0348, "lr": 2.884714129971805e-06, "epoch": 17.220634095634097, "percentage": 86.1, "elapsed_time": "1:36:20", "remaining_time": "0:15:32", "throughput": 1032.32, "total_tokens": 5967168} {"current_steps": 66270, "total_steps": 76960, "loss": 0.5004, "lr": 2.8820708011963073e-06, "epoch": 17.221933471933472, "percentage": 86.11, "elapsed_time": "1:36:20", "remaining_time": "0:15:32", "throughput": 1032.33, "total_tokens": 5967600} {"current_steps": 66275, "total_steps": 76960, "loss": 0.2119, "lr": 2.879428609967105e-06, "epoch": 17.223232848232847, "percentage": 86.12, "elapsed_time": "1:36:21", "remaining_time": "0:15:32", "throughput": 1032.33, "total_tokens": 5968048} {"current_steps": 66280, "total_steps": 76960, "loss": 0.2355, "lr": 2.8767875564200795e-06, "epoch": 17.224532224532226, "percentage": 86.12, "elapsed_time": "1:36:21", "remaining_time": "0:15:31", "throughput": 1032.33, "total_tokens": 5968464} {"current_steps": 66285, "total_steps": 76960, "loss": 0.1685, "lr": 2.8741476406910715e-06, "epoch": 17.2258316008316, "percentage": 86.13, "elapsed_time": "1:36:21", "remaining_time": "0:15:31", "throughput": 1032.33, "total_tokens": 5968928} {"current_steps": 66290, "total_steps": 76960, "loss": 0.3811, "lr": 2.8715088629158422e-06, "epoch": 17.227130977130976, "percentage": 86.14, "elapsed_time": "1:36:22", "remaining_time": "0:15:30", "throughput": 1032.33, "total_tokens": 5969376} {"current_steps": 66295, "total_steps": 76960, "loss": 0.5555, "lr": 2.868871223230124e-06, "epoch": 17.228430353430355, "percentage": 86.14, "elapsed_time": "1:36:22", "remaining_time": "0:15:30", "throughput": 1032.34, "total_tokens": 5969840} {"current_steps": 66300, "total_steps": 76960, "loss": 0.1492, "lr": 2.866234721769559e-06, "epoch": 17.22972972972973, "percentage": 86.15, "elapsed_time": "1:36:23", "remaining_time": "0:15:29", "throughput": 1032.35, "total_tokens": 5970304} {"current_steps": 66305, "total_steps": 76960, "loss": 0.0069, "lr": 2.8635993586697553e-06, "epoch": 17.231029106029105, "percentage": 86.16, "elapsed_time": "1:36:23", "remaining_time": "0:15:29", "throughput": 1032.35, "total_tokens": 5970736} {"current_steps": 66310, "total_steps": 76960, "loss": 0.0247, "lr": 2.8609651340662403e-06, "epoch": 17.232328482328484, "percentage": 86.16, "elapsed_time": "1:36:24", "remaining_time": "0:15:28", "throughput": 1032.35, "total_tokens": 5971200} {"current_steps": 66315, "total_steps": 76960, "loss": 0.0019, "lr": 2.858332048094506e-06, "epoch": 17.23362785862786, "percentage": 86.17, "elapsed_time": "1:36:24", "remaining_time": "0:15:28", "throughput": 1032.36, "total_tokens": 5971696} {"current_steps": 66320, "total_steps": 76960, "loss": 0.1645, "lr": 2.855700100889966e-06, "epoch": 17.234927234927234, "percentage": 86.17, "elapsed_time": "1:36:24", "remaining_time": "0:15:28", "throughput": 1032.36, "total_tokens": 5972128} {"current_steps": 66325, "total_steps": 76960, "loss": 0.0541, "lr": 2.8530692925879872e-06, "epoch": 17.236226611226613, "percentage": 86.18, "elapsed_time": "1:36:25", "remaining_time": "0:15:27", "throughput": 1032.38, "total_tokens": 5972624} {"current_steps": 66330, "total_steps": 76960, "loss": 0.1146, "lr": 2.850439623323878e-06, "epoch": 17.237525987525988, "percentage": 86.19, "elapsed_time": "1:36:25", "remaining_time": "0:15:27", "throughput": 1032.39, "total_tokens": 5973120} {"current_steps": 66335, "total_steps": 76960, "loss": 0.1894, "lr": 2.8478110932328773e-06, "epoch": 17.238825363825363, "percentage": 86.19, "elapsed_time": "1:36:26", "remaining_time": "0:15:26", "throughput": 1032.39, "total_tokens": 5973568} {"current_steps": 66340, "total_steps": 76960, "loss": 0.0016, "lr": 2.8451837024501826e-06, "epoch": 17.24012474012474, "percentage": 86.2, "elapsed_time": "1:36:26", "remaining_time": "0:15:26", "throughput": 1032.4, "total_tokens": 5974016} {"current_steps": 66345, "total_steps": 76960, "loss": 0.084, "lr": 2.842557451110914e-06, "epoch": 17.241424116424117, "percentage": 86.21, "elapsed_time": "1:36:26", "remaining_time": "0:15:25", "throughput": 1032.4, "total_tokens": 5974496} {"current_steps": 66350, "total_steps": 76960, "loss": 0.1607, "lr": 2.8399323393501514e-06, "epoch": 17.242723492723492, "percentage": 86.21, "elapsed_time": "1:36:27", "remaining_time": "0:15:25", "throughput": 1032.41, "total_tokens": 5974960} {"current_steps": 66355, "total_steps": 76960, "loss": 0.3062, "lr": 2.8373083673028934e-06, "epoch": 17.24402286902287, "percentage": 86.22, "elapsed_time": "1:36:27", "remaining_time": "0:15:25", "throughput": 1032.41, "total_tokens": 5975376} {"current_steps": 66360, "total_steps": 76960, "loss": 0.1477, "lr": 2.8346855351041036e-06, "epoch": 17.245322245322246, "percentage": 86.23, "elapsed_time": "1:36:28", "remaining_time": "0:15:24", "throughput": 1032.41, "total_tokens": 5975808} {"current_steps": 66365, "total_steps": 76960, "loss": 0.0091, "lr": 2.8320638428886742e-06, "epoch": 17.24662162162162, "percentage": 86.23, "elapsed_time": "1:36:28", "remaining_time": "0:15:24", "throughput": 1032.41, "total_tokens": 5976256} {"current_steps": 66370, "total_steps": 76960, "loss": 0.021, "lr": 2.829443290791445e-06, "epoch": 17.247920997920996, "percentage": 86.24, "elapsed_time": "1:36:29", "remaining_time": "0:15:23", "throughput": 1032.42, "total_tokens": 5976704} {"current_steps": 66375, "total_steps": 76960, "loss": 0.0072, "lr": 2.826823878947188e-06, "epoch": 17.249220374220375, "percentage": 86.25, "elapsed_time": "1:36:29", "remaining_time": "0:15:23", "throughput": 1032.42, "total_tokens": 5977136} {"current_steps": 66380, "total_steps": 76960, "loss": 0.0007, "lr": 2.8242056074906266e-06, "epoch": 17.25051975051975, "percentage": 86.25, "elapsed_time": "1:36:29", "remaining_time": "0:15:22", "throughput": 1032.43, "total_tokens": 5977616} {"current_steps": 66385, "total_steps": 76960, "loss": 0.1284, "lr": 2.8215884765564193e-06, "epoch": 17.251819126819125, "percentage": 86.26, "elapsed_time": "1:36:30", "remaining_time": "0:15:22", "throughput": 1032.43, "total_tokens": 5978064} {"current_steps": 66390, "total_steps": 76960, "loss": 0.1186, "lr": 2.8189724862791617e-06, "epoch": 17.253118503118504, "percentage": 86.27, "elapsed_time": "1:36:30", "remaining_time": "0:15:21", "throughput": 1032.43, "total_tokens": 5978496} {"current_steps": 66395, "total_steps": 76960, "loss": 0.1408, "lr": 2.8163576367934042e-06, "epoch": 17.25441787941788, "percentage": 86.27, "elapsed_time": "1:36:31", "remaining_time": "0:15:21", "throughput": 1032.43, "total_tokens": 5978944} {"current_steps": 66400, "total_steps": 76960, "loss": 0.0574, "lr": 2.813743928233625e-06, "epoch": 17.255717255717254, "percentage": 86.28, "elapsed_time": "1:36:31", "remaining_time": "0:15:21", "throughput": 1032.43, "total_tokens": 5979376} {"current_steps": 66405, "total_steps": 76960, "loss": 0.1226, "lr": 2.8111313607342623e-06, "epoch": 17.257016632016633, "percentage": 86.29, "elapsed_time": "1:36:31", "remaining_time": "0:15:20", "throughput": 1032.43, "total_tokens": 5979808} {"current_steps": 66410, "total_steps": 76960, "loss": 0.4184, "lr": 2.808519934429668e-06, "epoch": 17.258316008316008, "percentage": 86.29, "elapsed_time": "1:36:32", "remaining_time": "0:15:20", "throughput": 1032.44, "total_tokens": 5980256} {"current_steps": 66415, "total_steps": 76960, "loss": 0.0039, "lr": 2.8059096494541607e-06, "epoch": 17.259615384615383, "percentage": 86.3, "elapsed_time": "1:36:32", "remaining_time": "0:15:19", "throughput": 1032.44, "total_tokens": 5980704} {"current_steps": 66420, "total_steps": 76960, "loss": 0.0074, "lr": 2.80330050594198e-06, "epoch": 17.260914760914762, "percentage": 86.3, "elapsed_time": "1:36:33", "remaining_time": "0:15:19", "throughput": 1032.45, "total_tokens": 5981184} {"current_steps": 66425, "total_steps": 76960, "loss": 0.0494, "lr": 2.8006925040273275e-06, "epoch": 17.262214137214137, "percentage": 86.31, "elapsed_time": "1:36:33", "remaining_time": "0:15:18", "throughput": 1032.45, "total_tokens": 5981616} {"current_steps": 66430, "total_steps": 76960, "loss": 0.0324, "lr": 2.7980856438443255e-06, "epoch": 17.263513513513512, "percentage": 86.32, "elapsed_time": "1:36:34", "remaining_time": "0:15:18", "throughput": 1032.45, "total_tokens": 5982064} {"current_steps": 66435, "total_steps": 76960, "loss": 0.2963, "lr": 2.7954799255270502e-06, "epoch": 17.26481288981289, "percentage": 86.32, "elapsed_time": "1:36:34", "remaining_time": "0:15:17", "throughput": 1032.45, "total_tokens": 5982512} {"current_steps": 66440, "total_steps": 76960, "loss": 0.1814, "lr": 2.79287534920952e-06, "epoch": 17.266112266112266, "percentage": 86.33, "elapsed_time": "1:36:34", "remaining_time": "0:15:17", "throughput": 1032.46, "total_tokens": 5982960} {"current_steps": 66445, "total_steps": 76960, "loss": 0.16, "lr": 2.790271915025691e-06, "epoch": 17.26741164241164, "percentage": 86.34, "elapsed_time": "1:36:35", "remaining_time": "0:15:17", "throughput": 1032.46, "total_tokens": 5983408} {"current_steps": 66450, "total_steps": 76960, "loss": 0.0243, "lr": 2.7876696231094596e-06, "epoch": 17.26871101871102, "percentage": 86.34, "elapsed_time": "1:36:35", "remaining_time": "0:15:16", "throughput": 1032.47, "total_tokens": 5983872} {"current_steps": 66455, "total_steps": 76960, "loss": 0.1228, "lr": 2.785068473594657e-06, "epoch": 17.270010395010395, "percentage": 86.35, "elapsed_time": "1:36:36", "remaining_time": "0:15:16", "throughput": 1032.47, "total_tokens": 5984336} {"current_steps": 66460, "total_steps": 76960, "loss": 0.5128, "lr": 2.7824684666150706e-06, "epoch": 17.27130977130977, "percentage": 86.36, "elapsed_time": "1:36:36", "remaining_time": "0:15:15", "throughput": 1032.48, "total_tokens": 5984816} {"current_steps": 66465, "total_steps": 76960, "loss": 0.0082, "lr": 2.7798696023044163e-06, "epoch": 17.27260914760915, "percentage": 86.36, "elapsed_time": "1:36:36", "remaining_time": "0:15:15", "throughput": 1032.49, "total_tokens": 5985264} {"current_steps": 66470, "total_steps": 76960, "loss": 0.0534, "lr": 2.777271880796359e-06, "epoch": 17.273908523908524, "percentage": 86.37, "elapsed_time": "1:36:37", "remaining_time": "0:15:14", "throughput": 1032.48, "total_tokens": 5985680} {"current_steps": 66475, "total_steps": 76960, "loss": 0.0791, "lr": 2.7746753022244996e-06, "epoch": 17.2752079002079, "percentage": 86.38, "elapsed_time": "1:36:37", "remaining_time": "0:15:14", "throughput": 1032.48, "total_tokens": 5986096} {"current_steps": 66480, "total_steps": 76960, "loss": 0.0006, "lr": 2.7720798667223934e-06, "epoch": 17.276507276507278, "percentage": 86.38, "elapsed_time": "1:36:38", "remaining_time": "0:15:14", "throughput": 1032.48, "total_tokens": 5986512} {"current_steps": 66485, "total_steps": 76960, "loss": 0.1065, "lr": 2.7694855744235083e-06, "epoch": 17.277806652806653, "percentage": 86.39, "elapsed_time": "1:36:38", "remaining_time": "0:15:13", "throughput": 1032.49, "total_tokens": 5987008} {"current_steps": 66490, "total_steps": 76960, "loss": 0.0225, "lr": 2.766892425461287e-06, "epoch": 17.27910602910603, "percentage": 86.4, "elapsed_time": "1:36:39", "remaining_time": "0:15:13", "throughput": 1032.49, "total_tokens": 5987456} {"current_steps": 66495, "total_steps": 76960, "loss": 0.0369, "lr": 2.7643004199690873e-06, "epoch": 17.280405405405407, "percentage": 86.4, "elapsed_time": "1:36:39", "remaining_time": "0:15:12", "throughput": 1032.5, "total_tokens": 5987920} {"current_steps": 66500, "total_steps": 76960, "loss": 0.102, "lr": 2.761709558080225e-06, "epoch": 17.281704781704782, "percentage": 86.41, "elapsed_time": "1:36:39", "remaining_time": "0:15:12", "throughput": 1032.5, "total_tokens": 5988368} {"current_steps": 66505, "total_steps": 76960, "loss": 0.1956, "lr": 2.759119839927943e-06, "epoch": 17.283004158004157, "percentage": 86.42, "elapsed_time": "1:36:40", "remaining_time": "0:15:11", "throughput": 1032.5, "total_tokens": 5988800} {"current_steps": 66510, "total_steps": 76960, "loss": 0.1103, "lr": 2.75653126564544e-06, "epoch": 17.284303534303533, "percentage": 86.42, "elapsed_time": "1:36:40", "remaining_time": "0:15:11", "throughput": 1032.51, "total_tokens": 5989264} {"current_steps": 66515, "total_steps": 76960, "loss": 0.1675, "lr": 2.753943835365849e-06, "epoch": 17.28560291060291, "percentage": 86.43, "elapsed_time": "1:36:41", "remaining_time": "0:15:10", "throughput": 1032.51, "total_tokens": 5989728} {"current_steps": 66520, "total_steps": 76960, "loss": 0.5364, "lr": 2.7513575492222387e-06, "epoch": 17.286902286902286, "percentage": 86.43, "elapsed_time": "1:36:41", "remaining_time": "0:15:10", "throughput": 1032.52, "total_tokens": 5990208} {"current_steps": 66525, "total_steps": 76960, "loss": 0.2021, "lr": 2.7487724073476327e-06, "epoch": 17.28820166320166, "percentage": 86.44, "elapsed_time": "1:36:41", "remaining_time": "0:15:10", "throughput": 1032.53, "total_tokens": 5990656} {"current_steps": 66530, "total_steps": 76960, "loss": 0.0014, "lr": 2.746188409874975e-06, "epoch": 17.28950103950104, "percentage": 86.45, "elapsed_time": "1:36:42", "remaining_time": "0:15:09", "throughput": 1032.53, "total_tokens": 5991104} {"current_steps": 66535, "total_steps": 76960, "loss": 0.178, "lr": 2.743605556937176e-06, "epoch": 17.290800415800415, "percentage": 86.45, "elapsed_time": "1:36:42", "remaining_time": "0:15:09", "throughput": 1032.54, "total_tokens": 5991568} {"current_steps": 66540, "total_steps": 76960, "loss": 0.0489, "lr": 2.741023848667057e-06, "epoch": 17.29209979209979, "percentage": 86.46, "elapsed_time": "1:36:43", "remaining_time": "0:15:08", "throughput": 1032.54, "total_tokens": 5992032} {"current_steps": 66545, "total_steps": 76960, "loss": 0.0019, "lr": 2.73844328519742e-06, "epoch": 17.29339916839917, "percentage": 86.47, "elapsed_time": "1:36:43", "remaining_time": "0:15:08", "throughput": 1032.56, "total_tokens": 5992544} {"current_steps": 66550, "total_steps": 76960, "loss": 0.0858, "lr": 2.7358638666609702e-06, "epoch": 17.294698544698544, "percentage": 86.47, "elapsed_time": "1:36:44", "remaining_time": "0:15:07", "throughput": 1032.56, "total_tokens": 5993008} {"current_steps": 66555, "total_steps": 76960, "loss": 0.0258, "lr": 2.7332855931903794e-06, "epoch": 17.29599792099792, "percentage": 86.48, "elapsed_time": "1:36:44", "remaining_time": "0:15:07", "throughput": 1032.57, "total_tokens": 5993456} {"current_steps": 66560, "total_steps": 76960, "loss": 0.0023, "lr": 2.7307084649182385e-06, "epoch": 17.2972972972973, "percentage": 86.49, "elapsed_time": "1:36:44", "remaining_time": "0:15:07", "throughput": 1032.56, "total_tokens": 5993872} {"current_steps": 66565, "total_steps": 76960, "loss": 0.3456, "lr": 2.728132481977105e-06, "epoch": 17.298596673596673, "percentage": 86.49, "elapsed_time": "1:36:45", "remaining_time": "0:15:06", "throughput": 1032.57, "total_tokens": 5994336} {"current_steps": 66570, "total_steps": 76960, "loss": 0.0002, "lr": 2.725557644499452e-06, "epoch": 17.29989604989605, "percentage": 86.5, "elapsed_time": "1:36:45", "remaining_time": "0:15:06", "throughput": 1032.58, "total_tokens": 5994800} {"current_steps": 66575, "total_steps": 76960, "loss": 0.0153, "lr": 2.722983952617714e-06, "epoch": 17.301195426195427, "percentage": 86.51, "elapsed_time": "1:36:46", "remaining_time": "0:15:05", "throughput": 1032.58, "total_tokens": 5995248} {"current_steps": 66580, "total_steps": 76960, "loss": 0.0893, "lr": 2.72041140646426e-06, "epoch": 17.302494802494802, "percentage": 86.51, "elapsed_time": "1:36:46", "remaining_time": "0:15:05", "throughput": 1032.58, "total_tokens": 5995712} {"current_steps": 66585, "total_steps": 76960, "loss": 0.0617, "lr": 2.7178400061713875e-06, "epoch": 17.303794178794178, "percentage": 86.52, "elapsed_time": "1:36:46", "remaining_time": "0:15:04", "throughput": 1032.59, "total_tokens": 5996160} {"current_steps": 66590, "total_steps": 76960, "loss": 0.0458, "lr": 2.7152697518713603e-06, "epoch": 17.305093555093556, "percentage": 86.53, "elapsed_time": "1:36:47", "remaining_time": "0:15:04", "throughput": 1032.59, "total_tokens": 5996624} {"current_steps": 66595, "total_steps": 76960, "loss": 0.0002, "lr": 2.7127006436963557e-06, "epoch": 17.30639293139293, "percentage": 86.53, "elapsed_time": "1:36:47", "remaining_time": "0:15:03", "throughput": 1032.59, "total_tokens": 5997040} {"current_steps": 66600, "total_steps": 76960, "loss": 0.0369, "lr": 2.710132681778518e-06, "epoch": 17.307692307692307, "percentage": 86.54, "elapsed_time": "1:36:48", "remaining_time": "0:15:03", "throughput": 1032.6, "total_tokens": 5997504} {"current_steps": 66605, "total_steps": 76960, "loss": 0.009, "lr": 2.707565866249909e-06, "epoch": 17.308991683991685, "percentage": 86.54, "elapsed_time": "1:36:48", "remaining_time": "0:15:03", "throughput": 1032.6, "total_tokens": 5997936} {"current_steps": 66610, "total_steps": 76960, "loss": 0.5127, "lr": 2.7050001972425463e-06, "epoch": 17.31029106029106, "percentage": 86.55, "elapsed_time": "1:36:49", "remaining_time": "0:15:02", "throughput": 1032.6, "total_tokens": 5998352} {"current_steps": 66615, "total_steps": 76960, "loss": 0.0033, "lr": 2.7024356748883844e-06, "epoch": 17.311590436590436, "percentage": 86.56, "elapsed_time": "1:36:49", "remaining_time": "0:15:02", "throughput": 1032.6, "total_tokens": 5998784} {"current_steps": 66620, "total_steps": 76960, "loss": 0.2171, "lr": 2.6998722993193282e-06, "epoch": 17.312889812889814, "percentage": 86.56, "elapsed_time": "1:36:49", "remaining_time": "0:15:01", "throughput": 1032.6, "total_tokens": 5999232} {"current_steps": 66625, "total_steps": 76960, "loss": 0.1586, "lr": 2.6973100706672e-06, "epoch": 17.31418918918919, "percentage": 86.57, "elapsed_time": "1:36:50", "remaining_time": "0:15:01", "throughput": 1032.6, "total_tokens": 5999680} {"current_steps": 66630, "total_steps": 76960, "loss": 0.0263, "lr": 2.6947489890637887e-06, "epoch": 17.315488565488565, "percentage": 86.58, "elapsed_time": "1:36:50", "remaining_time": "0:15:00", "throughput": 1032.6, "total_tokens": 6000112} {"current_steps": 66635, "total_steps": 76960, "loss": 0.1367, "lr": 2.6921890546408034e-06, "epoch": 17.316787941787943, "percentage": 86.58, "elapsed_time": "1:36:51", "remaining_time": "0:15:00", "throughput": 1032.61, "total_tokens": 6000576} {"current_steps": 66640, "total_steps": 76960, "loss": 0.0313, "lr": 2.6896302675299134e-06, "epoch": 17.31808731808732, "percentage": 86.59, "elapsed_time": "1:36:51", "remaining_time": "0:14:59", "throughput": 1032.61, "total_tokens": 6001008} {"current_steps": 66645, "total_steps": 76960, "loss": 0.0003, "lr": 2.687072627862713e-06, "epoch": 17.319386694386694, "percentage": 86.6, "elapsed_time": "1:36:51", "remaining_time": "0:14:59", "throughput": 1032.62, "total_tokens": 6001472} {"current_steps": 66650, "total_steps": 76960, "loss": 0.0012, "lr": 2.6845161357707454e-06, "epoch": 17.320686070686072, "percentage": 86.6, "elapsed_time": "1:36:52", "remaining_time": "0:14:59", "throughput": 1032.62, "total_tokens": 6001936} {"current_steps": 66655, "total_steps": 76960, "loss": 0.029, "lr": 2.6819607913855017e-06, "epoch": 17.321985446985448, "percentage": 86.61, "elapsed_time": "1:36:52", "remaining_time": "0:14:58", "throughput": 1032.63, "total_tokens": 6002400} {"current_steps": 66660, "total_steps": 76960, "loss": 0.0089, "lr": 2.679406594838391e-06, "epoch": 17.323284823284823, "percentage": 86.62, "elapsed_time": "1:36:53", "remaining_time": "0:14:58", "throughput": 1032.63, "total_tokens": 6002848} {"current_steps": 66665, "total_steps": 76960, "loss": 0.4311, "lr": 2.676853546260791e-06, "epoch": 17.3245841995842, "percentage": 86.62, "elapsed_time": "1:36:53", "remaining_time": "0:14:57", "throughput": 1032.64, "total_tokens": 6003328} {"current_steps": 66670, "total_steps": 76960, "loss": 0.0326, "lr": 2.674301645783997e-06, "epoch": 17.325883575883577, "percentage": 86.63, "elapsed_time": "1:36:53", "remaining_time": "0:14:57", "throughput": 1032.64, "total_tokens": 6003792} {"current_steps": 66675, "total_steps": 76960, "loss": 0.0064, "lr": 2.6717508935392682e-06, "epoch": 17.32718295218295, "percentage": 86.64, "elapsed_time": "1:36:54", "remaining_time": "0:14:56", "throughput": 1032.65, "total_tokens": 6004240} {"current_steps": 66680, "total_steps": 76960, "loss": 0.1533, "lr": 2.669201289657777e-06, "epoch": 17.328482328482327, "percentage": 86.64, "elapsed_time": "1:36:54", "remaining_time": "0:14:56", "throughput": 1032.65, "total_tokens": 6004688} {"current_steps": 66685, "total_steps": 76960, "loss": 0.0176, "lr": 2.666652834270661e-06, "epoch": 17.329781704781706, "percentage": 86.65, "elapsed_time": "1:36:55", "remaining_time": "0:14:56", "throughput": 1032.65, "total_tokens": 6005088} {"current_steps": 66690, "total_steps": 76960, "loss": 0.1569, "lr": 2.6641055275089866e-06, "epoch": 17.33108108108108, "percentage": 86.66, "elapsed_time": "1:36:55", "remaining_time": "0:14:55", "throughput": 1032.65, "total_tokens": 6005536} {"current_steps": 66695, "total_steps": 76960, "loss": 0.1518, "lr": 2.6615593695037745e-06, "epoch": 17.332380457380456, "percentage": 86.66, "elapsed_time": "1:36:56", "remaining_time": "0:14:55", "throughput": 1032.65, "total_tokens": 6005984} {"current_steps": 66700, "total_steps": 76960, "loss": 0.472, "lr": 2.6590143603859614e-06, "epoch": 17.333679833679835, "percentage": 86.67, "elapsed_time": "1:36:56", "remaining_time": "0:14:54", "throughput": 1032.65, "total_tokens": 6006416} {"current_steps": 66705, "total_steps": 76960, "loss": 0.4773, "lr": 2.656470500286451e-06, "epoch": 17.33497920997921, "percentage": 86.67, "elapsed_time": "1:36:56", "remaining_time": "0:14:54", "throughput": 1032.66, "total_tokens": 6006896} {"current_steps": 66710, "total_steps": 76960, "loss": 0.0116, "lr": 2.6539277893360692e-06, "epoch": 17.336278586278585, "percentage": 86.68, "elapsed_time": "1:36:57", "remaining_time": "0:14:53", "throughput": 1032.66, "total_tokens": 6007344} {"current_steps": 66715, "total_steps": 76960, "loss": 0.1902, "lr": 2.6513862276655894e-06, "epoch": 17.337577962577964, "percentage": 86.69, "elapsed_time": "1:36:57", "remaining_time": "0:14:53", "throughput": 1032.67, "total_tokens": 6007776} {"current_steps": 66720, "total_steps": 76960, "loss": 0.2588, "lr": 2.648845815405729e-06, "epoch": 17.33887733887734, "percentage": 86.69, "elapsed_time": "1:36:58", "remaining_time": "0:14:52", "throughput": 1032.67, "total_tokens": 6008224} {"current_steps": 66725, "total_steps": 76960, "loss": 0.0464, "lr": 2.6463065526871445e-06, "epoch": 17.340176715176714, "percentage": 86.7, "elapsed_time": "1:36:58", "remaining_time": "0:14:52", "throughput": 1032.67, "total_tokens": 6008688} {"current_steps": 66730, "total_steps": 76960, "loss": 0.1269, "lr": 2.6437684396404344e-06, "epoch": 17.341476091476093, "percentage": 86.71, "elapsed_time": "1:36:58", "remaining_time": "0:14:52", "throughput": 1032.69, "total_tokens": 6009200} {"current_steps": 66735, "total_steps": 76960, "loss": 0.3687, "lr": 2.6412314763961332e-06, "epoch": 17.342775467775468, "percentage": 86.71, "elapsed_time": "1:36:59", "remaining_time": "0:14:51", "throughput": 1032.69, "total_tokens": 6009632} {"current_steps": 66740, "total_steps": 76960, "loss": 0.0282, "lr": 2.6386956630847226e-06, "epoch": 17.344074844074843, "percentage": 86.72, "elapsed_time": "1:36:59", "remaining_time": "0:14:51", "throughput": 1032.69, "total_tokens": 6010096} {"current_steps": 66745, "total_steps": 76960, "loss": 0.1131, "lr": 2.636160999836615e-06, "epoch": 17.34537422037422, "percentage": 86.73, "elapsed_time": "1:37:00", "remaining_time": "0:14:50", "throughput": 1032.7, "total_tokens": 6010528} {"current_steps": 66750, "total_steps": 76960, "loss": 0.0364, "lr": 2.6336274867821808e-06, "epoch": 17.346673596673597, "percentage": 86.73, "elapsed_time": "1:37:00", "remaining_time": "0:14:50", "throughput": 1032.71, "total_tokens": 6011024} {"current_steps": 66755, "total_steps": 76960, "loss": 0.0168, "lr": 2.6310951240517107e-06, "epoch": 17.347972972972972, "percentage": 86.74, "elapsed_time": "1:37:01", "remaining_time": "0:14:49", "throughput": 1032.71, "total_tokens": 6011488} {"current_steps": 66760, "total_steps": 76960, "loss": 0.0732, "lr": 2.62856391177545e-06, "epoch": 17.34927234927235, "percentage": 86.75, "elapsed_time": "1:37:01", "remaining_time": "0:14:49", "throughput": 1032.72, "total_tokens": 6011952} {"current_steps": 66765, "total_steps": 76960, "loss": 0.0471, "lr": 2.626033850083584e-06, "epoch": 17.350571725571726, "percentage": 86.75, "elapsed_time": "1:37:01", "remaining_time": "0:14:49", "throughput": 1032.73, "total_tokens": 6012432} {"current_steps": 66770, "total_steps": 76960, "loss": 0.0495, "lr": 2.623504939106239e-06, "epoch": 17.3518711018711, "percentage": 86.76, "elapsed_time": "1:37:02", "remaining_time": "0:14:48", "throughput": 1032.72, "total_tokens": 6012848} {"current_steps": 66775, "total_steps": 76960, "loss": 0.0119, "lr": 2.620977178973474e-06, "epoch": 17.35317047817048, "percentage": 86.77, "elapsed_time": "1:37:02", "remaining_time": "0:14:48", "throughput": 1032.73, "total_tokens": 6013312} {"current_steps": 66780, "total_steps": 76960, "loss": 0.026, "lr": 2.6184505698152922e-06, "epoch": 17.354469854469855, "percentage": 86.77, "elapsed_time": "1:37:03", "remaining_time": "0:14:47", "throughput": 1032.73, "total_tokens": 6013744} {"current_steps": 66785, "total_steps": 76960, "loss": 0.1835, "lr": 2.615925111761647e-06, "epoch": 17.35576923076923, "percentage": 86.78, "elapsed_time": "1:37:03", "remaining_time": "0:14:47", "throughput": 1032.73, "total_tokens": 6014192} {"current_steps": 66790, "total_steps": 76960, "loss": 0.0186, "lr": 2.613400804942412e-06, "epoch": 17.35706860706861, "percentage": 86.79, "elapsed_time": "1:37:03", "remaining_time": "0:14:46", "throughput": 1032.73, "total_tokens": 6014592} {"current_steps": 66795, "total_steps": 76960, "loss": 0.2492, "lr": 2.610877649487431e-06, "epoch": 17.358367983367984, "percentage": 86.79, "elapsed_time": "1:37:04", "remaining_time": "0:14:46", "throughput": 1032.73, "total_tokens": 6015040} {"current_steps": 66800, "total_steps": 76960, "loss": 0.0145, "lr": 2.6083556455264613e-06, "epoch": 17.35966735966736, "percentage": 86.8, "elapsed_time": "1:37:04", "remaining_time": "0:14:45", "throughput": 1032.74, "total_tokens": 6015536} {"current_steps": 66805, "total_steps": 76960, "loss": 0.0042, "lr": 2.6058347931892187e-06, "epoch": 17.360966735966738, "percentage": 86.8, "elapsed_time": "1:37:05", "remaining_time": "0:14:45", "throughput": 1032.75, "total_tokens": 6015984} {"current_steps": 66810, "total_steps": 76960, "loss": 0.0913, "lr": 2.6033150926053463e-06, "epoch": 17.362266112266113, "percentage": 86.81, "elapsed_time": "1:37:05", "remaining_time": "0:14:45", "throughput": 1032.75, "total_tokens": 6016416} {"current_steps": 66815, "total_steps": 76960, "loss": 0.0013, "lr": 2.6007965439044436e-06, "epoch": 17.363565488565488, "percentage": 86.82, "elapsed_time": "1:37:06", "remaining_time": "0:14:44", "throughput": 1032.75, "total_tokens": 6016880} {"current_steps": 66820, "total_steps": 76960, "loss": 0.0241, "lr": 2.598279147216029e-06, "epoch": 17.364864864864863, "percentage": 86.82, "elapsed_time": "1:37:06", "remaining_time": "0:14:44", "throughput": 1032.76, "total_tokens": 6017360} {"current_steps": 66825, "total_steps": 76960, "loss": 0.0865, "lr": 2.595762902669585e-06, "epoch": 17.366164241164242, "percentage": 86.83, "elapsed_time": "1:37:06", "remaining_time": "0:14:43", "throughput": 1032.77, "total_tokens": 6017808} {"current_steps": 66830, "total_steps": 76960, "loss": 0.0395, "lr": 2.5932478103945196e-06, "epoch": 17.367463617463617, "percentage": 86.84, "elapsed_time": "1:37:07", "remaining_time": "0:14:43", "throughput": 1032.77, "total_tokens": 6018240} {"current_steps": 66835, "total_steps": 76960, "loss": 0.0014, "lr": 2.5907338705201954e-06, "epoch": 17.368762993762992, "percentage": 86.84, "elapsed_time": "1:37:07", "remaining_time": "0:14:42", "throughput": 1032.78, "total_tokens": 6018768} {"current_steps": 66840, "total_steps": 76960, "loss": 0.0102, "lr": 2.5882210831758987e-06, "epoch": 17.37006237006237, "percentage": 86.85, "elapsed_time": "1:37:08", "remaining_time": "0:14:42", "throughput": 1032.78, "total_tokens": 6019200} {"current_steps": 66845, "total_steps": 76960, "loss": 0.0399, "lr": 2.585709448490858e-06, "epoch": 17.371361746361746, "percentage": 86.86, "elapsed_time": "1:37:08", "remaining_time": "0:14:41", "throughput": 1032.79, "total_tokens": 6019648} {"current_steps": 66850, "total_steps": 76960, "loss": 0.0331, "lr": 2.5831989665942664e-06, "epoch": 17.37266112266112, "percentage": 86.86, "elapsed_time": "1:37:08", "remaining_time": "0:14:41", "throughput": 1032.79, "total_tokens": 6020080} {"current_steps": 66855, "total_steps": 76960, "loss": 0.4054, "lr": 2.5806896376152218e-06, "epoch": 17.3739604989605, "percentage": 86.87, "elapsed_time": "1:37:09", "remaining_time": "0:14:41", "throughput": 1032.79, "total_tokens": 6020544} {"current_steps": 66860, "total_steps": 76960, "loss": 0.2002, "lr": 2.578181461682794e-06, "epoch": 17.375259875259875, "percentage": 86.88, "elapsed_time": "1:37:09", "remaining_time": "0:14:40", "throughput": 1032.8, "total_tokens": 6020992} {"current_steps": 66865, "total_steps": 76960, "loss": 0.3296, "lr": 2.5756744389259734e-06, "epoch": 17.37655925155925, "percentage": 86.88, "elapsed_time": "1:37:10", "remaining_time": "0:14:40", "throughput": 1032.8, "total_tokens": 6021440} {"current_steps": 66870, "total_steps": 76960, "loss": 0.0136, "lr": 2.573168569473711e-06, "epoch": 17.37785862785863, "percentage": 86.89, "elapsed_time": "1:37:10", "remaining_time": "0:14:39", "throughput": 1032.8, "total_tokens": 6021888} {"current_steps": 66875, "total_steps": 76960, "loss": 0.3472, "lr": 2.570663853454869e-06, "epoch": 17.379158004158004, "percentage": 86.9, "elapsed_time": "1:37:11", "remaining_time": "0:14:39", "throughput": 1032.81, "total_tokens": 6022352} {"current_steps": 66880, "total_steps": 76960, "loss": 0.0006, "lr": 2.568160290998281e-06, "epoch": 17.38045738045738, "percentage": 86.9, "elapsed_time": "1:37:11", "remaining_time": "0:14:38", "throughput": 1032.8, "total_tokens": 6022752} {"current_steps": 66885, "total_steps": 76960, "loss": 0.0399, "lr": 2.5656578822327e-06, "epoch": 17.381756756756758, "percentage": 86.91, "elapsed_time": "1:37:11", "remaining_time": "0:14:38", "throughput": 1032.82, "total_tokens": 6023280} {"current_steps": 66890, "total_steps": 76960, "loss": 0.017, "lr": 2.5631566272868335e-06, "epoch": 17.383056133056133, "percentage": 86.92, "elapsed_time": "1:37:12", "remaining_time": "0:14:38", "throughput": 1032.82, "total_tokens": 6023712} {"current_steps": 66895, "total_steps": 76960, "loss": 0.0016, "lr": 2.560656526289315e-06, "epoch": 17.384355509355508, "percentage": 86.92, "elapsed_time": "1:37:12", "remaining_time": "0:14:37", "throughput": 1032.83, "total_tokens": 6024176} {"current_steps": 66900, "total_steps": 76960, "loss": 0.0035, "lr": 2.5581575793687307e-06, "epoch": 17.385654885654887, "percentage": 86.93, "elapsed_time": "1:37:13", "remaining_time": "0:14:37", "throughput": 1032.84, "total_tokens": 6024672} {"current_steps": 66905, "total_steps": 76960, "loss": 0.1786, "lr": 2.555659786653611e-06, "epoch": 17.386954261954262, "percentage": 86.93, "elapsed_time": "1:37:13", "remaining_time": "0:14:36", "throughput": 1032.84, "total_tokens": 6025104} {"current_steps": 66910, "total_steps": 76960, "loss": 0.0397, "lr": 2.5531631482724085e-06, "epoch": 17.388253638253637, "percentage": 86.94, "elapsed_time": "1:37:13", "remaining_time": "0:14:36", "throughput": 1032.85, "total_tokens": 6025568} {"current_steps": 66915, "total_steps": 76960, "loss": 0.0422, "lr": 2.550667664353534e-06, "epoch": 17.389553014553016, "percentage": 86.95, "elapsed_time": "1:37:14", "remaining_time": "0:14:35", "throughput": 1032.85, "total_tokens": 6026016} {"current_steps": 66920, "total_steps": 76960, "loss": 0.0958, "lr": 2.5481733350253305e-06, "epoch": 17.39085239085239, "percentage": 86.95, "elapsed_time": "1:37:14", "remaining_time": "0:14:35", "throughput": 1032.85, "total_tokens": 6026448} {"current_steps": 66925, "total_steps": 76960, "loss": 0.0992, "lr": 2.545680160416089e-06, "epoch": 17.392151767151766, "percentage": 86.96, "elapsed_time": "1:37:15", "remaining_time": "0:14:34", "throughput": 1032.85, "total_tokens": 6026880} {"current_steps": 66930, "total_steps": 76960, "loss": 0.001, "lr": 2.5431881406540266e-06, "epoch": 17.393451143451145, "percentage": 86.97, "elapsed_time": "1:37:15", "remaining_time": "0:14:34", "throughput": 1032.85, "total_tokens": 6027312} {"current_steps": 66935, "total_steps": 76960, "loss": 0.0064, "lr": 2.540697275867315e-06, "epoch": 17.39475051975052, "percentage": 86.97, "elapsed_time": "1:37:16", "remaining_time": "0:14:34", "throughput": 1032.86, "total_tokens": 6027792} {"current_steps": 66940, "total_steps": 76960, "loss": 0.0931, "lr": 2.5382075661840613e-06, "epoch": 17.396049896049895, "percentage": 86.98, "elapsed_time": "1:37:16", "remaining_time": "0:14:33", "throughput": 1032.86, "total_tokens": 6028240} {"current_steps": 66945, "total_steps": 76960, "loss": 0.0812, "lr": 2.535719011732321e-06, "epoch": 17.397349272349274, "percentage": 86.99, "elapsed_time": "1:37:16", "remaining_time": "0:14:33", "throughput": 1032.86, "total_tokens": 6028688} {"current_steps": 66950, "total_steps": 76960, "loss": 0.0354, "lr": 2.533231612640069e-06, "epoch": 17.39864864864865, "percentage": 86.99, "elapsed_time": "1:37:17", "remaining_time": "0:14:32", "throughput": 1032.87, "total_tokens": 6029168} {"current_steps": 66955, "total_steps": 76960, "loss": 0.0488, "lr": 2.530745369035248e-06, "epoch": 17.399948024948024, "percentage": 87.0, "elapsed_time": "1:37:17", "remaining_time": "0:14:32", "throughput": 1032.88, "total_tokens": 6029616} {"current_steps": 66960, "total_steps": 76960, "loss": 0.0345, "lr": 2.5282602810457163e-06, "epoch": 17.401247401247403, "percentage": 87.01, "elapsed_time": "1:37:18", "remaining_time": "0:14:31", "throughput": 1032.88, "total_tokens": 6030080} {"current_steps": 66965, "total_steps": 76960, "loss": 0.2554, "lr": 2.525776348799297e-06, "epoch": 17.402546777546778, "percentage": 87.01, "elapsed_time": "1:37:18", "remaining_time": "0:14:31", "throughput": 1032.89, "total_tokens": 6030560} {"current_steps": 66970, "total_steps": 76960, "loss": 0.0091, "lr": 2.5232935724237266e-06, "epoch": 17.403846153846153, "percentage": 87.02, "elapsed_time": "1:37:18", "remaining_time": "0:14:31", "throughput": 1032.89, "total_tokens": 6030992} {"current_steps": 66975, "total_steps": 76960, "loss": 0.1718, "lr": 2.520811952046703e-06, "epoch": 17.40514553014553, "percentage": 87.03, "elapsed_time": "1:37:19", "remaining_time": "0:14:30", "throughput": 1032.9, "total_tokens": 6031472} {"current_steps": 66980, "total_steps": 76960, "loss": 0.019, "lr": 2.5183314877958663e-06, "epoch": 17.406444906444907, "percentage": 87.03, "elapsed_time": "1:37:19", "remaining_time": "0:14:30", "throughput": 1032.9, "total_tokens": 6031920} {"current_steps": 66985, "total_steps": 76960, "loss": 0.3731, "lr": 2.515852179798775e-06, "epoch": 17.407744282744282, "percentage": 87.04, "elapsed_time": "1:37:20", "remaining_time": "0:14:29", "throughput": 1032.91, "total_tokens": 6032384} {"current_steps": 66990, "total_steps": 76960, "loss": 0.0069, "lr": 2.513374028182955e-06, "epoch": 17.409043659043657, "percentage": 87.05, "elapsed_time": "1:37:20", "remaining_time": "0:14:29", "throughput": 1032.91, "total_tokens": 6032816} {"current_steps": 66995, "total_steps": 76960, "loss": 0.2468, "lr": 2.5108970330758515e-06, "epoch": 17.410343035343036, "percentage": 87.05, "elapsed_time": "1:37:21", "remaining_time": "0:14:28", "throughput": 1032.92, "total_tokens": 6033312} {"current_steps": 67000, "total_steps": 76960, "loss": 0.4116, "lr": 2.5084211946048654e-06, "epoch": 17.41164241164241, "percentage": 87.06, "elapsed_time": "1:37:21", "remaining_time": "0:14:28", "throughput": 1032.92, "total_tokens": 6033744} {"current_steps": 67005, "total_steps": 76960, "loss": 0.1083, "lr": 2.5059465128973198e-06, "epoch": 17.412941787941786, "percentage": 87.06, "elapsed_time": "1:37:21", "remaining_time": "0:14:27", "throughput": 1032.92, "total_tokens": 6034176} {"current_steps": 67010, "total_steps": 76960, "loss": 0.0688, "lr": 2.503472988080502e-06, "epoch": 17.414241164241165, "percentage": 87.07, "elapsed_time": "1:37:22", "remaining_time": "0:14:27", "throughput": 1032.93, "total_tokens": 6034656} {"current_steps": 67015, "total_steps": 76960, "loss": 0.0549, "lr": 2.501000620281621e-06, "epoch": 17.41554054054054, "percentage": 87.08, "elapsed_time": "1:37:22", "remaining_time": "0:14:27", "throughput": 1032.94, "total_tokens": 6035120} {"current_steps": 67020, "total_steps": 76960, "loss": 0.4072, "lr": 2.498529409627842e-06, "epoch": 17.416839916839916, "percentage": 87.08, "elapsed_time": "1:37:23", "remaining_time": "0:14:26", "throughput": 1032.94, "total_tokens": 6035584} {"current_steps": 67025, "total_steps": 76960, "loss": 0.0008, "lr": 2.49605935624625e-06, "epoch": 17.418139293139294, "percentage": 87.09, "elapsed_time": "1:37:23", "remaining_time": "0:14:26", "throughput": 1032.96, "total_tokens": 6036080} {"current_steps": 67030, "total_steps": 76960, "loss": 0.3493, "lr": 2.493590460263892e-06, "epoch": 17.41943866943867, "percentage": 87.1, "elapsed_time": "1:37:23", "remaining_time": "0:14:25", "throughput": 1032.95, "total_tokens": 6036480} {"current_steps": 67035, "total_steps": 76960, "loss": 0.0006, "lr": 2.49112272180774e-06, "epoch": 17.420738045738045, "percentage": 87.1, "elapsed_time": "1:37:24", "remaining_time": "0:14:25", "throughput": 1032.96, "total_tokens": 6036944} {"current_steps": 67040, "total_steps": 76960, "loss": 0.1565, "lr": 2.4886561410047053e-06, "epoch": 17.422037422037423, "percentage": 87.11, "elapsed_time": "1:37:24", "remaining_time": "0:14:24", "throughput": 1032.96, "total_tokens": 6037392} {"current_steps": 67045, "total_steps": 76960, "loss": 0.081, "lr": 2.486190717981665e-06, "epoch": 17.4233367983368, "percentage": 87.12, "elapsed_time": "1:37:25", "remaining_time": "0:14:24", "throughput": 1032.96, "total_tokens": 6037840} {"current_steps": 67050, "total_steps": 76960, "loss": 0.007, "lr": 2.4837264528654007e-06, "epoch": 17.424636174636174, "percentage": 87.12, "elapsed_time": "1:37:25", "remaining_time": "0:14:23", "throughput": 1032.96, "total_tokens": 6038256} {"current_steps": 67055, "total_steps": 76960, "loss": 0.1238, "lr": 2.4812633457826667e-06, "epoch": 17.425935550935552, "percentage": 87.13, "elapsed_time": "1:37:26", "remaining_time": "0:14:23", "throughput": 1032.96, "total_tokens": 6038688} {"current_steps": 67060, "total_steps": 76960, "loss": 0.6794, "lr": 2.478801396860128e-06, "epoch": 17.427234927234927, "percentage": 87.14, "elapsed_time": "1:37:26", "remaining_time": "0:14:23", "throughput": 1032.96, "total_tokens": 6039136} {"current_steps": 67065, "total_steps": 76960, "loss": 0.0045, "lr": 2.476340606224417e-06, "epoch": 17.428534303534303, "percentage": 87.14, "elapsed_time": "1:37:26", "remaining_time": "0:14:22", "throughput": 1032.97, "total_tokens": 6039632} {"current_steps": 67070, "total_steps": 76960, "loss": 0.0092, "lr": 2.473880974002088e-06, "epoch": 17.42983367983368, "percentage": 87.15, "elapsed_time": "1:37:27", "remaining_time": "0:14:22", "throughput": 1032.98, "total_tokens": 6040080} {"current_steps": 67075, "total_steps": 76960, "loss": 0.0574, "lr": 2.4714225003196423e-06, "epoch": 17.431133056133056, "percentage": 87.16, "elapsed_time": "1:37:27", "remaining_time": "0:14:21", "throughput": 1032.97, "total_tokens": 6040496} {"current_steps": 67080, "total_steps": 76960, "loss": 0.034, "lr": 2.4689651853035205e-06, "epoch": 17.43243243243243, "percentage": 87.16, "elapsed_time": "1:37:28", "remaining_time": "0:14:21", "throughput": 1032.98, "total_tokens": 6040944} {"current_steps": 67085, "total_steps": 76960, "loss": 0.0023, "lr": 2.4665090290801162e-06, "epoch": 17.43373180873181, "percentage": 87.17, "elapsed_time": "1:37:28", "remaining_time": "0:14:20", "throughput": 1032.98, "total_tokens": 6041376} {"current_steps": 67090, "total_steps": 76960, "loss": 0.0002, "lr": 2.4640540317757365e-06, "epoch": 17.435031185031185, "percentage": 87.18, "elapsed_time": "1:37:28", "remaining_time": "0:14:20", "throughput": 1032.98, "total_tokens": 6041808} {"current_steps": 67095, "total_steps": 76960, "loss": 0.0086, "lr": 2.4616001935166554e-06, "epoch": 17.43633056133056, "percentage": 87.18, "elapsed_time": "1:37:29", "remaining_time": "0:14:20", "throughput": 1032.98, "total_tokens": 6042272} {"current_steps": 67100, "total_steps": 76960, "loss": 0.0012, "lr": 2.4591475144290722e-06, "epoch": 17.43762993762994, "percentage": 87.19, "elapsed_time": "1:37:29", "remaining_time": "0:14:19", "throughput": 1032.98, "total_tokens": 6042704} {"current_steps": 67105, "total_steps": 76960, "loss": 0.0031, "lr": 2.4566959946391243e-06, "epoch": 17.438929313929314, "percentage": 87.19, "elapsed_time": "1:37:30", "remaining_time": "0:14:19", "throughput": 1032.99, "total_tokens": 6043184} {"current_steps": 67110, "total_steps": 76960, "loss": 0.1695, "lr": 2.4542456342729033e-06, "epoch": 17.44022869022869, "percentage": 87.2, "elapsed_time": "1:37:30", "remaining_time": "0:14:18", "throughput": 1033.0, "total_tokens": 6043632} {"current_steps": 67115, "total_steps": 76960, "loss": 0.0105, "lr": 2.4517964334564297e-06, "epoch": 17.441528066528065, "percentage": 87.21, "elapsed_time": "1:37:31", "remaining_time": "0:14:18", "throughput": 1033.0, "total_tokens": 6044112} {"current_steps": 67120, "total_steps": 76960, "loss": 0.2709, "lr": 2.449348392315676e-06, "epoch": 17.442827442827443, "percentage": 87.21, "elapsed_time": "1:37:31", "remaining_time": "0:14:17", "throughput": 1033.0, "total_tokens": 6044544} {"current_steps": 67125, "total_steps": 76960, "loss": 0.0218, "lr": 2.4469015109765345e-06, "epoch": 17.44412681912682, "percentage": 87.22, "elapsed_time": "1:37:31", "remaining_time": "0:14:17", "throughput": 1033.01, "total_tokens": 6045008} {"current_steps": 67130, "total_steps": 76960, "loss": 0.202, "lr": 2.4444557895648643e-06, "epoch": 17.445426195426194, "percentage": 87.23, "elapsed_time": "1:37:32", "remaining_time": "0:14:16", "throughput": 1033.01, "total_tokens": 6045440} {"current_steps": 67135, "total_steps": 76960, "loss": 0.1413, "lr": 2.4420112282064394e-06, "epoch": 17.446725571725572, "percentage": 87.23, "elapsed_time": "1:37:32", "remaining_time": "0:14:16", "throughput": 1033.01, "total_tokens": 6045856} {"current_steps": 67140, "total_steps": 76960, "loss": 0.0417, "lr": 2.439567827026995e-06, "epoch": 17.448024948024948, "percentage": 87.24, "elapsed_time": "1:37:33", "remaining_time": "0:14:16", "throughput": 1033.01, "total_tokens": 6046320} {"current_steps": 67145, "total_steps": 76960, "loss": 0.0142, "lr": 2.4371255861521917e-06, "epoch": 17.449324324324323, "percentage": 87.25, "elapsed_time": "1:37:33", "remaining_time": "0:14:15", "throughput": 1033.02, "total_tokens": 6046784} {"current_steps": 67150, "total_steps": 76960, "loss": 0.0396, "lr": 2.4346845057076352e-06, "epoch": 17.4506237006237, "percentage": 87.25, "elapsed_time": "1:37:33", "remaining_time": "0:14:15", "throughput": 1033.02, "total_tokens": 6047200} {"current_steps": 67155, "total_steps": 76960, "loss": 0.2186, "lr": 2.4322445858188768e-06, "epoch": 17.451923076923077, "percentage": 87.26, "elapsed_time": "1:37:34", "remaining_time": "0:14:14", "throughput": 1033.02, "total_tokens": 6047648} {"current_steps": 67160, "total_steps": 76960, "loss": 0.0157, "lr": 2.429805826611409e-06, "epoch": 17.453222453222452, "percentage": 87.27, "elapsed_time": "1:37:34", "remaining_time": "0:14:14", "throughput": 1033.02, "total_tokens": 6048080} {"current_steps": 67165, "total_steps": 76960, "loss": 0.0157, "lr": 2.4273682282106467e-06, "epoch": 17.45452182952183, "percentage": 87.27, "elapsed_time": "1:37:35", "remaining_time": "0:14:13", "throughput": 1033.02, "total_tokens": 6048528} {"current_steps": 67170, "total_steps": 76960, "loss": 0.0128, "lr": 2.424931790741969e-06, "epoch": 17.455821205821206, "percentage": 87.28, "elapsed_time": "1:37:35", "remaining_time": "0:14:13", "throughput": 1033.03, "total_tokens": 6048976} {"current_steps": 67175, "total_steps": 76960, "loss": 0.2894, "lr": 2.42249651433068e-06, "epoch": 17.45712058212058, "percentage": 87.29, "elapsed_time": "1:37:35", "remaining_time": "0:14:13", "throughput": 1033.03, "total_tokens": 6049424} {"current_steps": 67180, "total_steps": 76960, "loss": 0.1292, "lr": 2.4200623991020243e-06, "epoch": 17.45841995841996, "percentage": 87.29, "elapsed_time": "1:37:36", "remaining_time": "0:14:12", "throughput": 1033.04, "total_tokens": 6049904} {"current_steps": 67185, "total_steps": 76960, "loss": 0.0285, "lr": 2.417629445181194e-06, "epoch": 17.459719334719335, "percentage": 87.3, "elapsed_time": "1:37:36", "remaining_time": "0:14:12", "throughput": 1033.04, "total_tokens": 6050352} {"current_steps": 67190, "total_steps": 76960, "loss": 0.055, "lr": 2.4151976526933157e-06, "epoch": 17.46101871101871, "percentage": 87.31, "elapsed_time": "1:37:37", "remaining_time": "0:14:11", "throughput": 1033.04, "total_tokens": 6050784} {"current_steps": 67195, "total_steps": 76960, "loss": 0.122, "lr": 2.4127670217634707e-06, "epoch": 17.46231808731809, "percentage": 87.31, "elapsed_time": "1:37:37", "remaining_time": "0:14:11", "throughput": 1033.05, "total_tokens": 6051232} {"current_steps": 67200, "total_steps": 76960, "loss": 0.2377, "lr": 2.410337552516653e-06, "epoch": 17.463617463617464, "percentage": 87.32, "elapsed_time": "1:37:38", "remaining_time": "0:14:10", "throughput": 1033.05, "total_tokens": 6051664} {"current_steps": 67205, "total_steps": 76960, "loss": 0.0126, "lr": 2.4079092450778244e-06, "epoch": 17.46491683991684, "percentage": 87.32, "elapsed_time": "1:37:38", "remaining_time": "0:14:10", "throughput": 1033.05, "total_tokens": 6052128} {"current_steps": 67210, "total_steps": 76960, "loss": 0.0659, "lr": 2.405482099571865e-06, "epoch": 17.466216216216218, "percentage": 87.33, "elapsed_time": "1:37:38", "remaining_time": "0:14:09", "throughput": 1033.05, "total_tokens": 6052560} {"current_steps": 67215, "total_steps": 76960, "loss": 0.1794, "lr": 2.4030561161236172e-06, "epoch": 17.467515592515593, "percentage": 87.34, "elapsed_time": "1:37:39", "remaining_time": "0:14:09", "throughput": 1033.06, "total_tokens": 6053040} {"current_steps": 67220, "total_steps": 76960, "loss": 0.0014, "lr": 2.4006312948578387e-06, "epoch": 17.468814968814968, "percentage": 87.34, "elapsed_time": "1:37:39", "remaining_time": "0:14:09", "throughput": 1033.06, "total_tokens": 6053456} {"current_steps": 67225, "total_steps": 76960, "loss": 0.2788, "lr": 2.398207635899244e-06, "epoch": 17.470114345114347, "percentage": 87.35, "elapsed_time": "1:37:40", "remaining_time": "0:14:08", "throughput": 1033.06, "total_tokens": 6053904} {"current_steps": 67230, "total_steps": 76960, "loss": 0.0126, "lr": 2.395785139372489e-06, "epoch": 17.47141372141372, "percentage": 87.36, "elapsed_time": "1:37:40", "remaining_time": "0:14:08", "throughput": 1033.07, "total_tokens": 6054368} {"current_steps": 67235, "total_steps": 76960, "loss": 0.1461, "lr": 2.3933638054021654e-06, "epoch": 17.472713097713097, "percentage": 87.36, "elapsed_time": "1:37:40", "remaining_time": "0:14:07", "throughput": 1033.08, "total_tokens": 6054848} {"current_steps": 67240, "total_steps": 76960, "loss": 0.0007, "lr": 2.390943634112805e-06, "epoch": 17.474012474012476, "percentage": 87.37, "elapsed_time": "1:37:41", "remaining_time": "0:14:07", "throughput": 1033.08, "total_tokens": 6055296} {"current_steps": 67245, "total_steps": 76960, "loss": 0.0002, "lr": 2.3885246256288685e-06, "epoch": 17.47531185031185, "percentage": 87.38, "elapsed_time": "1:37:41", "remaining_time": "0:14:06", "throughput": 1033.08, "total_tokens": 6055744} {"current_steps": 67250, "total_steps": 76960, "loss": 0.1904, "lr": 2.3861067800747845e-06, "epoch": 17.476611226611226, "percentage": 87.38, "elapsed_time": "1:37:42", "remaining_time": "0:14:06", "throughput": 1033.08, "total_tokens": 6056160} {"current_steps": 67255, "total_steps": 76960, "loss": 0.0382, "lr": 2.3836900975748894e-06, "epoch": 17.477910602910605, "percentage": 87.39, "elapsed_time": "1:37:42", "remaining_time": "0:14:05", "throughput": 1033.09, "total_tokens": 6056624} {"current_steps": 67260, "total_steps": 76960, "loss": 0.0006, "lr": 2.3812745782534813e-06, "epoch": 17.47920997920998, "percentage": 87.4, "elapsed_time": "1:37:43", "remaining_time": "0:14:05", "throughput": 1033.09, "total_tokens": 6057056} {"current_steps": 67265, "total_steps": 76960, "loss": 0.2226, "lr": 2.378860222234794e-06, "epoch": 17.480509355509355, "percentage": 87.4, "elapsed_time": "1:37:43", "remaining_time": "0:14:05", "throughput": 1033.1, "total_tokens": 6057552} {"current_steps": 67270, "total_steps": 76960, "loss": 0.3281, "lr": 2.3764470296430056e-06, "epoch": 17.48180873180873, "percentage": 87.41, "elapsed_time": "1:37:43", "remaining_time": "0:14:04", "throughput": 1033.1, "total_tokens": 6058016} {"current_steps": 67275, "total_steps": 76960, "loss": 0.1786, "lr": 2.3740350006022175e-06, "epoch": 17.48310810810811, "percentage": 87.42, "elapsed_time": "1:37:44", "remaining_time": "0:14:04", "throughput": 1033.1, "total_tokens": 6058432} {"current_steps": 67280, "total_steps": 76960, "loss": 0.0001, "lr": 2.371624135236497e-06, "epoch": 17.484407484407484, "percentage": 87.42, "elapsed_time": "1:37:44", "remaining_time": "0:14:03", "throughput": 1033.1, "total_tokens": 6058848} {"current_steps": 67285, "total_steps": 76960, "loss": 0.0587, "lr": 2.3692144336698195e-06, "epoch": 17.48570686070686, "percentage": 87.43, "elapsed_time": "1:37:45", "remaining_time": "0:14:03", "throughput": 1033.1, "total_tokens": 6059296} {"current_steps": 67290, "total_steps": 76960, "loss": 0.0299, "lr": 2.3668058960261307e-06, "epoch": 17.487006237006238, "percentage": 87.44, "elapsed_time": "1:37:45", "remaining_time": "0:14:02", "throughput": 1033.1, "total_tokens": 6059744} {"current_steps": 67295, "total_steps": 76960, "loss": 0.0041, "lr": 2.364398522429298e-06, "epoch": 17.488305613305613, "percentage": 87.44, "elapsed_time": "1:37:45", "remaining_time": "0:14:02", "throughput": 1033.11, "total_tokens": 6060208} {"current_steps": 67300, "total_steps": 76960, "loss": 0.2851, "lr": 2.3619923130031446e-06, "epoch": 17.489604989604988, "percentage": 87.45, "elapsed_time": "1:37:46", "remaining_time": "0:14:02", "throughput": 1033.11, "total_tokens": 6060640} {"current_steps": 67305, "total_steps": 76960, "loss": 0.0038, "lr": 2.359587267871416e-06, "epoch": 17.490904365904367, "percentage": 87.45, "elapsed_time": "1:37:46", "remaining_time": "0:14:01", "throughput": 1033.11, "total_tokens": 6061056} {"current_steps": 67310, "total_steps": 76960, "loss": 0.0762, "lr": 2.357183387157802e-06, "epoch": 17.492203742203742, "percentage": 87.46, "elapsed_time": "1:37:47", "remaining_time": "0:14:01", "throughput": 1033.11, "total_tokens": 6061520} {"current_steps": 67315, "total_steps": 76960, "loss": 0.59, "lr": 2.3547806709859483e-06, "epoch": 17.493503118503117, "percentage": 87.47, "elapsed_time": "1:37:47", "remaining_time": "0:14:00", "throughput": 1033.12, "total_tokens": 6061968} {"current_steps": 67320, "total_steps": 76960, "loss": 0.0037, "lr": 2.352379119479417e-06, "epoch": 17.494802494802496, "percentage": 87.47, "elapsed_time": "1:37:48", "remaining_time": "0:14:00", "throughput": 1033.12, "total_tokens": 6062400} {"current_steps": 67325, "total_steps": 76960, "loss": 0.1064, "lr": 2.349978732761726e-06, "epoch": 17.49610187110187, "percentage": 87.48, "elapsed_time": "1:37:48", "remaining_time": "0:13:59", "throughput": 1033.12, "total_tokens": 6062832} {"current_steps": 67330, "total_steps": 76960, "loss": 0.7247, "lr": 2.3475795109563326e-06, "epoch": 17.497401247401246, "percentage": 87.49, "elapsed_time": "1:37:48", "remaining_time": "0:13:59", "throughput": 1033.11, "total_tokens": 6063248} {"current_steps": 67335, "total_steps": 76960, "loss": 0.0945, "lr": 2.3451814541866317e-06, "epoch": 17.498700623700625, "percentage": 87.49, "elapsed_time": "1:37:49", "remaining_time": "0:13:58", "throughput": 1033.13, "total_tokens": 6063760} {"current_steps": 67340, "total_steps": 76960, "loss": 0.0575, "lr": 2.342784562575953e-06, "epoch": 17.5, "percentage": 87.5, "elapsed_time": "1:37:49", "remaining_time": "0:13:58", "throughput": 1033.14, "total_tokens": 6064240} {"current_steps": 67345, "total_steps": 76960, "loss": 0.0032, "lr": 2.3403888362475782e-06, "epoch": 17.501299376299375, "percentage": 87.51, "elapsed_time": "1:37:50", "remaining_time": "0:13:58", "throughput": 1033.14, "total_tokens": 6064704} {"current_steps": 67350, "total_steps": 76960, "loss": 0.0175, "lr": 2.3379942753247118e-06, "epoch": 17.502598752598754, "percentage": 87.51, "elapsed_time": "1:37:50", "remaining_time": "0:13:57", "throughput": 1033.15, "total_tokens": 6065168} {"current_steps": 67355, "total_steps": 76960, "loss": 0.1806, "lr": 2.335600879930516e-06, "epoch": 17.50389812889813, "percentage": 87.52, "elapsed_time": "1:37:50", "remaining_time": "0:13:57", "throughput": 1033.15, "total_tokens": 6065632} {"current_steps": 67360, "total_steps": 76960, "loss": 0.2095, "lr": 2.3332086501880818e-06, "epoch": 17.505197505197504, "percentage": 87.53, "elapsed_time": "1:37:51", "remaining_time": "0:13:56", "throughput": 1033.16, "total_tokens": 6066080} {"current_steps": 67365, "total_steps": 76960, "loss": 0.0097, "lr": 2.3308175862204435e-06, "epoch": 17.506496881496883, "percentage": 87.53, "elapsed_time": "1:37:51", "remaining_time": "0:13:56", "throughput": 1033.16, "total_tokens": 6066528} {"current_steps": 67370, "total_steps": 76960, "loss": 0.183, "lr": 2.3284276881505805e-06, "epoch": 17.507796257796258, "percentage": 87.54, "elapsed_time": "1:37:52", "remaining_time": "0:13:55", "throughput": 1033.16, "total_tokens": 6066960} {"current_steps": 67375, "total_steps": 76960, "loss": 0.0106, "lr": 2.3260389561014035e-06, "epoch": 17.509095634095633, "percentage": 87.55, "elapsed_time": "1:37:52", "remaining_time": "0:13:55", "throughput": 1033.16, "total_tokens": 6067408} {"current_steps": 67380, "total_steps": 76960, "loss": 0.0646, "lr": 2.323651390195769e-06, "epoch": 17.510395010395012, "percentage": 87.55, "elapsed_time": "1:37:53", "remaining_time": "0:13:55", "throughput": 1033.17, "total_tokens": 6067856} {"current_steps": 67385, "total_steps": 76960, "loss": 0.0103, "lr": 2.321264990556468e-06, "epoch": 17.511694386694387, "percentage": 87.56, "elapsed_time": "1:37:53", "remaining_time": "0:13:54", "throughput": 1033.17, "total_tokens": 6068304} {"current_steps": 67390, "total_steps": 76960, "loss": 0.1071, "lr": 2.3188797573062415e-06, "epoch": 17.512993762993762, "percentage": 87.56, "elapsed_time": "1:37:53", "remaining_time": "0:13:54", "throughput": 1033.18, "total_tokens": 6068768} {"current_steps": 67395, "total_steps": 76960, "loss": 0.0072, "lr": 2.3164956905677577e-06, "epoch": 17.51429313929314, "percentage": 87.57, "elapsed_time": "1:37:54", "remaining_time": "0:13:53", "throughput": 1033.19, "total_tokens": 6069264} {"current_steps": 67400, "total_steps": 76960, "loss": 0.3551, "lr": 2.314112790463635e-06, "epoch": 17.515592515592516, "percentage": 87.58, "elapsed_time": "1:37:54", "remaining_time": "0:13:53", "throughput": 1033.2, "total_tokens": 6069744} {"current_steps": 67405, "total_steps": 76960, "loss": 0.3339, "lr": 2.3117310571164286e-06, "epoch": 17.51689189189189, "percentage": 87.58, "elapsed_time": "1:37:55", "remaining_time": "0:13:52", "throughput": 1033.2, "total_tokens": 6070192} {"current_steps": 67410, "total_steps": 76960, "loss": 0.0087, "lr": 2.3093504906486346e-06, "epoch": 17.518191268191266, "percentage": 87.59, "elapsed_time": "1:37:55", "remaining_time": "0:13:52", "throughput": 1033.21, "total_tokens": 6070656} {"current_steps": 67415, "total_steps": 76960, "loss": 0.5009, "lr": 2.306971091182686e-06, "epoch": 17.519490644490645, "percentage": 87.6, "elapsed_time": "1:37:55", "remaining_time": "0:13:51", "throughput": 1033.21, "total_tokens": 6071104} {"current_steps": 67420, "total_steps": 76960, "loss": 0.2149, "lr": 2.3045928588409594e-06, "epoch": 17.52079002079002, "percentage": 87.6, "elapsed_time": "1:37:56", "remaining_time": "0:13:51", "throughput": 1033.22, "total_tokens": 6071600} {"current_steps": 67425, "total_steps": 76960, "loss": 0.01, "lr": 2.3022157937457627e-06, "epoch": 17.522089397089395, "percentage": 87.61, "elapsed_time": "1:37:56", "remaining_time": "0:13:51", "throughput": 1033.22, "total_tokens": 6072032} {"current_steps": 67430, "total_steps": 76960, "loss": 0.4353, "lr": 2.2998398960193597e-06, "epoch": 17.523388773388774, "percentage": 87.62, "elapsed_time": "1:37:57", "remaining_time": "0:13:50", "throughput": 1033.22, "total_tokens": 6072448} {"current_steps": 67435, "total_steps": 76960, "loss": 0.3605, "lr": 2.297465165783938e-06, "epoch": 17.52468814968815, "percentage": 87.62, "elapsed_time": "1:37:57", "remaining_time": "0:13:50", "throughput": 1033.23, "total_tokens": 6072928} {"current_steps": 67440, "total_steps": 76960, "loss": 0.0009, "lr": 2.2950916031616338e-06, "epoch": 17.525987525987524, "percentage": 87.63, "elapsed_time": "1:37:58", "remaining_time": "0:13:49", "throughput": 1033.23, "total_tokens": 6073392} {"current_steps": 67445, "total_steps": 76960, "loss": 0.0079, "lr": 2.2927192082745296e-06, "epoch": 17.527286902286903, "percentage": 87.64, "elapsed_time": "1:37:58", "remaining_time": "0:13:49", "throughput": 1033.24, "total_tokens": 6073872} {"current_steps": 67450, "total_steps": 76960, "loss": 0.0715, "lr": 2.2903479812446284e-06, "epoch": 17.52858627858628, "percentage": 87.64, "elapsed_time": "1:37:58", "remaining_time": "0:13:48", "throughput": 1033.24, "total_tokens": 6074320} {"current_steps": 67455, "total_steps": 76960, "loss": 0.0002, "lr": 2.2879779221938957e-06, "epoch": 17.529885654885653, "percentage": 87.65, "elapsed_time": "1:37:59", "remaining_time": "0:13:48", "throughput": 1033.24, "total_tokens": 6074752} {"current_steps": 67460, "total_steps": 76960, "loss": 0.4782, "lr": 2.2856090312442123e-06, "epoch": 17.531185031185032, "percentage": 87.66, "elapsed_time": "1:37:59", "remaining_time": "0:13:48", "throughput": 1033.25, "total_tokens": 6075232} {"current_steps": 67465, "total_steps": 76960, "loss": 0.0313, "lr": 2.2832413085174282e-06, "epoch": 17.532484407484407, "percentage": 87.66, "elapsed_time": "1:38:00", "remaining_time": "0:13:47", "throughput": 1033.26, "total_tokens": 6075696} {"current_steps": 67470, "total_steps": 76960, "loss": 0.207, "lr": 2.2808747541353035e-06, "epoch": 17.533783783783782, "percentage": 87.67, "elapsed_time": "1:38:00", "remaining_time": "0:13:47", "throughput": 1033.26, "total_tokens": 6076144} {"current_steps": 67475, "total_steps": 76960, "loss": 0.0105, "lr": 2.2785093682195585e-06, "epoch": 17.53508316008316, "percentage": 87.68, "elapsed_time": "1:38:00", "remaining_time": "0:13:46", "throughput": 1033.26, "total_tokens": 6076544} {"current_steps": 67480, "total_steps": 76960, "loss": 0.0245, "lr": 2.276145150891848e-06, "epoch": 17.536382536382536, "percentage": 87.68, "elapsed_time": "1:38:01", "remaining_time": "0:13:46", "throughput": 1033.26, "total_tokens": 6076992} {"current_steps": 67485, "total_steps": 76960, "loss": 0.177, "lr": 2.2737821022737693e-06, "epoch": 17.53768191268191, "percentage": 87.69, "elapsed_time": "1:38:01", "remaining_time": "0:13:45", "throughput": 1033.26, "total_tokens": 6077424} {"current_steps": 67490, "total_steps": 76960, "loss": 0.0301, "lr": 2.2714202224868477e-06, "epoch": 17.53898128898129, "percentage": 87.69, "elapsed_time": "1:38:02", "remaining_time": "0:13:45", "throughput": 1033.26, "total_tokens": 6077872} {"current_steps": 67495, "total_steps": 76960, "loss": 0.1027, "lr": 2.2690595116525688e-06, "epoch": 17.540280665280665, "percentage": 87.7, "elapsed_time": "1:38:02", "remaining_time": "0:13:44", "throughput": 1033.26, "total_tokens": 6078304} {"current_steps": 67500, "total_steps": 76960, "loss": 0.1361, "lr": 2.2666999698923357e-06, "epoch": 17.54158004158004, "percentage": 87.71, "elapsed_time": "1:38:03", "remaining_time": "0:13:44", "throughput": 1033.26, "total_tokens": 6078736} {"current_steps": 67505, "total_steps": 76960, "loss": 0.0801, "lr": 2.2643415973275016e-06, "epoch": 17.54287941787942, "percentage": 87.71, "elapsed_time": "1:38:03", "remaining_time": "0:13:44", "throughput": 1033.27, "total_tokens": 6079184} {"current_steps": 67510, "total_steps": 76960, "loss": 0.002, "lr": 2.261984394079364e-06, "epoch": 17.544178794178794, "percentage": 87.72, "elapsed_time": "1:38:03", "remaining_time": "0:13:43", "throughput": 1033.26, "total_tokens": 6079600} {"current_steps": 67515, "total_steps": 76960, "loss": 0.4299, "lr": 2.259628360269153e-06, "epoch": 17.54547817047817, "percentage": 87.73, "elapsed_time": "1:38:04", "remaining_time": "0:13:43", "throughput": 1033.27, "total_tokens": 6080048} {"current_steps": 67520, "total_steps": 76960, "loss": 0.0726, "lr": 2.2572734960180502e-06, "epoch": 17.546777546777548, "percentage": 87.73, "elapsed_time": "1:38:04", "remaining_time": "0:13:42", "throughput": 1033.26, "total_tokens": 6080464} {"current_steps": 67525, "total_steps": 76960, "loss": 0.0224, "lr": 2.2549198014471584e-06, "epoch": 17.548076923076923, "percentage": 87.74, "elapsed_time": "1:38:05", "remaining_time": "0:13:42", "throughput": 1033.26, "total_tokens": 6080896} {"current_steps": 67530, "total_steps": 76960, "loss": 0.0033, "lr": 2.2525672766775392e-06, "epoch": 17.5493762993763, "percentage": 87.75, "elapsed_time": "1:38:05", "remaining_time": "0:13:41", "throughput": 1033.27, "total_tokens": 6081344} {"current_steps": 67535, "total_steps": 76960, "loss": 0.0118, "lr": 2.250215921830176e-06, "epoch": 17.550675675675677, "percentage": 87.75, "elapsed_time": "1:38:05", "remaining_time": "0:13:41", "throughput": 1033.27, "total_tokens": 6081792} {"current_steps": 67540, "total_steps": 76960, "loss": 0.004, "lr": 2.247865737026006e-06, "epoch": 17.551975051975052, "percentage": 87.76, "elapsed_time": "1:38:06", "remaining_time": "0:13:40", "throughput": 1033.27, "total_tokens": 6082240} {"current_steps": 67545, "total_steps": 76960, "loss": 0.0009, "lr": 2.2455167223859012e-06, "epoch": 17.553274428274428, "percentage": 87.77, "elapsed_time": "1:38:06", "remaining_time": "0:13:40", "throughput": 1033.28, "total_tokens": 6082720} {"current_steps": 67550, "total_steps": 76960, "loss": 0.2265, "lr": 2.243168878030677e-06, "epoch": 17.554573804573806, "percentage": 87.77, "elapsed_time": "1:38:07", "remaining_time": "0:13:40", "throughput": 1033.28, "total_tokens": 6083136} {"current_steps": 67555, "total_steps": 76960, "loss": 0.0166, "lr": 2.240822204081078e-06, "epoch": 17.55587318087318, "percentage": 87.78, "elapsed_time": "1:38:07", "remaining_time": "0:13:39", "throughput": 1033.28, "total_tokens": 6083568} {"current_steps": 67560, "total_steps": 76960, "loss": 0.3695, "lr": 2.2384767006578045e-06, "epoch": 17.557172557172557, "percentage": 87.79, "elapsed_time": "1:38:08", "remaining_time": "0:13:39", "throughput": 1033.29, "total_tokens": 6084048} {"current_steps": 67565, "total_steps": 76960, "loss": 0.1795, "lr": 2.236132367881483e-06, "epoch": 17.558471933471935, "percentage": 87.79, "elapsed_time": "1:38:08", "remaining_time": "0:13:38", "throughput": 1033.29, "total_tokens": 6084512} {"current_steps": 67570, "total_steps": 76960, "loss": 0.0102, "lr": 2.2337892058726826e-06, "epoch": 17.55977130977131, "percentage": 87.8, "elapsed_time": "1:38:08", "remaining_time": "0:13:38", "throughput": 1033.3, "total_tokens": 6084992} {"current_steps": 67575, "total_steps": 76960, "loss": 0.4288, "lr": 2.231447214751914e-06, "epoch": 17.561070686070686, "percentage": 87.81, "elapsed_time": "1:38:09", "remaining_time": "0:13:37", "throughput": 1033.31, "total_tokens": 6085440} {"current_steps": 67580, "total_steps": 76960, "loss": 0.0166, "lr": 2.2291063946396324e-06, "epoch": 17.56237006237006, "percentage": 87.81, "elapsed_time": "1:38:09", "remaining_time": "0:13:37", "throughput": 1033.31, "total_tokens": 6085872} {"current_steps": 67585, "total_steps": 76960, "loss": 0.0045, "lr": 2.2267667456562307e-06, "epoch": 17.56366943866944, "percentage": 87.82, "elapsed_time": "1:38:10", "remaining_time": "0:13:37", "throughput": 1033.31, "total_tokens": 6086336} {"current_steps": 67590, "total_steps": 76960, "loss": 0.0691, "lr": 2.2244282679220326e-06, "epoch": 17.564968814968815, "percentage": 87.82, "elapsed_time": "1:38:10", "remaining_time": "0:13:36", "throughput": 1033.31, "total_tokens": 6086768} {"current_steps": 67595, "total_steps": 76960, "loss": 0.1136, "lr": 2.2220909615573134e-06, "epoch": 17.56626819126819, "percentage": 87.83, "elapsed_time": "1:38:10", "remaining_time": "0:13:36", "throughput": 1033.32, "total_tokens": 6087232} {"current_steps": 67600, "total_steps": 76960, "loss": 0.0256, "lr": 2.219754826682277e-06, "epoch": 17.56756756756757, "percentage": 87.84, "elapsed_time": "1:38:11", "remaining_time": "0:13:35", "throughput": 1033.32, "total_tokens": 6087680} {"current_steps": 67605, "total_steps": 76960, "loss": 0.0009, "lr": 2.2174198634170836e-06, "epoch": 17.568866943866944, "percentage": 87.84, "elapsed_time": "1:38:11", "remaining_time": "0:13:35", "throughput": 1033.32, "total_tokens": 6088096} {"current_steps": 67610, "total_steps": 76960, "loss": 0.3331, "lr": 2.2150860718818085e-06, "epoch": 17.57016632016632, "percentage": 87.85, "elapsed_time": "1:38:12", "remaining_time": "0:13:34", "throughput": 1033.32, "total_tokens": 6088544} {"current_steps": 67615, "total_steps": 76960, "loss": 0.4045, "lr": 2.212753452196489e-06, "epoch": 17.571465696465697, "percentage": 87.86, "elapsed_time": "1:38:12", "remaining_time": "0:13:34", "throughput": 1033.33, "total_tokens": 6088992} {"current_steps": 67620, "total_steps": 76960, "loss": 0.2728, "lr": 2.210422004481094e-06, "epoch": 17.572765072765073, "percentage": 87.86, "elapsed_time": "1:38:13", "remaining_time": "0:13:33", "throughput": 1033.33, "total_tokens": 6089456} {"current_steps": 67625, "total_steps": 76960, "loss": 0.068, "lr": 2.208091728855535e-06, "epoch": 17.574064449064448, "percentage": 87.87, "elapsed_time": "1:38:13", "remaining_time": "0:13:33", "throughput": 1033.33, "total_tokens": 6089904} {"current_steps": 67630, "total_steps": 76960, "loss": 0.2122, "lr": 2.205762625439656e-06, "epoch": 17.575363825363826, "percentage": 87.88, "elapsed_time": "1:38:13", "remaining_time": "0:13:33", "throughput": 1033.33, "total_tokens": 6090320} {"current_steps": 67635, "total_steps": 76960, "loss": 0.0348, "lr": 2.203434694353243e-06, "epoch": 17.5766632016632, "percentage": 87.88, "elapsed_time": "1:38:14", "remaining_time": "0:13:32", "throughput": 1033.33, "total_tokens": 6090768} {"current_steps": 67640, "total_steps": 76960, "loss": 0.0801, "lr": 2.201107935716029e-06, "epoch": 17.577962577962577, "percentage": 87.89, "elapsed_time": "1:38:14", "remaining_time": "0:13:32", "throughput": 1033.34, "total_tokens": 6091248} {"current_steps": 67645, "total_steps": 76960, "loss": 0.0484, "lr": 2.198782349647674e-06, "epoch": 17.579261954261955, "percentage": 87.9, "elapsed_time": "1:38:15", "remaining_time": "0:13:31", "throughput": 1033.34, "total_tokens": 6091664} {"current_steps": 67650, "total_steps": 76960, "loss": 0.0044, "lr": 2.1964579362677903e-06, "epoch": 17.58056133056133, "percentage": 87.9, "elapsed_time": "1:38:15", "remaining_time": "0:13:31", "throughput": 1033.35, "total_tokens": 6092128} {"current_steps": 67655, "total_steps": 76960, "loss": 0.2538, "lr": 2.194134695695926e-06, "epoch": 17.581860706860706, "percentage": 87.91, "elapsed_time": "1:38:15", "remaining_time": "0:13:30", "throughput": 1033.35, "total_tokens": 6092576} {"current_steps": 67660, "total_steps": 76960, "loss": 0.0491, "lr": 2.1918126280515678e-06, "epoch": 17.583160083160084, "percentage": 87.92, "elapsed_time": "1:38:16", "remaining_time": "0:13:30", "throughput": 1033.35, "total_tokens": 6093040} {"current_steps": 67665, "total_steps": 76960, "loss": 0.1935, "lr": 2.1894917334541354e-06, "epoch": 17.58445945945946, "percentage": 87.92, "elapsed_time": "1:38:16", "remaining_time": "0:13:30", "throughput": 1033.35, "total_tokens": 6093472} {"current_steps": 67670, "total_steps": 76960, "loss": 0.1366, "lr": 2.187172012023006e-06, "epoch": 17.585758835758835, "percentage": 87.93, "elapsed_time": "1:38:17", "remaining_time": "0:13:29", "throughput": 1033.36, "total_tokens": 6093904} {"current_steps": 67675, "total_steps": 76960, "loss": 0.2611, "lr": 2.184853463877473e-06, "epoch": 17.587058212058214, "percentage": 87.94, "elapsed_time": "1:38:17", "remaining_time": "0:13:29", "throughput": 1033.35, "total_tokens": 6094320} {"current_steps": 67680, "total_steps": 76960, "loss": 0.4198, "lr": 2.1825360891367884e-06, "epoch": 17.58835758835759, "percentage": 87.94, "elapsed_time": "1:38:18", "remaining_time": "0:13:28", "throughput": 1033.35, "total_tokens": 6094752} {"current_steps": 67685, "total_steps": 76960, "loss": 0.004, "lr": 2.1802198879201346e-06, "epoch": 17.589656964656964, "percentage": 87.95, "elapsed_time": "1:38:18", "remaining_time": "0:13:28", "throughput": 1033.36, "total_tokens": 6095200} {"current_steps": 67690, "total_steps": 76960, "loss": 0.0202, "lr": 2.1779048603466357e-06, "epoch": 17.590956340956343, "percentage": 87.95, "elapsed_time": "1:38:18", "remaining_time": "0:13:27", "throughput": 1033.36, "total_tokens": 6095632} {"current_steps": 67695, "total_steps": 76960, "loss": 0.3011, "lr": 2.17559100653536e-06, "epoch": 17.592255717255718, "percentage": 87.96, "elapsed_time": "1:38:19", "remaining_time": "0:13:27", "throughput": 1033.36, "total_tokens": 6096064} {"current_steps": 67700, "total_steps": 76960, "loss": 0.2668, "lr": 2.1732783266053045e-06, "epoch": 17.593555093555093, "percentage": 87.97, "elapsed_time": "1:38:19", "remaining_time": "0:13:26", "throughput": 1033.36, "total_tokens": 6096512} {"current_steps": 67705, "total_steps": 76960, "loss": 0.1882, "lr": 2.1709668206754215e-06, "epoch": 17.59485446985447, "percentage": 87.97, "elapsed_time": "1:38:20", "remaining_time": "0:13:26", "throughput": 1033.36, "total_tokens": 6096960} {"current_steps": 67710, "total_steps": 76960, "loss": 0.0421, "lr": 2.1686564888645816e-06, "epoch": 17.596153846153847, "percentage": 87.98, "elapsed_time": "1:38:20", "remaining_time": "0:13:26", "throughput": 1033.37, "total_tokens": 6097408} {"current_steps": 67715, "total_steps": 76960, "loss": 0.4744, "lr": 2.166347331291621e-06, "epoch": 17.597453222453222, "percentage": 87.99, "elapsed_time": "1:38:20", "remaining_time": "0:13:25", "throughput": 1033.37, "total_tokens": 6097872} {"current_steps": 67720, "total_steps": 76960, "loss": 0.0008, "lr": 2.164039348075292e-06, "epoch": 17.598752598752597, "percentage": 87.99, "elapsed_time": "1:38:21", "remaining_time": "0:13:25", "throughput": 1033.38, "total_tokens": 6098336} {"current_steps": 67725, "total_steps": 76960, "loss": 0.0435, "lr": 2.161732539334299e-06, "epoch": 17.600051975051976, "percentage": 88.0, "elapsed_time": "1:38:21", "remaining_time": "0:13:24", "throughput": 1033.39, "total_tokens": 6098816} {"current_steps": 67730, "total_steps": 76960, "loss": 0.0002, "lr": 2.1594269051872812e-06, "epoch": 17.60135135135135, "percentage": 88.01, "elapsed_time": "1:38:22", "remaining_time": "0:13:24", "throughput": 1033.39, "total_tokens": 6099248} {"current_steps": 67735, "total_steps": 76960, "loss": 0.004, "lr": 2.1571224457528294e-06, "epoch": 17.602650727650726, "percentage": 88.01, "elapsed_time": "1:38:22", "remaining_time": "0:13:23", "throughput": 1033.38, "total_tokens": 6099664} {"current_steps": 67740, "total_steps": 76960, "loss": 0.0068, "lr": 2.154819161149452e-06, "epoch": 17.603950103950105, "percentage": 88.02, "elapsed_time": "1:38:23", "remaining_time": "0:13:23", "throughput": 1033.38, "total_tokens": 6100096} {"current_steps": 67745, "total_steps": 76960, "loss": 0.0043, "lr": 2.15251705149562e-06, "epoch": 17.60524948024948, "percentage": 88.03, "elapsed_time": "1:38:23", "remaining_time": "0:13:23", "throughput": 1033.38, "total_tokens": 6100512} {"current_steps": 67750, "total_steps": 76960, "loss": 0.1468, "lr": 2.150216116909723e-06, "epoch": 17.606548856548855, "percentage": 88.03, "elapsed_time": "1:38:23", "remaining_time": "0:13:22", "throughput": 1033.39, "total_tokens": 6100976} {"current_steps": 67755, "total_steps": 76960, "loss": 0.0893, "lr": 2.1479163575101075e-06, "epoch": 17.607848232848234, "percentage": 88.04, "elapsed_time": "1:38:24", "remaining_time": "0:13:22", "throughput": 1033.39, "total_tokens": 6101408} {"current_steps": 67760, "total_steps": 76960, "loss": 0.0021, "lr": 2.1456177734150455e-06, "epoch": 17.60914760914761, "percentage": 88.05, "elapsed_time": "1:38:24", "remaining_time": "0:13:21", "throughput": 1033.4, "total_tokens": 6101888} {"current_steps": 67765, "total_steps": 76960, "loss": 0.2911, "lr": 2.14332036474276e-06, "epoch": 17.610446985446984, "percentage": 88.05, "elapsed_time": "1:38:25", "remaining_time": "0:13:21", "throughput": 1033.41, "total_tokens": 6102368} {"current_steps": 67770, "total_steps": 76960, "loss": 0.0031, "lr": 2.1410241316114133e-06, "epoch": 17.611746361746363, "percentage": 88.06, "elapsed_time": "1:38:25", "remaining_time": "0:13:20", "throughput": 1033.41, "total_tokens": 6102800} {"current_steps": 67775, "total_steps": 76960, "loss": 0.0002, "lr": 2.1387290741390923e-06, "epoch": 17.613045738045738, "percentage": 88.07, "elapsed_time": "1:38:25", "remaining_time": "0:13:20", "throughput": 1033.41, "total_tokens": 6103264} {"current_steps": 67780, "total_steps": 76960, "loss": 0.0158, "lr": 2.1364351924438446e-06, "epoch": 17.614345114345113, "percentage": 88.07, "elapsed_time": "1:38:26", "remaining_time": "0:13:19", "throughput": 1033.42, "total_tokens": 6103712} {"current_steps": 67785, "total_steps": 76960, "loss": 0.1905, "lr": 2.1341424866436364e-06, "epoch": 17.615644490644492, "percentage": 88.08, "elapsed_time": "1:38:26", "remaining_time": "0:13:19", "throughput": 1033.42, "total_tokens": 6104144} {"current_steps": 67790, "total_steps": 76960, "loss": 0.0441, "lr": 2.1318509568563904e-06, "epoch": 17.616943866943867, "percentage": 88.08, "elapsed_time": "1:38:27", "remaining_time": "0:13:19", "throughput": 1033.42, "total_tokens": 6104608} {"current_steps": 67795, "total_steps": 76960, "loss": 0.2126, "lr": 2.1295606031999623e-06, "epoch": 17.618243243243242, "percentage": 88.09, "elapsed_time": "1:38:27", "remaining_time": "0:13:18", "throughput": 1033.42, "total_tokens": 6105056} {"current_steps": 67800, "total_steps": 76960, "loss": 0.0865, "lr": 2.127271425792146e-06, "epoch": 17.61954261954262, "percentage": 88.1, "elapsed_time": "1:38:28", "remaining_time": "0:13:18", "throughput": 1033.43, "total_tokens": 6105504} {"current_steps": 67805, "total_steps": 76960, "loss": 0.0007, "lr": 2.124983424750676e-06, "epoch": 17.620841995841996, "percentage": 88.1, "elapsed_time": "1:38:28", "remaining_time": "0:13:17", "throughput": 1033.44, "total_tokens": 6106016} {"current_steps": 67810, "total_steps": 76960, "loss": 0.2495, "lr": 2.1226966001932277e-06, "epoch": 17.62214137214137, "percentage": 88.11, "elapsed_time": "1:38:28", "remaining_time": "0:13:17", "throughput": 1033.44, "total_tokens": 6106448} {"current_steps": 67815, "total_steps": 76960, "loss": 0.0419, "lr": 2.120410952237409e-06, "epoch": 17.62344074844075, "percentage": 88.12, "elapsed_time": "1:38:29", "remaining_time": "0:13:16", "throughput": 1033.44, "total_tokens": 6106880} {"current_steps": 67820, "total_steps": 76960, "loss": 0.2645, "lr": 2.1181264810007817e-06, "epoch": 17.624740124740125, "percentage": 88.12, "elapsed_time": "1:38:29", "remaining_time": "0:13:16", "throughput": 1033.44, "total_tokens": 6107296} {"current_steps": 67825, "total_steps": 76960, "loss": 0.3521, "lr": 2.11584318660083e-06, "epoch": 17.6260395010395, "percentage": 88.13, "elapsed_time": "1:38:30", "remaining_time": "0:13:16", "throughput": 1033.44, "total_tokens": 6107744} {"current_steps": 67830, "total_steps": 76960, "loss": 0.0024, "lr": 2.11356106915499e-06, "epoch": 17.62733887733888, "percentage": 88.14, "elapsed_time": "1:38:30", "remaining_time": "0:13:15", "throughput": 1033.45, "total_tokens": 6108224} {"current_steps": 67835, "total_steps": 76960, "loss": 0.4303, "lr": 2.1112801287806378e-06, "epoch": 17.628638253638254, "percentage": 88.14, "elapsed_time": "1:38:30", "remaining_time": "0:13:15", "throughput": 1033.45, "total_tokens": 6108640} {"current_steps": 67840, "total_steps": 76960, "loss": 0.2358, "lr": 2.1090003655950737e-06, "epoch": 17.62993762993763, "percentage": 88.15, "elapsed_time": "1:38:31", "remaining_time": "0:13:14", "throughput": 1033.46, "total_tokens": 6109120} {"current_steps": 67845, "total_steps": 76960, "loss": 0.0662, "lr": 2.106721779715559e-06, "epoch": 17.631237006237008, "percentage": 88.16, "elapsed_time": "1:38:31", "remaining_time": "0:13:14", "throughput": 1033.46, "total_tokens": 6109568} {"current_steps": 67850, "total_steps": 76960, "loss": 0.5471, "lr": 2.1044443712592758e-06, "epoch": 17.632536382536383, "percentage": 88.16, "elapsed_time": "1:38:32", "remaining_time": "0:13:13", "throughput": 1033.46, "total_tokens": 6110000} {"current_steps": 67855, "total_steps": 76960, "loss": 0.1945, "lr": 2.102168140343358e-06, "epoch": 17.633835758835758, "percentage": 88.17, "elapsed_time": "1:38:32", "remaining_time": "0:13:13", "throughput": 1033.47, "total_tokens": 6110464} {"current_steps": 67860, "total_steps": 76960, "loss": 0.0512, "lr": 2.0998930870848698e-06, "epoch": 17.635135135135137, "percentage": 88.18, "elapsed_time": "1:38:33", "remaining_time": "0:13:12", "throughput": 1033.47, "total_tokens": 6110944} {"current_steps": 67865, "total_steps": 76960, "loss": 0.5648, "lr": 2.0976192116008208e-06, "epoch": 17.636434511434512, "percentage": 88.18, "elapsed_time": "1:38:33", "remaining_time": "0:13:12", "throughput": 1033.47, "total_tokens": 6111360} {"current_steps": 67870, "total_steps": 76960, "loss": 0.0162, "lr": 2.095346514008159e-06, "epoch": 17.637733887733887, "percentage": 88.19, "elapsed_time": "1:38:33", "remaining_time": "0:13:12", "throughput": 1033.47, "total_tokens": 6111776} {"current_steps": 67875, "total_steps": 76960, "loss": 0.2229, "lr": 2.093074994423777e-06, "epoch": 17.639033264033262, "percentage": 88.2, "elapsed_time": "1:38:34", "remaining_time": "0:13:11", "throughput": 1033.47, "total_tokens": 6112224} {"current_steps": 67880, "total_steps": 76960, "loss": 0.4533, "lr": 2.0908046529644926e-06, "epoch": 17.64033264033264, "percentage": 88.2, "elapsed_time": "1:38:34", "remaining_time": "0:13:11", "throughput": 1033.48, "total_tokens": 6112704} {"current_steps": 67885, "total_steps": 76960, "loss": 0.0303, "lr": 2.0885354897470787e-06, "epoch": 17.641632016632016, "percentage": 88.21, "elapsed_time": "1:38:35", "remaining_time": "0:13:10", "throughput": 1033.49, "total_tokens": 6113216} {"current_steps": 67890, "total_steps": 76960, "loss": 0.1827, "lr": 2.0862675048882395e-06, "epoch": 17.64293139293139, "percentage": 88.21, "elapsed_time": "1:38:35", "remaining_time": "0:13:10", "throughput": 1033.51, "total_tokens": 6113712} {"current_steps": 67895, "total_steps": 76960, "loss": 0.0644, "lr": 2.0840006985046094e-06, "epoch": 17.64423076923077, "percentage": 88.22, "elapsed_time": "1:38:35", "remaining_time": "0:13:09", "throughput": 1033.51, "total_tokens": 6114160} {"current_steps": 67900, "total_steps": 76960, "loss": 0.0483, "lr": 2.081735070712784e-06, "epoch": 17.645530145530145, "percentage": 88.23, "elapsed_time": "1:38:36", "remaining_time": "0:13:09", "throughput": 1033.52, "total_tokens": 6114656} {"current_steps": 67905, "total_steps": 76960, "loss": 0.0188, "lr": 2.0794706216292813e-06, "epoch": 17.64682952182952, "percentage": 88.23, "elapsed_time": "1:38:36", "remaining_time": "0:13:08", "throughput": 1033.53, "total_tokens": 6115120} {"current_steps": 67910, "total_steps": 76960, "loss": 0.1448, "lr": 2.077207351370572e-06, "epoch": 17.6481288981289, "percentage": 88.24, "elapsed_time": "1:38:37", "remaining_time": "0:13:08", "throughput": 1033.53, "total_tokens": 6115552} {"current_steps": 67915, "total_steps": 76960, "loss": 0.2319, "lr": 2.074945260053046e-06, "epoch": 17.649428274428274, "percentage": 88.25, "elapsed_time": "1:38:37", "remaining_time": "0:13:08", "throughput": 1033.53, "total_tokens": 6116016} {"current_steps": 67920, "total_steps": 76960, "loss": 0.0499, "lr": 2.072684347793055e-06, "epoch": 17.65072765072765, "percentage": 88.25, "elapsed_time": "1:38:38", "remaining_time": "0:13:07", "throughput": 1033.54, "total_tokens": 6116480} {"current_steps": 67925, "total_steps": 76960, "loss": 0.0602, "lr": 2.070424614706873e-06, "epoch": 17.652027027027028, "percentage": 88.26, "elapsed_time": "1:38:38", "remaining_time": "0:13:07", "throughput": 1033.54, "total_tokens": 6116944} {"current_steps": 67930, "total_steps": 76960, "loss": 0.2635, "lr": 2.068166060910728e-06, "epoch": 17.653326403326403, "percentage": 88.27, "elapsed_time": "1:38:38", "remaining_time": "0:13:06", "throughput": 1033.54, "total_tokens": 6117376} {"current_steps": 67935, "total_steps": 76960, "loss": 0.4934, "lr": 2.0659086865207677e-06, "epoch": 17.65462577962578, "percentage": 88.27, "elapsed_time": "1:38:39", "remaining_time": "0:13:06", "throughput": 1033.55, "total_tokens": 6117824} {"current_steps": 67940, "total_steps": 76960, "loss": 0.0361, "lr": 2.063652491653101e-06, "epoch": 17.655925155925157, "percentage": 88.28, "elapsed_time": "1:38:39", "remaining_time": "0:13:05", "throughput": 1033.55, "total_tokens": 6118272} {"current_steps": 67945, "total_steps": 76960, "loss": 0.1817, "lr": 2.0613974764237626e-06, "epoch": 17.657224532224532, "percentage": 88.29, "elapsed_time": "1:38:40", "remaining_time": "0:13:05", "throughput": 1033.55, "total_tokens": 6118720} {"current_steps": 67950, "total_steps": 76960, "loss": 0.4993, "lr": 2.0591436409487326e-06, "epoch": 17.658523908523907, "percentage": 88.29, "elapsed_time": "1:38:40", "remaining_time": "0:13:05", "throughput": 1033.55, "total_tokens": 6119152} {"current_steps": 67955, "total_steps": 76960, "loss": 0.5144, "lr": 2.056890985343929e-06, "epoch": 17.659823284823286, "percentage": 88.3, "elapsed_time": "1:38:40", "remaining_time": "0:13:04", "throughput": 1033.56, "total_tokens": 6119600} {"current_steps": 67960, "total_steps": 76960, "loss": 0.2621, "lr": 2.054639509725198e-06, "epoch": 17.66112266112266, "percentage": 88.31, "elapsed_time": "1:38:41", "remaining_time": "0:13:04", "throughput": 1033.56, "total_tokens": 6120080} {"current_steps": 67965, "total_steps": 76960, "loss": 0.1271, "lr": 2.05238921420835e-06, "epoch": 17.662422037422036, "percentage": 88.31, "elapsed_time": "1:38:41", "remaining_time": "0:13:03", "throughput": 1033.57, "total_tokens": 6120512} {"current_steps": 67970, "total_steps": 76960, "loss": 0.0099, "lr": 2.0501400989091036e-06, "epoch": 17.663721413721415, "percentage": 88.32, "elapsed_time": "1:38:42", "remaining_time": "0:13:03", "throughput": 1033.57, "total_tokens": 6120944} {"current_steps": 67975, "total_steps": 76960, "loss": 0.4363, "lr": 2.0478921639431436e-06, "epoch": 17.66502079002079, "percentage": 88.33, "elapsed_time": "1:38:42", "remaining_time": "0:13:02", "throughput": 1033.57, "total_tokens": 6121408} {"current_steps": 67980, "total_steps": 76960, "loss": 0.1449, "lr": 2.0456454094260807e-06, "epoch": 17.666320166320165, "percentage": 88.33, "elapsed_time": "1:38:42", "remaining_time": "0:13:02", "throughput": 1033.58, "total_tokens": 6121872} {"current_steps": 67985, "total_steps": 76960, "loss": 0.1232, "lr": 2.043399835473475e-06, "epoch": 17.667619542619544, "percentage": 88.34, "elapsed_time": "1:38:43", "remaining_time": "0:13:01", "throughput": 1033.59, "total_tokens": 6122368} {"current_steps": 67990, "total_steps": 76960, "loss": 0.3748, "lr": 2.041155442200804e-06, "epoch": 17.66891891891892, "percentage": 88.34, "elapsed_time": "1:38:43", "remaining_time": "0:13:01", "throughput": 1033.59, "total_tokens": 6122816} {"current_steps": 67995, "total_steps": 76960, "loss": 0.0026, "lr": 2.0389122297235134e-06, "epoch": 17.670218295218294, "percentage": 88.35, "elapsed_time": "1:38:44", "remaining_time": "0:13:01", "throughput": 1033.59, "total_tokens": 6123216} {"current_steps": 68000, "total_steps": 76960, "loss": 0.1324, "lr": 2.036670198156962e-06, "epoch": 17.671517671517673, "percentage": 88.36, "elapsed_time": "1:38:44", "remaining_time": "0:13:00", "throughput": 1033.59, "total_tokens": 6123664} {"current_steps": 68005, "total_steps": 76960, "loss": 0.0616, "lr": 2.034429347616468e-06, "epoch": 17.67281704781705, "percentage": 88.36, "elapsed_time": "1:38:45", "remaining_time": "0:13:00", "throughput": 1033.59, "total_tokens": 6124112} {"current_steps": 68010, "total_steps": 76960, "loss": 0.1692, "lr": 2.0321896782172693e-06, "epoch": 17.674116424116423, "percentage": 88.37, "elapsed_time": "1:38:45", "remaining_time": "0:12:59", "throughput": 1033.59, "total_tokens": 6124544} {"current_steps": 68015, "total_steps": 76960, "loss": 0.0015, "lr": 2.029951190074572e-06, "epoch": 17.6754158004158, "percentage": 88.38, "elapsed_time": "1:38:45", "remaining_time": "0:12:59", "throughput": 1033.59, "total_tokens": 6124992} {"current_steps": 68020, "total_steps": 76960, "loss": 0.0006, "lr": 2.027713883303492e-06, "epoch": 17.676715176715177, "percentage": 88.38, "elapsed_time": "1:38:46", "remaining_time": "0:12:58", "throughput": 1033.61, "total_tokens": 6125488} {"current_steps": 68025, "total_steps": 76960, "loss": 0.0084, "lr": 2.0254777580190954e-06, "epoch": 17.678014553014552, "percentage": 88.39, "elapsed_time": "1:38:46", "remaining_time": "0:12:58", "throughput": 1033.61, "total_tokens": 6125952} {"current_steps": 68030, "total_steps": 76960, "loss": 0.1514, "lr": 2.023242814336393e-06, "epoch": 17.679313929313928, "percentage": 88.4, "elapsed_time": "1:38:47", "remaining_time": "0:12:58", "throughput": 1033.62, "total_tokens": 6126416} {"current_steps": 68035, "total_steps": 76960, "loss": 0.4193, "lr": 2.0210090523703232e-06, "epoch": 17.680613305613306, "percentage": 88.4, "elapsed_time": "1:38:47", "remaining_time": "0:12:57", "throughput": 1033.62, "total_tokens": 6126864} {"current_steps": 68040, "total_steps": 76960, "loss": 0.0336, "lr": 2.0187764722357782e-06, "epoch": 17.68191268191268, "percentage": 88.41, "elapsed_time": "1:38:47", "remaining_time": "0:12:57", "throughput": 1033.62, "total_tokens": 6127280} {"current_steps": 68045, "total_steps": 76960, "loss": 0.008, "lr": 2.0165450740475765e-06, "epoch": 17.683212058212057, "percentage": 88.42, "elapsed_time": "1:38:48", "remaining_time": "0:12:56", "throughput": 1033.61, "total_tokens": 6127680} {"current_steps": 68050, "total_steps": 76960, "loss": 0.0143, "lr": 2.014314857920488e-06, "epoch": 17.684511434511435, "percentage": 88.42, "elapsed_time": "1:38:48", "remaining_time": "0:12:56", "throughput": 1033.61, "total_tokens": 6128096} {"current_steps": 68055, "total_steps": 76960, "loss": 0.4539, "lr": 2.0120858239692065e-06, "epoch": 17.68581081081081, "percentage": 88.43, "elapsed_time": "1:38:49", "remaining_time": "0:12:55", "throughput": 1033.61, "total_tokens": 6128512} {"current_steps": 68060, "total_steps": 76960, "loss": 0.025, "lr": 2.0098579723083823e-06, "epoch": 17.687110187110186, "percentage": 88.44, "elapsed_time": "1:38:49", "remaining_time": "0:12:55", "throughput": 1033.61, "total_tokens": 6128944} {"current_steps": 68065, "total_steps": 76960, "loss": 0.0148, "lr": 2.0076313030525844e-06, "epoch": 17.688409563409564, "percentage": 88.44, "elapsed_time": "1:38:50", "remaining_time": "0:12:54", "throughput": 1033.6, "total_tokens": 6129344} {"current_steps": 68070, "total_steps": 76960, "loss": 0.4371, "lr": 2.005405816316344e-06, "epoch": 17.68970893970894, "percentage": 88.45, "elapsed_time": "1:38:50", "remaining_time": "0:12:54", "throughput": 1033.61, "total_tokens": 6129808} {"current_steps": 68075, "total_steps": 76960, "loss": 0.1164, "lr": 2.0031815122141113e-06, "epoch": 17.691008316008315, "percentage": 88.46, "elapsed_time": "1:38:50", "remaining_time": "0:12:54", "throughput": 1033.61, "total_tokens": 6130224} {"current_steps": 68080, "total_steps": 76960, "loss": 0.0416, "lr": 2.0009583908602857e-06, "epoch": 17.692307692307693, "percentage": 88.46, "elapsed_time": "1:38:51", "remaining_time": "0:12:53", "throughput": 1033.62, "total_tokens": 6130720} {"current_steps": 68085, "total_steps": 76960, "loss": 0.0381, "lr": 1.9987364523692125e-06, "epoch": 17.69360706860707, "percentage": 88.47, "elapsed_time": "1:38:51", "remaining_time": "0:12:53", "throughput": 1033.63, "total_tokens": 6131200} {"current_steps": 68090, "total_steps": 76960, "loss": 0.2108, "lr": 1.9965156968551586e-06, "epoch": 17.694906444906444, "percentage": 88.47, "elapsed_time": "1:38:52", "remaining_time": "0:12:52", "throughput": 1033.63, "total_tokens": 6131632} {"current_steps": 68095, "total_steps": 76960, "loss": 0.1181, "lr": 1.994296124432346e-06, "epoch": 17.696205821205822, "percentage": 88.48, "elapsed_time": "1:38:52", "remaining_time": "0:12:52", "throughput": 1033.63, "total_tokens": 6132064} {"current_steps": 68100, "total_steps": 76960, "loss": 0.2646, "lr": 1.9920777352149255e-06, "epoch": 17.697505197505198, "percentage": 88.49, "elapsed_time": "1:38:52", "remaining_time": "0:12:51", "throughput": 1033.64, "total_tokens": 6132544} {"current_steps": 68105, "total_steps": 76960, "loss": 0.0218, "lr": 1.989860529316992e-06, "epoch": 17.698804573804573, "percentage": 88.49, "elapsed_time": "1:38:53", "remaining_time": "0:12:51", "throughput": 1033.64, "total_tokens": 6132992} {"current_steps": 68110, "total_steps": 76960, "loss": 0.1018, "lr": 1.987644506852579e-06, "epoch": 17.70010395010395, "percentage": 88.5, "elapsed_time": "1:38:53", "remaining_time": "0:12:51", "throughput": 1033.64, "total_tokens": 6133440} {"current_steps": 68115, "total_steps": 76960, "loss": 0.1086, "lr": 1.9854296679356536e-06, "epoch": 17.701403326403327, "percentage": 88.51, "elapsed_time": "1:38:54", "remaining_time": "0:12:50", "throughput": 1033.65, "total_tokens": 6133920} {"current_steps": 68120, "total_steps": 76960, "loss": 0.0682, "lr": 1.9832160126801365e-06, "epoch": 17.7027027027027, "percentage": 88.51, "elapsed_time": "1:38:54", "remaining_time": "0:12:50", "throughput": 1033.66, "total_tokens": 6134384} {"current_steps": 68125, "total_steps": 76960, "loss": 0.0037, "lr": 1.9810035411998746e-06, "epoch": 17.70400207900208, "percentage": 88.52, "elapsed_time": "1:38:55", "remaining_time": "0:12:49", "throughput": 1033.66, "total_tokens": 6134832} {"current_steps": 68130, "total_steps": 76960, "loss": 0.0026, "lr": 1.9787922536086522e-06, "epoch": 17.705301455301456, "percentage": 88.53, "elapsed_time": "1:38:55", "remaining_time": "0:12:49", "throughput": 1033.67, "total_tokens": 6135312} {"current_steps": 68135, "total_steps": 76960, "loss": 0.4396, "lr": 1.976582150020209e-06, "epoch": 17.70660083160083, "percentage": 88.53, "elapsed_time": "1:38:55", "remaining_time": "0:12:48", "throughput": 1033.67, "total_tokens": 6135760} {"current_steps": 68140, "total_steps": 76960, "loss": 0.0482, "lr": 1.9743732305481986e-06, "epoch": 17.70790020790021, "percentage": 88.54, "elapsed_time": "1:38:56", "remaining_time": "0:12:48", "throughput": 1033.67, "total_tokens": 6136208} {"current_steps": 68145, "total_steps": 76960, "loss": 0.0752, "lr": 1.972165495306241e-06, "epoch": 17.709199584199585, "percentage": 88.55, "elapsed_time": "1:38:56", "remaining_time": "0:12:47", "throughput": 1033.68, "total_tokens": 6136640} {"current_steps": 68150, "total_steps": 76960, "loss": 0.134, "lr": 1.969958944407871e-06, "epoch": 17.71049896049896, "percentage": 88.55, "elapsed_time": "1:38:57", "remaining_time": "0:12:47", "throughput": 1033.68, "total_tokens": 6137104} {"current_steps": 68155, "total_steps": 76960, "loss": 0.1996, "lr": 1.9677535779665803e-06, "epoch": 17.71179833679834, "percentage": 88.56, "elapsed_time": "1:38:57", "remaining_time": "0:12:47", "throughput": 1033.69, "total_tokens": 6137616} {"current_steps": 68160, "total_steps": 76960, "loss": 0.2174, "lr": 1.965549396095795e-06, "epoch": 17.713097713097714, "percentage": 88.57, "elapsed_time": "1:38:57", "remaining_time": "0:12:46", "throughput": 1033.7, "total_tokens": 6138080} {"current_steps": 68165, "total_steps": 76960, "loss": 0.1688, "lr": 1.963346398908869e-06, "epoch": 17.71439708939709, "percentage": 88.57, "elapsed_time": "1:38:58", "remaining_time": "0:12:46", "throughput": 1033.7, "total_tokens": 6138528} {"current_steps": 68170, "total_steps": 76960, "loss": 0.1708, "lr": 1.9611445865191146e-06, "epoch": 17.715696465696467, "percentage": 88.58, "elapsed_time": "1:38:58", "remaining_time": "0:12:45", "throughput": 1033.71, "total_tokens": 6138976} {"current_steps": 68175, "total_steps": 76960, "loss": 0.0944, "lr": 1.9589439590397664e-06, "epoch": 17.716995841995843, "percentage": 88.58, "elapsed_time": "1:38:59", "remaining_time": "0:12:45", "throughput": 1033.71, "total_tokens": 6139424} {"current_steps": 68180, "total_steps": 76960, "loss": 0.2387, "lr": 1.956744516584011e-06, "epoch": 17.718295218295218, "percentage": 88.59, "elapsed_time": "1:38:59", "remaining_time": "0:12:44", "throughput": 1033.71, "total_tokens": 6139856} {"current_steps": 68185, "total_steps": 76960, "loss": 0.0695, "lr": 1.954546259264961e-06, "epoch": 17.719594594594593, "percentage": 88.6, "elapsed_time": "1:39:00", "remaining_time": "0:12:44", "throughput": 1033.71, "total_tokens": 6140304} {"current_steps": 68190, "total_steps": 76960, "loss": 0.0833, "lr": 1.952349187195676e-06, "epoch": 17.72089397089397, "percentage": 88.6, "elapsed_time": "1:39:00", "remaining_time": "0:12:44", "throughput": 1033.71, "total_tokens": 6140752} {"current_steps": 68195, "total_steps": 76960, "loss": 0.1424, "lr": 1.9501533004891577e-06, "epoch": 17.722193347193347, "percentage": 88.61, "elapsed_time": "1:39:00", "remaining_time": "0:12:43", "throughput": 1033.72, "total_tokens": 6141200} {"current_steps": 68200, "total_steps": 76960, "loss": 0.3993, "lr": 1.9479585992583426e-06, "epoch": 17.723492723492722, "percentage": 88.62, "elapsed_time": "1:39:01", "remaining_time": "0:12:43", "throughput": 1033.72, "total_tokens": 6141616} {"current_steps": 68205, "total_steps": 76960, "loss": 0.2959, "lr": 1.9457650836160997e-06, "epoch": 17.7247920997921, "percentage": 88.62, "elapsed_time": "1:39:01", "remaining_time": "0:12:42", "throughput": 1033.71, "total_tokens": 6142016} {"current_steps": 68210, "total_steps": 76960, "loss": 0.0011, "lr": 1.9435727536752547e-06, "epoch": 17.726091476091476, "percentage": 88.63, "elapsed_time": "1:39:02", "remaining_time": "0:12:42", "throughput": 1033.72, "total_tokens": 6142480} {"current_steps": 68215, "total_steps": 76960, "loss": 0.0071, "lr": 1.941381609548551e-06, "epoch": 17.72739085239085, "percentage": 88.64, "elapsed_time": "1:39:02", "remaining_time": "0:12:41", "throughput": 1033.71, "total_tokens": 6142896} {"current_steps": 68220, "total_steps": 76960, "loss": 0.0104, "lr": 1.939191651348685e-06, "epoch": 17.72869022869023, "percentage": 88.64, "elapsed_time": "1:39:02", "remaining_time": "0:12:41", "throughput": 1033.72, "total_tokens": 6143392} {"current_steps": 68225, "total_steps": 76960, "loss": 0.0341, "lr": 1.937002879188285e-06, "epoch": 17.729989604989605, "percentage": 88.65, "elapsed_time": "1:39:03", "remaining_time": "0:12:40", "throughput": 1033.73, "total_tokens": 6143840} {"current_steps": 68230, "total_steps": 76960, "loss": 0.0292, "lr": 1.934815293179926e-06, "epoch": 17.73128898128898, "percentage": 88.66, "elapsed_time": "1:39:03", "remaining_time": "0:12:40", "throughput": 1033.74, "total_tokens": 6144320} {"current_steps": 68235, "total_steps": 76960, "loss": 0.6385, "lr": 1.93262889343612e-06, "epoch": 17.73258835758836, "percentage": 88.66, "elapsed_time": "1:39:04", "remaining_time": "0:12:40", "throughput": 1033.74, "total_tokens": 6144784} {"current_steps": 68240, "total_steps": 76960, "loss": 0.0624, "lr": 1.9304436800693074e-06, "epoch": 17.733887733887734, "percentage": 88.67, "elapsed_time": "1:39:04", "remaining_time": "0:12:39", "throughput": 1033.75, "total_tokens": 6145232} {"current_steps": 68245, "total_steps": 76960, "loss": 0.0006, "lr": 1.9282596531918855e-06, "epoch": 17.73518711018711, "percentage": 88.68, "elapsed_time": "1:39:05", "remaining_time": "0:12:39", "throughput": 1033.75, "total_tokens": 6145680} {"current_steps": 68250, "total_steps": 76960, "loss": 0.1499, "lr": 1.9260768129161723e-06, "epoch": 17.736486486486488, "percentage": 88.68, "elapsed_time": "1:39:05", "remaining_time": "0:12:38", "throughput": 1033.75, "total_tokens": 6146128} {"current_steps": 68255, "total_steps": 76960, "loss": 0.0211, "lr": 1.923895159354441e-06, "epoch": 17.737785862785863, "percentage": 88.69, "elapsed_time": "1:39:05", "remaining_time": "0:12:38", "throughput": 1033.75, "total_tokens": 6146544} {"current_steps": 68260, "total_steps": 76960, "loss": 0.071, "lr": 1.9217146926188813e-06, "epoch": 17.739085239085238, "percentage": 88.7, "elapsed_time": "1:39:06", "remaining_time": "0:12:37", "throughput": 1033.75, "total_tokens": 6146992} {"current_steps": 68265, "total_steps": 76960, "loss": 0.301, "lr": 1.91953541282166e-06, "epoch": 17.740384615384617, "percentage": 88.7, "elapsed_time": "1:39:06", "remaining_time": "0:12:37", "throughput": 1033.76, "total_tokens": 6147488} {"current_steps": 68270, "total_steps": 76960, "loss": 0.1025, "lr": 1.917357320074839e-06, "epoch": 17.741683991683992, "percentage": 88.71, "elapsed_time": "1:39:07", "remaining_time": "0:12:37", "throughput": 1033.76, "total_tokens": 6147904} {"current_steps": 68275, "total_steps": 76960, "loss": 0.2956, "lr": 1.9151804144904556e-06, "epoch": 17.742983367983367, "percentage": 88.71, "elapsed_time": "1:39:07", "remaining_time": "0:12:36", "throughput": 1033.76, "total_tokens": 6148352} {"current_steps": 68280, "total_steps": 76960, "loss": 0.2538, "lr": 1.9130046961804593e-06, "epoch": 17.744282744282746, "percentage": 88.72, "elapsed_time": "1:39:07", "remaining_time": "0:12:36", "throughput": 1033.77, "total_tokens": 6148832} {"current_steps": 68285, "total_steps": 76960, "loss": 0.0056, "lr": 1.9108301652567497e-06, "epoch": 17.74558212058212, "percentage": 88.73, "elapsed_time": "1:39:08", "remaining_time": "0:12:35", "throughput": 1033.78, "total_tokens": 6149280} {"current_steps": 68290, "total_steps": 76960, "loss": 0.0033, "lr": 1.908656821831167e-06, "epoch": 17.746881496881496, "percentage": 88.73, "elapsed_time": "1:39:08", "remaining_time": "0:12:35", "throughput": 1033.77, "total_tokens": 6149696} {"current_steps": 68295, "total_steps": 76960, "loss": 0.1522, "lr": 1.90648466601549e-06, "epoch": 17.748180873180875, "percentage": 88.74, "elapsed_time": "1:39:09", "remaining_time": "0:12:34", "throughput": 1033.78, "total_tokens": 6150160} {"current_steps": 68300, "total_steps": 76960, "loss": 0.003, "lr": 1.9043136979214365e-06, "epoch": 17.74948024948025, "percentage": 88.75, "elapsed_time": "1:39:09", "remaining_time": "0:12:34", "throughput": 1033.78, "total_tokens": 6150592} {"current_steps": 68305, "total_steps": 76960, "loss": 0.0015, "lr": 1.9021439176606564e-06, "epoch": 17.750779625779625, "percentage": 88.75, "elapsed_time": "1:39:10", "remaining_time": "0:12:33", "throughput": 1033.79, "total_tokens": 6151056} {"current_steps": 68310, "total_steps": 76960, "loss": 0.189, "lr": 1.8999753253447466e-06, "epoch": 17.752079002079, "percentage": 88.76, "elapsed_time": "1:39:10", "remaining_time": "0:12:33", "throughput": 1033.79, "total_tokens": 6151488} {"current_steps": 68315, "total_steps": 76960, "loss": 0.0048, "lr": 1.89780792108524e-06, "epoch": 17.75337837837838, "percentage": 88.77, "elapsed_time": "1:39:10", "remaining_time": "0:12:33", "throughput": 1033.79, "total_tokens": 6151920} {"current_steps": 68320, "total_steps": 76960, "loss": 0.043, "lr": 1.8956417049936088e-06, "epoch": 17.754677754677754, "percentage": 88.77, "elapsed_time": "1:39:11", "remaining_time": "0:12:32", "throughput": 1033.79, "total_tokens": 6152352} {"current_steps": 68325, "total_steps": 76960, "loss": 0.0001, "lr": 1.8934766771812578e-06, "epoch": 17.75597713097713, "percentage": 88.78, "elapsed_time": "1:39:11", "remaining_time": "0:12:32", "throughput": 1033.79, "total_tokens": 6152784} {"current_steps": 68330, "total_steps": 76960, "loss": 0.0983, "lr": 1.8913128377595402e-06, "epoch": 17.757276507276508, "percentage": 88.79, "elapsed_time": "1:39:12", "remaining_time": "0:12:31", "throughput": 1033.78, "total_tokens": 6153184} {"current_steps": 68335, "total_steps": 76960, "loss": 0.1932, "lr": 1.8891501868397472e-06, "epoch": 17.758575883575883, "percentage": 88.79, "elapsed_time": "1:39:12", "remaining_time": "0:12:31", "throughput": 1033.79, "total_tokens": 6153648} {"current_steps": 68340, "total_steps": 76960, "loss": 0.0011, "lr": 1.8869887245331063e-06, "epoch": 17.75987525987526, "percentage": 88.8, "elapsed_time": "1:39:12", "remaining_time": "0:12:30", "throughput": 1033.78, "total_tokens": 6154064} {"current_steps": 68345, "total_steps": 76960, "loss": 0.2038, "lr": 1.8848284509507818e-06, "epoch": 17.761174636174637, "percentage": 88.81, "elapsed_time": "1:39:13", "remaining_time": "0:12:30", "throughput": 1033.8, "total_tokens": 6154560} {"current_steps": 68350, "total_steps": 76960, "loss": 0.0039, "lr": 1.8826693662038737e-06, "epoch": 17.762474012474012, "percentage": 88.81, "elapsed_time": "1:39:13", "remaining_time": "0:12:29", "throughput": 1033.8, "total_tokens": 6155040} {"current_steps": 68355, "total_steps": 76960, "loss": 0.3724, "lr": 1.8805114704034343e-06, "epoch": 17.763773388773387, "percentage": 88.82, "elapsed_time": "1:39:14", "remaining_time": "0:12:29", "throughput": 1033.8, "total_tokens": 6155456} {"current_steps": 68360, "total_steps": 76960, "loss": 0.0151, "lr": 1.8783547636604392e-06, "epoch": 17.765072765072766, "percentage": 88.83, "elapsed_time": "1:39:14", "remaining_time": "0:12:29", "throughput": 1033.81, "total_tokens": 6155936} {"current_steps": 68365, "total_steps": 76960, "loss": 0.0007, "lr": 1.8761992460858107e-06, "epoch": 17.76637214137214, "percentage": 88.83, "elapsed_time": "1:39:15", "remaining_time": "0:12:28", "throughput": 1033.81, "total_tokens": 6156368} {"current_steps": 68370, "total_steps": 76960, "loss": 0.0062, "lr": 1.874044917790413e-06, "epoch": 17.767671517671516, "percentage": 88.84, "elapsed_time": "1:39:15", "remaining_time": "0:12:28", "throughput": 1033.81, "total_tokens": 6156784} {"current_steps": 68375, "total_steps": 76960, "loss": 0.1867, "lr": 1.871891778885046e-06, "epoch": 17.768970893970895, "percentage": 88.84, "elapsed_time": "1:39:15", "remaining_time": "0:12:27", "throughput": 1033.81, "total_tokens": 6157216} {"current_steps": 68380, "total_steps": 76960, "loss": 0.3894, "lr": 1.8697398294804407e-06, "epoch": 17.77027027027027, "percentage": 88.85, "elapsed_time": "1:39:16", "remaining_time": "0:12:27", "throughput": 1033.81, "total_tokens": 6157680} {"current_steps": 68385, "total_steps": 76960, "loss": 0.0009, "lr": 1.8675890696872838e-06, "epoch": 17.771569646569645, "percentage": 88.86, "elapsed_time": "1:39:16", "remaining_time": "0:12:26", "throughput": 1033.81, "total_tokens": 6158096} {"current_steps": 68390, "total_steps": 76960, "loss": 0.2704, "lr": 1.865439499616181e-06, "epoch": 17.772869022869024, "percentage": 88.86, "elapsed_time": "1:39:17", "remaining_time": "0:12:26", "throughput": 1033.82, "total_tokens": 6158560} {"current_steps": 68395, "total_steps": 76960, "loss": 0.1933, "lr": 1.8632911193776942e-06, "epoch": 17.7741683991684, "percentage": 88.87, "elapsed_time": "1:39:17", "remaining_time": "0:12:26", "throughput": 1033.82, "total_tokens": 6159024} {"current_steps": 68400, "total_steps": 76960, "loss": 0.05, "lr": 1.8611439290823096e-06, "epoch": 17.775467775467774, "percentage": 88.88, "elapsed_time": "1:39:17", "remaining_time": "0:12:25", "throughput": 1033.83, "total_tokens": 6159488} {"current_steps": 68405, "total_steps": 76960, "loss": 0.0626, "lr": 1.858997928840464e-06, "epoch": 17.776767151767153, "percentage": 88.88, "elapsed_time": "1:39:18", "remaining_time": "0:12:25", "throughput": 1033.84, "total_tokens": 6159968} {"current_steps": 68410, "total_steps": 76960, "loss": 0.0318, "lr": 1.8568531187625333e-06, "epoch": 17.778066528066528, "percentage": 88.89, "elapsed_time": "1:39:18", "remaining_time": "0:12:24", "throughput": 1033.84, "total_tokens": 6160432} {"current_steps": 68415, "total_steps": 76960, "loss": 0.028, "lr": 1.8547094989588148e-06, "epoch": 17.779365904365903, "percentage": 88.9, "elapsed_time": "1:39:19", "remaining_time": "0:12:24", "throughput": 1033.84, "total_tokens": 6160864} {"current_steps": 68420, "total_steps": 76960, "loss": 0.2012, "lr": 1.852567069539568e-06, "epoch": 17.780665280665282, "percentage": 88.9, "elapsed_time": "1:39:19", "remaining_time": "0:12:23", "throughput": 1033.85, "total_tokens": 6161312} {"current_steps": 68425, "total_steps": 76960, "loss": 0.0474, "lr": 1.8504258306149713e-06, "epoch": 17.781964656964657, "percentage": 88.91, "elapsed_time": "1:39:20", "remaining_time": "0:12:23", "throughput": 1033.85, "total_tokens": 6161744} {"current_steps": 68430, "total_steps": 76960, "loss": 0.0138, "lr": 1.8482857822951616e-06, "epoch": 17.783264033264032, "percentage": 88.92, "elapsed_time": "1:39:20", "remaining_time": "0:12:22", "throughput": 1033.85, "total_tokens": 6162208} {"current_steps": 68435, "total_steps": 76960, "loss": 0.0007, "lr": 1.8461469246901897e-06, "epoch": 17.78456340956341, "percentage": 88.92, "elapsed_time": "1:39:20", "remaining_time": "0:12:22", "throughput": 1033.86, "total_tokens": 6162688} {"current_steps": 68440, "total_steps": 76960, "loss": 0.0091, "lr": 1.8440092579100677e-06, "epoch": 17.785862785862786, "percentage": 88.93, "elapsed_time": "1:39:21", "remaining_time": "0:12:22", "throughput": 1033.86, "total_tokens": 6163136} {"current_steps": 68445, "total_steps": 76960, "loss": 0.4983, "lr": 1.841872782064738e-06, "epoch": 17.78716216216216, "percentage": 88.94, "elapsed_time": "1:39:21", "remaining_time": "0:12:21", "throughput": 1033.87, "total_tokens": 6163600} {"current_steps": 68450, "total_steps": 76960, "loss": 0.0004, "lr": 1.8397374972640823e-06, "epoch": 17.78846153846154, "percentage": 88.94, "elapsed_time": "1:39:22", "remaining_time": "0:12:21", "throughput": 1033.87, "total_tokens": 6164064} {"current_steps": 68455, "total_steps": 76960, "loss": 0.0009, "lr": 1.8376034036179158e-06, "epoch": 17.789760914760915, "percentage": 88.95, "elapsed_time": "1:39:22", "remaining_time": "0:12:20", "throughput": 1033.88, "total_tokens": 6164528} {"current_steps": 68460, "total_steps": 76960, "loss": 0.0004, "lr": 1.8354705012360002e-06, "epoch": 17.79106029106029, "percentage": 88.96, "elapsed_time": "1:39:22", "remaining_time": "0:12:20", "throughput": 1033.88, "total_tokens": 6164944} {"current_steps": 68465, "total_steps": 76960, "loss": 0.0056, "lr": 1.8333387902280314e-06, "epoch": 17.79235966735967, "percentage": 88.96, "elapsed_time": "1:39:23", "remaining_time": "0:12:19", "throughput": 1033.89, "total_tokens": 6165456} {"current_steps": 68470, "total_steps": 76960, "loss": 0.0882, "lr": 1.8312082707036494e-06, "epoch": 17.793659043659044, "percentage": 88.97, "elapsed_time": "1:39:23", "remaining_time": "0:12:19", "throughput": 1033.9, "total_tokens": 6165952} {"current_steps": 68475, "total_steps": 76960, "loss": 0.2111, "lr": 1.8290789427724191e-06, "epoch": 17.79495841995842, "percentage": 88.97, "elapsed_time": "1:39:24", "remaining_time": "0:12:19", "throughput": 1033.91, "total_tokens": 6166448} {"current_steps": 68480, "total_steps": 76960, "loss": 0.0047, "lr": 1.8269508065438617e-06, "epoch": 17.796257796257795, "percentage": 88.98, "elapsed_time": "1:39:24", "remaining_time": "0:12:18", "throughput": 1033.91, "total_tokens": 6166864} {"current_steps": 68485, "total_steps": 76960, "loss": 0.1225, "lr": 1.824823862127431e-06, "epoch": 17.797557172557173, "percentage": 88.99, "elapsed_time": "1:39:25", "remaining_time": "0:12:18", "throughput": 1033.92, "total_tokens": 6167328} {"current_steps": 68490, "total_steps": 76960, "loss": 0.022, "lr": 1.8226981096325119e-06, "epoch": 17.79885654885655, "percentage": 88.99, "elapsed_time": "1:39:25", "remaining_time": "0:12:17", "throughput": 1033.92, "total_tokens": 6167792} {"current_steps": 68495, "total_steps": 76960, "loss": 0.2801, "lr": 1.820573549168439e-06, "epoch": 17.800155925155924, "percentage": 89.0, "elapsed_time": "1:39:25", "remaining_time": "0:12:17", "throughput": 1033.93, "total_tokens": 6168288} {"current_steps": 68500, "total_steps": 76960, "loss": 0.001, "lr": 1.8184501808444749e-06, "epoch": 17.801455301455302, "percentage": 89.01, "elapsed_time": "1:39:26", "remaining_time": "0:12:16", "throughput": 1033.93, "total_tokens": 6168720} {"current_steps": 68505, "total_steps": 76960, "loss": 0.0004, "lr": 1.8163280047698323e-06, "epoch": 17.802754677754677, "percentage": 89.01, "elapsed_time": "1:39:26", "remaining_time": "0:12:16", "throughput": 1033.94, "total_tokens": 6169200} {"current_steps": 68510, "total_steps": 76960, "loss": 0.0531, "lr": 1.814207021053646e-06, "epoch": 17.804054054054053, "percentage": 89.02, "elapsed_time": "1:39:27", "remaining_time": "0:12:15", "throughput": 1033.94, "total_tokens": 6169616} {"current_steps": 68515, "total_steps": 76960, "loss": 0.2557, "lr": 1.812087229805018e-06, "epoch": 17.80535343035343, "percentage": 89.03, "elapsed_time": "1:39:27", "remaining_time": "0:12:15", "throughput": 1033.95, "total_tokens": 6170080} {"current_steps": 68520, "total_steps": 76960, "loss": 0.0027, "lr": 1.809968631132955e-06, "epoch": 17.806652806652806, "percentage": 89.03, "elapsed_time": "1:39:27", "remaining_time": "0:12:15", "throughput": 1033.96, "total_tokens": 6170560} {"current_steps": 68525, "total_steps": 76960, "loss": 0.3225, "lr": 1.8078512251464286e-06, "epoch": 17.80795218295218, "percentage": 89.04, "elapsed_time": "1:39:28", "remaining_time": "0:12:14", "throughput": 1033.96, "total_tokens": 6170992} {"current_steps": 68530, "total_steps": 76960, "loss": 0.0005, "lr": 1.8057350119543348e-06, "epoch": 17.80925155925156, "percentage": 89.05, "elapsed_time": "1:39:28", "remaining_time": "0:12:14", "throughput": 1033.96, "total_tokens": 6171472} {"current_steps": 68535, "total_steps": 76960, "loss": 0.0267, "lr": 1.8036199916655144e-06, "epoch": 17.810550935550935, "percentage": 89.05, "elapsed_time": "1:39:29", "remaining_time": "0:12:13", "throughput": 1033.97, "total_tokens": 6171920} {"current_steps": 68540, "total_steps": 76960, "loss": 0.0046, "lr": 1.8015061643887387e-06, "epoch": 17.81185031185031, "percentage": 89.06, "elapsed_time": "1:39:29", "remaining_time": "0:12:13", "throughput": 1033.97, "total_tokens": 6172336} {"current_steps": 68545, "total_steps": 76960, "loss": 0.1573, "lr": 1.7993935302327292e-06, "epoch": 17.81314968814969, "percentage": 89.07, "elapsed_time": "1:39:29", "remaining_time": "0:12:12", "throughput": 1033.97, "total_tokens": 6172784} {"current_steps": 68550, "total_steps": 76960, "loss": 0.0063, "lr": 1.797282089306146e-06, "epoch": 17.814449064449065, "percentage": 89.07, "elapsed_time": "1:39:30", "remaining_time": "0:12:12", "throughput": 1033.96, "total_tokens": 6173200} {"current_steps": 68555, "total_steps": 76960, "loss": 0.016, "lr": 1.7951718417175716e-06, "epoch": 17.81574844074844, "percentage": 89.08, "elapsed_time": "1:39:30", "remaining_time": "0:12:12", "throughput": 1033.96, "total_tokens": 6173632} {"current_steps": 68560, "total_steps": 76960, "loss": 0.0061, "lr": 1.7930627875755473e-06, "epoch": 17.81704781704782, "percentage": 89.09, "elapsed_time": "1:39:31", "remaining_time": "0:12:11", "throughput": 1033.97, "total_tokens": 6174096} {"current_steps": 68565, "total_steps": 76960, "loss": 0.0043, "lr": 1.7909549269885362e-06, "epoch": 17.818347193347194, "percentage": 89.09, "elapsed_time": "1:39:31", "remaining_time": "0:12:11", "throughput": 1033.97, "total_tokens": 6174544} {"current_steps": 68570, "total_steps": 76960, "loss": 0.0012, "lr": 1.7888482600649542e-06, "epoch": 17.81964656964657, "percentage": 89.1, "elapsed_time": "1:39:32", "remaining_time": "0:12:10", "throughput": 1033.97, "total_tokens": 6174976} {"current_steps": 68575, "total_steps": 76960, "loss": 0.0309, "lr": 1.7867427869131426e-06, "epoch": 17.820945945945947, "percentage": 89.1, "elapsed_time": "1:39:32", "remaining_time": "0:12:10", "throughput": 1033.98, "total_tokens": 6175440} {"current_steps": 68580, "total_steps": 76960, "loss": 0.342, "lr": 1.7846385076413897e-06, "epoch": 17.822245322245323, "percentage": 89.11, "elapsed_time": "1:39:32", "remaining_time": "0:12:09", "throughput": 1033.98, "total_tokens": 6175888} {"current_steps": 68585, "total_steps": 76960, "loss": 0.3566, "lr": 1.7825354223579255e-06, "epoch": 17.823544698544698, "percentage": 89.12, "elapsed_time": "1:39:33", "remaining_time": "0:12:09", "throughput": 1033.99, "total_tokens": 6176336} {"current_steps": 68590, "total_steps": 76960, "loss": 0.002, "lr": 1.7804335311709108e-06, "epoch": 17.824844074844076, "percentage": 89.12, "elapsed_time": "1:39:33", "remaining_time": "0:12:08", "throughput": 1033.99, "total_tokens": 6176768} {"current_steps": 68595, "total_steps": 76960, "loss": 0.0097, "lr": 1.7783328341884452e-06, "epoch": 17.82614345114345, "percentage": 89.13, "elapsed_time": "1:39:34", "remaining_time": "0:12:08", "throughput": 1033.99, "total_tokens": 6177216} {"current_steps": 68600, "total_steps": 76960, "loss": 0.2237, "lr": 1.776233331518576e-06, "epoch": 17.827442827442827, "percentage": 89.14, "elapsed_time": "1:39:34", "remaining_time": "0:12:08", "throughput": 1034.0, "total_tokens": 6177712} {"current_steps": 68605, "total_steps": 76960, "loss": 0.0044, "lr": 1.77413502326928e-06, "epoch": 17.828742203742205, "percentage": 89.14, "elapsed_time": "1:39:34", "remaining_time": "0:12:07", "throughput": 1034.0, "total_tokens": 6178144} {"current_steps": 68610, "total_steps": 76960, "loss": 0.0433, "lr": 1.7720379095484686e-06, "epoch": 17.83004158004158, "percentage": 89.15, "elapsed_time": "1:39:35", "remaining_time": "0:12:07", "throughput": 1034.01, "total_tokens": 6178640} {"current_steps": 68615, "total_steps": 76960, "loss": 0.0063, "lr": 1.7699419904640024e-06, "epoch": 17.831340956340956, "percentage": 89.16, "elapsed_time": "1:39:35", "remaining_time": "0:12:06", "throughput": 1034.01, "total_tokens": 6179040} {"current_steps": 68620, "total_steps": 76960, "loss": 0.0012, "lr": 1.7678472661236789e-06, "epoch": 17.83264033264033, "percentage": 89.16, "elapsed_time": "1:39:36", "remaining_time": "0:12:06", "throughput": 1034.01, "total_tokens": 6179472} {"current_steps": 68625, "total_steps": 76960, "loss": 0.3945, "lr": 1.7657537366352338e-06, "epoch": 17.83393970893971, "percentage": 89.17, "elapsed_time": "1:39:36", "remaining_time": "0:12:05", "throughput": 1034.01, "total_tokens": 6179936} {"current_steps": 68630, "total_steps": 76960, "loss": 0.0005, "lr": 1.7636614021063313e-06, "epoch": 17.835239085239085, "percentage": 89.18, "elapsed_time": "1:39:37", "remaining_time": "0:12:05", "throughput": 1034.02, "total_tokens": 6180400} {"current_steps": 68635, "total_steps": 76960, "loss": 0.0194, "lr": 1.7615702626445907e-06, "epoch": 17.83653846153846, "percentage": 89.18, "elapsed_time": "1:39:37", "remaining_time": "0:12:05", "throughput": 1034.02, "total_tokens": 6180848} {"current_steps": 68640, "total_steps": 76960, "loss": 0.0093, "lr": 1.7594803183575536e-06, "epoch": 17.83783783783784, "percentage": 89.19, "elapsed_time": "1:39:37", "remaining_time": "0:12:04", "throughput": 1034.02, "total_tokens": 6181280} {"current_steps": 68645, "total_steps": 76960, "loss": 0.0702, "lr": 1.7573915693527176e-06, "epoch": 17.839137214137214, "percentage": 89.2, "elapsed_time": "1:39:38", "remaining_time": "0:12:04", "throughput": 1034.03, "total_tokens": 6181760} {"current_steps": 68650, "total_steps": 76960, "loss": 0.0002, "lr": 1.7553040157374968e-06, "epoch": 17.84043659043659, "percentage": 89.2, "elapsed_time": "1:39:38", "remaining_time": "0:12:03", "throughput": 1034.04, "total_tokens": 6182224} {"current_steps": 68655, "total_steps": 76960, "loss": 0.0002, "lr": 1.753217657619266e-06, "epoch": 17.841735966735968, "percentage": 89.21, "elapsed_time": "1:39:39", "remaining_time": "0:12:03", "throughput": 1034.04, "total_tokens": 6182656} {"current_steps": 68660, "total_steps": 76960, "loss": 0.0646, "lr": 1.7511324951053204e-06, "epoch": 17.843035343035343, "percentage": 89.22, "elapsed_time": "1:39:39", "remaining_time": "0:12:02", "throughput": 1034.04, "total_tokens": 6183120} {"current_steps": 68665, "total_steps": 76960, "loss": 0.2868, "lr": 1.749048528302913e-06, "epoch": 17.844334719334718, "percentage": 89.22, "elapsed_time": "1:39:39", "remaining_time": "0:12:02", "throughput": 1034.05, "total_tokens": 6183584} {"current_steps": 68670, "total_steps": 76960, "loss": 0.1338, "lr": 1.746965757319219e-06, "epoch": 17.845634095634097, "percentage": 89.23, "elapsed_time": "1:39:40", "remaining_time": "0:12:01", "throughput": 1034.05, "total_tokens": 6184048} {"current_steps": 68675, "total_steps": 76960, "loss": 0.1082, "lr": 1.74488418226135e-06, "epoch": 17.846933471933472, "percentage": 89.23, "elapsed_time": "1:39:40", "remaining_time": "0:12:01", "throughput": 1034.06, "total_tokens": 6184496} {"current_steps": 68680, "total_steps": 76960, "loss": 0.0045, "lr": 1.7428038032363758e-06, "epoch": 17.848232848232847, "percentage": 89.24, "elapsed_time": "1:39:41", "remaining_time": "0:12:01", "throughput": 1034.06, "total_tokens": 6184944} {"current_steps": 68685, "total_steps": 76960, "loss": 0.0194, "lr": 1.7407246203512805e-06, "epoch": 17.849532224532226, "percentage": 89.25, "elapsed_time": "1:39:41", "remaining_time": "0:12:00", "throughput": 1034.07, "total_tokens": 6185440} {"current_steps": 68690, "total_steps": 76960, "loss": 0.2015, "lr": 1.7386466337130036e-06, "epoch": 17.8508316008316, "percentage": 89.25, "elapsed_time": "1:39:42", "remaining_time": "0:12:00", "throughput": 1034.07, "total_tokens": 6185856} {"current_steps": 68695, "total_steps": 76960, "loss": 0.2687, "lr": 1.7365698434284178e-06, "epoch": 17.852130977130976, "percentage": 89.26, "elapsed_time": "1:39:42", "remaining_time": "0:11:59", "throughput": 1034.07, "total_tokens": 6186304} {"current_steps": 68700, "total_steps": 76960, "loss": 0.0356, "lr": 1.7344942496043403e-06, "epoch": 17.853430353430355, "percentage": 89.27, "elapsed_time": "1:39:42", "remaining_time": "0:11:59", "throughput": 1034.07, "total_tokens": 6186736} {"current_steps": 68705, "total_steps": 76960, "loss": 0.0845, "lr": 1.732419852347511e-06, "epoch": 17.85472972972973, "percentage": 89.27, "elapsed_time": "1:39:43", "remaining_time": "0:11:58", "throughput": 1034.07, "total_tokens": 6187184} {"current_steps": 68710, "total_steps": 76960, "loss": 0.4741, "lr": 1.730346651764625e-06, "epoch": 17.856029106029105, "percentage": 89.28, "elapsed_time": "1:39:43", "remaining_time": "0:11:58", "throughput": 1034.08, "total_tokens": 6187632} {"current_steps": 68715, "total_steps": 76960, "loss": 0.1715, "lr": 1.728274647962305e-06, "epoch": 17.857328482328484, "percentage": 89.29, "elapsed_time": "1:39:44", "remaining_time": "0:11:58", "throughput": 1034.08, "total_tokens": 6188096} {"current_steps": 68720, "total_steps": 76960, "loss": 0.0675, "lr": 1.7262038410471193e-06, "epoch": 17.85862785862786, "percentage": 89.29, "elapsed_time": "1:39:44", "remaining_time": "0:11:57", "throughput": 1034.08, "total_tokens": 6188528} {"current_steps": 68725, "total_steps": 76960, "loss": 0.2131, "lr": 1.724134231125568e-06, "epoch": 17.859927234927234, "percentage": 89.3, "elapsed_time": "1:39:44", "remaining_time": "0:11:57", "throughput": 1034.09, "total_tokens": 6189008} {"current_steps": 68730, "total_steps": 76960, "loss": 0.0179, "lr": 1.7220658183040944e-06, "epoch": 17.861226611226613, "percentage": 89.31, "elapsed_time": "1:39:45", "remaining_time": "0:11:56", "throughput": 1034.09, "total_tokens": 6189456} {"current_steps": 68735, "total_steps": 76960, "loss": 0.0074, "lr": 1.7199986026890853e-06, "epoch": 17.862525987525988, "percentage": 89.31, "elapsed_time": "1:39:45", "remaining_time": "0:11:56", "throughput": 1034.09, "total_tokens": 6189888} {"current_steps": 68740, "total_steps": 76960, "loss": 0.1769, "lr": 1.717932584386847e-06, "epoch": 17.863825363825363, "percentage": 89.32, "elapsed_time": "1:39:46", "remaining_time": "0:11:55", "throughput": 1034.1, "total_tokens": 6190336} {"current_steps": 68745, "total_steps": 76960, "loss": 0.0076, "lr": 1.715867763503648e-06, "epoch": 17.86512474012474, "percentage": 89.33, "elapsed_time": "1:39:46", "remaining_time": "0:11:55", "throughput": 1034.1, "total_tokens": 6190816} {"current_steps": 68750, "total_steps": 76960, "loss": 0.1637, "lr": 1.7138041401456778e-06, "epoch": 17.866424116424117, "percentage": 89.33, "elapsed_time": "1:39:47", "remaining_time": "0:11:54", "throughput": 1034.1, "total_tokens": 6191232} {"current_steps": 68755, "total_steps": 76960, "loss": 0.2705, "lr": 1.711741714419074e-06, "epoch": 17.867723492723492, "percentage": 89.34, "elapsed_time": "1:39:47", "remaining_time": "0:11:54", "throughput": 1034.1, "total_tokens": 6191664} {"current_steps": 68760, "total_steps": 76960, "loss": 0.0273, "lr": 1.7096804864299015e-06, "epoch": 17.86902286902287, "percentage": 89.35, "elapsed_time": "1:39:47", "remaining_time": "0:11:54", "throughput": 1034.11, "total_tokens": 6192128} {"current_steps": 68765, "total_steps": 76960, "loss": 0.0003, "lr": 1.707620456284184e-06, "epoch": 17.870322245322246, "percentage": 89.35, "elapsed_time": "1:39:48", "remaining_time": "0:11:53", "throughput": 1034.11, "total_tokens": 6192592} {"current_steps": 68770, "total_steps": 76960, "loss": 0.1161, "lr": 1.7055616240878618e-06, "epoch": 17.87162162162162, "percentage": 89.36, "elapsed_time": "1:39:48", "remaining_time": "0:11:53", "throughput": 1034.12, "total_tokens": 6193040} {"current_steps": 68775, "total_steps": 76960, "loss": 0.057, "lr": 1.703503989946828e-06, "epoch": 17.872920997921, "percentage": 89.36, "elapsed_time": "1:39:49", "remaining_time": "0:11:52", "throughput": 1034.12, "total_tokens": 6193488} {"current_steps": 68780, "total_steps": 76960, "loss": 0.1459, "lr": 1.7014475539669005e-06, "epoch": 17.874220374220375, "percentage": 89.37, "elapsed_time": "1:39:49", "remaining_time": "0:11:52", "throughput": 1034.13, "total_tokens": 6193952} {"current_steps": 68785, "total_steps": 76960, "loss": 0.0035, "lr": 1.699392316253856e-06, "epoch": 17.87551975051975, "percentage": 89.38, "elapsed_time": "1:39:49", "remaining_time": "0:11:51", "throughput": 1034.13, "total_tokens": 6194400} {"current_steps": 68790, "total_steps": 76960, "loss": 0.208, "lr": 1.6973382769133823e-06, "epoch": 17.876819126819125, "percentage": 89.38, "elapsed_time": "1:39:50", "remaining_time": "0:11:51", "throughput": 1034.13, "total_tokens": 6194832} {"current_steps": 68795, "total_steps": 76960, "loss": 0.2351, "lr": 1.6952854360511305e-06, "epoch": 17.878118503118504, "percentage": 89.39, "elapsed_time": "1:39:50", "remaining_time": "0:11:51", "throughput": 1034.13, "total_tokens": 6195248} {"current_steps": 68800, "total_steps": 76960, "loss": 0.2619, "lr": 1.6932337937726834e-06, "epoch": 17.87941787941788, "percentage": 89.4, "elapsed_time": "1:39:51", "remaining_time": "0:11:50", "throughput": 1034.13, "total_tokens": 6195712} {"current_steps": 68805, "total_steps": 76960, "loss": 0.0027, "lr": 1.6911833501835478e-06, "epoch": 17.880717255717254, "percentage": 89.4, "elapsed_time": "1:39:51", "remaining_time": "0:11:50", "throughput": 1034.14, "total_tokens": 6196160} {"current_steps": 68810, "total_steps": 76960, "loss": 0.2926, "lr": 1.6891341053891896e-06, "epoch": 17.882016632016633, "percentage": 89.41, "elapsed_time": "1:39:52", "remaining_time": "0:11:49", "throughput": 1034.14, "total_tokens": 6196624} {"current_steps": 68815, "total_steps": 76960, "loss": 0.4479, "lr": 1.6870860594949966e-06, "epoch": 17.883316008316008, "percentage": 89.42, "elapsed_time": "1:39:52", "remaining_time": "0:11:49", "throughput": 1034.14, "total_tokens": 6197056} {"current_steps": 68820, "total_steps": 76960, "loss": 0.1409, "lr": 1.6850392126063097e-06, "epoch": 17.884615384615383, "percentage": 89.42, "elapsed_time": "1:39:52", "remaining_time": "0:11:48", "throughput": 1034.14, "total_tokens": 6197488} {"current_steps": 68825, "total_steps": 76960, "loss": 0.2754, "lr": 1.6829935648283918e-06, "epoch": 17.885914760914762, "percentage": 89.43, "elapsed_time": "1:39:53", "remaining_time": "0:11:48", "throughput": 1034.14, "total_tokens": 6197936} {"current_steps": 68830, "total_steps": 76960, "loss": 0.1238, "lr": 1.680949116266456e-06, "epoch": 17.887214137214137, "percentage": 89.44, "elapsed_time": "1:39:53", "remaining_time": "0:11:47", "throughput": 1034.14, "total_tokens": 6198368} {"current_steps": 68835, "total_steps": 76960, "loss": 0.2724, "lr": 1.6789058670256485e-06, "epoch": 17.888513513513512, "percentage": 89.44, "elapsed_time": "1:39:54", "remaining_time": "0:11:47", "throughput": 1034.14, "total_tokens": 6198800} {"current_steps": 68840, "total_steps": 76960, "loss": 0.013, "lr": 1.6768638172110606e-06, "epoch": 17.88981288981289, "percentage": 89.45, "elapsed_time": "1:39:54", "remaining_time": "0:11:47", "throughput": 1034.15, "total_tokens": 6199280} {"current_steps": 68845, "total_steps": 76960, "loss": 0.0004, "lr": 1.6748229669277138e-06, "epoch": 17.891112266112266, "percentage": 89.46, "elapsed_time": "1:39:54", "remaining_time": "0:11:46", "throughput": 1034.15, "total_tokens": 6199712} {"current_steps": 68850, "total_steps": 76960, "loss": 0.0109, "lr": 1.6727833162805711e-06, "epoch": 17.89241164241164, "percentage": 89.46, "elapsed_time": "1:39:55", "remaining_time": "0:11:46", "throughput": 1034.15, "total_tokens": 6200112} {"current_steps": 68855, "total_steps": 76960, "loss": 0.0016, "lr": 1.6707448653745323e-06, "epoch": 17.89371101871102, "percentage": 89.47, "elapsed_time": "1:39:55", "remaining_time": "0:11:45", "throughput": 1034.15, "total_tokens": 6200560} {"current_steps": 68860, "total_steps": 76960, "loss": 0.0171, "lr": 1.668707614314441e-06, "epoch": 17.895010395010395, "percentage": 89.48, "elapsed_time": "1:39:56", "remaining_time": "0:11:45", "throughput": 1034.15, "total_tokens": 6200992} {"current_steps": 68865, "total_steps": 76960, "loss": 0.1138, "lr": 1.666671563205069e-06, "epoch": 17.89630977130977, "percentage": 89.48, "elapsed_time": "1:39:56", "remaining_time": "0:11:44", "throughput": 1034.15, "total_tokens": 6201440} {"current_steps": 68870, "total_steps": 76960, "loss": 0.2155, "lr": 1.6646367121511326e-06, "epoch": 17.89760914760915, "percentage": 89.49, "elapsed_time": "1:39:57", "remaining_time": "0:11:44", "throughput": 1034.17, "total_tokens": 6201936} {"current_steps": 68875, "total_steps": 76960, "loss": 0.1688, "lr": 1.6626030612572951e-06, "epoch": 17.898908523908524, "percentage": 89.49, "elapsed_time": "1:39:57", "remaining_time": "0:11:44", "throughput": 1034.17, "total_tokens": 6202384} {"current_steps": 68880, "total_steps": 76960, "loss": 0.0052, "lr": 1.6605706106281399e-06, "epoch": 17.9002079002079, "percentage": 89.5, "elapsed_time": "1:39:57", "remaining_time": "0:11:43", "throughput": 1034.17, "total_tokens": 6202848} {"current_steps": 68885, "total_steps": 76960, "loss": 0.0564, "lr": 1.6585393603682026e-06, "epoch": 17.901507276507278, "percentage": 89.51, "elapsed_time": "1:39:58", "remaining_time": "0:11:43", "throughput": 1034.17, "total_tokens": 6203280} {"current_steps": 68890, "total_steps": 76960, "loss": 0.1719, "lr": 1.6565093105819468e-06, "epoch": 17.902806652806653, "percentage": 89.51, "elapsed_time": "1:39:58", "remaining_time": "0:11:42", "throughput": 1034.18, "total_tokens": 6203760} {"current_steps": 68895, "total_steps": 76960, "loss": 0.0044, "lr": 1.654480461373789e-06, "epoch": 17.90410602910603, "percentage": 89.52, "elapsed_time": "1:39:59", "remaining_time": "0:11:42", "throughput": 1034.19, "total_tokens": 6204224} {"current_steps": 68900, "total_steps": 76960, "loss": 0.3965, "lr": 1.6524528128480655e-06, "epoch": 17.905405405405407, "percentage": 89.53, "elapsed_time": "1:39:59", "remaining_time": "0:11:41", "throughput": 1034.19, "total_tokens": 6204672} {"current_steps": 68905, "total_steps": 76960, "loss": 0.3186, "lr": 1.6504263651090645e-06, "epoch": 17.906704781704782, "percentage": 89.53, "elapsed_time": "1:39:59", "remaining_time": "0:11:41", "throughput": 1034.19, "total_tokens": 6205088} {"current_steps": 68910, "total_steps": 76960, "loss": 0.1099, "lr": 1.6484011182610088e-06, "epoch": 17.908004158004157, "percentage": 89.54, "elapsed_time": "1:40:00", "remaining_time": "0:11:40", "throughput": 1034.19, "total_tokens": 6205536} {"current_steps": 68915, "total_steps": 76960, "loss": 0.0024, "lr": 1.6463770724080618e-06, "epoch": 17.909303534303533, "percentage": 89.55, "elapsed_time": "1:40:00", "remaining_time": "0:11:40", "throughput": 1034.2, "total_tokens": 6206000} {"current_steps": 68920, "total_steps": 76960, "loss": 0.0262, "lr": 1.6443542276543128e-06, "epoch": 17.91060291060291, "percentage": 89.55, "elapsed_time": "1:40:01", "remaining_time": "0:11:40", "throughput": 1034.2, "total_tokens": 6206432} {"current_steps": 68925, "total_steps": 76960, "loss": 0.2275, "lr": 1.642332584103809e-06, "epoch": 17.911902286902286, "percentage": 89.56, "elapsed_time": "1:40:01", "remaining_time": "0:11:39", "throughput": 1034.2, "total_tokens": 6206880} {"current_steps": 68930, "total_steps": 76960, "loss": 0.0873, "lr": 1.6403121418605172e-06, "epoch": 17.91320166320166, "percentage": 89.57, "elapsed_time": "1:40:02", "remaining_time": "0:11:39", "throughput": 1034.2, "total_tokens": 6207296} {"current_steps": 68935, "total_steps": 76960, "loss": 0.0121, "lr": 1.638292901028357e-06, "epoch": 17.91450103950104, "percentage": 89.57, "elapsed_time": "1:40:02", "remaining_time": "0:11:38", "throughput": 1034.2, "total_tokens": 6207728} {"current_steps": 68940, "total_steps": 76960, "loss": 0.0011, "lr": 1.6362748617111734e-06, "epoch": 17.915800415800415, "percentage": 89.58, "elapsed_time": "1:40:02", "remaining_time": "0:11:38", "throughput": 1034.2, "total_tokens": 6208192} {"current_steps": 68945, "total_steps": 76960, "loss": 0.1155, "lr": 1.6342580240127582e-06, "epoch": 17.91709979209979, "percentage": 89.59, "elapsed_time": "1:40:03", "remaining_time": "0:11:37", "throughput": 1034.2, "total_tokens": 6208640} {"current_steps": 68950, "total_steps": 76960, "loss": 0.027, "lr": 1.6322423880368477e-06, "epoch": 17.91839916839917, "percentage": 89.59, "elapsed_time": "1:40:03", "remaining_time": "0:11:37", "throughput": 1034.21, "total_tokens": 6209104} {"current_steps": 68955, "total_steps": 76960, "loss": 0.0937, "lr": 1.6302279538870952e-06, "epoch": 17.919698544698544, "percentage": 89.6, "elapsed_time": "1:40:04", "remaining_time": "0:11:37", "throughput": 1034.21, "total_tokens": 6209536} {"current_steps": 68960, "total_steps": 76960, "loss": 0.0009, "lr": 1.6282147216671152e-06, "epoch": 17.92099792099792, "percentage": 89.6, "elapsed_time": "1:40:04", "remaining_time": "0:11:36", "throughput": 1034.21, "total_tokens": 6209984} {"current_steps": 68965, "total_steps": 76960, "loss": 0.0068, "lr": 1.626202691480444e-06, "epoch": 17.9222972972973, "percentage": 89.61, "elapsed_time": "1:40:04", "remaining_time": "0:11:36", "throughput": 1034.21, "total_tokens": 6210416} {"current_steps": 68970, "total_steps": 76960, "loss": 0.3442, "lr": 1.6241918634305658e-06, "epoch": 17.923596673596673, "percentage": 89.62, "elapsed_time": "1:40:05", "remaining_time": "0:11:35", "throughput": 1034.22, "total_tokens": 6210896} {"current_steps": 68975, "total_steps": 76960, "loss": 0.2848, "lr": 1.6221822376208922e-06, "epoch": 17.92489604989605, "percentage": 89.62, "elapsed_time": "1:40:05", "remaining_time": "0:11:35", "throughput": 1034.22, "total_tokens": 6211312} {"current_steps": 68980, "total_steps": 76960, "loss": 0.1948, "lr": 1.620173814154788e-06, "epoch": 17.926195426195427, "percentage": 89.63, "elapsed_time": "1:40:06", "remaining_time": "0:11:34", "throughput": 1034.22, "total_tokens": 6211744} {"current_steps": 68985, "total_steps": 76960, "loss": 0.4566, "lr": 1.6181665931355478e-06, "epoch": 17.927494802494802, "percentage": 89.64, "elapsed_time": "1:40:06", "remaining_time": "0:11:34", "throughput": 1034.22, "total_tokens": 6212192} {"current_steps": 68990, "total_steps": 76960, "loss": 0.0243, "lr": 1.6161605746664032e-06, "epoch": 17.928794178794178, "percentage": 89.64, "elapsed_time": "1:40:07", "remaining_time": "0:11:33", "throughput": 1034.23, "total_tokens": 6212672} {"current_steps": 68995, "total_steps": 76960, "loss": 0.0012, "lr": 1.6141557588505246e-06, "epoch": 17.930093555093556, "percentage": 89.65, "elapsed_time": "1:40:07", "remaining_time": "0:11:33", "throughput": 1034.24, "total_tokens": 6213120} {"current_steps": 69000, "total_steps": 76960, "loss": 0.3782, "lr": 1.6121521457910239e-06, "epoch": 17.93139293139293, "percentage": 89.66, "elapsed_time": "1:40:07", "remaining_time": "0:11:33", "throughput": 1034.23, "total_tokens": 6213536} {"current_steps": 69005, "total_steps": 76960, "loss": 0.073, "lr": 1.610149735590949e-06, "epoch": 17.932692307692307, "percentage": 89.66, "elapsed_time": "1:40:08", "remaining_time": "0:11:32", "throughput": 1034.24, "total_tokens": 6214032} {"current_steps": 69010, "total_steps": 76960, "loss": 0.1672, "lr": 1.608148528353276e-06, "epoch": 17.933991683991685, "percentage": 89.67, "elapsed_time": "1:40:08", "remaining_time": "0:11:32", "throughput": 1034.25, "total_tokens": 6214480} {"current_steps": 69015, "total_steps": 76960, "loss": 0.4313, "lr": 1.6061485241809449e-06, "epoch": 17.93529106029106, "percentage": 89.68, "elapsed_time": "1:40:09", "remaining_time": "0:11:31", "throughput": 1034.25, "total_tokens": 6214944} {"current_steps": 69020, "total_steps": 76960, "loss": 0.0003, "lr": 1.6041497231768066e-06, "epoch": 17.936590436590436, "percentage": 89.68, "elapsed_time": "1:40:09", "remaining_time": "0:11:31", "throughput": 1034.25, "total_tokens": 6215376} {"current_steps": 69025, "total_steps": 76960, "loss": 0.1179, "lr": 1.6021521254436678e-06, "epoch": 17.937889812889814, "percentage": 89.69, "elapsed_time": "1:40:09", "remaining_time": "0:11:30", "throughput": 1034.26, "total_tokens": 6215840} {"current_steps": 69030, "total_steps": 76960, "loss": 0.0008, "lr": 1.600155731084263e-06, "epoch": 17.93918918918919, "percentage": 89.7, "elapsed_time": "1:40:10", "remaining_time": "0:11:30", "throughput": 1034.26, "total_tokens": 6216304} {"current_steps": 69035, "total_steps": 76960, "loss": 0.0572, "lr": 1.5981605402012711e-06, "epoch": 17.940488565488565, "percentage": 89.7, "elapsed_time": "1:40:10", "remaining_time": "0:11:30", "throughput": 1034.27, "total_tokens": 6216752} {"current_steps": 69040, "total_steps": 76960, "loss": 0.0062, "lr": 1.5961665528973019e-06, "epoch": 17.941787941787943, "percentage": 89.71, "elapsed_time": "1:40:11", "remaining_time": "0:11:29", "throughput": 1034.27, "total_tokens": 6217200} {"current_steps": 69045, "total_steps": 76960, "loss": 0.2335, "lr": 1.5941737692749091e-06, "epoch": 17.94308731808732, "percentage": 89.72, "elapsed_time": "1:40:11", "remaining_time": "0:11:29", "throughput": 1034.28, "total_tokens": 6217664} {"current_steps": 69050, "total_steps": 76960, "loss": 0.0422, "lr": 1.592182189436589e-06, "epoch": 17.944386694386694, "percentage": 89.72, "elapsed_time": "1:40:12", "remaining_time": "0:11:28", "throughput": 1034.28, "total_tokens": 6218128} {"current_steps": 69055, "total_steps": 76960, "loss": 0.0061, "lr": 1.5901918134847676e-06, "epoch": 17.945686070686072, "percentage": 89.73, "elapsed_time": "1:40:12", "remaining_time": "0:11:28", "throughput": 1034.28, "total_tokens": 6218576} {"current_steps": 69060, "total_steps": 76960, "loss": 0.1322, "lr": 1.5882026415218105e-06, "epoch": 17.946985446985448, "percentage": 89.73, "elapsed_time": "1:40:12", "remaining_time": "0:11:27", "throughput": 1034.28, "total_tokens": 6218992} {"current_steps": 69065, "total_steps": 76960, "loss": 0.1962, "lr": 1.5862146736500272e-06, "epoch": 17.948284823284823, "percentage": 89.74, "elapsed_time": "1:40:13", "remaining_time": "0:11:27", "throughput": 1034.29, "total_tokens": 6219440} {"current_steps": 69070, "total_steps": 76960, "loss": 0.1373, "lr": 1.5842279099716556e-06, "epoch": 17.9495841995842, "percentage": 89.75, "elapsed_time": "1:40:13", "remaining_time": "0:11:26", "throughput": 1034.28, "total_tokens": 6219856} {"current_steps": 69075, "total_steps": 76960, "loss": 0.4722, "lr": 1.5822423505888778e-06, "epoch": 17.950883575883577, "percentage": 89.75, "elapsed_time": "1:40:14", "remaining_time": "0:11:26", "throughput": 1034.29, "total_tokens": 6220304} {"current_steps": 69080, "total_steps": 76960, "loss": 0.0075, "lr": 1.5802579956038095e-06, "epoch": 17.95218295218295, "percentage": 89.76, "elapsed_time": "1:40:14", "remaining_time": "0:11:26", "throughput": 1034.28, "total_tokens": 6220704} {"current_steps": 69085, "total_steps": 76960, "loss": 0.0758, "lr": 1.578274845118516e-06, "epoch": 17.953482328482327, "percentage": 89.77, "elapsed_time": "1:40:14", "remaining_time": "0:11:25", "throughput": 1034.29, "total_tokens": 6221184} {"current_steps": 69090, "total_steps": 76960, "loss": 0.1328, "lr": 1.5762928992349907e-06, "epoch": 17.954781704781706, "percentage": 89.77, "elapsed_time": "1:40:15", "remaining_time": "0:11:25", "throughput": 1034.29, "total_tokens": 6221632} {"current_steps": 69095, "total_steps": 76960, "loss": 0.001, "lr": 1.5743121580551607e-06, "epoch": 17.95608108108108, "percentage": 89.78, "elapsed_time": "1:40:15", "remaining_time": "0:11:24", "throughput": 1034.3, "total_tokens": 6222112} {"current_steps": 69100, "total_steps": 76960, "loss": 0.2161, "lr": 1.5723326216809082e-06, "epoch": 17.957380457380456, "percentage": 89.79, "elapsed_time": "1:40:16", "remaining_time": "0:11:24", "throughput": 1034.31, "total_tokens": 6222592} {"current_steps": 69105, "total_steps": 76960, "loss": 0.0556, "lr": 1.5703542902140294e-06, "epoch": 17.958679833679835, "percentage": 89.79, "elapsed_time": "1:40:16", "remaining_time": "0:11:23", "throughput": 1034.31, "total_tokens": 6223056} {"current_steps": 69110, "total_steps": 76960, "loss": 0.0011, "lr": 1.568377163756285e-06, "epoch": 17.95997920997921, "percentage": 89.8, "elapsed_time": "1:40:17", "remaining_time": "0:11:23", "throughput": 1034.32, "total_tokens": 6223504} {"current_steps": 69115, "total_steps": 76960, "loss": 0.294, "lr": 1.5664012424093488e-06, "epoch": 17.961278586278585, "percentage": 89.81, "elapsed_time": "1:40:17", "remaining_time": "0:11:23", "throughput": 1034.32, "total_tokens": 6223952} {"current_steps": 69120, "total_steps": 76960, "loss": 0.0009, "lr": 1.5644265262748508e-06, "epoch": 17.962577962577964, "percentage": 89.81, "elapsed_time": "1:40:17", "remaining_time": "0:11:22", "throughput": 1034.33, "total_tokens": 6224432} {"current_steps": 69125, "total_steps": 76960, "loss": 0.262, "lr": 1.5624530154543487e-06, "epoch": 17.96387733887734, "percentage": 89.82, "elapsed_time": "1:40:18", "remaining_time": "0:11:22", "throughput": 1034.33, "total_tokens": 6224880} {"current_steps": 69130, "total_steps": 76960, "loss": 0.2479, "lr": 1.5604807100493528e-06, "epoch": 17.965176715176714, "percentage": 89.83, "elapsed_time": "1:40:18", "remaining_time": "0:11:21", "throughput": 1034.33, "total_tokens": 6225296} {"current_steps": 69135, "total_steps": 76960, "loss": 0.0581, "lr": 1.5585096101612906e-06, "epoch": 17.966476091476093, "percentage": 89.83, "elapsed_time": "1:40:19", "remaining_time": "0:11:21", "throughput": 1034.34, "total_tokens": 6225792} {"current_steps": 69140, "total_steps": 76960, "loss": 0.0021, "lr": 1.5565397158915363e-06, "epoch": 17.967775467775468, "percentage": 89.84, "elapsed_time": "1:40:19", "remaining_time": "0:11:20", "throughput": 1034.34, "total_tokens": 6226208} {"current_steps": 69145, "total_steps": 76960, "loss": 0.019, "lr": 1.5545710273414089e-06, "epoch": 17.969074844074843, "percentage": 89.85, "elapsed_time": "1:40:19", "remaining_time": "0:11:20", "throughput": 1034.34, "total_tokens": 6226656} {"current_steps": 69150, "total_steps": 76960, "loss": 0.4775, "lr": 1.552603544612155e-06, "epoch": 17.97037422037422, "percentage": 89.85, "elapsed_time": "1:40:20", "remaining_time": "0:11:19", "throughput": 1034.34, "total_tokens": 6227088} {"current_steps": 69155, "total_steps": 76960, "loss": 0.0029, "lr": 1.550637267804969e-06, "epoch": 17.971673596673597, "percentage": 89.86, "elapsed_time": "1:40:20", "remaining_time": "0:11:19", "throughput": 1034.35, "total_tokens": 6227552} {"current_steps": 69160, "total_steps": 76960, "loss": 0.0381, "lr": 1.5486721970209727e-06, "epoch": 17.972972972972972, "percentage": 89.86, "elapsed_time": "1:40:21", "remaining_time": "0:11:19", "throughput": 1034.35, "total_tokens": 6227984} {"current_steps": 69165, "total_steps": 76960, "loss": 0.0795, "lr": 1.5467083323612408e-06, "epoch": 17.97427234927235, "percentage": 89.87, "elapsed_time": "1:40:21", "remaining_time": "0:11:18", "throughput": 1034.35, "total_tokens": 6228448} {"current_steps": 69170, "total_steps": 76960, "loss": 0.1629, "lr": 1.54474567392677e-06, "epoch": 17.975571725571726, "percentage": 89.88, "elapsed_time": "1:40:22", "remaining_time": "0:11:18", "throughput": 1034.35, "total_tokens": 6228880} {"current_steps": 69175, "total_steps": 76960, "loss": 0.5177, "lr": 1.5427842218185025e-06, "epoch": 17.9768711018711, "percentage": 89.88, "elapsed_time": "1:40:22", "remaining_time": "0:11:17", "throughput": 1034.36, "total_tokens": 6229360} {"current_steps": 69180, "total_steps": 76960, "loss": 0.1297, "lr": 1.5408239761373177e-06, "epoch": 17.97817047817048, "percentage": 89.89, "elapsed_time": "1:40:22", "remaining_time": "0:11:17", "throughput": 1034.36, "total_tokens": 6229808} {"current_steps": 69185, "total_steps": 76960, "loss": 0.2143, "lr": 1.5388649369840357e-06, "epoch": 17.979469854469855, "percentage": 89.9, "elapsed_time": "1:40:23", "remaining_time": "0:11:16", "throughput": 1034.36, "total_tokens": 6230240} {"current_steps": 69190, "total_steps": 76960, "loss": 0.0907, "lr": 1.5369071044594063e-06, "epoch": 17.98076923076923, "percentage": 89.9, "elapsed_time": "1:40:23", "remaining_time": "0:11:16", "throughput": 1034.37, "total_tokens": 6230704} {"current_steps": 69195, "total_steps": 76960, "loss": 0.1895, "lr": 1.5349504786641239e-06, "epoch": 17.98206860706861, "percentage": 89.91, "elapsed_time": "1:40:24", "remaining_time": "0:11:16", "throughput": 1034.37, "total_tokens": 6231120} {"current_steps": 69200, "total_steps": 76960, "loss": 0.0028, "lr": 1.5329950596988273e-06, "epoch": 17.983367983367984, "percentage": 89.92, "elapsed_time": "1:40:24", "remaining_time": "0:11:15", "throughput": 1034.37, "total_tokens": 6231568} {"current_steps": 69205, "total_steps": 76960, "loss": 0.147, "lr": 1.5310408476640754e-06, "epoch": 17.98466735966736, "percentage": 89.92, "elapsed_time": "1:40:24", "remaining_time": "0:11:15", "throughput": 1034.37, "total_tokens": 6232016} {"current_steps": 69210, "total_steps": 76960, "loss": 0.0087, "lr": 1.5290878426603817e-06, "epoch": 17.985966735966738, "percentage": 89.93, "elapsed_time": "1:40:25", "remaining_time": "0:11:14", "throughput": 1034.38, "total_tokens": 6232464} {"current_steps": 69215, "total_steps": 76960, "loss": 0.1365, "lr": 1.5271360447881883e-06, "epoch": 17.987266112266113, "percentage": 89.94, "elapsed_time": "1:40:25", "remaining_time": "0:11:14", "throughput": 1034.38, "total_tokens": 6232896} {"current_steps": 69220, "total_steps": 76960, "loss": 0.3481, "lr": 1.5251854541478788e-06, "epoch": 17.988565488565488, "percentage": 89.94, "elapsed_time": "1:40:26", "remaining_time": "0:11:13", "throughput": 1034.37, "total_tokens": 6233312} {"current_steps": 69225, "total_steps": 76960, "loss": 0.0791, "lr": 1.523236070839773e-06, "epoch": 17.989864864864863, "percentage": 89.95, "elapsed_time": "1:40:26", "remaining_time": "0:11:13", "throughput": 1034.37, "total_tokens": 6233744} {"current_steps": 69230, "total_steps": 76960, "loss": 0.1906, "lr": 1.5212878949641296e-06, "epoch": 17.991164241164242, "percentage": 89.96, "elapsed_time": "1:40:27", "remaining_time": "0:11:12", "throughput": 1034.37, "total_tokens": 6234176} {"current_steps": 69235, "total_steps": 76960, "loss": 0.0002, "lr": 1.5193409266211462e-06, "epoch": 17.992463617463617, "percentage": 89.96, "elapsed_time": "1:40:27", "remaining_time": "0:11:12", "throughput": 1034.39, "total_tokens": 6234688} {"current_steps": 69240, "total_steps": 76960, "loss": 0.0945, "lr": 1.5173951659109592e-06, "epoch": 17.993762993762992, "percentage": 89.97, "elapsed_time": "1:40:27", "remaining_time": "0:11:12", "throughput": 1034.39, "total_tokens": 6235104} {"current_steps": 69245, "total_steps": 76960, "loss": 0.2616, "lr": 1.5154506129336388e-06, "epoch": 17.99506237006237, "percentage": 89.98, "elapsed_time": "1:40:28", "remaining_time": "0:11:11", "throughput": 1034.39, "total_tokens": 6235536} {"current_steps": 69250, "total_steps": 76960, "loss": 0.2545, "lr": 1.5135072677891965e-06, "epoch": 17.996361746361746, "percentage": 89.98, "elapsed_time": "1:40:28", "remaining_time": "0:11:11", "throughput": 1034.39, "total_tokens": 6236000} {"current_steps": 69255, "total_steps": 76960, "loss": 0.2349, "lr": 1.5115651305775746e-06, "epoch": 17.99766112266112, "percentage": 89.99, "elapsed_time": "1:40:29", "remaining_time": "0:11:10", "throughput": 1034.39, "total_tokens": 6236432} {"current_steps": 69260, "total_steps": 76960, "loss": 0.2789, "lr": 1.5096242013986628e-06, "epoch": 17.9989604989605, "percentage": 89.99, "elapsed_time": "1:40:29", "remaining_time": "0:11:10", "throughput": 1034.4, "total_tokens": 6236880} {"current_steps": 69264, "total_steps": 76960, "eval_loss": 0.7981295585632324, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "1:40:43", "remaining_time": "0:11:11", "throughput": 1032.13, "total_tokens": 6237200} {"current_steps": 69265, "total_steps": 76960, "loss": 0.0052, "lr": 1.5076844803522922e-06, "epoch": 18.000259875259875, "percentage": 90.0, "elapsed_time": "1:40:44", "remaining_time": "0:11:11", "throughput": 1031.82, "total_tokens": 6237280} {"current_steps": 69270, "total_steps": 76960, "loss": 0.1424, "lr": 1.5057459675382134e-06, "epoch": 18.00155925155925, "percentage": 90.01, "elapsed_time": "1:40:45", "remaining_time": "0:11:11", "throughput": 1031.83, "total_tokens": 6237728} {"current_steps": 69275, "total_steps": 76960, "loss": 0.0736, "lr": 1.5038086630561332e-06, "epoch": 18.00285862785863, "percentage": 90.01, "elapsed_time": "1:40:45", "remaining_time": "0:11:10", "throughput": 1031.83, "total_tokens": 6238240} {"current_steps": 69280, "total_steps": 76960, "loss": 0.0068, "lr": 1.5018725670056826e-06, "epoch": 18.004158004158004, "percentage": 90.02, "elapsed_time": "1:40:46", "remaining_time": "0:11:10", "throughput": 1031.83, "total_tokens": 6238688} {"current_steps": 69285, "total_steps": 76960, "loss": 0.0697, "lr": 1.4999376794864462e-06, "epoch": 18.00545738045738, "percentage": 90.03, "elapsed_time": "1:40:46", "remaining_time": "0:11:09", "throughput": 1031.85, "total_tokens": 6239184} {"current_steps": 69290, "total_steps": 76960, "loss": 0.0234, "lr": 1.4980040005979273e-06, "epoch": 18.006756756756758, "percentage": 90.03, "elapsed_time": "1:40:47", "remaining_time": "0:11:09", "throughput": 1031.84, "total_tokens": 6239616} {"current_steps": 69295, "total_steps": 76960, "loss": 0.2157, "lr": 1.49607153043958e-06, "epoch": 18.008056133056133, "percentage": 90.04, "elapsed_time": "1:40:47", "remaining_time": "0:11:08", "throughput": 1031.84, "total_tokens": 6240064} {"current_steps": 69300, "total_steps": 76960, "loss": 0.008, "lr": 1.4941402691107969e-06, "epoch": 18.009355509355508, "percentage": 90.05, "elapsed_time": "1:40:47", "remaining_time": "0:11:08", "throughput": 1031.85, "total_tokens": 6240560} {"current_steps": 69305, "total_steps": 76960, "loss": 0.0958, "lr": 1.4922102167109015e-06, "epoch": 18.010654885654887, "percentage": 90.05, "elapsed_time": "1:40:48", "remaining_time": "0:11:08", "throughput": 1031.86, "total_tokens": 6241024} {"current_steps": 69310, "total_steps": 76960, "loss": 0.0202, "lr": 1.4902813733391586e-06, "epoch": 18.011954261954262, "percentage": 90.06, "elapsed_time": "1:40:48", "remaining_time": "0:11:07", "throughput": 1031.85, "total_tokens": 6241440} {"current_steps": 69315, "total_steps": 76960, "loss": 0.1325, "lr": 1.4883537390947722e-06, "epoch": 18.013253638253637, "percentage": 90.07, "elapsed_time": "1:40:49", "remaining_time": "0:11:07", "throughput": 1031.86, "total_tokens": 6241904} {"current_steps": 69320, "total_steps": 76960, "loss": 0.1273, "lr": 1.4864273140768797e-06, "epoch": 18.014553014553016, "percentage": 90.07, "elapsed_time": "1:40:49", "remaining_time": "0:11:06", "throughput": 1031.86, "total_tokens": 6242336} {"current_steps": 69325, "total_steps": 76960, "loss": 0.0197, "lr": 1.4845020983845603e-06, "epoch": 18.01585239085239, "percentage": 90.08, "elapsed_time": "1:40:50", "remaining_time": "0:11:06", "throughput": 1031.86, "total_tokens": 6242784} {"current_steps": 69330, "total_steps": 76960, "loss": 0.0012, "lr": 1.4825780921168293e-06, "epoch": 18.017151767151766, "percentage": 90.09, "elapsed_time": "1:40:50", "remaining_time": "0:11:05", "throughput": 1031.87, "total_tokens": 6243264} {"current_steps": 69335, "total_steps": 76960, "loss": 0.0027, "lr": 1.4806552953726377e-06, "epoch": 18.018451143451145, "percentage": 90.09, "elapsed_time": "1:40:50", "remaining_time": "0:11:05", "throughput": 1031.87, "total_tokens": 6243680} {"current_steps": 69340, "total_steps": 76960, "loss": 0.0041, "lr": 1.4787337082508846e-06, "epoch": 18.01975051975052, "percentage": 90.1, "elapsed_time": "1:40:51", "remaining_time": "0:11:04", "throughput": 1031.87, "total_tokens": 6244144} {"current_steps": 69345, "total_steps": 76960, "loss": 0.0649, "lr": 1.476813330850388e-06, "epoch": 18.021049896049895, "percentage": 90.11, "elapsed_time": "1:40:51", "remaining_time": "0:11:04", "throughput": 1031.88, "total_tokens": 6244592} {"current_steps": 69350, "total_steps": 76960, "loss": 0.0142, "lr": 1.4748941632699271e-06, "epoch": 18.022349272349274, "percentage": 90.11, "elapsed_time": "1:40:52", "remaining_time": "0:11:04", "throughput": 1031.88, "total_tokens": 6245056} {"current_steps": 69355, "total_steps": 76960, "loss": 0.0115, "lr": 1.4729762056081952e-06, "epoch": 18.02364864864865, "percentage": 90.12, "elapsed_time": "1:40:52", "remaining_time": "0:11:03", "throughput": 1031.88, "total_tokens": 6245504} {"current_steps": 69360, "total_steps": 76960, "loss": 0.0018, "lr": 1.4710594579638443e-06, "epoch": 18.024948024948024, "percentage": 90.12, "elapsed_time": "1:40:52", "remaining_time": "0:11:03", "throughput": 1031.89, "total_tokens": 6245952} {"current_steps": 69365, "total_steps": 76960, "loss": 0.1706, "lr": 1.4691439204354424e-06, "epoch": 18.026247401247403, "percentage": 90.13, "elapsed_time": "1:40:53", "remaining_time": "0:11:02", "throughput": 1031.89, "total_tokens": 6246384} {"current_steps": 69370, "total_steps": 76960, "loss": 0.001, "lr": 1.4672295931215192e-06, "epoch": 18.027546777546778, "percentage": 90.14, "elapsed_time": "1:40:53", "remaining_time": "0:11:02", "throughput": 1031.88, "total_tokens": 6246800} {"current_steps": 69375, "total_steps": 76960, "loss": 0.0554, "lr": 1.4653164761205235e-06, "epoch": 18.028846153846153, "percentage": 90.14, "elapsed_time": "1:40:54", "remaining_time": "0:11:01", "throughput": 1031.88, "total_tokens": 6247216} {"current_steps": 69380, "total_steps": 76960, "loss": 0.0013, "lr": 1.4634045695308574e-06, "epoch": 18.03014553014553, "percentage": 90.15, "elapsed_time": "1:40:54", "remaining_time": "0:11:01", "throughput": 1031.88, "total_tokens": 6247648} {"current_steps": 69385, "total_steps": 76960, "loss": 0.0149, "lr": 1.4614938734508392e-06, "epoch": 18.031444906444907, "percentage": 90.16, "elapsed_time": "1:40:55", "remaining_time": "0:11:01", "throughput": 1031.88, "total_tokens": 6248096} {"current_steps": 69390, "total_steps": 76960, "loss": 0.0154, "lr": 1.459584387978749e-06, "epoch": 18.032744282744282, "percentage": 90.16, "elapsed_time": "1:40:55", "remaining_time": "0:11:00", "throughput": 1031.88, "total_tokens": 6248528} {"current_steps": 69395, "total_steps": 76960, "loss": 0.0105, "lr": 1.4576761132127915e-06, "epoch": 18.034043659043657, "percentage": 90.17, "elapsed_time": "1:40:55", "remaining_time": "0:11:00", "throughput": 1031.88, "total_tokens": 6248944} {"current_steps": 69400, "total_steps": 76960, "loss": 0.3879, "lr": 1.4557690492511016e-06, "epoch": 18.035343035343036, "percentage": 90.18, "elapsed_time": "1:40:56", "remaining_time": "0:10:59", "throughput": 1031.88, "total_tokens": 6249392} {"current_steps": 69405, "total_steps": 76960, "loss": 0.0132, "lr": 1.4538631961917709e-06, "epoch": 18.03664241164241, "percentage": 90.18, "elapsed_time": "1:40:56", "remaining_time": "0:10:59", "throughput": 1031.89, "total_tokens": 6249840} {"current_steps": 69410, "total_steps": 76960, "loss": 0.0058, "lr": 1.451958554132815e-06, "epoch": 18.037941787941786, "percentage": 90.19, "elapsed_time": "1:40:57", "remaining_time": "0:10:58", "throughput": 1031.89, "total_tokens": 6250320} {"current_steps": 69415, "total_steps": 76960, "loss": 0.2512, "lr": 1.4500551231722004e-06, "epoch": 18.039241164241165, "percentage": 90.2, "elapsed_time": "1:40:57", "remaining_time": "0:10:58", "throughput": 1031.89, "total_tokens": 6250752} {"current_steps": 69420, "total_steps": 76960, "loss": 0.0368, "lr": 1.4481529034078067e-06, "epoch": 18.04054054054054, "percentage": 90.2, "elapsed_time": "1:40:57", "remaining_time": "0:10:57", "throughput": 1031.91, "total_tokens": 6251264} {"current_steps": 69425, "total_steps": 76960, "loss": 0.0315, "lr": 1.4462518949374838e-06, "epoch": 18.041839916839916, "percentage": 90.21, "elapsed_time": "1:40:58", "remaining_time": "0:10:57", "throughput": 1031.91, "total_tokens": 6251680} {"current_steps": 69430, "total_steps": 76960, "loss": 0.0637, "lr": 1.4443520978589864e-06, "epoch": 18.043139293139294, "percentage": 90.22, "elapsed_time": "1:40:58", "remaining_time": "0:10:57", "throughput": 1031.9, "total_tokens": 6252096} {"current_steps": 69435, "total_steps": 76960, "loss": 0.0449, "lr": 1.4424535122700367e-06, "epoch": 18.04443866943867, "percentage": 90.22, "elapsed_time": "1:40:59", "remaining_time": "0:10:56", "throughput": 1031.91, "total_tokens": 6252592} {"current_steps": 69440, "total_steps": 76960, "loss": 0.0282, "lr": 1.4405561382682703e-06, "epoch": 18.045738045738045, "percentage": 90.23, "elapsed_time": "1:40:59", "remaining_time": "0:10:56", "throughput": 1031.92, "total_tokens": 6253024} {"current_steps": 69445, "total_steps": 76960, "loss": 0.0936, "lr": 1.4386599759512759e-06, "epoch": 18.047037422037423, "percentage": 90.24, "elapsed_time": "1:41:00", "remaining_time": "0:10:55", "throughput": 1031.92, "total_tokens": 6253456} {"current_steps": 69450, "total_steps": 76960, "loss": 0.4387, "lr": 1.4367650254165727e-06, "epoch": 18.0483367983368, "percentage": 90.24, "elapsed_time": "1:41:00", "remaining_time": "0:10:55", "throughput": 1031.92, "total_tokens": 6253920} {"current_steps": 69455, "total_steps": 76960, "loss": 0.0002, "lr": 1.434871286761627e-06, "epoch": 18.049636174636174, "percentage": 90.25, "elapsed_time": "1:41:00", "remaining_time": "0:10:54", "throughput": 1031.92, "total_tokens": 6254352} {"current_steps": 69460, "total_steps": 76960, "loss": 0.0205, "lr": 1.4329787600838308e-06, "epoch": 18.050935550935552, "percentage": 90.25, "elapsed_time": "1:41:01", "remaining_time": "0:10:54", "throughput": 1031.93, "total_tokens": 6254816} {"current_steps": 69465, "total_steps": 76960, "loss": 0.037, "lr": 1.4310874454805112e-06, "epoch": 18.052234927234927, "percentage": 90.26, "elapsed_time": "1:41:01", "remaining_time": "0:10:54", "throughput": 1031.93, "total_tokens": 6255264} {"current_steps": 69470, "total_steps": 76960, "loss": 0.052, "lr": 1.429197343048952e-06, "epoch": 18.053534303534303, "percentage": 90.27, "elapsed_time": "1:41:02", "remaining_time": "0:10:53", "throughput": 1031.94, "total_tokens": 6255728} {"current_steps": 69475, "total_steps": 76960, "loss": 0.1197, "lr": 1.4273084528863529e-06, "epoch": 18.05483367983368, "percentage": 90.27, "elapsed_time": "1:41:02", "remaining_time": "0:10:53", "throughput": 1031.94, "total_tokens": 6256192} {"current_steps": 69480, "total_steps": 76960, "loss": 0.3774, "lr": 1.4254207750898696e-06, "epoch": 18.056133056133056, "percentage": 90.28, "elapsed_time": "1:41:02", "remaining_time": "0:10:52", "throughput": 1031.94, "total_tokens": 6256624} {"current_steps": 69485, "total_steps": 76960, "loss": 0.1141, "lr": 1.42353430975658e-06, "epoch": 18.05743243243243, "percentage": 90.29, "elapsed_time": "1:41:03", "remaining_time": "0:10:52", "throughput": 1031.96, "total_tokens": 6257136} {"current_steps": 69490, "total_steps": 76960, "loss": 0.0031, "lr": 1.4216490569835178e-06, "epoch": 18.05873180873181, "percentage": 90.29, "elapsed_time": "1:41:03", "remaining_time": "0:10:51", "throughput": 1031.96, "total_tokens": 6257600} {"current_steps": 69495, "total_steps": 76960, "loss": 0.0001, "lr": 1.4197650168676301e-06, "epoch": 18.060031185031185, "percentage": 90.3, "elapsed_time": "1:41:04", "remaining_time": "0:10:51", "throughput": 1031.96, "total_tokens": 6258048} {"current_steps": 69500, "total_steps": 76960, "loss": 0.0002, "lr": 1.417882189505826e-06, "epoch": 18.06133056133056, "percentage": 90.31, "elapsed_time": "1:41:04", "remaining_time": "0:10:50", "throughput": 1031.97, "total_tokens": 6258528} {"current_steps": 69505, "total_steps": 76960, "loss": 0.0515, "lr": 1.4160005749949328e-06, "epoch": 18.06262993762994, "percentage": 90.31, "elapsed_time": "1:41:05", "remaining_time": "0:10:50", "throughput": 1031.98, "total_tokens": 6259008} {"current_steps": 69510, "total_steps": 76960, "loss": 0.1545, "lr": 1.4141201734317267e-06, "epoch": 18.063929313929314, "percentage": 90.32, "elapsed_time": "1:41:05", "remaining_time": "0:10:50", "throughput": 1031.98, "total_tokens": 6259440} {"current_steps": 69515, "total_steps": 76960, "loss": 0.0191, "lr": 1.4122409849129186e-06, "epoch": 18.06522869022869, "percentage": 90.33, "elapsed_time": "1:41:05", "remaining_time": "0:10:49", "throughput": 1031.98, "total_tokens": 6259888} {"current_steps": 69520, "total_steps": 76960, "loss": 0.0586, "lr": 1.4103630095351622e-06, "epoch": 18.066528066528065, "percentage": 90.33, "elapsed_time": "1:41:06", "remaining_time": "0:10:49", "throughput": 1031.98, "total_tokens": 6260304} {"current_steps": 69525, "total_steps": 76960, "loss": 0.0008, "lr": 1.4084862473950383e-06, "epoch": 18.067827442827443, "percentage": 90.34, "elapsed_time": "1:41:06", "remaining_time": "0:10:48", "throughput": 1031.98, "total_tokens": 6260736} {"current_steps": 69530, "total_steps": 76960, "loss": 0.1369, "lr": 1.406610698589067e-06, "epoch": 18.06912681912682, "percentage": 90.35, "elapsed_time": "1:41:07", "remaining_time": "0:10:48", "throughput": 1031.99, "total_tokens": 6261232} {"current_steps": 69535, "total_steps": 76960, "loss": 0.2086, "lr": 1.4047363632137157e-06, "epoch": 18.070426195426194, "percentage": 90.35, "elapsed_time": "1:41:07", "remaining_time": "0:10:47", "throughput": 1031.99, "total_tokens": 6261664} {"current_steps": 69540, "total_steps": 76960, "loss": 0.0008, "lr": 1.4028632413653792e-06, "epoch": 18.071725571725572, "percentage": 90.36, "elapsed_time": "1:41:07", "remaining_time": "0:10:47", "throughput": 1032.0, "total_tokens": 6262160} {"current_steps": 69545, "total_steps": 76960, "loss": 0.0051, "lr": 1.4009913331403945e-06, "epoch": 18.073024948024948, "percentage": 90.37, "elapsed_time": "1:41:08", "remaining_time": "0:10:47", "throughput": 1032.0, "total_tokens": 6262576} {"current_steps": 69550, "total_steps": 76960, "loss": 0.0047, "lr": 1.3991206386350403e-06, "epoch": 18.074324324324323, "percentage": 90.37, "elapsed_time": "1:41:08", "remaining_time": "0:10:46", "throughput": 1032.0, "total_tokens": 6263024} {"current_steps": 69555, "total_steps": 76960, "loss": 0.3761, "lr": 1.3972511579455254e-06, "epoch": 18.0756237006237, "percentage": 90.38, "elapsed_time": "1:41:09", "remaining_time": "0:10:46", "throughput": 1032.01, "total_tokens": 6263488} {"current_steps": 69560, "total_steps": 76960, "loss": 0.0078, "lr": 1.3953828911679955e-06, "epoch": 18.076923076923077, "percentage": 90.38, "elapsed_time": "1:41:09", "remaining_time": "0:10:45", "throughput": 1032.01, "total_tokens": 6263920} {"current_steps": 69565, "total_steps": 76960, "loss": 0.1414, "lr": 1.3935158383985431e-06, "epoch": 18.078222453222452, "percentage": 90.39, "elapsed_time": "1:41:10", "remaining_time": "0:10:45", "throughput": 1032.01, "total_tokens": 6264336} {"current_steps": 69570, "total_steps": 76960, "loss": 0.1511, "lr": 1.3916499997331883e-06, "epoch": 18.07952182952183, "percentage": 90.4, "elapsed_time": "1:41:10", "remaining_time": "0:10:44", "throughput": 1032.01, "total_tokens": 6264768} {"current_steps": 69575, "total_steps": 76960, "loss": 0.2205, "lr": 1.3897853752678964e-06, "epoch": 18.080821205821206, "percentage": 90.4, "elapsed_time": "1:41:10", "remaining_time": "0:10:44", "throughput": 1032.01, "total_tokens": 6265232} {"current_steps": 69580, "total_steps": 76960, "loss": 0.1612, "lr": 1.3879219650985625e-06, "epoch": 18.08212058212058, "percentage": 90.41, "elapsed_time": "1:41:11", "remaining_time": "0:10:43", "throughput": 1032.02, "total_tokens": 6265680} {"current_steps": 69585, "total_steps": 76960, "loss": 0.0016, "lr": 1.386059769321027e-06, "epoch": 18.08341995841996, "percentage": 90.42, "elapsed_time": "1:41:11", "remaining_time": "0:10:43", "throughput": 1032.02, "total_tokens": 6266128} {"current_steps": 69590, "total_steps": 76960, "loss": 0.0717, "lr": 1.384198788031063e-06, "epoch": 18.084719334719335, "percentage": 90.42, "elapsed_time": "1:41:12", "remaining_time": "0:10:43", "throughput": 1032.02, "total_tokens": 6266592} {"current_steps": 69595, "total_steps": 76960, "loss": 0.0107, "lr": 1.382339021324383e-06, "epoch": 18.08601871101871, "percentage": 90.43, "elapsed_time": "1:41:12", "remaining_time": "0:10:42", "throughput": 1032.03, "total_tokens": 6267072} {"current_steps": 69600, "total_steps": 76960, "loss": 0.0018, "lr": 1.3804804692966383e-06, "epoch": 18.08731808731809, "percentage": 90.44, "elapsed_time": "1:41:12", "remaining_time": "0:10:42", "throughput": 1032.03, "total_tokens": 6267472} {"current_steps": 69605, "total_steps": 76960, "loss": 0.0058, "lr": 1.3786231320434107e-06, "epoch": 18.088617463617464, "percentage": 90.44, "elapsed_time": "1:41:13", "remaining_time": "0:10:41", "throughput": 1032.03, "total_tokens": 6267904} {"current_steps": 69610, "total_steps": 76960, "loss": 0.0001, "lr": 1.376767009660232e-06, "epoch": 18.08991683991684, "percentage": 90.45, "elapsed_time": "1:41:13", "remaining_time": "0:10:41", "throughput": 1032.03, "total_tokens": 6268352} {"current_steps": 69615, "total_steps": 76960, "loss": 0.1419, "lr": 1.3749121022425593e-06, "epoch": 18.091216216216218, "percentage": 90.46, "elapsed_time": "1:41:14", "remaining_time": "0:10:40", "throughput": 1032.03, "total_tokens": 6268800} {"current_steps": 69620, "total_steps": 76960, "loss": 0.0021, "lr": 1.3730584098857913e-06, "epoch": 18.092515592515593, "percentage": 90.46, "elapsed_time": "1:41:14", "remaining_time": "0:10:40", "throughput": 1032.03, "total_tokens": 6269232} {"current_steps": 69625, "total_steps": 76960, "loss": 0.0514, "lr": 1.3712059326852683e-06, "epoch": 18.093814968814968, "percentage": 90.47, "elapsed_time": "1:41:15", "remaining_time": "0:10:40", "throughput": 1032.03, "total_tokens": 6269648} {"current_steps": 69630, "total_steps": 76960, "loss": 0.1489, "lr": 1.369354670736267e-06, "epoch": 18.095114345114347, "percentage": 90.48, "elapsed_time": "1:41:15", "remaining_time": "0:10:39", "throughput": 1032.04, "total_tokens": 6270112} {"current_steps": 69635, "total_steps": 76960, "loss": 0.022, "lr": 1.3675046241339918e-06, "epoch": 18.09641372141372, "percentage": 90.48, "elapsed_time": "1:41:15", "remaining_time": "0:10:39", "throughput": 1032.04, "total_tokens": 6270544} {"current_steps": 69640, "total_steps": 76960, "loss": 0.4692, "lr": 1.3656557929736053e-06, "epoch": 18.097713097713097, "percentage": 90.49, "elapsed_time": "1:41:16", "remaining_time": "0:10:38", "throughput": 1032.04, "total_tokens": 6270992} {"current_steps": 69645, "total_steps": 76960, "loss": 0.0517, "lr": 1.3638081773501788e-06, "epoch": 18.099012474012476, "percentage": 90.5, "elapsed_time": "1:41:16", "remaining_time": "0:10:38", "throughput": 1032.04, "total_tokens": 6271440} {"current_steps": 69650, "total_steps": 76960, "loss": 0.001, "lr": 1.36196177735875e-06, "epoch": 18.10031185031185, "percentage": 90.5, "elapsed_time": "1:41:17", "remaining_time": "0:10:37", "throughput": 1032.05, "total_tokens": 6271888} {"current_steps": 69655, "total_steps": 76960, "loss": 0.313, "lr": 1.3601165930942738e-06, "epoch": 18.101611226611226, "percentage": 90.51, "elapsed_time": "1:41:17", "remaining_time": "0:10:37", "throughput": 1032.05, "total_tokens": 6272320} {"current_steps": 69660, "total_steps": 76960, "loss": 0.1928, "lr": 1.3582726246516491e-06, "epoch": 18.102910602910605, "percentage": 90.51, "elapsed_time": "1:41:17", "remaining_time": "0:10:36", "throughput": 1032.05, "total_tokens": 6272784} {"current_steps": 69665, "total_steps": 76960, "loss": 0.0241, "lr": 1.3564298721257223e-06, "epoch": 18.10420997920998, "percentage": 90.52, "elapsed_time": "1:41:18", "remaining_time": "0:10:36", "throughput": 1032.06, "total_tokens": 6273264} {"current_steps": 69670, "total_steps": 76960, "loss": 0.0775, "lr": 1.3545883356112565e-06, "epoch": 18.105509355509355, "percentage": 90.53, "elapsed_time": "1:41:18", "remaining_time": "0:10:36", "throughput": 1032.06, "total_tokens": 6273712} {"current_steps": 69675, "total_steps": 76960, "loss": 0.0361, "lr": 1.3527480152029703e-06, "epoch": 18.10680873180873, "percentage": 90.53, "elapsed_time": "1:41:19", "remaining_time": "0:10:35", "throughput": 1032.06, "total_tokens": 6274144} {"current_steps": 69680, "total_steps": 76960, "loss": 0.312, "lr": 1.3509089109955104e-06, "epoch": 18.10810810810811, "percentage": 90.54, "elapsed_time": "1:41:19", "remaining_time": "0:10:35", "throughput": 1032.06, "total_tokens": 6274576} {"current_steps": 69685, "total_steps": 76960, "loss": 0.007, "lr": 1.3490710230834674e-06, "epoch": 18.109407484407484, "percentage": 90.55, "elapsed_time": "1:41:20", "remaining_time": "0:10:34", "throughput": 1032.08, "total_tokens": 6275072} {"current_steps": 69690, "total_steps": 76960, "loss": 0.0031, "lr": 1.3472343515613577e-06, "epoch": 18.11070686070686, "percentage": 90.55, "elapsed_time": "1:41:20", "remaining_time": "0:10:34", "throughput": 1032.08, "total_tokens": 6275520} {"current_steps": 69695, "total_steps": 76960, "loss": 0.1496, "lr": 1.3453988965236503e-06, "epoch": 18.112006237006238, "percentage": 90.56, "elapsed_time": "1:41:20", "remaining_time": "0:10:33", "throughput": 1032.08, "total_tokens": 6275968} {"current_steps": 69700, "total_steps": 76960, "loss": 0.0014, "lr": 1.3435646580647415e-06, "epoch": 18.113305613305613, "percentage": 90.57, "elapsed_time": "1:41:21", "remaining_time": "0:10:33", "throughput": 1032.1, "total_tokens": 6276480} {"current_steps": 69705, "total_steps": 76960, "loss": 0.2578, "lr": 1.3417316362789728e-06, "epoch": 18.114604989604988, "percentage": 90.57, "elapsed_time": "1:41:21", "remaining_time": "0:10:32", "throughput": 1032.1, "total_tokens": 6276944} {"current_steps": 69710, "total_steps": 76960, "loss": 0.0008, "lr": 1.3398998312606104e-06, "epoch": 18.115904365904367, "percentage": 90.58, "elapsed_time": "1:41:22", "remaining_time": "0:10:32", "throughput": 1032.1, "total_tokens": 6277376} {"current_steps": 69715, "total_steps": 76960, "loss": 0.0073, "lr": 1.3380692431038732e-06, "epoch": 18.117203742203742, "percentage": 90.59, "elapsed_time": "1:41:22", "remaining_time": "0:10:32", "throughput": 1032.1, "total_tokens": 6277808} {"current_steps": 69720, "total_steps": 76960, "loss": 0.0014, "lr": 1.3362398719029084e-06, "epoch": 18.118503118503117, "percentage": 90.59, "elapsed_time": "1:41:22", "remaining_time": "0:10:31", "throughput": 1032.11, "total_tokens": 6278304} {"current_steps": 69725, "total_steps": 76960, "loss": 0.0123, "lr": 1.3344117177517933e-06, "epoch": 18.119802494802496, "percentage": 90.6, "elapsed_time": "1:41:23", "remaining_time": "0:10:31", "throughput": 1032.12, "total_tokens": 6278784} {"current_steps": 69730, "total_steps": 76960, "loss": 0.0076, "lr": 1.3325847807445612e-06, "epoch": 18.12110187110187, "percentage": 90.61, "elapsed_time": "1:41:23", "remaining_time": "0:10:30", "throughput": 1032.12, "total_tokens": 6279200} {"current_steps": 69735, "total_steps": 76960, "loss": 0.0628, "lr": 1.330759060975173e-06, "epoch": 18.122401247401246, "percentage": 90.61, "elapsed_time": "1:41:24", "remaining_time": "0:10:30", "throughput": 1032.12, "total_tokens": 6279648} {"current_steps": 69740, "total_steps": 76960, "loss": 0.1726, "lr": 1.3289345585375257e-06, "epoch": 18.123700623700625, "percentage": 90.62, "elapsed_time": "1:41:24", "remaining_time": "0:10:29", "throughput": 1032.12, "total_tokens": 6280096} {"current_steps": 69745, "total_steps": 76960, "loss": 0.0383, "lr": 1.3271112735254498e-06, "epoch": 18.125, "percentage": 90.62, "elapsed_time": "1:41:25", "remaining_time": "0:10:29", "throughput": 1032.13, "total_tokens": 6280560} {"current_steps": 69750, "total_steps": 76960, "loss": 0.1368, "lr": 1.3252892060327288e-06, "epoch": 18.126299376299375, "percentage": 90.63, "elapsed_time": "1:41:25", "remaining_time": "0:10:29", "throughput": 1032.14, "total_tokens": 6281040} {"current_steps": 69755, "total_steps": 76960, "loss": 0.2447, "lr": 1.3234683561530653e-06, "epoch": 18.127598752598754, "percentage": 90.64, "elapsed_time": "1:41:25", "remaining_time": "0:10:28", "throughput": 1032.14, "total_tokens": 6281504} {"current_steps": 69760, "total_steps": 76960, "loss": 0.0008, "lr": 1.3216487239801095e-06, "epoch": 18.12889812889813, "percentage": 90.64, "elapsed_time": "1:41:26", "remaining_time": "0:10:28", "throughput": 1032.14, "total_tokens": 6281936} {"current_steps": 69765, "total_steps": 76960, "loss": 0.0291, "lr": 1.3198303096074478e-06, "epoch": 18.130197505197504, "percentage": 90.65, "elapsed_time": "1:41:26", "remaining_time": "0:10:27", "throughput": 1032.15, "total_tokens": 6282384} {"current_steps": 69770, "total_steps": 76960, "loss": 0.2878, "lr": 1.318013113128605e-06, "epoch": 18.131496881496883, "percentage": 90.66, "elapsed_time": "1:41:27", "remaining_time": "0:10:27", "throughput": 1032.15, "total_tokens": 6282832} {"current_steps": 69775, "total_steps": 76960, "loss": 0.0308, "lr": 1.3161971346370344e-06, "epoch": 18.132796257796258, "percentage": 90.66, "elapsed_time": "1:41:27", "remaining_time": "0:10:26", "throughput": 1032.15, "total_tokens": 6283248} {"current_steps": 69780, "total_steps": 76960, "loss": 0.2245, "lr": 1.3143823742261418e-06, "epoch": 18.134095634095633, "percentage": 90.67, "elapsed_time": "1:41:27", "remaining_time": "0:10:26", "throughput": 1032.16, "total_tokens": 6283744} {"current_steps": 69785, "total_steps": 76960, "loss": 0.0054, "lr": 1.312568831989258e-06, "epoch": 18.135395010395012, "percentage": 90.68, "elapsed_time": "1:41:28", "remaining_time": "0:10:25", "throughput": 1032.16, "total_tokens": 6284192} {"current_steps": 69790, "total_steps": 76960, "loss": 0.0011, "lr": 1.3107565080196533e-06, "epoch": 18.136694386694387, "percentage": 90.68, "elapsed_time": "1:41:28", "remaining_time": "0:10:25", "throughput": 1032.17, "total_tokens": 6284656} {"current_steps": 69795, "total_steps": 76960, "loss": 0.0001, "lr": 1.3089454024105385e-06, "epoch": 18.137993762993762, "percentage": 90.69, "elapsed_time": "1:41:29", "remaining_time": "0:10:25", "throughput": 1032.17, "total_tokens": 6285120} {"current_steps": 69800, "total_steps": 76960, "loss": 0.0091, "lr": 1.3071355152550619e-06, "epoch": 18.13929313929314, "percentage": 90.7, "elapsed_time": "1:41:29", "remaining_time": "0:10:24", "throughput": 1032.18, "total_tokens": 6285584} {"current_steps": 69805, "total_steps": 76960, "loss": 0.1979, "lr": 1.3053268466463099e-06, "epoch": 18.140592515592516, "percentage": 90.7, "elapsed_time": "1:41:30", "remaining_time": "0:10:24", "throughput": 1032.19, "total_tokens": 6286096} {"current_steps": 69810, "total_steps": 76960, "loss": 0.0195, "lr": 1.3035193966772996e-06, "epoch": 18.14189189189189, "percentage": 90.71, "elapsed_time": "1:41:30", "remaining_time": "0:10:23", "throughput": 1032.19, "total_tokens": 6286528} {"current_steps": 69815, "total_steps": 76960, "loss": 0.3654, "lr": 1.301713165440993e-06, "epoch": 18.14319126819127, "percentage": 90.72, "elapsed_time": "1:41:30", "remaining_time": "0:10:23", "throughput": 1032.19, "total_tokens": 6286928} {"current_steps": 69820, "total_steps": 76960, "loss": 0.3315, "lr": 1.2999081530302826e-06, "epoch": 18.144490644490645, "percentage": 90.72, "elapsed_time": "1:41:31", "remaining_time": "0:10:22", "throughput": 1032.19, "total_tokens": 6287376} {"current_steps": 69825, "total_steps": 76960, "loss": 0.0164, "lr": 1.298104359538005e-06, "epoch": 18.14579002079002, "percentage": 90.73, "elapsed_time": "1:41:31", "remaining_time": "0:10:22", "throughput": 1032.2, "total_tokens": 6287856} {"current_steps": 69830, "total_steps": 76960, "loss": 0.0026, "lr": 1.2963017850569304e-06, "epoch": 18.147089397089395, "percentage": 90.74, "elapsed_time": "1:41:32", "remaining_time": "0:10:22", "throughput": 1032.21, "total_tokens": 6288336} {"current_steps": 69835, "total_steps": 76960, "loss": 0.1696, "lr": 1.2945004296797654e-06, "epoch": 18.148388773388774, "percentage": 90.74, "elapsed_time": "1:41:32", "remaining_time": "0:10:21", "throughput": 1032.21, "total_tokens": 6288784} {"current_steps": 69840, "total_steps": 76960, "loss": 0.0015, "lr": 1.292700293499155e-06, "epoch": 18.14968814968815, "percentage": 90.75, "elapsed_time": "1:41:32", "remaining_time": "0:10:21", "throughput": 1032.21, "total_tokens": 6289216} {"current_steps": 69845, "total_steps": 76960, "loss": 0.071, "lr": 1.2909013766076893e-06, "epoch": 18.150987525987524, "percentage": 90.75, "elapsed_time": "1:41:33", "remaining_time": "0:10:20", "throughput": 1032.21, "total_tokens": 6289648} {"current_steps": 69850, "total_steps": 76960, "loss": 0.2238, "lr": 1.2891036790978833e-06, "epoch": 18.152286902286903, "percentage": 90.76, "elapsed_time": "1:41:33", "remaining_time": "0:10:20", "throughput": 1032.22, "total_tokens": 6290112} {"current_steps": 69855, "total_steps": 76960, "loss": 0.0006, "lr": 1.2873072010621878e-06, "epoch": 18.15358627858628, "percentage": 90.77, "elapsed_time": "1:41:34", "remaining_time": "0:10:19", "throughput": 1032.22, "total_tokens": 6290544} {"current_steps": 69860, "total_steps": 76960, "loss": 0.2395, "lr": 1.2855119425930096e-06, "epoch": 18.154885654885653, "percentage": 90.77, "elapsed_time": "1:41:34", "remaining_time": "0:10:19", "throughput": 1032.22, "total_tokens": 6290992} {"current_steps": 69865, "total_steps": 76960, "loss": 0.0009, "lr": 1.2837179037826692e-06, "epoch": 18.156185031185032, "percentage": 90.78, "elapsed_time": "1:41:35", "remaining_time": "0:10:18", "throughput": 1032.22, "total_tokens": 6291408} {"current_steps": 69870, "total_steps": 76960, "loss": 0.0348, "lr": 1.2819250847234427e-06, "epoch": 18.157484407484407, "percentage": 90.79, "elapsed_time": "1:41:35", "remaining_time": "0:10:18", "throughput": 1032.22, "total_tokens": 6291824} {"current_steps": 69875, "total_steps": 76960, "loss": 0.0165, "lr": 1.2801334855075314e-06, "epoch": 18.158783783783782, "percentage": 90.79, "elapsed_time": "1:41:35", "remaining_time": "0:10:18", "throughput": 1032.22, "total_tokens": 6292272} {"current_steps": 69880, "total_steps": 76960, "loss": 0.0114, "lr": 1.2783431062270895e-06, "epoch": 18.16008316008316, "percentage": 90.8, "elapsed_time": "1:41:36", "remaining_time": "0:10:17", "throughput": 1032.22, "total_tokens": 6292720} {"current_steps": 69885, "total_steps": 76960, "loss": 0.0038, "lr": 1.2765539469741849e-06, "epoch": 18.161382536382536, "percentage": 90.81, "elapsed_time": "1:41:36", "remaining_time": "0:10:17", "throughput": 1032.23, "total_tokens": 6293216} {"current_steps": 69890, "total_steps": 76960, "loss": 0.1303, "lr": 1.2747660078408442e-06, "epoch": 18.16268191268191, "percentage": 90.81, "elapsed_time": "1:41:37", "remaining_time": "0:10:16", "throughput": 1032.24, "total_tokens": 6293664} {"current_steps": 69895, "total_steps": 76960, "loss": 0.3172, "lr": 1.2729792889190184e-06, "epoch": 18.16398128898129, "percentage": 90.82, "elapsed_time": "1:41:37", "remaining_time": "0:10:16", "throughput": 1032.24, "total_tokens": 6294112} {"current_steps": 69900, "total_steps": 76960, "loss": 0.0191, "lr": 1.2711937903006039e-06, "epoch": 18.165280665280665, "percentage": 90.83, "elapsed_time": "1:41:37", "remaining_time": "0:10:15", "throughput": 1032.24, "total_tokens": 6294528} {"current_steps": 69905, "total_steps": 76960, "loss": 0.0008, "lr": 1.269409512077427e-06, "epoch": 18.16658004158004, "percentage": 90.83, "elapsed_time": "1:41:38", "remaining_time": "0:10:15", "throughput": 1032.24, "total_tokens": 6294976} {"current_steps": 69910, "total_steps": 76960, "loss": 0.0016, "lr": 1.2676264543412558e-06, "epoch": 18.16787941787942, "percentage": 90.84, "elapsed_time": "1:41:38", "remaining_time": "0:10:15", "throughput": 1032.24, "total_tokens": 6295408} {"current_steps": 69915, "total_steps": 76960, "loss": 0.2054, "lr": 1.2658446171837979e-06, "epoch": 18.169178794178794, "percentage": 90.85, "elapsed_time": "1:41:39", "remaining_time": "0:10:14", "throughput": 1032.25, "total_tokens": 6295872} {"current_steps": 69920, "total_steps": 76960, "loss": 0.001, "lr": 1.2640640006966882e-06, "epoch": 18.17047817047817, "percentage": 90.85, "elapsed_time": "1:41:39", "remaining_time": "0:10:14", "throughput": 1032.24, "total_tokens": 6296288} {"current_steps": 69925, "total_steps": 76960, "loss": 0.0019, "lr": 1.2622846049715142e-06, "epoch": 18.171777546777548, "percentage": 90.86, "elapsed_time": "1:41:40", "remaining_time": "0:10:13", "throughput": 1032.24, "total_tokens": 6296720} {"current_steps": 69930, "total_steps": 76960, "loss": 0.0024, "lr": 1.2605064300997837e-06, "epoch": 18.173076923076923, "percentage": 90.87, "elapsed_time": "1:41:40", "remaining_time": "0:10:13", "throughput": 1032.25, "total_tokens": 6297216} {"current_steps": 69935, "total_steps": 76960, "loss": 0.2462, "lr": 1.2587294761729596e-06, "epoch": 18.1743762993763, "percentage": 90.87, "elapsed_time": "1:41:40", "remaining_time": "0:10:12", "throughput": 1032.26, "total_tokens": 6297664} {"current_steps": 69940, "total_steps": 76960, "loss": 0.0019, "lr": 1.2569537432824186e-06, "epoch": 18.175675675675677, "percentage": 90.88, "elapsed_time": "1:41:41", "remaining_time": "0:10:12", "throughput": 1032.26, "total_tokens": 6298144} {"current_steps": 69945, "total_steps": 76960, "loss": 0.0292, "lr": 1.2551792315194989e-06, "epoch": 18.176975051975052, "percentage": 90.88, "elapsed_time": "1:41:41", "remaining_time": "0:10:11", "throughput": 1032.27, "total_tokens": 6298624} {"current_steps": 69950, "total_steps": 76960, "loss": 0.0022, "lr": 1.2534059409754606e-06, "epoch": 18.178274428274428, "percentage": 90.89, "elapsed_time": "1:41:42", "remaining_time": "0:10:11", "throughput": 1032.27, "total_tokens": 6299056} {"current_steps": 69955, "total_steps": 76960, "loss": 0.0142, "lr": 1.2516338717415144e-06, "epoch": 18.179573804573806, "percentage": 90.9, "elapsed_time": "1:41:42", "remaining_time": "0:10:11", "throughput": 1032.27, "total_tokens": 6299488} {"current_steps": 69960, "total_steps": 76960, "loss": 0.0016, "lr": 1.2498630239087873e-06, "epoch": 18.18087318087318, "percentage": 90.9, "elapsed_time": "1:41:42", "remaining_time": "0:10:10", "throughput": 1032.28, "total_tokens": 6299936} {"current_steps": 69965, "total_steps": 76960, "loss": 0.0194, "lr": 1.2480933975683617e-06, "epoch": 18.182172557172557, "percentage": 90.91, "elapsed_time": "1:41:43", "remaining_time": "0:10:10", "throughput": 1032.28, "total_tokens": 6300400} {"current_steps": 69970, "total_steps": 76960, "loss": 0.0428, "lr": 1.2463249928112514e-06, "epoch": 18.183471933471935, "percentage": 90.92, "elapsed_time": "1:41:43", "remaining_time": "0:10:09", "throughput": 1032.29, "total_tokens": 6300880} {"current_steps": 69975, "total_steps": 76960, "loss": 0.3067, "lr": 1.2445578097284084e-06, "epoch": 18.18477130977131, "percentage": 90.92, "elapsed_time": "1:41:44", "remaining_time": "0:10:09", "throughput": 1032.29, "total_tokens": 6301312} {"current_steps": 69980, "total_steps": 76960, "loss": 0.0058, "lr": 1.2427918484107153e-06, "epoch": 18.186070686070686, "percentage": 90.93, "elapsed_time": "1:41:44", "remaining_time": "0:10:08", "throughput": 1032.29, "total_tokens": 6301744} {"current_steps": 69985, "total_steps": 76960, "loss": 0.0005, "lr": 1.241027108949e-06, "epoch": 18.18737006237006, "percentage": 90.94, "elapsed_time": "1:41:45", "remaining_time": "0:10:08", "throughput": 1032.3, "total_tokens": 6302240} {"current_steps": 69990, "total_steps": 76960, "loss": 0.339, "lr": 1.2392635914340285e-06, "epoch": 18.18866943866944, "percentage": 90.94, "elapsed_time": "1:41:45", "remaining_time": "0:10:08", "throughput": 1032.3, "total_tokens": 6302672} {"current_steps": 69995, "total_steps": 76960, "loss": 0.0539, "lr": 1.2375012959564947e-06, "epoch": 18.189968814968815, "percentage": 90.95, "elapsed_time": "1:41:45", "remaining_time": "0:10:07", "throughput": 1032.3, "total_tokens": 6303120} {"current_steps": 70000, "total_steps": 76960, "loss": 0.3659, "lr": 1.2357402226070402e-06, "epoch": 18.19126819126819, "percentage": 90.96, "elapsed_time": "1:41:46", "remaining_time": "0:10:07", "throughput": 1032.31, "total_tokens": 6303568} {"current_steps": 70005, "total_steps": 76960, "loss": 0.0188, "lr": 1.2339803714762316e-06, "epoch": 18.19256756756757, "percentage": 90.96, "elapsed_time": "1:41:46", "remaining_time": "0:10:06", "throughput": 1032.31, "total_tokens": 6304032} {"current_steps": 70010, "total_steps": 76960, "loss": 0.2627, "lr": 1.232221742654585e-06, "epoch": 18.193866943866944, "percentage": 90.97, "elapsed_time": "1:41:47", "remaining_time": "0:10:06", "throughput": 1032.32, "total_tokens": 6304480} {"current_steps": 70015, "total_steps": 76960, "loss": 0.0001, "lr": 1.2304643362325452e-06, "epoch": 18.19516632016632, "percentage": 90.98, "elapsed_time": "1:41:47", "remaining_time": "0:10:05", "throughput": 1032.32, "total_tokens": 6304960} {"current_steps": 70020, "total_steps": 76960, "loss": 0.0368, "lr": 1.2287081523005062e-06, "epoch": 18.196465696465697, "percentage": 90.98, "elapsed_time": "1:41:47", "remaining_time": "0:10:05", "throughput": 1032.32, "total_tokens": 6305376} {"current_steps": 70025, "total_steps": 76960, "loss": 0.0006, "lr": 1.226953190948779e-06, "epoch": 18.197765072765073, "percentage": 90.99, "elapsed_time": "1:41:48", "remaining_time": "0:10:04", "throughput": 1032.32, "total_tokens": 6305808} {"current_steps": 70030, "total_steps": 76960, "loss": 0.0011, "lr": 1.2251994522676307e-06, "epoch": 18.199064449064448, "percentage": 91.0, "elapsed_time": "1:41:48", "remaining_time": "0:10:04", "throughput": 1032.32, "total_tokens": 6306256} {"current_steps": 70035, "total_steps": 76960, "loss": 0.0048, "lr": 1.22344693634725e-06, "epoch": 18.200363825363826, "percentage": 91.0, "elapsed_time": "1:41:49", "remaining_time": "0:10:04", "throughput": 1032.33, "total_tokens": 6306704} {"current_steps": 70040, "total_steps": 76960, "loss": 0.006, "lr": 1.2216956432777788e-06, "epoch": 18.2016632016632, "percentage": 91.01, "elapsed_time": "1:41:49", "remaining_time": "0:10:03", "throughput": 1032.33, "total_tokens": 6307136} {"current_steps": 70045, "total_steps": 76960, "loss": 0.1326, "lr": 1.2199455731492809e-06, "epoch": 18.202962577962577, "percentage": 91.01, "elapsed_time": "1:41:50", "remaining_time": "0:10:03", "throughput": 1032.33, "total_tokens": 6307568} {"current_steps": 70050, "total_steps": 76960, "loss": 0.16, "lr": 1.218196726051768e-06, "epoch": 18.204261954261955, "percentage": 91.02, "elapsed_time": "1:41:50", "remaining_time": "0:10:02", "throughput": 1032.33, "total_tokens": 6307984} {"current_steps": 70055, "total_steps": 76960, "loss": 0.0007, "lr": 1.2164491020751872e-06, "epoch": 18.20556133056133, "percentage": 91.03, "elapsed_time": "1:41:50", "remaining_time": "0:10:02", "throughput": 1032.33, "total_tokens": 6308448} {"current_steps": 70060, "total_steps": 76960, "loss": 0.5243, "lr": 1.2147027013094113e-06, "epoch": 18.206860706860706, "percentage": 91.03, "elapsed_time": "1:41:51", "remaining_time": "0:10:01", "throughput": 1032.34, "total_tokens": 6308912} {"current_steps": 70065, "total_steps": 76960, "loss": 0.0612, "lr": 1.2129575238442715e-06, "epoch": 18.208160083160084, "percentage": 91.04, "elapsed_time": "1:41:51", "remaining_time": "0:10:01", "throughput": 1032.33, "total_tokens": 6309328} {"current_steps": 70070, "total_steps": 76960, "loss": 0.2224, "lr": 1.2112135697695147e-06, "epoch": 18.20945945945946, "percentage": 91.05, "elapsed_time": "1:41:52", "remaining_time": "0:10:01", "throughput": 1032.34, "total_tokens": 6309776} {"current_steps": 70075, "total_steps": 76960, "loss": 0.0334, "lr": 1.2094708391748395e-06, "epoch": 18.210758835758835, "percentage": 91.05, "elapsed_time": "1:41:52", "remaining_time": "0:10:00", "throughput": 1032.34, "total_tokens": 6310224} {"current_steps": 70080, "total_steps": 76960, "loss": 0.601, "lr": 1.2077293321498706e-06, "epoch": 18.212058212058214, "percentage": 91.06, "elapsed_time": "1:41:52", "remaining_time": "0:10:00", "throughput": 1032.35, "total_tokens": 6310688} {"current_steps": 70085, "total_steps": 76960, "loss": 0.019, "lr": 1.2059890487841813e-06, "epoch": 18.21335758835759, "percentage": 91.07, "elapsed_time": "1:41:53", "remaining_time": "0:09:59", "throughput": 1032.34, "total_tokens": 6311104} {"current_steps": 70090, "total_steps": 76960, "loss": 0.0643, "lr": 1.2042499891672693e-06, "epoch": 18.214656964656964, "percentage": 91.07, "elapsed_time": "1:41:53", "remaining_time": "0:09:59", "throughput": 1032.34, "total_tokens": 6311504} {"current_steps": 70095, "total_steps": 76960, "loss": 0.0031, "lr": 1.202512153388588e-06, "epoch": 18.215956340956343, "percentage": 91.08, "elapsed_time": "1:41:54", "remaining_time": "0:09:58", "throughput": 1032.34, "total_tokens": 6311952} {"current_steps": 70100, "total_steps": 76960, "loss": 0.0066, "lr": 1.2007755415375022e-06, "epoch": 18.217255717255718, "percentage": 91.09, "elapsed_time": "1:41:54", "remaining_time": "0:09:58", "throughput": 1032.35, "total_tokens": 6312416} {"current_steps": 70105, "total_steps": 76960, "loss": 0.0014, "lr": 1.1990401537033373e-06, "epoch": 18.218555093555093, "percentage": 91.09, "elapsed_time": "1:41:55", "remaining_time": "0:09:57", "throughput": 1032.35, "total_tokens": 6312896} {"current_steps": 70110, "total_steps": 76960, "loss": 0.0003, "lr": 1.197305989975342e-06, "epoch": 18.21985446985447, "percentage": 91.1, "elapsed_time": "1:41:55", "remaining_time": "0:09:57", "throughput": 1032.36, "total_tokens": 6313328} {"current_steps": 70115, "total_steps": 76960, "loss": 0.1248, "lr": 1.1955730504427055e-06, "epoch": 18.221153846153847, "percentage": 91.11, "elapsed_time": "1:41:55", "remaining_time": "0:09:57", "throughput": 1032.36, "total_tokens": 6313760} {"current_steps": 70120, "total_steps": 76960, "loss": 0.0006, "lr": 1.193841335194551e-06, "epoch": 18.222453222453222, "percentage": 91.11, "elapsed_time": "1:41:56", "remaining_time": "0:09:56", "throughput": 1032.37, "total_tokens": 6314256} {"current_steps": 70125, "total_steps": 76960, "loss": 0.0233, "lr": 1.192110844319949e-06, "epoch": 18.223752598752597, "percentage": 91.12, "elapsed_time": "1:41:56", "remaining_time": "0:09:56", "throughput": 1032.37, "total_tokens": 6314736} {"current_steps": 70130, "total_steps": 76960, "loss": 0.0038, "lr": 1.1903815779079035e-06, "epoch": 18.225051975051976, "percentage": 91.13, "elapsed_time": "1:41:57", "remaining_time": "0:09:55", "throughput": 1032.37, "total_tokens": 6315152} {"current_steps": 70135, "total_steps": 76960, "loss": 0.0121, "lr": 1.1886535360473406e-06, "epoch": 18.22635135135135, "percentage": 91.13, "elapsed_time": "1:41:57", "remaining_time": "0:09:55", "throughput": 1032.37, "total_tokens": 6315568} {"current_steps": 70140, "total_steps": 76960, "loss": 0.1103, "lr": 1.1869267188271444e-06, "epoch": 18.227650727650726, "percentage": 91.14, "elapsed_time": "1:41:57", "remaining_time": "0:09:54", "throughput": 1032.37, "total_tokens": 6316000} {"current_steps": 70145, "total_steps": 76960, "loss": 0.1418, "lr": 1.185201126336122e-06, "epoch": 18.228950103950105, "percentage": 91.14, "elapsed_time": "1:41:58", "remaining_time": "0:09:54", "throughput": 1032.38, "total_tokens": 6316464} {"current_steps": 70150, "total_steps": 76960, "loss": 0.2205, "lr": 1.183476758663024e-06, "epoch": 18.23024948024948, "percentage": 91.15, "elapsed_time": "1:41:58", "remaining_time": "0:09:53", "throughput": 1032.38, "total_tokens": 6316944} {"current_steps": 70155, "total_steps": 76960, "loss": 0.0034, "lr": 1.181753615896536e-06, "epoch": 18.231548856548855, "percentage": 91.16, "elapsed_time": "1:41:59", "remaining_time": "0:09:53", "throughput": 1032.39, "total_tokens": 6317392} {"current_steps": 70160, "total_steps": 76960, "loss": 0.1742, "lr": 1.1800316981252808e-06, "epoch": 18.232848232848234, "percentage": 91.16, "elapsed_time": "1:41:59", "remaining_time": "0:09:53", "throughput": 1032.39, "total_tokens": 6317840} {"current_steps": 70165, "total_steps": 76960, "loss": 0.0743, "lr": 1.1783110054378182e-06, "epoch": 18.23414760914761, "percentage": 91.17, "elapsed_time": "1:42:00", "remaining_time": "0:09:52", "throughput": 1032.39, "total_tokens": 6318272} {"current_steps": 70170, "total_steps": 76960, "loss": 0.1025, "lr": 1.1765915379226471e-06, "epoch": 18.235446985446984, "percentage": 91.18, "elapsed_time": "1:42:00", "remaining_time": "0:09:52", "throughput": 1032.39, "total_tokens": 6318704} {"current_steps": 70175, "total_steps": 76960, "loss": 0.308, "lr": 1.1748732956682025e-06, "epoch": 18.236746361746363, "percentage": 91.18, "elapsed_time": "1:42:00", "remaining_time": "0:09:51", "throughput": 1032.4, "total_tokens": 6319168} {"current_steps": 70180, "total_steps": 76960, "loss": 0.0005, "lr": 1.1731562787628464e-06, "epoch": 18.238045738045738, "percentage": 91.19, "elapsed_time": "1:42:01", "remaining_time": "0:09:51", "throughput": 1032.39, "total_tokens": 6319584} {"current_steps": 70185, "total_steps": 76960, "loss": 0.0127, "lr": 1.1714404872948976e-06, "epoch": 18.239345114345113, "percentage": 91.2, "elapsed_time": "1:42:01", "remaining_time": "0:09:50", "throughput": 1032.39, "total_tokens": 6320000} {"current_steps": 70190, "total_steps": 76960, "loss": 0.1446, "lr": 1.1697259213525935e-06, "epoch": 18.240644490644492, "percentage": 91.2, "elapsed_time": "1:42:02", "remaining_time": "0:09:50", "throughput": 1032.4, "total_tokens": 6320480} {"current_steps": 70195, "total_steps": 76960, "loss": 0.3552, "lr": 1.1680125810241166e-06, "epoch": 18.241943866943867, "percentage": 91.21, "elapsed_time": "1:42:02", "remaining_time": "0:09:50", "throughput": 1032.41, "total_tokens": 6320960} {"current_steps": 70200, "total_steps": 76960, "loss": 0.0115, "lr": 1.166300466397588e-06, "epoch": 18.243243243243242, "percentage": 91.22, "elapsed_time": "1:42:02", "remaining_time": "0:09:49", "throughput": 1032.41, "total_tokens": 6321424} {"current_steps": 70205, "total_steps": 76960, "loss": 0.4704, "lr": 1.1645895775610677e-06, "epoch": 18.24454261954262, "percentage": 91.22, "elapsed_time": "1:42:03", "remaining_time": "0:09:49", "throughput": 1032.42, "total_tokens": 6321872} {"current_steps": 70210, "total_steps": 76960, "loss": 0.3071, "lr": 1.1628799146025383e-06, "epoch": 18.245841995841996, "percentage": 91.23, "elapsed_time": "1:42:03", "remaining_time": "0:09:48", "throughput": 1032.42, "total_tokens": 6322320} {"current_steps": 70215, "total_steps": 76960, "loss": 0.0076, "lr": 1.1611714776099376e-06, "epoch": 18.24714137214137, "percentage": 91.24, "elapsed_time": "1:42:04", "remaining_time": "0:09:48", "throughput": 1032.42, "total_tokens": 6322736} {"current_steps": 70220, "total_steps": 76960, "loss": 0.0343, "lr": 1.1594642666711259e-06, "epoch": 18.24844074844075, "percentage": 91.24, "elapsed_time": "1:42:04", "remaining_time": "0:09:47", "throughput": 1032.42, "total_tokens": 6323184} {"current_steps": 70225, "total_steps": 76960, "loss": 0.0259, "lr": 1.1577582818739135e-06, "epoch": 18.249740124740125, "percentage": 91.25, "elapsed_time": "1:42:05", "remaining_time": "0:09:47", "throughput": 1032.42, "total_tokens": 6323600} {"current_steps": 70230, "total_steps": 76960, "loss": 0.0327, "lr": 1.1560535233060304e-06, "epoch": 18.2510395010395, "percentage": 91.26, "elapsed_time": "1:42:05", "remaining_time": "0:09:46", "throughput": 1032.42, "total_tokens": 6324064} {"current_steps": 70235, "total_steps": 76960, "loss": 0.0006, "lr": 1.1543499910551676e-06, "epoch": 18.25233887733888, "percentage": 91.26, "elapsed_time": "1:42:05", "remaining_time": "0:09:46", "throughput": 1032.43, "total_tokens": 6324512} {"current_steps": 70240, "total_steps": 76960, "loss": 0.032, "lr": 1.1526476852089324e-06, "epoch": 18.253638253638254, "percentage": 91.27, "elapsed_time": "1:42:06", "remaining_time": "0:09:46", "throughput": 1032.43, "total_tokens": 6324944} {"current_steps": 70245, "total_steps": 76960, "loss": 0.001, "lr": 1.1509466058548719e-06, "epoch": 18.25493762993763, "percentage": 91.27, "elapsed_time": "1:42:06", "remaining_time": "0:09:45", "throughput": 1032.43, "total_tokens": 6325424} {"current_steps": 70250, "total_steps": 76960, "loss": 0.0025, "lr": 1.1492467530804823e-06, "epoch": 18.256237006237008, "percentage": 91.28, "elapsed_time": "1:42:07", "remaining_time": "0:09:45", "throughput": 1032.43, "total_tokens": 6325856} {"current_steps": 70255, "total_steps": 76960, "loss": 0.1453, "lr": 1.147548126973183e-06, "epoch": 18.257536382536383, "percentage": 91.29, "elapsed_time": "1:42:07", "remaining_time": "0:09:44", "throughput": 1032.44, "total_tokens": 6326304} {"current_steps": 70260, "total_steps": 76960, "loss": 0.0025, "lr": 1.1458507276203373e-06, "epoch": 18.258835758835758, "percentage": 91.29, "elapsed_time": "1:42:07", "remaining_time": "0:09:44", "throughput": 1032.45, "total_tokens": 6326784} {"current_steps": 70265, "total_steps": 76960, "loss": 0.0002, "lr": 1.1441545551092448e-06, "epoch": 18.260135135135137, "percentage": 91.3, "elapsed_time": "1:42:08", "remaining_time": "0:09:43", "throughput": 1032.45, "total_tokens": 6327232} {"current_steps": 70270, "total_steps": 76960, "loss": 0.0072, "lr": 1.142459609527144e-06, "epoch": 18.261434511434512, "percentage": 91.31, "elapsed_time": "1:42:08", "remaining_time": "0:09:43", "throughput": 1032.45, "total_tokens": 6327680} {"current_steps": 70275, "total_steps": 76960, "loss": 0.1993, "lr": 1.1407658909612012e-06, "epoch": 18.262733887733887, "percentage": 91.31, "elapsed_time": "1:42:09", "remaining_time": "0:09:43", "throughput": 1032.45, "total_tokens": 6328128} {"current_steps": 70280, "total_steps": 76960, "loss": 0.3501, "lr": 1.139073399498533e-06, "epoch": 18.264033264033262, "percentage": 91.32, "elapsed_time": "1:42:09", "remaining_time": "0:09:42", "throughput": 1032.45, "total_tokens": 6328560} {"current_steps": 70285, "total_steps": 76960, "loss": 0.1448, "lr": 1.1373821352261781e-06, "epoch": 18.26533264033264, "percentage": 91.33, "elapsed_time": "1:42:10", "remaining_time": "0:09:42", "throughput": 1032.46, "total_tokens": 6329024} {"current_steps": 70290, "total_steps": 76960, "loss": 0.0017, "lr": 1.135692098231128e-06, "epoch": 18.266632016632016, "percentage": 91.33, "elapsed_time": "1:42:10", "remaining_time": "0:09:41", "throughput": 1032.47, "total_tokens": 6329488} {"current_steps": 70295, "total_steps": 76960, "loss": 0.0704, "lr": 1.1340032886002966e-06, "epoch": 18.26793139293139, "percentage": 91.34, "elapsed_time": "1:42:10", "remaining_time": "0:09:41", "throughput": 1032.47, "total_tokens": 6329936} {"current_steps": 70300, "total_steps": 76960, "loss": 0.0774, "lr": 1.132315706420542e-06, "epoch": 18.26923076923077, "percentage": 91.35, "elapsed_time": "1:42:11", "remaining_time": "0:09:40", "throughput": 1032.47, "total_tokens": 6330352} {"current_steps": 70305, "total_steps": 76960, "loss": 0.043, "lr": 1.1306293517786614e-06, "epoch": 18.270530145530145, "percentage": 91.35, "elapsed_time": "1:42:11", "remaining_time": "0:09:40", "throughput": 1032.47, "total_tokens": 6330784} {"current_steps": 70310, "total_steps": 76960, "loss": 0.5393, "lr": 1.128944224761383e-06, "epoch": 18.27182952182952, "percentage": 91.36, "elapsed_time": "1:42:12", "remaining_time": "0:09:39", "throughput": 1032.48, "total_tokens": 6331264} {"current_steps": 70315, "total_steps": 76960, "loss": 0.0672, "lr": 1.1272603254553786e-06, "epoch": 18.2731288981289, "percentage": 91.37, "elapsed_time": "1:42:12", "remaining_time": "0:09:39", "throughput": 1032.48, "total_tokens": 6331712} {"current_steps": 70320, "total_steps": 76960, "loss": 0.2975, "lr": 1.1255776539472463e-06, "epoch": 18.274428274428274, "percentage": 91.37, "elapsed_time": "1:42:12", "remaining_time": "0:09:39", "throughput": 1032.48, "total_tokens": 6332128} {"current_steps": 70325, "total_steps": 76960, "loss": 0.1249, "lr": 1.1238962103235329e-06, "epoch": 18.27572765072765, "percentage": 91.38, "elapsed_time": "1:42:13", "remaining_time": "0:09:38", "throughput": 1032.48, "total_tokens": 6332592} {"current_steps": 70330, "total_steps": 76960, "loss": 0.0231, "lr": 1.1222159946707112e-06, "epoch": 18.277027027027028, "percentage": 91.39, "elapsed_time": "1:42:13", "remaining_time": "0:09:38", "throughput": 1032.49, "total_tokens": 6333056} {"current_steps": 70335, "total_steps": 76960, "loss": 0.0008, "lr": 1.120537007075198e-06, "epoch": 18.278326403326403, "percentage": 91.39, "elapsed_time": "1:42:14", "remaining_time": "0:09:37", "throughput": 1032.49, "total_tokens": 6333488} {"current_steps": 70340, "total_steps": 76960, "loss": 0.1928, "lr": 1.1188592476233494e-06, "epoch": 18.27962577962578, "percentage": 91.4, "elapsed_time": "1:42:14", "remaining_time": "0:09:37", "throughput": 1032.49, "total_tokens": 6333936} {"current_steps": 70345, "total_steps": 76960, "loss": 0.4375, "lr": 1.117182716401452e-06, "epoch": 18.280925155925157, "percentage": 91.4, "elapsed_time": "1:42:15", "remaining_time": "0:09:36", "throughput": 1032.49, "total_tokens": 6334384} {"current_steps": 70350, "total_steps": 76960, "loss": 0.0411, "lr": 1.1155074134957312e-06, "epoch": 18.282224532224532, "percentage": 91.41, "elapsed_time": "1:42:15", "remaining_time": "0:09:36", "throughput": 1032.49, "total_tokens": 6334816} {"current_steps": 70355, "total_steps": 76960, "loss": 0.0073, "lr": 1.113833338992351e-06, "epoch": 18.283523908523907, "percentage": 91.42, "elapsed_time": "1:42:15", "remaining_time": "0:09:36", "throughput": 1032.49, "total_tokens": 6335232} {"current_steps": 70360, "total_steps": 76960, "loss": 0.0574, "lr": 1.1121604929774044e-06, "epoch": 18.284823284823286, "percentage": 91.42, "elapsed_time": "1:42:16", "remaining_time": "0:09:35", "throughput": 1032.49, "total_tokens": 6335664} {"current_steps": 70365, "total_steps": 76960, "loss": 0.0005, "lr": 1.1104888755369359e-06, "epoch": 18.28612266112266, "percentage": 91.43, "elapsed_time": "1:42:16", "remaining_time": "0:09:35", "throughput": 1032.5, "total_tokens": 6336144} {"current_steps": 70370, "total_steps": 76960, "loss": 0.0077, "lr": 1.1088184867569101e-06, "epoch": 18.287422037422036, "percentage": 91.44, "elapsed_time": "1:42:17", "remaining_time": "0:09:34", "throughput": 1032.5, "total_tokens": 6336560} {"current_steps": 70375, "total_steps": 76960, "loss": 0.283, "lr": 1.107149326723242e-06, "epoch": 18.288721413721415, "percentage": 91.44, "elapsed_time": "1:42:17", "remaining_time": "0:09:34", "throughput": 1032.51, "total_tokens": 6337056} {"current_steps": 70380, "total_steps": 76960, "loss": 0.0626, "lr": 1.105481395521779e-06, "epoch": 18.29002079002079, "percentage": 91.45, "elapsed_time": "1:42:17", "remaining_time": "0:09:33", "throughput": 1032.51, "total_tokens": 6337488} {"current_steps": 70385, "total_steps": 76960, "loss": 0.0668, "lr": 1.1038146932383004e-06, "epoch": 18.291320166320165, "percentage": 91.46, "elapsed_time": "1:42:18", "remaining_time": "0:09:33", "throughput": 1032.51, "total_tokens": 6337920} {"current_steps": 70390, "total_steps": 76960, "loss": 0.0042, "lr": 1.1021492199585314e-06, "epoch": 18.292619542619544, "percentage": 91.46, "elapsed_time": "1:42:18", "remaining_time": "0:09:32", "throughput": 1032.51, "total_tokens": 6338368} {"current_steps": 70395, "total_steps": 76960, "loss": 0.001, "lr": 1.1004849757681235e-06, "epoch": 18.29391891891892, "percentage": 91.47, "elapsed_time": "1:42:19", "remaining_time": "0:09:32", "throughput": 1032.51, "total_tokens": 6338816} {"current_steps": 70400, "total_steps": 76960, "loss": 0.0366, "lr": 1.0988219607526745e-06, "epoch": 18.295218295218294, "percentage": 91.48, "elapsed_time": "1:42:19", "remaining_time": "0:09:32", "throughput": 1032.52, "total_tokens": 6339280} {"current_steps": 70405, "total_steps": 76960, "loss": 0.2224, "lr": 1.0971601749977106e-06, "epoch": 18.296517671517673, "percentage": 91.48, "elapsed_time": "1:42:20", "remaining_time": "0:09:31", "throughput": 1032.52, "total_tokens": 6339744} {"current_steps": 70410, "total_steps": 76960, "loss": 0.0507, "lr": 1.0954996185887023e-06, "epoch": 18.29781704781705, "percentage": 91.49, "elapsed_time": "1:42:20", "remaining_time": "0:09:31", "throughput": 1032.53, "total_tokens": 6340208} {"current_steps": 70415, "total_steps": 76960, "loss": 0.0772, "lr": 1.0938402916110508e-06, "epoch": 18.299116424116423, "percentage": 91.5, "elapsed_time": "1:42:20", "remaining_time": "0:09:30", "throughput": 1032.54, "total_tokens": 6340688} {"current_steps": 70420, "total_steps": 76960, "loss": 0.0458, "lr": 1.0921821941501043e-06, "epoch": 18.3004158004158, "percentage": 91.5, "elapsed_time": "1:42:21", "remaining_time": "0:09:30", "throughput": 1032.54, "total_tokens": 6341152} {"current_steps": 70425, "total_steps": 76960, "loss": 0.0027, "lr": 1.0905253262911309e-06, "epoch": 18.301715176715177, "percentage": 91.51, "elapsed_time": "1:42:21", "remaining_time": "0:09:29", "throughput": 1032.54, "total_tokens": 6341584} {"current_steps": 70430, "total_steps": 76960, "loss": 0.0332, "lr": 1.088869688119351e-06, "epoch": 18.303014553014552, "percentage": 91.52, "elapsed_time": "1:42:22", "remaining_time": "0:09:29", "throughput": 1032.55, "total_tokens": 6342048} {"current_steps": 70435, "total_steps": 76960, "loss": 0.1127, "lr": 1.0872152797199136e-06, "epoch": 18.304313929313928, "percentage": 91.52, "elapsed_time": "1:42:22", "remaining_time": "0:09:29", "throughput": 1032.55, "total_tokens": 6342496} {"current_steps": 70440, "total_steps": 76960, "loss": 0.0078, "lr": 1.085562101177906e-06, "epoch": 18.305613305613306, "percentage": 91.53, "elapsed_time": "1:42:22", "remaining_time": "0:09:28", "throughput": 1032.55, "total_tokens": 6342912} {"current_steps": 70445, "total_steps": 76960, "loss": 0.0281, "lr": 1.0839101525783491e-06, "epoch": 18.30691268191268, "percentage": 91.53, "elapsed_time": "1:42:23", "remaining_time": "0:09:28", "throughput": 1032.55, "total_tokens": 6343360} {"current_steps": 70450, "total_steps": 76960, "loss": 0.0049, "lr": 1.0822594340062109e-06, "epoch": 18.308212058212057, "percentage": 91.54, "elapsed_time": "1:42:23", "remaining_time": "0:09:27", "throughput": 1032.56, "total_tokens": 6343856} {"current_steps": 70455, "total_steps": 76960, "loss": 0.0005, "lr": 1.0806099455463903e-06, "epoch": 18.309511434511435, "percentage": 91.55, "elapsed_time": "1:42:24", "remaining_time": "0:09:27", "throughput": 1032.57, "total_tokens": 6344336} {"current_steps": 70460, "total_steps": 76960, "loss": 0.2529, "lr": 1.0789616872837167e-06, "epoch": 18.31081081081081, "percentage": 91.55, "elapsed_time": "1:42:24", "remaining_time": "0:09:26", "throughput": 1032.58, "total_tokens": 6344784} {"current_steps": 70465, "total_steps": 76960, "loss": 0.2958, "lr": 1.0773146593029637e-06, "epoch": 18.312110187110186, "percentage": 91.56, "elapsed_time": "1:42:25", "remaining_time": "0:09:26", "throughput": 1032.58, "total_tokens": 6345248} {"current_steps": 70470, "total_steps": 76960, "loss": 0.0002, "lr": 1.0756688616888361e-06, "epoch": 18.313409563409564, "percentage": 91.57, "elapsed_time": "1:42:25", "remaining_time": "0:09:25", "throughput": 1032.59, "total_tokens": 6345744} {"current_steps": 70475, "total_steps": 76960, "loss": 0.1951, "lr": 1.0740242945259855e-06, "epoch": 18.31470893970894, "percentage": 91.57, "elapsed_time": "1:42:25", "remaining_time": "0:09:25", "throughput": 1032.59, "total_tokens": 6346160} {"current_steps": 70480, "total_steps": 76960, "loss": 0.0367, "lr": 1.0723809578989884e-06, "epoch": 18.316008316008315, "percentage": 91.58, "elapsed_time": "1:42:26", "remaining_time": "0:09:25", "throughput": 1032.59, "total_tokens": 6346592} {"current_steps": 70485, "total_steps": 76960, "loss": 0.0108, "lr": 1.0707388518923668e-06, "epoch": 18.317307692307693, "percentage": 91.59, "elapsed_time": "1:42:26", "remaining_time": "0:09:24", "throughput": 1032.59, "total_tokens": 6346992} {"current_steps": 70490, "total_steps": 76960, "loss": 0.0232, "lr": 1.0690979765905718e-06, "epoch": 18.31860706860707, "percentage": 91.59, "elapsed_time": "1:42:27", "remaining_time": "0:09:24", "throughput": 1032.59, "total_tokens": 6347440} {"current_steps": 70495, "total_steps": 76960, "loss": 0.095, "lr": 1.067458332078e-06, "epoch": 18.319906444906444, "percentage": 91.6, "elapsed_time": "1:42:27", "remaining_time": "0:09:23", "throughput": 1032.59, "total_tokens": 6347888} {"current_steps": 70500, "total_steps": 76960, "loss": 0.0068, "lr": 1.0658199184389762e-06, "epoch": 18.321205821205822, "percentage": 91.61, "elapsed_time": "1:42:27", "remaining_time": "0:09:23", "throughput": 1032.6, "total_tokens": 6348352} {"current_steps": 70505, "total_steps": 76960, "loss": 0.025, "lr": 1.0641827357577682e-06, "epoch": 18.322505197505198, "percentage": 91.61, "elapsed_time": "1:42:28", "remaining_time": "0:09:22", "throughput": 1032.6, "total_tokens": 6348800} {"current_steps": 70510, "total_steps": 76960, "loss": 0.3117, "lr": 1.0625467841185733e-06, "epoch": 18.323804573804573, "percentage": 91.62, "elapsed_time": "1:42:28", "remaining_time": "0:09:22", "throughput": 1032.6, "total_tokens": 6349232} {"current_steps": 70515, "total_steps": 76960, "loss": 0.0575, "lr": 1.060912063605532e-06, "epoch": 18.32510395010395, "percentage": 91.63, "elapsed_time": "1:42:29", "remaining_time": "0:09:22", "throughput": 1032.6, "total_tokens": 6349680} {"current_steps": 70520, "total_steps": 76960, "loss": 0.1474, "lr": 1.0592785743027244e-06, "epoch": 18.326403326403327, "percentage": 91.63, "elapsed_time": "1:42:29", "remaining_time": "0:09:21", "throughput": 1032.6, "total_tokens": 6350112} {"current_steps": 70525, "total_steps": 76960, "loss": 0.0252, "lr": 1.0576463162941558e-06, "epoch": 18.3277027027027, "percentage": 91.64, "elapsed_time": "1:42:30", "remaining_time": "0:09:21", "throughput": 1032.61, "total_tokens": 6350560} {"current_steps": 70530, "total_steps": 76960, "loss": 0.0007, "lr": 1.056015289663781e-06, "epoch": 18.32900207900208, "percentage": 91.65, "elapsed_time": "1:42:30", "remaining_time": "0:09:20", "throughput": 1032.61, "total_tokens": 6351024} {"current_steps": 70535, "total_steps": 76960, "loss": 0.0234, "lr": 1.05438549449548e-06, "epoch": 18.330301455301456, "percentage": 91.65, "elapsed_time": "1:42:30", "remaining_time": "0:09:20", "throughput": 1032.61, "total_tokens": 6351440} {"current_steps": 70540, "total_steps": 76960, "loss": 0.0013, "lr": 1.0527569308730779e-06, "epoch": 18.33160083160083, "percentage": 91.66, "elapsed_time": "1:42:31", "remaining_time": "0:09:19", "throughput": 1032.61, "total_tokens": 6351856} {"current_steps": 70545, "total_steps": 76960, "loss": 0.0834, "lr": 1.0511295988803294e-06, "epoch": 18.33290020790021, "percentage": 91.66, "elapsed_time": "1:42:31", "remaining_time": "0:09:19", "throughput": 1032.61, "total_tokens": 6352304} {"current_steps": 70550, "total_steps": 76960, "loss": 0.0864, "lr": 1.0495034986009316e-06, "epoch": 18.334199584199585, "percentage": 91.67, "elapsed_time": "1:42:32", "remaining_time": "0:09:18", "throughput": 1032.62, "total_tokens": 6352816} {"current_steps": 70555, "total_steps": 76960, "loss": 0.0054, "lr": 1.0478786301185178e-06, "epoch": 18.33549896049896, "percentage": 91.68, "elapsed_time": "1:42:32", "remaining_time": "0:09:18", "throughput": 1032.62, "total_tokens": 6353248} {"current_steps": 70560, "total_steps": 76960, "loss": 0.0022, "lr": 1.0462549935166572e-06, "epoch": 18.33679833679834, "percentage": 91.68, "elapsed_time": "1:42:32", "remaining_time": "0:09:18", "throughput": 1032.63, "total_tokens": 6353696} {"current_steps": 70565, "total_steps": 76960, "loss": 0.2378, "lr": 1.0446325888788521e-06, "epoch": 18.338097713097714, "percentage": 91.69, "elapsed_time": "1:42:33", "remaining_time": "0:09:17", "throughput": 1032.63, "total_tokens": 6354128} {"current_steps": 70570, "total_steps": 76960, "loss": 0.12, "lr": 1.0430114162885502e-06, "epoch": 18.33939708939709, "percentage": 91.7, "elapsed_time": "1:42:33", "remaining_time": "0:09:17", "throughput": 1032.64, "total_tokens": 6354608} {"current_steps": 70575, "total_steps": 76960, "loss": 0.0073, "lr": 1.0413914758291233e-06, "epoch": 18.340696465696467, "percentage": 91.7, "elapsed_time": "1:42:34", "remaining_time": "0:09:16", "throughput": 1032.64, "total_tokens": 6355040} {"current_steps": 70580, "total_steps": 76960, "loss": 0.0096, "lr": 1.0397727675838882e-06, "epoch": 18.341995841995843, "percentage": 91.71, "elapsed_time": "1:42:34", "remaining_time": "0:09:16", "throughput": 1032.64, "total_tokens": 6355504} {"current_steps": 70585, "total_steps": 76960, "loss": 0.3141, "lr": 1.0381552916360948e-06, "epoch": 18.343295218295218, "percentage": 91.72, "elapsed_time": "1:42:35", "remaining_time": "0:09:15", "throughput": 1032.64, "total_tokens": 6355952} {"current_steps": 70590, "total_steps": 76960, "loss": 0.0864, "lr": 1.0365390480689353e-06, "epoch": 18.344594594594593, "percentage": 91.72, "elapsed_time": "1:42:35", "remaining_time": "0:09:15", "throughput": 1032.65, "total_tokens": 6356432} {"current_steps": 70595, "total_steps": 76960, "loss": 0.1055, "lr": 1.0349240369655373e-06, "epoch": 18.34589397089397, "percentage": 91.73, "elapsed_time": "1:42:35", "remaining_time": "0:09:15", "throughput": 1032.65, "total_tokens": 6356864} {"current_steps": 70600, "total_steps": 76960, "loss": 0.2875, "lr": 1.0333102584089537e-06, "epoch": 18.347193347193347, "percentage": 91.74, "elapsed_time": "1:42:36", "remaining_time": "0:09:14", "throughput": 1032.65, "total_tokens": 6357296} {"current_steps": 70605, "total_steps": 76960, "loss": 0.1421, "lr": 1.0316977124821908e-06, "epoch": 18.348492723492722, "percentage": 91.74, "elapsed_time": "1:42:36", "remaining_time": "0:09:14", "throughput": 1032.66, "total_tokens": 6357760} {"current_steps": 70610, "total_steps": 76960, "loss": 0.1661, "lr": 1.0300863992681763e-06, "epoch": 18.3497920997921, "percentage": 91.75, "elapsed_time": "1:42:37", "remaining_time": "0:09:13", "throughput": 1032.66, "total_tokens": 6358208} {"current_steps": 70615, "total_steps": 76960, "loss": 0.0009, "lr": 1.0284763188497886e-06, "epoch": 18.351091476091476, "percentage": 91.76, "elapsed_time": "1:42:37", "remaining_time": "0:09:13", "throughput": 1032.66, "total_tokens": 6358640} {"current_steps": 70620, "total_steps": 76960, "loss": 0.011, "lr": 1.026867471309828e-06, "epoch": 18.35239085239085, "percentage": 91.76, "elapsed_time": "1:42:37", "remaining_time": "0:09:12", "throughput": 1032.67, "total_tokens": 6359104} {"current_steps": 70625, "total_steps": 76960, "loss": 0.0003, "lr": 1.0252598567310451e-06, "epoch": 18.35369022869023, "percentage": 91.77, "elapsed_time": "1:42:38", "remaining_time": "0:09:12", "throughput": 1032.67, "total_tokens": 6359552} {"current_steps": 70630, "total_steps": 76960, "loss": 0.037, "lr": 1.023653475196118e-06, "epoch": 18.354989604989605, "percentage": 91.77, "elapsed_time": "1:42:38", "remaining_time": "0:09:11", "throughput": 1032.68, "total_tokens": 6360032} {"current_steps": 70635, "total_steps": 76960, "loss": 0.1948, "lr": 1.0220483267876696e-06, "epoch": 18.35628898128898, "percentage": 91.78, "elapsed_time": "1:42:39", "remaining_time": "0:09:11", "throughput": 1032.69, "total_tokens": 6360528} {"current_steps": 70640, "total_steps": 76960, "loss": 0.0218, "lr": 1.0204444115882505e-06, "epoch": 18.35758835758836, "percentage": 91.79, "elapsed_time": "1:42:39", "remaining_time": "0:09:11", "throughput": 1032.69, "total_tokens": 6360992} {"current_steps": 70645, "total_steps": 76960, "loss": 0.0009, "lr": 1.0188417296803476e-06, "epoch": 18.358887733887734, "percentage": 91.79, "elapsed_time": "1:42:40", "remaining_time": "0:09:10", "throughput": 1032.7, "total_tokens": 6361440} {"current_steps": 70650, "total_steps": 76960, "loss": 0.0037, "lr": 1.017240281146395e-06, "epoch": 18.36018711018711, "percentage": 91.8, "elapsed_time": "1:42:40", "remaining_time": "0:09:10", "throughput": 1032.7, "total_tokens": 6361888} {"current_steps": 70655, "total_steps": 76960, "loss": 0.0005, "lr": 1.0156400660687515e-06, "epoch": 18.361486486486488, "percentage": 91.81, "elapsed_time": "1:42:40", "remaining_time": "0:09:09", "throughput": 1032.7, "total_tokens": 6362320} {"current_steps": 70660, "total_steps": 76960, "loss": 0.2261, "lr": 1.014041084529721e-06, "epoch": 18.362785862785863, "percentage": 91.81, "elapsed_time": "1:42:41", "remaining_time": "0:09:09", "throughput": 1032.7, "total_tokens": 6362768} {"current_steps": 70665, "total_steps": 76960, "loss": 0.0003, "lr": 1.0124433366115376e-06, "epoch": 18.364085239085238, "percentage": 91.82, "elapsed_time": "1:42:41", "remaining_time": "0:09:08", "throughput": 1032.71, "total_tokens": 6363216} {"current_steps": 70670, "total_steps": 76960, "loss": 0.0001, "lr": 1.010846822396383e-06, "epoch": 18.365384615384617, "percentage": 91.83, "elapsed_time": "1:42:42", "remaining_time": "0:09:08", "throughput": 1032.71, "total_tokens": 6363648} {"current_steps": 70675, "total_steps": 76960, "loss": 0.0036, "lr": 1.0092515419663578e-06, "epoch": 18.366683991683992, "percentage": 91.83, "elapsed_time": "1:42:42", "remaining_time": "0:09:08", "throughput": 1032.71, "total_tokens": 6364112} {"current_steps": 70680, "total_steps": 76960, "loss": 0.0002, "lr": 1.0076574954035133e-06, "epoch": 18.367983367983367, "percentage": 91.84, "elapsed_time": "1:42:42", "remaining_time": "0:09:07", "throughput": 1032.72, "total_tokens": 6364608} {"current_steps": 70685, "total_steps": 76960, "loss": 0.0665, "lr": 1.0060646827898313e-06, "epoch": 18.369282744282746, "percentage": 91.85, "elapsed_time": "1:42:43", "remaining_time": "0:09:07", "throughput": 1032.73, "total_tokens": 6365072} {"current_steps": 70690, "total_steps": 76960, "loss": 0.0258, "lr": 1.0044731042072348e-06, "epoch": 18.37058212058212, "percentage": 91.85, "elapsed_time": "1:42:43", "remaining_time": "0:09:06", "throughput": 1032.74, "total_tokens": 6365552} {"current_steps": 70695, "total_steps": 76960, "loss": 0.0016, "lr": 1.0028827597375751e-06, "epoch": 18.371881496881496, "percentage": 91.86, "elapsed_time": "1:42:44", "remaining_time": "0:09:06", "throughput": 1032.74, "total_tokens": 6365984} {"current_steps": 70700, "total_steps": 76960, "loss": 0.0005, "lr": 1.001293649462648e-06, "epoch": 18.373180873180875, "percentage": 91.87, "elapsed_time": "1:42:44", "remaining_time": "0:09:05", "throughput": 1032.74, "total_tokens": 6366448} {"current_steps": 70705, "total_steps": 76960, "loss": 0.0051, "lr": 9.99705773464185e-07, "epoch": 18.37448024948025, "percentage": 91.87, "elapsed_time": "1:42:45", "remaining_time": "0:09:05", "throughput": 1032.75, "total_tokens": 6366912} {"current_steps": 70710, "total_steps": 76960, "loss": 0.0067, "lr": 9.98119131823849e-07, "epoch": 18.375779625779625, "percentage": 91.88, "elapsed_time": "1:42:45", "remaining_time": "0:09:04", "throughput": 1032.75, "total_tokens": 6367376} {"current_steps": 70715, "total_steps": 76960, "loss": 0.6427, "lr": 9.965337246232441e-07, "epoch": 18.377079002079004, "percentage": 91.89, "elapsed_time": "1:42:45", "remaining_time": "0:09:04", "throughput": 1032.76, "total_tokens": 6367824} {"current_steps": 70720, "total_steps": 76960, "loss": 0.0025, "lr": 9.949495519439077e-07, "epoch": 18.37837837837838, "percentage": 91.89, "elapsed_time": "1:42:46", "remaining_time": "0:09:04", "throughput": 1032.76, "total_tokens": 6368304} {"current_steps": 70725, "total_steps": 76960, "loss": 0.2592, "lr": 9.933666138673164e-07, "epoch": 18.379677754677754, "percentage": 91.9, "elapsed_time": "1:42:46", "remaining_time": "0:09:03", "throughput": 1032.76, "total_tokens": 6368736} {"current_steps": 70730, "total_steps": 76960, "loss": 0.2021, "lr": 9.917849104748827e-07, "epoch": 18.38097713097713, "percentage": 91.9, "elapsed_time": "1:42:47", "remaining_time": "0:09:03", "throughput": 1032.77, "total_tokens": 6369184} {"current_steps": 70735, "total_steps": 76960, "loss": 0.0131, "lr": 9.902044418479556e-07, "epoch": 18.382276507276508, "percentage": 91.91, "elapsed_time": "1:42:47", "remaining_time": "0:09:02", "throughput": 1032.78, "total_tokens": 6369680} {"current_steps": 70740, "total_steps": 76960, "loss": 0.2835, "lr": 9.886252080678172e-07, "epoch": 18.383575883575883, "percentage": 91.92, "elapsed_time": "1:42:47", "remaining_time": "0:09:02", "throughput": 1032.77, "total_tokens": 6370080} {"current_steps": 70745, "total_steps": 76960, "loss": 0.2029, "lr": 9.87047209215694e-07, "epoch": 18.38487525987526, "percentage": 91.92, "elapsed_time": "1:42:48", "remaining_time": "0:09:01", "throughput": 1032.77, "total_tokens": 6370528} {"current_steps": 70750, "total_steps": 76960, "loss": 0.2119, "lr": 9.85470445372738e-07, "epoch": 18.386174636174637, "percentage": 91.93, "elapsed_time": "1:42:48", "remaining_time": "0:09:01", "throughput": 1032.78, "total_tokens": 6371008} {"current_steps": 70755, "total_steps": 76960, "loss": 0.0023, "lr": 9.838949166200484e-07, "epoch": 18.387474012474012, "percentage": 91.94, "elapsed_time": "1:42:49", "remaining_time": "0:09:01", "throughput": 1032.79, "total_tokens": 6371456} {"current_steps": 70760, "total_steps": 76960, "loss": 0.0894, "lr": 9.823206230386517e-07, "epoch": 18.388773388773387, "percentage": 91.94, "elapsed_time": "1:42:49", "remaining_time": "0:09:00", "throughput": 1032.79, "total_tokens": 6371904} {"current_steps": 70765, "total_steps": 76960, "loss": 0.3245, "lr": 9.807475647095194e-07, "epoch": 18.390072765072766, "percentage": 91.95, "elapsed_time": "1:42:50", "remaining_time": "0:09:00", "throughput": 1032.79, "total_tokens": 6372352} {"current_steps": 70770, "total_steps": 76960, "loss": 0.0116, "lr": 9.79175741713556e-07, "epoch": 18.39137214137214, "percentage": 91.96, "elapsed_time": "1:42:50", "remaining_time": "0:08:59", "throughput": 1032.8, "total_tokens": 6372832} {"current_steps": 70775, "total_steps": 76960, "loss": 0.161, "lr": 9.776051541315972e-07, "epoch": 18.392671517671516, "percentage": 91.96, "elapsed_time": "1:42:50", "remaining_time": "0:08:59", "throughput": 1032.8, "total_tokens": 6373280} {"current_steps": 70780, "total_steps": 76960, "loss": 0.2516, "lr": 9.760358020444255e-07, "epoch": 18.393970893970895, "percentage": 91.97, "elapsed_time": "1:42:51", "remaining_time": "0:08:58", "throughput": 1032.8, "total_tokens": 6373696} {"current_steps": 70785, "total_steps": 76960, "loss": 0.0093, "lr": 9.744676855327483e-07, "epoch": 18.39527027027027, "percentage": 91.98, "elapsed_time": "1:42:51", "remaining_time": "0:08:58", "throughput": 1032.81, "total_tokens": 6374160} {"current_steps": 70790, "total_steps": 76960, "loss": 0.0005, "lr": 9.729008046772208e-07, "epoch": 18.396569646569645, "percentage": 91.98, "elapsed_time": "1:42:52", "remaining_time": "0:08:57", "throughput": 1032.81, "total_tokens": 6374592} {"current_steps": 70795, "total_steps": 76960, "loss": 0.2119, "lr": 9.71335159558423e-07, "epoch": 18.397869022869024, "percentage": 91.99, "elapsed_time": "1:42:52", "remaining_time": "0:08:57", "throughput": 1032.81, "total_tokens": 6375056} {"current_steps": 70800, "total_steps": 76960, "loss": 0.0105, "lr": 9.69770750256882e-07, "epoch": 18.3991683991684, "percentage": 92.0, "elapsed_time": "1:42:52", "remaining_time": "0:08:57", "throughput": 1032.81, "total_tokens": 6375488} {"current_steps": 70805, "total_steps": 76960, "loss": 0.3382, "lr": 9.682075768530558e-07, "epoch": 18.400467775467774, "percentage": 92.0, "elapsed_time": "1:42:53", "remaining_time": "0:08:56", "throughput": 1032.82, "total_tokens": 6375952} {"current_steps": 70810, "total_steps": 76960, "loss": 0.2138, "lr": 9.666456394273438e-07, "epoch": 18.401767151767153, "percentage": 92.01, "elapsed_time": "1:42:53", "remaining_time": "0:08:56", "throughput": 1032.82, "total_tokens": 6376400} {"current_steps": 70815, "total_steps": 76960, "loss": 0.015, "lr": 9.650849380600708e-07, "epoch": 18.403066528066528, "percentage": 92.02, "elapsed_time": "1:42:54", "remaining_time": "0:08:55", "throughput": 1032.82, "total_tokens": 6376848} {"current_steps": 70820, "total_steps": 76960, "loss": 0.0003, "lr": 9.635254728315113e-07, "epoch": 18.404365904365903, "percentage": 92.02, "elapsed_time": "1:42:54", "remaining_time": "0:08:55", "throughput": 1032.83, "total_tokens": 6377296} {"current_steps": 70825, "total_steps": 76960, "loss": 0.0561, "lr": 9.619672438218624e-07, "epoch": 18.405665280665282, "percentage": 92.03, "elapsed_time": "1:42:55", "remaining_time": "0:08:54", "throughput": 1032.83, "total_tokens": 6377744} {"current_steps": 70830, "total_steps": 76960, "loss": 0.0005, "lr": 9.604102511112766e-07, "epoch": 18.406964656964657, "percentage": 92.03, "elapsed_time": "1:42:55", "remaining_time": "0:08:54", "throughput": 1032.84, "total_tokens": 6378208} {"current_steps": 70835, "total_steps": 76960, "loss": 0.0352, "lr": 9.588544947798206e-07, "epoch": 18.408264033264032, "percentage": 92.04, "elapsed_time": "1:42:55", "remaining_time": "0:08:54", "throughput": 1032.84, "total_tokens": 6378656} {"current_steps": 70840, "total_steps": 76960, "loss": 0.0272, "lr": 9.572999749075135e-07, "epoch": 18.40956340956341, "percentage": 92.05, "elapsed_time": "1:42:56", "remaining_time": "0:08:53", "throughput": 1032.84, "total_tokens": 6379072} {"current_steps": 70845, "total_steps": 76960, "loss": 0.0343, "lr": 9.55746691574308e-07, "epoch": 18.410862785862786, "percentage": 92.05, "elapsed_time": "1:42:56", "remaining_time": "0:08:53", "throughput": 1032.84, "total_tokens": 6379520} {"current_steps": 70850, "total_steps": 76960, "loss": 0.0029, "lr": 9.541946448600846e-07, "epoch": 18.41216216216216, "percentage": 92.06, "elapsed_time": "1:42:57", "remaining_time": "0:08:52", "throughput": 1032.84, "total_tokens": 6379968} {"current_steps": 70855, "total_steps": 76960, "loss": 0.0447, "lr": 9.526438348446742e-07, "epoch": 18.41346153846154, "percentage": 92.07, "elapsed_time": "1:42:57", "remaining_time": "0:08:52", "throughput": 1032.84, "total_tokens": 6380416} {"current_steps": 70860, "total_steps": 76960, "loss": 0.0008, "lr": 9.510942616078294e-07, "epoch": 18.414760914760915, "percentage": 92.07, "elapsed_time": "1:42:57", "remaining_time": "0:08:51", "throughput": 1032.85, "total_tokens": 6380864} {"current_steps": 70865, "total_steps": 76960, "loss": 0.2471, "lr": 9.495459252292504e-07, "epoch": 18.41606029106029, "percentage": 92.08, "elapsed_time": "1:42:58", "remaining_time": "0:08:51", "throughput": 1032.85, "total_tokens": 6381312} {"current_steps": 70870, "total_steps": 76960, "loss": 0.2158, "lr": 9.47998825788568e-07, "epoch": 18.41735966735967, "percentage": 92.09, "elapsed_time": "1:42:58", "remaining_time": "0:08:50", "throughput": 1032.85, "total_tokens": 6381744} {"current_steps": 70875, "total_steps": 76960, "loss": 0.0048, "lr": 9.46452963365349e-07, "epoch": 18.418659043659044, "percentage": 92.09, "elapsed_time": "1:42:59", "remaining_time": "0:08:50", "throughput": 1032.85, "total_tokens": 6382192} {"current_steps": 70880, "total_steps": 76960, "loss": 0.1715, "lr": 9.44908338039105e-07, "epoch": 18.41995841995842, "percentage": 92.1, "elapsed_time": "1:42:59", "remaining_time": "0:08:50", "throughput": 1032.86, "total_tokens": 6382672} {"current_steps": 70885, "total_steps": 76960, "loss": 0.333, "lr": 9.433649498892721e-07, "epoch": 18.421257796257795, "percentage": 92.11, "elapsed_time": "1:43:00", "remaining_time": "0:08:49", "throughput": 1032.87, "total_tokens": 6383152} {"current_steps": 70890, "total_steps": 76960, "loss": 0.41, "lr": 9.418227989952288e-07, "epoch": 18.422557172557173, "percentage": 92.11, "elapsed_time": "1:43:00", "remaining_time": "0:08:49", "throughput": 1032.87, "total_tokens": 6383616} {"current_steps": 70895, "total_steps": 76960, "loss": 0.0006, "lr": 9.402818854362949e-07, "epoch": 18.42385654885655, "percentage": 92.12, "elapsed_time": "1:43:00", "remaining_time": "0:08:48", "throughput": 1032.88, "total_tokens": 6384080} {"current_steps": 70900, "total_steps": 76960, "loss": 0.1908, "lr": 9.387422092917153e-07, "epoch": 18.425155925155924, "percentage": 92.13, "elapsed_time": "1:43:01", "remaining_time": "0:08:48", "throughput": 1032.88, "total_tokens": 6384512} {"current_steps": 70905, "total_steps": 76960, "loss": 0.005, "lr": 9.372037706406739e-07, "epoch": 18.426455301455302, "percentage": 92.13, "elapsed_time": "1:43:01", "remaining_time": "0:08:47", "throughput": 1032.89, "total_tokens": 6385008} {"current_steps": 70910, "total_steps": 76960, "loss": 0.0187, "lr": 9.356665695623018e-07, "epoch": 18.427754677754677, "percentage": 92.14, "elapsed_time": "1:43:02", "remaining_time": "0:08:47", "throughput": 1032.89, "total_tokens": 6385440} {"current_steps": 70915, "total_steps": 76960, "loss": 0.072, "lr": 9.341306061356525e-07, "epoch": 18.429054054054053, "percentage": 92.15, "elapsed_time": "1:43:02", "remaining_time": "0:08:47", "throughput": 1032.89, "total_tokens": 6385856} {"current_steps": 70920, "total_steps": 76960, "loss": 0.1141, "lr": 9.325958804397295e-07, "epoch": 18.43035343035343, "percentage": 92.15, "elapsed_time": "1:43:02", "remaining_time": "0:08:46", "throughput": 1032.89, "total_tokens": 6386304} {"current_steps": 70925, "total_steps": 76960, "loss": 0.0005, "lr": 9.310623925534556e-07, "epoch": 18.431652806652806, "percentage": 92.16, "elapsed_time": "1:43:03", "remaining_time": "0:08:46", "throughput": 1032.89, "total_tokens": 6386752} {"current_steps": 70930, "total_steps": 76960, "loss": 0.0059, "lr": 9.295301425557095e-07, "epoch": 18.43295218295218, "percentage": 92.16, "elapsed_time": "1:43:03", "remaining_time": "0:08:45", "throughput": 1032.9, "total_tokens": 6387216} {"current_steps": 70935, "total_steps": 76960, "loss": 0.2171, "lr": 9.279991305252866e-07, "epoch": 18.43425155925156, "percentage": 92.17, "elapsed_time": "1:43:04", "remaining_time": "0:08:45", "throughput": 1032.91, "total_tokens": 6387680} {"current_steps": 70940, "total_steps": 76960, "loss": 0.1918, "lr": 9.264693565409377e-07, "epoch": 18.435550935550935, "percentage": 92.18, "elapsed_time": "1:43:04", "remaining_time": "0:08:44", "throughput": 1032.92, "total_tokens": 6388176} {"current_steps": 70945, "total_steps": 76960, "loss": 0.0642, "lr": 9.249408206813332e-07, "epoch": 18.43685031185031, "percentage": 92.18, "elapsed_time": "1:43:05", "remaining_time": "0:08:44", "throughput": 1032.91, "total_tokens": 6388592} {"current_steps": 70950, "total_steps": 76960, "loss": 0.0016, "lr": 9.234135230250879e-07, "epoch": 18.43814968814969, "percentage": 92.19, "elapsed_time": "1:43:05", "remaining_time": "0:08:43", "throughput": 1032.92, "total_tokens": 6389040} {"current_steps": 70955, "total_steps": 76960, "loss": 0.0038, "lr": 9.218874636507558e-07, "epoch": 18.439449064449065, "percentage": 92.2, "elapsed_time": "1:43:05", "remaining_time": "0:08:43", "throughput": 1032.92, "total_tokens": 6389504} {"current_steps": 70960, "total_steps": 76960, "loss": 0.0786, "lr": 9.20362642636824e-07, "epoch": 18.44074844074844, "percentage": 92.2, "elapsed_time": "1:43:06", "remaining_time": "0:08:43", "throughput": 1032.93, "total_tokens": 6389984} {"current_steps": 70965, "total_steps": 76960, "loss": 0.0428, "lr": 9.188390600617158e-07, "epoch": 18.44204781704782, "percentage": 92.21, "elapsed_time": "1:43:06", "remaining_time": "0:08:42", "throughput": 1032.93, "total_tokens": 6390416} {"current_steps": 70970, "total_steps": 76960, "loss": 0.025, "lr": 9.173167160037827e-07, "epoch": 18.443347193347194, "percentage": 92.22, "elapsed_time": "1:43:07", "remaining_time": "0:08:42", "throughput": 1032.93, "total_tokens": 6390848} {"current_steps": 70975, "total_steps": 76960, "loss": 0.0784, "lr": 9.157956105413257e-07, "epoch": 18.44464656964657, "percentage": 92.22, "elapsed_time": "1:43:07", "remaining_time": "0:08:41", "throughput": 1032.93, "total_tokens": 6391280} {"current_steps": 70980, "total_steps": 76960, "loss": 0.0049, "lr": 9.142757437525795e-07, "epoch": 18.445945945945947, "percentage": 92.23, "elapsed_time": "1:43:07", "remaining_time": "0:08:41", "throughput": 1032.94, "total_tokens": 6391728} {"current_steps": 70985, "total_steps": 76960, "loss": 0.1855, "lr": 9.127571157157094e-07, "epoch": 18.447245322245323, "percentage": 92.24, "elapsed_time": "1:43:08", "remaining_time": "0:08:40", "throughput": 1032.94, "total_tokens": 6392192} {"current_steps": 70990, "total_steps": 76960, "loss": 0.0026, "lr": 9.112397265088196e-07, "epoch": 18.448544698544698, "percentage": 92.24, "elapsed_time": "1:43:08", "remaining_time": "0:08:40", "throughput": 1032.95, "total_tokens": 6392656} {"current_steps": 70995, "total_steps": 76960, "loss": 0.3468, "lr": 9.097235762099532e-07, "epoch": 18.449844074844076, "percentage": 92.25, "elapsed_time": "1:43:09", "remaining_time": "0:08:40", "throughput": 1032.94, "total_tokens": 6393072} {"current_steps": 71000, "total_steps": 76960, "loss": 0.0013, "lr": 9.082086648970811e-07, "epoch": 18.45114345114345, "percentage": 92.26, "elapsed_time": "1:43:09", "remaining_time": "0:08:39", "throughput": 1032.95, "total_tokens": 6393520} {"current_steps": 71005, "total_steps": 76960, "loss": 0.2184, "lr": 9.066949926481271e-07, "epoch": 18.452442827442827, "percentage": 92.26, "elapsed_time": "1:43:10", "remaining_time": "0:08:39", "throughput": 1032.95, "total_tokens": 6393968} {"current_steps": 71010, "total_steps": 76960, "loss": 0.0612, "lr": 9.051825595409291e-07, "epoch": 18.453742203742205, "percentage": 92.27, "elapsed_time": "1:43:10", "remaining_time": "0:08:38", "throughput": 1032.95, "total_tokens": 6394416} {"current_steps": 71015, "total_steps": 76960, "loss": 0.423, "lr": 9.036713656532802e-07, "epoch": 18.45504158004158, "percentage": 92.28, "elapsed_time": "1:43:10", "remaining_time": "0:08:38", "throughput": 1032.96, "total_tokens": 6394880} {"current_steps": 71020, "total_steps": 76960, "loss": 0.0059, "lr": 9.02161411062899e-07, "epoch": 18.456340956340956, "percentage": 92.28, "elapsed_time": "1:43:11", "remaining_time": "0:08:37", "throughput": 1032.96, "total_tokens": 6395328} {"current_steps": 71025, "total_steps": 76960, "loss": 0.1615, "lr": 9.006526958474509e-07, "epoch": 18.45764033264033, "percentage": 92.29, "elapsed_time": "1:43:11", "remaining_time": "0:08:37", "throughput": 1032.97, "total_tokens": 6395808} {"current_steps": 71030, "total_steps": 76960, "loss": 0.2051, "lr": 8.991452200845268e-07, "epoch": 18.45893970893971, "percentage": 92.29, "elapsed_time": "1:43:12", "remaining_time": "0:08:36", "throughput": 1032.97, "total_tokens": 6396256} {"current_steps": 71035, "total_steps": 76960, "loss": 0.0924, "lr": 8.976389838516508e-07, "epoch": 18.460239085239085, "percentage": 92.3, "elapsed_time": "1:43:12", "remaining_time": "0:08:36", "throughput": 1032.98, "total_tokens": 6396720} {"current_steps": 71040, "total_steps": 76960, "loss": 0.0021, "lr": 8.961339872262997e-07, "epoch": 18.46153846153846, "percentage": 92.31, "elapsed_time": "1:43:12", "remaining_time": "0:08:36", "throughput": 1032.98, "total_tokens": 6397152} {"current_steps": 71045, "total_steps": 76960, "loss": 0.0031, "lr": 8.946302302858672e-07, "epoch": 18.46283783783784, "percentage": 92.31, "elapsed_time": "1:43:13", "remaining_time": "0:08:35", "throughput": 1032.97, "total_tokens": 6397552} {"current_steps": 71050, "total_steps": 76960, "loss": 0.4659, "lr": 8.931277131077026e-07, "epoch": 18.464137214137214, "percentage": 92.32, "elapsed_time": "1:43:13", "remaining_time": "0:08:35", "throughput": 1032.98, "total_tokens": 6398000} {"current_steps": 71055, "total_steps": 76960, "loss": 0.0533, "lr": 8.916264357690746e-07, "epoch": 18.46543659043659, "percentage": 92.33, "elapsed_time": "1:43:14", "remaining_time": "0:08:34", "throughput": 1032.98, "total_tokens": 6398432} {"current_steps": 71060, "total_steps": 76960, "loss": 0.0027, "lr": 8.901263983472047e-07, "epoch": 18.466735966735968, "percentage": 92.33, "elapsed_time": "1:43:14", "remaining_time": "0:08:34", "throughput": 1032.99, "total_tokens": 6398912} {"current_steps": 71065, "total_steps": 76960, "loss": 0.0798, "lr": 8.886276009192284e-07, "epoch": 18.468035343035343, "percentage": 92.34, "elapsed_time": "1:43:15", "remaining_time": "0:08:33", "throughput": 1032.99, "total_tokens": 6399360} {"current_steps": 71070, "total_steps": 76960, "loss": 0.0124, "lr": 8.871300435622427e-07, "epoch": 18.469334719334718, "percentage": 92.35, "elapsed_time": "1:43:15", "remaining_time": "0:08:33", "throughput": 1033.0, "total_tokens": 6399840} {"current_steps": 71075, "total_steps": 76960, "loss": 0.0101, "lr": 8.856337263532605e-07, "epoch": 18.470634095634097, "percentage": 92.35, "elapsed_time": "1:43:15", "remaining_time": "0:08:33", "throughput": 1033.0, "total_tokens": 6400288} {"current_steps": 71080, "total_steps": 76960, "loss": 0.3132, "lr": 8.841386493692428e-07, "epoch": 18.471933471933472, "percentage": 92.36, "elapsed_time": "1:43:16", "remaining_time": "0:08:32", "throughput": 1033.0, "total_tokens": 6400720} {"current_steps": 71085, "total_steps": 76960, "loss": 0.0082, "lr": 8.826448126870779e-07, "epoch": 18.473232848232847, "percentage": 92.37, "elapsed_time": "1:43:16", "remaining_time": "0:08:32", "throughput": 1033.0, "total_tokens": 6401184} {"current_steps": 71090, "total_steps": 76960, "loss": 0.1417, "lr": 8.811522163835961e-07, "epoch": 18.474532224532226, "percentage": 92.37, "elapsed_time": "1:43:17", "remaining_time": "0:08:31", "throughput": 1033.01, "total_tokens": 6401632} {"current_steps": 71095, "total_steps": 76960, "loss": 0.0012, "lr": 8.796608605355722e-07, "epoch": 18.4758316008316, "percentage": 92.38, "elapsed_time": "1:43:17", "remaining_time": "0:08:31", "throughput": 1033.0, "total_tokens": 6402048} {"current_steps": 71100, "total_steps": 76960, "loss": 0.0144, "lr": 8.781707452196947e-07, "epoch": 18.477130977130976, "percentage": 92.39, "elapsed_time": "1:43:17", "remaining_time": "0:08:30", "throughput": 1033.01, "total_tokens": 6402496} {"current_steps": 71105, "total_steps": 76960, "loss": 0.0611, "lr": 8.766818705126134e-07, "epoch": 18.478430353430355, "percentage": 92.39, "elapsed_time": "1:43:18", "remaining_time": "0:08:30", "throughput": 1033.01, "total_tokens": 6402944} {"current_steps": 71110, "total_steps": 76960, "loss": 0.0871, "lr": 8.751942364908949e-07, "epoch": 18.47972972972973, "percentage": 92.4, "elapsed_time": "1:43:18", "remaining_time": "0:08:29", "throughput": 1033.01, "total_tokens": 6403376} {"current_steps": 71115, "total_steps": 76960, "loss": 0.0185, "lr": 8.737078432310531e-07, "epoch": 18.481029106029105, "percentage": 92.41, "elapsed_time": "1:43:19", "remaining_time": "0:08:29", "throughput": 1033.01, "total_tokens": 6403808} {"current_steps": 71120, "total_steps": 76960, "loss": 0.1198, "lr": 8.722226908095321e-07, "epoch": 18.482328482328484, "percentage": 92.41, "elapsed_time": "1:43:19", "remaining_time": "0:08:29", "throughput": 1033.01, "total_tokens": 6404256} {"current_steps": 71125, "total_steps": 76960, "loss": 0.0669, "lr": 8.707387793027155e-07, "epoch": 18.48362785862786, "percentage": 92.42, "elapsed_time": "1:43:20", "remaining_time": "0:08:28", "throughput": 1033.01, "total_tokens": 6404688} {"current_steps": 71130, "total_steps": 76960, "loss": 0.05, "lr": 8.692561087869256e-07, "epoch": 18.484927234927234, "percentage": 92.42, "elapsed_time": "1:43:20", "remaining_time": "0:08:28", "throughput": 1033.02, "total_tokens": 6405168} {"current_steps": 71135, "total_steps": 76960, "loss": 0.1826, "lr": 8.677746793384151e-07, "epoch": 18.486226611226613, "percentage": 92.43, "elapsed_time": "1:43:20", "remaining_time": "0:08:27", "throughput": 1033.02, "total_tokens": 6405600} {"current_steps": 71140, "total_steps": 76960, "loss": 0.4008, "lr": 8.662944910333731e-07, "epoch": 18.487525987525988, "percentage": 92.44, "elapsed_time": "1:43:21", "remaining_time": "0:08:27", "throughput": 1033.02, "total_tokens": 6406032} {"current_steps": 71145, "total_steps": 76960, "loss": 0.0196, "lr": 8.648155439479305e-07, "epoch": 18.488825363825363, "percentage": 92.44, "elapsed_time": "1:43:21", "remaining_time": "0:08:26", "throughput": 1033.03, "total_tokens": 6406496} {"current_steps": 71150, "total_steps": 76960, "loss": 0.022, "lr": 8.633378381581487e-07, "epoch": 18.49012474012474, "percentage": 92.45, "elapsed_time": "1:43:22", "remaining_time": "0:08:26", "throughput": 1033.03, "total_tokens": 6406944} {"current_steps": 71155, "total_steps": 76960, "loss": 0.003, "lr": 8.618613737400305e-07, "epoch": 18.491424116424117, "percentage": 92.46, "elapsed_time": "1:43:22", "remaining_time": "0:08:26", "throughput": 1033.03, "total_tokens": 6407376} {"current_steps": 71160, "total_steps": 76960, "loss": 0.0112, "lr": 8.6038615076951e-07, "epoch": 18.492723492723492, "percentage": 92.46, "elapsed_time": "1:43:22", "remaining_time": "0:08:25", "throughput": 1033.03, "total_tokens": 6407792} {"current_steps": 71165, "total_steps": 76960, "loss": 0.0049, "lr": 8.589121693224567e-07, "epoch": 18.49402286902287, "percentage": 92.47, "elapsed_time": "1:43:23", "remaining_time": "0:08:25", "throughput": 1033.03, "total_tokens": 6408224} {"current_steps": 71170, "total_steps": 76960, "loss": 0.0571, "lr": 8.574394294746824e-07, "epoch": 18.495322245322246, "percentage": 92.48, "elapsed_time": "1:43:23", "remaining_time": "0:08:24", "throughput": 1033.03, "total_tokens": 6408656} {"current_steps": 71175, "total_steps": 76960, "loss": 0.0045, "lr": 8.559679313019292e-07, "epoch": 18.49662162162162, "percentage": 92.48, "elapsed_time": "1:43:24", "remaining_time": "0:08:24", "throughput": 1033.03, "total_tokens": 6409104} {"current_steps": 71180, "total_steps": 76960, "loss": 0.5227, "lr": 8.544976748798838e-07, "epoch": 18.497920997920996, "percentage": 92.49, "elapsed_time": "1:43:24", "remaining_time": "0:08:23", "throughput": 1033.03, "total_tokens": 6409552} {"current_steps": 71185, "total_steps": 76960, "loss": 0.0143, "lr": 8.530286602841525e-07, "epoch": 18.499220374220375, "percentage": 92.5, "elapsed_time": "1:43:25", "remaining_time": "0:08:23", "throughput": 1033.04, "total_tokens": 6410016} {"current_steps": 71190, "total_steps": 76960, "loss": 0.0005, "lr": 8.515608875902997e-07, "epoch": 18.50051975051975, "percentage": 92.5, "elapsed_time": "1:43:25", "remaining_time": "0:08:22", "throughput": 1033.04, "total_tokens": 6410448} {"current_steps": 71195, "total_steps": 76960, "loss": 0.1381, "lr": 8.500943568737984e-07, "epoch": 18.501819126819125, "percentage": 92.51, "elapsed_time": "1:43:25", "remaining_time": "0:08:22", "throughput": 1033.04, "total_tokens": 6410912} {"current_steps": 71200, "total_steps": 76960, "loss": 0.1805, "lr": 8.486290682100939e-07, "epoch": 18.503118503118504, "percentage": 92.52, "elapsed_time": "1:43:26", "remaining_time": "0:08:22", "throughput": 1033.05, "total_tokens": 6411360} {"current_steps": 71205, "total_steps": 76960, "loss": 0.0109, "lr": 8.471650216745314e-07, "epoch": 18.50441787941788, "percentage": 92.52, "elapsed_time": "1:43:26", "remaining_time": "0:08:21", "throughput": 1033.05, "total_tokens": 6411824} {"current_steps": 71210, "total_steps": 76960, "loss": 0.0541, "lr": 8.457022173424173e-07, "epoch": 18.505717255717254, "percentage": 92.53, "elapsed_time": "1:43:27", "remaining_time": "0:08:21", "throughput": 1033.05, "total_tokens": 6412256} {"current_steps": 71215, "total_steps": 76960, "loss": 0.0008, "lr": 8.442406552889776e-07, "epoch": 18.507016632016633, "percentage": 92.54, "elapsed_time": "1:43:27", "remaining_time": "0:08:20", "throughput": 1033.06, "total_tokens": 6412704} {"current_steps": 71220, "total_steps": 76960, "loss": 0.109, "lr": 8.42780335589391e-07, "epoch": 18.508316008316008, "percentage": 92.54, "elapsed_time": "1:43:27", "remaining_time": "0:08:20", "throughput": 1033.06, "total_tokens": 6413136} {"current_steps": 71225, "total_steps": 76960, "loss": 0.0829, "lr": 8.413212583187558e-07, "epoch": 18.509615384615383, "percentage": 92.55, "elapsed_time": "1:43:28", "remaining_time": "0:08:19", "throughput": 1033.06, "total_tokens": 6413568} {"current_steps": 71230, "total_steps": 76960, "loss": 0.0088, "lr": 8.398634235521147e-07, "epoch": 18.510914760914762, "percentage": 92.55, "elapsed_time": "1:43:28", "remaining_time": "0:08:19", "throughput": 1033.06, "total_tokens": 6414000} {"current_steps": 71235, "total_steps": 76960, "loss": 0.0127, "lr": 8.384068313644494e-07, "epoch": 18.512214137214137, "percentage": 92.56, "elapsed_time": "1:43:29", "remaining_time": "0:08:19", "throughput": 1033.06, "total_tokens": 6414432} {"current_steps": 71240, "total_steps": 76960, "loss": 0.2007, "lr": 8.369514818306667e-07, "epoch": 18.513513513513512, "percentage": 92.57, "elapsed_time": "1:43:29", "remaining_time": "0:08:18", "throughput": 1033.06, "total_tokens": 6414896} {"current_steps": 71245, "total_steps": 76960, "loss": 0.0664, "lr": 8.354973750256262e-07, "epoch": 18.51481288981289, "percentage": 92.57, "elapsed_time": "1:43:30", "remaining_time": "0:08:18", "throughput": 1033.07, "total_tokens": 6415376} {"current_steps": 71250, "total_steps": 76960, "loss": 0.0003, "lr": 8.340445110241069e-07, "epoch": 18.516112266112266, "percentage": 92.58, "elapsed_time": "1:43:30", "remaining_time": "0:08:17", "throughput": 1033.08, "total_tokens": 6415872} {"current_steps": 71255, "total_steps": 76960, "loss": 0.1041, "lr": 8.32592889900835e-07, "epoch": 18.51741164241164, "percentage": 92.59, "elapsed_time": "1:43:30", "remaining_time": "0:08:17", "throughput": 1033.09, "total_tokens": 6416352} {"current_steps": 71260, "total_steps": 76960, "loss": 0.1603, "lr": 8.311425117304649e-07, "epoch": 18.51871101871102, "percentage": 92.59, "elapsed_time": "1:43:31", "remaining_time": "0:08:16", "throughput": 1033.09, "total_tokens": 6416816} {"current_steps": 71265, "total_steps": 76960, "loss": 0.2846, "lr": 8.296933765875897e-07, "epoch": 18.520010395010395, "percentage": 92.6, "elapsed_time": "1:43:31", "remaining_time": "0:08:16", "throughput": 1033.09, "total_tokens": 6417248} {"current_steps": 71270, "total_steps": 76960, "loss": 0.2464, "lr": 8.282454845467468e-07, "epoch": 18.52130977130977, "percentage": 92.61, "elapsed_time": "1:43:32", "remaining_time": "0:08:15", "throughput": 1033.1, "total_tokens": 6417696} {"current_steps": 71275, "total_steps": 76960, "loss": 0.2526, "lr": 8.267988356823992e-07, "epoch": 18.52260914760915, "percentage": 92.61, "elapsed_time": "1:43:32", "remaining_time": "0:08:15", "throughput": 1033.1, "total_tokens": 6418128} {"current_steps": 71280, "total_steps": 76960, "loss": 0.0497, "lr": 8.253534300689481e-07, "epoch": 18.523908523908524, "percentage": 92.62, "elapsed_time": "1:43:32", "remaining_time": "0:08:15", "throughput": 1033.1, "total_tokens": 6418592} {"current_steps": 71285, "total_steps": 76960, "loss": 0.3619, "lr": 8.239092677807342e-07, "epoch": 18.5252079002079, "percentage": 92.63, "elapsed_time": "1:43:33", "remaining_time": "0:08:14", "throughput": 1033.11, "total_tokens": 6419040} {"current_steps": 71290, "total_steps": 76960, "loss": 0.01, "lr": 8.224663488920342e-07, "epoch": 18.526507276507278, "percentage": 92.63, "elapsed_time": "1:43:33", "remaining_time": "0:08:14", "throughput": 1033.11, "total_tokens": 6419472} {"current_steps": 71295, "total_steps": 76960, "loss": 0.0489, "lr": 8.210246734770499e-07, "epoch": 18.527806652806653, "percentage": 92.64, "elapsed_time": "1:43:34", "remaining_time": "0:08:13", "throughput": 1033.11, "total_tokens": 6419936} {"current_steps": 71300, "total_steps": 76960, "loss": 0.0095, "lr": 8.195842416099359e-07, "epoch": 18.52910602910603, "percentage": 92.65, "elapsed_time": "1:43:34", "remaining_time": "0:08:13", "throughput": 1033.12, "total_tokens": 6420416} {"current_steps": 71305, "total_steps": 76960, "loss": 0.0005, "lr": 8.181450533647717e-07, "epoch": 18.530405405405407, "percentage": 92.65, "elapsed_time": "1:43:35", "remaining_time": "0:08:12", "throughput": 1033.12, "total_tokens": 6420864} {"current_steps": 71310, "total_steps": 76960, "loss": 0.0853, "lr": 8.167071088155787e-07, "epoch": 18.531704781704782, "percentage": 92.66, "elapsed_time": "1:43:35", "remaining_time": "0:08:12", "throughput": 1033.12, "total_tokens": 6421280} {"current_steps": 71315, "total_steps": 76960, "loss": 0.0246, "lr": 8.152704080363089e-07, "epoch": 18.533004158004157, "percentage": 92.67, "elapsed_time": "1:43:35", "remaining_time": "0:08:12", "throughput": 1033.12, "total_tokens": 6421728} {"current_steps": 71320, "total_steps": 76960, "loss": 0.0887, "lr": 8.138349511008586e-07, "epoch": 18.534303534303533, "percentage": 92.67, "elapsed_time": "1:43:36", "remaining_time": "0:08:11", "throughput": 1033.12, "total_tokens": 6422144} {"current_steps": 71325, "total_steps": 76960, "loss": 0.0202, "lr": 8.124007380830467e-07, "epoch": 18.53560291060291, "percentage": 92.68, "elapsed_time": "1:43:36", "remaining_time": "0:08:11", "throughput": 1033.12, "total_tokens": 6422576} {"current_steps": 71330, "total_steps": 76960, "loss": 0.0161, "lr": 8.10967769056642e-07, "epoch": 18.536902286902286, "percentage": 92.68, "elapsed_time": "1:43:37", "remaining_time": "0:08:10", "throughput": 1033.12, "total_tokens": 6422992} {"current_steps": 71335, "total_steps": 76960, "loss": 0.0048, "lr": 8.095360440953409e-07, "epoch": 18.53820166320166, "percentage": 92.69, "elapsed_time": "1:43:37", "remaining_time": "0:08:10", "throughput": 1033.12, "total_tokens": 6423440} {"current_steps": 71340, "total_steps": 76960, "loss": 0.1916, "lr": 8.081055632727791e-07, "epoch": 18.53950103950104, "percentage": 92.7, "elapsed_time": "1:43:37", "remaining_time": "0:08:09", "throughput": 1033.13, "total_tokens": 6423888} {"current_steps": 71345, "total_steps": 76960, "loss": 0.0864, "lr": 8.066763266625282e-07, "epoch": 18.540800415800415, "percentage": 92.7, "elapsed_time": "1:43:38", "remaining_time": "0:08:09", "throughput": 1033.13, "total_tokens": 6424320} {"current_steps": 71350, "total_steps": 76960, "loss": 0.3039, "lr": 8.052483343380962e-07, "epoch": 18.54209979209979, "percentage": 92.71, "elapsed_time": "1:43:38", "remaining_time": "0:08:08", "throughput": 1033.13, "total_tokens": 6424752} {"current_steps": 71355, "total_steps": 76960, "loss": 0.434, "lr": 8.038215863729242e-07, "epoch": 18.54339916839917, "percentage": 92.72, "elapsed_time": "1:43:39", "remaining_time": "0:08:08", "throughput": 1033.13, "total_tokens": 6425184} {"current_steps": 71360, "total_steps": 76960, "loss": 0.0008, "lr": 8.023960828403898e-07, "epoch": 18.544698544698544, "percentage": 92.72, "elapsed_time": "1:43:39", "remaining_time": "0:08:08", "throughput": 1033.13, "total_tokens": 6425616} {"current_steps": 71365, "total_steps": 76960, "loss": 0.1088, "lr": 8.009718238138148e-07, "epoch": 18.54599792099792, "percentage": 92.73, "elapsed_time": "1:43:40", "remaining_time": "0:08:07", "throughput": 1033.14, "total_tokens": 6426112} {"current_steps": 71370, "total_steps": 76960, "loss": 0.0006, "lr": 7.995488093664405e-07, "epoch": 18.5472972972973, "percentage": 92.74, "elapsed_time": "1:43:40", "remaining_time": "0:08:07", "throughput": 1033.15, "total_tokens": 6426592} {"current_steps": 71375, "total_steps": 76960, "loss": 0.3844, "lr": 7.981270395714585e-07, "epoch": 18.548596673596673, "percentage": 92.74, "elapsed_time": "1:43:40", "remaining_time": "0:08:06", "throughput": 1033.15, "total_tokens": 6427040} {"current_steps": 71380, "total_steps": 76960, "loss": 0.0282, "lr": 7.967065145019908e-07, "epoch": 18.54989604989605, "percentage": 92.75, "elapsed_time": "1:43:41", "remaining_time": "0:08:06", "throughput": 1033.15, "total_tokens": 6427488} {"current_steps": 71385, "total_steps": 76960, "loss": 0.0023, "lr": 7.952872342311013e-07, "epoch": 18.551195426195427, "percentage": 92.76, "elapsed_time": "1:43:41", "remaining_time": "0:08:05", "throughput": 1033.15, "total_tokens": 6427904} {"current_steps": 71390, "total_steps": 76960, "loss": 0.1887, "lr": 7.938691988317787e-07, "epoch": 18.552494802494802, "percentage": 92.76, "elapsed_time": "1:43:42", "remaining_time": "0:08:05", "throughput": 1033.16, "total_tokens": 6428384} {"current_steps": 71395, "total_steps": 76960, "loss": 0.0019, "lr": 7.924524083769591e-07, "epoch": 18.553794178794178, "percentage": 92.77, "elapsed_time": "1:43:42", "remaining_time": "0:08:05", "throughput": 1033.16, "total_tokens": 6428832} {"current_steps": 71400, "total_steps": 76960, "loss": 0.0039, "lr": 7.910368629395038e-07, "epoch": 18.555093555093556, "percentage": 92.78, "elapsed_time": "1:43:42", "remaining_time": "0:08:04", "throughput": 1033.16, "total_tokens": 6429280} {"current_steps": 71405, "total_steps": 76960, "loss": 0.0454, "lr": 7.896225625922238e-07, "epoch": 18.55639293139293, "percentage": 92.78, "elapsed_time": "1:43:43", "remaining_time": "0:08:04", "throughput": 1033.17, "total_tokens": 6429744} {"current_steps": 71410, "total_steps": 76960, "loss": 0.1475, "lr": 7.882095074078472e-07, "epoch": 18.557692307692307, "percentage": 92.79, "elapsed_time": "1:43:43", "remaining_time": "0:08:03", "throughput": 1033.17, "total_tokens": 6430192} {"current_steps": 71415, "total_steps": 76960, "loss": 0.0049, "lr": 7.867976974590546e-07, "epoch": 18.558991683991685, "percentage": 92.79, "elapsed_time": "1:43:44", "remaining_time": "0:08:03", "throughput": 1033.17, "total_tokens": 6430608} {"current_steps": 71420, "total_steps": 76960, "loss": 0.0004, "lr": 7.853871328184576e-07, "epoch": 18.56029106029106, "percentage": 92.8, "elapsed_time": "1:43:44", "remaining_time": "0:08:02", "throughput": 1033.17, "total_tokens": 6431056} {"current_steps": 71425, "total_steps": 76960, "loss": 0.0383, "lr": 7.839778135586007e-07, "epoch": 18.561590436590436, "percentage": 92.81, "elapsed_time": "1:43:44", "remaining_time": "0:08:02", "throughput": 1033.17, "total_tokens": 6431504} {"current_steps": 71430, "total_steps": 76960, "loss": 0.0443, "lr": 7.825697397519705e-07, "epoch": 18.562889812889814, "percentage": 92.81, "elapsed_time": "1:43:45", "remaining_time": "0:08:01", "throughput": 1033.17, "total_tokens": 6431936} {"current_steps": 71435, "total_steps": 76960, "loss": 0.0034, "lr": 7.811629114709812e-07, "epoch": 18.56418918918919, "percentage": 92.82, "elapsed_time": "1:43:45", "remaining_time": "0:08:01", "throughput": 1033.18, "total_tokens": 6432400} {"current_steps": 71440, "total_steps": 76960, "loss": 0.0005, "lr": 7.797573287879889e-07, "epoch": 18.565488565488565, "percentage": 92.83, "elapsed_time": "1:43:46", "remaining_time": "0:08:01", "throughput": 1033.19, "total_tokens": 6432880} {"current_steps": 71445, "total_steps": 76960, "loss": 0.1034, "lr": 7.783529917752802e-07, "epoch": 18.566787941787943, "percentage": 92.83, "elapsed_time": "1:43:46", "remaining_time": "0:08:00", "throughput": 1033.18, "total_tokens": 6433280} {"current_steps": 71450, "total_steps": 76960, "loss": 0.001, "lr": 7.76949900505089e-07, "epoch": 18.56808731808732, "percentage": 92.84, "elapsed_time": "1:43:47", "remaining_time": "0:08:00", "throughput": 1033.19, "total_tokens": 6433744} {"current_steps": 71455, "total_steps": 76960, "loss": 0.0135, "lr": 7.755480550495714e-07, "epoch": 18.569386694386694, "percentage": 92.85, "elapsed_time": "1:43:47", "remaining_time": "0:07:59", "throughput": 1033.19, "total_tokens": 6434208} {"current_steps": 71460, "total_steps": 76960, "loss": 0.1497, "lr": 7.741474554808309e-07, "epoch": 18.570686070686072, "percentage": 92.85, "elapsed_time": "1:43:47", "remaining_time": "0:07:59", "throughput": 1033.19, "total_tokens": 6434656} {"current_steps": 71465, "total_steps": 76960, "loss": 0.0349, "lr": 7.72748101870896e-07, "epoch": 18.571985446985448, "percentage": 92.86, "elapsed_time": "1:43:48", "remaining_time": "0:07:58", "throughput": 1033.2, "total_tokens": 6435104} {"current_steps": 71470, "total_steps": 76960, "loss": 0.0881, "lr": 7.713499942917452e-07, "epoch": 18.573284823284823, "percentage": 92.87, "elapsed_time": "1:43:48", "remaining_time": "0:07:58", "throughput": 1033.2, "total_tokens": 6435520} {"current_steps": 71475, "total_steps": 76960, "loss": 0.2022, "lr": 7.699531328152737e-07, "epoch": 18.5745841995842, "percentage": 92.87, "elapsed_time": "1:43:49", "remaining_time": "0:07:58", "throughput": 1033.19, "total_tokens": 6435936} {"current_steps": 71480, "total_steps": 76960, "loss": 0.0989, "lr": 7.685575175133269e-07, "epoch": 18.575883575883577, "percentage": 92.88, "elapsed_time": "1:43:49", "remaining_time": "0:07:57", "throughput": 1033.2, "total_tokens": 6436400} {"current_steps": 71485, "total_steps": 76960, "loss": 0.0145, "lr": 7.671631484576892e-07, "epoch": 18.57718295218295, "percentage": 92.89, "elapsed_time": "1:43:50", "remaining_time": "0:07:57", "throughput": 1033.2, "total_tokens": 6436848} {"current_steps": 71490, "total_steps": 76960, "loss": 0.0169, "lr": 7.657700257200668e-07, "epoch": 18.578482328482327, "percentage": 92.89, "elapsed_time": "1:43:50", "remaining_time": "0:07:56", "throughput": 1033.21, "total_tokens": 6437328} {"current_steps": 71495, "total_steps": 76960, "loss": 0.0012, "lr": 7.643781493721164e-07, "epoch": 18.579781704781706, "percentage": 92.9, "elapsed_time": "1:43:50", "remaining_time": "0:07:56", "throughput": 1033.21, "total_tokens": 6437760} {"current_steps": 71500, "total_steps": 76960, "loss": 0.0098, "lr": 7.629875194854141e-07, "epoch": 18.58108108108108, "percentage": 92.91, "elapsed_time": "1:43:51", "remaining_time": "0:07:55", "throughput": 1033.21, "total_tokens": 6438192} {"current_steps": 71505, "total_steps": 76960, "loss": 0.1017, "lr": 7.615981361314889e-07, "epoch": 18.582380457380456, "percentage": 92.91, "elapsed_time": "1:43:51", "remaining_time": "0:07:55", "throughput": 1033.21, "total_tokens": 6438640} {"current_steps": 71510, "total_steps": 76960, "loss": 0.2906, "lr": 7.602099993817946e-07, "epoch": 18.583679833679835, "percentage": 92.92, "elapsed_time": "1:43:52", "remaining_time": "0:07:54", "throughput": 1033.22, "total_tokens": 6439120} {"current_steps": 71515, "total_steps": 76960, "loss": 0.0618, "lr": 7.588231093077241e-07, "epoch": 18.58497920997921, "percentage": 92.92, "elapsed_time": "1:43:52", "remaining_time": "0:07:54", "throughput": 1033.22, "total_tokens": 6439552} {"current_steps": 71520, "total_steps": 76960, "loss": 0.0736, "lr": 7.574374659806094e-07, "epoch": 18.586278586278585, "percentage": 92.93, "elapsed_time": "1:43:52", "remaining_time": "0:07:54", "throughput": 1033.23, "total_tokens": 6440016} {"current_steps": 71525, "total_steps": 76960, "loss": 0.0086, "lr": 7.560530694717155e-07, "epoch": 18.587577962577964, "percentage": 92.94, "elapsed_time": "1:43:53", "remaining_time": "0:07:53", "throughput": 1033.23, "total_tokens": 6440464} {"current_steps": 71530, "total_steps": 76960, "loss": 0.0011, "lr": 7.546699198522411e-07, "epoch": 18.58887733887734, "percentage": 92.94, "elapsed_time": "1:43:53", "remaining_time": "0:07:53", "throughput": 1033.24, "total_tokens": 6440944} {"current_steps": 71535, "total_steps": 76960, "loss": 0.1794, "lr": 7.532880171933237e-07, "epoch": 18.590176715176714, "percentage": 92.95, "elapsed_time": "1:43:54", "remaining_time": "0:07:52", "throughput": 1033.25, "total_tokens": 6441440} {"current_steps": 71540, "total_steps": 76960, "loss": 0.1444, "lr": 7.519073615660344e-07, "epoch": 18.591476091476093, "percentage": 92.96, "elapsed_time": "1:43:54", "remaining_time": "0:07:52", "throughput": 1033.25, "total_tokens": 6441904} {"current_steps": 71545, "total_steps": 76960, "loss": 0.0961, "lr": 7.505279530413855e-07, "epoch": 18.592775467775468, "percentage": 92.96, "elapsed_time": "1:43:54", "remaining_time": "0:07:51", "throughput": 1033.25, "total_tokens": 6442336} {"current_steps": 71550, "total_steps": 76960, "loss": 0.1264, "lr": 7.491497916903151e-07, "epoch": 18.594074844074843, "percentage": 92.97, "elapsed_time": "1:43:55", "remaining_time": "0:07:51", "throughput": 1033.26, "total_tokens": 6442768} {"current_steps": 71555, "total_steps": 76960, "loss": 0.0182, "lr": 7.477728775837078e-07, "epoch": 18.59537422037422, "percentage": 92.98, "elapsed_time": "1:43:55", "remaining_time": "0:07:51", "throughput": 1033.25, "total_tokens": 6443184} {"current_steps": 71560, "total_steps": 76960, "loss": 0.0468, "lr": 7.463972107923794e-07, "epoch": 18.596673596673597, "percentage": 92.98, "elapsed_time": "1:43:56", "remaining_time": "0:07:50", "throughput": 1033.26, "total_tokens": 6443632} {"current_steps": 71565, "total_steps": 76960, "loss": 0.235, "lr": 7.450227913870816e-07, "epoch": 18.597972972972972, "percentage": 92.99, "elapsed_time": "1:43:56", "remaining_time": "0:07:50", "throughput": 1033.26, "total_tokens": 6444080} {"current_steps": 71570, "total_steps": 76960, "loss": 0.0004, "lr": 7.436496194385024e-07, "epoch": 18.59927234927235, "percentage": 93.0, "elapsed_time": "1:43:57", "remaining_time": "0:07:49", "throughput": 1033.27, "total_tokens": 6444560} {"current_steps": 71575, "total_steps": 76960, "loss": 0.1605, "lr": 7.422776950172599e-07, "epoch": 18.600571725571726, "percentage": 93.0, "elapsed_time": "1:43:57", "remaining_time": "0:07:49", "throughput": 1033.27, "total_tokens": 6445024} {"current_steps": 71580, "total_steps": 76960, "loss": 0.1237, "lr": 7.409070181939231e-07, "epoch": 18.6018711018711, "percentage": 93.01, "elapsed_time": "1:43:57", "remaining_time": "0:07:48", "throughput": 1033.28, "total_tokens": 6445504} {"current_steps": 71585, "total_steps": 76960, "loss": 0.0049, "lr": 7.3953758903898e-07, "epoch": 18.60317047817048, "percentage": 93.02, "elapsed_time": "1:43:58", "remaining_time": "0:07:48", "throughput": 1033.29, "total_tokens": 6445968} {"current_steps": 71590, "total_steps": 76960, "loss": 0.2937, "lr": 7.381694076228656e-07, "epoch": 18.604469854469855, "percentage": 93.02, "elapsed_time": "1:43:58", "remaining_time": "0:07:47", "throughput": 1033.28, "total_tokens": 6446384} {"current_steps": 71595, "total_steps": 76960, "loss": 0.2946, "lr": 7.368024740159434e-07, "epoch": 18.60576923076923, "percentage": 93.03, "elapsed_time": "1:43:59", "remaining_time": "0:07:47", "throughput": 1033.29, "total_tokens": 6446864} {"current_steps": 71600, "total_steps": 76960, "loss": 0.084, "lr": 7.354367882885183e-07, "epoch": 18.60706860706861, "percentage": 93.04, "elapsed_time": "1:43:59", "remaining_time": "0:07:47", "throughput": 1033.29, "total_tokens": 6447312} {"current_steps": 71605, "total_steps": 76960, "loss": 0.3863, "lr": 7.340723505108283e-07, "epoch": 18.608367983367984, "percentage": 93.04, "elapsed_time": "1:43:59", "remaining_time": "0:07:46", "throughput": 1033.3, "total_tokens": 6447792} {"current_steps": 71610, "total_steps": 76960, "loss": 0.0692, "lr": 7.327091607530506e-07, "epoch": 18.60966735966736, "percentage": 93.05, "elapsed_time": "1:44:00", "remaining_time": "0:07:46", "throughput": 1033.31, "total_tokens": 6448256} {"current_steps": 71615, "total_steps": 76960, "loss": 0.0438, "lr": 7.313472190852905e-07, "epoch": 18.610966735966738, "percentage": 93.05, "elapsed_time": "1:44:00", "remaining_time": "0:07:45", "throughput": 1033.32, "total_tokens": 6448736} {"current_steps": 71620, "total_steps": 76960, "loss": 0.0125, "lr": 7.299865255775946e-07, "epoch": 18.612266112266113, "percentage": 93.06, "elapsed_time": "1:44:01", "remaining_time": "0:07:45", "throughput": 1033.33, "total_tokens": 6449232} {"current_steps": 71625, "total_steps": 76960, "loss": 0.2502, "lr": 7.286270802999457e-07, "epoch": 18.613565488565488, "percentage": 93.07, "elapsed_time": "1:44:01", "remaining_time": "0:07:44", "throughput": 1033.33, "total_tokens": 6449680} {"current_steps": 71630, "total_steps": 76960, "loss": 0.0007, "lr": 7.27268883322263e-07, "epoch": 18.614864864864863, "percentage": 93.07, "elapsed_time": "1:44:02", "remaining_time": "0:07:44", "throughput": 1033.33, "total_tokens": 6450112} {"current_steps": 71635, "total_steps": 76960, "loss": 0.6772, "lr": 7.259119347144017e-07, "epoch": 18.616164241164242, "percentage": 93.08, "elapsed_time": "1:44:02", "remaining_time": "0:07:44", "throughput": 1033.32, "total_tokens": 6450512} {"current_steps": 71640, "total_steps": 76960, "loss": 0.2042, "lr": 7.24556234546142e-07, "epoch": 18.617463617463617, "percentage": 93.09, "elapsed_time": "1:44:02", "remaining_time": "0:07:43", "throughput": 1033.33, "total_tokens": 6450976} {"current_steps": 71645, "total_steps": 76960, "loss": 0.0007, "lr": 7.2320178288722e-07, "epoch": 18.618762993762992, "percentage": 93.09, "elapsed_time": "1:44:03", "remaining_time": "0:07:43", "throughput": 1033.33, "total_tokens": 6451408} {"current_steps": 71650, "total_steps": 76960, "loss": 0.1408, "lr": 7.218485798072883e-07, "epoch": 18.62006237006237, "percentage": 93.1, "elapsed_time": "1:44:03", "remaining_time": "0:07:42", "throughput": 1033.33, "total_tokens": 6451872} {"current_steps": 71655, "total_steps": 76960, "loss": 0.0191, "lr": 7.204966253759493e-07, "epoch": 18.621361746361746, "percentage": 93.11, "elapsed_time": "1:44:04", "remaining_time": "0:07:42", "throughput": 1033.34, "total_tokens": 6452336} {"current_steps": 71660, "total_steps": 76960, "loss": 0.0002, "lr": 7.191459196627282e-07, "epoch": 18.62266112266112, "percentage": 93.11, "elapsed_time": "1:44:04", "remaining_time": "0:07:41", "throughput": 1033.34, "total_tokens": 6452768} {"current_steps": 71665, "total_steps": 76960, "loss": 0.1264, "lr": 7.177964627370997e-07, "epoch": 18.6239604989605, "percentage": 93.12, "elapsed_time": "1:44:04", "remaining_time": "0:07:41", "throughput": 1033.34, "total_tokens": 6453184} {"current_steps": 71670, "total_steps": 76960, "loss": 0.3163, "lr": 7.164482546684642e-07, "epoch": 18.625259875259875, "percentage": 93.13, "elapsed_time": "1:44:05", "remaining_time": "0:07:40", "throughput": 1033.34, "total_tokens": 6453632} {"current_steps": 71675, "total_steps": 76960, "loss": 0.3197, "lr": 7.151012955261632e-07, "epoch": 18.62655925155925, "percentage": 93.13, "elapsed_time": "1:44:05", "remaining_time": "0:07:40", "throughput": 1033.35, "total_tokens": 6454096} {"current_steps": 71680, "total_steps": 76960, "loss": 0.05, "lr": 7.13755585379472e-07, "epoch": 18.62785862785863, "percentage": 93.14, "elapsed_time": "1:44:06", "remaining_time": "0:07:40", "throughput": 1033.35, "total_tokens": 6454560} {"current_steps": 71685, "total_steps": 76960, "loss": 0.21, "lr": 7.12411124297599e-07, "epoch": 18.629158004158004, "percentage": 93.15, "elapsed_time": "1:44:06", "remaining_time": "0:07:39", "throughput": 1033.37, "total_tokens": 6455072} {"current_steps": 71690, "total_steps": 76960, "loss": 0.0026, "lr": 7.110679123496972e-07, "epoch": 18.63045738045738, "percentage": 93.15, "elapsed_time": "1:44:07", "remaining_time": "0:07:39", "throughput": 1033.37, "total_tokens": 6455520} {"current_steps": 71695, "total_steps": 76960, "loss": 0.0287, "lr": 7.097259496048364e-07, "epoch": 18.631756756756758, "percentage": 93.16, "elapsed_time": "1:44:07", "remaining_time": "0:07:38", "throughput": 1033.37, "total_tokens": 6455952} {"current_steps": 71700, "total_steps": 76960, "loss": 0.3698, "lr": 7.083852361320531e-07, "epoch": 18.633056133056133, "percentage": 93.17, "elapsed_time": "1:44:07", "remaining_time": "0:07:38", "throughput": 1033.37, "total_tokens": 6456368} {"current_steps": 71705, "total_steps": 76960, "loss": 0.0116, "lr": 7.070457720002865e-07, "epoch": 18.634355509355508, "percentage": 93.17, "elapsed_time": "1:44:08", "remaining_time": "0:07:37", "throughput": 1033.37, "total_tokens": 6456832} {"current_steps": 71710, "total_steps": 76960, "loss": 0.0238, "lr": 7.057075572784372e-07, "epoch": 18.635654885654887, "percentage": 93.18, "elapsed_time": "1:44:08", "remaining_time": "0:07:37", "throughput": 1033.37, "total_tokens": 6457264} {"current_steps": 71715, "total_steps": 76960, "loss": 0.0815, "lr": 7.043705920353222e-07, "epoch": 18.636954261954262, "percentage": 93.18, "elapsed_time": "1:44:09", "remaining_time": "0:07:37", "throughput": 1033.38, "total_tokens": 6457728} {"current_steps": 71720, "total_steps": 76960, "loss": 0.0031, "lr": 7.030348763397088e-07, "epoch": 18.638253638253637, "percentage": 93.19, "elapsed_time": "1:44:09", "remaining_time": "0:07:36", "throughput": 1033.39, "total_tokens": 6458208} {"current_steps": 71725, "total_steps": 76960, "loss": 0.0064, "lr": 7.017004102602892e-07, "epoch": 18.639553014553016, "percentage": 93.2, "elapsed_time": "1:44:09", "remaining_time": "0:07:36", "throughput": 1033.39, "total_tokens": 6458656} {"current_steps": 71730, "total_steps": 76960, "loss": 0.1273, "lr": 7.003671938656975e-07, "epoch": 18.64085239085239, "percentage": 93.2, "elapsed_time": "1:44:10", "remaining_time": "0:07:35", "throughput": 1033.38, "total_tokens": 6459056} {"current_steps": 71735, "total_steps": 76960, "loss": 0.006, "lr": 6.990352272245065e-07, "epoch": 18.642151767151766, "percentage": 93.21, "elapsed_time": "1:44:10", "remaining_time": "0:07:35", "throughput": 1033.39, "total_tokens": 6459536} {"current_steps": 71740, "total_steps": 76960, "loss": 0.4183, "lr": 6.977045104052199e-07, "epoch": 18.643451143451145, "percentage": 93.22, "elapsed_time": "1:44:11", "remaining_time": "0:07:34", "throughput": 1033.4, "total_tokens": 6460016} {"current_steps": 71745, "total_steps": 76960, "loss": 0.0714, "lr": 6.963750434762745e-07, "epoch": 18.64475051975052, "percentage": 93.22, "elapsed_time": "1:44:11", "remaining_time": "0:07:34", "throughput": 1033.41, "total_tokens": 6460528} {"current_steps": 71750, "total_steps": 76960, "loss": 0.0003, "lr": 6.950468265060461e-07, "epoch": 18.646049896049895, "percentage": 93.23, "elapsed_time": "1:44:12", "remaining_time": "0:07:33", "throughput": 1033.42, "total_tokens": 6460992} {"current_steps": 71755, "total_steps": 76960, "loss": 0.4827, "lr": 6.937198595628496e-07, "epoch": 18.647349272349274, "percentage": 93.24, "elapsed_time": "1:44:12", "remaining_time": "0:07:33", "throughput": 1033.41, "total_tokens": 6461392} {"current_steps": 71760, "total_steps": 76960, "loss": 0.0263, "lr": 6.923941427149277e-07, "epoch": 18.64864864864865, "percentage": 93.24, "elapsed_time": "1:44:12", "remaining_time": "0:07:33", "throughput": 1033.42, "total_tokens": 6461840} {"current_steps": 71765, "total_steps": 76960, "loss": 0.2628, "lr": 6.910696760304646e-07, "epoch": 18.649948024948024, "percentage": 93.25, "elapsed_time": "1:44:13", "remaining_time": "0:07:32", "throughput": 1033.42, "total_tokens": 6462320} {"current_steps": 71770, "total_steps": 76960, "loss": 0.039, "lr": 6.897464595775782e-07, "epoch": 18.651247401247403, "percentage": 93.26, "elapsed_time": "1:44:13", "remaining_time": "0:07:32", "throughput": 1033.43, "total_tokens": 6462800} {"current_steps": 71775, "total_steps": 76960, "loss": 0.0508, "lr": 6.884244934243305e-07, "epoch": 18.652546777546778, "percentage": 93.26, "elapsed_time": "1:44:14", "remaining_time": "0:07:31", "throughput": 1033.44, "total_tokens": 6463264} {"current_steps": 71780, "total_steps": 76960, "loss": 0.1549, "lr": 6.871037776387007e-07, "epoch": 18.653846153846153, "percentage": 93.27, "elapsed_time": "1:44:14", "remaining_time": "0:07:31", "throughput": 1033.44, "total_tokens": 6463696} {"current_steps": 71785, "total_steps": 76960, "loss": 0.0265, "lr": 6.857843122886204e-07, "epoch": 18.65514553014553, "percentage": 93.28, "elapsed_time": "1:44:14", "remaining_time": "0:07:30", "throughput": 1033.43, "total_tokens": 6464096} {"current_steps": 71790, "total_steps": 76960, "loss": 0.2373, "lr": 6.844660974419492e-07, "epoch": 18.656444906444907, "percentage": 93.28, "elapsed_time": "1:44:15", "remaining_time": "0:07:30", "throughput": 1033.43, "total_tokens": 6464528} {"current_steps": 71795, "total_steps": 76960, "loss": 0.0443, "lr": 6.831491331664858e-07, "epoch": 18.657744282744282, "percentage": 93.29, "elapsed_time": "1:44:15", "remaining_time": "0:07:30", "throughput": 1033.43, "total_tokens": 6464944} {"current_steps": 71800, "total_steps": 76960, "loss": 0.0903, "lr": 6.818334195299592e-07, "epoch": 18.659043659043657, "percentage": 93.3, "elapsed_time": "1:44:16", "remaining_time": "0:07:29", "throughput": 1033.43, "total_tokens": 6465376} {"current_steps": 71805, "total_steps": 76960, "loss": 0.0005, "lr": 6.80518956600043e-07, "epoch": 18.660343035343036, "percentage": 93.3, "elapsed_time": "1:44:16", "remaining_time": "0:07:29", "throughput": 1033.43, "total_tokens": 6465792} {"current_steps": 71810, "total_steps": 76960, "loss": 0.1268, "lr": 6.79205744444339e-07, "epoch": 18.66164241164241, "percentage": 93.31, "elapsed_time": "1:44:17", "remaining_time": "0:07:28", "throughput": 1033.43, "total_tokens": 6466240} {"current_steps": 71815, "total_steps": 76960, "loss": 0.0085, "lr": 6.778937831303844e-07, "epoch": 18.662941787941786, "percentage": 93.31, "elapsed_time": "1:44:17", "remaining_time": "0:07:28", "throughput": 1033.43, "total_tokens": 6466672} {"current_steps": 71820, "total_steps": 76960, "loss": 0.0005, "lr": 6.765830727256589e-07, "epoch": 18.664241164241165, "percentage": 93.32, "elapsed_time": "1:44:17", "remaining_time": "0:07:27", "throughput": 1033.44, "total_tokens": 6467136} {"current_steps": 71825, "total_steps": 76960, "loss": 0.0029, "lr": 6.752736132975696e-07, "epoch": 18.66554054054054, "percentage": 93.33, "elapsed_time": "1:44:18", "remaining_time": "0:07:27", "throughput": 1033.45, "total_tokens": 6467632} {"current_steps": 71830, "total_steps": 76960, "loss": 0.0122, "lr": 6.739654049134681e-07, "epoch": 18.666839916839916, "percentage": 93.33, "elapsed_time": "1:44:18", "remaining_time": "0:07:26", "throughput": 1033.46, "total_tokens": 6468128} {"current_steps": 71835, "total_steps": 76960, "loss": 0.2502, "lr": 6.726584476406311e-07, "epoch": 18.668139293139294, "percentage": 93.34, "elapsed_time": "1:44:19", "remaining_time": "0:07:26", "throughput": 1033.46, "total_tokens": 6468560} {"current_steps": 71840, "total_steps": 76960, "loss": 0.098, "lr": 6.713527415462772e-07, "epoch": 18.66943866943867, "percentage": 93.35, "elapsed_time": "1:44:19", "remaining_time": "0:07:26", "throughput": 1033.46, "total_tokens": 6469024} {"current_steps": 71845, "total_steps": 76960, "loss": 0.4641, "lr": 6.700482866975665e-07, "epoch": 18.670738045738045, "percentage": 93.35, "elapsed_time": "1:44:19", "remaining_time": "0:07:25", "throughput": 1033.46, "total_tokens": 6469440} {"current_steps": 71850, "total_steps": 76960, "loss": 0.4313, "lr": 6.687450831615844e-07, "epoch": 18.672037422037423, "percentage": 93.36, "elapsed_time": "1:44:20", "remaining_time": "0:07:25", "throughput": 1033.47, "total_tokens": 6469936} {"current_steps": 71855, "total_steps": 76960, "loss": 0.2124, "lr": 6.674431310053519e-07, "epoch": 18.6733367983368, "percentage": 93.37, "elapsed_time": "1:44:20", "remaining_time": "0:07:24", "throughput": 1033.47, "total_tokens": 6470384} {"current_steps": 71860, "total_steps": 76960, "loss": 0.2059, "lr": 6.66142430295838e-07, "epoch": 18.674636174636174, "percentage": 93.37, "elapsed_time": "1:44:21", "remaining_time": "0:07:24", "throughput": 1033.48, "total_tokens": 6470848} {"current_steps": 71865, "total_steps": 76960, "loss": 0.0055, "lr": 6.648429810999335e-07, "epoch": 18.675935550935552, "percentage": 93.38, "elapsed_time": "1:44:21", "remaining_time": "0:07:23", "throughput": 1033.49, "total_tokens": 6471344} {"current_steps": 71870, "total_steps": 76960, "loss": 0.0101, "lr": 6.63544783484471e-07, "epoch": 18.677234927234927, "percentage": 93.39, "elapsed_time": "1:44:22", "remaining_time": "0:07:23", "throughput": 1033.49, "total_tokens": 6471792} {"current_steps": 71875, "total_steps": 76960, "loss": 0.0222, "lr": 6.622478375162167e-07, "epoch": 18.678534303534303, "percentage": 93.39, "elapsed_time": "1:44:22", "remaining_time": "0:07:23", "throughput": 1033.49, "total_tokens": 6472240} {"current_steps": 71880, "total_steps": 76960, "loss": 0.0282, "lr": 6.609521432618754e-07, "epoch": 18.67983367983368, "percentage": 93.4, "elapsed_time": "1:44:22", "remaining_time": "0:07:22", "throughput": 1033.49, "total_tokens": 6472672} {"current_steps": 71885, "total_steps": 76960, "loss": 0.0008, "lr": 6.596577007880883e-07, "epoch": 18.681133056133056, "percentage": 93.41, "elapsed_time": "1:44:23", "remaining_time": "0:07:22", "throughput": 1033.49, "total_tokens": 6473104} {"current_steps": 71890, "total_steps": 76960, "loss": 0.0241, "lr": 6.583645101614271e-07, "epoch": 18.68243243243243, "percentage": 93.41, "elapsed_time": "1:44:23", "remaining_time": "0:07:21", "throughput": 1033.49, "total_tokens": 6473520} {"current_steps": 71895, "total_steps": 76960, "loss": 0.0029, "lr": 6.570725714484028e-07, "epoch": 18.68373180873181, "percentage": 93.42, "elapsed_time": "1:44:24", "remaining_time": "0:07:21", "throughput": 1033.5, "total_tokens": 6473984} {"current_steps": 71900, "total_steps": 76960, "loss": 0.2104, "lr": 6.557818847154562e-07, "epoch": 18.685031185031185, "percentage": 93.43, "elapsed_time": "1:44:24", "remaining_time": "0:07:20", "throughput": 1033.5, "total_tokens": 6474448} {"current_steps": 71905, "total_steps": 76960, "loss": 0.0016, "lr": 6.54492450028979e-07, "epoch": 18.68633056133056, "percentage": 93.43, "elapsed_time": "1:44:24", "remaining_time": "0:07:20", "throughput": 1033.51, "total_tokens": 6474912} {"current_steps": 71910, "total_steps": 76960, "loss": 0.0118, "lr": 6.532042674552763e-07, "epoch": 18.68762993762994, "percentage": 93.44, "elapsed_time": "1:44:25", "remaining_time": "0:07:19", "throughput": 1033.51, "total_tokens": 6475328} {"current_steps": 71915, "total_steps": 76960, "loss": 0.0103, "lr": 6.519173370606063e-07, "epoch": 18.688929313929314, "percentage": 93.44, "elapsed_time": "1:44:25", "remaining_time": "0:07:19", "throughput": 1033.5, "total_tokens": 6475744} {"current_steps": 71920, "total_steps": 76960, "loss": 0.1785, "lr": 6.506316589111577e-07, "epoch": 18.69022869022869, "percentage": 93.45, "elapsed_time": "1:44:26", "remaining_time": "0:07:19", "throughput": 1033.51, "total_tokens": 6476224} {"current_steps": 71925, "total_steps": 76960, "loss": 0.0053, "lr": 6.493472330730554e-07, "epoch": 18.691528066528065, "percentage": 93.46, "elapsed_time": "1:44:26", "remaining_time": "0:07:18", "throughput": 1033.52, "total_tokens": 6476688} {"current_steps": 71930, "total_steps": 76960, "loss": 0.0004, "lr": 6.480640596123549e-07, "epoch": 18.692827442827443, "percentage": 93.46, "elapsed_time": "1:44:27", "remaining_time": "0:07:18", "throughput": 1033.52, "total_tokens": 6477152} {"current_steps": 71935, "total_steps": 76960, "loss": 0.5071, "lr": 6.467821385950562e-07, "epoch": 18.69412681912682, "percentage": 93.47, "elapsed_time": "1:44:27", "remaining_time": "0:07:17", "throughput": 1033.52, "total_tokens": 6477584} {"current_steps": 71940, "total_steps": 76960, "loss": 0.0004, "lr": 6.455014700870842e-07, "epoch": 18.695426195426194, "percentage": 93.48, "elapsed_time": "1:44:27", "remaining_time": "0:07:17", "throughput": 1033.52, "total_tokens": 6478000} {"current_steps": 71945, "total_steps": 76960, "loss": 0.0656, "lr": 6.442220541543031e-07, "epoch": 18.696725571725572, "percentage": 93.48, "elapsed_time": "1:44:28", "remaining_time": "0:07:16", "throughput": 1033.52, "total_tokens": 6478432} {"current_steps": 71950, "total_steps": 76960, "loss": 0.3071, "lr": 6.429438908625213e-07, "epoch": 18.698024948024948, "percentage": 93.49, "elapsed_time": "1:44:28", "remaining_time": "0:07:16", "throughput": 1033.53, "total_tokens": 6478896} {"current_steps": 71955, "total_steps": 76960, "loss": 0.1132, "lr": 6.416669802774722e-07, "epoch": 18.699324324324323, "percentage": 93.5, "elapsed_time": "1:44:29", "remaining_time": "0:07:16", "throughput": 1033.53, "total_tokens": 6479328} {"current_steps": 71960, "total_steps": 76960, "loss": 0.0291, "lr": 6.403913224648312e-07, "epoch": 18.7006237006237, "percentage": 93.5, "elapsed_time": "1:44:29", "remaining_time": "0:07:15", "throughput": 1033.53, "total_tokens": 6479776} {"current_steps": 71965, "total_steps": 76960, "loss": 0.2696, "lr": 6.39116917490204e-07, "epoch": 18.701923076923077, "percentage": 93.51, "elapsed_time": "1:44:29", "remaining_time": "0:07:15", "throughput": 1033.53, "total_tokens": 6480192} {"current_steps": 71970, "total_steps": 76960, "loss": 0.2079, "lr": 6.378437654191355e-07, "epoch": 18.703222453222452, "percentage": 93.52, "elapsed_time": "1:44:30", "remaining_time": "0:07:14", "throughput": 1033.53, "total_tokens": 6480640} {"current_steps": 71975, "total_steps": 76960, "loss": 0.1977, "lr": 6.365718663171038e-07, "epoch": 18.70452182952183, "percentage": 93.52, "elapsed_time": "1:44:30", "remaining_time": "0:07:14", "throughput": 1033.53, "total_tokens": 6481072} {"current_steps": 71980, "total_steps": 76960, "loss": 0.3157, "lr": 6.353012202495235e-07, "epoch": 18.705821205821206, "percentage": 93.53, "elapsed_time": "1:44:31", "remaining_time": "0:07:13", "throughput": 1033.53, "total_tokens": 6481504} {"current_steps": 71985, "total_steps": 76960, "loss": 0.0025, "lr": 6.340318272817474e-07, "epoch": 18.70712058212058, "percentage": 93.54, "elapsed_time": "1:44:31", "remaining_time": "0:07:13", "throughput": 1033.53, "total_tokens": 6481952} {"current_steps": 71990, "total_steps": 76960, "loss": 0.0007, "lr": 6.327636874790654e-07, "epoch": 18.70841995841996, "percentage": 93.54, "elapsed_time": "1:44:32", "remaining_time": "0:07:13", "throughput": 1033.53, "total_tokens": 6482400} {"current_steps": 71995, "total_steps": 76960, "loss": 0.0017, "lr": 6.314968009066891e-07, "epoch": 18.709719334719335, "percentage": 93.55, "elapsed_time": "1:44:32", "remaining_time": "0:07:12", "throughput": 1033.53, "total_tokens": 6482832} {"current_steps": 72000, "total_steps": 76960, "loss": 0.0868, "lr": 6.302311676297829e-07, "epoch": 18.71101871101871, "percentage": 93.56, "elapsed_time": "1:44:32", "remaining_time": "0:07:12", "throughput": 1033.54, "total_tokens": 6483312} {"current_steps": 72005, "total_steps": 76960, "loss": 0.0017, "lr": 6.289667877134392e-07, "epoch": 18.71231808731809, "percentage": 93.56, "elapsed_time": "1:44:33", "remaining_time": "0:07:11", "throughput": 1033.54, "total_tokens": 6483760} {"current_steps": 72010, "total_steps": 76960, "loss": 0.1852, "lr": 6.277036612226839e-07, "epoch": 18.713617463617464, "percentage": 93.57, "elapsed_time": "1:44:33", "remaining_time": "0:07:11", "throughput": 1033.54, "total_tokens": 6484160} {"current_steps": 72015, "total_steps": 76960, "loss": 0.0633, "lr": 6.264417882224788e-07, "epoch": 18.71491683991684, "percentage": 93.57, "elapsed_time": "1:44:34", "remaining_time": "0:07:10", "throughput": 1033.54, "total_tokens": 6484592} {"current_steps": 72020, "total_steps": 76960, "loss": 0.1232, "lr": 6.251811687777276e-07, "epoch": 18.716216216216218, "percentage": 93.58, "elapsed_time": "1:44:34", "remaining_time": "0:07:10", "throughput": 1033.53, "total_tokens": 6484992} {"current_steps": 72025, "total_steps": 76960, "loss": 0.0123, "lr": 6.239218029532673e-07, "epoch": 18.717515592515593, "percentage": 93.59, "elapsed_time": "1:44:34", "remaining_time": "0:07:09", "throughput": 1033.54, "total_tokens": 6485440} {"current_steps": 72030, "total_steps": 76960, "loss": 0.0004, "lr": 6.2266369081386e-07, "epoch": 18.718814968814968, "percentage": 93.59, "elapsed_time": "1:44:35", "remaining_time": "0:07:09", "throughput": 1033.55, "total_tokens": 6485920} {"current_steps": 72035, "total_steps": 76960, "loss": 0.0173, "lr": 6.214068324242206e-07, "epoch": 18.720114345114347, "percentage": 93.6, "elapsed_time": "1:44:35", "remaining_time": "0:07:09", "throughput": 1033.56, "total_tokens": 6486416} {"current_steps": 72040, "total_steps": 76960, "loss": 0.0076, "lr": 6.201512278489835e-07, "epoch": 18.72141372141372, "percentage": 93.61, "elapsed_time": "1:44:36", "remaining_time": "0:07:08", "throughput": 1033.56, "total_tokens": 6486864} {"current_steps": 72045, "total_steps": 76960, "loss": 0.0215, "lr": 6.188968771527303e-07, "epoch": 18.722713097713097, "percentage": 93.61, "elapsed_time": "1:44:36", "remaining_time": "0:07:08", "throughput": 1033.57, "total_tokens": 6487344} {"current_steps": 72050, "total_steps": 76960, "loss": 0.0159, "lr": 6.176437803999679e-07, "epoch": 18.724012474012476, "percentage": 93.62, "elapsed_time": "1:44:37", "remaining_time": "0:07:07", "throughput": 1033.56, "total_tokens": 6487760} {"current_steps": 72055, "total_steps": 76960, "loss": 0.0016, "lr": 6.163919376551502e-07, "epoch": 18.72531185031185, "percentage": 93.63, "elapsed_time": "1:44:37", "remaining_time": "0:07:07", "throughput": 1033.57, "total_tokens": 6488208} {"current_steps": 72060, "total_steps": 76960, "loss": 0.003, "lr": 6.151413489826563e-07, "epoch": 18.726611226611226, "percentage": 93.63, "elapsed_time": "1:44:37", "remaining_time": "0:07:06", "throughput": 1033.57, "total_tokens": 6488656} {"current_steps": 72065, "total_steps": 76960, "loss": 0.0062, "lr": 6.138920144468124e-07, "epoch": 18.727910602910605, "percentage": 93.64, "elapsed_time": "1:44:38", "remaining_time": "0:07:06", "throughput": 1033.58, "total_tokens": 6489152} {"current_steps": 72070, "total_steps": 76960, "loss": 0.0003, "lr": 6.126439341118645e-07, "epoch": 18.72920997920998, "percentage": 93.65, "elapsed_time": "1:44:38", "remaining_time": "0:07:06", "throughput": 1033.58, "total_tokens": 6489584} {"current_steps": 72075, "total_steps": 76960, "loss": 0.061, "lr": 6.113971080420056e-07, "epoch": 18.730509355509355, "percentage": 93.65, "elapsed_time": "1:44:39", "remaining_time": "0:07:05", "throughput": 1033.58, "total_tokens": 6490016} {"current_steps": 72080, "total_steps": 76960, "loss": 0.001, "lr": 6.101515363013649e-07, "epoch": 18.731808731808734, "percentage": 93.66, "elapsed_time": "1:44:39", "remaining_time": "0:07:05", "throughput": 1033.58, "total_tokens": 6490448} {"current_steps": 72085, "total_steps": 76960, "loss": 0.0029, "lr": 6.089072189539968e-07, "epoch": 18.73310810810811, "percentage": 93.67, "elapsed_time": "1:44:39", "remaining_time": "0:07:04", "throughput": 1033.58, "total_tokens": 6490880} {"current_steps": 72090, "total_steps": 76960, "loss": 0.0859, "lr": 6.076641560639002e-07, "epoch": 18.734407484407484, "percentage": 93.67, "elapsed_time": "1:44:40", "remaining_time": "0:07:04", "throughput": 1033.59, "total_tokens": 6491344} {"current_steps": 72095, "total_steps": 76960, "loss": 0.4382, "lr": 6.06422347695007e-07, "epoch": 18.73570686070686, "percentage": 93.68, "elapsed_time": "1:44:40", "remaining_time": "0:07:03", "throughput": 1033.59, "total_tokens": 6491808} {"current_steps": 72100, "total_steps": 76960, "loss": 0.0777, "lr": 6.051817939111887e-07, "epoch": 18.737006237006238, "percentage": 93.69, "elapsed_time": "1:44:41", "remaining_time": "0:07:03", "throughput": 1033.59, "total_tokens": 6492240} {"current_steps": 72105, "total_steps": 76960, "loss": 0.0087, "lr": 6.039424947762413e-07, "epoch": 18.738305613305613, "percentage": 93.69, "elapsed_time": "1:44:41", "remaining_time": "0:07:02", "throughput": 1033.59, "total_tokens": 6492656} {"current_steps": 72110, "total_steps": 76960, "loss": 0.0023, "lr": 6.027044503539081e-07, "epoch": 18.739604989604988, "percentage": 93.7, "elapsed_time": "1:44:42", "remaining_time": "0:07:02", "throughput": 1033.59, "total_tokens": 6493088} {"current_steps": 72115, "total_steps": 76960, "loss": 0.049, "lr": 6.014676607078607e-07, "epoch": 18.740904365904367, "percentage": 93.7, "elapsed_time": "1:44:42", "remaining_time": "0:07:02", "throughput": 1033.6, "total_tokens": 6493552} {"current_steps": 72120, "total_steps": 76960, "loss": 0.0007, "lr": 6.002321259017118e-07, "epoch": 18.742203742203742, "percentage": 93.71, "elapsed_time": "1:44:42", "remaining_time": "0:07:01", "throughput": 1033.59, "total_tokens": 6493968} {"current_steps": 72125, "total_steps": 76960, "loss": 0.1537, "lr": 5.989978459989998e-07, "epoch": 18.743503118503117, "percentage": 93.72, "elapsed_time": "1:44:43", "remaining_time": "0:07:01", "throughput": 1033.6, "total_tokens": 6494416} {"current_steps": 72130, "total_steps": 76960, "loss": 0.0003, "lr": 5.977648210632097e-07, "epoch": 18.744802494802496, "percentage": 93.72, "elapsed_time": "1:44:43", "remaining_time": "0:07:00", "throughput": 1033.6, "total_tokens": 6494880} {"current_steps": 72135, "total_steps": 76960, "loss": 0.0534, "lr": 5.96533051157755e-07, "epoch": 18.74610187110187, "percentage": 93.73, "elapsed_time": "1:44:44", "remaining_time": "0:07:00", "throughput": 1033.61, "total_tokens": 6495360} {"current_steps": 72140, "total_steps": 76960, "loss": 0.4511, "lr": 5.953025363459902e-07, "epoch": 18.747401247401246, "percentage": 93.74, "elapsed_time": "1:44:44", "remaining_time": "0:06:59", "throughput": 1033.62, "total_tokens": 6495824} {"current_steps": 72145, "total_steps": 76960, "loss": 0.0162, "lr": 5.94073276691201e-07, "epoch": 18.748700623700625, "percentage": 93.74, "elapsed_time": "1:44:44", "remaining_time": "0:06:59", "throughput": 1033.62, "total_tokens": 6496272} {"current_steps": 72150, "total_steps": 76960, "loss": 0.0677, "lr": 5.928452722566036e-07, "epoch": 18.75, "percentage": 93.75, "elapsed_time": "1:44:45", "remaining_time": "0:06:59", "throughput": 1033.62, "total_tokens": 6496688} {"current_steps": 72155, "total_steps": 76960, "loss": 0.01, "lr": 5.916185231053611e-07, "epoch": 18.751299376299375, "percentage": 93.76, "elapsed_time": "1:44:45", "remaining_time": "0:06:58", "throughput": 1033.62, "total_tokens": 6497136} {"current_steps": 72160, "total_steps": 76960, "loss": 0.1674, "lr": 5.90393029300565e-07, "epoch": 18.752598752598754, "percentage": 93.76, "elapsed_time": "1:44:46", "remaining_time": "0:06:58", "throughput": 1033.62, "total_tokens": 6497552} {"current_steps": 72165, "total_steps": 76960, "loss": 0.0131, "lr": 5.891687909052423e-07, "epoch": 18.75389812889813, "percentage": 93.77, "elapsed_time": "1:44:46", "remaining_time": "0:06:57", "throughput": 1033.62, "total_tokens": 6498000} {"current_steps": 72170, "total_steps": 76960, "loss": 0.0007, "lr": 5.879458079823596e-07, "epoch": 18.755197505197504, "percentage": 93.78, "elapsed_time": "1:44:47", "remaining_time": "0:06:57", "throughput": 1033.62, "total_tokens": 6498464} {"current_steps": 72175, "total_steps": 76960, "loss": 0.0991, "lr": 5.867240805948138e-07, "epoch": 18.756496881496883, "percentage": 93.78, "elapsed_time": "1:44:47", "remaining_time": "0:06:56", "throughput": 1033.63, "total_tokens": 6498944} {"current_steps": 72180, "total_steps": 76960, "loss": 0.0163, "lr": 5.855036088054406e-07, "epoch": 18.757796257796258, "percentage": 93.79, "elapsed_time": "1:44:47", "remaining_time": "0:06:56", "throughput": 1033.63, "total_tokens": 6499376} {"current_steps": 72185, "total_steps": 76960, "loss": 0.159, "lr": 5.842843926770119e-07, "epoch": 18.759095634095633, "percentage": 93.8, "elapsed_time": "1:44:48", "remaining_time": "0:06:55", "throughput": 1033.63, "total_tokens": 6499808} {"current_steps": 72190, "total_steps": 76960, "loss": 0.5801, "lr": 5.830664322722279e-07, "epoch": 18.760395010395012, "percentage": 93.8, "elapsed_time": "1:44:48", "remaining_time": "0:06:55", "throughput": 1033.63, "total_tokens": 6500240} {"current_steps": 72195, "total_steps": 76960, "loss": 0.0012, "lr": 5.818497276537299e-07, "epoch": 18.761694386694387, "percentage": 93.81, "elapsed_time": "1:44:49", "remaining_time": "0:06:55", "throughput": 1033.64, "total_tokens": 6500704} {"current_steps": 72200, "total_steps": 76960, "loss": 0.2013, "lr": 5.806342788841013e-07, "epoch": 18.762993762993762, "percentage": 93.81, "elapsed_time": "1:44:49", "remaining_time": "0:06:54", "throughput": 1033.64, "total_tokens": 6501136} {"current_steps": 72205, "total_steps": 76960, "loss": 0.4763, "lr": 5.794200860258476e-07, "epoch": 18.76429313929314, "percentage": 93.82, "elapsed_time": "1:44:49", "remaining_time": "0:06:54", "throughput": 1033.64, "total_tokens": 6501584} {"current_steps": 72210, "total_steps": 76960, "loss": 0.0424, "lr": 5.782071491414187e-07, "epoch": 18.765592515592516, "percentage": 93.83, "elapsed_time": "1:44:50", "remaining_time": "0:06:53", "throughput": 1033.65, "total_tokens": 6502048} {"current_steps": 72215, "total_steps": 76960, "loss": 0.0014, "lr": 5.769954682931955e-07, "epoch": 18.76689189189189, "percentage": 93.83, "elapsed_time": "1:44:50", "remaining_time": "0:06:53", "throughput": 1033.64, "total_tokens": 6502464} {"current_steps": 72220, "total_steps": 76960, "loss": 0.0006, "lr": 5.757850435434975e-07, "epoch": 18.768191268191266, "percentage": 93.84, "elapsed_time": "1:44:51", "remaining_time": "0:06:52", "throughput": 1033.65, "total_tokens": 6502928} {"current_steps": 72225, "total_steps": 76960, "loss": 0.0017, "lr": 5.745758749545749e-07, "epoch": 18.769490644490645, "percentage": 93.85, "elapsed_time": "1:44:51", "remaining_time": "0:06:52", "throughput": 1033.66, "total_tokens": 6503440} {"current_steps": 72230, "total_steps": 76960, "loss": 0.0124, "lr": 5.733679625886168e-07, "epoch": 18.77079002079002, "percentage": 93.85, "elapsed_time": "1:44:52", "remaining_time": "0:06:52", "throughput": 1033.66, "total_tokens": 6503872} {"current_steps": 72235, "total_steps": 76960, "loss": 0.1943, "lr": 5.721613065077514e-07, "epoch": 18.772089397089395, "percentage": 93.86, "elapsed_time": "1:44:52", "remaining_time": "0:06:51", "throughput": 1033.66, "total_tokens": 6504288} {"current_steps": 72240, "total_steps": 76960, "loss": 0.1499, "lr": 5.709559067740344e-07, "epoch": 18.773388773388774, "percentage": 93.87, "elapsed_time": "1:44:52", "remaining_time": "0:06:51", "throughput": 1033.66, "total_tokens": 6504720} {"current_steps": 72245, "total_steps": 76960, "loss": 0.0801, "lr": 5.697517634494637e-07, "epoch": 18.77468814968815, "percentage": 93.87, "elapsed_time": "1:44:53", "remaining_time": "0:06:50", "throughput": 1033.66, "total_tokens": 6505168} {"current_steps": 72250, "total_steps": 76960, "loss": 0.0366, "lr": 5.685488765959673e-07, "epoch": 18.775987525987524, "percentage": 93.88, "elapsed_time": "1:44:53", "remaining_time": "0:06:50", "throughput": 1033.67, "total_tokens": 6505616} {"current_steps": 72255, "total_steps": 76960, "loss": 0.0314, "lr": 5.673472462754098e-07, "epoch": 18.777286902286903, "percentage": 93.89, "elapsed_time": "1:44:54", "remaining_time": "0:06:49", "throughput": 1033.67, "total_tokens": 6506064} {"current_steps": 72260, "total_steps": 76960, "loss": 0.0465, "lr": 5.661468725495944e-07, "epoch": 18.77858627858628, "percentage": 93.89, "elapsed_time": "1:44:54", "remaining_time": "0:06:49", "throughput": 1033.67, "total_tokens": 6506512} {"current_steps": 72265, "total_steps": 76960, "loss": 0.165, "lr": 5.649477554802579e-07, "epoch": 18.779885654885653, "percentage": 93.9, "elapsed_time": "1:44:54", "remaining_time": "0:06:48", "throughput": 1033.67, "total_tokens": 6506944} {"current_steps": 72270, "total_steps": 76960, "loss": 0.0905, "lr": 5.637498951290676e-07, "epoch": 18.781185031185032, "percentage": 93.91, "elapsed_time": "1:44:55", "remaining_time": "0:06:48", "throughput": 1033.68, "total_tokens": 6507440} {"current_steps": 72275, "total_steps": 76960, "loss": 0.0011, "lr": 5.625532915576381e-07, "epoch": 18.782484407484407, "percentage": 93.91, "elapsed_time": "1:44:55", "remaining_time": "0:06:48", "throughput": 1033.68, "total_tokens": 6507872} {"current_steps": 72280, "total_steps": 76960, "loss": 0.1754, "lr": 5.613579448275036e-07, "epoch": 18.783783783783782, "percentage": 93.92, "elapsed_time": "1:44:56", "remaining_time": "0:06:47", "throughput": 1033.69, "total_tokens": 6508352} {"current_steps": 72285, "total_steps": 76960, "loss": 0.236, "lr": 5.601638550001509e-07, "epoch": 18.78508316008316, "percentage": 93.93, "elapsed_time": "1:44:56", "remaining_time": "0:06:47", "throughput": 1033.69, "total_tokens": 6508800} {"current_steps": 72290, "total_steps": 76960, "loss": 0.1829, "lr": 5.589710221369837e-07, "epoch": 18.786382536382536, "percentage": 93.93, "elapsed_time": "1:44:57", "remaining_time": "0:06:46", "throughput": 1033.7, "total_tokens": 6509280} {"current_steps": 72295, "total_steps": 76960, "loss": 0.0494, "lr": 5.577794462993586e-07, "epoch": 18.78768191268191, "percentage": 93.94, "elapsed_time": "1:44:57", "remaining_time": "0:06:46", "throughput": 1033.71, "total_tokens": 6509744} {"current_steps": 72300, "total_steps": 76960, "loss": 0.1505, "lr": 5.56589127548554e-07, "epoch": 18.78898128898129, "percentage": 93.94, "elapsed_time": "1:44:57", "remaining_time": "0:06:45", "throughput": 1033.71, "total_tokens": 6510176} {"current_steps": 72305, "total_steps": 76960, "loss": 0.0011, "lr": 5.554000659457881e-07, "epoch": 18.790280665280665, "percentage": 93.95, "elapsed_time": "1:44:58", "remaining_time": "0:06:45", "throughput": 1033.71, "total_tokens": 6510640} {"current_steps": 72310, "total_steps": 76960, "loss": 0.1593, "lr": 5.542122615522227e-07, "epoch": 18.79158004158004, "percentage": 93.96, "elapsed_time": "1:44:58", "remaining_time": "0:06:45", "throughput": 1033.72, "total_tokens": 6511120} {"current_steps": 72315, "total_steps": 76960, "loss": 0.0149, "lr": 5.530257144289425e-07, "epoch": 18.79287941787942, "percentage": 93.96, "elapsed_time": "1:44:59", "remaining_time": "0:06:44", "throughput": 1033.72, "total_tokens": 6511568} {"current_steps": 72320, "total_steps": 76960, "loss": 0.0008, "lr": 5.518404246369735e-07, "epoch": 18.794178794178794, "percentage": 93.97, "elapsed_time": "1:44:59", "remaining_time": "0:06:44", "throughput": 1033.72, "total_tokens": 6512000} {"current_steps": 72325, "total_steps": 76960, "loss": 0.1892, "lr": 5.506563922372781e-07, "epoch": 18.79547817047817, "percentage": 93.98, "elapsed_time": "1:44:59", "remaining_time": "0:06:43", "throughput": 1033.73, "total_tokens": 6512448} {"current_steps": 72330, "total_steps": 76960, "loss": 0.0517, "lr": 5.494736172907495e-07, "epoch": 18.796777546777548, "percentage": 93.98, "elapsed_time": "1:45:00", "remaining_time": "0:06:43", "throughput": 1033.73, "total_tokens": 6512928} {"current_steps": 72335, "total_steps": 76960, "loss": 0.0016, "lr": 5.482920998582191e-07, "epoch": 18.798076923076923, "percentage": 93.99, "elapsed_time": "1:45:00", "remaining_time": "0:06:42", "throughput": 1033.74, "total_tokens": 6513376} {"current_steps": 72340, "total_steps": 76960, "loss": 0.0003, "lr": 5.471118400004555e-07, "epoch": 18.7993762993763, "percentage": 94.0, "elapsed_time": "1:45:01", "remaining_time": "0:06:42", "throughput": 1033.74, "total_tokens": 6513840} {"current_steps": 72345, "total_steps": 76960, "loss": 0.0246, "lr": 5.459328377781598e-07, "epoch": 18.800675675675677, "percentage": 94.0, "elapsed_time": "1:45:01", "remaining_time": "0:06:41", "throughput": 1033.75, "total_tokens": 6514288} {"current_steps": 72350, "total_steps": 76960, "loss": 0.0313, "lr": 5.447550932519696e-07, "epoch": 18.801975051975052, "percentage": 94.01, "elapsed_time": "1:45:02", "remaining_time": "0:06:41", "throughput": 1033.74, "total_tokens": 6514704} {"current_steps": 72355, "total_steps": 76960, "loss": 0.0008, "lr": 5.435786064824533e-07, "epoch": 18.803274428274428, "percentage": 94.02, "elapsed_time": "1:45:02", "remaining_time": "0:06:41", "throughput": 1033.75, "total_tokens": 6515184} {"current_steps": 72360, "total_steps": 76960, "loss": 0.0005, "lr": 5.424033775301262e-07, "epoch": 18.804573804573806, "percentage": 94.02, "elapsed_time": "1:45:02", "remaining_time": "0:06:40", "throughput": 1033.75, "total_tokens": 6515632} {"current_steps": 72365, "total_steps": 76960, "loss": 0.0373, "lr": 5.412294064554263e-07, "epoch": 18.80587318087318, "percentage": 94.03, "elapsed_time": "1:45:03", "remaining_time": "0:06:40", "throughput": 1033.76, "total_tokens": 6516080} {"current_steps": 72370, "total_steps": 76960, "loss": 0.0019, "lr": 5.400566933187357e-07, "epoch": 18.807172557172557, "percentage": 94.04, "elapsed_time": "1:45:03", "remaining_time": "0:06:39", "throughput": 1033.76, "total_tokens": 6516528} {"current_steps": 72375, "total_steps": 76960, "loss": 0.0027, "lr": 5.388852381803617e-07, "epoch": 18.808471933471935, "percentage": 94.04, "elapsed_time": "1:45:04", "remaining_time": "0:06:39", "throughput": 1033.76, "total_tokens": 6516960} {"current_steps": 72380, "total_steps": 76960, "loss": 0.4942, "lr": 5.377150411005588e-07, "epoch": 18.80977130977131, "percentage": 94.05, "elapsed_time": "1:45:04", "remaining_time": "0:06:38", "throughput": 1033.76, "total_tokens": 6517408} {"current_steps": 72385, "total_steps": 76960, "loss": 0.0002, "lr": 5.365461021395096e-07, "epoch": 18.811070686070686, "percentage": 94.06, "elapsed_time": "1:45:04", "remaining_time": "0:06:38", "throughput": 1033.77, "total_tokens": 6517872} {"current_steps": 72390, "total_steps": 76960, "loss": 0.2195, "lr": 5.353784213573354e-07, "epoch": 18.81237006237006, "percentage": 94.06, "elapsed_time": "1:45:05", "remaining_time": "0:06:38", "throughput": 1033.77, "total_tokens": 6518320} {"current_steps": 72395, "total_steps": 76960, "loss": 0.2369, "lr": 5.342119988140881e-07, "epoch": 18.81366943866944, "percentage": 94.07, "elapsed_time": "1:45:05", "remaining_time": "0:06:37", "throughput": 1033.77, "total_tokens": 6518736} {"current_steps": 72400, "total_steps": 76960, "loss": 0.0138, "lr": 5.330468345697615e-07, "epoch": 18.814968814968815, "percentage": 94.07, "elapsed_time": "1:45:06", "remaining_time": "0:06:37", "throughput": 1033.78, "total_tokens": 6519216} {"current_steps": 72405, "total_steps": 76960, "loss": 0.0016, "lr": 5.318829286842796e-07, "epoch": 18.81626819126819, "percentage": 94.08, "elapsed_time": "1:45:06", "remaining_time": "0:06:36", "throughput": 1033.78, "total_tokens": 6519664} {"current_steps": 72410, "total_steps": 76960, "loss": 0.0004, "lr": 5.307202812175005e-07, "epoch": 18.81756756756757, "percentage": 94.09, "elapsed_time": "1:45:07", "remaining_time": "0:06:36", "throughput": 1033.78, "total_tokens": 6520112} {"current_steps": 72415, "total_steps": 76960, "loss": 0.5062, "lr": 5.295588922292233e-07, "epoch": 18.818866943866944, "percentage": 94.09, "elapsed_time": "1:45:07", "remaining_time": "0:06:35", "throughput": 1033.78, "total_tokens": 6520528} {"current_steps": 72420, "total_steps": 76960, "loss": 0.0188, "lr": 5.28398761779178e-07, "epoch": 18.82016632016632, "percentage": 94.1, "elapsed_time": "1:45:07", "remaining_time": "0:06:35", "throughput": 1033.78, "total_tokens": 6520976} {"current_steps": 72425, "total_steps": 76960, "loss": 0.0319, "lr": 5.272398899270364e-07, "epoch": 18.821465696465697, "percentage": 94.11, "elapsed_time": "1:45:08", "remaining_time": "0:06:35", "throughput": 1033.78, "total_tokens": 6521424} {"current_steps": 72430, "total_steps": 76960, "loss": 0.0767, "lr": 5.260822767323926e-07, "epoch": 18.822765072765073, "percentage": 94.11, "elapsed_time": "1:45:08", "remaining_time": "0:06:34", "throughput": 1033.79, "total_tokens": 6521872} {"current_steps": 72435, "total_steps": 76960, "loss": 0.6267, "lr": 5.249259222547876e-07, "epoch": 18.824064449064448, "percentage": 94.12, "elapsed_time": "1:45:09", "remaining_time": "0:06:34", "throughput": 1033.79, "total_tokens": 6522304} {"current_steps": 72440, "total_steps": 76960, "loss": 0.1858, "lr": 5.237708265536934e-07, "epoch": 18.825363825363826, "percentage": 94.13, "elapsed_time": "1:45:09", "remaining_time": "0:06:33", "throughput": 1033.79, "total_tokens": 6522736} {"current_steps": 72445, "total_steps": 76960, "loss": 0.2544, "lr": 5.226169896885153e-07, "epoch": 18.8266632016632, "percentage": 94.13, "elapsed_time": "1:45:09", "remaining_time": "0:06:33", "throughput": 1033.79, "total_tokens": 6523200} {"current_steps": 72450, "total_steps": 76960, "loss": 0.0821, "lr": 5.214644117186002e-07, "epoch": 18.827962577962577, "percentage": 94.14, "elapsed_time": "1:45:10", "remaining_time": "0:06:32", "throughput": 1033.8, "total_tokens": 6523648} {"current_steps": 72455, "total_steps": 76960, "loss": 0.0083, "lr": 5.203130927032257e-07, "epoch": 18.829261954261955, "percentage": 94.15, "elapsed_time": "1:45:10", "remaining_time": "0:06:32", "throughput": 1033.81, "total_tokens": 6524160} {"current_steps": 72460, "total_steps": 76960, "loss": 0.0145, "lr": 5.191630327016028e-07, "epoch": 18.83056133056133, "percentage": 94.15, "elapsed_time": "1:45:11", "remaining_time": "0:06:31", "throughput": 1033.81, "total_tokens": 6524592} {"current_steps": 72465, "total_steps": 76960, "loss": 0.0029, "lr": 5.180142317728815e-07, "epoch": 18.831860706860706, "percentage": 94.16, "elapsed_time": "1:45:11", "remaining_time": "0:06:31", "throughput": 1033.81, "total_tokens": 6525024} {"current_steps": 72470, "total_steps": 76960, "loss": 0.0135, "lr": 5.168666899761476e-07, "epoch": 18.833160083160084, "percentage": 94.17, "elapsed_time": "1:45:12", "remaining_time": "0:06:31", "throughput": 1033.82, "total_tokens": 6525504} {"current_steps": 72475, "total_steps": 76960, "loss": 0.1008, "lr": 5.15720407370418e-07, "epoch": 18.83445945945946, "percentage": 94.17, "elapsed_time": "1:45:12", "remaining_time": "0:06:30", "throughput": 1033.82, "total_tokens": 6525936} {"current_steps": 72480, "total_steps": 76960, "loss": 0.0021, "lr": 5.145753840146456e-07, "epoch": 18.835758835758835, "percentage": 94.18, "elapsed_time": "1:45:12", "remaining_time": "0:06:30", "throughput": 1033.83, "total_tokens": 6526416} {"current_steps": 72485, "total_steps": 76960, "loss": 0.0336, "lr": 5.13431619967722e-07, "epoch": 18.837058212058214, "percentage": 94.19, "elapsed_time": "1:45:13", "remaining_time": "0:06:29", "throughput": 1033.83, "total_tokens": 6526848} {"current_steps": 72490, "total_steps": 76960, "loss": 0.0005, "lr": 5.122891152884751e-07, "epoch": 18.83835758835759, "percentage": 94.19, "elapsed_time": "1:45:13", "remaining_time": "0:06:29", "throughput": 1033.83, "total_tokens": 6527312} {"current_steps": 72495, "total_steps": 76960, "loss": 0.0058, "lr": 5.111478700356582e-07, "epoch": 18.839656964656964, "percentage": 94.2, "elapsed_time": "1:45:14", "remaining_time": "0:06:28", "throughput": 1033.84, "total_tokens": 6527776} {"current_steps": 72500, "total_steps": 76960, "loss": 0.0028, "lr": 5.10007884267974e-07, "epoch": 18.840956340956343, "percentage": 94.2, "elapsed_time": "1:45:14", "remaining_time": "0:06:28", "throughput": 1033.84, "total_tokens": 6528240} {"current_steps": 72505, "total_steps": 76960, "loss": 0.024, "lr": 5.08869158044048e-07, "epoch": 18.842255717255718, "percentage": 94.21, "elapsed_time": "1:45:14", "remaining_time": "0:06:28", "throughput": 1033.85, "total_tokens": 6528688} {"current_steps": 72510, "total_steps": 76960, "loss": 0.0002, "lr": 5.077316914224472e-07, "epoch": 18.843555093555093, "percentage": 94.22, "elapsed_time": "1:45:15", "remaining_time": "0:06:27", "throughput": 1033.85, "total_tokens": 6529168} {"current_steps": 72515, "total_steps": 76960, "loss": 0.3366, "lr": 5.065954844616721e-07, "epoch": 18.84485446985447, "percentage": 94.22, "elapsed_time": "1:45:15", "remaining_time": "0:06:27", "throughput": 1033.86, "total_tokens": 6529616} {"current_steps": 72520, "total_steps": 76960, "loss": 0.0024, "lr": 5.054605372201593e-07, "epoch": 18.846153846153847, "percentage": 94.23, "elapsed_time": "1:45:16", "remaining_time": "0:06:26", "throughput": 1033.86, "total_tokens": 6530096} {"current_steps": 72525, "total_steps": 76960, "loss": 0.0152, "lr": 5.043268497562814e-07, "epoch": 18.847453222453222, "percentage": 94.24, "elapsed_time": "1:45:16", "remaining_time": "0:06:26", "throughput": 1033.87, "total_tokens": 6530544} {"current_steps": 72530, "total_steps": 76960, "loss": 0.0011, "lr": 5.031944221283474e-07, "epoch": 18.848752598752597, "percentage": 94.24, "elapsed_time": "1:45:17", "remaining_time": "0:06:25", "throughput": 1033.87, "total_tokens": 6530976} {"current_steps": 72535, "total_steps": 76960, "loss": 0.0019, "lr": 5.020632543945941e-07, "epoch": 18.850051975051976, "percentage": 94.25, "elapsed_time": "1:45:17", "remaining_time": "0:06:25", "throughput": 1033.87, "total_tokens": 6531424} {"current_steps": 72540, "total_steps": 76960, "loss": 0.0059, "lr": 5.009333466131971e-07, "epoch": 18.85135135135135, "percentage": 94.26, "elapsed_time": "1:45:17", "remaining_time": "0:06:24", "throughput": 1033.87, "total_tokens": 6531888} {"current_steps": 72545, "total_steps": 76960, "loss": 0.0001, "lr": 4.998046988422766e-07, "epoch": 18.852650727650726, "percentage": 94.26, "elapsed_time": "1:45:18", "remaining_time": "0:06:24", "throughput": 1033.88, "total_tokens": 6532336} {"current_steps": 72550, "total_steps": 76960, "loss": 0.3778, "lr": 4.986773111398724e-07, "epoch": 18.853950103950105, "percentage": 94.27, "elapsed_time": "1:45:18", "remaining_time": "0:06:24", "throughput": 1033.88, "total_tokens": 6532800} {"current_steps": 72555, "total_steps": 76960, "loss": 0.0002, "lr": 4.975511835639712e-07, "epoch": 18.85524948024948, "percentage": 94.28, "elapsed_time": "1:45:19", "remaining_time": "0:06:23", "throughput": 1033.88, "total_tokens": 6533232} {"current_steps": 72560, "total_steps": 76960, "loss": 0.0258, "lr": 4.964263161724881e-07, "epoch": 18.856548856548855, "percentage": 94.28, "elapsed_time": "1:45:19", "remaining_time": "0:06:23", "throughput": 1033.89, "total_tokens": 6533712} {"current_steps": 72565, "total_steps": 76960, "loss": 0.0005, "lr": 4.953027090232792e-07, "epoch": 18.857848232848234, "percentage": 94.29, "elapsed_time": "1:45:19", "remaining_time": "0:06:22", "throughput": 1033.89, "total_tokens": 6534160} {"current_steps": 72570, "total_steps": 76960, "loss": 0.1185, "lr": 4.94180362174132e-07, "epoch": 18.85914760914761, "percentage": 94.3, "elapsed_time": "1:45:20", "remaining_time": "0:06:22", "throughput": 1033.9, "total_tokens": 6534608} {"current_steps": 72575, "total_steps": 76960, "loss": 0.0151, "lr": 4.930592756827695e-07, "epoch": 18.860446985446984, "percentage": 94.3, "elapsed_time": "1:45:20", "remaining_time": "0:06:21", "throughput": 1033.89, "total_tokens": 6535024} {"current_steps": 72580, "total_steps": 76960, "loss": 0.0035, "lr": 4.919394496068486e-07, "epoch": 18.861746361746363, "percentage": 94.31, "elapsed_time": "1:45:21", "remaining_time": "0:06:21", "throughput": 1033.9, "total_tokens": 6535472} {"current_steps": 72585, "total_steps": 76960, "loss": 0.0004, "lr": 4.908208840039646e-07, "epoch": 18.863045738045738, "percentage": 94.32, "elapsed_time": "1:45:21", "remaining_time": "0:06:21", "throughput": 1033.9, "total_tokens": 6535904} {"current_steps": 72590, "total_steps": 76960, "loss": 0.3351, "lr": 4.89703578931644e-07, "epoch": 18.864345114345113, "percentage": 94.32, "elapsed_time": "1:45:22", "remaining_time": "0:06:20", "throughput": 1033.9, "total_tokens": 6536368} {"current_steps": 72595, "total_steps": 76960, "loss": 0.603, "lr": 4.885875344473545e-07, "epoch": 18.865644490644492, "percentage": 94.33, "elapsed_time": "1:45:22", "remaining_time": "0:06:20", "throughput": 1033.91, "total_tokens": 6536832} {"current_steps": 72600, "total_steps": 76960, "loss": 0.0229, "lr": 4.874727506084947e-07, "epoch": 18.866943866943867, "percentage": 94.33, "elapsed_time": "1:45:22", "remaining_time": "0:06:19", "throughput": 1033.91, "total_tokens": 6537264} {"current_steps": 72605, "total_steps": 76960, "loss": 0.3622, "lr": 4.863592274723965e-07, "epoch": 18.868243243243242, "percentage": 94.34, "elapsed_time": "1:45:23", "remaining_time": "0:06:19", "throughput": 1033.91, "total_tokens": 6537712} {"current_steps": 72610, "total_steps": 76960, "loss": 0.2552, "lr": 4.852469650963337e-07, "epoch": 18.86954261954262, "percentage": 94.35, "elapsed_time": "1:45:23", "remaining_time": "0:06:18", "throughput": 1033.91, "total_tokens": 6538160} {"current_steps": 72615, "total_steps": 76960, "loss": 0.1321, "lr": 4.841359635375076e-07, "epoch": 18.870841995841996, "percentage": 94.35, "elapsed_time": "1:45:24", "remaining_time": "0:06:18", "throughput": 1033.91, "total_tokens": 6538608} {"current_steps": 72620, "total_steps": 76960, "loss": 0.0144, "lr": 4.830262228530585e-07, "epoch": 18.87214137214137, "percentage": 94.36, "elapsed_time": "1:45:24", "remaining_time": "0:06:17", "throughput": 1033.91, "total_tokens": 6539040} {"current_steps": 72625, "total_steps": 76960, "loss": 0.0005, "lr": 4.819177431000604e-07, "epoch": 18.87344074844075, "percentage": 94.37, "elapsed_time": "1:45:24", "remaining_time": "0:06:17", "throughput": 1033.92, "total_tokens": 6539488} {"current_steps": 72630, "total_steps": 76960, "loss": 0.0003, "lr": 4.80810524335526e-07, "epoch": 18.874740124740125, "percentage": 94.37, "elapsed_time": "1:45:25", "remaining_time": "0:06:17", "throughput": 1033.92, "total_tokens": 6539952} {"current_steps": 72635, "total_steps": 76960, "loss": 0.1396, "lr": 4.797045666163986e-07, "epoch": 18.8760395010395, "percentage": 94.38, "elapsed_time": "1:45:25", "remaining_time": "0:06:16", "throughput": 1033.92, "total_tokens": 6540384} {"current_steps": 72640, "total_steps": 76960, "loss": 0.1795, "lr": 4.785998699995603e-07, "epoch": 18.87733887733888, "percentage": 94.39, "elapsed_time": "1:45:26", "remaining_time": "0:06:16", "throughput": 1033.93, "total_tokens": 6540880} {"current_steps": 72645, "total_steps": 76960, "loss": 0.0042, "lr": 4.77496434541827e-07, "epoch": 18.878638253638254, "percentage": 94.39, "elapsed_time": "1:45:26", "remaining_time": "0:06:15", "throughput": 1033.94, "total_tokens": 6541376} {"current_steps": 72650, "total_steps": 76960, "loss": 0.1373, "lr": 4.763942602999477e-07, "epoch": 18.87993762993763, "percentage": 94.4, "elapsed_time": "1:45:27", "remaining_time": "0:06:15", "throughput": 1033.95, "total_tokens": 6541824} {"current_steps": 72655, "total_steps": 76960, "loss": 0.0015, "lr": 4.752933473306076e-07, "epoch": 18.881237006237008, "percentage": 94.41, "elapsed_time": "1:45:27", "remaining_time": "0:06:14", "throughput": 1033.95, "total_tokens": 6542256} {"current_steps": 72660, "total_steps": 76960, "loss": 0.197, "lr": 4.741936956904308e-07, "epoch": 18.882536382536383, "percentage": 94.41, "elapsed_time": "1:45:27", "remaining_time": "0:06:14", "throughput": 1033.95, "total_tokens": 6542736} {"current_steps": 72665, "total_steps": 76960, "loss": 0.0364, "lr": 4.730953054359694e-07, "epoch": 18.883835758835758, "percentage": 94.42, "elapsed_time": "1:45:28", "remaining_time": "0:06:14", "throughput": 1033.96, "total_tokens": 6543200} {"current_steps": 72670, "total_steps": 76960, "loss": 0.0267, "lr": 4.719981766237197e-07, "epoch": 18.885135135135137, "percentage": 94.43, "elapsed_time": "1:45:28", "remaining_time": "0:06:13", "throughput": 1033.96, "total_tokens": 6543632} {"current_steps": 72675, "total_steps": 76960, "loss": 0.0263, "lr": 4.7090230931010615e-07, "epoch": 18.886434511434512, "percentage": 94.43, "elapsed_time": "1:45:29", "remaining_time": "0:06:13", "throughput": 1033.97, "total_tokens": 6544096} {"current_steps": 72680, "total_steps": 76960, "loss": 0.0002, "lr": 4.698077035514864e-07, "epoch": 18.887733887733887, "percentage": 94.44, "elapsed_time": "1:45:29", "remaining_time": "0:06:12", "throughput": 1033.96, "total_tokens": 6544512} {"current_steps": 72685, "total_steps": 76960, "loss": 0.0305, "lr": 4.687143594041626e-07, "epoch": 18.889033264033262, "percentage": 94.45, "elapsed_time": "1:45:29", "remaining_time": "0:06:12", "throughput": 1033.96, "total_tokens": 6544928} {"current_steps": 72690, "total_steps": 76960, "loss": 0.041, "lr": 4.6762227692436213e-07, "epoch": 18.89033264033264, "percentage": 94.45, "elapsed_time": "1:45:30", "remaining_time": "0:06:11", "throughput": 1033.96, "total_tokens": 6545360} {"current_steps": 72695, "total_steps": 76960, "loss": 0.0276, "lr": 4.665314561682538e-07, "epoch": 18.891632016632016, "percentage": 94.46, "elapsed_time": "1:45:30", "remaining_time": "0:06:11", "throughput": 1033.97, "total_tokens": 6545856} {"current_steps": 72700, "total_steps": 76960, "loss": 0.0001, "lr": 4.654418971919372e-07, "epoch": 18.89293139293139, "percentage": 94.46, "elapsed_time": "1:45:31", "remaining_time": "0:06:10", "throughput": 1033.98, "total_tokens": 6546336} {"current_steps": 72705, "total_steps": 76960, "loss": 0.3564, "lr": 4.6435360005145644e-07, "epoch": 18.89423076923077, "percentage": 94.47, "elapsed_time": "1:45:31", "remaining_time": "0:06:10", "throughput": 1033.99, "total_tokens": 6546816} {"current_steps": 72710, "total_steps": 76960, "loss": 0.0005, "lr": 4.632665648027779e-07, "epoch": 18.895530145530145, "percentage": 94.48, "elapsed_time": "1:45:32", "remaining_time": "0:06:10", "throughput": 1033.99, "total_tokens": 6547248} {"current_steps": 72715, "total_steps": 76960, "loss": 0.0172, "lr": 4.6218079150180946e-07, "epoch": 18.89682952182952, "percentage": 94.48, "elapsed_time": "1:45:32", "remaining_time": "0:06:09", "throughput": 1033.99, "total_tokens": 6547696} {"current_steps": 72720, "total_steps": 76960, "loss": 0.1406, "lr": 4.610962802043928e-07, "epoch": 18.8981288981289, "percentage": 94.49, "elapsed_time": "1:45:32", "remaining_time": "0:06:09", "throughput": 1033.99, "total_tokens": 6548112} {"current_steps": 72725, "total_steps": 76960, "loss": 0.0038, "lr": 4.600130309663081e-07, "epoch": 18.899428274428274, "percentage": 94.5, "elapsed_time": "1:45:33", "remaining_time": "0:06:08", "throughput": 1033.99, "total_tokens": 6548576} {"current_steps": 72730, "total_steps": 76960, "loss": 0.0016, "lr": 4.5893104384326367e-07, "epoch": 18.90072765072765, "percentage": 94.5, "elapsed_time": "1:45:33", "remaining_time": "0:06:08", "throughput": 1033.99, "total_tokens": 6548976} {"current_steps": 72735, "total_steps": 76960, "loss": 0.1599, "lr": 4.5785031889091225e-07, "epoch": 18.902027027027028, "percentage": 94.51, "elapsed_time": "1:45:34", "remaining_time": "0:06:07", "throughput": 1034.0, "total_tokens": 6549456} {"current_steps": 72740, "total_steps": 76960, "loss": 0.1402, "lr": 4.5677085616483427e-07, "epoch": 18.903326403326403, "percentage": 94.52, "elapsed_time": "1:45:34", "remaining_time": "0:06:07", "throughput": 1034.0, "total_tokens": 6549904} {"current_steps": 72745, "total_steps": 76960, "loss": 0.001, "lr": 4.5569265572054655e-07, "epoch": 18.90462577962578, "percentage": 94.52, "elapsed_time": "1:45:34", "remaining_time": "0:06:07", "throughput": 1034.0, "total_tokens": 6550352} {"current_steps": 72750, "total_steps": 76960, "loss": 0.0031, "lr": 4.5461571761350465e-07, "epoch": 18.905925155925157, "percentage": 94.53, "elapsed_time": "1:45:35", "remaining_time": "0:06:06", "throughput": 1034.0, "total_tokens": 6550768} {"current_steps": 72755, "total_steps": 76960, "loss": 0.1577, "lr": 4.5354004189909203e-07, "epoch": 18.907224532224532, "percentage": 94.54, "elapsed_time": "1:45:35", "remaining_time": "0:06:06", "throughput": 1034.0, "total_tokens": 6551200} {"current_steps": 72760, "total_steps": 76960, "loss": 0.0004, "lr": 4.52465628632634e-07, "epoch": 18.908523908523907, "percentage": 94.54, "elapsed_time": "1:45:36", "remaining_time": "0:06:05", "throughput": 1034.0, "total_tokens": 6551648} {"current_steps": 72765, "total_steps": 76960, "loss": 0.0407, "lr": 4.51392477869389e-07, "epoch": 18.909823284823286, "percentage": 94.55, "elapsed_time": "1:45:36", "remaining_time": "0:06:05", "throughput": 1034.0, "total_tokens": 6552080} {"current_steps": 72770, "total_steps": 76960, "loss": 0.0007, "lr": 4.503205896645518e-07, "epoch": 18.91112266112266, "percentage": 94.56, "elapsed_time": "1:45:37", "remaining_time": "0:06:04", "throughput": 1034.01, "total_tokens": 6552560} {"current_steps": 72775, "total_steps": 76960, "loss": 0.0338, "lr": 4.492499640732478e-07, "epoch": 18.912422037422036, "percentage": 94.56, "elapsed_time": "1:45:37", "remaining_time": "0:06:04", "throughput": 1034.01, "total_tokens": 6553024} {"current_steps": 72780, "total_steps": 76960, "loss": 0.0003, "lr": 4.4818060115054406e-07, "epoch": 18.913721413721415, "percentage": 94.57, "elapsed_time": "1:45:37", "remaining_time": "0:06:04", "throughput": 1034.02, "total_tokens": 6553472} {"current_steps": 72785, "total_steps": 76960, "loss": 0.2525, "lr": 4.4711250095143267e-07, "epoch": 18.91502079002079, "percentage": 94.58, "elapsed_time": "1:45:38", "remaining_time": "0:06:03", "throughput": 1034.02, "total_tokens": 6553920} {"current_steps": 72790, "total_steps": 76960, "loss": 0.0004, "lr": 4.4604566353085296e-07, "epoch": 18.916320166320165, "percentage": 94.58, "elapsed_time": "1:45:38", "remaining_time": "0:06:03", "throughput": 1034.02, "total_tokens": 6554352} {"current_steps": 72795, "total_steps": 76960, "loss": 0.2452, "lr": 4.4498008894367227e-07, "epoch": 18.917619542619544, "percentage": 94.59, "elapsed_time": "1:45:39", "remaining_time": "0:06:02", "throughput": 1034.02, "total_tokens": 6554800} {"current_steps": 72800, "total_steps": 76960, "loss": 0.0012, "lr": 4.4391577724469114e-07, "epoch": 18.91891891891892, "percentage": 94.59, "elapsed_time": "1:45:39", "remaining_time": "0:06:02", "throughput": 1034.03, "total_tokens": 6555248} {"current_steps": 72805, "total_steps": 76960, "loss": 0.0015, "lr": 4.428527284886519e-07, "epoch": 18.920218295218294, "percentage": 94.6, "elapsed_time": "1:45:39", "remaining_time": "0:06:01", "throughput": 1034.03, "total_tokens": 6555680} {"current_steps": 72810, "total_steps": 76960, "loss": 0.1076, "lr": 4.417909427302247e-07, "epoch": 18.921517671517673, "percentage": 94.61, "elapsed_time": "1:45:40", "remaining_time": "0:06:01", "throughput": 1034.03, "total_tokens": 6556160} {"current_steps": 72815, "total_steps": 76960, "loss": 0.0018, "lr": 4.407304200240214e-07, "epoch": 18.92281704781705, "percentage": 94.61, "elapsed_time": "1:45:40", "remaining_time": "0:06:00", "throughput": 1034.03, "total_tokens": 6556592} {"current_steps": 72820, "total_steps": 76960, "loss": 0.0001, "lr": 4.3967116042458177e-07, "epoch": 18.924116424116423, "percentage": 94.62, "elapsed_time": "1:45:41", "remaining_time": "0:06:00", "throughput": 1034.04, "total_tokens": 6557056} {"current_steps": 72825, "total_steps": 76960, "loss": 0.1748, "lr": 4.3861316398638995e-07, "epoch": 18.9254158004158, "percentage": 94.63, "elapsed_time": "1:45:41", "remaining_time": "0:06:00", "throughput": 1034.04, "total_tokens": 6557488} {"current_steps": 72830, "total_steps": 76960, "loss": 0.1649, "lr": 4.3755643076385243e-07, "epoch": 18.926715176715177, "percentage": 94.63, "elapsed_time": "1:45:42", "remaining_time": "0:05:59", "throughput": 1034.05, "total_tokens": 6557952} {"current_steps": 72835, "total_steps": 76960, "loss": 0.0003, "lr": 4.365009608113285e-07, "epoch": 18.928014553014552, "percentage": 94.64, "elapsed_time": "1:45:42", "remaining_time": "0:05:59", "throughput": 1034.05, "total_tokens": 6558400} {"current_steps": 72840, "total_steps": 76960, "loss": 0.1875, "lr": 4.3544675418309144e-07, "epoch": 18.929313929313928, "percentage": 94.65, "elapsed_time": "1:45:42", "remaining_time": "0:05:58", "throughput": 1034.05, "total_tokens": 6558832} {"current_steps": 72845, "total_steps": 76960, "loss": 0.1568, "lr": 4.343938109333645e-07, "epoch": 18.930613305613306, "percentage": 94.65, "elapsed_time": "1:45:43", "remaining_time": "0:05:58", "throughput": 1034.05, "total_tokens": 6559264} {"current_steps": 72850, "total_steps": 76960, "loss": 0.038, "lr": 4.3334213111629883e-07, "epoch": 18.93191268191268, "percentage": 94.66, "elapsed_time": "1:45:43", "remaining_time": "0:05:57", "throughput": 1034.06, "total_tokens": 6559744} {"current_steps": 72855, "total_steps": 76960, "loss": 0.0541, "lr": 4.3229171478599283e-07, "epoch": 18.933212058212057, "percentage": 94.67, "elapsed_time": "1:45:44", "remaining_time": "0:05:57", "throughput": 1034.06, "total_tokens": 6560208} {"current_steps": 72860, "total_steps": 76960, "loss": 0.1658, "lr": 4.3124256199645884e-07, "epoch": 18.934511434511435, "percentage": 94.67, "elapsed_time": "1:45:44", "remaining_time": "0:05:57", "throughput": 1034.06, "total_tokens": 6560640} {"current_steps": 72865, "total_steps": 76960, "loss": 0.0021, "lr": 4.30194672801662e-07, "epoch": 18.93581081081081, "percentage": 94.68, "elapsed_time": "1:45:44", "remaining_time": "0:05:56", "throughput": 1034.06, "total_tokens": 6561088} {"current_steps": 72870, "total_steps": 76960, "loss": 0.1235, "lr": 4.291480472554954e-07, "epoch": 18.937110187110186, "percentage": 94.69, "elapsed_time": "1:45:45", "remaining_time": "0:05:56", "throughput": 1034.07, "total_tokens": 6561536} {"current_steps": 72875, "total_steps": 76960, "loss": 0.111, "lr": 4.281026854117853e-07, "epoch": 18.938409563409564, "percentage": 94.69, "elapsed_time": "1:45:45", "remaining_time": "0:05:55", "throughput": 1034.07, "total_tokens": 6561968} {"current_steps": 72880, "total_steps": 76960, "loss": 0.2155, "lr": 4.2705858732429993e-07, "epoch": 18.93970893970894, "percentage": 94.7, "elapsed_time": "1:45:46", "remaining_time": "0:05:55", "throughput": 1034.07, "total_tokens": 6562448} {"current_steps": 72885, "total_steps": 76960, "loss": 0.0088, "lr": 4.2601575304673234e-07, "epoch": 18.941008316008315, "percentage": 94.71, "elapsed_time": "1:45:46", "remaining_time": "0:05:54", "throughput": 1034.08, "total_tokens": 6562896} {"current_steps": 72890, "total_steps": 76960, "loss": 0.0345, "lr": 4.2497418263272583e-07, "epoch": 18.942307692307693, "percentage": 94.71, "elapsed_time": "1:45:47", "remaining_time": "0:05:54", "throughput": 1034.08, "total_tokens": 6563344} {"current_steps": 72895, "total_steps": 76960, "loss": 0.0131, "lr": 4.2393387613584025e-07, "epoch": 18.94360706860707, "percentage": 94.72, "elapsed_time": "1:45:47", "remaining_time": "0:05:53", "throughput": 1034.09, "total_tokens": 6563840} {"current_steps": 72900, "total_steps": 76960, "loss": 0.0002, "lr": 4.228948336095856e-07, "epoch": 18.944906444906444, "percentage": 94.72, "elapsed_time": "1:45:47", "remaining_time": "0:05:53", "throughput": 1034.09, "total_tokens": 6564288} {"current_steps": 72905, "total_steps": 76960, "loss": 0.0659, "lr": 4.2185705510739415e-07, "epoch": 18.946205821205822, "percentage": 94.73, "elapsed_time": "1:45:48", "remaining_time": "0:05:53", "throughput": 1034.1, "total_tokens": 6564736} {"current_steps": 72910, "total_steps": 76960, "loss": 0.0095, "lr": 4.208205406826482e-07, "epoch": 18.947505197505198, "percentage": 94.74, "elapsed_time": "1:45:48", "remaining_time": "0:05:52", "throughput": 1034.1, "total_tokens": 6565200} {"current_steps": 72915, "total_steps": 76960, "loss": 0.0799, "lr": 4.1978529038864676e-07, "epoch": 18.948804573804573, "percentage": 94.74, "elapsed_time": "1:45:49", "remaining_time": "0:05:52", "throughput": 1034.11, "total_tokens": 6565680} {"current_steps": 72920, "total_steps": 76960, "loss": 0.0031, "lr": 4.187513042786445e-07, "epoch": 18.95010395010395, "percentage": 94.75, "elapsed_time": "1:45:49", "remaining_time": "0:05:51", "throughput": 1034.11, "total_tokens": 6566112} {"current_steps": 72925, "total_steps": 76960, "loss": 0.0006, "lr": 4.177185824058155e-07, "epoch": 18.951403326403327, "percentage": 94.76, "elapsed_time": "1:45:49", "remaining_time": "0:05:51", "throughput": 1034.12, "total_tokens": 6566576} {"current_steps": 72930, "total_steps": 76960, "loss": 0.0004, "lr": 4.166871248232729e-07, "epoch": 18.9527027027027, "percentage": 94.76, "elapsed_time": "1:45:50", "remaining_time": "0:05:50", "throughput": 1034.12, "total_tokens": 6567024} {"current_steps": 72935, "total_steps": 76960, "loss": 0.0002, "lr": 4.1565693158406584e-07, "epoch": 18.95400207900208, "percentage": 94.77, "elapsed_time": "1:45:50", "remaining_time": "0:05:50", "throughput": 1034.12, "total_tokens": 6567472} {"current_steps": 72940, "total_steps": 76960, "loss": 0.081, "lr": 4.1462800274117697e-07, "epoch": 18.955301455301456, "percentage": 94.78, "elapsed_time": "1:45:51", "remaining_time": "0:05:50", "throughput": 1034.13, "total_tokens": 6567952} {"current_steps": 72945, "total_steps": 76960, "loss": 0.0013, "lr": 4.136003383475251e-07, "epoch": 18.95660083160083, "percentage": 94.78, "elapsed_time": "1:45:51", "remaining_time": "0:05:49", "throughput": 1034.12, "total_tokens": 6568352} {"current_steps": 72950, "total_steps": 76960, "loss": 0.0145, "lr": 4.1257393845596793e-07, "epoch": 18.95790020790021, "percentage": 94.79, "elapsed_time": "1:45:52", "remaining_time": "0:05:49", "throughput": 1034.13, "total_tokens": 6568800} {"current_steps": 72955, "total_steps": 76960, "loss": 0.1673, "lr": 4.11548803119291e-07, "epoch": 18.959199584199585, "percentage": 94.8, "elapsed_time": "1:45:52", "remaining_time": "0:05:48", "throughput": 1034.13, "total_tokens": 6569232} {"current_steps": 72960, "total_steps": 76960, "loss": 0.2948, "lr": 4.105249323902188e-07, "epoch": 18.96049896049896, "percentage": 94.8, "elapsed_time": "1:45:52", "remaining_time": "0:05:48", "throughput": 1034.13, "total_tokens": 6569680} {"current_steps": 72965, "total_steps": 76960, "loss": 0.0049, "lr": 4.095023263214121e-07, "epoch": 18.96179833679834, "percentage": 94.81, "elapsed_time": "1:45:53", "remaining_time": "0:05:47", "throughput": 1034.14, "total_tokens": 6570144} {"current_steps": 72970, "total_steps": 76960, "loss": 0.0001, "lr": 4.0848098496545915e-07, "epoch": 18.963097713097714, "percentage": 94.82, "elapsed_time": "1:45:53", "remaining_time": "0:05:47", "throughput": 1034.14, "total_tokens": 6570592} {"current_steps": 72975, "total_steps": 76960, "loss": 0.0033, "lr": 4.0746090837489316e-07, "epoch": 18.96439708939709, "percentage": 94.82, "elapsed_time": "1:45:54", "remaining_time": "0:05:46", "throughput": 1034.14, "total_tokens": 6571024} {"current_steps": 72980, "total_steps": 76960, "loss": 0.0023, "lr": 4.064420966021748e-07, "epoch": 18.965696465696467, "percentage": 94.83, "elapsed_time": "1:45:54", "remaining_time": "0:05:46", "throughput": 1034.15, "total_tokens": 6571504} {"current_steps": 72985, "total_steps": 76960, "loss": 0.2672, "lr": 4.0542454969970387e-07, "epoch": 18.966995841995843, "percentage": 94.83, "elapsed_time": "1:45:54", "remaining_time": "0:05:46", "throughput": 1034.15, "total_tokens": 6571936} {"current_steps": 72990, "total_steps": 76960, "loss": 0.0008, "lr": 4.0440826771981354e-07, "epoch": 18.968295218295218, "percentage": 94.84, "elapsed_time": "1:45:55", "remaining_time": "0:05:45", "throughput": 1034.15, "total_tokens": 6572400} {"current_steps": 72995, "total_steps": 76960, "loss": 0.0289, "lr": 4.033932507147731e-07, "epoch": 18.969594594594593, "percentage": 94.85, "elapsed_time": "1:45:55", "remaining_time": "0:05:45", "throughput": 1034.16, "total_tokens": 6572912} {"current_steps": 73000, "total_steps": 76960, "loss": 0.0013, "lr": 4.0237949873678516e-07, "epoch": 18.97089397089397, "percentage": 94.85, "elapsed_time": "1:45:56", "remaining_time": "0:05:44", "throughput": 1034.17, "total_tokens": 6573360} {"current_steps": 73005, "total_steps": 76960, "loss": 0.1313, "lr": 4.0136701183798866e-07, "epoch": 18.972193347193347, "percentage": 94.86, "elapsed_time": "1:45:56", "remaining_time": "0:05:44", "throughput": 1034.17, "total_tokens": 6573824} {"current_steps": 73010, "total_steps": 76960, "loss": 0.0682, "lr": 4.0035579007045577e-07, "epoch": 18.973492723492722, "percentage": 94.87, "elapsed_time": "1:45:57", "remaining_time": "0:05:43", "throughput": 1034.18, "total_tokens": 6574304} {"current_steps": 73015, "total_steps": 76960, "loss": 0.3422, "lr": 3.993458334861949e-07, "epoch": 18.9747920997921, "percentage": 94.87, "elapsed_time": "1:45:57", "remaining_time": "0:05:43", "throughput": 1034.18, "total_tokens": 6574752} {"current_steps": 73020, "total_steps": 76960, "loss": 0.0139, "lr": 3.9833714213714513e-07, "epoch": 18.976091476091476, "percentage": 94.88, "elapsed_time": "1:45:57", "remaining_time": "0:05:43", "throughput": 1034.19, "total_tokens": 6575200} {"current_steps": 73025, "total_steps": 76960, "loss": 0.0924, "lr": 3.9732971607519265e-07, "epoch": 18.97739085239085, "percentage": 94.89, "elapsed_time": "1:45:58", "remaining_time": "0:05:42", "throughput": 1034.19, "total_tokens": 6575648} {"current_steps": 73030, "total_steps": 76960, "loss": 0.001, "lr": 3.9632355535214603e-07, "epoch": 18.97869022869023, "percentage": 94.89, "elapsed_time": "1:45:58", "remaining_time": "0:05:42", "throughput": 1034.19, "total_tokens": 6576080} {"current_steps": 73035, "total_steps": 76960, "loss": 0.0906, "lr": 3.9531866001975003e-07, "epoch": 18.979989604989605, "percentage": 94.9, "elapsed_time": "1:45:59", "remaining_time": "0:05:41", "throughput": 1034.19, "total_tokens": 6576512} {"current_steps": 73040, "total_steps": 76960, "loss": 0.0028, "lr": 3.9431503012969384e-07, "epoch": 18.98128898128898, "percentage": 94.91, "elapsed_time": "1:45:59", "remaining_time": "0:05:41", "throughput": 1034.19, "total_tokens": 6576944} {"current_steps": 73045, "total_steps": 76960, "loss": 0.299, "lr": 3.933126657335889e-07, "epoch": 18.98258835758836, "percentage": 94.91, "elapsed_time": "1:45:59", "remaining_time": "0:05:40", "throughput": 1034.19, "total_tokens": 6577360} {"current_steps": 73050, "total_steps": 76960, "loss": 0.0198, "lr": 3.9231156688299406e-07, "epoch": 18.983887733887734, "percentage": 94.92, "elapsed_time": "1:46:00", "remaining_time": "0:05:40", "throughput": 1034.19, "total_tokens": 6577792} {"current_steps": 73055, "total_steps": 76960, "loss": 0.4137, "lr": 3.9131173362939033e-07, "epoch": 18.98518711018711, "percentage": 94.93, "elapsed_time": "1:46:00", "remaining_time": "0:05:40", "throughput": 1034.18, "total_tokens": 6578192} {"current_steps": 73060, "total_steps": 76960, "loss": 0.3114, "lr": 3.9031316602420323e-07, "epoch": 18.986486486486488, "percentage": 94.93, "elapsed_time": "1:46:01", "remaining_time": "0:05:39", "throughput": 1034.18, "total_tokens": 6578640} {"current_steps": 73065, "total_steps": 76960, "loss": 0.0019, "lr": 3.8931586411879163e-07, "epoch": 18.987785862785863, "percentage": 94.94, "elapsed_time": "1:46:01", "remaining_time": "0:05:39", "throughput": 1034.19, "total_tokens": 6579104} {"current_steps": 73070, "total_steps": 76960, "loss": 0.0033, "lr": 3.8831982796444233e-07, "epoch": 18.989085239085238, "percentage": 94.95, "elapsed_time": "1:46:02", "remaining_time": "0:05:38", "throughput": 1034.2, "total_tokens": 6579600} {"current_steps": 73075, "total_steps": 76960, "loss": 0.0577, "lr": 3.8732505761239215e-07, "epoch": 18.990384615384617, "percentage": 94.95, "elapsed_time": "1:46:02", "remaining_time": "0:05:38", "throughput": 1034.2, "total_tokens": 6580032} {"current_steps": 73080, "total_steps": 76960, "loss": 0.2154, "lr": 3.8633155311379174e-07, "epoch": 18.991683991683992, "percentage": 94.96, "elapsed_time": "1:46:02", "remaining_time": "0:05:37", "throughput": 1034.21, "total_tokens": 6580496} {"current_steps": 73085, "total_steps": 76960, "loss": 0.4811, "lr": 3.853393145197448e-07, "epoch": 18.992983367983367, "percentage": 94.96, "elapsed_time": "1:46:03", "remaining_time": "0:05:37", "throughput": 1034.21, "total_tokens": 6580960} {"current_steps": 73090, "total_steps": 76960, "loss": 0.0326, "lr": 3.8434834188128266e-07, "epoch": 18.994282744282746, "percentage": 94.97, "elapsed_time": "1:46:03", "remaining_time": "0:05:36", "throughput": 1034.22, "total_tokens": 6581424} {"current_steps": 73095, "total_steps": 76960, "loss": 0.0011, "lr": 3.8335863524936733e-07, "epoch": 18.99558212058212, "percentage": 94.98, "elapsed_time": "1:46:04", "remaining_time": "0:05:36", "throughput": 1034.22, "total_tokens": 6581872} {"current_steps": 73100, "total_steps": 76960, "loss": 0.4712, "lr": 3.8237019467490533e-07, "epoch": 18.996881496881496, "percentage": 94.98, "elapsed_time": "1:46:04", "remaining_time": "0:05:36", "throughput": 1034.23, "total_tokens": 6582352} {"current_steps": 73105, "total_steps": 76960, "loss": 0.0948, "lr": 3.8138302020873373e-07, "epoch": 18.998180873180875, "percentage": 94.99, "elapsed_time": "1:46:04", "remaining_time": "0:05:35", "throughput": 1034.23, "total_tokens": 6582816} {"current_steps": 73110, "total_steps": 76960, "loss": 0.3151, "lr": 3.803971119016203e-07, "epoch": 18.99948024948025, "percentage": 95.0, "elapsed_time": "1:46:05", "remaining_time": "0:05:35", "throughput": 1034.24, "total_tokens": 6583264} {"current_steps": 73112, "total_steps": 76960, "eval_loss": 0.9201962947845459, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "1:46:18", "remaining_time": "0:05:35", "throughput": 1032.09, "total_tokens": 6583408} {"current_steps": 73115, "total_steps": 76960, "loss": 0.181, "lr": 3.7941246980427445e-07, "epoch": 19.000779625779625, "percentage": 95.0, "elapsed_time": "1:46:21", "remaining_time": "0:05:35", "throughput": 1031.73, "total_tokens": 6583664} {"current_steps": 73120, "total_steps": 76960, "loss": 0.0023, "lr": 3.7842909396733627e-07, "epoch": 19.002079002079004, "percentage": 95.01, "elapsed_time": "1:46:21", "remaining_time": "0:05:35", "throughput": 1031.73, "total_tokens": 6584112} {"current_steps": 73125, "total_steps": 76960, "loss": 0.0042, "lr": 3.774469844413792e-07, "epoch": 19.00337837837838, "percentage": 95.02, "elapsed_time": "1:46:22", "remaining_time": "0:05:34", "throughput": 1031.73, "total_tokens": 6584560} {"current_steps": 73130, "total_steps": 76960, "loss": 0.0029, "lr": 3.7646614127691546e-07, "epoch": 19.004677754677754, "percentage": 95.02, "elapsed_time": "1:46:22", "remaining_time": "0:05:34", "throughput": 1031.72, "total_tokens": 6584960} {"current_steps": 73135, "total_steps": 76960, "loss": 0.0245, "lr": 3.7548656452438826e-07, "epoch": 19.00597713097713, "percentage": 95.03, "elapsed_time": "1:46:22", "remaining_time": "0:05:33", "throughput": 1031.72, "total_tokens": 6585392} {"current_steps": 73140, "total_steps": 76960, "loss": 0.2734, "lr": 3.7450825423418767e-07, "epoch": 19.007276507276508, "percentage": 95.04, "elapsed_time": "1:46:23", "remaining_time": "0:05:33", "throughput": 1031.72, "total_tokens": 6585856} {"current_steps": 73145, "total_steps": 76960, "loss": 0.144, "lr": 3.7353121045661797e-07, "epoch": 19.008575883575883, "percentage": 95.04, "elapsed_time": "1:46:23", "remaining_time": "0:05:32", "throughput": 1031.73, "total_tokens": 6586336} {"current_steps": 73150, "total_steps": 76960, "loss": 0.0002, "lr": 3.725554332419362e-07, "epoch": 19.00987525987526, "percentage": 95.05, "elapsed_time": "1:46:24", "remaining_time": "0:05:32", "throughput": 1031.73, "total_tokens": 6586752} {"current_steps": 73155, "total_steps": 76960, "loss": 0.0164, "lr": 3.715809226403244e-07, "epoch": 19.011174636174637, "percentage": 95.06, "elapsed_time": "1:46:24", "remaining_time": "0:05:32", "throughput": 1031.73, "total_tokens": 6587216} {"current_steps": 73160, "total_steps": 76960, "loss": 0.0013, "lr": 3.706076787019036e-07, "epoch": 19.012474012474012, "percentage": 95.06, "elapsed_time": "1:46:25", "remaining_time": "0:05:31", "throughput": 1031.74, "total_tokens": 6587680} {"current_steps": 73165, "total_steps": 76960, "loss": 0.0023, "lr": 3.6963570147672824e-07, "epoch": 19.013773388773387, "percentage": 95.07, "elapsed_time": "1:46:25", "remaining_time": "0:05:31", "throughput": 1031.75, "total_tokens": 6588176} {"current_steps": 73170, "total_steps": 76960, "loss": 0.0202, "lr": 3.686649910147888e-07, "epoch": 19.015072765072766, "percentage": 95.08, "elapsed_time": "1:46:25", "remaining_time": "0:05:30", "throughput": 1031.75, "total_tokens": 6588624} {"current_steps": 73175, "total_steps": 76960, "loss": 0.0429, "lr": 3.676955473660093e-07, "epoch": 19.01637214137214, "percentage": 95.08, "elapsed_time": "1:46:26", "remaining_time": "0:05:30", "throughput": 1031.75, "total_tokens": 6589040} {"current_steps": 73180, "total_steps": 76960, "loss": 0.1748, "lr": 3.6672737058025266e-07, "epoch": 19.017671517671516, "percentage": 95.09, "elapsed_time": "1:46:26", "remaining_time": "0:05:29", "throughput": 1031.74, "total_tokens": 6589456} {"current_steps": 73185, "total_steps": 76960, "loss": 0.0015, "lr": 3.6576046070730675e-07, "epoch": 19.018970893970895, "percentage": 95.09, "elapsed_time": "1:46:27", "remaining_time": "0:05:29", "throughput": 1031.74, "total_tokens": 6589872} {"current_steps": 73190, "total_steps": 76960, "loss": 0.002, "lr": 3.6479481779690403e-07, "epoch": 19.02027027027027, "percentage": 95.1, "elapsed_time": "1:46:27", "remaining_time": "0:05:29", "throughput": 1031.74, "total_tokens": 6590304} {"current_steps": 73195, "total_steps": 76960, "loss": 0.0088, "lr": 3.6383044189870763e-07, "epoch": 19.021569646569645, "percentage": 95.11, "elapsed_time": "1:46:27", "remaining_time": "0:05:28", "throughput": 1031.74, "total_tokens": 6590720} {"current_steps": 73200, "total_steps": 76960, "loss": 0.0055, "lr": 3.628673330623139e-07, "epoch": 19.022869022869024, "percentage": 95.11, "elapsed_time": "1:46:28", "remaining_time": "0:05:28", "throughput": 1031.75, "total_tokens": 6591200} {"current_steps": 73205, "total_steps": 76960, "loss": 0.0221, "lr": 3.619054913372638e-07, "epoch": 19.0241683991684, "percentage": 95.12, "elapsed_time": "1:46:28", "remaining_time": "0:05:27", "throughput": 1031.75, "total_tokens": 6591632} {"current_steps": 73210, "total_steps": 76960, "loss": 0.0323, "lr": 3.609449167730206e-07, "epoch": 19.025467775467774, "percentage": 95.13, "elapsed_time": "1:46:29", "remaining_time": "0:05:27", "throughput": 1031.75, "total_tokens": 6592080} {"current_steps": 73215, "total_steps": 76960, "loss": 0.0015, "lr": 3.5998560941898907e-07, "epoch": 19.026767151767153, "percentage": 95.13, "elapsed_time": "1:46:29", "remaining_time": "0:05:26", "throughput": 1031.76, "total_tokens": 6592560} {"current_steps": 73220, "total_steps": 76960, "loss": 0.0006, "lr": 3.5902756932450486e-07, "epoch": 19.028066528066528, "percentage": 95.14, "elapsed_time": "1:46:30", "remaining_time": "0:05:26", "throughput": 1031.76, "total_tokens": 6593024} {"current_steps": 73225, "total_steps": 76960, "loss": 0.0094, "lr": 3.5807079653884526e-07, "epoch": 19.029365904365903, "percentage": 95.15, "elapsed_time": "1:46:30", "remaining_time": "0:05:25", "throughput": 1031.77, "total_tokens": 6593472} {"current_steps": 73230, "total_steps": 76960, "loss": 0.0335, "lr": 3.5711529111121244e-07, "epoch": 19.030665280665282, "percentage": 95.15, "elapsed_time": "1:46:30", "remaining_time": "0:05:25", "throughput": 1031.77, "total_tokens": 6593952} {"current_steps": 73235, "total_steps": 76960, "loss": 0.2378, "lr": 3.561610530907505e-07, "epoch": 19.031964656964657, "percentage": 95.16, "elapsed_time": "1:46:31", "remaining_time": "0:05:25", "throughput": 1031.77, "total_tokens": 6594384} {"current_steps": 73240, "total_steps": 76960, "loss": 0.1014, "lr": 3.552080825265397e-07, "epoch": 19.033264033264032, "percentage": 95.17, "elapsed_time": "1:46:31", "remaining_time": "0:05:24", "throughput": 1031.77, "total_tokens": 6594800} {"current_steps": 73245, "total_steps": 76960, "loss": 0.0577, "lr": 3.5425637946759347e-07, "epoch": 19.03456340956341, "percentage": 95.17, "elapsed_time": "1:46:32", "remaining_time": "0:05:24", "throughput": 1031.78, "total_tokens": 6595264} {"current_steps": 73250, "total_steps": 76960, "loss": 0.1905, "lr": 3.533059439628561e-07, "epoch": 19.035862785862786, "percentage": 95.18, "elapsed_time": "1:46:32", "remaining_time": "0:05:23", "throughput": 1031.78, "total_tokens": 6595712} {"current_steps": 73255, "total_steps": 76960, "loss": 0.0002, "lr": 3.523567760612051e-07, "epoch": 19.03716216216216, "percentage": 95.19, "elapsed_time": "1:46:32", "remaining_time": "0:05:23", "throughput": 1031.78, "total_tokens": 6596176} {"current_steps": 73260, "total_steps": 76960, "loss": 0.1467, "lr": 3.5140887581146534e-07, "epoch": 19.03846153846154, "percentage": 95.19, "elapsed_time": "1:46:33", "remaining_time": "0:05:22", "throughput": 1031.78, "total_tokens": 6596592} {"current_steps": 73265, "total_steps": 76960, "loss": 0.1366, "lr": 3.5046224326238107e-07, "epoch": 19.039760914760915, "percentage": 95.2, "elapsed_time": "1:46:33", "remaining_time": "0:05:22", "throughput": 1031.78, "total_tokens": 6597040} {"current_steps": 73270, "total_steps": 76960, "loss": 0.002, "lr": 3.49516878462644e-07, "epoch": 19.04106029106029, "percentage": 95.21, "elapsed_time": "1:46:34", "remaining_time": "0:05:22", "throughput": 1031.79, "total_tokens": 6597520} {"current_steps": 73275, "total_steps": 76960, "loss": 0.1164, "lr": 3.485727814608708e-07, "epoch": 19.04235966735967, "percentage": 95.21, "elapsed_time": "1:46:34", "remaining_time": "0:05:21", "throughput": 1031.79, "total_tokens": 6597968} {"current_steps": 73280, "total_steps": 76960, "loss": 0.0009, "lr": 3.476299523056198e-07, "epoch": 19.043659043659044, "percentage": 95.22, "elapsed_time": "1:46:35", "remaining_time": "0:05:21", "throughput": 1031.79, "total_tokens": 6598400} {"current_steps": 73285, "total_steps": 76960, "loss": 0.0007, "lr": 3.4668839104538273e-07, "epoch": 19.04495841995842, "percentage": 95.22, "elapsed_time": "1:46:35", "remaining_time": "0:05:20", "throughput": 1031.8, "total_tokens": 6598848} {"current_steps": 73290, "total_steps": 76960, "loss": 0.008, "lr": 3.457480977285821e-07, "epoch": 19.046257796257795, "percentage": 95.23, "elapsed_time": "1:46:35", "remaining_time": "0:05:20", "throughput": 1031.8, "total_tokens": 6599280} {"current_steps": 73295, "total_steps": 76960, "loss": 0.0138, "lr": 3.4480907240357906e-07, "epoch": 19.047557172557173, "percentage": 95.24, "elapsed_time": "1:46:36", "remaining_time": "0:05:19", "throughput": 1031.8, "total_tokens": 6599728} {"current_steps": 73300, "total_steps": 76960, "loss": 0.4383, "lr": 3.438713151186712e-07, "epoch": 19.04885654885655, "percentage": 95.24, "elapsed_time": "1:46:36", "remaining_time": "0:05:19", "throughput": 1031.8, "total_tokens": 6600176} {"current_steps": 73305, "total_steps": 76960, "loss": 0.091, "lr": 3.429348259220838e-07, "epoch": 19.050155925155924, "percentage": 95.25, "elapsed_time": "1:46:37", "remaining_time": "0:05:18", "throughput": 1031.8, "total_tokens": 6600608} {"current_steps": 73310, "total_steps": 76960, "loss": 0.0368, "lr": 3.419996048619839e-07, "epoch": 19.051455301455302, "percentage": 95.26, "elapsed_time": "1:46:37", "remaining_time": "0:05:18", "throughput": 1031.8, "total_tokens": 6601040} {"current_steps": 73315, "total_steps": 76960, "loss": 0.245, "lr": 3.410656519864719e-07, "epoch": 19.052754677754677, "percentage": 95.26, "elapsed_time": "1:46:37", "remaining_time": "0:05:18", "throughput": 1031.8, "total_tokens": 6601472} {"current_steps": 73320, "total_steps": 76960, "loss": 0.3608, "lr": 3.401329673435788e-07, "epoch": 19.054054054054053, "percentage": 95.27, "elapsed_time": "1:46:38", "remaining_time": "0:05:17", "throughput": 1031.81, "total_tokens": 6601952} {"current_steps": 73325, "total_steps": 76960, "loss": 0.017, "lr": 3.3920155098127457e-07, "epoch": 19.05535343035343, "percentage": 95.28, "elapsed_time": "1:46:38", "remaining_time": "0:05:17", "throughput": 1031.82, "total_tokens": 6602416} {"current_steps": 73330, "total_steps": 76960, "loss": 0.0056, "lr": 3.382714029474654e-07, "epoch": 19.056652806652806, "percentage": 95.28, "elapsed_time": "1:46:39", "remaining_time": "0:05:16", "throughput": 1031.82, "total_tokens": 6602864} {"current_steps": 73335, "total_steps": 76960, "loss": 0.186, "lr": 3.3734252328998795e-07, "epoch": 19.05795218295218, "percentage": 95.29, "elapsed_time": "1:46:39", "remaining_time": "0:05:16", "throughput": 1031.82, "total_tokens": 6603296} {"current_steps": 73340, "total_steps": 76960, "loss": 0.0641, "lr": 3.3641491205661236e-07, "epoch": 19.05925155925156, "percentage": 95.3, "elapsed_time": "1:46:40", "remaining_time": "0:05:15", "throughput": 1031.82, "total_tokens": 6603728} {"current_steps": 73345, "total_steps": 76960, "loss": 0.0021, "lr": 3.3548856929505047e-07, "epoch": 19.060550935550935, "percentage": 95.3, "elapsed_time": "1:46:40", "remaining_time": "0:05:15", "throughput": 1031.82, "total_tokens": 6604176} {"current_steps": 73350, "total_steps": 76960, "loss": 0.1468, "lr": 3.345634950529419e-07, "epoch": 19.06185031185031, "percentage": 95.31, "elapsed_time": "1:46:40", "remaining_time": "0:05:15", "throughput": 1031.83, "total_tokens": 6604624} {"current_steps": 73355, "total_steps": 76960, "loss": 0.0018, "lr": 3.336396893778709e-07, "epoch": 19.06314968814969, "percentage": 95.32, "elapsed_time": "1:46:41", "remaining_time": "0:05:14", "throughput": 1031.84, "total_tokens": 6605120} {"current_steps": 73360, "total_steps": 76960, "loss": 0.0011, "lr": 3.3271715231734113e-07, "epoch": 19.064449064449065, "percentage": 95.32, "elapsed_time": "1:46:41", "remaining_time": "0:05:14", "throughput": 1031.83, "total_tokens": 6605536} {"current_steps": 73365, "total_steps": 76960, "loss": 0.0086, "lr": 3.317958839188062e-07, "epoch": 19.06574844074844, "percentage": 95.33, "elapsed_time": "1:46:42", "remaining_time": "0:05:13", "throughput": 1031.84, "total_tokens": 6606000} {"current_steps": 73370, "total_steps": 76960, "loss": 0.1659, "lr": 3.3087588422964223e-07, "epoch": 19.06704781704782, "percentage": 95.34, "elapsed_time": "1:46:42", "remaining_time": "0:05:13", "throughput": 1031.85, "total_tokens": 6606480} {"current_steps": 73375, "total_steps": 76960, "loss": 0.0435, "lr": 3.2995715329716957e-07, "epoch": 19.068347193347194, "percentage": 95.34, "elapsed_time": "1:46:42", "remaining_time": "0:05:12", "throughput": 1031.85, "total_tokens": 6606912} {"current_steps": 73380, "total_steps": 76960, "loss": 0.002, "lr": 3.2903969116863667e-07, "epoch": 19.06964656964657, "percentage": 95.35, "elapsed_time": "1:46:43", "remaining_time": "0:05:12", "throughput": 1031.84, "total_tokens": 6607328} {"current_steps": 73385, "total_steps": 76960, "loss": 0.1614, "lr": 3.2812349789123063e-07, "epoch": 19.070945945945947, "percentage": 95.35, "elapsed_time": "1:46:43", "remaining_time": "0:05:11", "throughput": 1031.84, "total_tokens": 6607760} {"current_steps": 73390, "total_steps": 76960, "loss": 0.002, "lr": 3.272085735120778e-07, "epoch": 19.072245322245323, "percentage": 95.36, "elapsed_time": "1:46:44", "remaining_time": "0:05:11", "throughput": 1031.85, "total_tokens": 6608208} {"current_steps": 73395, "total_steps": 76960, "loss": 0.0986, "lr": 3.2629491807822375e-07, "epoch": 19.073544698544698, "percentage": 95.37, "elapsed_time": "1:46:44", "remaining_time": "0:05:11", "throughput": 1031.85, "total_tokens": 6608656} {"current_steps": 73400, "total_steps": 76960, "loss": 0.0027, "lr": 3.253825316366643e-07, "epoch": 19.074844074844076, "percentage": 95.37, "elapsed_time": "1:46:45", "remaining_time": "0:05:10", "throughput": 1031.85, "total_tokens": 6609088} {"current_steps": 73405, "total_steps": 76960, "loss": 0.0001, "lr": 3.24471414234323e-07, "epoch": 19.07614345114345, "percentage": 95.38, "elapsed_time": "1:46:45", "remaining_time": "0:05:10", "throughput": 1031.86, "total_tokens": 6609568} {"current_steps": 73410, "total_steps": 76960, "loss": 0.0001, "lr": 3.2356156591805966e-07, "epoch": 19.077442827442827, "percentage": 95.39, "elapsed_time": "1:46:45", "remaining_time": "0:05:09", "throughput": 1031.86, "total_tokens": 6610000} {"current_steps": 73415, "total_steps": 76960, "loss": 0.0014, "lr": 3.226529867346673e-07, "epoch": 19.078742203742205, "percentage": 95.39, "elapsed_time": "1:46:46", "remaining_time": "0:05:09", "throughput": 1031.86, "total_tokens": 6610448} {"current_steps": 73420, "total_steps": 76960, "loss": 0.0002, "lr": 3.2174567673088077e-07, "epoch": 19.08004158004158, "percentage": 95.4, "elapsed_time": "1:46:46", "remaining_time": "0:05:08", "throughput": 1031.87, "total_tokens": 6610928} {"current_steps": 73425, "total_steps": 76960, "loss": 0.1347, "lr": 3.208396359533572e-07, "epoch": 19.081340956340956, "percentage": 95.41, "elapsed_time": "1:46:47", "remaining_time": "0:05:08", "throughput": 1031.87, "total_tokens": 6611376} {"current_steps": 73430, "total_steps": 76960, "loss": 0.0173, "lr": 3.1993486444869823e-07, "epoch": 19.08264033264033, "percentage": 95.41, "elapsed_time": "1:46:47", "remaining_time": "0:05:08", "throughput": 1031.87, "total_tokens": 6611824} {"current_steps": 73435, "total_steps": 76960, "loss": 0.0116, "lr": 3.190313622634333e-07, "epoch": 19.08393970893971, "percentage": 95.42, "elapsed_time": "1:46:48", "remaining_time": "0:05:07", "throughput": 1031.87, "total_tokens": 6612256} {"current_steps": 73440, "total_steps": 76960, "loss": 0.1345, "lr": 3.1812912944403915e-07, "epoch": 19.085239085239085, "percentage": 95.43, "elapsed_time": "1:46:48", "remaining_time": "0:05:07", "throughput": 1031.88, "total_tokens": 6612704} {"current_steps": 73445, "total_steps": 76960, "loss": 0.0006, "lr": 3.172281660369092e-07, "epoch": 19.08653846153846, "percentage": 95.43, "elapsed_time": "1:46:48", "remaining_time": "0:05:06", "throughput": 1031.88, "total_tokens": 6613152} {"current_steps": 73450, "total_steps": 76960, "loss": 0.3105, "lr": 3.163284720883841e-07, "epoch": 19.08783783783784, "percentage": 95.44, "elapsed_time": "1:46:49", "remaining_time": "0:05:06", "throughput": 1031.89, "total_tokens": 6613616} {"current_steps": 73455, "total_steps": 76960, "loss": 0.0005, "lr": 3.1543004764473805e-07, "epoch": 19.089137214137214, "percentage": 95.45, "elapsed_time": "1:46:49", "remaining_time": "0:05:05", "throughput": 1031.89, "total_tokens": 6614080} {"current_steps": 73460, "total_steps": 76960, "loss": 0.0759, "lr": 3.145328927521757e-07, "epoch": 19.09043659043659, "percentage": 95.45, "elapsed_time": "1:46:50", "remaining_time": "0:05:05", "throughput": 1031.9, "total_tokens": 6614560} {"current_steps": 73465, "total_steps": 76960, "loss": 0.1129, "lr": 3.1363700745684065e-07, "epoch": 19.091735966735968, "percentage": 95.46, "elapsed_time": "1:46:50", "remaining_time": "0:05:04", "throughput": 1031.9, "total_tokens": 6615008} {"current_steps": 73470, "total_steps": 76960, "loss": 0.2572, "lr": 3.1274239180480446e-07, "epoch": 19.093035343035343, "percentage": 95.47, "elapsed_time": "1:46:50", "remaining_time": "0:05:04", "throughput": 1031.9, "total_tokens": 6615440} {"current_steps": 73475, "total_steps": 76960, "loss": 0.3657, "lr": 3.1184904584208586e-07, "epoch": 19.094334719334718, "percentage": 95.47, "elapsed_time": "1:46:51", "remaining_time": "0:05:04", "throughput": 1031.91, "total_tokens": 6615888} {"current_steps": 73480, "total_steps": 76960, "loss": 0.2061, "lr": 3.109569696146231e-07, "epoch": 19.095634095634097, "percentage": 95.48, "elapsed_time": "1:46:51", "remaining_time": "0:05:03", "throughput": 1031.91, "total_tokens": 6616352} {"current_steps": 73485, "total_steps": 76960, "loss": 0.0186, "lr": 3.1006616316829886e-07, "epoch": 19.096933471933472, "percentage": 95.48, "elapsed_time": "1:46:52", "remaining_time": "0:05:03", "throughput": 1031.91, "total_tokens": 6616784} {"current_steps": 73490, "total_steps": 76960, "loss": 0.1593, "lr": 3.0917662654892654e-07, "epoch": 19.098232848232847, "percentage": 95.49, "elapsed_time": "1:46:52", "remaining_time": "0:05:02", "throughput": 1031.92, "total_tokens": 6617248} {"current_steps": 73495, "total_steps": 76960, "loss": 0.0017, "lr": 3.082883598022612e-07, "epoch": 19.099532224532226, "percentage": 95.5, "elapsed_time": "1:46:52", "remaining_time": "0:05:02", "throughput": 1031.93, "total_tokens": 6617728} {"current_steps": 73500, "total_steps": 76960, "loss": 0.0014, "lr": 3.0740136297398305e-07, "epoch": 19.1008316008316, "percentage": 95.5, "elapsed_time": "1:46:53", "remaining_time": "0:05:01", "throughput": 1031.93, "total_tokens": 6618192} {"current_steps": 73505, "total_steps": 76960, "loss": 0.0014, "lr": 3.065156361097138e-07, "epoch": 19.102130977130976, "percentage": 95.51, "elapsed_time": "1:46:53", "remaining_time": "0:05:01", "throughput": 1031.93, "total_tokens": 6618624} {"current_steps": 73510, "total_steps": 76960, "loss": 0.2685, "lr": 3.0563117925500595e-07, "epoch": 19.103430353430355, "percentage": 95.52, "elapsed_time": "1:46:54", "remaining_time": "0:05:01", "throughput": 1031.93, "total_tokens": 6619056} {"current_steps": 73515, "total_steps": 76960, "loss": 0.0198, "lr": 3.0474799245534537e-07, "epoch": 19.10472972972973, "percentage": 95.52, "elapsed_time": "1:46:54", "remaining_time": "0:05:00", "throughput": 1031.93, "total_tokens": 6619488} {"current_steps": 73520, "total_steps": 76960, "loss": 0.0005, "lr": 3.038660757561568e-07, "epoch": 19.106029106029105, "percentage": 95.53, "elapsed_time": "1:46:55", "remaining_time": "0:05:00", "throughput": 1031.94, "total_tokens": 6619968} {"current_steps": 73525, "total_steps": 76960, "loss": 0.0239, "lr": 3.0298542920279835e-07, "epoch": 19.107328482328484, "percentage": 95.54, "elapsed_time": "1:46:55", "remaining_time": "0:04:59", "throughput": 1031.94, "total_tokens": 6620400} {"current_steps": 73530, "total_steps": 76960, "loss": 0.0039, "lr": 3.021060528405645e-07, "epoch": 19.10862785862786, "percentage": 95.54, "elapsed_time": "1:46:55", "remaining_time": "0:04:59", "throughput": 1031.94, "total_tokens": 6620848} {"current_steps": 73535, "total_steps": 76960, "loss": 0.1192, "lr": 3.0122794671468004e-07, "epoch": 19.109927234927234, "percentage": 95.55, "elapsed_time": "1:46:56", "remaining_time": "0:04:58", "throughput": 1031.94, "total_tokens": 6621280} {"current_steps": 73540, "total_steps": 76960, "loss": 0.0001, "lr": 3.0035111087030885e-07, "epoch": 19.111226611226613, "percentage": 95.56, "elapsed_time": "1:46:56", "remaining_time": "0:04:58", "throughput": 1031.95, "total_tokens": 6621760} {"current_steps": 73545, "total_steps": 76960, "loss": 0.0063, "lr": 2.9947554535254275e-07, "epoch": 19.112525987525988, "percentage": 95.56, "elapsed_time": "1:46:57", "remaining_time": "0:04:57", "throughput": 1031.95, "total_tokens": 6622192} {"current_steps": 73550, "total_steps": 76960, "loss": 0.0938, "lr": 2.9860125020642063e-07, "epoch": 19.113825363825363, "percentage": 95.57, "elapsed_time": "1:46:57", "remaining_time": "0:04:57", "throughput": 1031.95, "total_tokens": 6622624} {"current_steps": 73555, "total_steps": 76960, "loss": 0.0062, "lr": 2.977282254769009e-07, "epoch": 19.11512474012474, "percentage": 95.58, "elapsed_time": "1:46:57", "remaining_time": "0:04:57", "throughput": 1031.95, "total_tokens": 6623072} {"current_steps": 73560, "total_steps": 76960, "loss": 0.2992, "lr": 2.968564712088867e-07, "epoch": 19.116424116424117, "percentage": 95.58, "elapsed_time": "1:46:58", "remaining_time": "0:04:56", "throughput": 1031.95, "total_tokens": 6623488} {"current_steps": 73565, "total_steps": 76960, "loss": 0.3634, "lr": 2.959859874472143e-07, "epoch": 19.117723492723492, "percentage": 95.59, "elapsed_time": "1:46:58", "remaining_time": "0:04:56", "throughput": 1031.96, "total_tokens": 6623952} {"current_steps": 73570, "total_steps": 76960, "loss": 0.0005, "lr": 2.951167742366534e-07, "epoch": 19.11902286902287, "percentage": 95.6, "elapsed_time": "1:46:59", "remaining_time": "0:04:55", "throughput": 1031.96, "total_tokens": 6624416} {"current_steps": 73575, "total_steps": 76960, "loss": 0.0006, "lr": 2.9424883162191e-07, "epoch": 19.120322245322246, "percentage": 95.6, "elapsed_time": "1:46:59", "remaining_time": "0:04:55", "throughput": 1031.96, "total_tokens": 6624848} {"current_steps": 73580, "total_steps": 76960, "loss": 0.0194, "lr": 2.933821596476177e-07, "epoch": 19.12162162162162, "percentage": 95.61, "elapsed_time": "1:47:00", "remaining_time": "0:04:54", "throughput": 1031.96, "total_tokens": 6625280} {"current_steps": 73585, "total_steps": 76960, "loss": 0.0308, "lr": 2.925167583583577e-07, "epoch": 19.122920997920996, "percentage": 95.61, "elapsed_time": "1:47:00", "remaining_time": "0:04:54", "throughput": 1031.96, "total_tokens": 6625696} {"current_steps": 73590, "total_steps": 76960, "loss": 0.1281, "lr": 2.9165262779863036e-07, "epoch": 19.124220374220375, "percentage": 95.62, "elapsed_time": "1:47:00", "remaining_time": "0:04:54", "throughput": 1031.96, "total_tokens": 6626112} {"current_steps": 73595, "total_steps": 76960, "loss": 0.0815, "lr": 2.907897680128835e-07, "epoch": 19.12551975051975, "percentage": 95.63, "elapsed_time": "1:47:01", "remaining_time": "0:04:53", "throughput": 1031.96, "total_tokens": 6626528} {"current_steps": 73600, "total_steps": 76960, "loss": 0.1224, "lr": 2.899281790454927e-07, "epoch": 19.126819126819125, "percentage": 95.63, "elapsed_time": "1:47:01", "remaining_time": "0:04:53", "throughput": 1031.96, "total_tokens": 6626976} {"current_steps": 73605, "total_steps": 76960, "loss": 0.0003, "lr": 2.890678609407754e-07, "epoch": 19.128118503118504, "percentage": 95.64, "elapsed_time": "1:47:02", "remaining_time": "0:04:52", "throughput": 1031.97, "total_tokens": 6627440} {"current_steps": 73610, "total_steps": 76960, "loss": 0.0971, "lr": 2.8820881374297113e-07, "epoch": 19.12941787941788, "percentage": 95.65, "elapsed_time": "1:47:02", "remaining_time": "0:04:52", "throughput": 1031.97, "total_tokens": 6627872} {"current_steps": 73615, "total_steps": 76960, "loss": 0.0007, "lr": 2.8735103749626955e-07, "epoch": 19.130717255717254, "percentage": 95.65, "elapsed_time": "1:47:02", "remaining_time": "0:04:51", "throughput": 1031.98, "total_tokens": 6628368} {"current_steps": 73620, "total_steps": 76960, "loss": 0.0004, "lr": 2.8649453224477986e-07, "epoch": 19.132016632016633, "percentage": 95.66, "elapsed_time": "1:47:03", "remaining_time": "0:04:51", "throughput": 1031.98, "total_tokens": 6628848} {"current_steps": 73625, "total_steps": 76960, "loss": 0.5107, "lr": 2.856392980325556e-07, "epoch": 19.133316008316008, "percentage": 95.67, "elapsed_time": "1:47:03", "remaining_time": "0:04:50", "throughput": 1031.98, "total_tokens": 6629280} {"current_steps": 73630, "total_steps": 76960, "loss": 0.0039, "lr": 2.8478533490358395e-07, "epoch": 19.134615384615383, "percentage": 95.67, "elapsed_time": "1:47:04", "remaining_time": "0:04:50", "throughput": 1032.0, "total_tokens": 6629792} {"current_steps": 73635, "total_steps": 76960, "loss": 0.0057, "lr": 2.8393264290178243e-07, "epoch": 19.135914760914762, "percentage": 95.68, "elapsed_time": "1:47:04", "remaining_time": "0:04:50", "throughput": 1032.0, "total_tokens": 6630240} {"current_steps": 73640, "total_steps": 76960, "loss": 0.0065, "lr": 2.8308122207100773e-07, "epoch": 19.137214137214137, "percentage": 95.69, "elapsed_time": "1:47:05", "remaining_time": "0:04:49", "throughput": 1032.0, "total_tokens": 6630688} {"current_steps": 73645, "total_steps": 76960, "loss": 0.1871, "lr": 2.82231072455047e-07, "epoch": 19.138513513513512, "percentage": 95.69, "elapsed_time": "1:47:05", "remaining_time": "0:04:49", "throughput": 1032.01, "total_tokens": 6631136} {"current_steps": 73650, "total_steps": 76960, "loss": 0.1032, "lr": 2.8138219409762633e-07, "epoch": 19.13981288981289, "percentage": 95.7, "elapsed_time": "1:47:05", "remaining_time": "0:04:48", "throughput": 1032.0, "total_tokens": 6631552} {"current_steps": 73655, "total_steps": 76960, "loss": 0.0162, "lr": 2.805345870424025e-07, "epoch": 19.141112266112266, "percentage": 95.71, "elapsed_time": "1:47:06", "remaining_time": "0:04:48", "throughput": 1032.0, "total_tokens": 6631984} {"current_steps": 73660, "total_steps": 76960, "loss": 0.0685, "lr": 2.796882513329713e-07, "epoch": 19.14241164241164, "percentage": 95.71, "elapsed_time": "1:47:06", "remaining_time": "0:04:47", "throughput": 1032.01, "total_tokens": 6632432} {"current_steps": 73665, "total_steps": 76960, "loss": 0.0066, "lr": 2.7884318701285885e-07, "epoch": 19.14371101871102, "percentage": 95.72, "elapsed_time": "1:47:07", "remaining_time": "0:04:47", "throughput": 1032.01, "total_tokens": 6632864} {"current_steps": 73670, "total_steps": 76960, "loss": 0.2459, "lr": 2.779993941255277e-07, "epoch": 19.145010395010395, "percentage": 95.73, "elapsed_time": "1:47:07", "remaining_time": "0:04:47", "throughput": 1032.01, "total_tokens": 6633296} {"current_steps": 73675, "total_steps": 76960, "loss": 0.0173, "lr": 2.771568727143736e-07, "epoch": 19.14630977130977, "percentage": 95.73, "elapsed_time": "1:47:07", "remaining_time": "0:04:46", "throughput": 1032.01, "total_tokens": 6633760} {"current_steps": 73680, "total_steps": 76960, "loss": 0.0003, "lr": 2.7631562282273425e-07, "epoch": 19.14760914760915, "percentage": 95.74, "elapsed_time": "1:47:08", "remaining_time": "0:04:46", "throughput": 1032.03, "total_tokens": 6634272} {"current_steps": 73685, "total_steps": 76960, "loss": 0.2333, "lr": 2.7547564449386664e-07, "epoch": 19.148908523908524, "percentage": 95.74, "elapsed_time": "1:47:08", "remaining_time": "0:04:45", "throughput": 1032.03, "total_tokens": 6634704} {"current_steps": 73690, "total_steps": 76960, "loss": 0.0026, "lr": 2.7463693777098065e-07, "epoch": 19.1502079002079, "percentage": 95.75, "elapsed_time": "1:47:09", "remaining_time": "0:04:45", "throughput": 1032.04, "total_tokens": 6635232} {"current_steps": 73695, "total_steps": 76960, "loss": 0.0221, "lr": 2.7379950269720565e-07, "epoch": 19.151507276507278, "percentage": 95.76, "elapsed_time": "1:47:09", "remaining_time": "0:04:44", "throughput": 1032.04, "total_tokens": 6635648} {"current_steps": 73700, "total_steps": 76960, "loss": 0.0022, "lr": 2.729633393156128e-07, "epoch": 19.152806652806653, "percentage": 95.76, "elapsed_time": "1:47:10", "remaining_time": "0:04:44", "throughput": 1032.04, "total_tokens": 6636096} {"current_steps": 73705, "total_steps": 76960, "loss": 0.0086, "lr": 2.721284476692093e-07, "epoch": 19.15410602910603, "percentage": 95.77, "elapsed_time": "1:47:10", "remaining_time": "0:04:43", "throughput": 1032.05, "total_tokens": 6636576} {"current_steps": 73710, "total_steps": 76960, "loss": 0.0395, "lr": 2.7129482780093305e-07, "epoch": 19.155405405405407, "percentage": 95.78, "elapsed_time": "1:47:10", "remaining_time": "0:04:43", "throughput": 1032.05, "total_tokens": 6637024} {"current_steps": 73715, "total_steps": 76960, "loss": 0.022, "lr": 2.7046247975365815e-07, "epoch": 19.156704781704782, "percentage": 95.78, "elapsed_time": "1:47:11", "remaining_time": "0:04:43", "throughput": 1032.06, "total_tokens": 6637472} {"current_steps": 73720, "total_steps": 76960, "loss": 0.1497, "lr": 2.6963140357018914e-07, "epoch": 19.158004158004157, "percentage": 95.79, "elapsed_time": "1:47:11", "remaining_time": "0:04:42", "throughput": 1032.06, "total_tokens": 6637904} {"current_steps": 73725, "total_steps": 76960, "loss": 0.2852, "lr": 2.6880159929327796e-07, "epoch": 19.159303534303536, "percentage": 95.8, "elapsed_time": "1:47:12", "remaining_time": "0:04:42", "throughput": 1032.06, "total_tokens": 6638384} {"current_steps": 73730, "total_steps": 76960, "loss": 0.094, "lr": 2.679730669655933e-07, "epoch": 19.16060291060291, "percentage": 95.8, "elapsed_time": "1:47:12", "remaining_time": "0:04:41", "throughput": 1032.07, "total_tokens": 6638848} {"current_steps": 73735, "total_steps": 76960, "loss": 0.0205, "lr": 2.671458066297511e-07, "epoch": 19.161902286902286, "percentage": 95.81, "elapsed_time": "1:47:12", "remaining_time": "0:04:41", "throughput": 1032.07, "total_tokens": 6639296} {"current_steps": 73740, "total_steps": 76960, "loss": 0.0113, "lr": 2.66319818328295e-07, "epoch": 19.16320166320166, "percentage": 95.82, "elapsed_time": "1:47:13", "remaining_time": "0:04:40", "throughput": 1032.08, "total_tokens": 6639760} {"current_steps": 73745, "total_steps": 76960, "loss": 0.0069, "lr": 2.6549510210371607e-07, "epoch": 19.16450103950104, "percentage": 95.82, "elapsed_time": "1:47:13", "remaining_time": "0:04:40", "throughput": 1032.08, "total_tokens": 6640192} {"current_steps": 73750, "total_steps": 76960, "loss": 0.0141, "lr": 2.646716579984193e-07, "epoch": 19.165800415800415, "percentage": 95.83, "elapsed_time": "1:47:14", "remaining_time": "0:04:40", "throughput": 1032.08, "total_tokens": 6640656} {"current_steps": 73755, "total_steps": 76960, "loss": 0.004, "lr": 2.638494860547597e-07, "epoch": 19.16709979209979, "percentage": 95.84, "elapsed_time": "1:47:14", "remaining_time": "0:04:39", "throughput": 1032.09, "total_tokens": 6641104} {"current_steps": 73760, "total_steps": 76960, "loss": 0.0015, "lr": 2.6302858631502283e-07, "epoch": 19.16839916839917, "percentage": 95.84, "elapsed_time": "1:47:15", "remaining_time": "0:04:39", "throughput": 1032.09, "total_tokens": 6641536} {"current_steps": 73765, "total_steps": 76960, "loss": 0.0195, "lr": 2.622089588214277e-07, "epoch": 19.169698544698544, "percentage": 95.85, "elapsed_time": "1:47:15", "remaining_time": "0:04:38", "throughput": 1032.09, "total_tokens": 6642000} {"current_steps": 73770, "total_steps": 76960, "loss": 0.1285, "lr": 2.613906036161268e-07, "epoch": 19.17099792099792, "percentage": 95.85, "elapsed_time": "1:47:15", "remaining_time": "0:04:38", "throughput": 1032.1, "total_tokens": 6642480} {"current_steps": 73775, "total_steps": 76960, "loss": 0.1825, "lr": 2.6057352074121134e-07, "epoch": 19.1722972972973, "percentage": 95.86, "elapsed_time": "1:47:16", "remaining_time": "0:04:37", "throughput": 1032.1, "total_tokens": 6642912} {"current_steps": 73780, "total_steps": 76960, "loss": 0.055, "lr": 2.597577102387061e-07, "epoch": 19.173596673596673, "percentage": 95.87, "elapsed_time": "1:47:16", "remaining_time": "0:04:37", "throughput": 1032.1, "total_tokens": 6643344} {"current_steps": 73785, "total_steps": 76960, "loss": 0.0002, "lr": 2.5894317215056363e-07, "epoch": 19.17489604989605, "percentage": 95.87, "elapsed_time": "1:47:17", "remaining_time": "0:04:36", "throughput": 1032.1, "total_tokens": 6643776} {"current_steps": 73790, "total_steps": 76960, "loss": 0.3333, "lr": 2.5812990651868097e-07, "epoch": 19.176195426195427, "percentage": 95.88, "elapsed_time": "1:47:17", "remaining_time": "0:04:36", "throughput": 1032.1, "total_tokens": 6644208} {"current_steps": 73795, "total_steps": 76960, "loss": 0.2218, "lr": 2.5731791338488296e-07, "epoch": 19.177494802494802, "percentage": 95.89, "elapsed_time": "1:47:17", "remaining_time": "0:04:36", "throughput": 1032.1, "total_tokens": 6644640} {"current_steps": 73800, "total_steps": 76960, "loss": 0.0042, "lr": 2.5650719279093347e-07, "epoch": 19.178794178794178, "percentage": 95.89, "elapsed_time": "1:47:18", "remaining_time": "0:04:35", "throughput": 1032.1, "total_tokens": 6645056} {"current_steps": 73805, "total_steps": 76960, "loss": 0.2077, "lr": 2.5569774477852695e-07, "epoch": 19.180093555093556, "percentage": 95.9, "elapsed_time": "1:47:18", "remaining_time": "0:04:35", "throughput": 1032.1, "total_tokens": 6645504} {"current_steps": 73810, "total_steps": 76960, "loss": 0.1037, "lr": 2.548895693892911e-07, "epoch": 19.18139293139293, "percentage": 95.91, "elapsed_time": "1:47:19", "remaining_time": "0:04:34", "throughput": 1032.1, "total_tokens": 6645952} {"current_steps": 73815, "total_steps": 76960, "loss": 0.012, "lr": 2.540826666647955e-07, "epoch": 19.182692307692307, "percentage": 95.91, "elapsed_time": "1:47:19", "remaining_time": "0:04:34", "throughput": 1032.11, "total_tokens": 6646400} {"current_steps": 73820, "total_steps": 76960, "loss": 0.3664, "lr": 2.532770366465431e-07, "epoch": 19.183991683991685, "percentage": 95.92, "elapsed_time": "1:47:20", "remaining_time": "0:04:33", "throughput": 1032.11, "total_tokens": 6646864} {"current_steps": 73825, "total_steps": 76960, "loss": 0.3938, "lr": 2.524726793759591e-07, "epoch": 19.18529106029106, "percentage": 95.93, "elapsed_time": "1:47:20", "remaining_time": "0:04:33", "throughput": 1032.11, "total_tokens": 6647296} {"current_steps": 73830, "total_steps": 76960, "loss": 0.0023, "lr": 2.5166959489441866e-07, "epoch": 19.186590436590436, "percentage": 95.93, "elapsed_time": "1:47:20", "remaining_time": "0:04:33", "throughput": 1032.11, "total_tokens": 6647696} {"current_steps": 73835, "total_steps": 76960, "loss": 0.0016, "lr": 2.508677832432249e-07, "epoch": 19.187889812889814, "percentage": 95.94, "elapsed_time": "1:47:21", "remaining_time": "0:04:32", "throughput": 1032.11, "total_tokens": 6648144} {"current_steps": 73840, "total_steps": 76960, "loss": 0.0002, "lr": 2.500672444636143e-07, "epoch": 19.18918918918919, "percentage": 95.95, "elapsed_time": "1:47:21", "remaining_time": "0:04:32", "throughput": 1032.11, "total_tokens": 6648576} {"current_steps": 73845, "total_steps": 76960, "loss": 0.2185, "lr": 2.4926797859675666e-07, "epoch": 19.190488565488565, "percentage": 95.95, "elapsed_time": "1:47:22", "remaining_time": "0:04:31", "throughput": 1032.11, "total_tokens": 6648992} {"current_steps": 73850, "total_steps": 76960, "loss": 0.025, "lr": 2.484699856837636e-07, "epoch": 19.191787941787943, "percentage": 95.96, "elapsed_time": "1:47:22", "remaining_time": "0:04:31", "throughput": 1032.11, "total_tokens": 6649408} {"current_steps": 73855, "total_steps": 76960, "loss": 0.0157, "lr": 2.4767326576567716e-07, "epoch": 19.19308731808732, "percentage": 95.97, "elapsed_time": "1:47:22", "remaining_time": "0:04:30", "throughput": 1032.11, "total_tokens": 6649856} {"current_steps": 73860, "total_steps": 76960, "loss": 0.0006, "lr": 2.468778188834675e-07, "epoch": 19.194386694386694, "percentage": 95.97, "elapsed_time": "1:47:23", "remaining_time": "0:04:30", "throughput": 1032.12, "total_tokens": 6650352} {"current_steps": 73865, "total_steps": 76960, "loss": 0.0015, "lr": 2.4608364507805184e-07, "epoch": 19.195686070686072, "percentage": 95.98, "elapsed_time": "1:47:23", "remaining_time": "0:04:30", "throughput": 1032.12, "total_tokens": 6650800} {"current_steps": 73870, "total_steps": 76960, "loss": 0.0181, "lr": 2.4529074439027244e-07, "epoch": 19.196985446985448, "percentage": 95.98, "elapsed_time": "1:47:24", "remaining_time": "0:04:29", "throughput": 1032.12, "total_tokens": 6651232} {"current_steps": 73875, "total_steps": 76960, "loss": 0.0019, "lr": 2.444991168609079e-07, "epoch": 19.198284823284823, "percentage": 95.99, "elapsed_time": "1:47:24", "remaining_time": "0:04:29", "throughput": 1032.13, "total_tokens": 6651728} {"current_steps": 73880, "total_steps": 76960, "loss": 0.042, "lr": 2.4370876253067277e-07, "epoch": 19.1995841995842, "percentage": 96.0, "elapsed_time": "1:47:25", "remaining_time": "0:04:28", "throughput": 1032.14, "total_tokens": 6652176} {"current_steps": 73885, "total_steps": 76960, "loss": 0.0008, "lr": 2.4291968144021516e-07, "epoch": 19.200883575883577, "percentage": 96.0, "elapsed_time": "1:47:25", "remaining_time": "0:04:28", "throughput": 1032.15, "total_tokens": 6652704} {"current_steps": 73890, "total_steps": 76960, "loss": 0.0331, "lr": 2.421318736301192e-07, "epoch": 19.20218295218295, "percentage": 96.01, "elapsed_time": "1:47:25", "remaining_time": "0:04:27", "throughput": 1032.15, "total_tokens": 6653136} {"current_steps": 73895, "total_steps": 76960, "loss": 0.0144, "lr": 2.4134533914090817e-07, "epoch": 19.203482328482327, "percentage": 96.02, "elapsed_time": "1:47:26", "remaining_time": "0:04:27", "throughput": 1032.15, "total_tokens": 6653552} {"current_steps": 73900, "total_steps": 76960, "loss": 0.0006, "lr": 2.405600780130246e-07, "epoch": 19.204781704781706, "percentage": 96.02, "elapsed_time": "1:47:26", "remaining_time": "0:04:26", "throughput": 1032.15, "total_tokens": 6654000} {"current_steps": 73905, "total_steps": 76960, "loss": 0.0837, "lr": 2.397760902868612e-07, "epoch": 19.20608108108108, "percentage": 96.03, "elapsed_time": "1:47:27", "remaining_time": "0:04:26", "throughput": 1032.15, "total_tokens": 6654416} {"current_steps": 73910, "total_steps": 76960, "loss": 0.0014, "lr": 2.3899337600273577e-07, "epoch": 19.207380457380456, "percentage": 96.04, "elapsed_time": "1:47:27", "remaining_time": "0:04:26", "throughput": 1032.15, "total_tokens": 6654864} {"current_steps": 73915, "total_steps": 76960, "loss": 0.0012, "lr": 2.382119352009049e-07, "epoch": 19.208679833679835, "percentage": 96.04, "elapsed_time": "1:47:27", "remaining_time": "0:04:25", "throughput": 1032.16, "total_tokens": 6655312} {"current_steps": 73920, "total_steps": 76960, "loss": 0.0303, "lr": 2.374317679215643e-07, "epoch": 19.20997920997921, "percentage": 96.05, "elapsed_time": "1:47:28", "remaining_time": "0:04:25", "throughput": 1032.16, "total_tokens": 6655744} {"current_steps": 73925, "total_steps": 76960, "loss": 0.0006, "lr": 2.3665287420482907e-07, "epoch": 19.211278586278585, "percentage": 96.06, "elapsed_time": "1:47:28", "remaining_time": "0:04:24", "throughput": 1032.16, "total_tokens": 6656208} {"current_steps": 73930, "total_steps": 76960, "loss": 0.0093, "lr": 2.3587525409076716e-07, "epoch": 19.212577962577964, "percentage": 96.06, "elapsed_time": "1:47:29", "remaining_time": "0:04:24", "throughput": 1032.17, "total_tokens": 6656672} {"current_steps": 73935, "total_steps": 76960, "loss": 0.0003, "lr": 2.3509890761936882e-07, "epoch": 19.21387733887734, "percentage": 96.07, "elapsed_time": "1:47:29", "remaining_time": "0:04:23", "throughput": 1032.17, "total_tokens": 6657104} {"current_steps": 73940, "total_steps": 76960, "loss": 0.0003, "lr": 2.3432383483056041e-07, "epoch": 19.215176715176714, "percentage": 96.08, "elapsed_time": "1:47:30", "remaining_time": "0:04:23", "throughput": 1032.17, "total_tokens": 6657552} {"current_steps": 73945, "total_steps": 76960, "loss": 0.0941, "lr": 2.335500357642073e-07, "epoch": 19.216476091476093, "percentage": 96.08, "elapsed_time": "1:47:30", "remaining_time": "0:04:23", "throughput": 1032.18, "total_tokens": 6658016} {"current_steps": 73950, "total_steps": 76960, "loss": 0.0949, "lr": 2.3277751046010543e-07, "epoch": 19.217775467775468, "percentage": 96.09, "elapsed_time": "1:47:30", "remaining_time": "0:04:22", "throughput": 1032.18, "total_tokens": 6658464} {"current_steps": 73955, "total_steps": 76960, "loss": 0.3579, "lr": 2.3200625895798688e-07, "epoch": 19.219074844074843, "percentage": 96.1, "elapsed_time": "1:47:31", "remaining_time": "0:04:22", "throughput": 1032.18, "total_tokens": 6658912} {"current_steps": 73960, "total_steps": 76960, "loss": 0.0003, "lr": 2.3123628129751996e-07, "epoch": 19.22037422037422, "percentage": 96.1, "elapsed_time": "1:47:31", "remaining_time": "0:04:21", "throughput": 1032.19, "total_tokens": 6659392} {"current_steps": 73965, "total_steps": 76960, "loss": 0.3203, "lr": 2.3046757751830073e-07, "epoch": 19.221673596673597, "percentage": 96.11, "elapsed_time": "1:47:32", "remaining_time": "0:04:21", "throughput": 1032.19, "total_tokens": 6659840} {"current_steps": 73970, "total_steps": 76960, "loss": 0.0054, "lr": 2.297001476598698e-07, "epoch": 19.222972972972972, "percentage": 96.11, "elapsed_time": "1:47:32", "remaining_time": "0:04:20", "throughput": 1032.19, "total_tokens": 6660256} {"current_steps": 73975, "total_steps": 76960, "loss": 0.1865, "lr": 2.2893399176169284e-07, "epoch": 19.22427234927235, "percentage": 96.12, "elapsed_time": "1:47:32", "remaining_time": "0:04:20", "throughput": 1032.19, "total_tokens": 6660688} {"current_steps": 73980, "total_steps": 76960, "loss": 0.0002, "lr": 2.281691098631744e-07, "epoch": 19.225571725571726, "percentage": 96.13, "elapsed_time": "1:47:33", "remaining_time": "0:04:19", "throughput": 1032.19, "total_tokens": 6661136} {"current_steps": 73985, "total_steps": 76960, "loss": 0.0458, "lr": 2.274055020036553e-07, "epoch": 19.2268711018711, "percentage": 96.13, "elapsed_time": "1:47:33", "remaining_time": "0:04:19", "throughput": 1032.2, "total_tokens": 6661584} {"current_steps": 73990, "total_steps": 76960, "loss": 0.461, "lr": 2.2664316822240407e-07, "epoch": 19.22817047817048, "percentage": 96.14, "elapsed_time": "1:47:34", "remaining_time": "0:04:19", "throughput": 1032.2, "total_tokens": 6662032} {"current_steps": 73995, "total_steps": 76960, "loss": 0.4063, "lr": 2.258821085586338e-07, "epoch": 19.229469854469855, "percentage": 96.15, "elapsed_time": "1:47:34", "remaining_time": "0:04:18", "throughput": 1032.21, "total_tokens": 6662528} {"current_steps": 74000, "total_steps": 76960, "loss": 0.0015, "lr": 2.251223230514854e-07, "epoch": 19.23076923076923, "percentage": 96.15, "elapsed_time": "1:47:35", "remaining_time": "0:04:18", "throughput": 1032.22, "total_tokens": 6663024} {"current_steps": 74005, "total_steps": 76960, "loss": 0.0553, "lr": 2.243638117400332e-07, "epoch": 19.23206860706861, "percentage": 96.16, "elapsed_time": "1:47:35", "remaining_time": "0:04:17", "throughput": 1032.22, "total_tokens": 6663456} {"current_steps": 74010, "total_steps": 76960, "loss": 0.2757, "lr": 2.2360657466328761e-07, "epoch": 19.233367983367984, "percentage": 96.17, "elapsed_time": "1:47:35", "remaining_time": "0:04:17", "throughput": 1032.22, "total_tokens": 6663904} {"current_steps": 74015, "total_steps": 76960, "loss": 0.1017, "lr": 2.228506118601953e-07, "epoch": 19.23466735966736, "percentage": 96.17, "elapsed_time": "1:47:36", "remaining_time": "0:04:16", "throughput": 1032.22, "total_tokens": 6664320} {"current_steps": 74020, "total_steps": 76960, "loss": 0.0003, "lr": 2.2209592336963625e-07, "epoch": 19.235966735966738, "percentage": 96.18, "elapsed_time": "1:47:36", "remaining_time": "0:04:16", "throughput": 1032.22, "total_tokens": 6664736} {"current_steps": 74025, "total_steps": 76960, "loss": 0.0556, "lr": 2.2134250923042665e-07, "epoch": 19.237266112266113, "percentage": 96.19, "elapsed_time": "1:47:37", "remaining_time": "0:04:16", "throughput": 1032.21, "total_tokens": 6665152} {"current_steps": 74030, "total_steps": 76960, "loss": 0.0003, "lr": 2.205903694813133e-07, "epoch": 19.238565488565488, "percentage": 96.19, "elapsed_time": "1:47:37", "remaining_time": "0:04:15", "throughput": 1032.23, "total_tokens": 6665648} {"current_steps": 74035, "total_steps": 76960, "loss": 0.5437, "lr": 2.198395041609791e-07, "epoch": 19.239864864864863, "percentage": 96.2, "elapsed_time": "1:47:37", "remaining_time": "0:04:15", "throughput": 1032.23, "total_tokens": 6666096} {"current_steps": 74040, "total_steps": 76960, "loss": 0.0809, "lr": 2.1908991330804319e-07, "epoch": 19.241164241164242, "percentage": 96.21, "elapsed_time": "1:47:38", "remaining_time": "0:04:14", "throughput": 1032.23, "total_tokens": 6666512} {"current_steps": 74045, "total_steps": 76960, "loss": 0.1067, "lr": 2.1834159696105528e-07, "epoch": 19.242463617463617, "percentage": 96.21, "elapsed_time": "1:47:38", "remaining_time": "0:04:14", "throughput": 1032.23, "total_tokens": 6666992} {"current_steps": 74050, "total_steps": 76960, "loss": 0.0866, "lr": 2.175945551585068e-07, "epoch": 19.243762993762992, "percentage": 96.22, "elapsed_time": "1:47:39", "remaining_time": "0:04:13", "throughput": 1032.23, "total_tokens": 6667424} {"current_steps": 74055, "total_steps": 76960, "loss": 0.2138, "lr": 2.1684878793881146e-07, "epoch": 19.24506237006237, "percentage": 96.23, "elapsed_time": "1:47:39", "remaining_time": "0:04:13", "throughput": 1032.25, "total_tokens": 6667936} {"current_steps": 74060, "total_steps": 76960, "loss": 0.1322, "lr": 2.1610429534033027e-07, "epoch": 19.246361746361746, "percentage": 96.23, "elapsed_time": "1:47:40", "remaining_time": "0:04:12", "throughput": 1032.25, "total_tokens": 6668384} {"current_steps": 74065, "total_steps": 76960, "loss": 0.1325, "lr": 2.1536107740135482e-07, "epoch": 19.24766112266112, "percentage": 96.24, "elapsed_time": "1:47:40", "remaining_time": "0:04:12", "throughput": 1032.26, "total_tokens": 6668864} {"current_steps": 74070, "total_steps": 76960, "loss": 0.334, "lr": 2.1461913416010448e-07, "epoch": 19.2489604989605, "percentage": 96.24, "elapsed_time": "1:47:40", "remaining_time": "0:04:12", "throughput": 1032.26, "total_tokens": 6669328} {"current_steps": 74075, "total_steps": 76960, "loss": 0.3307, "lr": 2.1387846565474045e-07, "epoch": 19.250259875259875, "percentage": 96.25, "elapsed_time": "1:47:41", "remaining_time": "0:04:11", "throughput": 1032.27, "total_tokens": 6669776} {"current_steps": 74080, "total_steps": 76960, "loss": 0.2115, "lr": 2.1313907192335724e-07, "epoch": 19.25155925155925, "percentage": 96.26, "elapsed_time": "1:47:41", "remaining_time": "0:04:11", "throughput": 1032.27, "total_tokens": 6670256} {"current_steps": 74085, "total_steps": 76960, "loss": 0.0194, "lr": 2.1240095300397723e-07, "epoch": 19.25285862785863, "percentage": 96.26, "elapsed_time": "1:47:42", "remaining_time": "0:04:10", "throughput": 1032.28, "total_tokens": 6670704} {"current_steps": 74090, "total_steps": 76960, "loss": 0.0012, "lr": 2.1166410893457e-07, "epoch": 19.254158004158004, "percentage": 96.27, "elapsed_time": "1:47:42", "remaining_time": "0:04:10", "throughput": 1032.28, "total_tokens": 6671184} {"current_steps": 74095, "total_steps": 76960, "loss": 0.0327, "lr": 2.109285397530275e-07, "epoch": 19.25545738045738, "percentage": 96.28, "elapsed_time": "1:47:42", "remaining_time": "0:04:09", "throughput": 1032.28, "total_tokens": 6671584} {"current_steps": 74100, "total_steps": 76960, "loss": 0.4546, "lr": 2.1019424549718335e-07, "epoch": 19.256756756756758, "percentage": 96.28, "elapsed_time": "1:47:43", "remaining_time": "0:04:09", "throughput": 1032.28, "total_tokens": 6672016} {"current_steps": 74105, "total_steps": 76960, "loss": 0.0009, "lr": 2.09461226204799e-07, "epoch": 19.258056133056133, "percentage": 96.29, "elapsed_time": "1:47:43", "remaining_time": "0:04:09", "throughput": 1032.28, "total_tokens": 6672448} {"current_steps": 74110, "total_steps": 76960, "loss": 0.0022, "lr": 2.0872948191358045e-07, "epoch": 19.259355509355508, "percentage": 96.3, "elapsed_time": "1:47:44", "remaining_time": "0:04:08", "throughput": 1032.27, "total_tokens": 6672848} {"current_steps": 74115, "total_steps": 76960, "loss": 0.0004, "lr": 2.0799901266115585e-07, "epoch": 19.260654885654887, "percentage": 96.3, "elapsed_time": "1:47:44", "remaining_time": "0:04:08", "throughput": 1032.28, "total_tokens": 6673296} {"current_steps": 74120, "total_steps": 76960, "loss": 0.0009, "lr": 2.0726981848509797e-07, "epoch": 19.261954261954262, "percentage": 96.31, "elapsed_time": "1:47:45", "remaining_time": "0:04:07", "throughput": 1032.27, "total_tokens": 6673712} {"current_steps": 74125, "total_steps": 76960, "loss": 0.0146, "lr": 2.0654189942290735e-07, "epoch": 19.263253638253637, "percentage": 96.32, "elapsed_time": "1:47:45", "remaining_time": "0:04:07", "throughput": 1032.28, "total_tokens": 6674160} {"current_steps": 74130, "total_steps": 76960, "loss": 0.0035, "lr": 2.0581525551202352e-07, "epoch": 19.264553014553016, "percentage": 96.32, "elapsed_time": "1:47:45", "remaining_time": "0:04:06", "throughput": 1032.28, "total_tokens": 6674592} {"current_steps": 74135, "total_steps": 76960, "loss": 0.001, "lr": 2.0508988678981656e-07, "epoch": 19.26585239085239, "percentage": 96.33, "elapsed_time": "1:47:46", "remaining_time": "0:04:06", "throughput": 1032.28, "total_tokens": 6675008} {"current_steps": 74140, "total_steps": 76960, "loss": 0.0118, "lr": 2.043657932935955e-07, "epoch": 19.267151767151766, "percentage": 96.34, "elapsed_time": "1:47:46", "remaining_time": "0:04:05", "throughput": 1032.28, "total_tokens": 6675440} {"current_steps": 74145, "total_steps": 76960, "loss": 0.1041, "lr": 2.0364297506060003e-07, "epoch": 19.268451143451145, "percentage": 96.34, "elapsed_time": "1:47:47", "remaining_time": "0:04:05", "throughput": 1032.28, "total_tokens": 6675888} {"current_steps": 74150, "total_steps": 76960, "loss": 0.1016, "lr": 2.029214321280032e-07, "epoch": 19.26975051975052, "percentage": 96.35, "elapsed_time": "1:47:47", "remaining_time": "0:04:05", "throughput": 1032.28, "total_tokens": 6676320} {"current_steps": 74155, "total_steps": 76960, "loss": 0.0476, "lr": 2.0220116453291693e-07, "epoch": 19.271049896049895, "percentage": 96.36, "elapsed_time": "1:47:47", "remaining_time": "0:04:04", "throughput": 1032.28, "total_tokens": 6676752} {"current_steps": 74160, "total_steps": 76960, "loss": 0.005, "lr": 2.0148217231238664e-07, "epoch": 19.272349272349274, "percentage": 96.36, "elapsed_time": "1:47:48", "remaining_time": "0:04:04", "throughput": 1032.28, "total_tokens": 6677168} {"current_steps": 74165, "total_steps": 76960, "loss": 0.002, "lr": 2.007644555033855e-07, "epoch": 19.27364864864865, "percentage": 96.37, "elapsed_time": "1:47:48", "remaining_time": "0:04:03", "throughput": 1032.28, "total_tokens": 6677632} {"current_steps": 74170, "total_steps": 76960, "loss": 0.0021, "lr": 2.0004801414283402e-07, "epoch": 19.274948024948024, "percentage": 96.37, "elapsed_time": "1:47:49", "remaining_time": "0:04:03", "throughput": 1032.29, "total_tokens": 6678128} {"current_steps": 74175, "total_steps": 76960, "loss": 0.0198, "lr": 1.9933284826757216e-07, "epoch": 19.276247401247403, "percentage": 96.38, "elapsed_time": "1:47:49", "remaining_time": "0:04:02", "throughput": 1032.29, "total_tokens": 6678544} {"current_steps": 74180, "total_steps": 76960, "loss": 0.1247, "lr": 1.9861895791438712e-07, "epoch": 19.277546777546778, "percentage": 96.39, "elapsed_time": "1:47:50", "remaining_time": "0:04:02", "throughput": 1032.3, "total_tokens": 6679024} {"current_steps": 74185, "total_steps": 76960, "loss": 0.1756, "lr": 1.9790634311999124e-07, "epoch": 19.278846153846153, "percentage": 96.39, "elapsed_time": "1:47:50", "remaining_time": "0:04:02", "throughput": 1032.31, "total_tokens": 6679504} {"current_steps": 74190, "total_steps": 76960, "loss": 0.0008, "lr": 1.971950039210385e-07, "epoch": 19.28014553014553, "percentage": 96.4, "elapsed_time": "1:47:50", "remaining_time": "0:04:01", "throughput": 1032.31, "total_tokens": 6679936} {"current_steps": 74195, "total_steps": 76960, "loss": 0.0058, "lr": 1.964849403541108e-07, "epoch": 19.281444906444907, "percentage": 96.41, "elapsed_time": "1:47:51", "remaining_time": "0:04:01", "throughput": 1032.31, "total_tokens": 6680368} {"current_steps": 74200, "total_steps": 76960, "loss": 0.0004, "lr": 1.957761524557261e-07, "epoch": 19.282744282744282, "percentage": 96.41, "elapsed_time": "1:47:51", "remaining_time": "0:04:00", "throughput": 1032.31, "total_tokens": 6680800} {"current_steps": 74205, "total_steps": 76960, "loss": 0.0111, "lr": 1.950686402623414e-07, "epoch": 19.284043659043657, "percentage": 96.42, "elapsed_time": "1:47:52", "remaining_time": "0:04:00", "throughput": 1032.31, "total_tokens": 6681264} {"current_steps": 74210, "total_steps": 76960, "loss": 0.0569, "lr": 1.943624038103442e-07, "epoch": 19.285343035343036, "percentage": 96.43, "elapsed_time": "1:47:52", "remaining_time": "0:03:59", "throughput": 1032.31, "total_tokens": 6681696} {"current_steps": 74215, "total_steps": 76960, "loss": 0.3067, "lr": 1.936574431360555e-07, "epoch": 19.28664241164241, "percentage": 96.43, "elapsed_time": "1:47:52", "remaining_time": "0:03:59", "throughput": 1032.32, "total_tokens": 6682160} {"current_steps": 74220, "total_steps": 76960, "loss": 0.0071, "lr": 1.9295375827573238e-07, "epoch": 19.287941787941786, "percentage": 96.44, "elapsed_time": "1:47:53", "remaining_time": "0:03:58", "throughput": 1032.32, "total_tokens": 6682624} {"current_steps": 74225, "total_steps": 76960, "loss": 0.0448, "lr": 1.922513492655653e-07, "epoch": 19.289241164241165, "percentage": 96.45, "elapsed_time": "1:47:53", "remaining_time": "0:03:58", "throughput": 1032.33, "total_tokens": 6683088} {"current_steps": 74230, "total_steps": 76960, "loss": 0.1007, "lr": 1.915502161416838e-07, "epoch": 19.29054054054054, "percentage": 96.45, "elapsed_time": "1:47:54", "remaining_time": "0:03:58", "throughput": 1032.33, "total_tokens": 6683536} {"current_steps": 74235, "total_steps": 76960, "loss": 0.0237, "lr": 1.9085035894014224e-07, "epoch": 19.291839916839916, "percentage": 96.46, "elapsed_time": "1:47:54", "remaining_time": "0:03:57", "throughput": 1032.34, "total_tokens": 6684000} {"current_steps": 74240, "total_steps": 76960, "loss": 0.0399, "lr": 1.901517776969397e-07, "epoch": 19.293139293139294, "percentage": 96.47, "elapsed_time": "1:47:55", "remaining_time": "0:03:57", "throughput": 1032.34, "total_tokens": 6684432} {"current_steps": 74245, "total_steps": 76960, "loss": 0.0003, "lr": 1.8945447244800297e-07, "epoch": 19.29443866943867, "percentage": 96.47, "elapsed_time": "1:47:55", "remaining_time": "0:03:56", "throughput": 1032.33, "total_tokens": 6684848} {"current_steps": 74250, "total_steps": 76960, "loss": 0.2293, "lr": 1.88758443229195e-07, "epoch": 19.295738045738045, "percentage": 96.48, "elapsed_time": "1:47:55", "remaining_time": "0:03:56", "throughput": 1032.33, "total_tokens": 6685264} {"current_steps": 74255, "total_steps": 76960, "loss": 0.0084, "lr": 1.8806369007631219e-07, "epoch": 19.297037422037423, "percentage": 96.49, "elapsed_time": "1:47:56", "remaining_time": "0:03:55", "throughput": 1032.33, "total_tokens": 6685696} {"current_steps": 74260, "total_steps": 76960, "loss": 0.0008, "lr": 1.8737021302508707e-07, "epoch": 19.2983367983368, "percentage": 96.49, "elapsed_time": "1:47:56", "remaining_time": "0:03:55", "throughput": 1032.33, "total_tokens": 6686144} {"current_steps": 74265, "total_steps": 76960, "loss": 0.1665, "lr": 1.8667801211118828e-07, "epoch": 19.299636174636174, "percentage": 96.5, "elapsed_time": "1:47:57", "remaining_time": "0:03:55", "throughput": 1032.34, "total_tokens": 6686592} {"current_steps": 74270, "total_steps": 76960, "loss": 0.0186, "lr": 1.8598708737021243e-07, "epoch": 19.300935550935552, "percentage": 96.5, "elapsed_time": "1:47:57", "remaining_time": "0:03:54", "throughput": 1032.34, "total_tokens": 6687040} {"current_steps": 74275, "total_steps": 76960, "loss": 0.0271, "lr": 1.852974388376977e-07, "epoch": 19.302234927234927, "percentage": 96.51, "elapsed_time": "1:47:57", "remaining_time": "0:03:54", "throughput": 1032.34, "total_tokens": 6687472} {"current_steps": 74280, "total_steps": 76960, "loss": 0.0012, "lr": 1.8460906654911014e-07, "epoch": 19.303534303534303, "percentage": 96.52, "elapsed_time": "1:47:58", "remaining_time": "0:03:53", "throughput": 1032.35, "total_tokens": 6687936} {"current_steps": 74285, "total_steps": 76960, "loss": 0.1129, "lr": 1.839219705398576e-07, "epoch": 19.30483367983368, "percentage": 96.52, "elapsed_time": "1:47:58", "remaining_time": "0:03:53", "throughput": 1032.35, "total_tokens": 6688368} {"current_steps": 74290, "total_steps": 76960, "loss": 0.0132, "lr": 1.832361508452729e-07, "epoch": 19.306133056133056, "percentage": 96.53, "elapsed_time": "1:47:59", "remaining_time": "0:03:52", "throughput": 1032.35, "total_tokens": 6688816} {"current_steps": 74295, "total_steps": 76960, "loss": 0.0019, "lr": 1.8255160750063338e-07, "epoch": 19.30743243243243, "percentage": 96.54, "elapsed_time": "1:47:59", "remaining_time": "0:03:52", "throughput": 1032.35, "total_tokens": 6689264} {"current_steps": 74300, "total_steps": 76960, "loss": 0.0002, "lr": 1.8186834054114422e-07, "epoch": 19.30873180873181, "percentage": 96.54, "elapsed_time": "1:48:00", "remaining_time": "0:03:51", "throughput": 1032.35, "total_tokens": 6689696} {"current_steps": 74305, "total_steps": 76960, "loss": 0.1327, "lr": 1.8118635000194396e-07, "epoch": 19.310031185031185, "percentage": 96.55, "elapsed_time": "1:48:00", "remaining_time": "0:03:51", "throughput": 1032.35, "total_tokens": 6690128} {"current_steps": 74310, "total_steps": 76960, "loss": 0.0009, "lr": 1.805056359181101e-07, "epoch": 19.31133056133056, "percentage": 96.56, "elapsed_time": "1:48:00", "remaining_time": "0:03:51", "throughput": 1032.36, "total_tokens": 6690624} {"current_steps": 74315, "total_steps": 76960, "loss": 0.0003, "lr": 1.7982619832465353e-07, "epoch": 19.31262993762994, "percentage": 96.56, "elapsed_time": "1:48:01", "remaining_time": "0:03:50", "throughput": 1032.37, "total_tokens": 6691072} {"current_steps": 74320, "total_steps": 76960, "loss": 0.022, "lr": 1.7914803725651573e-07, "epoch": 19.313929313929314, "percentage": 96.57, "elapsed_time": "1:48:01", "remaining_time": "0:03:50", "throughput": 1032.38, "total_tokens": 6691568} {"current_steps": 74325, "total_steps": 76960, "loss": 0.1351, "lr": 1.7847115274857718e-07, "epoch": 19.31522869022869, "percentage": 96.58, "elapsed_time": "1:48:02", "remaining_time": "0:03:49", "throughput": 1032.38, "total_tokens": 6692016} {"current_steps": 74330, "total_steps": 76960, "loss": 0.0868, "lr": 1.7779554483565163e-07, "epoch": 19.316528066528065, "percentage": 96.58, "elapsed_time": "1:48:02", "remaining_time": "0:03:49", "throughput": 1032.38, "total_tokens": 6692448} {"current_steps": 74335, "total_steps": 76960, "loss": 0.1206, "lr": 1.7712121355248356e-07, "epoch": 19.317827442827443, "percentage": 96.59, "elapsed_time": "1:48:02", "remaining_time": "0:03:48", "throughput": 1032.38, "total_tokens": 6692896} {"current_steps": 74340, "total_steps": 76960, "loss": 0.2277, "lr": 1.7644815893375632e-07, "epoch": 19.31912681912682, "percentage": 96.6, "elapsed_time": "1:48:03", "remaining_time": "0:03:48", "throughput": 1032.38, "total_tokens": 6693328} {"current_steps": 74345, "total_steps": 76960, "loss": 0.2095, "lr": 1.7577638101408389e-07, "epoch": 19.320426195426194, "percentage": 96.6, "elapsed_time": "1:48:03", "remaining_time": "0:03:48", "throughput": 1032.39, "total_tokens": 6693792} {"current_steps": 74350, "total_steps": 76960, "loss": 0.23, "lr": 1.7510587982801641e-07, "epoch": 19.321725571725572, "percentage": 96.61, "elapsed_time": "1:48:04", "remaining_time": "0:03:47", "throughput": 1032.4, "total_tokens": 6694304} {"current_steps": 74355, "total_steps": 76960, "loss": 0.0002, "lr": 1.7443665541004016e-07, "epoch": 19.323024948024948, "percentage": 96.62, "elapsed_time": "1:48:04", "remaining_time": "0:03:47", "throughput": 1032.4, "total_tokens": 6694752} {"current_steps": 74360, "total_steps": 76960, "loss": 0.0021, "lr": 1.7376870779457487e-07, "epoch": 19.324324324324323, "percentage": 96.62, "elapsed_time": "1:48:05", "remaining_time": "0:03:46", "throughput": 1032.41, "total_tokens": 6695216} {"current_steps": 74365, "total_steps": 76960, "loss": 0.0093, "lr": 1.731020370159736e-07, "epoch": 19.3256237006237, "percentage": 96.63, "elapsed_time": "1:48:05", "remaining_time": "0:03:46", "throughput": 1032.41, "total_tokens": 6695664} {"current_steps": 74370, "total_steps": 76960, "loss": 0.0036, "lr": 1.7243664310852003e-07, "epoch": 19.326923076923077, "percentage": 96.63, "elapsed_time": "1:48:05", "remaining_time": "0:03:45", "throughput": 1032.41, "total_tokens": 6696112} {"current_steps": 74375, "total_steps": 76960, "loss": 0.0003, "lr": 1.7177252610643958e-07, "epoch": 19.328222453222452, "percentage": 96.64, "elapsed_time": "1:48:06", "remaining_time": "0:03:45", "throughput": 1032.42, "total_tokens": 6696576} {"current_steps": 74380, "total_steps": 76960, "loss": 0.0328, "lr": 1.7110968604388544e-07, "epoch": 19.32952182952183, "percentage": 96.65, "elapsed_time": "1:48:06", "remaining_time": "0:03:45", "throughput": 1032.42, "total_tokens": 6697024} {"current_steps": 74385, "total_steps": 76960, "loss": 0.1391, "lr": 1.704481229549526e-07, "epoch": 19.330821205821206, "percentage": 96.65, "elapsed_time": "1:48:07", "remaining_time": "0:03:44", "throughput": 1032.43, "total_tokens": 6697504} {"current_steps": 74390, "total_steps": 76960, "loss": 0.1668, "lr": 1.6978783687366107e-07, "epoch": 19.33212058212058, "percentage": 96.66, "elapsed_time": "1:48:07", "remaining_time": "0:03:44", "throughput": 1032.44, "total_tokens": 6698000} {"current_steps": 74395, "total_steps": 76960, "loss": 0.0037, "lr": 1.691288278339753e-07, "epoch": 19.33341995841996, "percentage": 96.67, "elapsed_time": "1:48:07", "remaining_time": "0:03:43", "throughput": 1032.44, "total_tokens": 6698432} {"current_steps": 74400, "total_steps": 76960, "loss": 0.0018, "lr": 1.6847109586978216e-07, "epoch": 19.334719334719335, "percentage": 96.67, "elapsed_time": "1:48:08", "remaining_time": "0:03:43", "throughput": 1032.45, "total_tokens": 6698896} {"current_steps": 74405, "total_steps": 76960, "loss": 0.0211, "lr": 1.678146410149156e-07, "epoch": 19.33601871101871, "percentage": 96.68, "elapsed_time": "1:48:08", "remaining_time": "0:03:42", "throughput": 1032.45, "total_tokens": 6699360} {"current_steps": 74410, "total_steps": 76960, "loss": 0.0525, "lr": 1.671594633031348e-07, "epoch": 19.33731808731809, "percentage": 96.69, "elapsed_time": "1:48:09", "remaining_time": "0:03:42", "throughput": 1032.45, "total_tokens": 6699808} {"current_steps": 74415, "total_steps": 76960, "loss": 0.0083, "lr": 1.66505562768135e-07, "epoch": 19.338617463617464, "percentage": 96.69, "elapsed_time": "1:48:09", "remaining_time": "0:03:41", "throughput": 1032.46, "total_tokens": 6700240} {"current_steps": 74420, "total_steps": 76960, "loss": 0.0005, "lr": 1.6585293944354762e-07, "epoch": 19.33991683991684, "percentage": 96.7, "elapsed_time": "1:48:10", "remaining_time": "0:03:41", "throughput": 1032.46, "total_tokens": 6700720} {"current_steps": 74425, "total_steps": 76960, "loss": 0.0007, "lr": 1.6520159336294306e-07, "epoch": 19.341216216216218, "percentage": 96.71, "elapsed_time": "1:48:10", "remaining_time": "0:03:41", "throughput": 1032.46, "total_tokens": 6701120} {"current_steps": 74430, "total_steps": 76960, "loss": 0.0014, "lr": 1.6455152455981392e-07, "epoch": 19.342515592515593, "percentage": 96.71, "elapsed_time": "1:48:10", "remaining_time": "0:03:40", "throughput": 1032.46, "total_tokens": 6701584} {"current_steps": 74435, "total_steps": 76960, "loss": 0.0038, "lr": 1.6390273306759463e-07, "epoch": 19.343814968814968, "percentage": 96.72, "elapsed_time": "1:48:11", "remaining_time": "0:03:40", "throughput": 1032.47, "total_tokens": 6702032} {"current_steps": 74440, "total_steps": 76960, "loss": 0.0569, "lr": 1.6325521891965568e-07, "epoch": 19.345114345114347, "percentage": 96.73, "elapsed_time": "1:48:11", "remaining_time": "0:03:39", "throughput": 1032.47, "total_tokens": 6702480} {"current_steps": 74445, "total_steps": 76960, "loss": 0.0012, "lr": 1.6260898214929542e-07, "epoch": 19.34641372141372, "percentage": 96.73, "elapsed_time": "1:48:12", "remaining_time": "0:03:39", "throughput": 1032.48, "total_tokens": 6702944} {"current_steps": 74450, "total_steps": 76960, "loss": 0.0059, "lr": 1.6196402278975675e-07, "epoch": 19.347713097713097, "percentage": 96.74, "elapsed_time": "1:48:12", "remaining_time": "0:03:38", "throughput": 1032.48, "total_tokens": 6703376} {"current_steps": 74455, "total_steps": 76960, "loss": 0.1383, "lr": 1.6132034087420477e-07, "epoch": 19.349012474012476, "percentage": 96.75, "elapsed_time": "1:48:12", "remaining_time": "0:03:38", "throughput": 1032.47, "total_tokens": 6703792} {"current_steps": 74460, "total_steps": 76960, "loss": 0.0002, "lr": 1.6067793643574912e-07, "epoch": 19.35031185031185, "percentage": 96.75, "elapsed_time": "1:48:13", "remaining_time": "0:03:38", "throughput": 1032.48, "total_tokens": 6704256} {"current_steps": 74465, "total_steps": 76960, "loss": 0.0004, "lr": 1.6003680950742728e-07, "epoch": 19.351611226611226, "percentage": 96.76, "elapsed_time": "1:48:13", "remaining_time": "0:03:37", "throughput": 1032.48, "total_tokens": 6704720} {"current_steps": 74470, "total_steps": 76960, "loss": 0.011, "lr": 1.5939696012221007e-07, "epoch": 19.352910602910605, "percentage": 96.76, "elapsed_time": "1:48:14", "remaining_time": "0:03:37", "throughput": 1032.48, "total_tokens": 6705136} {"current_steps": 74475, "total_steps": 76960, "loss": 0.0025, "lr": 1.5875838831301004e-07, "epoch": 19.35420997920998, "percentage": 96.77, "elapsed_time": "1:48:14", "remaining_time": "0:03:36", "throughput": 1032.49, "total_tokens": 6705600} {"current_steps": 74480, "total_steps": 76960, "loss": 0.0011, "lr": 1.5812109411266762e-07, "epoch": 19.355509355509355, "percentage": 96.78, "elapsed_time": "1:48:15", "remaining_time": "0:03:36", "throughput": 1032.49, "total_tokens": 6706048} {"current_steps": 74485, "total_steps": 76960, "loss": 0.0671, "lr": 1.5748507755395936e-07, "epoch": 19.35680873180873, "percentage": 96.78, "elapsed_time": "1:48:15", "remaining_time": "0:03:35", "throughput": 1032.49, "total_tokens": 6706480} {"current_steps": 74490, "total_steps": 76960, "loss": 0.0207, "lr": 1.5685033866959798e-07, "epoch": 19.35810810810811, "percentage": 96.79, "elapsed_time": "1:48:15", "remaining_time": "0:03:35", "throughput": 1032.49, "total_tokens": 6706928} {"current_steps": 74495, "total_steps": 76960, "loss": 0.0015, "lr": 1.5621687749222679e-07, "epoch": 19.359407484407484, "percentage": 96.8, "elapsed_time": "1:48:16", "remaining_time": "0:03:34", "throughput": 1032.5, "total_tokens": 6707392} {"current_steps": 74500, "total_steps": 76960, "loss": 0.0182, "lr": 1.5558469405442534e-07, "epoch": 19.36070686070686, "percentage": 96.8, "elapsed_time": "1:48:16", "remaining_time": "0:03:34", "throughput": 1032.5, "total_tokens": 6707872} {"current_steps": 74505, "total_steps": 76960, "loss": 0.0328, "lr": 1.5495378838870643e-07, "epoch": 19.362006237006238, "percentage": 96.81, "elapsed_time": "1:48:17", "remaining_time": "0:03:34", "throughput": 1032.5, "total_tokens": 6708288} {"current_steps": 74510, "total_steps": 76960, "loss": 0.0005, "lr": 1.5432416052752198e-07, "epoch": 19.363305613305613, "percentage": 96.82, "elapsed_time": "1:48:17", "remaining_time": "0:03:33", "throughput": 1032.51, "total_tokens": 6708752} {"current_steps": 74515, "total_steps": 76960, "loss": 0.1366, "lr": 1.5369581050325155e-07, "epoch": 19.364604989604988, "percentage": 96.82, "elapsed_time": "1:48:17", "remaining_time": "0:03:33", "throughput": 1032.51, "total_tokens": 6709216} {"current_steps": 74520, "total_steps": 76960, "loss": 0.0001, "lr": 1.5306873834821102e-07, "epoch": 19.365904365904367, "percentage": 96.83, "elapsed_time": "1:48:18", "remaining_time": "0:03:32", "throughput": 1032.51, "total_tokens": 6709664} {"current_steps": 74525, "total_steps": 76960, "loss": 0.1629, "lr": 1.5244294409465232e-07, "epoch": 19.367203742203742, "percentage": 96.84, "elapsed_time": "1:48:18", "remaining_time": "0:03:32", "throughput": 1032.52, "total_tokens": 6710112} {"current_steps": 74530, "total_steps": 76960, "loss": 0.0286, "lr": 1.5181842777476084e-07, "epoch": 19.368503118503117, "percentage": 96.84, "elapsed_time": "1:48:19", "remaining_time": "0:03:31", "throughput": 1032.52, "total_tokens": 6710544} {"current_steps": 74535, "total_steps": 76960, "loss": 0.0149, "lr": 1.5119518942065535e-07, "epoch": 19.369802494802496, "percentage": 96.85, "elapsed_time": "1:48:19", "remaining_time": "0:03:31", "throughput": 1032.52, "total_tokens": 6710992} {"current_steps": 74540, "total_steps": 76960, "loss": 0.0871, "lr": 1.5057322906439075e-07, "epoch": 19.37110187110187, "percentage": 96.86, "elapsed_time": "1:48:20", "remaining_time": "0:03:31", "throughput": 1032.52, "total_tokens": 6711440} {"current_steps": 74545, "total_steps": 76960, "loss": 0.0001, "lr": 1.4995254673795812e-07, "epoch": 19.372401247401246, "percentage": 96.86, "elapsed_time": "1:48:20", "remaining_time": "0:03:30", "throughput": 1032.53, "total_tokens": 6711904} {"current_steps": 74550, "total_steps": 76960, "loss": 0.0022, "lr": 1.4933314247327078e-07, "epoch": 19.373700623700625, "percentage": 96.87, "elapsed_time": "1:48:20", "remaining_time": "0:03:30", "throughput": 1032.54, "total_tokens": 6712384} {"current_steps": 74555, "total_steps": 76960, "loss": 0.0576, "lr": 1.48715016302195e-07, "epoch": 19.375, "percentage": 96.88, "elapsed_time": "1:48:21", "remaining_time": "0:03:29", "throughput": 1032.54, "total_tokens": 6712832} {"current_steps": 74560, "total_steps": 76960, "loss": 0.0022, "lr": 1.4809816825651356e-07, "epoch": 19.376299376299375, "percentage": 96.88, "elapsed_time": "1:48:21", "remaining_time": "0:03:29", "throughput": 1032.54, "total_tokens": 6713264} {"current_steps": 74565, "total_steps": 76960, "loss": 0.0003, "lr": 1.4748259836795675e-07, "epoch": 19.377598752598754, "percentage": 96.89, "elapsed_time": "1:48:22", "remaining_time": "0:03:28", "throughput": 1032.55, "total_tokens": 6713760} {"current_steps": 74570, "total_steps": 76960, "loss": 0.4416, "lr": 1.468683066681853e-07, "epoch": 19.37889812889813, "percentage": 96.89, "elapsed_time": "1:48:22", "remaining_time": "0:03:28", "throughput": 1032.55, "total_tokens": 6714224} {"current_steps": 74575, "total_steps": 76960, "loss": 0.0156, "lr": 1.4625529318878505e-07, "epoch": 19.380197505197504, "percentage": 96.9, "elapsed_time": "1:48:22", "remaining_time": "0:03:27", "throughput": 1032.56, "total_tokens": 6714656} {"current_steps": 74580, "total_steps": 76960, "loss": 0.2713, "lr": 1.4564355796129193e-07, "epoch": 19.381496881496883, "percentage": 96.91, "elapsed_time": "1:48:23", "remaining_time": "0:03:27", "throughput": 1032.56, "total_tokens": 6715136} {"current_steps": 74585, "total_steps": 76960, "loss": 0.0099, "lr": 1.4503310101716406e-07, "epoch": 19.382796257796258, "percentage": 96.91, "elapsed_time": "1:48:23", "remaining_time": "0:03:27", "throughput": 1032.57, "total_tokens": 6715584} {"current_steps": 74590, "total_steps": 76960, "loss": 0.0011, "lr": 1.4442392238779856e-07, "epoch": 19.384095634095633, "percentage": 96.92, "elapsed_time": "1:48:24", "remaining_time": "0:03:26", "throughput": 1032.57, "total_tokens": 6716032} {"current_steps": 74595, "total_steps": 76960, "loss": 0.0026, "lr": 1.4381602210452593e-07, "epoch": 19.385395010395012, "percentage": 96.93, "elapsed_time": "1:48:24", "remaining_time": "0:03:26", "throughput": 1032.57, "total_tokens": 6716464} {"current_steps": 74600, "total_steps": 76960, "loss": 0.0476, "lr": 1.4320940019861283e-07, "epoch": 19.386694386694387, "percentage": 96.93, "elapsed_time": "1:48:25", "remaining_time": "0:03:25", "throughput": 1032.57, "total_tokens": 6716896} {"current_steps": 74605, "total_steps": 76960, "loss": 0.0507, "lr": 1.4260405670125378e-07, "epoch": 19.387993762993762, "percentage": 96.94, "elapsed_time": "1:48:25", "remaining_time": "0:03:25", "throughput": 1032.58, "total_tokens": 6717360} {"current_steps": 74610, "total_steps": 76960, "loss": 0.0004, "lr": 1.4199999164359045e-07, "epoch": 19.38929313929314, "percentage": 96.95, "elapsed_time": "1:48:25", "remaining_time": "0:03:24", "throughput": 1032.58, "total_tokens": 6717792} {"current_steps": 74615, "total_steps": 76960, "loss": 0.0027, "lr": 1.4139720505668141e-07, "epoch": 19.390592515592516, "percentage": 96.95, "elapsed_time": "1:48:26", "remaining_time": "0:03:24", "throughput": 1032.58, "total_tokens": 6718256} {"current_steps": 74620, "total_steps": 76960, "loss": 0.0186, "lr": 1.4079569697153239e-07, "epoch": 19.39189189189189, "percentage": 96.96, "elapsed_time": "1:48:26", "remaining_time": "0:03:24", "throughput": 1032.59, "total_tokens": 6718736} {"current_steps": 74625, "total_steps": 76960, "loss": 0.053, "lr": 1.4019546741908251e-07, "epoch": 19.39319126819127, "percentage": 96.97, "elapsed_time": "1:48:27", "remaining_time": "0:03:23", "throughput": 1032.59, "total_tokens": 6719200} {"current_steps": 74630, "total_steps": 76960, "loss": 0.0234, "lr": 1.39596516430196e-07, "epoch": 19.394490644490645, "percentage": 96.97, "elapsed_time": "1:48:27", "remaining_time": "0:03:23", "throughput": 1032.6, "total_tokens": 6719632} {"current_steps": 74635, "total_steps": 76960, "loss": 0.1017, "lr": 1.3899884403568153e-07, "epoch": 19.39579002079002, "percentage": 96.98, "elapsed_time": "1:48:27", "remaining_time": "0:03:22", "throughput": 1032.6, "total_tokens": 6720112} {"current_steps": 74640, "total_steps": 76960, "loss": 0.1185, "lr": 1.384024502662784e-07, "epoch": 19.397089397089395, "percentage": 96.99, "elapsed_time": "1:48:28", "remaining_time": "0:03:22", "throughput": 1032.61, "total_tokens": 6720592} {"current_steps": 74645, "total_steps": 76960, "loss": 0.2012, "lr": 1.378073351526593e-07, "epoch": 19.398388773388774, "percentage": 96.99, "elapsed_time": "1:48:28", "remaining_time": "0:03:21", "throughput": 1032.61, "total_tokens": 6721040} {"current_steps": 74650, "total_steps": 76960, "loss": 0.0714, "lr": 1.3721349872542756e-07, "epoch": 19.39968814968815, "percentage": 97.0, "elapsed_time": "1:48:29", "remaining_time": "0:03:21", "throughput": 1032.62, "total_tokens": 6721504} {"current_steps": 74655, "total_steps": 76960, "loss": 0.0764, "lr": 1.366209410151309e-07, "epoch": 19.400987525987524, "percentage": 97.0, "elapsed_time": "1:48:29", "remaining_time": "0:03:20", "throughput": 1032.62, "total_tokens": 6721968} {"current_steps": 74660, "total_steps": 76960, "loss": 0.0098, "lr": 1.3602966205223943e-07, "epoch": 19.402286902286903, "percentage": 97.01, "elapsed_time": "1:48:30", "remaining_time": "0:03:20", "throughput": 1032.63, "total_tokens": 6722432} {"current_steps": 74665, "total_steps": 76960, "loss": 0.0032, "lr": 1.3543966186716773e-07, "epoch": 19.40358627858628, "percentage": 97.02, "elapsed_time": "1:48:30", "remaining_time": "0:03:20", "throughput": 1032.64, "total_tokens": 6722944} {"current_steps": 74670, "total_steps": 76960, "loss": 0.0018, "lr": 1.3485094049025816e-07, "epoch": 19.404885654885653, "percentage": 97.02, "elapsed_time": "1:48:30", "remaining_time": "0:03:19", "throughput": 1032.64, "total_tokens": 6723376} {"current_steps": 74675, "total_steps": 76960, "loss": 0.0067, "lr": 1.3426349795178926e-07, "epoch": 19.406185031185032, "percentage": 97.03, "elapsed_time": "1:48:31", "remaining_time": "0:03:19", "throughput": 1032.64, "total_tokens": 6723808} {"current_steps": 74680, "total_steps": 76960, "loss": 0.0042, "lr": 1.3367733428197304e-07, "epoch": 19.407484407484407, "percentage": 97.04, "elapsed_time": "1:48:31", "remaining_time": "0:03:18", "throughput": 1032.65, "total_tokens": 6724256} {"current_steps": 74685, "total_steps": 76960, "loss": 0.0074, "lr": 1.3309244951095756e-07, "epoch": 19.408783783783782, "percentage": 97.04, "elapsed_time": "1:48:32", "remaining_time": "0:03:18", "throughput": 1032.65, "total_tokens": 6724720} {"current_steps": 74690, "total_steps": 76960, "loss": 0.0716, "lr": 1.325088436688271e-07, "epoch": 19.41008316008316, "percentage": 97.05, "elapsed_time": "1:48:32", "remaining_time": "0:03:17", "throughput": 1032.66, "total_tokens": 6725216} {"current_steps": 74695, "total_steps": 76960, "loss": 0.0001, "lr": 1.319265167855882e-07, "epoch": 19.411382536382536, "percentage": 97.06, "elapsed_time": "1:48:32", "remaining_time": "0:03:17", "throughput": 1032.67, "total_tokens": 6725664} {"current_steps": 74700, "total_steps": 76960, "loss": 0.0028, "lr": 1.3134546889120026e-07, "epoch": 19.41268191268191, "percentage": 97.06, "elapsed_time": "1:48:33", "remaining_time": "0:03:17", "throughput": 1032.68, "total_tokens": 6726160} {"current_steps": 74705, "total_steps": 76960, "loss": 0.0982, "lr": 1.3076570001553934e-07, "epoch": 19.41398128898129, "percentage": 97.07, "elapsed_time": "1:48:33", "remaining_time": "0:03:16", "throughput": 1032.68, "total_tokens": 6726608} {"current_steps": 74710, "total_steps": 76960, "loss": 0.0072, "lr": 1.3018721018842883e-07, "epoch": 19.415280665280665, "percentage": 97.08, "elapsed_time": "1:48:34", "remaining_time": "0:03:16", "throughput": 1032.68, "total_tokens": 6727072} {"current_steps": 74715, "total_steps": 76960, "loss": 0.0094, "lr": 1.2960999943961992e-07, "epoch": 19.41658004158004, "percentage": 97.08, "elapsed_time": "1:48:34", "remaining_time": "0:03:15", "throughput": 1032.69, "total_tokens": 6727536} {"current_steps": 74720, "total_steps": 76960, "loss": 0.0281, "lr": 1.2903406779879722e-07, "epoch": 19.41787941787942, "percentage": 97.09, "elapsed_time": "1:48:34", "remaining_time": "0:03:15", "throughput": 1032.7, "total_tokens": 6728016} {"current_steps": 74725, "total_steps": 76960, "loss": 0.4705, "lr": 1.2845941529558424e-07, "epoch": 19.419178794178794, "percentage": 97.1, "elapsed_time": "1:48:35", "remaining_time": "0:03:14", "throughput": 1032.69, "total_tokens": 6728432} {"current_steps": 74730, "total_steps": 76960, "loss": 0.0003, "lr": 1.2788604195953234e-07, "epoch": 19.42047817047817, "percentage": 97.1, "elapsed_time": "1:48:35", "remaining_time": "0:03:14", "throughput": 1032.7, "total_tokens": 6728880} {"current_steps": 74735, "total_steps": 76960, "loss": 0.2007, "lr": 1.273139478201346e-07, "epoch": 19.421777546777548, "percentage": 97.11, "elapsed_time": "1:48:36", "remaining_time": "0:03:14", "throughput": 1032.7, "total_tokens": 6729296} {"current_steps": 74740, "total_steps": 76960, "loss": 0.0246, "lr": 1.2674313290680916e-07, "epoch": 19.423076923076923, "percentage": 97.12, "elapsed_time": "1:48:36", "remaining_time": "0:03:13", "throughput": 1032.7, "total_tokens": 6729728} {"current_steps": 74745, "total_steps": 76960, "loss": 0.0007, "lr": 1.2617359724891863e-07, "epoch": 19.4243762993763, "percentage": 97.12, "elapsed_time": "1:48:37", "remaining_time": "0:03:13", "throughput": 1032.7, "total_tokens": 6730176} {"current_steps": 74750, "total_steps": 76960, "loss": 0.1564, "lr": 1.2560534087575349e-07, "epoch": 19.425675675675677, "percentage": 97.13, "elapsed_time": "1:48:37", "remaining_time": "0:03:12", "throughput": 1032.7, "total_tokens": 6730624} {"current_steps": 74755, "total_steps": 76960, "loss": 0.1978, "lr": 1.2503836381654032e-07, "epoch": 19.426975051975052, "percentage": 97.13, "elapsed_time": "1:48:37", "remaining_time": "0:03:12", "throughput": 1032.71, "total_tokens": 6731088} {"current_steps": 74760, "total_steps": 76960, "loss": 0.0062, "lr": 1.244726661004364e-07, "epoch": 19.428274428274428, "percentage": 97.14, "elapsed_time": "1:48:38", "remaining_time": "0:03:11", "throughput": 1032.71, "total_tokens": 6731552} {"current_steps": 74765, "total_steps": 76960, "loss": 0.0072, "lr": 1.2390824775653788e-07, "epoch": 19.429573804573806, "percentage": 97.15, "elapsed_time": "1:48:38", "remaining_time": "0:03:11", "throughput": 1032.71, "total_tokens": 6731968} {"current_steps": 74770, "total_steps": 76960, "loss": 0.1766, "lr": 1.233451088138743e-07, "epoch": 19.43087318087318, "percentage": 97.15, "elapsed_time": "1:48:39", "remaining_time": "0:03:10", "throughput": 1032.71, "total_tokens": 6732400} {"current_steps": 74775, "total_steps": 76960, "loss": 0.071, "lr": 1.2278324930140585e-07, "epoch": 19.432172557172557, "percentage": 97.16, "elapsed_time": "1:48:39", "remaining_time": "0:03:10", "throughput": 1032.71, "total_tokens": 6732816} {"current_steps": 74780, "total_steps": 76960, "loss": 0.1949, "lr": 1.2222266924803161e-07, "epoch": 19.433471933471935, "percentage": 97.17, "elapsed_time": "1:48:39", "remaining_time": "0:03:10", "throughput": 1032.71, "total_tokens": 6733264} {"current_steps": 74785, "total_steps": 76960, "loss": 0.0954, "lr": 1.216633686825841e-07, "epoch": 19.43477130977131, "percentage": 97.17, "elapsed_time": "1:48:40", "remaining_time": "0:03:09", "throughput": 1032.71, "total_tokens": 6733696} {"current_steps": 74790, "total_steps": 76960, "loss": 0.0085, "lr": 1.2110534763382365e-07, "epoch": 19.436070686070686, "percentage": 97.18, "elapsed_time": "1:48:40", "remaining_time": "0:03:09", "throughput": 1032.71, "total_tokens": 6734144} {"current_steps": 74795, "total_steps": 76960, "loss": 0.5306, "lr": 1.2054860613045504e-07, "epoch": 19.43737006237006, "percentage": 97.19, "elapsed_time": "1:48:41", "remaining_time": "0:03:08", "throughput": 1032.72, "total_tokens": 6734624} {"current_steps": 74800, "total_steps": 76960, "loss": 0.0254, "lr": 1.1999314420111095e-07, "epoch": 19.43866943866944, "percentage": 97.19, "elapsed_time": "1:48:41", "remaining_time": "0:03:08", "throughput": 1032.73, "total_tokens": 6735088} {"current_steps": 74805, "total_steps": 76960, "loss": 0.3679, "lr": 1.1943896187435744e-07, "epoch": 19.439968814968815, "percentage": 97.2, "elapsed_time": "1:48:42", "remaining_time": "0:03:07", "throughput": 1032.73, "total_tokens": 6735552} {"current_steps": 74810, "total_steps": 76960, "loss": 0.0334, "lr": 1.1888605917869666e-07, "epoch": 19.44126819126819, "percentage": 97.21, "elapsed_time": "1:48:42", "remaining_time": "0:03:07", "throughput": 1032.73, "total_tokens": 6735984} {"current_steps": 74815, "total_steps": 76960, "loss": 0.0527, "lr": 1.1833443614256423e-07, "epoch": 19.44256756756757, "percentage": 97.21, "elapsed_time": "1:48:42", "remaining_time": "0:03:07", "throughput": 1032.75, "total_tokens": 6736496} {"current_steps": 74820, "total_steps": 76960, "loss": 0.0004, "lr": 1.1778409279433467e-07, "epoch": 19.443866943866944, "percentage": 97.22, "elapsed_time": "1:48:43", "remaining_time": "0:03:06", "throughput": 1032.75, "total_tokens": 6736976} {"current_steps": 74825, "total_steps": 76960, "loss": 0.001, "lr": 1.1723502916231032e-07, "epoch": 19.44516632016632, "percentage": 97.23, "elapsed_time": "1:48:43", "remaining_time": "0:03:06", "throughput": 1032.76, "total_tokens": 6737424} {"current_steps": 74830, "total_steps": 76960, "loss": 0.3934, "lr": 1.1668724527472974e-07, "epoch": 19.446465696465697, "percentage": 97.23, "elapsed_time": "1:48:44", "remaining_time": "0:03:05", "throughput": 1032.76, "total_tokens": 6737872} {"current_steps": 74835, "total_steps": 76960, "loss": 0.0004, "lr": 1.1614074115976481e-07, "epoch": 19.447765072765073, "percentage": 97.24, "elapsed_time": "1:48:44", "remaining_time": "0:03:05", "throughput": 1032.77, "total_tokens": 6738352} {"current_steps": 74840, "total_steps": 76960, "loss": 0.2381, "lr": 1.1559551684552638e-07, "epoch": 19.449064449064448, "percentage": 97.25, "elapsed_time": "1:48:44", "remaining_time": "0:03:04", "throughput": 1032.77, "total_tokens": 6738800} {"current_steps": 74845, "total_steps": 76960, "loss": 0.4484, "lr": 1.1505157236005037e-07, "epoch": 19.450363825363826, "percentage": 97.25, "elapsed_time": "1:48:45", "remaining_time": "0:03:04", "throughput": 1032.77, "total_tokens": 6739248} {"current_steps": 74850, "total_steps": 76960, "loss": 0.2536, "lr": 1.1450890773131717e-07, "epoch": 19.4516632016632, "percentage": 97.26, "elapsed_time": "1:48:45", "remaining_time": "0:03:03", "throughput": 1032.78, "total_tokens": 6739712} {"current_steps": 74855, "total_steps": 76960, "loss": 0.0864, "lr": 1.1396752298723501e-07, "epoch": 19.452962577962577, "percentage": 97.26, "elapsed_time": "1:48:46", "remaining_time": "0:03:03", "throughput": 1032.77, "total_tokens": 6740128} {"current_steps": 74860, "total_steps": 76960, "loss": 0.0566, "lr": 1.1342741815564828e-07, "epoch": 19.454261954261955, "percentage": 97.27, "elapsed_time": "1:48:46", "remaining_time": "0:03:03", "throughput": 1032.77, "total_tokens": 6740560} {"current_steps": 74865, "total_steps": 76960, "loss": 0.0494, "lr": 1.1288859326433477e-07, "epoch": 19.45556133056133, "percentage": 97.28, "elapsed_time": "1:48:47", "remaining_time": "0:03:02", "throughput": 1032.78, "total_tokens": 6740992} {"current_steps": 74870, "total_steps": 76960, "loss": 0.0105, "lr": 1.1235104834100563e-07, "epoch": 19.456860706860706, "percentage": 97.28, "elapsed_time": "1:48:47", "remaining_time": "0:03:02", "throughput": 1032.78, "total_tokens": 6741440} {"current_steps": 74875, "total_steps": 76960, "loss": 0.01, "lr": 1.118147834133082e-07, "epoch": 19.458160083160084, "percentage": 97.29, "elapsed_time": "1:48:47", "remaining_time": "0:03:01", "throughput": 1032.78, "total_tokens": 6741856} {"current_steps": 74880, "total_steps": 76960, "loss": 0.0005, "lr": 1.1127979850882598e-07, "epoch": 19.45945945945946, "percentage": 97.3, "elapsed_time": "1:48:48", "remaining_time": "0:03:01", "throughput": 1032.78, "total_tokens": 6742288} {"current_steps": 74885, "total_steps": 76960, "loss": 0.171, "lr": 1.107460936550675e-07, "epoch": 19.460758835758835, "percentage": 97.3, "elapsed_time": "1:48:48", "remaining_time": "0:03:00", "throughput": 1032.78, "total_tokens": 6742768} {"current_steps": 74890, "total_steps": 76960, "loss": 0.3031, "lr": 1.1021366887948581e-07, "epoch": 19.462058212058214, "percentage": 97.31, "elapsed_time": "1:48:49", "remaining_time": "0:03:00", "throughput": 1032.79, "total_tokens": 6743232} {"current_steps": 74895, "total_steps": 76960, "loss": 0.121, "lr": 1.0968252420946456e-07, "epoch": 19.46335758835759, "percentage": 97.32, "elapsed_time": "1:48:49", "remaining_time": "0:03:00", "throughput": 1032.79, "total_tokens": 6743664} {"current_steps": 74900, "total_steps": 76960, "loss": 0.2179, "lr": 1.0915265967231802e-07, "epoch": 19.464656964656964, "percentage": 97.32, "elapsed_time": "1:48:49", "remaining_time": "0:02:59", "throughput": 1032.79, "total_tokens": 6744080} {"current_steps": 74905, "total_steps": 76960, "loss": 0.0397, "lr": 1.0862407529530217e-07, "epoch": 19.465956340956343, "percentage": 97.33, "elapsed_time": "1:48:50", "remaining_time": "0:02:59", "throughput": 1032.79, "total_tokens": 6744528} {"current_steps": 74910, "total_steps": 76960, "loss": 0.1178, "lr": 1.0809677110559802e-07, "epoch": 19.467255717255718, "percentage": 97.34, "elapsed_time": "1:48:50", "remaining_time": "0:02:58", "throughput": 1032.79, "total_tokens": 6744976} {"current_steps": 74915, "total_steps": 76960, "loss": 0.0093, "lr": 1.0757074713032556e-07, "epoch": 19.468555093555093, "percentage": 97.34, "elapsed_time": "1:48:51", "remaining_time": "0:02:58", "throughput": 1032.8, "total_tokens": 6745424} {"current_steps": 74920, "total_steps": 76960, "loss": 0.0009, "lr": 1.0704600339654369e-07, "epoch": 19.46985446985447, "percentage": 97.35, "elapsed_time": "1:48:51", "remaining_time": "0:02:57", "throughput": 1032.81, "total_tokens": 6745904} {"current_steps": 74925, "total_steps": 76960, "loss": 0.0004, "lr": 1.065225399312364e-07, "epoch": 19.471153846153847, "percentage": 97.36, "elapsed_time": "1:48:52", "remaining_time": "0:02:57", "throughput": 1032.81, "total_tokens": 6746336} {"current_steps": 74930, "total_steps": 76960, "loss": 0.285, "lr": 1.060003567613238e-07, "epoch": 19.472453222453222, "percentage": 97.36, "elapsed_time": "1:48:52", "remaining_time": "0:02:56", "throughput": 1032.81, "total_tokens": 6746768} {"current_steps": 74935, "total_steps": 76960, "loss": 0.0289, "lr": 1.0547945391366776e-07, "epoch": 19.473752598752597, "percentage": 97.37, "elapsed_time": "1:48:52", "remaining_time": "0:02:56", "throughput": 1032.81, "total_tokens": 6747216} {"current_steps": 74940, "total_steps": 76960, "loss": 0.0001, "lr": 1.0495983141505794e-07, "epoch": 19.475051975051976, "percentage": 97.38, "elapsed_time": "1:48:53", "remaining_time": "0:02:56", "throughput": 1032.81, "total_tokens": 6747648} {"current_steps": 74945, "total_steps": 76960, "loss": 0.1152, "lr": 1.0444148929221464e-07, "epoch": 19.47635135135135, "percentage": 97.38, "elapsed_time": "1:48:53", "remaining_time": "0:02:55", "throughput": 1032.81, "total_tokens": 6748096} {"current_steps": 74950, "total_steps": 76960, "loss": 0.0081, "lr": 1.0392442757179987e-07, "epoch": 19.477650727650726, "percentage": 97.39, "elapsed_time": "1:48:54", "remaining_time": "0:02:55", "throughput": 1032.81, "total_tokens": 6748496} {"current_steps": 74955, "total_steps": 76960, "loss": 0.4189, "lr": 1.0340864628040626e-07, "epoch": 19.478950103950105, "percentage": 97.39, "elapsed_time": "1:48:54", "remaining_time": "0:02:54", "throughput": 1032.81, "total_tokens": 6748928} {"current_steps": 74960, "total_steps": 76960, "loss": 0.4371, "lr": 1.0289414544455978e-07, "epoch": 19.48024948024948, "percentage": 97.4, "elapsed_time": "1:48:54", "remaining_time": "0:02:54", "throughput": 1032.81, "total_tokens": 6749344} {"current_steps": 74965, "total_steps": 76960, "loss": 0.001, "lr": 1.0238092509072262e-07, "epoch": 19.481548856548855, "percentage": 97.41, "elapsed_time": "1:48:55", "remaining_time": "0:02:53", "throughput": 1032.81, "total_tokens": 6749792} {"current_steps": 74970, "total_steps": 76960, "loss": 0.0074, "lr": 1.0186898524529309e-07, "epoch": 19.482848232848234, "percentage": 97.41, "elapsed_time": "1:48:55", "remaining_time": "0:02:53", "throughput": 1032.82, "total_tokens": 6750272} {"current_steps": 74975, "total_steps": 76960, "loss": 0.1604, "lr": 1.013583259345946e-07, "epoch": 19.48414760914761, "percentage": 97.42, "elapsed_time": "1:48:56", "remaining_time": "0:02:53", "throughput": 1032.82, "total_tokens": 6750736} {"current_steps": 74980, "total_steps": 76960, "loss": 0.191, "lr": 1.0084894718489501e-07, "epoch": 19.485446985446984, "percentage": 97.43, "elapsed_time": "1:48:56", "remaining_time": "0:02:52", "throughput": 1032.82, "total_tokens": 6751168} {"current_steps": 74985, "total_steps": 76960, "loss": 0.0003, "lr": 1.0034084902239282e-07, "epoch": 19.486746361746363, "percentage": 97.43, "elapsed_time": "1:48:57", "remaining_time": "0:02:52", "throughput": 1032.83, "total_tokens": 6751616} {"current_steps": 74990, "total_steps": 76960, "loss": 0.0038, "lr": 9.983403147321712e-08, "epoch": 19.488045738045738, "percentage": 97.44, "elapsed_time": "1:48:57", "remaining_time": "0:02:51", "throughput": 1032.82, "total_tokens": 6752032} {"current_steps": 74995, "total_steps": 76960, "loss": 0.0001, "lr": 9.932849456343318e-08, "epoch": 19.489345114345113, "percentage": 97.45, "elapsed_time": "1:48:57", "remaining_time": "0:02:51", "throughput": 1032.83, "total_tokens": 6752480} {"current_steps": 75000, "total_steps": 76960, "loss": 0.5291, "lr": 9.882423831904797e-08, "epoch": 19.490644490644492, "percentage": 97.45, "elapsed_time": "1:48:58", "remaining_time": "0:02:50", "throughput": 1032.83, "total_tokens": 6752960} {"current_steps": 75005, "total_steps": 76960, "loss": 0.2203, "lr": 9.832126276598797e-08, "epoch": 19.491943866943867, "percentage": 97.46, "elapsed_time": "1:48:58", "remaining_time": "0:02:50", "throughput": 1032.84, "total_tokens": 6753392} {"current_steps": 75010, "total_steps": 76960, "loss": 0.0528, "lr": 9.781956793012692e-08, "epoch": 19.493243243243242, "percentage": 97.47, "elapsed_time": "1:48:59", "remaining_time": "0:02:49", "throughput": 1032.84, "total_tokens": 6753824} {"current_steps": 75015, "total_steps": 76960, "loss": 0.0226, "lr": 9.731915383726364e-08, "epoch": 19.49454261954262, "percentage": 97.47, "elapsed_time": "1:48:59", "remaining_time": "0:02:49", "throughput": 1032.84, "total_tokens": 6754304} {"current_steps": 75020, "total_steps": 76960, "loss": 0.102, "lr": 9.682002051313866e-08, "epoch": 19.495841995841996, "percentage": 97.48, "elapsed_time": "1:48:59", "remaining_time": "0:02:49", "throughput": 1032.85, "total_tokens": 6754800} {"current_steps": 75025, "total_steps": 76960, "loss": 0.1213, "lr": 9.63221679834203e-08, "epoch": 19.49714137214137, "percentage": 97.49, "elapsed_time": "1:49:00", "remaining_time": "0:02:48", "throughput": 1032.86, "total_tokens": 6755280} {"current_steps": 75030, "total_steps": 76960, "loss": 0.2315, "lr": 9.582559627371313e-08, "epoch": 19.49844074844075, "percentage": 97.49, "elapsed_time": "1:49:00", "remaining_time": "0:02:48", "throughput": 1032.87, "total_tokens": 6755744} {"current_steps": 75035, "total_steps": 76960, "loss": 0.078, "lr": 9.533030540956056e-08, "epoch": 19.499740124740125, "percentage": 97.5, "elapsed_time": "1:49:01", "remaining_time": "0:02:47", "throughput": 1032.87, "total_tokens": 6756192} {"current_steps": 75040, "total_steps": 76960, "loss": 0.0009, "lr": 9.483629541643114e-08, "epoch": 19.5010395010395, "percentage": 97.51, "elapsed_time": "1:49:01", "remaining_time": "0:02:47", "throughput": 1032.88, "total_tokens": 6756656} {"current_steps": 75045, "total_steps": 76960, "loss": 0.009, "lr": 9.434356631973506e-08, "epoch": 19.50233887733888, "percentage": 97.51, "elapsed_time": "1:49:02", "remaining_time": "0:02:46", "throughput": 1032.88, "total_tokens": 6757136} {"current_steps": 75050, "total_steps": 76960, "loss": 0.0002, "lr": 9.38521181448132e-08, "epoch": 19.503638253638254, "percentage": 97.52, "elapsed_time": "1:49:02", "remaining_time": "0:02:46", "throughput": 1032.89, "total_tokens": 6757584} {"current_steps": 75055, "total_steps": 76960, "loss": 0.0017, "lr": 9.336195091693978e-08, "epoch": 19.50493762993763, "percentage": 97.52, "elapsed_time": "1:49:02", "remaining_time": "0:02:46", "throughput": 1032.89, "total_tokens": 6758016} {"current_steps": 75060, "total_steps": 76960, "loss": 0.0959, "lr": 9.287306466132518e-08, "epoch": 19.506237006237008, "percentage": 97.53, "elapsed_time": "1:49:03", "remaining_time": "0:02:45", "throughput": 1032.89, "total_tokens": 6758480} {"current_steps": 75065, "total_steps": 76960, "loss": 0.0563, "lr": 9.238545940311316e-08, "epoch": 19.507536382536383, "percentage": 97.54, "elapsed_time": "1:49:03", "remaining_time": "0:02:45", "throughput": 1032.9, "total_tokens": 6758944} {"current_steps": 75070, "total_steps": 76960, "loss": 0.0161, "lr": 9.189913516738368e-08, "epoch": 19.508835758835758, "percentage": 97.54, "elapsed_time": "1:49:04", "remaining_time": "0:02:44", "throughput": 1032.9, "total_tokens": 6759376} {"current_steps": 75075, "total_steps": 76960, "loss": 0.0002, "lr": 9.14140919791473e-08, "epoch": 19.510135135135137, "percentage": 97.55, "elapsed_time": "1:49:04", "remaining_time": "0:02:44", "throughput": 1032.91, "total_tokens": 6759856} {"current_steps": 75080, "total_steps": 76960, "loss": 0.0003, "lr": 9.09303298633507e-08, "epoch": 19.511434511434512, "percentage": 97.56, "elapsed_time": "1:49:04", "remaining_time": "0:02:43", "throughput": 1032.91, "total_tokens": 6760336} {"current_steps": 75085, "total_steps": 76960, "loss": 0.0003, "lr": 9.044784884487123e-08, "epoch": 19.512733887733887, "percentage": 97.56, "elapsed_time": "1:49:05", "remaining_time": "0:02:43", "throughput": 1032.92, "total_tokens": 6760784} {"current_steps": 75090, "total_steps": 76960, "loss": 0.2153, "lr": 8.996664894853069e-08, "epoch": 19.514033264033262, "percentage": 97.57, "elapsed_time": "1:49:05", "remaining_time": "0:02:43", "throughput": 1032.92, "total_tokens": 6761232} {"current_steps": 75095, "total_steps": 76960, "loss": 0.0022, "lr": 8.948673019906762e-08, "epoch": 19.51533264033264, "percentage": 97.58, "elapsed_time": "1:49:06", "remaining_time": "0:02:42", "throughput": 1032.92, "total_tokens": 6761680} {"current_steps": 75100, "total_steps": 76960, "loss": 0.1041, "lr": 8.900809262117337e-08, "epoch": 19.516632016632016, "percentage": 97.58, "elapsed_time": "1:49:06", "remaining_time": "0:02:42", "throughput": 1032.93, "total_tokens": 6762128} {"current_steps": 75105, "total_steps": 76960, "loss": 0.0015, "lr": 8.853073623946162e-08, "epoch": 19.51793139293139, "percentage": 97.59, "elapsed_time": "1:49:06", "remaining_time": "0:02:41", "throughput": 1032.93, "total_tokens": 6762592} {"current_steps": 75110, "total_steps": 76960, "loss": 0.002, "lr": 8.805466107848215e-08, "epoch": 19.51923076923077, "percentage": 97.6, "elapsed_time": "1:49:07", "remaining_time": "0:02:41", "throughput": 1032.94, "total_tokens": 6763072} {"current_steps": 75115, "total_steps": 76960, "loss": 0.0412, "lr": 8.757986716272093e-08, "epoch": 19.520530145530145, "percentage": 97.6, "elapsed_time": "1:49:07", "remaining_time": "0:02:40", "throughput": 1032.95, "total_tokens": 6763584} {"current_steps": 75120, "total_steps": 76960, "loss": 0.0001, "lr": 8.71063545166001e-08, "epoch": 19.52182952182952, "percentage": 97.61, "elapsed_time": "1:49:08", "remaining_time": "0:02:40", "throughput": 1032.96, "total_tokens": 6764032} {"current_steps": 75125, "total_steps": 76960, "loss": 0.0283, "lr": 8.663412316446684e-08, "epoch": 19.5231288981289, "percentage": 97.62, "elapsed_time": "1:49:08", "remaining_time": "0:02:39", "throughput": 1032.96, "total_tokens": 6764464} {"current_steps": 75130, "total_steps": 76960, "loss": 0.007, "lr": 8.616317313061285e-08, "epoch": 19.524428274428274, "percentage": 97.62, "elapsed_time": "1:49:09", "remaining_time": "0:02:39", "throughput": 1032.96, "total_tokens": 6764896} {"current_steps": 75135, "total_steps": 76960, "loss": 0.0102, "lr": 8.569350443925484e-08, "epoch": 19.52572765072765, "percentage": 97.63, "elapsed_time": "1:49:09", "remaining_time": "0:02:39", "throughput": 1032.96, "total_tokens": 6765360} {"current_steps": 75140, "total_steps": 76960, "loss": 0.0681, "lr": 8.522511711455406e-08, "epoch": 19.527027027027028, "percentage": 97.64, "elapsed_time": "1:49:09", "remaining_time": "0:02:38", "throughput": 1032.96, "total_tokens": 6765776} {"current_steps": 75145, "total_steps": 76960, "loss": 0.0005, "lr": 8.475801118059956e-08, "epoch": 19.528326403326403, "percentage": 97.64, "elapsed_time": "1:49:10", "remaining_time": "0:02:38", "throughput": 1032.97, "total_tokens": 6766240} {"current_steps": 75150, "total_steps": 76960, "loss": 0.0013, "lr": 8.429218666141103e-08, "epoch": 19.52962577962578, "percentage": 97.65, "elapsed_time": "1:49:10", "remaining_time": "0:02:37", "throughput": 1032.97, "total_tokens": 6766688} {"current_steps": 75155, "total_steps": 76960, "loss": 0.0373, "lr": 8.382764358094708e-08, "epoch": 19.530925155925157, "percentage": 97.65, "elapsed_time": "1:49:11", "remaining_time": "0:02:37", "throughput": 1032.97, "total_tokens": 6767136} {"current_steps": 75160, "total_steps": 76960, "loss": 0.067, "lr": 8.336438196310248e-08, "epoch": 19.532224532224532, "percentage": 97.66, "elapsed_time": "1:49:11", "remaining_time": "0:02:36", "throughput": 1032.98, "total_tokens": 6767584} {"current_steps": 75165, "total_steps": 76960, "loss": 0.0823, "lr": 8.290240183170261e-08, "epoch": 19.533523908523907, "percentage": 97.67, "elapsed_time": "1:49:11", "remaining_time": "0:02:36", "throughput": 1032.98, "total_tokens": 6768016} {"current_steps": 75170, "total_steps": 76960, "loss": 0.0758, "lr": 8.244170321050626e-08, "epoch": 19.534823284823286, "percentage": 97.67, "elapsed_time": "1:49:12", "remaining_time": "0:02:36", "throughput": 1032.98, "total_tokens": 6768448} {"current_steps": 75175, "total_steps": 76960, "loss": 0.0603, "lr": 8.198228612320558e-08, "epoch": 19.53612266112266, "percentage": 97.68, "elapsed_time": "1:49:12", "remaining_time": "0:02:35", "throughput": 1032.98, "total_tokens": 6768912} {"current_steps": 75180, "total_steps": 76960, "loss": 0.0131, "lr": 8.152415059343443e-08, "epoch": 19.537422037422036, "percentage": 97.69, "elapsed_time": "1:49:13", "remaining_time": "0:02:35", "throughput": 1032.98, "total_tokens": 6769344} {"current_steps": 75185, "total_steps": 76960, "loss": 0.0003, "lr": 8.106729664475176e-08, "epoch": 19.538721413721415, "percentage": 97.69, "elapsed_time": "1:49:13", "remaining_time": "0:02:34", "throughput": 1032.98, "total_tokens": 6769760} {"current_steps": 75190, "total_steps": 76960, "loss": 0.0006, "lr": 8.061172430065266e-08, "epoch": 19.54002079002079, "percentage": 97.7, "elapsed_time": "1:49:14", "remaining_time": "0:02:34", "throughput": 1032.99, "total_tokens": 6770224} {"current_steps": 75195, "total_steps": 76960, "loss": 0.0735, "lr": 8.01574335845684e-08, "epoch": 19.541320166320165, "percentage": 97.71, "elapsed_time": "1:49:14", "remaining_time": "0:02:33", "throughput": 1032.99, "total_tokens": 6770656} {"current_steps": 75200, "total_steps": 76960, "loss": 0.0867, "lr": 7.970442451986638e-08, "epoch": 19.542619542619544, "percentage": 97.71, "elapsed_time": "1:49:14", "remaining_time": "0:02:33", "throughput": 1032.99, "total_tokens": 6771104} {"current_steps": 75205, "total_steps": 76960, "loss": 0.0004, "lr": 7.925269712984184e-08, "epoch": 19.54391891891892, "percentage": 97.72, "elapsed_time": "1:49:15", "remaining_time": "0:02:32", "throughput": 1032.99, "total_tokens": 6771552} {"current_steps": 75210, "total_steps": 76960, "loss": 0.1321, "lr": 7.880225143772902e-08, "epoch": 19.545218295218294, "percentage": 97.73, "elapsed_time": "1:49:15", "remaining_time": "0:02:32", "throughput": 1033.0, "total_tokens": 6772000} {"current_steps": 75215, "total_steps": 76960, "loss": 0.0032, "lr": 7.835308746669545e-08, "epoch": 19.546517671517673, "percentage": 97.73, "elapsed_time": "1:49:16", "remaining_time": "0:02:32", "throughput": 1033.0, "total_tokens": 6772432} {"current_steps": 75220, "total_steps": 76960, "loss": 0.6433, "lr": 7.790520523984213e-08, "epoch": 19.54781704781705, "percentage": 97.74, "elapsed_time": "1:49:16", "remaining_time": "0:02:31", "throughput": 1032.99, "total_tokens": 6772848} {"current_steps": 75225, "total_steps": 76960, "loss": 0.0678, "lr": 7.74586047802034e-08, "epoch": 19.549116424116423, "percentage": 97.75, "elapsed_time": "1:49:16", "remaining_time": "0:02:31", "throughput": 1033.0, "total_tokens": 6773296} {"current_steps": 75230, "total_steps": 76960, "loss": 0.09, "lr": 7.701328611074698e-08, "epoch": 19.5504158004158, "percentage": 97.75, "elapsed_time": "1:49:17", "remaining_time": "0:02:30", "throughput": 1032.99, "total_tokens": 6773712} {"current_steps": 75235, "total_steps": 76960, "loss": 0.0925, "lr": 7.656924925437681e-08, "epoch": 19.551715176715177, "percentage": 97.76, "elapsed_time": "1:49:17", "remaining_time": "0:02:30", "throughput": 1033.0, "total_tokens": 6774176} {"current_steps": 75240, "total_steps": 76960, "loss": 0.3901, "lr": 7.612649423393014e-08, "epoch": 19.553014553014552, "percentage": 97.77, "elapsed_time": "1:49:18", "remaining_time": "0:02:29", "throughput": 1033.0, "total_tokens": 6774592} {"current_steps": 75245, "total_steps": 76960, "loss": 0.2096, "lr": 7.568502107218044e-08, "epoch": 19.554313929313928, "percentage": 97.77, "elapsed_time": "1:49:18", "remaining_time": "0:02:29", "throughput": 1033.01, "total_tokens": 6775072} {"current_steps": 75250, "total_steps": 76960, "loss": 0.1357, "lr": 7.524482979183178e-08, "epoch": 19.555613305613306, "percentage": 97.78, "elapsed_time": "1:49:19", "remaining_time": "0:02:29", "throughput": 1033.01, "total_tokens": 6775536} {"current_steps": 75255, "total_steps": 76960, "loss": 0.0035, "lr": 7.48059204155216e-08, "epoch": 19.55691268191268, "percentage": 97.78, "elapsed_time": "1:49:19", "remaining_time": "0:02:28", "throughput": 1033.02, "total_tokens": 6775984} {"current_steps": 75260, "total_steps": 76960, "loss": 0.0013, "lr": 7.436829296582626e-08, "epoch": 19.558212058212057, "percentage": 97.79, "elapsed_time": "1:49:19", "remaining_time": "0:02:28", "throughput": 1033.02, "total_tokens": 6776432} {"current_steps": 75265, "total_steps": 76960, "loss": 0.3756, "lr": 7.393194746525279e-08, "epoch": 19.559511434511435, "percentage": 97.8, "elapsed_time": "1:49:20", "remaining_time": "0:02:27", "throughput": 1033.03, "total_tokens": 6776912} {"current_steps": 75270, "total_steps": 76960, "loss": 0.0116, "lr": 7.349688393624154e-08, "epoch": 19.56081081081081, "percentage": 97.8, "elapsed_time": "1:49:20", "remaining_time": "0:02:27", "throughput": 1033.03, "total_tokens": 6777360} {"current_steps": 75275, "total_steps": 76960, "loss": 0.016, "lr": 7.30631024011691e-08, "epoch": 19.562110187110186, "percentage": 97.81, "elapsed_time": "1:49:21", "remaining_time": "0:02:26", "throughput": 1033.03, "total_tokens": 6777808} {"current_steps": 75280, "total_steps": 76960, "loss": 0.0627, "lr": 7.263060288234535e-08, "epoch": 19.563409563409564, "percentage": 97.82, "elapsed_time": "1:49:21", "remaining_time": "0:02:26", "throughput": 1033.03, "total_tokens": 6778224} {"current_steps": 75285, "total_steps": 76960, "loss": 0.0051, "lr": 7.219938540201366e-08, "epoch": 19.56470893970894, "percentage": 97.82, "elapsed_time": "1:49:21", "remaining_time": "0:02:25", "throughput": 1033.03, "total_tokens": 6778672} {"current_steps": 75290, "total_steps": 76960, "loss": 0.1542, "lr": 7.17694499823507e-08, "epoch": 19.566008316008315, "percentage": 97.83, "elapsed_time": "1:49:22", "remaining_time": "0:02:25", "throughput": 1033.04, "total_tokens": 6779136} {"current_steps": 75295, "total_steps": 76960, "loss": 0.0002, "lr": 7.13407966454721e-08, "epoch": 19.567307692307693, "percentage": 97.84, "elapsed_time": "1:49:22", "remaining_time": "0:02:25", "throughput": 1033.04, "total_tokens": 6779568} {"current_steps": 75300, "total_steps": 76960, "loss": 0.0031, "lr": 7.091342541342139e-08, "epoch": 19.56860706860707, "percentage": 97.84, "elapsed_time": "1:49:23", "remaining_time": "0:02:24", "throughput": 1033.04, "total_tokens": 6780000} {"current_steps": 75305, "total_steps": 76960, "loss": 0.0118, "lr": 7.048733630817817e-08, "epoch": 19.569906444906444, "percentage": 97.85, "elapsed_time": "1:49:23", "remaining_time": "0:02:24", "throughput": 1033.04, "total_tokens": 6780432} {"current_steps": 75310, "total_steps": 76960, "loss": 0.2386, "lr": 7.006252935165824e-08, "epoch": 19.571205821205822, "percentage": 97.86, "elapsed_time": "1:49:23", "remaining_time": "0:02:23", "throughput": 1033.04, "total_tokens": 6780880} {"current_steps": 75315, "total_steps": 76960, "loss": 0.0008, "lr": 6.963900456571081e-08, "epoch": 19.572505197505198, "percentage": 97.86, "elapsed_time": "1:49:24", "remaining_time": "0:02:23", "throughput": 1033.05, "total_tokens": 6781344} {"current_steps": 75320, "total_steps": 76960, "loss": 0.1828, "lr": 6.921676197211291e-08, "epoch": 19.573804573804573, "percentage": 97.87, "elapsed_time": "1:49:24", "remaining_time": "0:02:22", "throughput": 1033.05, "total_tokens": 6781776} {"current_steps": 75325, "total_steps": 76960, "loss": 0.0005, "lr": 6.87958015925888e-08, "epoch": 19.57510395010395, "percentage": 97.88, "elapsed_time": "1:49:25", "remaining_time": "0:02:22", "throughput": 1033.06, "total_tokens": 6782240} {"current_steps": 75330, "total_steps": 76960, "loss": 0.1866, "lr": 6.837612344877952e-08, "epoch": 19.576403326403327, "percentage": 97.88, "elapsed_time": "1:49:25", "remaining_time": "0:02:22", "throughput": 1033.06, "total_tokens": 6782688} {"current_steps": 75335, "total_steps": 76960, "loss": 0.0041, "lr": 6.795772756227891e-08, "epoch": 19.5777027027027, "percentage": 97.89, "elapsed_time": "1:49:26", "remaining_time": "0:02:21", "throughput": 1033.06, "total_tokens": 6783136} {"current_steps": 75340, "total_steps": 76960, "loss": 0.0881, "lr": 6.754061395460032e-08, "epoch": 19.57900207900208, "percentage": 97.9, "elapsed_time": "1:49:26", "remaining_time": "0:02:21", "throughput": 1033.06, "total_tokens": 6783568} {"current_steps": 75345, "total_steps": 76960, "loss": 0.0133, "lr": 6.712478264719601e-08, "epoch": 19.580301455301456, "percentage": 97.9, "elapsed_time": "1:49:26", "remaining_time": "0:02:20", "throughput": 1033.06, "total_tokens": 6784000} {"current_steps": 75350, "total_steps": 76960, "loss": 0.0004, "lr": 6.671023366145169e-08, "epoch": 19.58160083160083, "percentage": 97.91, "elapsed_time": "1:49:27", "remaining_time": "0:02:20", "throughput": 1033.07, "total_tokens": 6784448} {"current_steps": 75355, "total_steps": 76960, "loss": 0.1137, "lr": 6.629696701869193e-08, "epoch": 19.58290020790021, "percentage": 97.91, "elapsed_time": "1:49:27", "remaining_time": "0:02:19", "throughput": 1033.07, "total_tokens": 6784896} {"current_steps": 75360, "total_steps": 76960, "loss": 0.0079, "lr": 6.588498274017196e-08, "epoch": 19.584199584199585, "percentage": 97.92, "elapsed_time": "1:49:28", "remaining_time": "0:02:19", "throughput": 1033.08, "total_tokens": 6785376} {"current_steps": 75365, "total_steps": 76960, "loss": 0.0008, "lr": 6.547428084707485e-08, "epoch": 19.58549896049896, "percentage": 97.93, "elapsed_time": "1:49:28", "remaining_time": "0:02:19", "throughput": 1033.08, "total_tokens": 6785808} {"current_steps": 75370, "total_steps": 76960, "loss": 0.0495, "lr": 6.506486136052814e-08, "epoch": 19.58679833679834, "percentage": 97.93, "elapsed_time": "1:49:28", "remaining_time": "0:02:18", "throughput": 1033.09, "total_tokens": 6786304} {"current_steps": 75375, "total_steps": 76960, "loss": 0.0165, "lr": 6.465672430158443e-08, "epoch": 19.588097713097714, "percentage": 97.94, "elapsed_time": "1:49:29", "remaining_time": "0:02:18", "throughput": 1033.09, "total_tokens": 6786736} {"current_steps": 75380, "total_steps": 76960, "loss": 0.0218, "lr": 6.424986969124081e-08, "epoch": 19.58939708939709, "percentage": 97.95, "elapsed_time": "1:49:29", "remaining_time": "0:02:17", "throughput": 1033.09, "total_tokens": 6787200} {"current_steps": 75385, "total_steps": 76960, "loss": 0.0071, "lr": 6.384429755041665e-08, "epoch": 19.590696465696467, "percentage": 97.95, "elapsed_time": "1:49:30", "remaining_time": "0:02:17", "throughput": 1033.09, "total_tokens": 6787632} {"current_steps": 75390, "total_steps": 76960, "loss": 0.0014, "lr": 6.344000789997307e-08, "epoch": 19.591995841995843, "percentage": 97.96, "elapsed_time": "1:49:30", "remaining_time": "0:02:16", "throughput": 1033.1, "total_tokens": 6788096} {"current_steps": 75395, "total_steps": 76960, "loss": 0.0002, "lr": 6.303700076070173e-08, "epoch": 19.593295218295218, "percentage": 97.97, "elapsed_time": "1:49:31", "remaining_time": "0:02:16", "throughput": 1033.1, "total_tokens": 6788544} {"current_steps": 75400, "total_steps": 76960, "loss": 0.086, "lr": 6.26352761533333e-08, "epoch": 19.594594594594593, "percentage": 97.97, "elapsed_time": "1:49:31", "remaining_time": "0:02:15", "throughput": 1033.11, "total_tokens": 6789024} {"current_steps": 75405, "total_steps": 76960, "loss": 0.1483, "lr": 6.223483409852626e-08, "epoch": 19.59589397089397, "percentage": 97.98, "elapsed_time": "1:49:31", "remaining_time": "0:02:15", "throughput": 1033.11, "total_tokens": 6789440} {"current_steps": 75410, "total_steps": 76960, "loss": 0.2518, "lr": 6.183567461687523e-08, "epoch": 19.597193347193347, "percentage": 97.99, "elapsed_time": "1:49:32", "remaining_time": "0:02:15", "throughput": 1033.12, "total_tokens": 6789952} {"current_steps": 75415, "total_steps": 76960, "loss": 0.0756, "lr": 6.1437797728911e-08, "epoch": 19.598492723492722, "percentage": 97.99, "elapsed_time": "1:49:32", "remaining_time": "0:02:14", "throughput": 1033.13, "total_tokens": 6790416} {"current_steps": 75420, "total_steps": 76960, "loss": 0.1465, "lr": 6.1041203455095e-08, "epoch": 19.5997920997921, "percentage": 98.0, "elapsed_time": "1:49:33", "remaining_time": "0:02:14", "throughput": 1033.14, "total_tokens": 6790912} {"current_steps": 75425, "total_steps": 76960, "loss": 0.0605, "lr": 6.064589181582481e-08, "epoch": 19.601091476091476, "percentage": 98.01, "elapsed_time": "1:49:33", "remaining_time": "0:02:13", "throughput": 1033.14, "total_tokens": 6791360} {"current_steps": 75430, "total_steps": 76960, "loss": 0.2378, "lr": 6.025186283143136e-08, "epoch": 19.60239085239085, "percentage": 98.01, "elapsed_time": "1:49:33", "remaining_time": "0:02:13", "throughput": 1033.14, "total_tokens": 6791792} {"current_steps": 75435, "total_steps": 76960, "loss": 0.182, "lr": 5.985911652218179e-08, "epoch": 19.60369022869023, "percentage": 98.02, "elapsed_time": "1:49:34", "remaining_time": "0:02:12", "throughput": 1033.15, "total_tokens": 6792256} {"current_steps": 75440, "total_steps": 76960, "loss": 0.0131, "lr": 5.946765290827383e-08, "epoch": 19.604989604989605, "percentage": 98.02, "elapsed_time": "1:49:34", "remaining_time": "0:02:12", "throughput": 1033.15, "total_tokens": 6792704} {"current_steps": 75445, "total_steps": 76960, "loss": 0.001, "lr": 5.907747200984415e-08, "epoch": 19.60628898128898, "percentage": 98.03, "elapsed_time": "1:49:35", "remaining_time": "0:02:12", "throughput": 1033.15, "total_tokens": 6793136} {"current_steps": 75450, "total_steps": 76960, "loss": 0.001, "lr": 5.8688573846954474e-08, "epoch": 19.60758835758836, "percentage": 98.04, "elapsed_time": "1:49:35", "remaining_time": "0:02:11", "throughput": 1033.15, "total_tokens": 6793552} {"current_steps": 75455, "total_steps": 76960, "loss": 0.0011, "lr": 5.8300958439608254e-08, "epoch": 19.608887733887734, "percentage": 98.04, "elapsed_time": "1:49:35", "remaining_time": "0:02:11", "throughput": 1033.15, "total_tokens": 6794016} {"current_steps": 75460, "total_steps": 76960, "loss": 0.1093, "lr": 5.791462580774232e-08, "epoch": 19.61018711018711, "percentage": 98.05, "elapsed_time": "1:49:36", "remaining_time": "0:02:10", "throughput": 1033.16, "total_tokens": 6794464} {"current_steps": 75465, "total_steps": 76960, "loss": 0.0077, "lr": 5.7529575971226877e-08, "epoch": 19.611486486486488, "percentage": 98.06, "elapsed_time": "1:49:36", "remaining_time": "0:02:10", "throughput": 1033.17, "total_tokens": 6794944} {"current_steps": 75470, "total_steps": 76960, "loss": 0.1612, "lr": 5.7145808949865546e-08, "epoch": 19.612785862785863, "percentage": 98.06, "elapsed_time": "1:49:37", "remaining_time": "0:02:09", "throughput": 1033.17, "total_tokens": 6795392} {"current_steps": 75475, "total_steps": 76960, "loss": 0.5882, "lr": 5.676332476339252e-08, "epoch": 19.614085239085238, "percentage": 98.07, "elapsed_time": "1:49:37", "remaining_time": "0:02:09", "throughput": 1033.17, "total_tokens": 6795824} {"current_steps": 75480, "total_steps": 76960, "loss": 0.0006, "lr": 5.638212343148097e-08, "epoch": 19.615384615384617, "percentage": 98.08, "elapsed_time": "1:49:38", "remaining_time": "0:02:08", "throughput": 1033.18, "total_tokens": 6796288} {"current_steps": 75485, "total_steps": 76960, "loss": 0.1714, "lr": 5.600220497373465e-08, "epoch": 19.616683991683992, "percentage": 98.08, "elapsed_time": "1:49:38", "remaining_time": "0:02:08", "throughput": 1033.18, "total_tokens": 6796720} {"current_steps": 75490, "total_steps": 76960, "loss": 0.0352, "lr": 5.562356940969904e-08, "epoch": 19.617983367983367, "percentage": 98.09, "elapsed_time": "1:49:38", "remaining_time": "0:02:08", "throughput": 1033.19, "total_tokens": 6797216} {"current_steps": 75495, "total_steps": 76960, "loss": 0.1328, "lr": 5.5246216758841895e-08, "epoch": 19.619282744282746, "percentage": 98.1, "elapsed_time": "1:49:39", "remaining_time": "0:02:07", "throughput": 1033.19, "total_tokens": 6797664} {"current_steps": 75500, "total_steps": 76960, "loss": 0.2572, "lr": 5.48701470405727e-08, "epoch": 19.62058212058212, "percentage": 98.1, "elapsed_time": "1:49:39", "remaining_time": "0:02:07", "throughput": 1033.19, "total_tokens": 6798112} {"current_steps": 75505, "total_steps": 76960, "loss": 0.0026, "lr": 5.4495360274231524e-08, "epoch": 19.621881496881496, "percentage": 98.11, "elapsed_time": "1:49:40", "remaining_time": "0:02:06", "throughput": 1033.19, "total_tokens": 6798544} {"current_steps": 75510, "total_steps": 76960, "loss": 0.035, "lr": 5.41218564790974e-08, "epoch": 19.623180873180875, "percentage": 98.12, "elapsed_time": "1:49:40", "remaining_time": "0:02:06", "throughput": 1033.2, "total_tokens": 6799008} {"current_steps": 75515, "total_steps": 76960, "loss": 0.0008, "lr": 5.374963567437719e-08, "epoch": 19.62448024948025, "percentage": 98.12, "elapsed_time": "1:49:40", "remaining_time": "0:02:05", "throughput": 1033.2, "total_tokens": 6799456} {"current_steps": 75520, "total_steps": 76960, "loss": 0.0046, "lr": 5.3378697879216676e-08, "epoch": 19.625779625779625, "percentage": 98.13, "elapsed_time": "1:49:41", "remaining_time": "0:02:05", "throughput": 1033.2, "total_tokens": 6799904} {"current_steps": 75525, "total_steps": 76960, "loss": 0.0103, "lr": 5.300904311269228e-08, "epoch": 19.627079002079, "percentage": 98.14, "elapsed_time": "1:49:41", "remaining_time": "0:02:05", "throughput": 1033.2, "total_tokens": 6800336} {"current_steps": 75530, "total_steps": 76960, "loss": 0.1673, "lr": 5.2640671393816566e-08, "epoch": 19.62837837837838, "percentage": 98.14, "elapsed_time": "1:49:42", "remaining_time": "0:02:04", "throughput": 1033.21, "total_tokens": 6800816} {"current_steps": 75535, "total_steps": 76960, "loss": 0.2626, "lr": 5.227358274153271e-08, "epoch": 19.629677754677754, "percentage": 98.15, "elapsed_time": "1:49:42", "remaining_time": "0:02:04", "throughput": 1033.21, "total_tokens": 6801248} {"current_steps": 75540, "total_steps": 76960, "loss": 0.0003, "lr": 5.1907777174722835e-08, "epoch": 19.63097713097713, "percentage": 98.15, "elapsed_time": "1:49:43", "remaining_time": "0:02:03", "throughput": 1033.22, "total_tokens": 6801728} {"current_steps": 75545, "total_steps": 76960, "loss": 0.0016, "lr": 5.154325471220245e-08, "epoch": 19.632276507276508, "percentage": 98.16, "elapsed_time": "1:49:43", "remaining_time": "0:02:03", "throughput": 1033.22, "total_tokens": 6802176} {"current_steps": 75550, "total_steps": 76960, "loss": 0.283, "lr": 5.1180015372714886e-08, "epoch": 19.633575883575883, "percentage": 98.17, "elapsed_time": "1:49:43", "remaining_time": "0:02:02", "throughput": 1033.22, "total_tokens": 6802608} {"current_steps": 75555, "total_steps": 76960, "loss": 0.0003, "lr": 5.081805917494242e-08, "epoch": 19.63487525987526, "percentage": 98.17, "elapsed_time": "1:49:44", "remaining_time": "0:02:02", "throughput": 1033.23, "total_tokens": 6803072} {"current_steps": 75560, "total_steps": 76960, "loss": 0.2331, "lr": 5.045738613750628e-08, "epoch": 19.636174636174637, "percentage": 98.18, "elapsed_time": "1:49:44", "remaining_time": "0:02:02", "throughput": 1033.23, "total_tokens": 6803504} {"current_steps": 75565, "total_steps": 76960, "loss": 0.1971, "lr": 5.009799627894718e-08, "epoch": 19.637474012474012, "percentage": 98.19, "elapsed_time": "1:49:45", "remaining_time": "0:02:01", "throughput": 1033.23, "total_tokens": 6803936} {"current_steps": 75570, "total_steps": 76960, "loss": 0.0465, "lr": 4.973988961775866e-08, "epoch": 19.638773388773387, "percentage": 98.19, "elapsed_time": "1:49:45", "remaining_time": "0:02:01", "throughput": 1033.23, "total_tokens": 6804368} {"current_steps": 75575, "total_steps": 76960, "loss": 0.0292, "lr": 4.9383066172351e-08, "epoch": 19.640072765072766, "percentage": 98.2, "elapsed_time": "1:49:45", "remaining_time": "0:02:00", "throughput": 1033.24, "total_tokens": 6804832} {"current_steps": 75580, "total_steps": 76960, "loss": 0.0761, "lr": 4.902752596107896e-08, "epoch": 19.64137214137214, "percentage": 98.21, "elapsed_time": "1:49:46", "remaining_time": "0:02:00", "throughput": 1033.24, "total_tokens": 6805280} {"current_steps": 75585, "total_steps": 76960, "loss": 0.0009, "lr": 4.867326900223068e-08, "epoch": 19.642671517671516, "percentage": 98.21, "elapsed_time": "1:49:46", "remaining_time": "0:01:59", "throughput": 1033.25, "total_tokens": 6805776} {"current_steps": 75590, "total_steps": 76960, "loss": 0.2865, "lr": 4.832029531401938e-08, "epoch": 19.643970893970895, "percentage": 98.22, "elapsed_time": "1:49:47", "remaining_time": "0:01:59", "throughput": 1033.25, "total_tokens": 6806224} {"current_steps": 75595, "total_steps": 76960, "loss": 0.2045, "lr": 4.7968604914605534e-08, "epoch": 19.64527027027027, "percentage": 98.23, "elapsed_time": "1:49:47", "remaining_time": "0:01:58", "throughput": 1033.26, "total_tokens": 6806688} {"current_steps": 75600, "total_steps": 76960, "loss": 0.4816, "lr": 4.761819782207466e-08, "epoch": 19.646569646569645, "percentage": 98.23, "elapsed_time": "1:49:48", "remaining_time": "0:01:58", "throughput": 1033.26, "total_tokens": 6807136} {"current_steps": 75605, "total_steps": 76960, "loss": 0.0026, "lr": 4.726907405444569e-08, "epoch": 19.647869022869024, "percentage": 98.24, "elapsed_time": "1:49:48", "remaining_time": "0:01:58", "throughput": 1033.26, "total_tokens": 6807584} {"current_steps": 75610, "total_steps": 76960, "loss": 0.3166, "lr": 4.692123362967926e-08, "epoch": 19.6491683991684, "percentage": 98.25, "elapsed_time": "1:49:48", "remaining_time": "0:01:57", "throughput": 1033.27, "total_tokens": 6808048} {"current_steps": 75615, "total_steps": 76960, "loss": 0.1089, "lr": 4.657467656566106e-08, "epoch": 19.650467775467774, "percentage": 98.25, "elapsed_time": "1:49:49", "remaining_time": "0:01:57", "throughput": 1033.27, "total_tokens": 6808480} {"current_steps": 75620, "total_steps": 76960, "loss": 0.119, "lr": 4.6229402880215713e-08, "epoch": 19.651767151767153, "percentage": 98.26, "elapsed_time": "1:49:49", "remaining_time": "0:01:56", "throughput": 1033.27, "total_tokens": 6808896} {"current_steps": 75625, "total_steps": 76960, "loss": 0.0025, "lr": 4.5885412591104016e-08, "epoch": 19.653066528066528, "percentage": 98.27, "elapsed_time": "1:49:50", "remaining_time": "0:01:56", "throughput": 1033.27, "total_tokens": 6809344} {"current_steps": 75630, "total_steps": 76960, "loss": 0.0943, "lr": 4.55427057160146e-08, "epoch": 19.654365904365903, "percentage": 98.27, "elapsed_time": "1:49:50", "remaining_time": "0:01:55", "throughput": 1033.28, "total_tokens": 6809808} {"current_steps": 75635, "total_steps": 76960, "loss": 0.1022, "lr": 4.520128227257226e-08, "epoch": 19.655665280665282, "percentage": 98.28, "elapsed_time": "1:49:50", "remaining_time": "0:01:55", "throughput": 1033.28, "total_tokens": 6810256} {"current_steps": 75640, "total_steps": 76960, "loss": 0.0413, "lr": 4.4861142278340704e-08, "epoch": 19.656964656964657, "percentage": 98.28, "elapsed_time": "1:49:51", "remaining_time": "0:01:55", "throughput": 1033.28, "total_tokens": 6810688} {"current_steps": 75645, "total_steps": 76960, "loss": 0.0015, "lr": 4.452228575081152e-08, "epoch": 19.658264033264032, "percentage": 98.29, "elapsed_time": "1:49:51", "remaining_time": "0:01:54", "throughput": 1033.29, "total_tokens": 6811152} {"current_steps": 75650, "total_steps": 76960, "loss": 0.0008, "lr": 4.4184712707412426e-08, "epoch": 19.65956340956341, "percentage": 98.3, "elapsed_time": "1:49:52", "remaining_time": "0:01:54", "throughput": 1033.29, "total_tokens": 6811600} {"current_steps": 75655, "total_steps": 76960, "loss": 0.001, "lr": 4.384842316550453e-08, "epoch": 19.660862785862786, "percentage": 98.3, "elapsed_time": "1:49:52", "remaining_time": "0:01:53", "throughput": 1033.29, "total_tokens": 6812016} {"current_steps": 75660, "total_steps": 76960, "loss": 0.0009, "lr": 4.351341714238233e-08, "epoch": 19.66216216216216, "percentage": 98.31, "elapsed_time": "1:49:52", "remaining_time": "0:01:53", "throughput": 1033.29, "total_tokens": 6812464} {"current_steps": 75665, "total_steps": 76960, "loss": 0.3542, "lr": 4.317969465527927e-08, "epoch": 19.66346153846154, "percentage": 98.32, "elapsed_time": "1:49:53", "remaining_time": "0:01:52", "throughput": 1033.3, "total_tokens": 6812928} {"current_steps": 75670, "total_steps": 76960, "loss": 0.308, "lr": 4.2847255721356616e-08, "epoch": 19.664760914760915, "percentage": 98.32, "elapsed_time": "1:49:53", "remaining_time": "0:01:52", "throughput": 1033.3, "total_tokens": 6813392} {"current_steps": 75675, "total_steps": 76960, "loss": 0.0014, "lr": 4.251610035771181e-08, "epoch": 19.66606029106029, "percentage": 98.33, "elapsed_time": "1:49:54", "remaining_time": "0:01:51", "throughput": 1033.3, "total_tokens": 6813840} {"current_steps": 75680, "total_steps": 76960, "loss": 0.136, "lr": 4.218622858137844e-08, "epoch": 19.66735966735967, "percentage": 98.34, "elapsed_time": "1:49:54", "remaining_time": "0:01:51", "throughput": 1033.31, "total_tokens": 6814320} {"current_steps": 75685, "total_steps": 76960, "loss": 0.1466, "lr": 4.1857640409317946e-08, "epoch": 19.668659043659044, "percentage": 98.34, "elapsed_time": "1:49:55", "remaining_time": "0:01:51", "throughput": 1033.32, "total_tokens": 6814816} {"current_steps": 75690, "total_steps": 76960, "loss": 0.2458, "lr": 4.153033585843624e-08, "epoch": 19.66995841995842, "percentage": 98.35, "elapsed_time": "1:49:55", "remaining_time": "0:01:50", "throughput": 1033.33, "total_tokens": 6815264} {"current_steps": 75695, "total_steps": 76960, "loss": 0.0044, "lr": 4.120431494556154e-08, "epoch": 19.671257796257795, "percentage": 98.36, "elapsed_time": "1:49:55", "remaining_time": "0:01:50", "throughput": 1033.33, "total_tokens": 6815728} {"current_steps": 75700, "total_steps": 76960, "loss": 0.0549, "lr": 4.087957768746375e-08, "epoch": 19.672557172557173, "percentage": 98.36, "elapsed_time": "1:49:56", "remaining_time": "0:01:49", "throughput": 1033.33, "total_tokens": 6816176} {"current_steps": 75705, "total_steps": 76960, "loss": 0.0057, "lr": 4.055612410084342e-08, "epoch": 19.67385654885655, "percentage": 98.37, "elapsed_time": "1:49:56", "remaining_time": "0:01:49", "throughput": 1033.34, "total_tokens": 6816624} {"current_steps": 75710, "total_steps": 76960, "loss": 0.0007, "lr": 4.023395420233722e-08, "epoch": 19.675155925155924, "percentage": 98.38, "elapsed_time": "1:49:57", "remaining_time": "0:01:48", "throughput": 1033.34, "total_tokens": 6817056} {"current_steps": 75715, "total_steps": 76960, "loss": 0.0073, "lr": 3.9913068008512466e-08, "epoch": 19.676455301455302, "percentage": 98.38, "elapsed_time": "1:49:57", "remaining_time": "0:01:48", "throughput": 1033.34, "total_tokens": 6817488} {"current_steps": 75720, "total_steps": 76960, "loss": 0.0003, "lr": 3.9593465535875396e-08, "epoch": 19.677754677754677, "percentage": 98.39, "elapsed_time": "1:49:57", "remaining_time": "0:01:48", "throughput": 1033.35, "total_tokens": 6817968} {"current_steps": 75725, "total_steps": 76960, "loss": 0.0019, "lr": 3.927514680086286e-08, "epoch": 19.679054054054053, "percentage": 98.4, "elapsed_time": "1:49:58", "remaining_time": "0:01:47", "throughput": 1033.35, "total_tokens": 6818416} {"current_steps": 75730, "total_steps": 76960, "loss": 0.0029, "lr": 3.89581118198451e-08, "epoch": 19.68035343035343, "percentage": 98.4, "elapsed_time": "1:49:58", "remaining_time": "0:01:47", "throughput": 1033.35, "total_tokens": 6818864} {"current_steps": 75735, "total_steps": 76960, "loss": 0.0011, "lr": 3.8642360609128516e-08, "epoch": 19.681652806652806, "percentage": 98.41, "elapsed_time": "1:49:59", "remaining_time": "0:01:46", "throughput": 1033.36, "total_tokens": 6819328} {"current_steps": 75740, "total_steps": 76960, "loss": 0.0006, "lr": 3.832789318495289e-08, "epoch": 19.68295218295218, "percentage": 98.41, "elapsed_time": "1:49:59", "remaining_time": "0:01:46", "throughput": 1033.36, "total_tokens": 6819792} {"current_steps": 75745, "total_steps": 76960, "loss": 0.4826, "lr": 3.8014709563488625e-08, "epoch": 19.68425155925156, "percentage": 98.42, "elapsed_time": "1:50:00", "remaining_time": "0:01:45", "throughput": 1033.37, "total_tokens": 6820256} {"current_steps": 75750, "total_steps": 76960, "loss": 0.2011, "lr": 3.7702809760847833e-08, "epoch": 19.685550935550935, "percentage": 98.43, "elapsed_time": "1:50:00", "remaining_time": "0:01:45", "throughput": 1033.37, "total_tokens": 6820688} {"current_steps": 75755, "total_steps": 76960, "loss": 0.0188, "lr": 3.7392193793067684e-08, "epoch": 19.68685031185031, "percentage": 98.43, "elapsed_time": "1:50:00", "remaining_time": "0:01:44", "throughput": 1033.36, "total_tokens": 6821088} {"current_steps": 75760, "total_steps": 76960, "loss": 0.039, "lr": 3.708286167612707e-08, "epoch": 19.68814968814969, "percentage": 98.44, "elapsed_time": "1:50:01", "remaining_time": "0:01:44", "throughput": 1033.37, "total_tokens": 6821552} {"current_steps": 75765, "total_steps": 76960, "loss": 0.0093, "lr": 3.677481342592992e-08, "epoch": 19.689449064449065, "percentage": 98.45, "elapsed_time": "1:50:01", "remaining_time": "0:01:44", "throughput": 1033.38, "total_tokens": 6822016} {"current_steps": 75770, "total_steps": 76960, "loss": 0.195, "lr": 3.646804905832468e-08, "epoch": 19.69074844074844, "percentage": 98.45, "elapsed_time": "1:50:02", "remaining_time": "0:01:43", "throughput": 1033.38, "total_tokens": 6822464} {"current_steps": 75775, "total_steps": 76960, "loss": 0.5548, "lr": 3.6162568589084845e-08, "epoch": 19.69204781704782, "percentage": 98.46, "elapsed_time": "1:50:02", "remaining_time": "0:01:43", "throughput": 1033.38, "total_tokens": 6822912} {"current_steps": 75780, "total_steps": 76960, "loss": 0.2642, "lr": 3.585837203392561e-08, "epoch": 19.693347193347194, "percentage": 98.47, "elapsed_time": "1:50:02", "remaining_time": "0:01:42", "throughput": 1033.38, "total_tokens": 6823344} {"current_steps": 75785, "total_steps": 76960, "loss": 0.0004, "lr": 3.555545940848726e-08, "epoch": 19.69464656964657, "percentage": 98.47, "elapsed_time": "1:50:03", "remaining_time": "0:01:42", "throughput": 1033.38, "total_tokens": 6823792} {"current_steps": 75790, "total_steps": 76960, "loss": 0.0105, "lr": 3.525383072835453e-08, "epoch": 19.695945945945947, "percentage": 98.48, "elapsed_time": "1:50:03", "remaining_time": "0:01:41", "throughput": 1033.39, "total_tokens": 6824224} {"current_steps": 75795, "total_steps": 76960, "loss": 0.0004, "lr": 3.495348600903448e-08, "epoch": 19.697245322245323, "percentage": 98.49, "elapsed_time": "1:50:04", "remaining_time": "0:01:41", "throughput": 1033.39, "total_tokens": 6824656} {"current_steps": 75800, "total_steps": 76960, "loss": 0.0059, "lr": 3.4654425265978616e-08, "epoch": 19.698544698544698, "percentage": 98.49, "elapsed_time": "1:50:04", "remaining_time": "0:01:41", "throughput": 1033.4, "total_tokens": 6825152} {"current_steps": 75805, "total_steps": 76960, "loss": 0.1261, "lr": 3.435664851456632e-08, "epoch": 19.699844074844076, "percentage": 98.5, "elapsed_time": "1:50:04", "remaining_time": "0:01:40", "throughput": 1033.4, "total_tokens": 6825600} {"current_steps": 75810, "total_steps": 76960, "loss": 0.2064, "lr": 3.406015577011312e-08, "epoch": 19.70114345114345, "percentage": 98.51, "elapsed_time": "1:50:05", "remaining_time": "0:01:40", "throughput": 1033.4, "total_tokens": 6826048} {"current_steps": 75815, "total_steps": 76960, "loss": 0.0035, "lr": 3.376494704786515e-08, "epoch": 19.702442827442827, "percentage": 98.51, "elapsed_time": "1:50:05", "remaining_time": "0:01:39", "throughput": 1033.4, "total_tokens": 6826464} {"current_steps": 75820, "total_steps": 76960, "loss": 0.0056, "lr": 3.347102236301025e-08, "epoch": 19.703742203742205, "percentage": 98.52, "elapsed_time": "1:50:06", "remaining_time": "0:01:39", "throughput": 1033.4, "total_tokens": 6826880} {"current_steps": 75825, "total_steps": 76960, "loss": 0.2354, "lr": 3.317838173066135e-08, "epoch": 19.70504158004158, "percentage": 98.53, "elapsed_time": "1:50:06", "remaining_time": "0:01:38", "throughput": 1033.41, "total_tokens": 6827344} {"current_steps": 75830, "total_steps": 76960, "loss": 0.1935, "lr": 3.28870251658675e-08, "epoch": 19.706340956340956, "percentage": 98.53, "elapsed_time": "1:50:07", "remaining_time": "0:01:38", "throughput": 1033.41, "total_tokens": 6827776} {"current_steps": 75835, "total_steps": 76960, "loss": 0.0107, "lr": 3.259695268361951e-08, "epoch": 19.70764033264033, "percentage": 98.54, "elapsed_time": "1:50:07", "remaining_time": "0:01:38", "throughput": 1033.41, "total_tokens": 6828224} {"current_steps": 75840, "total_steps": 76960, "loss": 0.0024, "lr": 3.230816429883321e-08, "epoch": 19.70893970893971, "percentage": 98.54, "elapsed_time": "1:50:07", "remaining_time": "0:01:37", "throughput": 1033.41, "total_tokens": 6828656} {"current_steps": 75845, "total_steps": 76960, "loss": 0.0162, "lr": 3.2020660026360615e-08, "epoch": 19.710239085239085, "percentage": 98.55, "elapsed_time": "1:50:08", "remaining_time": "0:01:37", "throughput": 1033.41, "total_tokens": 6829104} {"current_steps": 75850, "total_steps": 76960, "loss": 0.3247, "lr": 3.173443988098712e-08, "epoch": 19.71153846153846, "percentage": 98.56, "elapsed_time": "1:50:08", "remaining_time": "0:01:36", "throughput": 1033.42, "total_tokens": 6829552} {"current_steps": 75855, "total_steps": 76960, "loss": 0.0046, "lr": 3.144950387743428e-08, "epoch": 19.71283783783784, "percentage": 98.56, "elapsed_time": "1:50:09", "remaining_time": "0:01:36", "throughput": 1033.42, "total_tokens": 6830016} {"current_steps": 75860, "total_steps": 76960, "loss": 0.0574, "lr": 3.116585203035705e-08, "epoch": 19.714137214137214, "percentage": 98.57, "elapsed_time": "1:50:09", "remaining_time": "0:01:35", "throughput": 1033.42, "total_tokens": 6830448} {"current_steps": 75865, "total_steps": 76960, "loss": 0.1859, "lr": 3.0883484354346514e-08, "epoch": 19.71543659043659, "percentage": 98.58, "elapsed_time": "1:50:09", "remaining_time": "0:01:35", "throughput": 1033.43, "total_tokens": 6830912} {"current_steps": 75870, "total_steps": 76960, "loss": 0.0023, "lr": 3.060240086392163e-08, "epoch": 19.716735966735968, "percentage": 98.58, "elapsed_time": "1:50:10", "remaining_time": "0:01:34", "throughput": 1033.44, "total_tokens": 6831440} {"current_steps": 75875, "total_steps": 76960, "loss": 0.0068, "lr": 3.032260157354028e-08, "epoch": 19.718035343035343, "percentage": 98.59, "elapsed_time": "1:50:10", "remaining_time": "0:01:34", "throughput": 1033.45, "total_tokens": 6831920} {"current_steps": 75880, "total_steps": 76960, "loss": 0.0112, "lr": 3.004408649759094e-08, "epoch": 19.719334719334718, "percentage": 98.6, "elapsed_time": "1:50:11", "remaining_time": "0:01:34", "throughput": 1033.45, "total_tokens": 6832320} {"current_steps": 75885, "total_steps": 76960, "loss": 0.0656, "lr": 2.9766855650398273e-08, "epoch": 19.720634095634097, "percentage": 98.6, "elapsed_time": "1:50:11", "remaining_time": "0:01:33", "throughput": 1033.45, "total_tokens": 6832768} {"current_steps": 75890, "total_steps": 76960, "loss": 0.0072, "lr": 2.9490909046225867e-08, "epoch": 19.721933471933472, "percentage": 98.61, "elapsed_time": "1:50:12", "remaining_time": "0:01:33", "throughput": 1033.44, "total_tokens": 6833168} {"current_steps": 75895, "total_steps": 76960, "loss": 0.0004, "lr": 2.921624669925682e-08, "epoch": 19.723232848232847, "percentage": 98.62, "elapsed_time": "1:50:12", "remaining_time": "0:01:32", "throughput": 1033.45, "total_tokens": 6833600} {"current_steps": 75900, "total_steps": 76960, "loss": 0.0002, "lr": 2.8942868623624276e-08, "epoch": 19.724532224532226, "percentage": 98.62, "elapsed_time": "1:50:12", "remaining_time": "0:01:32", "throughput": 1033.45, "total_tokens": 6834048} {"current_steps": 75905, "total_steps": 76960, "loss": 0.053, "lr": 2.8670774833386426e-08, "epoch": 19.7258316008316, "percentage": 98.63, "elapsed_time": "1:50:13", "remaining_time": "0:01:31", "throughput": 1033.45, "total_tokens": 6834496} {"current_steps": 75910, "total_steps": 76960, "loss": 0.0009, "lr": 2.8399965342537637e-08, "epoch": 19.727130977130976, "percentage": 98.64, "elapsed_time": "1:50:13", "remaining_time": "0:01:31", "throughput": 1033.45, "total_tokens": 6834944} {"current_steps": 75915, "total_steps": 76960, "loss": 0.0032, "lr": 2.813044016500288e-08, "epoch": 19.728430353430355, "percentage": 98.64, "elapsed_time": "1:50:14", "remaining_time": "0:01:31", "throughput": 1033.45, "total_tokens": 6835360} {"current_steps": 75920, "total_steps": 76960, "loss": 0.0808, "lr": 2.786219931464884e-08, "epoch": 19.72972972972973, "percentage": 98.65, "elapsed_time": "1:50:14", "remaining_time": "0:01:30", "throughput": 1033.46, "total_tokens": 6835824} {"current_steps": 75925, "total_steps": 76960, "loss": 0.0466, "lr": 2.7595242805267262e-08, "epoch": 19.731029106029105, "percentage": 98.66, "elapsed_time": "1:50:14", "remaining_time": "0:01:30", "throughput": 1033.46, "total_tokens": 6836288} {"current_steps": 75930, "total_steps": 76960, "loss": 0.1236, "lr": 2.7329570650591606e-08, "epoch": 19.732328482328484, "percentage": 98.66, "elapsed_time": "1:50:15", "remaining_time": "0:01:29", "throughput": 1033.47, "total_tokens": 6836768} {"current_steps": 75935, "total_steps": 76960, "loss": 0.0459, "lr": 2.7065182864283167e-08, "epoch": 19.73362785862786, "percentage": 98.67, "elapsed_time": "1:50:15", "remaining_time": "0:01:29", "throughput": 1033.47, "total_tokens": 6837216} {"current_steps": 75940, "total_steps": 76960, "loss": 0.0004, "lr": 2.68020794599394e-08, "epoch": 19.734927234927234, "percentage": 98.67, "elapsed_time": "1:50:16", "remaining_time": "0:01:28", "throughput": 1033.48, "total_tokens": 6837696} {"current_steps": 75945, "total_steps": 76960, "loss": 0.085, "lr": 2.6540260451093922e-08, "epoch": 19.736226611226613, "percentage": 98.68, "elapsed_time": "1:50:16", "remaining_time": "0:01:28", "throughput": 1033.49, "total_tokens": 6838176} {"current_steps": 75950, "total_steps": 76960, "loss": 0.004, "lr": 2.6279725851208194e-08, "epoch": 19.737525987525988, "percentage": 98.69, "elapsed_time": "1:50:17", "remaining_time": "0:01:27", "throughput": 1033.49, "total_tokens": 6838592} {"current_steps": 75955, "total_steps": 76960, "loss": 0.0005, "lr": 2.602047567368815e-08, "epoch": 19.738825363825363, "percentage": 98.69, "elapsed_time": "1:50:17", "remaining_time": "0:01:27", "throughput": 1033.5, "total_tokens": 6839072} {"current_steps": 75960, "total_steps": 76960, "loss": 0.0017, "lr": 2.5762509931862023e-08, "epoch": 19.74012474012474, "percentage": 98.7, "elapsed_time": "1:50:17", "remaining_time": "0:01:27", "throughput": 1033.5, "total_tokens": 6839536} {"current_steps": 75965, "total_steps": 76960, "loss": 0.1345, "lr": 2.5505828639002527e-08, "epoch": 19.741424116424117, "percentage": 98.71, "elapsed_time": "1:50:18", "remaining_time": "0:01:26", "throughput": 1033.5, "total_tokens": 6839968} {"current_steps": 75970, "total_steps": 76960, "loss": 0.0043, "lr": 2.5250431808304665e-08, "epoch": 19.742723492723492, "percentage": 98.71, "elapsed_time": "1:50:18", "remaining_time": "0:01:26", "throughput": 1033.5, "total_tokens": 6840384} {"current_steps": 75975, "total_steps": 76960, "loss": 0.0031, "lr": 2.4996319452907925e-08, "epoch": 19.74402286902287, "percentage": 98.72, "elapsed_time": "1:50:19", "remaining_time": "0:01:25", "throughput": 1033.5, "total_tokens": 6840832} {"current_steps": 75980, "total_steps": 76960, "loss": 0.0558, "lr": 2.474349158587963e-08, "epoch": 19.745322245322246, "percentage": 98.73, "elapsed_time": "1:50:19", "remaining_time": "0:01:25", "throughput": 1033.51, "total_tokens": 6841296} {"current_steps": 75985, "total_steps": 76960, "loss": 0.1946, "lr": 2.449194822022327e-08, "epoch": 19.74662162162162, "percentage": 98.73, "elapsed_time": "1:50:19", "remaining_time": "0:01:24", "throughput": 1033.51, "total_tokens": 6841760} {"current_steps": 75990, "total_steps": 76960, "loss": 0.0609, "lr": 2.4241689368878494e-08, "epoch": 19.747920997921, "percentage": 98.74, "elapsed_time": "1:50:20", "remaining_time": "0:01:24", "throughput": 1033.52, "total_tokens": 6842240} {"current_steps": 75995, "total_steps": 76960, "loss": 0.1413, "lr": 2.3992715044710012e-08, "epoch": 19.749220374220375, "percentage": 98.75, "elapsed_time": "1:50:20", "remaining_time": "0:01:24", "throughput": 1033.53, "total_tokens": 6842704} {"current_steps": 76000, "total_steps": 76960, "loss": 0.0078, "lr": 2.374502526053257e-08, "epoch": 19.75051975051975, "percentage": 98.75, "elapsed_time": "1:50:21", "remaining_time": "0:01:23", "throughput": 1033.52, "total_tokens": 6843120} {"current_steps": 76005, "total_steps": 76960, "loss": 0.171, "lr": 2.349862002907488e-08, "epoch": 19.751819126819125, "percentage": 98.76, "elapsed_time": "1:50:21", "remaining_time": "0:01:23", "throughput": 1033.53, "total_tokens": 6843584} {"current_steps": 76010, "total_steps": 76960, "loss": 0.0009, "lr": 2.325349936301846e-08, "epoch": 19.753118503118504, "percentage": 98.77, "elapsed_time": "1:50:21", "remaining_time": "0:01:22", "throughput": 1033.53, "total_tokens": 6844032} {"current_steps": 76015, "total_steps": 76960, "loss": 0.4221, "lr": 2.300966327496157e-08, "epoch": 19.75441787941788, "percentage": 98.77, "elapsed_time": "1:50:22", "remaining_time": "0:01:22", "throughput": 1033.54, "total_tokens": 6844512} {"current_steps": 76020, "total_steps": 76960, "loss": 0.0592, "lr": 2.27671117774525e-08, "epoch": 19.755717255717254, "percentage": 98.78, "elapsed_time": "1:50:22", "remaining_time": "0:01:21", "throughput": 1033.54, "total_tokens": 6844928} {"current_steps": 76025, "total_steps": 76960, "loss": 0.0016, "lr": 2.2525844882964607e-08, "epoch": 19.757016632016633, "percentage": 98.79, "elapsed_time": "1:50:23", "remaining_time": "0:01:21", "throughput": 1033.54, "total_tokens": 6845376} {"current_steps": 76030, "total_steps": 76960, "loss": 0.0011, "lr": 2.2285862603901865e-08, "epoch": 19.758316008316008, "percentage": 98.79, "elapsed_time": "1:50:23", "remaining_time": "0:01:21", "throughput": 1033.55, "total_tokens": 6845856} {"current_steps": 76035, "total_steps": 76960, "loss": 0.0067, "lr": 2.2047164952609944e-08, "epoch": 19.759615384615383, "percentage": 98.8, "elapsed_time": "1:50:24", "remaining_time": "0:01:20", "throughput": 1033.56, "total_tokens": 6846320} {"current_steps": 76040, "total_steps": 76960, "loss": 0.0047, "lr": 2.1809751941365142e-08, "epoch": 19.760914760914762, "percentage": 98.8, "elapsed_time": "1:50:24", "remaining_time": "0:01:20", "throughput": 1033.56, "total_tokens": 6846752} {"current_steps": 76045, "total_steps": 76960, "loss": 0.0018, "lr": 2.1573623582377133e-08, "epoch": 19.762214137214137, "percentage": 98.81, "elapsed_time": "1:50:24", "remaining_time": "0:01:19", "throughput": 1033.56, "total_tokens": 6847232} {"current_steps": 76050, "total_steps": 76960, "loss": 0.0017, "lr": 2.1338779887794534e-08, "epoch": 19.763513513513512, "percentage": 98.82, "elapsed_time": "1:50:25", "remaining_time": "0:01:19", "throughput": 1033.57, "total_tokens": 6847664} {"current_steps": 76055, "total_steps": 76960, "loss": 0.0627, "lr": 2.1105220869688246e-08, "epoch": 19.76481288981289, "percentage": 98.82, "elapsed_time": "1:50:25", "remaining_time": "0:01:18", "throughput": 1033.56, "total_tokens": 6848080} {"current_steps": 76060, "total_steps": 76960, "loss": 0.0167, "lr": 2.0872946540076433e-08, "epoch": 19.766112266112266, "percentage": 98.83, "elapsed_time": "1:50:26", "remaining_time": "0:01:18", "throughput": 1033.57, "total_tokens": 6848576} {"current_steps": 76065, "total_steps": 76960, "loss": 0.1462, "lr": 2.064195691089954e-08, "epoch": 19.76741164241164, "percentage": 98.84, "elapsed_time": "1:50:26", "remaining_time": "0:01:17", "throughput": 1033.57, "total_tokens": 6849008} {"current_steps": 76070, "total_steps": 76960, "loss": 0.0903, "lr": 2.0412251994042508e-08, "epoch": 19.76871101871102, "percentage": 98.84, "elapsed_time": "1:50:26", "remaining_time": "0:01:17", "throughput": 1033.58, "total_tokens": 6849488} {"current_steps": 76075, "total_steps": 76960, "loss": 0.001, "lr": 2.018383180131811e-08, "epoch": 19.770010395010395, "percentage": 98.85, "elapsed_time": "1:50:27", "remaining_time": "0:01:17", "throughput": 1033.58, "total_tokens": 6849920} {"current_steps": 76080, "total_steps": 76960, "loss": 0.044, "lr": 1.995669634447528e-08, "epoch": 19.77130977130977, "percentage": 98.86, "elapsed_time": "1:50:27", "remaining_time": "0:01:16", "throughput": 1033.59, "total_tokens": 6850368} {"current_steps": 76085, "total_steps": 76960, "loss": 0.0139, "lr": 1.9730845635190788e-08, "epoch": 19.77260914760915, "percentage": 98.86, "elapsed_time": "1:50:28", "remaining_time": "0:01:16", "throughput": 1033.59, "total_tokens": 6850800} {"current_steps": 76090, "total_steps": 76960, "loss": 0.0009, "lr": 1.950627968508589e-08, "epoch": 19.773908523908524, "percentage": 98.87, "elapsed_time": "1:50:28", "remaining_time": "0:01:15", "throughput": 1033.59, "total_tokens": 6851280} {"current_steps": 76095, "total_steps": 76960, "loss": 0.1665, "lr": 1.9282998505709693e-08, "epoch": 19.7752079002079, "percentage": 98.88, "elapsed_time": "1:50:29", "remaining_time": "0:01:15", "throughput": 1033.59, "total_tokens": 6851696} {"current_steps": 76100, "total_steps": 76960, "loss": 0.0001, "lr": 1.906100210854189e-08, "epoch": 19.776507276507278, "percentage": 98.88, "elapsed_time": "1:50:29", "remaining_time": "0:01:14", "throughput": 1033.59, "total_tokens": 6852128} {"current_steps": 76105, "total_steps": 76960, "loss": 0.117, "lr": 1.8840290505001134e-08, "epoch": 19.777806652806653, "percentage": 98.89, "elapsed_time": "1:50:29", "remaining_time": "0:01:14", "throughput": 1033.6, "total_tokens": 6852608} {"current_steps": 76110, "total_steps": 76960, "loss": 0.0005, "lr": 1.8620863706442228e-08, "epoch": 19.77910602910603, "percentage": 98.9, "elapsed_time": "1:50:30", "remaining_time": "0:01:14", "throughput": 1033.6, "total_tokens": 6853040} {"current_steps": 76115, "total_steps": 76960, "loss": 0.0001, "lr": 1.840272172414781e-08, "epoch": 19.780405405405407, "percentage": 98.9, "elapsed_time": "1:50:30", "remaining_time": "0:01:13", "throughput": 1033.6, "total_tokens": 6853472} {"current_steps": 76120, "total_steps": 76960, "loss": 0.2944, "lr": 1.8185864569336687e-08, "epoch": 19.781704781704782, "percentage": 98.91, "elapsed_time": "1:50:31", "remaining_time": "0:01:13", "throughput": 1033.6, "total_tokens": 6853904} {"current_steps": 76125, "total_steps": 76960, "loss": 0.1953, "lr": 1.79702922531666e-08, "epoch": 19.783004158004157, "percentage": 98.92, "elapsed_time": "1:50:31", "remaining_time": "0:01:12", "throughput": 1033.61, "total_tokens": 6854384} {"current_steps": 76130, "total_steps": 76960, "loss": 0.1222, "lr": 1.7756004786717572e-08, "epoch": 19.784303534303533, "percentage": 98.92, "elapsed_time": "1:50:31", "remaining_time": "0:01:12", "throughput": 1033.61, "total_tokens": 6854816} {"current_steps": 76135, "total_steps": 76960, "loss": 0.039, "lr": 1.7543002181014125e-08, "epoch": 19.78560291060291, "percentage": 98.93, "elapsed_time": "1:50:32", "remaining_time": "0:01:11", "throughput": 1033.61, "total_tokens": 6855264} {"current_steps": 76140, "total_steps": 76960, "loss": 0.0031, "lr": 1.7331284447011377e-08, "epoch": 19.786902286902286, "percentage": 98.93, "elapsed_time": "1:50:32", "remaining_time": "0:01:11", "throughput": 1033.61, "total_tokens": 6855696} {"current_steps": 76145, "total_steps": 76960, "loss": 0.128, "lr": 1.712085159559784e-08, "epoch": 19.78820166320166, "percentage": 98.94, "elapsed_time": "1:50:33", "remaining_time": "0:01:10", "throughput": 1033.62, "total_tokens": 6856144} {"current_steps": 76150, "total_steps": 76960, "loss": 0.5711, "lr": 1.69117036375982e-08, "epoch": 19.78950103950104, "percentage": 98.95, "elapsed_time": "1:50:33", "remaining_time": "0:01:10", "throughput": 1033.62, "total_tokens": 6856592} {"current_steps": 76155, "total_steps": 76960, "loss": 0.0028, "lr": 1.670384058376495e-08, "epoch": 19.790800415800415, "percentage": 98.95, "elapsed_time": "1:50:33", "remaining_time": "0:01:10", "throughput": 1033.63, "total_tokens": 6857056} {"current_steps": 76160, "total_steps": 76960, "loss": 0.0715, "lr": 1.6497262444792326e-08, "epoch": 19.79209979209979, "percentage": 98.96, "elapsed_time": "1:50:34", "remaining_time": "0:01:09", "throughput": 1033.63, "total_tokens": 6857488} {"current_steps": 76165, "total_steps": 76960, "loss": 0.1582, "lr": 1.629196923130516e-08, "epoch": 19.79339916839917, "percentage": 98.97, "elapsed_time": "1:50:34", "remaining_time": "0:01:09", "throughput": 1033.63, "total_tokens": 6857936} {"current_steps": 76170, "total_steps": 76960, "loss": 0.0332, "lr": 1.608796095385612e-08, "epoch": 19.794698544698544, "percentage": 98.97, "elapsed_time": "1:50:35", "remaining_time": "0:01:08", "throughput": 1033.63, "total_tokens": 6858384} {"current_steps": 76175, "total_steps": 76960, "loss": 0.0243, "lr": 1.5885237622945136e-08, "epoch": 19.79599792099792, "percentage": 98.98, "elapsed_time": "1:50:35", "remaining_time": "0:01:08", "throughput": 1033.63, "total_tokens": 6858816} {"current_steps": 76180, "total_steps": 76960, "loss": 0.0034, "lr": 1.5683799248994436e-08, "epoch": 19.7972972972973, "percentage": 98.99, "elapsed_time": "1:50:36", "remaining_time": "0:01:07", "throughput": 1033.63, "total_tokens": 6859248} {"current_steps": 76185, "total_steps": 76960, "loss": 0.0144, "lr": 1.5483645842362392e-08, "epoch": 19.798596673596673, "percentage": 98.99, "elapsed_time": "1:50:36", "remaining_time": "0:01:07", "throughput": 1033.63, "total_tokens": 6859664} {"current_steps": 76190, "total_steps": 76960, "loss": 0.0049, "lr": 1.5284777413349106e-08, "epoch": 19.79989604989605, "percentage": 99.0, "elapsed_time": "1:50:36", "remaining_time": "0:01:07", "throughput": 1033.64, "total_tokens": 6860128} {"current_steps": 76195, "total_steps": 76960, "loss": 0.1375, "lr": 1.508719397217695e-08, "epoch": 19.801195426195427, "percentage": 99.01, "elapsed_time": "1:50:37", "remaining_time": "0:01:06", "throughput": 1033.65, "total_tokens": 6860624} {"current_steps": 76200, "total_steps": 76960, "loss": 0.0974, "lr": 1.4890895529010019e-08, "epoch": 19.802494802494802, "percentage": 99.01, "elapsed_time": "1:50:37", "remaining_time": "0:01:06", "throughput": 1033.65, "total_tokens": 6861088} {"current_steps": 76205, "total_steps": 76960, "loss": 0.0001, "lr": 1.4695882093943015e-08, "epoch": 19.803794178794178, "percentage": 99.02, "elapsed_time": "1:50:38", "remaining_time": "0:01:05", "throughput": 1033.66, "total_tokens": 6861536} {"current_steps": 76210, "total_steps": 76960, "loss": 0.1276, "lr": 1.4502153677006802e-08, "epoch": 19.805093555093556, "percentage": 99.03, "elapsed_time": "1:50:38", "remaining_time": "0:01:05", "throughput": 1033.66, "total_tokens": 6861968} {"current_steps": 76215, "total_steps": 76960, "loss": 0.0076, "lr": 1.4309710288165634e-08, "epoch": 19.80639293139293, "percentage": 99.03, "elapsed_time": "1:50:38", "remaining_time": "0:01:04", "throughput": 1033.66, "total_tokens": 6862400} {"current_steps": 76220, "total_steps": 76960, "loss": 0.0028, "lr": 1.4118551937314372e-08, "epoch": 19.807692307692307, "percentage": 99.04, "elapsed_time": "1:50:39", "remaining_time": "0:01:04", "throughput": 1033.66, "total_tokens": 6862848} {"current_steps": 76225, "total_steps": 76960, "loss": 0.0002, "lr": 1.3928678634289593e-08, "epoch": 19.808991683991685, "percentage": 99.04, "elapsed_time": "1:50:39", "remaining_time": "0:01:04", "throughput": 1033.66, "total_tokens": 6863296} {"current_steps": 76230, "total_steps": 76960, "loss": 0.0014, "lr": 1.3740090388850158e-08, "epoch": 19.81029106029106, "percentage": 99.05, "elapsed_time": "1:50:40", "remaining_time": "0:01:03", "throughput": 1033.66, "total_tokens": 6863712} {"current_steps": 76235, "total_steps": 76960, "loss": 0.0011, "lr": 1.3552787210699413e-08, "epoch": 19.811590436590436, "percentage": 99.06, "elapsed_time": "1:50:40", "remaining_time": "0:01:03", "throughput": 1033.66, "total_tokens": 6864144} {"current_steps": 76240, "total_steps": 76960, "loss": 0.0002, "lr": 1.3366769109471321e-08, "epoch": 19.812889812889814, "percentage": 99.06, "elapsed_time": "1:50:41", "remaining_time": "0:01:02", "throughput": 1033.66, "total_tokens": 6864576} {"current_steps": 76245, "total_steps": 76960, "loss": 0.3562, "lr": 1.3182036094730454e-08, "epoch": 19.81418918918919, "percentage": 99.07, "elapsed_time": "1:50:41", "remaining_time": "0:01:02", "throughput": 1033.67, "total_tokens": 6865024} {"current_steps": 76250, "total_steps": 76960, "loss": 0.0005, "lr": 1.2998588175977544e-08, "epoch": 19.815488565488565, "percentage": 99.08, "elapsed_time": "1:50:41", "remaining_time": "0:01:01", "throughput": 1033.67, "total_tokens": 6865504} {"current_steps": 76255, "total_steps": 76960, "loss": 0.0002, "lr": 1.2816425362649487e-08, "epoch": 19.816787941787943, "percentage": 99.08, "elapsed_time": "1:50:42", "remaining_time": "0:01:01", "throughput": 1033.68, "total_tokens": 6865968} {"current_steps": 76260, "total_steps": 76960, "loss": 0.0618, "lr": 1.263554766411379e-08, "epoch": 19.81808731808732, "percentage": 99.09, "elapsed_time": "1:50:42", "remaining_time": "0:01:00", "throughput": 1033.68, "total_tokens": 6866432} {"current_steps": 76265, "total_steps": 76960, "loss": 0.0001, "lr": 1.245595508967412e-08, "epoch": 19.819386694386694, "percentage": 99.1, "elapsed_time": "1:50:43", "remaining_time": "0:01:00", "throughput": 1033.69, "total_tokens": 6866896} {"current_steps": 76270, "total_steps": 76960, "loss": 0.0001, "lr": 1.2277647648567537e-08, "epoch": 19.820686070686072, "percentage": 99.1, "elapsed_time": "1:50:43", "remaining_time": "0:01:00", "throughput": 1033.7, "total_tokens": 6867376} {"current_steps": 76275, "total_steps": 76960, "loss": 0.2063, "lr": 1.2100625349961702e-08, "epoch": 19.821985446985448, "percentage": 99.11, "elapsed_time": "1:50:43", "remaining_time": "0:00:59", "throughput": 1033.7, "total_tokens": 6867808} {"current_steps": 76280, "total_steps": 76960, "loss": 0.0066, "lr": 1.1924888202963224e-08, "epoch": 19.823284823284823, "percentage": 99.12, "elapsed_time": "1:50:44", "remaining_time": "0:00:59", "throughput": 1033.7, "total_tokens": 6868272} {"current_steps": 76285, "total_steps": 76960, "loss": 0.0853, "lr": 1.1750436216612092e-08, "epoch": 19.8245841995842, "percentage": 99.12, "elapsed_time": "1:50:44", "remaining_time": "0:00:58", "throughput": 1033.71, "total_tokens": 6868752} {"current_steps": 76290, "total_steps": 76960, "loss": 0.0533, "lr": 1.1577269399876135e-08, "epoch": 19.825883575883577, "percentage": 99.13, "elapsed_time": "1:50:45", "remaining_time": "0:00:58", "throughput": 1033.71, "total_tokens": 6869184} {"current_steps": 76295, "total_steps": 76960, "loss": 0.0023, "lr": 1.1405387761664887e-08, "epoch": 19.82718295218295, "percentage": 99.14, "elapsed_time": "1:50:45", "remaining_time": "0:00:57", "throughput": 1033.72, "total_tokens": 6869648} {"current_steps": 76300, "total_steps": 76960, "loss": 0.0003, "lr": 1.1234791310818504e-08, "epoch": 19.828482328482327, "percentage": 99.14, "elapsed_time": "1:50:45", "remaining_time": "0:00:57", "throughput": 1033.72, "total_tokens": 6870080} {"current_steps": 76305, "total_steps": 76960, "loss": 0.0026, "lr": 1.1065480056110522e-08, "epoch": 19.829781704781706, "percentage": 99.15, "elapsed_time": "1:50:46", "remaining_time": "0:00:57", "throughput": 1033.72, "total_tokens": 6870528} {"current_steps": 76310, "total_steps": 76960, "loss": 0.0223, "lr": 1.0897454006245089e-08, "epoch": 19.83108108108108, "percentage": 99.16, "elapsed_time": "1:50:46", "remaining_time": "0:00:56", "throughput": 1033.72, "total_tokens": 6870944} {"current_steps": 76315, "total_steps": 76960, "loss": 0.0105, "lr": 1.0730713169868067e-08, "epoch": 19.832380457380456, "percentage": 99.16, "elapsed_time": "1:50:47", "remaining_time": "0:00:56", "throughput": 1033.72, "total_tokens": 6871392} {"current_steps": 76320, "total_steps": 76960, "loss": 0.0081, "lr": 1.056525755555593e-08, "epoch": 19.833679833679835, "percentage": 99.17, "elapsed_time": "1:50:47", "remaining_time": "0:00:55", "throughput": 1033.72, "total_tokens": 6871840} {"current_steps": 76325, "total_steps": 76960, "loss": 0.0007, "lr": 1.040108717181576e-08, "epoch": 19.83497920997921, "percentage": 99.17, "elapsed_time": "1:50:48", "remaining_time": "0:00:55", "throughput": 1033.73, "total_tokens": 6872304} {"current_steps": 76330, "total_steps": 76960, "loss": 0.0081, "lr": 1.0238202027090804e-08, "epoch": 19.836278586278585, "percentage": 99.18, "elapsed_time": "1:50:48", "remaining_time": "0:00:54", "throughput": 1033.73, "total_tokens": 6872736} {"current_steps": 76335, "total_steps": 76960, "loss": 0.0765, "lr": 1.0076602129757696e-08, "epoch": 19.837577962577964, "percentage": 99.19, "elapsed_time": "1:50:48", "remaining_time": "0:00:54", "throughput": 1033.73, "total_tokens": 6873184} {"current_steps": 76340, "total_steps": 76960, "loss": 0.0005, "lr": 9.916287488132003e-09, "epoch": 19.83887733887734, "percentage": 99.19, "elapsed_time": "1:50:49", "remaining_time": "0:00:54", "throughput": 1033.73, "total_tokens": 6873616} {"current_steps": 76345, "total_steps": 76960, "loss": 0.0001, "lr": 9.757258110454359e-09, "epoch": 19.840176715176714, "percentage": 99.2, "elapsed_time": "1:50:49", "remaining_time": "0:00:53", "throughput": 1033.74, "total_tokens": 6874080} {"current_steps": 76350, "total_steps": 76960, "loss": 0.0367, "lr": 9.599514004904331e-09, "epoch": 19.841476091476093, "percentage": 99.21, "elapsed_time": "1:50:50", "remaining_time": "0:00:53", "throughput": 1033.74, "total_tokens": 6874528} {"current_steps": 76355, "total_steps": 76960, "loss": 0.0984, "lr": 9.443055179597648e-09, "epoch": 19.842775467775468, "percentage": 99.21, "elapsed_time": "1:50:50", "remaining_time": "0:00:52", "throughput": 1033.74, "total_tokens": 6874944} {"current_steps": 76360, "total_steps": 76960, "loss": 0.0713, "lr": 9.287881642577878e-09, "epoch": 19.844074844074843, "percentage": 99.22, "elapsed_time": "1:50:50", "remaining_time": "0:00:52", "throughput": 1033.75, "total_tokens": 6875424} {"current_steps": 76365, "total_steps": 76960, "loss": 0.0129, "lr": 9.133993401830298e-09, "epoch": 19.84537422037422, "percentage": 99.23, "elapsed_time": "1:50:51", "remaining_time": "0:00:51", "throughput": 1033.75, "total_tokens": 6875856} {"current_steps": 76370, "total_steps": 76960, "loss": 0.0001, "lr": 8.981390465262474e-09, "epoch": 19.846673596673597, "percentage": 99.23, "elapsed_time": "1:50:51", "remaining_time": "0:00:51", "throughput": 1033.75, "total_tokens": 6876304} {"current_steps": 76375, "total_steps": 76960, "loss": 0.3114, "lr": 8.83007284072923e-09, "epoch": 19.847972972972972, "percentage": 99.24, "elapsed_time": "1:50:52", "remaining_time": "0:00:50", "throughput": 1033.75, "total_tokens": 6876736} {"current_steps": 76380, "total_steps": 76960, "loss": 0.0009, "lr": 8.680040536010458e-09, "epoch": 19.84927234927235, "percentage": 99.25, "elapsed_time": "1:50:52", "remaining_time": "0:00:50", "throughput": 1033.75, "total_tokens": 6877168} {"current_steps": 76385, "total_steps": 76960, "loss": 0.0008, "lr": 8.531293558824982e-09, "epoch": 19.850571725571726, "percentage": 99.25, "elapsed_time": "1:50:53", "remaining_time": "0:00:50", "throughput": 1033.76, "total_tokens": 6877616} {"current_steps": 76390, "total_steps": 76960, "loss": 0.0193, "lr": 8.383831916816686e-09, "epoch": 19.8518711018711, "percentage": 99.26, "elapsed_time": "1:50:53", "remaining_time": "0:00:49", "throughput": 1033.76, "total_tokens": 6878080} {"current_steps": 76395, "total_steps": 76960, "loss": 0.0249, "lr": 8.237655617576723e-09, "epoch": 19.85317047817048, "percentage": 99.27, "elapsed_time": "1:50:53", "remaining_time": "0:00:49", "throughput": 1033.77, "total_tokens": 6878544} {"current_steps": 76400, "total_steps": 76960, "loss": 0.0025, "lr": 8.092764668618524e-09, "epoch": 19.854469854469855, "percentage": 99.27, "elapsed_time": "1:50:54", "remaining_time": "0:00:48", "throughput": 1033.77, "total_tokens": 6878976} {"current_steps": 76405, "total_steps": 76960, "loss": 0.0219, "lr": 7.949159077397238e-09, "epoch": 19.85576923076923, "percentage": 99.28, "elapsed_time": "1:50:54", "remaining_time": "0:00:48", "throughput": 1033.78, "total_tokens": 6879456} {"current_steps": 76410, "total_steps": 76960, "loss": 0.0785, "lr": 7.80683885129585e-09, "epoch": 19.85706860706861, "percentage": 99.29, "elapsed_time": "1:50:55", "remaining_time": "0:00:47", "throughput": 1033.78, "total_tokens": 6879888} {"current_steps": 76415, "total_steps": 76960, "loss": 0.0053, "lr": 7.665803997633503e-09, "epoch": 19.858367983367984, "percentage": 99.29, "elapsed_time": "1:50:55", "remaining_time": "0:00:47", "throughput": 1033.78, "total_tokens": 6880352} {"current_steps": 76420, "total_steps": 76960, "loss": 0.0046, "lr": 7.52605452366828e-09, "epoch": 19.85966735966736, "percentage": 99.3, "elapsed_time": "1:50:55", "remaining_time": "0:00:47", "throughput": 1033.78, "total_tokens": 6880768} {"current_steps": 76425, "total_steps": 76960, "loss": 0.0644, "lr": 7.387590436583325e-09, "epoch": 19.860966735966738, "percentage": 99.3, "elapsed_time": "1:50:56", "remaining_time": "0:00:46", "throughput": 1033.78, "total_tokens": 6881168} {"current_steps": 76430, "total_steps": 76960, "loss": 0.0005, "lr": 7.250411743500718e-09, "epoch": 19.862266112266113, "percentage": 99.31, "elapsed_time": "1:50:56", "remaining_time": "0:00:46", "throughput": 1033.78, "total_tokens": 6881632} {"current_steps": 76435, "total_steps": 76960, "loss": 0.0013, "lr": 7.114518451478702e-09, "epoch": 19.863565488565488, "percentage": 99.32, "elapsed_time": "1:50:57", "remaining_time": "0:00:45", "throughput": 1033.79, "total_tokens": 6882096} {"current_steps": 76440, "total_steps": 76960, "loss": 0.0841, "lr": 6.979910567500581e-09, "epoch": 19.864864864864863, "percentage": 99.32, "elapsed_time": "1:50:57", "remaining_time": "0:00:45", "throughput": 1033.79, "total_tokens": 6882544} {"current_steps": 76445, "total_steps": 76960, "loss": 0.1963, "lr": 6.8465880984941444e-09, "epoch": 19.866164241164242, "percentage": 99.33, "elapsed_time": "1:50:57", "remaining_time": "0:00:44", "throughput": 1033.8, "total_tokens": 6883008} {"current_steps": 76450, "total_steps": 76960, "loss": 0.0197, "lr": 6.714551051317796e-09, "epoch": 19.867463617463617, "percentage": 99.34, "elapsed_time": "1:50:58", "remaining_time": "0:00:44", "throughput": 1033.8, "total_tokens": 6883456} {"current_steps": 76455, "total_steps": 76960, "loss": 0.0011, "lr": 6.583799432755e-09, "epoch": 19.868762993762992, "percentage": 99.34, "elapsed_time": "1:50:58", "remaining_time": "0:00:43", "throughput": 1033.81, "total_tokens": 6883936} {"current_steps": 76460, "total_steps": 76960, "loss": 0.0995, "lr": 6.454333249536482e-09, "epoch": 19.87006237006237, "percentage": 99.35, "elapsed_time": "1:50:59", "remaining_time": "0:00:43", "throughput": 1033.82, "total_tokens": 6884448} {"current_steps": 76465, "total_steps": 76960, "loss": 0.0009, "lr": 6.326152508320804e-09, "epoch": 19.871361746361746, "percentage": 99.36, "elapsed_time": "1:50:59", "remaining_time": "0:00:43", "throughput": 1033.83, "total_tokens": 6884960} {"current_steps": 76470, "total_steps": 76960, "loss": 0.0172, "lr": 6.199257215697141e-09, "epoch": 19.87266112266112, "percentage": 99.36, "elapsed_time": "1:51:00", "remaining_time": "0:00:42", "throughput": 1033.84, "total_tokens": 6885472} {"current_steps": 76475, "total_steps": 76960, "loss": 0.0822, "lr": 6.073647378196379e-09, "epoch": 19.8739604989605, "percentage": 99.37, "elapsed_time": "1:51:00", "remaining_time": "0:00:42", "throughput": 1033.84, "total_tokens": 6885888} {"current_steps": 76480, "total_steps": 76960, "loss": 0.2098, "lr": 5.94932300227169e-09, "epoch": 19.875259875259875, "percentage": 99.38, "elapsed_time": "1:51:00", "remaining_time": "0:00:41", "throughput": 1033.85, "total_tokens": 6886368} {"current_steps": 76485, "total_steps": 76960, "loss": 0.0026, "lr": 5.8262840943235085e-09, "epoch": 19.87655925155925, "percentage": 99.38, "elapsed_time": "1:51:01", "remaining_time": "0:00:41", "throughput": 1033.85, "total_tokens": 6886816} {"current_steps": 76490, "total_steps": 76960, "loss": 0.3259, "lr": 5.7045306606801075e-09, "epoch": 19.87785862785863, "percentage": 99.39, "elapsed_time": "1:51:01", "remaining_time": "0:00:40", "throughput": 1033.85, "total_tokens": 6887248} {"current_steps": 76495, "total_steps": 76960, "loss": 0.0005, "lr": 5.584062707597593e-09, "epoch": 19.879158004158004, "percentage": 99.4, "elapsed_time": "1:51:02", "remaining_time": "0:00:40", "throughput": 1033.86, "total_tokens": 6887728} {"current_steps": 76500, "total_steps": 76960, "loss": 0.1159, "lr": 5.46488024127656e-09, "epoch": 19.88045738045738, "percentage": 99.4, "elapsed_time": "1:51:02", "remaining_time": "0:00:40", "throughput": 1033.86, "total_tokens": 6888160} {"current_steps": 76505, "total_steps": 76960, "loss": 0.2307, "lr": 5.34698326784544e-09, "epoch": 19.881756756756758, "percentage": 99.41, "elapsed_time": "1:51:02", "remaining_time": "0:00:39", "throughput": 1033.87, "total_tokens": 6888640} {"current_steps": 76510, "total_steps": 76960, "loss": 0.0098, "lr": 5.230371793368827e-09, "epoch": 19.883056133056133, "percentage": 99.42, "elapsed_time": "1:51:03", "remaining_time": "0:00:39", "throughput": 1033.87, "total_tokens": 6889072} {"current_steps": 76515, "total_steps": 76960, "loss": 0.002, "lr": 5.115045823841924e-09, "epoch": 19.884355509355508, "percentage": 99.42, "elapsed_time": "1:51:03", "remaining_time": "0:00:38", "throughput": 1033.87, "total_tokens": 6889504} {"current_steps": 76520, "total_steps": 76960, "loss": 0.0234, "lr": 5.001005365196098e-09, "epoch": 19.885654885654887, "percentage": 99.43, "elapsed_time": "1:51:04", "remaining_time": "0:00:38", "throughput": 1033.87, "total_tokens": 6889936} {"current_steps": 76525, "total_steps": 76960, "loss": 0.0001, "lr": 4.888250423298879e-09, "epoch": 19.886954261954262, "percentage": 99.43, "elapsed_time": "1:51:04", "remaining_time": "0:00:37", "throughput": 1033.87, "total_tokens": 6890384} {"current_steps": 76530, "total_steps": 76960, "loss": 0.0055, "lr": 4.776781003948405e-09, "epoch": 19.888253638253637, "percentage": 99.44, "elapsed_time": "1:51:05", "remaining_time": "0:00:37", "throughput": 1033.87, "total_tokens": 6890800} {"current_steps": 76535, "total_steps": 76960, "loss": 0.0007, "lr": 4.666597112876203e-09, "epoch": 19.889553014553016, "percentage": 99.45, "elapsed_time": "1:51:05", "remaining_time": "0:00:37", "throughput": 1033.88, "total_tokens": 6891264} {"current_steps": 76540, "total_steps": 76960, "loss": 0.1765, "lr": 4.557698755749962e-09, "epoch": 19.89085239085239, "percentage": 99.45, "elapsed_time": "1:51:05", "remaining_time": "0:00:36", "throughput": 1033.88, "total_tokens": 6891712} {"current_steps": 76545, "total_steps": 76960, "loss": 0.028, "lr": 4.450085938170756e-09, "epoch": 19.892151767151766, "percentage": 99.46, "elapsed_time": "1:51:06", "remaining_time": "0:00:36", "throughput": 1033.88, "total_tokens": 6892160} {"current_steps": 76550, "total_steps": 76960, "loss": 0.003, "lr": 4.3437586656758236e-09, "epoch": 19.893451143451145, "percentage": 99.47, "elapsed_time": "1:51:06", "remaining_time": "0:00:35", "throughput": 1033.89, "total_tokens": 6892640} {"current_steps": 76555, "total_steps": 76960, "loss": 0.0046, "lr": 4.238716943727461e-09, "epoch": 19.89475051975052, "percentage": 99.47, "elapsed_time": "1:51:07", "remaining_time": "0:00:35", "throughput": 1033.9, "total_tokens": 6893136} {"current_steps": 76560, "total_steps": 76960, "loss": 0.0007, "lr": 4.1349607777352305e-09, "epoch": 19.896049896049895, "percentage": 99.48, "elapsed_time": "1:51:07", "remaining_time": "0:00:34", "throughput": 1033.91, "total_tokens": 6893584} {"current_steps": 76565, "total_steps": 76960, "loss": 0.0018, "lr": 4.032490173030978e-09, "epoch": 19.897349272349274, "percentage": 99.49, "elapsed_time": "1:51:07", "remaining_time": "0:00:34", "throughput": 1033.91, "total_tokens": 6894048} {"current_steps": 76570, "total_steps": 76960, "loss": 0.274, "lr": 3.931305134882712e-09, "epoch": 19.89864864864865, "percentage": 99.49, "elapsed_time": "1:51:08", "remaining_time": "0:00:33", "throughput": 1033.91, "total_tokens": 6894496} {"current_steps": 76575, "total_steps": 76960, "loss": 0.0008, "lr": 3.831405668500154e-09, "epoch": 19.899948024948024, "percentage": 99.5, "elapsed_time": "1:51:08", "remaining_time": "0:00:33", "throughput": 1033.92, "total_tokens": 6894944} {"current_steps": 76580, "total_steps": 76960, "loss": 0.4099, "lr": 3.732791779018086e-09, "epoch": 19.901247401247403, "percentage": 99.51, "elapsed_time": "1:51:09", "remaining_time": "0:00:33", "throughput": 1033.92, "total_tokens": 6895376} {"current_steps": 76585, "total_steps": 76960, "loss": 0.0253, "lr": 3.6354634715102255e-09, "epoch": 19.902546777546778, "percentage": 99.51, "elapsed_time": "1:51:09", "remaining_time": "0:00:32", "throughput": 1033.92, "total_tokens": 6895808} {"current_steps": 76590, "total_steps": 76960, "loss": 0.3439, "lr": 3.5394207509781287e-09, "epoch": 19.903846153846153, "percentage": 99.52, "elapsed_time": "1:51:10", "remaining_time": "0:00:32", "throughput": 1033.92, "total_tokens": 6896256} {"current_steps": 76595, "total_steps": 76960, "loss": 0.0131, "lr": 3.444663622365063e-09, "epoch": 19.90514553014553, "percentage": 99.53, "elapsed_time": "1:51:10", "remaining_time": "0:00:31", "throughput": 1033.93, "total_tokens": 6896736} {"current_steps": 76600, "total_steps": 76960, "loss": 0.2191, "lr": 3.351192090544908e-09, "epoch": 19.906444906444907, "percentage": 99.53, "elapsed_time": "1:51:10", "remaining_time": "0:00:31", "throughput": 1033.94, "total_tokens": 6897216} {"current_steps": 76605, "total_steps": 76960, "loss": 0.2251, "lr": 3.2590061603221535e-09, "epoch": 19.907744282744282, "percentage": 99.54, "elapsed_time": "1:51:11", "remaining_time": "0:00:30", "throughput": 1033.94, "total_tokens": 6897648} {"current_steps": 76610, "total_steps": 76960, "loss": 0.1483, "lr": 3.1681058364402272e-09, "epoch": 19.909043659043657, "percentage": 99.55, "elapsed_time": "1:51:11", "remaining_time": "0:00:30", "throughput": 1033.94, "total_tokens": 6898096} {"current_steps": 76615, "total_steps": 76960, "loss": 0.0005, "lr": 3.078491123573168e-09, "epoch": 19.910343035343036, "percentage": 99.55, "elapsed_time": "1:51:12", "remaining_time": "0:00:30", "throughput": 1033.95, "total_tokens": 6898560} {"current_steps": 76620, "total_steps": 76960, "loss": 0.0055, "lr": 2.9901620263284026e-09, "epoch": 19.91164241164241, "percentage": 99.56, "elapsed_time": "1:51:12", "remaining_time": "0:00:29", "throughput": 1033.95, "total_tokens": 6898992} {"current_steps": 76625, "total_steps": 76960, "loss": 0.1088, "lr": 2.9031185492522926e-09, "epoch": 19.912941787941786, "percentage": 99.56, "elapsed_time": "1:51:12", "remaining_time": "0:00:29", "throughput": 1033.95, "total_tokens": 6899424} {"current_steps": 76630, "total_steps": 76960, "loss": 0.0001, "lr": 2.817360696819038e-09, "epoch": 19.914241164241165, "percentage": 99.57, "elapsed_time": "1:51:13", "remaining_time": "0:00:28", "throughput": 1033.95, "total_tokens": 6899872} {"current_steps": 76635, "total_steps": 76960, "loss": 0.0016, "lr": 2.732888473441775e-09, "epoch": 19.91554054054054, "percentage": 99.58, "elapsed_time": "1:51:13", "remaining_time": "0:00:28", "throughput": 1033.95, "total_tokens": 6900288} {"current_steps": 76640, "total_steps": 76960, "loss": 0.3209, "lr": 2.649701883461475e-09, "epoch": 19.916839916839916, "percentage": 99.58, "elapsed_time": "1:51:14", "remaining_time": "0:00:27", "throughput": 1033.96, "total_tokens": 6900784} {"current_steps": 76645, "total_steps": 76960, "loss": 0.0545, "lr": 2.5678009311608243e-09, "epoch": 19.918139293139294, "percentage": 99.59, "elapsed_time": "1:51:14", "remaining_time": "0:00:27", "throughput": 1033.96, "total_tokens": 6901232} {"current_steps": 76650, "total_steps": 76960, "loss": 0.0007, "lr": 2.4871856207475673e-09, "epoch": 19.91943866943867, "percentage": 99.6, "elapsed_time": "1:51:14", "remaining_time": "0:00:26", "throughput": 1033.97, "total_tokens": 6901728} {"current_steps": 76655, "total_steps": 76960, "loss": 0.2168, "lr": 2.407855956368388e-09, "epoch": 19.920738045738045, "percentage": 99.6, "elapsed_time": "1:51:15", "remaining_time": "0:00:26", "throughput": 1033.97, "total_tokens": 6902176} {"current_steps": 76660, "total_steps": 76960, "loss": 0.0013, "lr": 2.329811942108906e-09, "epoch": 19.922037422037423, "percentage": 99.61, "elapsed_time": "1:51:15", "remaining_time": "0:00:26", "throughput": 1033.98, "total_tokens": 6902624} {"current_steps": 76665, "total_steps": 76960, "loss": 0.2307, "lr": 2.2530535819742514e-09, "epoch": 19.9233367983368, "percentage": 99.62, "elapsed_time": "1:51:16", "remaining_time": "0:00:25", "throughput": 1033.98, "total_tokens": 6903072} {"current_steps": 76670, "total_steps": 76960, "loss": 0.357, "lr": 2.177580879919594e-09, "epoch": 19.924636174636174, "percentage": 99.62, "elapsed_time": "1:51:16", "remaining_time": "0:00:25", "throughput": 1033.98, "total_tokens": 6903504} {"current_steps": 76675, "total_steps": 76960, "loss": 0.0026, "lr": 2.1033938398223872e-09, "epoch": 19.925935550935552, "percentage": 99.63, "elapsed_time": "1:51:17", "remaining_time": "0:00:24", "throughput": 1033.99, "total_tokens": 6904000} {"current_steps": 76680, "total_steps": 76960, "loss": 0.0004, "lr": 2.0304924655017986e-09, "epoch": 19.927234927234927, "percentage": 99.64, "elapsed_time": "1:51:17", "remaining_time": "0:00:24", "throughput": 1033.99, "total_tokens": 6904432} {"current_steps": 76685, "total_steps": 76960, "loss": 0.0289, "lr": 1.9588767607020553e-09, "epoch": 19.928534303534303, "percentage": 99.64, "elapsed_time": "1:51:17", "remaining_time": "0:00:23", "throughput": 1034.01, "total_tokens": 6904960} {"current_steps": 76690, "total_steps": 76960, "loss": 0.0048, "lr": 1.8885467291090973e-09, "epoch": 19.92983367983368, "percentage": 99.65, "elapsed_time": "1:51:18", "remaining_time": "0:00:23", "throughput": 1034.01, "total_tokens": 6905440} {"current_steps": 76695, "total_steps": 76960, "loss": 0.0693, "lr": 1.8195023743422523e-09, "epoch": 19.931133056133056, "percentage": 99.66, "elapsed_time": "1:51:18", "remaining_time": "0:00:23", "throughput": 1034.02, "total_tokens": 6905888} {"current_steps": 76700, "total_steps": 76960, "loss": 0.0006, "lr": 1.7517436999486825e-09, "epoch": 19.93243243243243, "percentage": 99.66, "elapsed_time": "1:51:19", "remaining_time": "0:00:22", "throughput": 1034.02, "total_tokens": 6906352} {"current_steps": 76705, "total_steps": 76960, "loss": 0.0036, "lr": 1.6852707094172636e-09, "epoch": 19.93373180873181, "percentage": 99.67, "elapsed_time": "1:51:19", "remaining_time": "0:00:22", "throughput": 1034.03, "total_tokens": 6906816} {"current_steps": 76710, "total_steps": 76960, "loss": 0.0137, "lr": 1.620083406161932e-09, "epoch": 19.935031185031185, "percentage": 99.68, "elapsed_time": "1:51:19", "remaining_time": "0:00:21", "throughput": 1034.03, "total_tokens": 6907248} {"current_steps": 76715, "total_steps": 76960, "loss": 0.0051, "lr": 1.5561817935411116e-09, "epoch": 19.93633056133056, "percentage": 99.68, "elapsed_time": "1:51:20", "remaining_time": "0:00:21", "throughput": 1034.03, "total_tokens": 6907712} {"current_steps": 76720, "total_steps": 76960, "loss": 0.4065, "lr": 1.493565874835512e-09, "epoch": 19.93762993762994, "percentage": 99.69, "elapsed_time": "1:51:20", "remaining_time": "0:00:20", "throughput": 1034.04, "total_tokens": 6908192} {"current_steps": 76725, "total_steps": 76960, "loss": 0.0016, "lr": 1.4322356532703308e-09, "epoch": 19.938929313929314, "percentage": 99.69, "elapsed_time": "1:51:21", "remaining_time": "0:00:20", "throughput": 1034.04, "total_tokens": 6908640} {"current_steps": 76730, "total_steps": 76960, "loss": 0.0769, "lr": 1.3721911319958258e-09, "epoch": 19.94022869022869, "percentage": 99.7, "elapsed_time": "1:51:21", "remaining_time": "0:00:20", "throughput": 1034.05, "total_tokens": 6909088} {"current_steps": 76735, "total_steps": 76960, "loss": 0.1907, "lr": 1.3134323141039683e-09, "epoch": 19.941528066528065, "percentage": 99.71, "elapsed_time": "1:51:22", "remaining_time": "0:00:19", "throughput": 1034.05, "total_tokens": 6909536} {"current_steps": 76740, "total_steps": 76960, "loss": 0.1245, "lr": 1.255959202614565e-09, "epoch": 19.942827442827443, "percentage": 99.71, "elapsed_time": "1:51:22", "remaining_time": "0:00:19", "throughput": 1034.05, "total_tokens": 6910000} {"current_steps": 76745, "total_steps": 76960, "loss": 0.0234, "lr": 1.199771800480809e-09, "epoch": 19.94412681912682, "percentage": 99.72, "elapsed_time": "1:51:22", "remaining_time": "0:00:18", "throughput": 1034.05, "total_tokens": 6910432} {"current_steps": 76750, "total_steps": 76960, "loss": 0.1204, "lr": 1.1448701105976068e-09, "epoch": 19.945426195426194, "percentage": 99.73, "elapsed_time": "1:51:23", "remaining_time": "0:00:18", "throughput": 1034.06, "total_tokens": 6910880} {"current_steps": 76755, "total_steps": 76960, "loss": 0.2203, "lr": 1.0912541357877004e-09, "epoch": 19.946725571725572, "percentage": 99.73, "elapsed_time": "1:51:23", "remaining_time": "0:00:17", "throughput": 1034.06, "total_tokens": 6911312} {"current_steps": 76760, "total_steps": 76960, "loss": 0.0422, "lr": 1.0389238788072187e-09, "epoch": 19.948024948024948, "percentage": 99.74, "elapsed_time": "1:51:24", "remaining_time": "0:00:17", "throughput": 1034.07, "total_tokens": 6911792} {"current_steps": 76765, "total_steps": 76960, "loss": 0.0007, "lr": 9.878793423456767e-10, "epoch": 19.949324324324323, "percentage": 99.75, "elapsed_time": "1:51:24", "remaining_time": "0:00:16", "throughput": 1034.07, "total_tokens": 6912240} {"current_steps": 76770, "total_steps": 76960, "loss": 0.1742, "lr": 9.381205290315276e-10, "epoch": 19.9506237006237, "percentage": 99.75, "elapsed_time": "1:51:24", "remaining_time": "0:00:16", "throughput": 1034.07, "total_tokens": 6912672} {"current_steps": 76775, "total_steps": 76960, "loss": 0.0017, "lr": 8.896474414238354e-10, "epoch": 19.951923076923077, "percentage": 99.76, "elapsed_time": "1:51:25", "remaining_time": "0:00:16", "throughput": 1034.08, "total_tokens": 6913152} {"current_steps": 76780, "total_steps": 76960, "loss": 0.008, "lr": 8.424600820122752e-10, "epoch": 19.953222453222452, "percentage": 99.77, "elapsed_time": "1:51:25", "remaining_time": "0:00:15", "throughput": 1034.08, "total_tokens": 6913616} {"current_steps": 76785, "total_steps": 76960, "loss": 0.0421, "lr": 7.965584532282355e-10, "epoch": 19.95452182952183, "percentage": 99.77, "elapsed_time": "1:51:26", "remaining_time": "0:00:15", "throughput": 1034.08, "total_tokens": 6914016} {"current_steps": 76790, "total_steps": 76960, "loss": 0.0009, "lr": 7.519425574281647e-10, "epoch": 19.955821205821206, "percentage": 99.78, "elapsed_time": "1:51:26", "remaining_time": "0:00:14", "throughput": 1034.08, "total_tokens": 6914464} {"current_steps": 76795, "total_steps": 76960, "loss": 0.1222, "lr": 7.086123969102243e-10, "epoch": 19.95712058212058, "percentage": 99.79, "elapsed_time": "1:51:26", "remaining_time": "0:00:14", "throughput": 1034.09, "total_tokens": 6914928} {"current_steps": 76800, "total_steps": 76960, "loss": 0.0004, "lr": 6.665679739031871e-10, "epoch": 19.95841995841996, "percentage": 99.79, "elapsed_time": "1:51:27", "remaining_time": "0:00:13", "throughput": 1034.09, "total_tokens": 6915376} {"current_steps": 76805, "total_steps": 76960, "loss": 0.0587, "lr": 6.258092905636614e-10, "epoch": 19.959719334719335, "percentage": 99.8, "elapsed_time": "1:51:27", "remaining_time": "0:00:13", "throughput": 1034.09, "total_tokens": 6915824} {"current_steps": 76810, "total_steps": 76960, "loss": 0.0001, "lr": 5.863363489955198e-10, "epoch": 19.96101871101871, "percentage": 99.81, "elapsed_time": "1:51:28", "remaining_time": "0:00:13", "throughput": 1034.1, "total_tokens": 6916288} {"current_steps": 76815, "total_steps": 76960, "loss": 0.0918, "lr": 5.481491512249193e-10, "epoch": 19.96231808731809, "percentage": 99.81, "elapsed_time": "1:51:28", "remaining_time": "0:00:12", "throughput": 1034.1, "total_tokens": 6916752} {"current_steps": 76820, "total_steps": 76960, "loss": 0.001, "lr": 5.11247699214179e-10, "epoch": 19.963617463617464, "percentage": 99.82, "elapsed_time": "1:51:29", "remaining_time": "0:00:12", "throughput": 1034.1, "total_tokens": 6917168} {"current_steps": 76825, "total_steps": 76960, "loss": 0.0145, "lr": 4.75631994864556e-10, "epoch": 19.96491683991684, "percentage": 99.82, "elapsed_time": "1:51:29", "remaining_time": "0:00:11", "throughput": 1034.1, "total_tokens": 6917584} {"current_steps": 76830, "total_steps": 76960, "loss": 0.0519, "lr": 4.413020400079182e-10, "epoch": 19.966216216216218, "percentage": 99.83, "elapsed_time": "1:51:29", "remaining_time": "0:00:11", "throughput": 1034.1, "total_tokens": 6918032} {"current_steps": 76835, "total_steps": 76960, "loss": 0.0263, "lr": 4.082578364067446e-10, "epoch": 19.967515592515593, "percentage": 99.84, "elapsed_time": "1:51:30", "remaining_time": "0:00:10", "throughput": 1034.11, "total_tokens": 6918496} {"current_steps": 76840, "total_steps": 76960, "loss": 0.0608, "lr": 3.764993857624521e-10, "epoch": 19.968814968814968, "percentage": 99.84, "elapsed_time": "1:51:30", "remaining_time": "0:00:10", "throughput": 1034.1, "total_tokens": 6918896} {"current_steps": 76845, "total_steps": 76960, "loss": 0.0002, "lr": 3.460266897098441e-10, "epoch": 19.970114345114347, "percentage": 99.85, "elapsed_time": "1:51:31", "remaining_time": "0:00:10", "throughput": 1034.11, "total_tokens": 6919360} {"current_steps": 76850, "total_steps": 76960, "loss": 0.0186, "lr": 3.168397498115594e-10, "epoch": 19.97141372141372, "percentage": 99.86, "elapsed_time": "1:51:31", "remaining_time": "0:00:09", "throughput": 1034.12, "total_tokens": 6919824} {"current_steps": 76855, "total_steps": 76960, "loss": 0.2904, "lr": 2.889385675747258e-10, "epoch": 19.972713097713097, "percentage": 99.86, "elapsed_time": "1:51:31", "remaining_time": "0:00:09", "throughput": 1034.11, "total_tokens": 6920240} {"current_steps": 76860, "total_steps": 76960, "loss": 0.0087, "lr": 2.6232314443153106e-10, "epoch": 19.974012474012476, "percentage": 99.87, "elapsed_time": "1:51:32", "remaining_time": "0:00:08", "throughput": 1034.11, "total_tokens": 6920656} {"current_steps": 76865, "total_steps": 76960, "loss": 0.3398, "lr": 2.3699348174754945e-10, "epoch": 19.97531185031185, "percentage": 99.88, "elapsed_time": "1:51:32", "remaining_time": "0:00:08", "throughput": 1034.11, "total_tokens": 6921104} {"current_steps": 76870, "total_steps": 76960, "loss": 0.0002, "lr": 2.1294958083006855e-10, "epoch": 19.976611226611226, "percentage": 99.88, "elapsed_time": "1:51:33", "remaining_time": "0:00:07", "throughput": 1034.12, "total_tokens": 6921568} {"current_steps": 76875, "total_steps": 76960, "loss": 0.0897, "lr": 1.9019144291421153e-10, "epoch": 19.977910602910605, "percentage": 99.89, "elapsed_time": "1:51:33", "remaining_time": "0:00:07", "throughput": 1034.13, "total_tokens": 6922048} {"current_steps": 76880, "total_steps": 76960, "loss": 0.0067, "lr": 1.6871906917126367e-10, "epoch": 19.97920997920998, "percentage": 99.9, "elapsed_time": "1:51:34", "remaining_time": "0:00:06", "throughput": 1034.13, "total_tokens": 6922528} {"current_steps": 76885, "total_steps": 76960, "loss": 0.0982, "lr": 1.4853246070589689e-10, "epoch": 19.980509355509355, "percentage": 99.9, "elapsed_time": "1:51:34", "remaining_time": "0:00:06", "throughput": 1034.14, "total_tokens": 6922976} {"current_steps": 76890, "total_steps": 76960, "loss": 0.0093, "lr": 1.2963161855339413e-10, "epoch": 19.981808731808734, "percentage": 99.91, "elapsed_time": "1:51:34", "remaining_time": "0:00:06", "throughput": 1034.14, "total_tokens": 6923424} {"current_steps": 76895, "total_steps": 76960, "loss": 0.0031, "lr": 1.120165436879761e-10, "epoch": 19.98310810810811, "percentage": 99.92, "elapsed_time": "1:51:35", "remaining_time": "0:00:05", "throughput": 1034.15, "total_tokens": 6923888} {"current_steps": 76900, "total_steps": 76960, "loss": 0.0694, "lr": 9.568723701447457e-11, "epoch": 19.984407484407484, "percentage": 99.92, "elapsed_time": "1:51:35", "remaining_time": "0:00:05", "throughput": 1034.15, "total_tokens": 6924336} {"current_steps": 76905, "total_steps": 76960, "loss": 0.1367, "lr": 8.064369937388349e-11, "epoch": 19.98570686070686, "percentage": 99.93, "elapsed_time": "1:51:36", "remaining_time": "0:00:04", "throughput": 1034.15, "total_tokens": 6924768} {"current_steps": 76910, "total_steps": 76960, "loss": 0.0127, "lr": 6.688593154058343e-11, "epoch": 19.987006237006238, "percentage": 99.94, "elapsed_time": "1:51:36", "remaining_time": "0:00:04", "throughput": 1034.15, "total_tokens": 6925232} {"current_steps": 76915, "total_steps": 76960, "loss": 0.0096, "lr": 5.4413934219565974e-11, "epoch": 19.988305613305613, "percentage": 99.94, "elapsed_time": "1:51:36", "remaining_time": "0:00:03", "throughput": 1034.16, "total_tokens": 6925664} {"current_steps": 76920, "total_steps": 76960, "loss": 0.4628, "lr": 4.3227708054760504e-11, "epoch": 19.989604989604988, "percentage": 99.95, "elapsed_time": "1:51:37", "remaining_time": "0:00:03", "throughput": 1034.16, "total_tokens": 6926128} {"current_steps": 76925, "total_steps": 76960, "loss": 0.0004, "lr": 3.3327253620707433e-11, "epoch": 19.990904365904367, "percentage": 99.95, "elapsed_time": "1:51:37", "remaining_time": "0:00:03", "throughput": 1034.16, "total_tokens": 6926576} {"current_steps": 76930, "total_steps": 76960, "loss": 0.0002, "lr": 2.4712571428109344e-11, "epoch": 19.992203742203742, "percentage": 99.96, "elapsed_time": "1:51:38", "remaining_time": "0:00:02", "throughput": 1034.16, "total_tokens": 6927008} {"current_steps": 76935, "total_steps": 76960, "loss": 0.0001, "lr": 1.7383661915504334e-11, "epoch": 19.993503118503117, "percentage": 99.97, "elapsed_time": "1:51:38", "remaining_time": "0:00:02", "throughput": 1034.17, "total_tokens": 6927488} {"current_steps": 76940, "total_steps": 76960, "loss": 0.0201, "lr": 1.1340525463143791e-11, "epoch": 19.994802494802496, "percentage": 99.97, "elapsed_time": "1:51:38", "remaining_time": "0:00:01", "throughput": 1034.18, "total_tokens": 6927968} {"current_steps": 76945, "total_steps": 76960, "loss": 0.1956, "lr": 6.583162381890162e-12, "epoch": 19.99610187110187, "percentage": 99.98, "elapsed_time": "1:51:39", "remaining_time": "0:00:01", "throughput": 1034.18, "total_tokens": 6928400} {"current_steps": 76950, "total_steps": 76960, "loss": 0.0006, "lr": 3.111572915992511e-12, "epoch": 19.997401247401246, "percentage": 99.99, "elapsed_time": "1:51:39", "remaining_time": "0:00:00", "throughput": 1034.18, "total_tokens": 6928848} {"current_steps": 76955, "total_steps": 76960, "loss": 0.4653, "lr": 9.2575724586208e-13, "epoch": 19.998700623700625, "percentage": 99.99, "elapsed_time": "1:51:40", "remaining_time": "0:00:00", "throughput": 1034.18, "total_tokens": 6929280} {"current_steps": 76960, "total_steps": 76960, "loss": 0.0006, "lr": 2.5715479745613837e-14, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:51:40", "remaining_time": "0:00:00", "throughput": 1034.17, "total_tokens": 6929680} {"current_steps": 76960, "total_steps": 76960, "eval_loss": 0.9521387219429016, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:51:53", "remaining_time": "0:00:00", "throughput": 1032.14, "total_tokens": 6929680} {"current_steps": 76960, "total_steps": 76960, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:51:55", "remaining_time": "0:00:00", "throughput": 1031.82, "total_tokens": 6929680}