diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,429 @@ +{"current_steps": 5, "total_steps": 42420, "loss": 0.6845, "lr": 2.8288543140028288e-05, "epoch": 0.0023573785950023575, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "3:39:29", "throughput": 3339.04, "total_tokens": 5184} +{"current_steps": 10, "total_steps": 42420, "loss": 0.6179, "lr": 6.364922206506364e-05, "epoch": 0.004714757190004715, "percentage": 0.02, "elapsed_time": "0:00:02", "remaining_time": "2:52:30", "throughput": 3933.55, "total_tokens": 9600} +{"current_steps": 15, "total_steps": 42420, "loss": 0.4621, "lr": 9.9009900990099e-05, "epoch": 0.007072135785007072, "percentage": 0.04, "elapsed_time": "0:00:03", "remaining_time": "2:39:14", "throughput": 4241.64, "total_tokens": 14336} +{"current_steps": 20, "total_steps": 42420, "loss": 0.1491, "lr": 0.00013437057991513436, "epoch": 0.00942951438000943, "percentage": 0.05, "elapsed_time": "0:00:04", "remaining_time": "2:34:37", "throughput": 4496.96, "total_tokens": 19680} +{"current_steps": 25, "total_steps": 42420, "loss": 0.6704, "lr": 0.00016973125884016973, "epoch": 0.011786892975011787, "percentage": 0.06, "elapsed_time": "0:00:05", "remaining_time": "2:30:06", "throughput": 4627.47, "total_tokens": 24576} +{"current_steps": 30, "total_steps": 42420, "loss": 0.0951, "lr": 0.00020509193776520508, "epoch": 0.014144271570014143, "percentage": 0.07, "elapsed_time": "0:00:06", "remaining_time": "2:26:38", "throughput": 4692.2, "total_tokens": 29216} +{"current_steps": 35, "total_steps": 42420, "loss": 0.071, "lr": 0.00024045261669024045, "epoch": 0.0165016501650165, "percentage": 0.08, "elapsed_time": "0:00:07", "remaining_time": "2:22:56", "throughput": 4721.92, "total_tokens": 33440} +{"current_steps": 40, "total_steps": 42420, "loss": 0.4836, "lr": 0.0002758132956152758, "epoch": 0.01885902876001886, "percentage": 0.09, "elapsed_time": "0:00:08", "remaining_time": "2:21:18", "throughput": 4778.51, "total_tokens": 38240} +{"current_steps": 45, "total_steps": 42420, "loss": 0.2748, "lr": 0.00031117397454031117, "epoch": 0.021216407355021217, "percentage": 0.11, "elapsed_time": "0:00:08", "remaining_time": "2:20:37", "throughput": 4832.0, "total_tokens": 43296} +{"current_steps": 50, "total_steps": 42420, "loss": 0.1015, "lr": 0.0003465346534653465, "epoch": 0.023573785950023574, "percentage": 0.12, "elapsed_time": "0:00:09", "remaining_time": "2:18:55", "throughput": 4857.14, "total_tokens": 47776} +{"current_steps": 55, "total_steps": 42420, "loss": 0.5362, "lr": 0.0003818953323903819, "epoch": 0.02593116454502593, "percentage": 0.13, "elapsed_time": "0:00:10", "remaining_time": "2:18:05", "throughput": 4884.81, "total_tokens": 52544} +{"current_steps": 60, "total_steps": 42420, "loss": 0.3298, "lr": 0.00041725601131541726, "epoch": 0.028288543140028287, "percentage": 0.14, "elapsed_time": "0:00:11", "remaining_time": "2:18:42", "throughput": 4935.14, "total_tokens": 58176} +{"current_steps": 65, "total_steps": 42420, "loss": 0.2339, "lr": 0.0004526166902404526, "epoch": 0.030645921735030647, "percentage": 0.15, "elapsed_time": "0:00:12", "remaining_time": "2:17:54", "throughput": 4954.2, "total_tokens": 62912} +{"current_steps": 70, "total_steps": 42420, "loss": 5.1476, "lr": 0.00048797736916548795, "epoch": 0.033003300330033, "percentage": 0.17, "elapsed_time": "0:00:13", "remaining_time": "2:18:52", "throughput": 5009.26, "total_tokens": 68992} +{"current_steps": 75, "total_steps": 42420, "loss": 6.5396, "lr": 0.0005233380480905234, "epoch": 0.03536067892503536, "percentage": 0.18, "elapsed_time": "0:00:14", "remaining_time": "2:17:36", "throughput": 5013.03, "total_tokens": 73312} +{"current_steps": 80, "total_steps": 42420, "loss": 0.2725, "lr": 0.0005586987270155586, "epoch": 0.03771805752003772, "percentage": 0.19, "elapsed_time": "0:00:15", "remaining_time": "2:18:05", "throughput": 5044.75, "total_tokens": 78976} +{"current_steps": 85, "total_steps": 42420, "loss": 0.1301, "lr": 0.000594059405940594, "epoch": 0.040075436115040074, "percentage": 0.2, "elapsed_time": "0:00:16", "remaining_time": "2:17:35", "throughput": 5050.36, "total_tokens": 83712} +{"current_steps": 90, "total_steps": 42420, "loss": 0.1647, "lr": 0.0006294200848656295, "epoch": 0.042432814710042434, "percentage": 0.21, "elapsed_time": "0:00:17", "remaining_time": "2:16:32", "throughput": 5048.53, "total_tokens": 87936} +{"current_steps": 95, "total_steps": 42420, "loss": 0.131, "lr": 0.0006647807637906647, "epoch": 0.04479019330504479, "percentage": 0.22, "elapsed_time": "0:00:18", "remaining_time": "2:16:11", "throughput": 5054.6, "total_tokens": 92704} +{"current_steps": 100, "total_steps": 42420, "loss": 0.0297, "lr": 0.0007001414427157002, "epoch": 0.04714757190004715, "percentage": 0.24, "elapsed_time": "0:00:19", "remaining_time": "2:16:03", "throughput": 5063.04, "total_tokens": 97664} +{"current_steps": 105, "total_steps": 42420, "loss": 0.3538, "lr": 0.0007355021216407354, "epoch": 0.04950495049504951, "percentage": 0.25, "elapsed_time": "0:00:20", "remaining_time": "2:15:33", "throughput": 5066.1, "total_tokens": 102240} +{"current_steps": 110, "total_steps": 42420, "loss": 0.1293, "lr": 0.0007708628005657709, "epoch": 0.05186232909005186, "percentage": 0.26, "elapsed_time": "0:00:21", "remaining_time": "2:15:32", "throughput": 5074.73, "total_tokens": 107296} +{"current_steps": 115, "total_steps": 42420, "loss": 0.0423, "lr": 0.0008062234794908062, "epoch": 0.05421970768505422, "percentage": 0.27, "elapsed_time": "0:00:22", "remaining_time": "2:16:02", "throughput": 5092.64, "total_tokens": 112992} +{"current_steps": 120, "total_steps": 42420, "loss": 0.7046, "lr": 0.0008415841584158416, "epoch": 0.056577086280056574, "percentage": 0.28, "elapsed_time": "0:00:23", "remaining_time": "2:16:18", "throughput": 5105.84, "total_tokens": 118464} +{"current_steps": 125, "total_steps": 42420, "loss": 0.9779, "lr": 0.0008769448373408769, "epoch": 0.058934464875058934, "percentage": 0.29, "elapsed_time": "0:00:24", "remaining_time": "2:17:04", "throughput": 5126.33, "total_tokens": 124608} +{"current_steps": 130, "total_steps": 42420, "loss": 1.3421, "lr": 0.0009123055162659123, "epoch": 0.061291843470061294, "percentage": 0.31, "elapsed_time": "0:00:25", "remaining_time": "2:17:59", "throughput": 5147.58, "total_tokens": 131008} +{"current_steps": 135, "total_steps": 42420, "loss": 0.4475, "lr": 0.0009476661951909475, "epoch": 0.06364922206506365, "percentage": 0.32, "elapsed_time": "0:00:26", "remaining_time": "2:18:09", "throughput": 5157.15, "total_tokens": 136480} +{"current_steps": 140, "total_steps": 42420, "loss": 0.386, "lr": 0.0009830268741159828, "epoch": 0.066006600660066, "percentage": 0.33, "elapsed_time": "0:00:27", "remaining_time": "2:17:52", "throughput": 5157.74, "total_tokens": 141280} +{"current_steps": 145, "total_steps": 42420, "loss": 2.4365, "lr": 0.0010183875530410183, "epoch": 0.06836397925506836, "percentage": 0.34, "elapsed_time": "0:00:28", "remaining_time": "2:17:49", "throughput": 5161.48, "total_tokens": 146400} +{"current_steps": 150, "total_steps": 42420, "loss": 0.3901, "lr": 0.0010537482319660538, "epoch": 0.07072135785007072, "percentage": 0.35, "elapsed_time": "0:00:29", "remaining_time": "2:17:42", "throughput": 5163.64, "total_tokens": 151392} +{"current_steps": 155, "total_steps": 42420, "loss": 0.4841, "lr": 0.0010891089108910892, "epoch": 0.07307873644507308, "percentage": 0.37, "elapsed_time": "0:00:30", "remaining_time": "2:17:45", "throughput": 5171.79, "total_tokens": 156768} +{"current_steps": 160, "total_steps": 42420, "loss": 0.5334, "lr": 0.0011244695898161242, "epoch": 0.07543611504007544, "percentage": 0.38, "elapsed_time": "0:00:31", "remaining_time": "2:17:18", "throughput": 5168.79, "total_tokens": 161216} +{"current_steps": 165, "total_steps": 42420, "loss": 0.4357, "lr": 0.0011598302687411597, "epoch": 0.07779349363507779, "percentage": 0.39, "elapsed_time": "0:00:32", "remaining_time": "2:17:22", "throughput": 5173.82, "total_tokens": 166528} +{"current_steps": 170, "total_steps": 42420, "loss": 0.5349, "lr": 0.0011951909476661951, "epoch": 0.08015087223008015, "percentage": 0.4, "elapsed_time": "0:00:33", "remaining_time": "2:17:31", "throughput": 5182.64, "total_tokens": 172064} +{"current_steps": 175, "total_steps": 42420, "loss": 0.4979, "lr": 0.0012305516265912306, "epoch": 0.08250825082508251, "percentage": 0.41, "elapsed_time": "0:00:34", "remaining_time": "2:17:27", "throughput": 5188.69, "total_tokens": 177280} +{"current_steps": 180, "total_steps": 42420, "loss": 0.3544, "lr": 0.0012659123055162658, "epoch": 0.08486562942008487, "percentage": 0.42, "elapsed_time": "0:00:35", "remaining_time": "2:16:54", "throughput": 5183.26, "total_tokens": 181440} +{"current_steps": 185, "total_steps": 42420, "loss": 1.5311, "lr": 0.001301272984441301, "epoch": 0.08722300801508723, "percentage": 0.44, "elapsed_time": "0:00:35", "remaining_time": "2:16:44", "throughput": 5189.53, "total_tokens": 186496} +{"current_steps": 190, "total_steps": 42420, "loss": 2.5966, "lr": 0.0013366336633663365, "epoch": 0.08958038661008957, "percentage": 0.45, "elapsed_time": "0:00:36", "remaining_time": "2:16:16", "throughput": 5183.44, "total_tokens": 190688} +{"current_steps": 195, "total_steps": 42420, "loss": 0.5223, "lr": 0.001371994342291372, "epoch": 0.09193776520509193, "percentage": 0.46, "elapsed_time": "0:00:37", "remaining_time": "2:16:09", "throughput": 5185.54, "total_tokens": 195648} +{"current_steps": 200, "total_steps": 42420, "loss": 1.531, "lr": 0.0014073550212164074, "epoch": 0.0942951438000943, "percentage": 0.47, "elapsed_time": "0:00:38", "remaining_time": "2:16:00", "throughput": 5187.1, "total_tokens": 200512} +{"current_steps": 205, "total_steps": 42420, "loss": 2.1468, "lr": 0.0014427157001414427, "epoch": 0.09665252239509665, "percentage": 0.48, "elapsed_time": "0:00:39", "remaining_time": "2:16:08", "throughput": 5189.48, "total_tokens": 205856} +{"current_steps": 210, "total_steps": 42420, "loss": 2.248, "lr": 0.0014780763790664781, "epoch": 0.09900990099009901, "percentage": 0.5, "elapsed_time": "0:00:40", "remaining_time": "2:16:02", "throughput": 5190.32, "total_tokens": 210784} +{"current_steps": 215, "total_steps": 42420, "loss": 0.4126, "lr": 0.0015134370579915134, "epoch": 0.10136727958510136, "percentage": 0.51, "elapsed_time": "0:00:41", "remaining_time": "2:15:48", "throughput": 5188.27, "total_tokens": 215360} +{"current_steps": 220, "total_steps": 42420, "loss": 0.2974, "lr": 0.0015487977369165488, "epoch": 0.10372465818010372, "percentage": 0.52, "elapsed_time": "0:00:42", "remaining_time": "2:15:36", "throughput": 5188.2, "total_tokens": 220064} +{"current_steps": 225, "total_steps": 42420, "loss": 0.4155, "lr": 0.001584158415841584, "epoch": 0.10608203677510608, "percentage": 0.53, "elapsed_time": "0:00:43", "remaining_time": "2:15:13", "throughput": 5185.62, "total_tokens": 224352} +{"current_steps": 230, "total_steps": 42420, "loss": 4.1296, "lr": 0.0016195190947666195, "epoch": 0.10843941537010844, "percentage": 0.54, "elapsed_time": "0:00:44", "remaining_time": "2:15:04", "throughput": 5185.4, "total_tokens": 229088} +{"current_steps": 235, "total_steps": 42420, "loss": 4.0794, "lr": 0.001654879773691655, "epoch": 0.1107967939651108, "percentage": 0.55, "elapsed_time": "0:00:45", "remaining_time": "2:14:55", "throughput": 5185.11, "total_tokens": 233824} +{"current_steps": 240, "total_steps": 42420, "loss": 3.4462, "lr": 0.0016902404526166902, "epoch": 0.11315417256011315, "percentage": 0.57, "elapsed_time": "0:00:46", "remaining_time": "2:14:51", "throughput": 5186.93, "total_tokens": 238816} +{"current_steps": 245, "total_steps": 42420, "loss": 1.0522, "lr": 0.0017256011315417254, "epoch": 0.11551155115511551, "percentage": 0.58, "elapsed_time": "0:00:46", "remaining_time": "2:14:37", "throughput": 5185.65, "total_tokens": 243328} +{"current_steps": 250, "total_steps": 42420, "loss": 0.2924, "lr": 0.0017609618104667609, "epoch": 0.11786892975011787, "percentage": 0.59, "elapsed_time": "0:00:47", "remaining_time": "2:14:47", "throughput": 5190.93, "total_tokens": 248896} +{"current_steps": 255, "total_steps": 42420, "loss": 0.6957, "lr": 0.0017963224893917963, "epoch": 0.12022630834512023, "percentage": 0.6, "elapsed_time": "0:00:48", "remaining_time": "2:14:32", "throughput": 5191.16, "total_tokens": 253440} +{"current_steps": 260, "total_steps": 42420, "loss": 0.95, "lr": 0.0018316831683168318, "epoch": 0.12258368694012259, "percentage": 0.61, "elapsed_time": "0:00:49", "remaining_time": "2:14:24", "throughput": 5191.88, "total_tokens": 258208} +{"current_steps": 265, "total_steps": 42420, "loss": 0.3657, "lr": 0.0018670438472418668, "epoch": 0.12494106553512493, "percentage": 0.62, "elapsed_time": "0:00:50", "remaining_time": "2:14:10", "throughput": 5188.54, "total_tokens": 262592} +{"current_steps": 270, "total_steps": 42420, "loss": 0.3083, "lr": 0.0019024045261669025, "epoch": 0.1272984441301273, "percentage": 0.64, "elapsed_time": "0:00:51", "remaining_time": "2:14:09", "throughput": 5190.58, "total_tokens": 267648} +{"current_steps": 275, "total_steps": 42420, "loss": 0.2898, "lr": 0.0019377652050919377, "epoch": 0.12965582272512965, "percentage": 0.65, "elapsed_time": "0:00:52", "remaining_time": "2:14:01", "throughput": 5191.32, "total_tokens": 272384} +{"current_steps": 280, "total_steps": 42420, "loss": 0.3053, "lr": 0.001973125884016973, "epoch": 0.132013201320132, "percentage": 0.66, "elapsed_time": "0:00:53", "remaining_time": "2:14:21", "throughput": 5198.51, "total_tokens": 278464} +{"current_steps": 285, "total_steps": 42420, "loss": 0.2953, "lr": 0.0020084865629420084, "epoch": 0.13437057991513437, "percentage": 0.67, "elapsed_time": "0:00:54", "remaining_time": "2:13:58", "throughput": 5194.6, "total_tokens": 282432} +{"current_steps": 290, "total_steps": 42420, "loss": 0.4164, "lr": 0.002043847241867044, "epoch": 0.13672795851013672, "percentage": 0.68, "elapsed_time": "0:00:55", "remaining_time": "2:14:00", "throughput": 5198.8, "total_tokens": 287744} +{"current_steps": 295, "total_steps": 42420, "loss": 1.2235, "lr": 0.0020792079207920793, "epoch": 0.1390853371051391, "percentage": 0.7, "elapsed_time": "0:00:56", "remaining_time": "2:13:42", "throughput": 5194.8, "total_tokens": 291840} +{"current_steps": 300, "total_steps": 42420, "loss": 0.3503, "lr": 0.0021145685997171143, "epoch": 0.14144271570014144, "percentage": 0.71, "elapsed_time": "0:00:57", "remaining_time": "2:13:40", "throughput": 5197.99, "total_tokens": 296928} +{"current_steps": 305, "total_steps": 42420, "loss": 0.3897, "lr": 0.00214992927864215, "epoch": 0.1438000942951438, "percentage": 0.72, "elapsed_time": "0:00:58", "remaining_time": "2:13:45", "throughput": 5201.02, "total_tokens": 302272} +{"current_steps": 310, "total_steps": 42420, "loss": 0.4543, "lr": 0.0021852899575671852, "epoch": 0.14615747289014616, "percentage": 0.73, "elapsed_time": "0:00:58", "remaining_time": "2:13:33", "throughput": 5198.9, "total_tokens": 306688} +{"current_steps": 315, "total_steps": 42420, "loss": 0.4124, "lr": 0.0022206506364922207, "epoch": 0.1485148514851485, "percentage": 0.74, "elapsed_time": "0:00:59", "remaining_time": "2:13:12", "throughput": 5193.04, "total_tokens": 310528} +{"current_steps": 320, "total_steps": 42420, "loss": 0.373, "lr": 0.002256011315417256, "epoch": 0.15087223008015088, "percentage": 0.75, "elapsed_time": "0:01:00", "remaining_time": "2:13:01", "throughput": 5191.0, "total_tokens": 314912} +{"current_steps": 325, "total_steps": 42420, "loss": 0.4255, "lr": 0.002291371994342291, "epoch": 0.15322960867515323, "percentage": 0.77, "elapsed_time": "0:01:01", "remaining_time": "2:12:56", "throughput": 5191.67, "total_tokens": 319712} +{"current_steps": 330, "total_steps": 42420, "loss": 0.3519, "lr": 0.0023267326732673266, "epoch": 0.15558698727015557, "percentage": 0.78, "elapsed_time": "0:01:02", "remaining_time": "2:12:55", "throughput": 5192.5, "total_tokens": 324704} +{"current_steps": 335, "total_steps": 42420, "loss": 0.3444, "lr": 0.002362093352192362, "epoch": 0.15794436586515795, "percentage": 0.79, "elapsed_time": "0:01:03", "remaining_time": "2:13:01", "throughput": 5195.87, "total_tokens": 330112} +{"current_steps": 340, "total_steps": 42420, "loss": 0.2765, "lr": 0.002397454031117397, "epoch": 0.1603017444601603, "percentage": 0.8, "elapsed_time": "0:01:04", "remaining_time": "2:13:47", "throughput": 5210.98, "total_tokens": 337984} +{"current_steps": 345, "total_steps": 42420, "loss": 0.419, "lr": 0.002432814710042433, "epoch": 0.16265912305516267, "percentage": 0.81, "elapsed_time": "0:01:05", "remaining_time": "2:13:45", "throughput": 5214.28, "total_tokens": 343136} +{"current_steps": 350, "total_steps": 42420, "loss": 4.2493, "lr": 0.002468175388967468, "epoch": 0.16501650165016502, "percentage": 0.83, "elapsed_time": "0:01:06", "remaining_time": "2:13:59", "throughput": 5218.12, "total_tokens": 348992} +{"current_steps": 355, "total_steps": 42420, "loss": 7.6579, "lr": 0.0025035360678925035, "epoch": 0.16737388024516736, "percentage": 0.84, "elapsed_time": "0:01:07", "remaining_time": "2:13:49", "throughput": 5216.86, "total_tokens": 353504} +{"current_steps": 360, "total_steps": 42420, "loss": 4.0053, "lr": 0.002538896746817539, "epoch": 0.16973125884016974, "percentage": 0.85, "elapsed_time": "0:01:08", "remaining_time": "2:13:56", "throughput": 5220.89, "total_tokens": 359104} +{"current_steps": 365, "total_steps": 42420, "loss": 1.3316, "lr": 0.002574257425742574, "epoch": 0.17208863743517208, "percentage": 0.86, "elapsed_time": "0:01:09", "remaining_time": "2:13:48", "throughput": 5219.91, "total_tokens": 363744} +{"current_steps": 370, "total_steps": 42420, "loss": 0.6581, "lr": 0.00260961810466761, "epoch": 0.17444601603017446, "percentage": 0.87, "elapsed_time": "0:01:10", "remaining_time": "2:13:45", "throughput": 5223.59, "total_tokens": 368864} +{"current_steps": 375, "total_steps": 42420, "loss": 0.4714, "lr": 0.002644978783592645, "epoch": 0.1768033946251768, "percentage": 0.88, "elapsed_time": "0:01:11", "remaining_time": "2:13:42", "throughput": 5224.21, "total_tokens": 373824} +{"current_steps": 380, "total_steps": 42420, "loss": 0.4531, "lr": 0.00268033946251768, "epoch": 0.17916077322017915, "percentage": 0.9, "elapsed_time": "0:01:12", "remaining_time": "2:13:34", "throughput": 5223.65, "total_tokens": 378432} +{"current_steps": 385, "total_steps": 42420, "loss": 0.217, "lr": 0.0027157001414427158, "epoch": 0.18151815181518152, "percentage": 0.91, "elapsed_time": "0:01:13", "remaining_time": "2:13:34", "throughput": 5225.04, "total_tokens": 383552} +{"current_steps": 390, "total_steps": 42420, "loss": 0.4561, "lr": 0.0027510608203677508, "epoch": 0.18387553041018387, "percentage": 0.92, "elapsed_time": "0:01:14", "remaining_time": "2:13:34", "throughput": 5227.67, "total_tokens": 388768} +{"current_steps": 395, "total_steps": 42420, "loss": 0.34, "lr": 0.0027864214992927867, "epoch": 0.18623290900518624, "percentage": 0.93, "elapsed_time": "0:01:15", "remaining_time": "2:13:24", "throughput": 5225.2, "total_tokens": 393120} +{"current_steps": 400, "total_steps": 42420, "loss": 0.7904, "lr": 0.0028217821782178217, "epoch": 0.1885902876001886, "percentage": 0.94, "elapsed_time": "0:01:16", "remaining_time": "2:13:17", "throughput": 5225.68, "total_tokens": 397856} +{"current_steps": 405, "total_steps": 42420, "loss": 0.5888, "lr": 0.0028571428571428567, "epoch": 0.19094766619519093, "percentage": 0.95, "elapsed_time": "0:01:17", "remaining_time": "2:13:15", "throughput": 5226.75, "total_tokens": 402848} +{"current_steps": 410, "total_steps": 42420, "loss": 0.4424, "lr": 0.0028925035360678926, "epoch": 0.1933050447901933, "percentage": 0.97, "elapsed_time": "0:01:18", "remaining_time": "2:13:14", "throughput": 5228.51, "total_tokens": 407936} +{"current_steps": 415, "total_steps": 42420, "loss": 0.3755, "lr": 0.0029278642149929276, "epoch": 0.19566242338519566, "percentage": 0.98, "elapsed_time": "0:01:18", "remaining_time": "2:13:12", "throughput": 5230.76, "total_tokens": 413024} +{"current_steps": 420, "total_steps": 42420, "loss": 0.552, "lr": 0.0029632248939179635, "epoch": 0.19801980198019803, "percentage": 0.99, "elapsed_time": "0:01:19", "remaining_time": "2:13:18", "throughput": 5235.03, "total_tokens": 418720} +{"current_steps": 425, "total_steps": 42420, "loss": 0.3263, "lr": 0.0029985855728429985, "epoch": 0.20037718057520038, "percentage": 1.0, "elapsed_time": "0:01:21", "remaining_time": "2:13:40", "throughput": 5241.64, "total_tokens": 425440} +{"current_steps": 430, "total_steps": 42420, "loss": 0.818, "lr": 0.0030339462517680335, "epoch": 0.20273455917020272, "percentage": 1.01, "elapsed_time": "0:01:22", "remaining_time": "2:13:37", "throughput": 5242.95, "total_tokens": 430464} +{"current_steps": 435, "total_steps": 42420, "loss": 0.3694, "lr": 0.0030693069306930694, "epoch": 0.2050919377652051, "percentage": 1.03, "elapsed_time": "0:01:23", "remaining_time": "2:13:39", "throughput": 5245.01, "total_tokens": 435776} +{"current_steps": 440, "total_steps": 42420, "loss": 0.4605, "lr": 0.0031046676096181045, "epoch": 0.20744931636020744, "percentage": 1.04, "elapsed_time": "0:01:23", "remaining_time": "2:13:31", "throughput": 5244.21, "total_tokens": 440352} +{"current_steps": 445, "total_steps": 42420, "loss": 0.3507, "lr": 0.00314002828854314, "epoch": 0.20980669495520982, "percentage": 1.05, "elapsed_time": "0:01:24", "remaining_time": "2:13:22", "throughput": 5242.28, "total_tokens": 444768} +{"current_steps": 450, "total_steps": 42420, "loss": 0.5127, "lr": 0.0031753889674681754, "epoch": 0.21216407355021216, "percentage": 1.06, "elapsed_time": "0:01:25", "remaining_time": "2:13:29", "throughput": 5246.17, "total_tokens": 450528} +{"current_steps": 455, "total_steps": 42420, "loss": 0.3498, "lr": 0.0032107496463932104, "epoch": 0.2145214521452145, "percentage": 1.07, "elapsed_time": "0:01:26", "remaining_time": "2:13:20", "throughput": 5244.71, "total_tokens": 454976} +{"current_steps": 460, "total_steps": 42420, "loss": 0.4289, "lr": 0.0032461103253182463, "epoch": 0.21687883074021688, "percentage": 1.08, "elapsed_time": "0:01:27", "remaining_time": "2:13:07", "throughput": 5242.43, "total_tokens": 459072} +{"current_steps": 465, "total_steps": 42420, "loss": 0.3406, "lr": 0.0032814710042432813, "epoch": 0.21923620933521923, "percentage": 1.1, "elapsed_time": "0:01:28", "remaining_time": "2:13:07", "throughput": 5244.75, "total_tokens": 464320} +{"current_steps": 470, "total_steps": 42420, "loss": 0.3884, "lr": 0.0033168316831683167, "epoch": 0.2215935879302216, "percentage": 1.11, "elapsed_time": "0:01:29", "remaining_time": "2:13:03", "throughput": 5244.88, "total_tokens": 469120} +{"current_steps": 475, "total_steps": 42420, "loss": 0.4522, "lr": 0.003352192362093352, "epoch": 0.22395096652522395, "percentage": 1.12, "elapsed_time": "0:01:30", "remaining_time": "2:12:59", "throughput": 5244.8, "total_tokens": 473920} +{"current_steps": 480, "total_steps": 42420, "loss": 0.3726, "lr": 0.003387553041018387, "epoch": 0.2263083451202263, "percentage": 1.13, "elapsed_time": "0:01:31", "remaining_time": "2:12:46", "throughput": 5241.95, "total_tokens": 477920} +{"current_steps": 485, "total_steps": 42420, "loss": 0.4329, "lr": 0.0034229137199434227, "epoch": 0.22866572371522867, "percentage": 1.14, "elapsed_time": "0:01:32", "remaining_time": "2:12:46", "throughput": 5242.79, "total_tokens": 483040} +{"current_steps": 490, "total_steps": 42420, "loss": 0.4037, "lr": 0.003458274398868458, "epoch": 0.23102310231023102, "percentage": 1.16, "elapsed_time": "0:01:33", "remaining_time": "2:12:42", "throughput": 5242.93, "total_tokens": 487872} +{"current_steps": 495, "total_steps": 42420, "loss": 0.4206, "lr": 0.0034936350777934936, "epoch": 0.2333804809052334, "percentage": 1.17, "elapsed_time": "0:01:34", "remaining_time": "2:12:41", "throughput": 5244.21, "total_tokens": 492960} +{"current_steps": 500, "total_steps": 42420, "loss": 0.3303, "lr": 0.003528995756718529, "epoch": 0.23573785950023574, "percentage": 1.18, "elapsed_time": "0:01:35", "remaining_time": "2:12:45", "throughput": 5246.07, "total_tokens": 498400} +{"current_steps": 505, "total_steps": 42420, "loss": 0.3465, "lr": 0.003564356435643564, "epoch": 0.23809523809523808, "percentage": 1.19, "elapsed_time": "0:01:35", "remaining_time": "2:12:36", "throughput": 5244.73, "total_tokens": 502784} +{"current_steps": 510, "total_steps": 42420, "loss": 0.3437, "lr": 0.0035997171145685995, "epoch": 0.24045261669024046, "percentage": 1.2, "elapsed_time": "0:01:36", "remaining_time": "2:12:35", "throughput": 5244.98, "total_tokens": 507776} +{"current_steps": 515, "total_steps": 42420, "loss": 0.3353, "lr": 0.003635077793493635, "epoch": 0.2428099952852428, "percentage": 1.21, "elapsed_time": "0:01:37", "remaining_time": "2:12:31", "throughput": 5244.56, "total_tokens": 512480} +{"current_steps": 520, "total_steps": 42420, "loss": 0.3671, "lr": 0.0036704384724186704, "epoch": 0.24516737388024518, "percentage": 1.23, "elapsed_time": "0:01:38", "remaining_time": "2:12:30", "throughput": 5245.93, "total_tokens": 517600} +{"current_steps": 525, "total_steps": 42420, "loss": 0.3286, "lr": 0.003705799151343706, "epoch": 0.24752475247524752, "percentage": 1.24, "elapsed_time": "0:01:39", "remaining_time": "2:12:39", "throughput": 5248.97, "total_tokens": 523520} +{"current_steps": 530, "total_steps": 42420, "loss": 0.3548, "lr": 0.003741159830268741, "epoch": 0.24988213107024987, "percentage": 1.25, "elapsed_time": "0:01:40", "remaining_time": "2:12:28", "throughput": 5246.17, "total_tokens": 527584} +{"current_steps": 535, "total_steps": 42420, "loss": 0.197, "lr": 0.003776520509193776, "epoch": 0.2522395096652522, "percentage": 1.26, "elapsed_time": "0:01:41", "remaining_time": "2:12:27", "throughput": 5247.72, "total_tokens": 532736} +{"current_steps": 540, "total_steps": 42420, "loss": 0.485, "lr": 0.0038118811881188122, "epoch": 0.2545968882602546, "percentage": 1.27, "elapsed_time": "0:01:42", "remaining_time": "2:12:23", "throughput": 5247.5, "total_tokens": 537440} +{"current_steps": 545, "total_steps": 42420, "loss": 0.3253, "lr": 0.0038472418670438473, "epoch": 0.25695426685525696, "percentage": 1.28, "elapsed_time": "0:01:43", "remaining_time": "2:12:27", "throughput": 5250.26, "total_tokens": 543040} +{"current_steps": 550, "total_steps": 42420, "loss": 0.4435, "lr": 0.0038826025459688823, "epoch": 0.2593116454502593, "percentage": 1.3, "elapsed_time": "0:01:44", "remaining_time": "2:12:19", "throughput": 5249.54, "total_tokens": 547520} +{"current_steps": 555, "total_steps": 42420, "loss": 0.4553, "lr": 0.003917963224893918, "epoch": 0.26166902404526166, "percentage": 1.31, "elapsed_time": "0:01:45", "remaining_time": "2:12:20", "throughput": 5251.21, "total_tokens": 552800} +{"current_steps": 560, "total_steps": 42420, "loss": 0.3682, "lr": 0.003953323903818953, "epoch": 0.264026402640264, "percentage": 1.32, "elapsed_time": "0:01:46", "remaining_time": "2:12:13", "throughput": 5251.36, "total_tokens": 557376} +{"current_steps": 565, "total_steps": 42420, "loss": 0.3719, "lr": 0.003988684582743989, "epoch": 0.2663837812352664, "percentage": 1.33, "elapsed_time": "0:01:47", "remaining_time": "2:12:24", "throughput": 5257.03, "total_tokens": 563776} +{"current_steps": 570, "total_steps": 42420, "loss": 0.5079, "lr": 0.004024045261669024, "epoch": 0.26874115983026875, "percentage": 1.34, "elapsed_time": "0:01:48", "remaining_time": "2:12:13", "throughput": 5254.16, "total_tokens": 567712} +{"current_steps": 575, "total_steps": 42420, "loss": 0.3619, "lr": 0.0040594059405940595, "epoch": 0.2710985384252711, "percentage": 1.36, "elapsed_time": "0:01:49", "remaining_time": "2:12:13", "throughput": 5256.02, "total_tokens": 572992} +{"current_steps": 580, "total_steps": 42420, "loss": 0.379, "lr": 0.0040947666195190946, "epoch": 0.27345591702027344, "percentage": 1.37, "elapsed_time": "0:01:50", "remaining_time": "2:12:18", "throughput": 5259.74, "total_tokens": 578816} +{"current_steps": 585, "total_steps": 42420, "loss": 0.3523, "lr": 0.00413012729844413, "epoch": 0.2758132956152758, "percentage": 1.38, "elapsed_time": "0:01:50", "remaining_time": "2:12:14", "throughput": 5259.51, "total_tokens": 583552} +{"current_steps": 590, "total_steps": 42420, "loss": 0.2749, "lr": 0.0041654879773691655, "epoch": 0.2781706742102782, "percentage": 1.39, "elapsed_time": "0:01:51", "remaining_time": "2:12:16", "throughput": 5260.7, "total_tokens": 588864} +{"current_steps": 595, "total_steps": 42420, "loss": 0.4256, "lr": 0.0042008486562942005, "epoch": 0.28052805280528054, "percentage": 1.4, "elapsed_time": "0:01:52", "remaining_time": "2:12:08", "throughput": 5259.43, "total_tokens": 593248} +{"current_steps": 600, "total_steps": 42420, "loss": 0.43, "lr": 0.004236209335219236, "epoch": 0.2828854314002829, "percentage": 1.41, "elapsed_time": "0:01:53", "remaining_time": "2:12:18", "throughput": 5262.69, "total_tokens": 599360} +{"current_steps": 605, "total_steps": 42420, "loss": 0.4733, "lr": 0.004271570014144271, "epoch": 0.28524280999528523, "percentage": 1.43, "elapsed_time": "0:01:54", "remaining_time": "2:12:15", "throughput": 5263.53, "total_tokens": 604352} +{"current_steps": 610, "total_steps": 42420, "loss": 0.3085, "lr": 0.004306930693069306, "epoch": 0.2876001885902876, "percentage": 1.44, "elapsed_time": "0:01:55", "remaining_time": "2:12:18", "throughput": 5266.33, "total_tokens": 609952} +{"current_steps": 615, "total_steps": 42420, "loss": 0.4594, "lr": 0.004342291371994342, "epoch": 0.28995756718529, "percentage": 1.45, "elapsed_time": "0:01:56", "remaining_time": "2:12:11", "throughput": 5265.53, "total_tokens": 614400} +{"current_steps": 620, "total_steps": 42420, "loss": 0.4276, "lr": 0.004377652050919377, "epoch": 0.2923149457802923, "percentage": 1.46, "elapsed_time": "0:01:57", "remaining_time": "2:12:10", "throughput": 5267.0, "total_tokens": 619552} +{"current_steps": 625, "total_steps": 42420, "loss": 0.3609, "lr": 0.004413012729844413, "epoch": 0.29467232437529467, "percentage": 1.47, "elapsed_time": "0:01:58", "remaining_time": "2:12:11", "throughput": 5269.33, "total_tokens": 624960} +{"current_steps": 630, "total_steps": 42420, "loss": 0.4579, "lr": 0.004448373408769448, "epoch": 0.297029702970297, "percentage": 1.49, "elapsed_time": "0:01:59", "remaining_time": "2:12:23", "throughput": 5273.87, "total_tokens": 631520} +{"current_steps": 635, "total_steps": 42420, "loss": 0.3012, "lr": 0.004483734087694483, "epoch": 0.29938708156529936, "percentage": 1.5, "elapsed_time": "0:02:00", "remaining_time": "2:12:29", "throughput": 5277.33, "total_tokens": 637568} +{"current_steps": 640, "total_steps": 42420, "loss": 0.6666, "lr": 0.004519094766619519, "epoch": 0.30174446016030176, "percentage": 1.51, "elapsed_time": "0:02:01", "remaining_time": "2:12:28", "throughput": 5278.37, "total_tokens": 642688} +{"current_steps": 645, "total_steps": 42420, "loss": 0.3584, "lr": 0.004554455445544554, "epoch": 0.3041018387553041, "percentage": 1.52, "elapsed_time": "0:02:02", "remaining_time": "2:12:24", "throughput": 5277.88, "total_tokens": 647392} +{"current_steps": 650, "total_steps": 42420, "loss": 0.39, "lr": 0.00458981612446959, "epoch": 0.30645921735030646, "percentage": 1.53, "elapsed_time": "0:02:03", "remaining_time": "2:12:26", "throughput": 5279.31, "total_tokens": 652800} +{"current_steps": 655, "total_steps": 42420, "loss": 0.3478, "lr": 0.004625176803394625, "epoch": 0.3088165959453088, "percentage": 1.54, "elapsed_time": "0:02:04", "remaining_time": "2:12:36", "throughput": 5283.89, "total_tokens": 659328} +{"current_steps": 660, "total_steps": 42420, "loss": 0.349, "lr": 0.00466053748231966, "epoch": 0.31117397454031115, "percentage": 1.56, "elapsed_time": "0:02:05", "remaining_time": "2:12:27", "throughput": 5282.22, "total_tokens": 663488} +{"current_steps": 665, "total_steps": 42420, "loss": 0.3831, "lr": 0.004695898161244696, "epoch": 0.31353135313531355, "percentage": 1.57, "elapsed_time": "0:02:06", "remaining_time": "2:12:22", "throughput": 5282.09, "total_tokens": 668192} +{"current_steps": 670, "total_steps": 42420, "loss": 0.3569, "lr": 0.004731258840169731, "epoch": 0.3158887317303159, "percentage": 1.58, "elapsed_time": "0:02:07", "remaining_time": "2:12:23", "throughput": 5283.95, "total_tokens": 673568} +{"current_steps": 675, "total_steps": 42420, "loss": 0.3833, "lr": 0.004766619519094766, "epoch": 0.31824611032531824, "percentage": 1.59, "elapsed_time": "0:02:08", "remaining_time": "2:12:41", "throughput": 5290.59, "total_tokens": 681056} +{"current_steps": 680, "total_steps": 42420, "loss": 0.2861, "lr": 0.004801980198019802, "epoch": 0.3206034889203206, "percentage": 1.6, "elapsed_time": "0:02:09", "remaining_time": "2:12:38", "throughput": 5290.31, "total_tokens": 685920} +{"current_steps": 685, "total_steps": 42420, "loss": 0.4125, "lr": 0.004837340876944837, "epoch": 0.32296086751532294, "percentage": 1.61, "elapsed_time": "0:02:10", "remaining_time": "2:12:35", "throughput": 5290.71, "total_tokens": 690816} +{"current_steps": 690, "total_steps": 42420, "loss": 0.3123, "lr": 0.004872701555869873, "epoch": 0.32531824611032534, "percentage": 1.63, "elapsed_time": "0:02:11", "remaining_time": "2:12:31", "throughput": 5290.93, "total_tokens": 695648} +{"current_steps": 695, "total_steps": 42420, "loss": 0.353, "lr": 0.004908062234794908, "epoch": 0.3276756247053277, "percentage": 1.64, "elapsed_time": "0:02:12", "remaining_time": "2:12:33", "throughput": 5291.31, "total_tokens": 700960} +{"current_steps": 700, "total_steps": 42420, "loss": 0.3663, "lr": 0.004943422913719943, "epoch": 0.33003300330033003, "percentage": 1.65, "elapsed_time": "0:02:13", "remaining_time": "2:12:30", "throughput": 5291.3, "total_tokens": 705856} +{"current_steps": 705, "total_steps": 42420, "loss": 0.3448, "lr": 0.004978783592644979, "epoch": 0.3323903818953324, "percentage": 1.66, "elapsed_time": "0:02:14", "remaining_time": "2:12:23", "throughput": 5290.41, "total_tokens": 710272} +{"current_steps": 710, "total_steps": 42420, "loss": 0.334, "lr": 0.005014144271570014, "epoch": 0.3347477604903347, "percentage": 1.67, "elapsed_time": "0:02:15", "remaining_time": "2:12:18", "throughput": 5289.47, "total_tokens": 714816} +{"current_steps": 715, "total_steps": 42420, "loss": 0.4334, "lr": 0.00504950495049505, "epoch": 0.3371051390853371, "percentage": 1.69, "elapsed_time": "0:02:16", "remaining_time": "2:12:25", "throughput": 5290.91, "total_tokens": 720736} +{"current_steps": 720, "total_steps": 42420, "loss": 0.3603, "lr": 0.005084865629420085, "epoch": 0.33946251768033947, "percentage": 1.7, "elapsed_time": "0:02:17", "remaining_time": "2:12:30", "throughput": 5294.53, "total_tokens": 726848} +{"current_steps": 725, "total_steps": 42420, "loss": 0.3878, "lr": 0.00512022630834512, "epoch": 0.3418198962753418, "percentage": 1.71, "elapsed_time": "0:02:18", "remaining_time": "2:12:33", "throughput": 5296.76, "total_tokens": 732512} +{"current_steps": 730, "total_steps": 42420, "loss": 0.2851, "lr": 0.005155586987270156, "epoch": 0.34417727487034416, "percentage": 1.72, "elapsed_time": "0:02:19", "remaining_time": "2:12:34", "throughput": 5297.91, "total_tokens": 737952} +{"current_steps": 735, "total_steps": 42420, "loss": 0.4213, "lr": 0.005190947666195191, "epoch": 0.3465346534653465, "percentage": 1.73, "elapsed_time": "0:02:20", "remaining_time": "2:12:32", "throughput": 5297.13, "total_tokens": 742752} +{"current_steps": 740, "total_steps": 42420, "loss": 0.4133, "lr": 0.0052263083451202265, "epoch": 0.3488920320603489, "percentage": 1.74, "elapsed_time": "0:02:21", "remaining_time": "2:12:32", "throughput": 5297.58, "total_tokens": 747968} +{"current_steps": 745, "total_steps": 42420, "loss": 0.3612, "lr": 0.0052616690240452615, "epoch": 0.35124941065535126, "percentage": 1.76, "elapsed_time": "0:02:22", "remaining_time": "2:12:35", "throughput": 5299.12, "total_tokens": 753632} +{"current_steps": 750, "total_steps": 42420, "loss": 0.4092, "lr": 0.0052970297029702965, "epoch": 0.3536067892503536, "percentage": 1.77, "elapsed_time": "0:02:23", "remaining_time": "2:12:43", "throughput": 5301.98, "total_tokens": 759904} +{"current_steps": 755, "total_steps": 42420, "loss": 0.3677, "lr": 0.005332390381895332, "epoch": 0.35596416784535595, "percentage": 1.78, "elapsed_time": "0:02:24", "remaining_time": "2:12:41", "throughput": 5302.2, "total_tokens": 764960} +{"current_steps": 760, "total_steps": 42420, "loss": 0.3474, "lr": 0.0053677510608203674, "epoch": 0.3583215464403583, "percentage": 1.79, "elapsed_time": "0:02:25", "remaining_time": "2:12:34", "throughput": 5300.41, "total_tokens": 769184} +{"current_steps": 765, "total_steps": 42420, "loss": 0.2496, "lr": 0.005403111739745403, "epoch": 0.3606789250353607, "percentage": 1.8, "elapsed_time": "0:02:26", "remaining_time": "2:12:40", "throughput": 5302.06, "total_tokens": 775104} +{"current_steps": 770, "total_steps": 42420, "loss": 0.4412, "lr": 0.005438472418670438, "epoch": 0.36303630363036304, "percentage": 1.82, "elapsed_time": "0:02:27", "remaining_time": "2:12:35", "throughput": 5301.34, "total_tokens": 779744} +{"current_steps": 775, "total_steps": 42420, "loss": 0.4712, "lr": 0.005473833097595473, "epoch": 0.3653936822253654, "percentage": 1.83, "elapsed_time": "0:02:28", "remaining_time": "2:12:33", "throughput": 5302.16, "total_tokens": 784832} +{"current_steps": 780, "total_steps": 42420, "loss": 0.3462, "lr": 0.005509193776520508, "epoch": 0.36775106082036774, "percentage": 1.84, "elapsed_time": "0:02:28", "remaining_time": "2:12:32", "throughput": 5302.78, "total_tokens": 789920} +{"current_steps": 785, "total_steps": 42420, "loss": 0.3655, "lr": 0.005544554455445544, "epoch": 0.3701084394153701, "percentage": 1.85, "elapsed_time": "0:02:29", "remaining_time": "2:12:33", "throughput": 5302.84, "total_tokens": 795168} +{"current_steps": 790, "total_steps": 42420, "loss": 0.3628, "lr": 0.00557991513437058, "epoch": 0.3724658180103725, "percentage": 1.86, "elapsed_time": "0:02:30", "remaining_time": "2:12:30", "throughput": 5302.94, "total_tokens": 800096} +{"current_steps": 795, "total_steps": 42420, "loss": 0.3315, "lr": 0.005615275813295615, "epoch": 0.37482319660537483, "percentage": 1.87, "elapsed_time": "0:02:31", "remaining_time": "2:12:31", "throughput": 5304.58, "total_tokens": 805632} +{"current_steps": 800, "total_steps": 42420, "loss": 0.3035, "lr": 0.00565063649222065, "epoch": 0.3771805752003772, "percentage": 1.89, "elapsed_time": "0:02:32", "remaining_time": "2:12:30", "throughput": 5304.83, "total_tokens": 810688} +{"current_steps": 805, "total_steps": 42420, "loss": 0.3527, "lr": 0.005685997171145685, "epoch": 0.3795379537953795, "percentage": 1.9, "elapsed_time": "0:02:33", "remaining_time": "2:12:26", "throughput": 5303.69, "total_tokens": 815264} +{"current_steps": 810, "total_steps": 42420, "loss": 0.3882, "lr": 0.005721357850070721, "epoch": 0.38189533239038187, "percentage": 1.91, "elapsed_time": "0:02:34", "remaining_time": "2:12:25", "throughput": 5303.97, "total_tokens": 820320} +{"current_steps": 815, "total_steps": 42420, "loss": 0.3581, "lr": 0.005756718528995757, "epoch": 0.38425271098538427, "percentage": 1.92, "elapsed_time": "0:02:35", "remaining_time": "2:12:15", "throughput": 5301.51, "total_tokens": 824064} +{"current_steps": 820, "total_steps": 42420, "loss": 0.362, "lr": 0.005792079207920792, "epoch": 0.3866100895803866, "percentage": 1.93, "elapsed_time": "0:02:36", "remaining_time": "2:12:13", "throughput": 5301.7, "total_tokens": 829120} +{"current_steps": 825, "total_steps": 42420, "loss": 0.2724, "lr": 0.005827439886845827, "epoch": 0.38896746817538896, "percentage": 1.94, "elapsed_time": "0:02:37", "remaining_time": "2:12:16", "throughput": 5303.25, "total_tokens": 834816} +{"current_steps": 830, "total_steps": 42420, "loss": 0.4482, "lr": 0.005862800565770862, "epoch": 0.3913248467703913, "percentage": 1.96, "elapsed_time": "0:02:38", "remaining_time": "2:12:17", "throughput": 5304.55, "total_tokens": 840256} +{"current_steps": 835, "total_steps": 42420, "loss": 0.3177, "lr": 0.005898161244695898, "epoch": 0.39368222536539366, "percentage": 1.97, "elapsed_time": "0:02:39", "remaining_time": "2:12:13", "throughput": 5303.58, "total_tokens": 844864} +{"current_steps": 840, "total_steps": 42420, "loss": 0.35, "lr": 0.005933521923620934, "epoch": 0.39603960396039606, "percentage": 1.98, "elapsed_time": "0:02:40", "remaining_time": "2:12:14", "throughput": 5304.39, "total_tokens": 850304} +{"current_steps": 845, "total_steps": 42420, "loss": 0.3499, "lr": 0.005968882602545969, "epoch": 0.3983969825553984, "percentage": 1.99, "elapsed_time": "0:02:41", "remaining_time": "2:12:12", "throughput": 5304.25, "total_tokens": 855232} +{"current_steps": 850, "total_steps": 42420, "loss": 0.3475, "lr": 0.006004243281471004, "epoch": 0.40075436115040075, "percentage": 2.0, "elapsed_time": "0:02:42", "remaining_time": "2:12:10", "throughput": 5304.1, "total_tokens": 860128} +{"current_steps": 855, "total_steps": 42420, "loss": 0.3669, "lr": 0.006039603960396039, "epoch": 0.4031117397454031, "percentage": 2.02, "elapsed_time": "0:02:43", "remaining_time": "2:12:07", "throughput": 5303.93, "total_tokens": 864896} +{"current_steps": 860, "total_steps": 42420, "loss": 0.327, "lr": 0.006074964639321075, "epoch": 0.40546911834040544, "percentage": 2.03, "elapsed_time": "0:02:43", "remaining_time": "2:12:02", "throughput": 5302.98, "total_tokens": 869408} +{"current_steps": 865, "total_steps": 42420, "loss": 0.3752, "lr": 0.006110325318246111, "epoch": 0.40782649693540785, "percentage": 2.04, "elapsed_time": "0:02:44", "remaining_time": "2:11:59", "throughput": 5302.59, "total_tokens": 874144} +{"current_steps": 870, "total_steps": 42420, "loss": 0.3569, "lr": 0.006145685997171146, "epoch": 0.4101838755304102, "percentage": 2.05, "elapsed_time": "0:02:45", "remaining_time": "2:11:57", "throughput": 5302.65, "total_tokens": 879040} +{"current_steps": 875, "total_steps": 42420, "loss": 0.3492, "lr": 0.006181046676096181, "epoch": 0.41254125412541254, "percentage": 2.06, "elapsed_time": "0:02:46", "remaining_time": "2:11:53", "throughput": 5302.04, "total_tokens": 883712} +{"current_steps": 880, "total_steps": 42420, "loss": 0.343, "lr": 0.006216407355021216, "epoch": 0.4148986327204149, "percentage": 2.07, "elapsed_time": "0:02:47", "remaining_time": "2:11:48", "throughput": 5301.0, "total_tokens": 888128} +{"current_steps": 885, "total_steps": 42420, "loss": 0.3452, "lr": 0.006251768033946251, "epoch": 0.41725601131541723, "percentage": 2.09, "elapsed_time": "0:02:48", "remaining_time": "2:11:53", "throughput": 5303.25, "total_tokens": 894240} +{"current_steps": 890, "total_steps": 42420, "loss": 0.3473, "lr": 0.0062871287128712875, "epoch": 0.41961338991041963, "percentage": 2.1, "elapsed_time": "0:02:49", "remaining_time": "2:11:53", "throughput": 5304.07, "total_tokens": 899456} +{"current_steps": 895, "total_steps": 42420, "loss": 0.3571, "lr": 0.0063224893917963225, "epoch": 0.421970768505422, "percentage": 2.11, "elapsed_time": "0:02:50", "remaining_time": "2:11:52", "throughput": 5304.81, "total_tokens": 904672} +{"current_steps": 900, "total_steps": 42420, "loss": 0.3511, "lr": 0.0063578500707213575, "epoch": 0.4243281471004243, "percentage": 2.12, "elapsed_time": "0:02:51", "remaining_time": "2:12:14", "throughput": 5309.97, "total_tokens": 913216} +{"current_steps": 905, "total_steps": 42420, "loss": 0.3554, "lr": 0.006393210749646393, "epoch": 0.42668552569542667, "percentage": 2.13, "elapsed_time": "0:02:52", "remaining_time": "2:12:09", "throughput": 5308.93, "total_tokens": 917664} +{"current_steps": 910, "total_steps": 42420, "loss": 0.2872, "lr": 0.006428571428571428, "epoch": 0.429042904290429, "percentage": 2.15, "elapsed_time": "0:02:53", "remaining_time": "2:12:11", "throughput": 5310.51, "total_tokens": 923360} +{"current_steps": 915, "total_steps": 42420, "loss": 0.3485, "lr": 0.006463932107496464, "epoch": 0.4314002828854314, "percentage": 2.16, "elapsed_time": "0:02:54", "remaining_time": "2:12:11", "throughput": 5310.97, "total_tokens": 928608} +{"current_steps": 920, "total_steps": 42420, "loss": 0.3614, "lr": 0.006499292786421499, "epoch": 0.43375766148043376, "percentage": 2.17, "elapsed_time": "0:02:55", "remaining_time": "2:12:07", "throughput": 5310.42, "total_tokens": 933312} +{"current_steps": 925, "total_steps": 42420, "loss": 0.3743, "lr": 0.006534653465346534, "epoch": 0.4361150400754361, "percentage": 2.18, "elapsed_time": "0:02:56", "remaining_time": "2:12:03", "throughput": 5309.56, "total_tokens": 937824} +{"current_steps": 930, "total_steps": 42420, "loss": 0.3493, "lr": 0.006570014144271569, "epoch": 0.43847241867043846, "percentage": 2.19, "elapsed_time": "0:02:57", "remaining_time": "2:11:57", "throughput": 5308.18, "total_tokens": 942016} +{"current_steps": 935, "total_steps": 42420, "loss": 0.3529, "lr": 0.006605374823196604, "epoch": 0.4408297972654408, "percentage": 2.2, "elapsed_time": "0:02:58", "remaining_time": "2:11:50", "throughput": 5306.61, "total_tokens": 946080} +{"current_steps": 940, "total_steps": 42420, "loss": 0.3315, "lr": 0.006640735502121641, "epoch": 0.4431871758604432, "percentage": 2.22, "elapsed_time": "0:02:59", "remaining_time": "2:11:48", "throughput": 5307.02, "total_tokens": 951168} +{"current_steps": 945, "total_steps": 42420, "loss": 0.2576, "lr": 0.006676096181046676, "epoch": 0.44554455445544555, "percentage": 2.23, "elapsed_time": "0:03:00", "remaining_time": "2:11:51", "throughput": 5308.65, "total_tokens": 956992} +{"current_steps": 950, "total_steps": 42420, "loss": 0.5709, "lr": 0.006711456859971711, "epoch": 0.4479019330504479, "percentage": 2.24, "elapsed_time": "0:03:01", "remaining_time": "2:11:45", "throughput": 5307.49, "total_tokens": 961248} +{"current_steps": 955, "total_steps": 42420, "loss": 0.3426, "lr": 0.006746817538896746, "epoch": 0.45025931164545024, "percentage": 2.25, "elapsed_time": "0:03:01", "remaining_time": "2:11:39", "throughput": 5305.95, "total_tokens": 965376} +{"current_steps": 960, "total_steps": 42420, "loss": 0.3708, "lr": 0.006782178217821781, "epoch": 0.4526166902404526, "percentage": 2.26, "elapsed_time": "0:03:02", "remaining_time": "2:11:34", "throughput": 5304.66, "total_tokens": 969664} +{"current_steps": 965, "total_steps": 42420, "loss": 0.3121, "lr": 0.006817538896746818, "epoch": 0.454974068835455, "percentage": 2.27, "elapsed_time": "0:03:03", "remaining_time": "2:11:29", "throughput": 5303.3, "total_tokens": 974016} +{"current_steps": 970, "total_steps": 42420, "loss": 0.3469, "lr": 0.006852899575671853, "epoch": 0.45733144743045734, "percentage": 2.29, "elapsed_time": "0:03:04", "remaining_time": "2:11:27", "throughput": 5304.1, "total_tokens": 979072} +{"current_steps": 975, "total_steps": 42420, "loss": 0.4002, "lr": 0.006888260254596888, "epoch": 0.4596888260254597, "percentage": 2.3, "elapsed_time": "0:03:05", "remaining_time": "2:11:26", "throughput": 5304.04, "total_tokens": 984032} +{"current_steps": 980, "total_steps": 42420, "loss": 0.4089, "lr": 0.006923620933521923, "epoch": 0.46204620462046203, "percentage": 2.31, "elapsed_time": "0:03:06", "remaining_time": "2:11:22", "throughput": 5303.22, "total_tokens": 988544} +{"current_steps": 985, "total_steps": 42420, "loss": 0.4072, "lr": 0.006958981612446958, "epoch": 0.4644035832154644, "percentage": 2.32, "elapsed_time": "0:03:07", "remaining_time": "2:11:20", "throughput": 5303.19, "total_tokens": 993504} +{"current_steps": 990, "total_steps": 42420, "loss": 0.2991, "lr": 0.006994342291371994, "epoch": 0.4667609618104668, "percentage": 2.33, "elapsed_time": "0:03:08", "remaining_time": "2:11:22", "throughput": 5304.05, "total_tokens": 999104} +{"current_steps": 995, "total_steps": 42420, "loss": 0.3103, "lr": 0.00702970297029703, "epoch": 0.4691183404054691, "percentage": 2.35, "elapsed_time": "0:03:09", "remaining_time": "2:11:25", "throughput": 5305.64, "total_tokens": 1004864} +{"current_steps": 1000, "total_steps": 42420, "loss": 0.3735, "lr": 0.007065063649222065, "epoch": 0.47147571900047147, "percentage": 2.36, "elapsed_time": "0:03:10", "remaining_time": "2:11:21", "throughput": 5305.08, "total_tokens": 1009472} +{"current_steps": 1005, "total_steps": 42420, "loss": 0.3407, "lr": 0.0071004243281471, "epoch": 0.4738330975954738, "percentage": 2.37, "elapsed_time": "0:03:11", "remaining_time": "2:11:14", "throughput": 5303.72, "total_tokens": 1013536} +{"current_steps": 1010, "total_steps": 42420, "loss": 0.359, "lr": 0.007135785007072135, "epoch": 0.47619047619047616, "percentage": 2.38, "elapsed_time": "0:03:11", "remaining_time": "2:11:11", "throughput": 5303.01, "total_tokens": 1018144} +{"current_steps": 1015, "total_steps": 42420, "loss": 0.3816, "lr": 0.007171145685997171, "epoch": 0.47854785478547857, "percentage": 2.39, "elapsed_time": "0:03:12", "remaining_time": "2:11:09", "throughput": 5302.46, "total_tokens": 1022848} +{"current_steps": 1020, "total_steps": 42420, "loss": 0.3518, "lr": 0.007206506364922207, "epoch": 0.4809052333804809, "percentage": 2.4, "elapsed_time": "0:03:13", "remaining_time": "2:11:05", "throughput": 5301.78, "total_tokens": 1027424} +{"current_steps": 1025, "total_steps": 42420, "loss": 0.346, "lr": 0.007241867043847242, "epoch": 0.48326261197548326, "percentage": 2.42, "elapsed_time": "0:03:14", "remaining_time": "2:11:05", "throughput": 5302.52, "total_tokens": 1032768} +{"current_steps": 1030, "total_steps": 42420, "loss": 0.3398, "lr": 0.007277227722772277, "epoch": 0.4856199905704856, "percentage": 2.43, "elapsed_time": "0:03:15", "remaining_time": "2:11:02", "throughput": 5302.17, "total_tokens": 1037440} +{"current_steps": 1035, "total_steps": 42420, "loss": 0.3742, "lr": 0.007312588401697312, "epoch": 0.48797736916548795, "percentage": 2.44, "elapsed_time": "0:03:16", "remaining_time": "2:10:59", "throughput": 5303.05, "total_tokens": 1042400} +{"current_steps": 1040, "total_steps": 42420, "loss": 0.3405, "lr": 0.007347949080622348, "epoch": 0.49033474776049035, "percentage": 2.45, "elapsed_time": "0:03:17", "remaining_time": "2:11:01", "throughput": 5304.12, "total_tokens": 1048032} +{"current_steps": 1045, "total_steps": 42420, "loss": 0.3618, "lr": 0.0073833097595473835, "epoch": 0.4926921263554927, "percentage": 2.46, "elapsed_time": "0:03:18", "remaining_time": "2:11:02", "throughput": 5304.79, "total_tokens": 1053408} +{"current_steps": 1050, "total_steps": 42420, "loss": 0.5627, "lr": 0.007418670438472419, "epoch": 0.49504950495049505, "percentage": 2.48, "elapsed_time": "0:03:19", "remaining_time": "2:11:04", "throughput": 5305.48, "total_tokens": 1059008} +{"current_steps": 1055, "total_steps": 42420, "loss": 0.3393, "lr": 0.007454031117397454, "epoch": 0.4974068835454974, "percentage": 2.49, "elapsed_time": "0:03:20", "remaining_time": "2:11:01", "throughput": 5305.3, "total_tokens": 1063712} +{"current_steps": 1060, "total_steps": 42420, "loss": 0.4149, "lr": 0.007489391796322489, "epoch": 0.49976426214049974, "percentage": 2.5, "elapsed_time": "0:03:21", "remaining_time": "2:10:58", "throughput": 5304.29, "total_tokens": 1068320} +{"current_steps": 1065, "total_steps": 42420, "loss": 0.3387, "lr": 0.007524752475247524, "epoch": 0.5021216407355021, "percentage": 2.51, "elapsed_time": "0:03:22", "remaining_time": "2:10:58", "throughput": 5303.57, "total_tokens": 1073280} +{"current_steps": 1070, "total_steps": 42420, "loss": 0.3277, "lr": 0.00756011315417256, "epoch": 0.5044790193305044, "percentage": 2.52, "elapsed_time": "0:03:23", "remaining_time": "2:10:51", "throughput": 5301.81, "total_tokens": 1077184} +{"current_steps": 1075, "total_steps": 42420, "loss": 0.2783, "lr": 0.007595473833097596, "epoch": 0.5068363979255068, "percentage": 2.53, "elapsed_time": "0:03:24", "remaining_time": "2:10:48", "throughput": 5300.77, "total_tokens": 1081664} +{"current_steps": 1080, "total_steps": 42420, "loss": 0.4828, "lr": 0.00763083451202263, "epoch": 0.5091937765205092, "percentage": 2.55, "elapsed_time": "0:03:24", "remaining_time": "2:10:45", "throughput": 5300.01, "total_tokens": 1086304} +{"current_steps": 1085, "total_steps": 42420, "loss": 0.3005, "lr": 0.007666195190947666, "epoch": 0.5115511551155115, "percentage": 2.56, "elapsed_time": "0:03:25", "remaining_time": "2:10:45", "throughput": 5300.99, "total_tokens": 1091616} +{"current_steps": 1090, "total_steps": 42420, "loss": 0.3623, "lr": 0.0077015558698727005, "epoch": 0.5139085337105139, "percentage": 2.57, "elapsed_time": "0:03:26", "remaining_time": "2:10:39", "throughput": 5299.4, "total_tokens": 1095616} +{"current_steps": 1095, "total_steps": 42420, "loss": 0.3459, "lr": 0.007736916548797736, "epoch": 0.5162659123055162, "percentage": 2.58, "elapsed_time": "0:03:27", "remaining_time": "2:10:43", "throughput": 5300.89, "total_tokens": 1101632} +{"current_steps": 1100, "total_steps": 42420, "loss": 0.2593, "lr": 0.007772277227722773, "epoch": 0.5186232909005186, "percentage": 2.59, "elapsed_time": "0:03:28", "remaining_time": "2:10:39", "throughput": 5300.21, "total_tokens": 1106080} +{"current_steps": 1105, "total_steps": 42420, "loss": 0.4578, "lr": 0.007807637906647807, "epoch": 0.520980669495521, "percentage": 2.6, "elapsed_time": "0:03:29", "remaining_time": "2:10:39", "throughput": 5300.83, "total_tokens": 1111456} +{"current_steps": 1110, "total_steps": 42420, "loss": 0.3998, "lr": 0.007842998585572844, "epoch": 0.5233380480905233, "percentage": 2.62, "elapsed_time": "0:03:30", "remaining_time": "2:10:43", "throughput": 5302.89, "total_tokens": 1117632} +{"current_steps": 1115, "total_steps": 42420, "loss": 0.4111, "lr": 0.007878359264497878, "epoch": 0.5256954266855257, "percentage": 2.63, "elapsed_time": "0:03:31", "remaining_time": "2:10:42", "throughput": 5302.5, "total_tokens": 1122496} +{"current_steps": 1120, "total_steps": 42420, "loss": 0.441, "lr": 0.007913719943422914, "epoch": 0.528052805280528, "percentage": 2.64, "elapsed_time": "0:03:32", "remaining_time": "2:10:34", "throughput": 5300.52, "total_tokens": 1126176} +{"current_steps": 1125, "total_steps": 42420, "loss": 0.3241, "lr": 0.00794908062234795, "epoch": 0.5304101838755304, "percentage": 2.65, "elapsed_time": "0:03:33", "remaining_time": "2:10:42", "throughput": 5303.09, "total_tokens": 1133024} +{"current_steps": 1130, "total_steps": 42420, "loss": 0.3042, "lr": 0.007984441301272984, "epoch": 0.5327675624705328, "percentage": 2.66, "elapsed_time": "0:03:34", "remaining_time": "2:10:41", "throughput": 5303.34, "total_tokens": 1138112} +{"current_steps": 1135, "total_steps": 42420, "loss": 0.3674, "lr": 0.00801980198019802, "epoch": 0.5351249410655351, "percentage": 2.68, "elapsed_time": "0:03:35", "remaining_time": "2:10:45", "throughput": 5304.18, "total_tokens": 1144064} +{"current_steps": 1140, "total_steps": 42420, "loss": 0.4061, "lr": 0.008055162659123054, "epoch": 0.5374823196605375, "percentage": 2.69, "elapsed_time": "0:03:36", "remaining_time": "2:10:43", "throughput": 5304.24, "total_tokens": 1148992} +{"current_steps": 1145, "total_steps": 42420, "loss": 0.3807, "lr": 0.00809052333804809, "epoch": 0.5398396982555398, "percentage": 2.7, "elapsed_time": "0:03:37", "remaining_time": "2:10:45", "throughput": 5304.96, "total_tokens": 1154592} +{"current_steps": 1150, "total_steps": 42420, "loss": 0.34, "lr": 0.008125884016973126, "epoch": 0.5421970768505422, "percentage": 2.71, "elapsed_time": "0:03:38", "remaining_time": "2:10:45", "throughput": 5305.88, "total_tokens": 1159936} +{"current_steps": 1155, "total_steps": 42420, "loss": 0.4135, "lr": 0.00816124469589816, "epoch": 0.5445544554455446, "percentage": 2.72, "elapsed_time": "0:03:39", "remaining_time": "2:10:41", "throughput": 5305.55, "total_tokens": 1164448} +{"current_steps": 1160, "total_steps": 42420, "loss": 0.3674, "lr": 0.008196605374823196, "epoch": 0.5469118340405469, "percentage": 2.73, "elapsed_time": "0:03:40", "remaining_time": "2:10:35", "throughput": 5304.56, "total_tokens": 1168544} +{"current_steps": 1165, "total_steps": 42420, "loss": 0.3834, "lr": 0.008231966053748232, "epoch": 0.5492692126355493, "percentage": 2.75, "elapsed_time": "0:03:41", "remaining_time": "2:10:31", "throughput": 5303.9, "total_tokens": 1172960} +{"current_steps": 1170, "total_steps": 42420, "loss": 0.32, "lr": 0.008267326732673268, "epoch": 0.5516265912305516, "percentage": 2.76, "elapsed_time": "0:03:42", "remaining_time": "2:10:30", "throughput": 5304.33, "total_tokens": 1178144} +{"current_steps": 1175, "total_steps": 42420, "loss": 0.2584, "lr": 0.008302687411598304, "epoch": 0.553983969825554, "percentage": 2.77, "elapsed_time": "0:03:43", "remaining_time": "2:10:35", "throughput": 5306.22, "total_tokens": 1184448} +{"current_steps": 1180, "total_steps": 42420, "loss": 0.4046, "lr": 0.008338048090523338, "epoch": 0.5563413484205564, "percentage": 2.78, "elapsed_time": "0:03:44", "remaining_time": "2:10:34", "throughput": 5306.07, "total_tokens": 1189472} +{"current_steps": 1185, "total_steps": 42420, "loss": 0.3414, "lr": 0.008373408769448374, "epoch": 0.5586987270155587, "percentage": 2.79, "elapsed_time": "0:03:45", "remaining_time": "2:10:35", "throughput": 5307.26, "total_tokens": 1195072} +{"current_steps": 1190, "total_steps": 42420, "loss": 0.3421, "lr": 0.008408769448373408, "epoch": 0.5610561056105611, "percentage": 2.81, "elapsed_time": "0:03:45", "remaining_time": "2:10:28", "throughput": 5305.1, "total_tokens": 1198656} +{"current_steps": 1195, "total_steps": 42420, "loss": 0.4234, "lr": 0.008444130127298444, "epoch": 0.5634134842055634, "percentage": 2.82, "elapsed_time": "0:03:46", "remaining_time": "2:10:26", "throughput": 5305.02, "total_tokens": 1203616} +{"current_steps": 1200, "total_steps": 42420, "loss": 0.3065, "lr": 0.00847949080622348, "epoch": 0.5657708628005658, "percentage": 2.83, "elapsed_time": "0:03:47", "remaining_time": "2:10:24", "throughput": 5304.45, "total_tokens": 1208224} +{"current_steps": 1205, "total_steps": 42420, "loss": 0.6195, "lr": 0.008514851485148514, "epoch": 0.5681282413955682, "percentage": 2.84, "elapsed_time": "0:03:48", "remaining_time": "2:10:20", "throughput": 5303.73, "total_tokens": 1212608} +{"current_steps": 1210, "total_steps": 42420, "loss": 0.3542, "lr": 0.00855021216407355, "epoch": 0.5704856199905705, "percentage": 2.85, "elapsed_time": "0:03:49", "remaining_time": "2:10:22", "throughput": 5304.72, "total_tokens": 1218336} +{"current_steps": 1215, "total_steps": 42420, "loss": 0.3279, "lr": 0.008585572842998586, "epoch": 0.5728429985855729, "percentage": 2.86, "elapsed_time": "0:03:50", "remaining_time": "2:10:19", "throughput": 5305.21, "total_tokens": 1223296} +{"current_steps": 1220, "total_steps": 42420, "loss": 0.3457, "lr": 0.008620933521923621, "epoch": 0.5752003771805752, "percentage": 2.88, "elapsed_time": "0:03:51", "remaining_time": "2:10:19", "throughput": 5305.55, "total_tokens": 1228448} +{"current_steps": 1225, "total_steps": 42420, "loss": 0.3115, "lr": 0.008656294200848657, "epoch": 0.5775577557755776, "percentage": 2.89, "elapsed_time": "0:03:52", "remaining_time": "2:10:16", "throughput": 5304.85, "total_tokens": 1233024} +{"current_steps": 1230, "total_steps": 42420, "loss": 0.341, "lr": 0.008691654879773691, "epoch": 0.57991513437058, "percentage": 2.9, "elapsed_time": "0:03:53", "remaining_time": "2:10:15", "throughput": 5304.99, "total_tokens": 1238080} +{"current_steps": 1235, "total_steps": 42420, "loss": 0.1672, "lr": 0.008727015558698727, "epoch": 0.5822725129655822, "percentage": 2.91, "elapsed_time": "0:03:54", "remaining_time": "2:10:14", "throughput": 5305.44, "total_tokens": 1243296} +{"current_steps": 1240, "total_steps": 42420, "loss": 0.5275, "lr": 0.008762376237623761, "epoch": 0.5846298915605846, "percentage": 2.92, "elapsed_time": "0:03:55", "remaining_time": "2:10:12", "throughput": 5305.38, "total_tokens": 1248128} +{"current_steps": 1245, "total_steps": 42420, "loss": 0.3898, "lr": 0.008797736916548797, "epoch": 0.5869872701555869, "percentage": 2.93, "elapsed_time": "0:03:56", "remaining_time": "2:10:10", "throughput": 5305.19, "total_tokens": 1252864} +{"current_steps": 1250, "total_steps": 42420, "loss": 0.367, "lr": 0.008833097595473833, "epoch": 0.5893446487505893, "percentage": 2.95, "elapsed_time": "0:03:57", "remaining_time": "2:10:09", "throughput": 5305.25, "total_tokens": 1257856} +{"current_steps": 1255, "total_steps": 42420, "loss": 0.3444, "lr": 0.008868458274398867, "epoch": 0.5917020273455917, "percentage": 2.96, "elapsed_time": "0:03:57", "remaining_time": "2:10:04", "throughput": 5304.73, "total_tokens": 1262240} +{"current_steps": 1260, "total_steps": 42420, "loss": 0.2911, "lr": 0.008903818953323903, "epoch": 0.594059405940594, "percentage": 2.97, "elapsed_time": "0:03:58", "remaining_time": "2:10:03", "throughput": 5305.32, "total_tokens": 1267392} +{"current_steps": 1265, "total_steps": 42420, "loss": 0.3374, "lr": 0.008939179632248937, "epoch": 0.5964167845355964, "percentage": 2.98, "elapsed_time": "0:03:59", "remaining_time": "2:10:01", "throughput": 5304.82, "total_tokens": 1272064} +{"current_steps": 1270, "total_steps": 42420, "loss": 0.3674, "lr": 0.008974540311173975, "epoch": 0.5987741631305987, "percentage": 2.99, "elapsed_time": "0:04:00", "remaining_time": "2:09:55", "throughput": 5303.31, "total_tokens": 1275968} +{"current_steps": 1275, "total_steps": 42420, "loss": 0.3303, "lr": 0.009009900990099011, "epoch": 0.6011315417256011, "percentage": 3.01, "elapsed_time": "0:04:01", "remaining_time": "2:09:50", "throughput": 5302.27, "total_tokens": 1280096} +{"current_steps": 1280, "total_steps": 42420, "loss": 0.3611, "lr": 0.009045261669024045, "epoch": 0.6034889203206035, "percentage": 3.02, "elapsed_time": "0:04:02", "remaining_time": "2:09:48", "throughput": 5301.84, "total_tokens": 1284704} +{"current_steps": 1285, "total_steps": 42420, "loss": 0.3319, "lr": 0.009080622347949081, "epoch": 0.6058462989156058, "percentage": 3.03, "elapsed_time": "0:04:03", "remaining_time": "2:09:46", "throughput": 5300.9, "total_tokens": 1289312} +{"current_steps": 1290, "total_steps": 42420, "loss": 0.3963, "lr": 0.009115983026874115, "epoch": 0.6082036775106082, "percentage": 3.04, "elapsed_time": "0:04:04", "remaining_time": "2:09:41", "throughput": 5299.8, "total_tokens": 1293440} +{"current_steps": 1295, "total_steps": 42420, "loss": 0.3588, "lr": 0.009151343705799151, "epoch": 0.6105610561056105, "percentage": 3.05, "elapsed_time": "0:04:04", "remaining_time": "2:09:35", "throughput": 5298.79, "total_tokens": 1297408} +{"current_steps": 1300, "total_steps": 42420, "loss": 0.352, "lr": 0.009186704384724187, "epoch": 0.6129184347006129, "percentage": 3.06, "elapsed_time": "0:04:05", "remaining_time": "2:09:34", "throughput": 5298.39, "total_tokens": 1302304} +{"current_steps": 1305, "total_steps": 42420, "loss": 0.3597, "lr": 0.009222065063649221, "epoch": 0.6152758132956153, "percentage": 3.08, "elapsed_time": "0:04:06", "remaining_time": "2:09:30", "throughput": 5296.96, "total_tokens": 1306368} +{"current_steps": 1310, "total_steps": 42420, "loss": 0.3799, "lr": 0.009257425742574257, "epoch": 0.6176331918906176, "percentage": 3.09, "elapsed_time": "0:04:07", "remaining_time": "2:09:30", "throughput": 5297.23, "total_tokens": 1311712} +{"current_steps": 1315, "total_steps": 42420, "loss": 0.834, "lr": 0.009292786421499291, "epoch": 0.61999057048562, "percentage": 3.1, "elapsed_time": "0:04:09", "remaining_time": "2:09:43", "throughput": 5301.04, "total_tokens": 1320000} +{"current_steps": 1320, "total_steps": 42420, "loss": 0.3767, "lr": 0.009328147100424329, "epoch": 0.6223479490806223, "percentage": 3.11, "elapsed_time": "0:04:09", "remaining_time": "2:09:40", "throughput": 5300.41, "total_tokens": 1324448} +{"current_steps": 1325, "total_steps": 42420, "loss": 0.3516, "lr": 0.009363507779349365, "epoch": 0.6247053276756247, "percentage": 3.12, "elapsed_time": "0:04:10", "remaining_time": "2:09:37", "throughput": 5300.26, "total_tokens": 1329088} +{"current_steps": 1330, "total_steps": 42420, "loss": 0.3388, "lr": 0.009398868458274399, "epoch": 0.6270627062706271, "percentage": 3.14, "elapsed_time": "0:04:11", "remaining_time": "2:09:35", "throughput": 5300.22, "total_tokens": 1333920} +{"current_steps": 1335, "total_steps": 42420, "loss": 0.339, "lr": 0.009434229137199435, "epoch": 0.6294200848656294, "percentage": 3.15, "elapsed_time": "0:04:12", "remaining_time": "2:09:33", "throughput": 5300.2, "total_tokens": 1338848} +{"current_steps": 1340, "total_steps": 42420, "loss": 0.3538, "lr": 0.009469589816124469, "epoch": 0.6317774634606318, "percentage": 3.16, "elapsed_time": "0:04:13", "remaining_time": "2:09:36", "throughput": 5301.58, "total_tokens": 1344864} +{"current_steps": 1345, "total_steps": 42420, "loss": 1.7786, "lr": 0.009504950495049505, "epoch": 0.6341348420556341, "percentage": 3.17, "elapsed_time": "0:04:14", "remaining_time": "2:09:36", "throughput": 5302.02, "total_tokens": 1350144} +{"current_steps": 1350, "total_steps": 42420, "loss": 5.8852, "lr": 0.00954031117397454, "epoch": 0.6364922206506365, "percentage": 3.18, "elapsed_time": "0:04:15", "remaining_time": "2:09:33", "throughput": 5301.46, "total_tokens": 1354592} +{"current_steps": 1355, "total_steps": 42420, "loss": 0.5484, "lr": 0.009575671852899575, "epoch": 0.6388495992456389, "percentage": 3.19, "elapsed_time": "0:04:16", "remaining_time": "2:09:28", "throughput": 5299.5, "total_tokens": 1358368} +{"current_steps": 1360, "total_steps": 42420, "loss": 0.4071, "lr": 0.00961103253182461, "epoch": 0.6412069778406412, "percentage": 3.21, "elapsed_time": "0:04:17", "remaining_time": "2:09:24", "throughput": 5299.02, "total_tokens": 1362848} +{"current_steps": 1365, "total_steps": 42420, "loss": 0.3765, "lr": 0.009646393210749645, "epoch": 0.6435643564356436, "percentage": 3.22, "elapsed_time": "0:04:18", "remaining_time": "2:09:22", "throughput": 5298.53, "total_tokens": 1367456} +{"current_steps": 1370, "total_steps": 42420, "loss": 0.375, "lr": 0.00968175388967468, "epoch": 0.6459217350306459, "percentage": 3.23, "elapsed_time": "0:04:19", "remaining_time": "2:09:27", "throughput": 5299.99, "total_tokens": 1373888} +{"current_steps": 1375, "total_steps": 42420, "loss": 0.3798, "lr": 0.009717114568599718, "epoch": 0.6482791136256483, "percentage": 3.24, "elapsed_time": "0:04:20", "remaining_time": "2:09:26", "throughput": 5299.9, "total_tokens": 1378944} +{"current_steps": 1380, "total_steps": 42420, "loss": 0.3699, "lr": 0.009752475247524752, "epoch": 0.6506364922206507, "percentage": 3.25, "elapsed_time": "0:04:21", "remaining_time": "2:09:23", "throughput": 5299.26, "total_tokens": 1383328} +{"current_steps": 1385, "total_steps": 42420, "loss": 0.3967, "lr": 0.009787835926449788, "epoch": 0.652993870815653, "percentage": 3.26, "elapsed_time": "0:04:22", "remaining_time": "2:09:24", "throughput": 5300.14, "total_tokens": 1388928} +{"current_steps": 1390, "total_steps": 42420, "loss": 0.2867, "lr": 0.009823196605374823, "epoch": 0.6553512494106554, "percentage": 3.28, "elapsed_time": "0:04:23", "remaining_time": "2:09:29", "throughput": 5302.36, "total_tokens": 1395712} +{"current_steps": 1395, "total_steps": 42420, "loss": 0.511, "lr": 0.009858557284299858, "epoch": 0.6577086280056577, "percentage": 3.29, "elapsed_time": "0:04:24", "remaining_time": "2:09:25", "throughput": 5301.49, "total_tokens": 1399936} +{"current_steps": 1400, "total_steps": 42420, "loss": 0.3398, "lr": 0.009893917963224894, "epoch": 0.6600660066006601, "percentage": 3.3, "elapsed_time": "0:04:25", "remaining_time": "2:09:24", "throughput": 5301.81, "total_tokens": 1404992} +{"current_steps": 1405, "total_steps": 42420, "loss": 0.6691, "lr": 0.009929278642149928, "epoch": 0.6624233851956625, "percentage": 3.31, "elapsed_time": "0:04:25", "remaining_time": "2:09:21", "throughput": 5301.52, "total_tokens": 1409568} +{"current_steps": 1410, "total_steps": 42420, "loss": 0.3426, "lr": 0.009964639321074964, "epoch": 0.6647807637906648, "percentage": 3.32, "elapsed_time": "0:04:26", "remaining_time": "2:09:22", "throughput": 5302.37, "total_tokens": 1415072} +{"current_steps": 1415, "total_steps": 42420, "loss": 0.373, "lr": 0.009999999999999998, "epoch": 0.6671381423856672, "percentage": 3.34, "elapsed_time": "0:04:27", "remaining_time": "2:09:18", "throughput": 5301.89, "total_tokens": 1419552} +{"current_steps": 1420, "total_steps": 42420, "loss": 0.3751, "lr": 0.010035360678925034, "epoch": 0.6694955209806694, "percentage": 3.35, "elapsed_time": "0:04:28", "remaining_time": "2:09:17", "throughput": 5302.27, "total_tokens": 1424544} +{"current_steps": 1425, "total_steps": 42420, "loss": 0.3569, "lr": 0.010070721357850072, "epoch": 0.6718528995756718, "percentage": 3.36, "elapsed_time": "0:04:29", "remaining_time": "2:09:15", "throughput": 5302.35, "total_tokens": 1429504} +{"current_steps": 1430, "total_steps": 42420, "loss": 0.3635, "lr": 0.010106082036775106, "epoch": 0.6742102781706742, "percentage": 3.37, "elapsed_time": "0:04:30", "remaining_time": "2:09:14", "throughput": 5302.12, "total_tokens": 1434336} +{"current_steps": 1435, "total_steps": 42420, "loss": 0.3291, "lr": 0.010141442715700142, "epoch": 0.6765676567656765, "percentage": 3.38, "elapsed_time": "0:04:31", "remaining_time": "2:09:10", "throughput": 5301.19, "total_tokens": 1438496} +{"current_steps": 1440, "total_steps": 42420, "loss": 0.2913, "lr": 0.010176803394625176, "epoch": 0.6789250353606789, "percentage": 3.39, "elapsed_time": "0:04:32", "remaining_time": "2:09:10", "throughput": 5302.02, "total_tokens": 1444032} +{"current_steps": 1445, "total_steps": 42420, "loss": 0.294, "lr": 0.010212164073550212, "epoch": 0.6812824139556812, "percentage": 3.41, "elapsed_time": "0:04:33", "remaining_time": "2:09:08", "throughput": 5301.98, "total_tokens": 1448864} +{"current_steps": 1450, "total_steps": 42420, "loss": 0.3141, "lr": 0.010247524752475248, "epoch": 0.6836397925506836, "percentage": 3.42, "elapsed_time": "0:04:34", "remaining_time": "2:09:05", "throughput": 5301.58, "total_tokens": 1453376} +{"current_steps": 1455, "total_steps": 42420, "loss": 0.3651, "lr": 0.010282885431400282, "epoch": 0.685997171145686, "percentage": 3.43, "elapsed_time": "0:04:34", "remaining_time": "2:09:01", "throughput": 5300.47, "total_tokens": 1457376} +{"current_steps": 1460, "total_steps": 42420, "loss": 0.3663, "lr": 0.010318246110325318, "epoch": 0.6883545497406883, "percentage": 3.44, "elapsed_time": "0:04:35", "remaining_time": "2:09:01", "throughput": 5301.44, "total_tokens": 1462848} +{"current_steps": 1465, "total_steps": 42420, "loss": 0.3368, "lr": 0.010353606789250352, "epoch": 0.6907119283356907, "percentage": 3.45, "elapsed_time": "0:04:36", "remaining_time": "2:09:00", "throughput": 5301.54, "total_tokens": 1467872} +{"current_steps": 1470, "total_steps": 42420, "loss": 0.3738, "lr": 0.010388967468175388, "epoch": 0.693069306930693, "percentage": 3.47, "elapsed_time": "0:04:37", "remaining_time": "2:08:56", "throughput": 5300.49, "total_tokens": 1472096} +{"current_steps": 1475, "total_steps": 42420, "loss": 0.3443, "lr": 0.010424328147100424, "epoch": 0.6954266855256954, "percentage": 3.48, "elapsed_time": "0:04:38", "remaining_time": "2:08:57", "throughput": 5301.2, "total_tokens": 1477632} +{"current_steps": 1480, "total_steps": 42420, "loss": 0.3158, "lr": 0.01045968882602546, "epoch": 0.6977840641206978, "percentage": 3.49, "elapsed_time": "0:04:39", "remaining_time": "2:08:57", "throughput": 5301.79, "total_tokens": 1482944} +{"current_steps": 1485, "total_steps": 42420, "loss": 0.3743, "lr": 0.010495049504950496, "epoch": 0.7001414427157001, "percentage": 3.5, "elapsed_time": "0:04:40", "remaining_time": "2:08:53", "throughput": 5300.5, "total_tokens": 1486976} +{"current_steps": 1490, "total_steps": 42420, "loss": 0.314, "lr": 0.01053041018387553, "epoch": 0.7024988213107025, "percentage": 3.51, "elapsed_time": "0:04:41", "remaining_time": "2:08:48", "throughput": 5299.84, "total_tokens": 1491168} +{"current_steps": 1495, "total_steps": 42420, "loss": 0.3445, "lr": 0.010565770862800566, "epoch": 0.7048561999057048, "percentage": 3.52, "elapsed_time": "0:04:42", "remaining_time": "2:08:47", "throughput": 5299.62, "total_tokens": 1496000} +{"current_steps": 1500, "total_steps": 42420, "loss": 0.3187, "lr": 0.010601131541725602, "epoch": 0.7072135785007072, "percentage": 3.54, "elapsed_time": "0:04:43", "remaining_time": "2:08:43", "throughput": 5298.39, "total_tokens": 1500064} +{"current_steps": 1505, "total_steps": 42420, "loss": 0.355, "lr": 0.010636492220650636, "epoch": 0.7095709570957096, "percentage": 3.55, "elapsed_time": "0:04:44", "remaining_time": "2:08:42", "throughput": 5298.42, "total_tokens": 1505120} +{"current_steps": 1510, "total_steps": 42420, "loss": 0.3845, "lr": 0.010671852899575672, "epoch": 0.7119283356907119, "percentage": 3.56, "elapsed_time": "0:04:45", "remaining_time": "2:08:41", "throughput": 5298.77, "total_tokens": 1510240} +{"current_steps": 1515, "total_steps": 42420, "loss": 0.3642, "lr": 0.010707213578500706, "epoch": 0.7142857142857143, "percentage": 3.57, "elapsed_time": "0:04:46", "remaining_time": "2:08:42", "throughput": 5299.5, "total_tokens": 1515712} +{"current_steps": 1520, "total_steps": 42420, "loss": 0.2998, "lr": 0.010742574257425742, "epoch": 0.7166430928807166, "percentage": 3.58, "elapsed_time": "0:04:46", "remaining_time": "2:08:40", "throughput": 5299.25, "total_tokens": 1520512} +{"current_steps": 1525, "total_steps": 42420, "loss": 0.3233, "lr": 0.010777934936350778, "epoch": 0.719000471475719, "percentage": 3.6, "elapsed_time": "0:04:47", "remaining_time": "2:08:35", "throughput": 5297.74, "total_tokens": 1524288} +{"current_steps": 1530, "total_steps": 42420, "loss": 0.3478, "lr": 0.010813295615275813, "epoch": 0.7213578500707214, "percentage": 3.61, "elapsed_time": "0:04:48", "remaining_time": "2:08:33", "throughput": 5297.33, "total_tokens": 1528896} +{"current_steps": 1535, "total_steps": 42420, "loss": 0.3706, "lr": 0.01084865629420085, "epoch": 0.7237152286657237, "percentage": 3.62, "elapsed_time": "0:04:49", "remaining_time": "2:08:34", "throughput": 5298.59, "total_tokens": 1534656} +{"current_steps": 1540, "total_steps": 42420, "loss": 0.3753, "lr": 0.010884016973125884, "epoch": 0.7260726072607261, "percentage": 3.63, "elapsed_time": "0:04:50", "remaining_time": "2:08:30", "throughput": 5297.73, "total_tokens": 1538848} +{"current_steps": 1545, "total_steps": 42420, "loss": 0.2935, "lr": 0.01091937765205092, "epoch": 0.7284299858557284, "percentage": 3.64, "elapsed_time": "0:04:51", "remaining_time": "2:08:29", "throughput": 5297.52, "total_tokens": 1543712} +{"current_steps": 1550, "total_steps": 42420, "loss": 0.4379, "lr": 0.010954738330975955, "epoch": 0.7307873644507308, "percentage": 3.65, "elapsed_time": "0:04:52", "remaining_time": "2:08:30", "throughput": 5297.81, "total_tokens": 1549152} +{"current_steps": 1555, "total_steps": 42420, "loss": 0.3556, "lr": 0.01099009900990099, "epoch": 0.7331447430457332, "percentage": 3.67, "elapsed_time": "0:04:53", "remaining_time": "2:08:29", "throughput": 5297.72, "total_tokens": 1554080} +{"current_steps": 1560, "total_steps": 42420, "loss": 0.3887, "lr": 0.011025459688826025, "epoch": 0.7355021216407355, "percentage": 3.68, "elapsed_time": "0:04:54", "remaining_time": "2:08:28", "throughput": 5297.85, "total_tokens": 1559104} +{"current_steps": 1565, "total_steps": 42420, "loss": 0.345, "lr": 0.01106082036775106, "epoch": 0.7378595002357379, "percentage": 3.69, "elapsed_time": "0:04:55", "remaining_time": "2:08:30", "throughput": 5299.1, "total_tokens": 1565152} +{"current_steps": 1570, "total_steps": 42420, "loss": 0.2978, "lr": 0.011096181046676095, "epoch": 0.7402168788307402, "percentage": 3.7, "elapsed_time": "0:04:56", "remaining_time": "2:08:31", "throughput": 5299.55, "total_tokens": 1570688} +{"current_steps": 1575, "total_steps": 42420, "loss": 0.3154, "lr": 0.011131541725601131, "epoch": 0.7425742574257426, "percentage": 3.71, "elapsed_time": "0:04:57", "remaining_time": "2:08:32", "throughput": 5300.19, "total_tokens": 1576256} +{"current_steps": 1580, "total_steps": 42420, "loss": 0.2121, "lr": 0.011166902404526165, "epoch": 0.744931636020745, "percentage": 3.72, "elapsed_time": "0:04:58", "remaining_time": "2:08:30", "throughput": 5300.18, "total_tokens": 1581056} +{"current_steps": 1585, "total_steps": 42420, "loss": 0.4194, "lr": 0.011202263083451203, "epoch": 0.7472890146157473, "percentage": 3.74, "elapsed_time": "0:04:59", "remaining_time": "2:08:31", "throughput": 5300.53, "total_tokens": 1586464} +{"current_steps": 1590, "total_steps": 42420, "loss": 0.3507, "lr": 0.011237623762376237, "epoch": 0.7496463932107497, "percentage": 3.75, "elapsed_time": "0:05:00", "remaining_time": "2:08:29", "throughput": 5300.49, "total_tokens": 1591296} +{"current_steps": 1595, "total_steps": 42420, "loss": 0.4032, "lr": 0.011272984441301273, "epoch": 0.752003771805752, "percentage": 3.76, "elapsed_time": "0:05:01", "remaining_time": "2:08:26", "throughput": 5299.34, "total_tokens": 1595488} +{"current_steps": 1600, "total_steps": 42420, "loss": 0.3521, "lr": 0.011308345120226309, "epoch": 0.7543611504007544, "percentage": 3.77, "elapsed_time": "0:05:02", "remaining_time": "2:08:27", "throughput": 5300.4, "total_tokens": 1601312} +{"current_steps": 1605, "total_steps": 42420, "loss": 0.2933, "lr": 0.011343705799151343, "epoch": 0.7567185289957568, "percentage": 3.78, "elapsed_time": "0:05:03", "remaining_time": "2:08:26", "throughput": 5300.48, "total_tokens": 1606336} +{"current_steps": 1610, "total_steps": 42420, "loss": 0.3539, "lr": 0.011379066478076379, "epoch": 0.759075907590759, "percentage": 3.8, "elapsed_time": "0:05:03", "remaining_time": "2:08:24", "throughput": 5300.13, "total_tokens": 1611008} +{"current_steps": 1615, "total_steps": 42420, "loss": 0.3467, "lr": 0.011414427157001413, "epoch": 0.7614332861857614, "percentage": 3.81, "elapsed_time": "0:05:04", "remaining_time": "2:08:21", "throughput": 5299.42, "total_tokens": 1615328} +{"current_steps": 1620, "total_steps": 42420, "loss": 0.3254, "lr": 0.011449787835926449, "epoch": 0.7637906647807637, "percentage": 3.82, "elapsed_time": "0:05:05", "remaining_time": "2:08:20", "throughput": 5299.46, "total_tokens": 1620320} +{"current_steps": 1625, "total_steps": 42420, "loss": 0.2831, "lr": 0.011485148514851485, "epoch": 0.7661480433757661, "percentage": 3.83, "elapsed_time": "0:05:06", "remaining_time": "2:08:19", "throughput": 5299.56, "total_tokens": 1625344} +{"current_steps": 1630, "total_steps": 42420, "loss": 0.3296, "lr": 0.011520509193776519, "epoch": 0.7685054219707685, "percentage": 3.84, "elapsed_time": "0:05:07", "remaining_time": "2:08:19", "throughput": 5300.05, "total_tokens": 1630624} +{"current_steps": 1635, "total_steps": 42420, "loss": 0.3187, "lr": 0.011555869872701557, "epoch": 0.7708628005657708, "percentage": 3.85, "elapsed_time": "0:05:08", "remaining_time": "2:08:16", "throughput": 5299.53, "total_tokens": 1635136} +{"current_steps": 1640, "total_steps": 42420, "loss": 0.3409, "lr": 0.011591230551626591, "epoch": 0.7732201791607732, "percentage": 3.87, "elapsed_time": "0:05:09", "remaining_time": "2:08:17", "throughput": 5299.97, "total_tokens": 1640640} +{"current_steps": 1645, "total_steps": 42420, "loss": 0.3357, "lr": 0.011626591230551627, "epoch": 0.7755775577557755, "percentage": 3.88, "elapsed_time": "0:05:10", "remaining_time": "2:08:21", "throughput": 5301.02, "total_tokens": 1647040} +{"current_steps": 1650, "total_steps": 42420, "loss": 0.3002, "lr": 0.011661951909476663, "epoch": 0.7779349363507779, "percentage": 3.89, "elapsed_time": "0:05:11", "remaining_time": "2:08:19", "throughput": 5300.59, "total_tokens": 1651712} +{"current_steps": 1655, "total_steps": 42420, "loss": 0.337, "lr": 0.011697312588401697, "epoch": 0.7802923149457803, "percentage": 3.9, "elapsed_time": "0:05:12", "remaining_time": "2:08:21", "throughput": 5301.4, "total_tokens": 1657536} +{"current_steps": 1660, "total_steps": 42420, "loss": 1.3826, "lr": 0.011732673267326733, "epoch": 0.7826496935407826, "percentage": 3.91, "elapsed_time": "0:05:13", "remaining_time": "2:08:23", "throughput": 5302.4, "total_tokens": 1663616} +{"current_steps": 1665, "total_steps": 42420, "loss": 4.3289, "lr": 0.011768033946251767, "epoch": 0.785007072135785, "percentage": 3.93, "elapsed_time": "0:05:14", "remaining_time": "2:08:25", "throughput": 5303.4, "total_tokens": 1669600} +{"current_steps": 1670, "total_steps": 42420, "loss": 1.137, "lr": 0.011803394625176803, "epoch": 0.7873644507307873, "percentage": 3.94, "elapsed_time": "0:05:15", "remaining_time": "2:08:24", "throughput": 5303.48, "total_tokens": 1674560} +{"current_steps": 1675, "total_steps": 42420, "loss": 0.361, "lr": 0.011838755304101839, "epoch": 0.7897218293257897, "percentage": 3.95, "elapsed_time": "0:05:16", "remaining_time": "2:08:23", "throughput": 5303.78, "total_tokens": 1679616} +{"current_steps": 1680, "total_steps": 42420, "loss": 0.3624, "lr": 0.011874115983026873, "epoch": 0.7920792079207921, "percentage": 3.96, "elapsed_time": "0:05:17", "remaining_time": "2:08:20", "throughput": 5303.37, "total_tokens": 1684160} +{"current_steps": 1685, "total_steps": 42420, "loss": 0.3409, "lr": 0.011909476661951909, "epoch": 0.7944365865157944, "percentage": 3.97, "elapsed_time": "0:05:18", "remaining_time": "2:08:20", "throughput": 5303.57, "total_tokens": 1689280} +{"current_steps": 1690, "total_steps": 42420, "loss": 0.3328, "lr": 0.011944837340876945, "epoch": 0.7967939651107968, "percentage": 3.98, "elapsed_time": "0:05:19", "remaining_time": "2:08:19", "throughput": 5303.59, "total_tokens": 1694368} +{"current_steps": 1695, "total_steps": 42420, "loss": 0.3726, "lr": 0.01198019801980198, "epoch": 0.7991513437057991, "percentage": 4.0, "elapsed_time": "0:05:20", "remaining_time": "2:08:17", "throughput": 5303.43, "total_tokens": 1699072} +{"current_steps": 1700, "total_steps": 42420, "loss": 0.3329, "lr": 0.012015558698727016, "epoch": 0.8015087223008015, "percentage": 4.01, "elapsed_time": "0:05:21", "remaining_time": "2:08:17", "throughput": 5303.67, "total_tokens": 1704352} +{"current_steps": 1705, "total_steps": 42420, "loss": 0.3376, "lr": 0.01205091937765205, "epoch": 0.8038661008958039, "percentage": 4.02, "elapsed_time": "0:05:22", "remaining_time": "2:08:15", "throughput": 5303.44, "total_tokens": 1709088} +{"current_steps": 1710, "total_steps": 42420, "loss": 0.3324, "lr": 0.012086280056577086, "epoch": 0.8062234794908062, "percentage": 4.03, "elapsed_time": "0:05:23", "remaining_time": "2:08:13", "throughput": 5302.91, "total_tokens": 1713600} +{"current_steps": 1715, "total_steps": 42420, "loss": 0.3139, "lr": 0.01212164073550212, "epoch": 0.8085808580858086, "percentage": 4.04, "elapsed_time": "0:05:24", "remaining_time": "2:08:16", "throughput": 5304.65, "total_tokens": 1720224} +{"current_steps": 1720, "total_steps": 42420, "loss": 0.4062, "lr": 0.012157001414427156, "epoch": 0.8109382366808109, "percentage": 4.05, "elapsed_time": "0:05:25", "remaining_time": "2:08:15", "throughput": 5304.75, "total_tokens": 1725280} +{"current_steps": 1725, "total_steps": 42420, "loss": 0.4286, "lr": 0.012192362093352192, "epoch": 0.8132956152758133, "percentage": 4.07, "elapsed_time": "0:05:26", "remaining_time": "2:08:20", "throughput": 5306.1, "total_tokens": 1731904} +{"current_steps": 1730, "total_steps": 42420, "loss": 0.3458, "lr": 0.012227722772277226, "epoch": 0.8156529938708157, "percentage": 4.08, "elapsed_time": "0:05:27", "remaining_time": "2:08:19", "throughput": 5306.4, "total_tokens": 1737056} +{"current_steps": 1735, "total_steps": 42420, "loss": 0.4322, "lr": 0.012263083451202262, "epoch": 0.818010372465818, "percentage": 4.09, "elapsed_time": "0:05:28", "remaining_time": "2:08:16", "throughput": 5306.14, "total_tokens": 1741568} +{"current_steps": 1740, "total_steps": 42420, "loss": 0.4529, "lr": 0.012298444130127298, "epoch": 0.8203677510608204, "percentage": 4.1, "elapsed_time": "0:05:29", "remaining_time": "2:08:13", "throughput": 5305.87, "total_tokens": 1745984} +{"current_steps": 1745, "total_steps": 42420, "loss": 0.3553, "lr": 0.012333804809052334, "epoch": 0.8227251296558227, "percentage": 4.11, "elapsed_time": "0:05:29", "remaining_time": "2:08:11", "throughput": 5305.51, "total_tokens": 1750688} +{"current_steps": 1750, "total_steps": 42420, "loss": 0.3464, "lr": 0.01236916548797737, "epoch": 0.8250825082508251, "percentage": 4.13, "elapsed_time": "0:05:30", "remaining_time": "2:08:10", "throughput": 5305.52, "total_tokens": 1755648} +{"current_steps": 1755, "total_steps": 42420, "loss": 0.359, "lr": 0.012404526166902404, "epoch": 0.8274398868458275, "percentage": 4.14, "elapsed_time": "0:05:31", "remaining_time": "2:08:11", "throughput": 5306.32, "total_tokens": 1761408} +{"current_steps": 1760, "total_steps": 42420, "loss": 0.3394, "lr": 0.01243988684582744, "epoch": 0.8297972654408298, "percentage": 4.15, "elapsed_time": "0:05:32", "remaining_time": "2:08:09", "throughput": 5305.93, "total_tokens": 1765984} +{"current_steps": 1765, "total_steps": 42420, "loss": 0.3405, "lr": 0.012475247524752474, "epoch": 0.8321546440358322, "percentage": 4.16, "elapsed_time": "0:05:33", "remaining_time": "2:08:08", "throughput": 5306.01, "total_tokens": 1771040} +{"current_steps": 1770, "total_steps": 42420, "loss": 0.3767, "lr": 0.01251060820367751, "epoch": 0.8345120226308345, "percentage": 4.17, "elapsed_time": "0:05:34", "remaining_time": "2:08:07", "throughput": 5306.49, "total_tokens": 1776288} +{"current_steps": 1775, "total_steps": 42420, "loss": 0.3452, "lr": 0.012545968882602546, "epoch": 0.8368694012258369, "percentage": 4.18, "elapsed_time": "0:05:35", "remaining_time": "2:08:07", "throughput": 5306.88, "total_tokens": 1781632} +{"current_steps": 1780, "total_steps": 42420, "loss": 0.3316, "lr": 0.01258132956152758, "epoch": 0.8392267798208393, "percentage": 4.2, "elapsed_time": "0:05:36", "remaining_time": "2:08:04", "throughput": 5306.42, "total_tokens": 1786048} +{"current_steps": 1785, "total_steps": 42420, "loss": 0.3493, "lr": 0.012616690240452616, "epoch": 0.8415841584158416, "percentage": 4.21, "elapsed_time": "0:05:37", "remaining_time": "2:08:03", "throughput": 5306.25, "total_tokens": 1790848} +{"current_steps": 1790, "total_steps": 42420, "loss": 0.3411, "lr": 0.01265205091937765, "epoch": 0.843941537010844, "percentage": 4.22, "elapsed_time": "0:05:38", "remaining_time": "2:08:01", "throughput": 5306.39, "total_tokens": 1795680} +{"current_steps": 1795, "total_steps": 42420, "loss": 0.3269, "lr": 0.012687411598302688, "epoch": 0.8462989156058462, "percentage": 4.23, "elapsed_time": "0:05:39", "remaining_time": "2:07:59", "throughput": 5306.14, "total_tokens": 1800448} +{"current_steps": 1800, "total_steps": 42420, "loss": 0.3836, "lr": 0.012722772277227724, "epoch": 0.8486562942008486, "percentage": 4.24, "elapsed_time": "0:05:40", "remaining_time": "2:07:58", "throughput": 5306.35, "total_tokens": 1805568} +{"current_steps": 1805, "total_steps": 42420, "loss": 0.338, "lr": 0.012758132956152758, "epoch": 0.851013672795851, "percentage": 4.26, "elapsed_time": "0:05:41", "remaining_time": "2:07:56", "throughput": 5305.96, "total_tokens": 1810080} +{"current_steps": 1810, "total_steps": 42420, "loss": 0.293, "lr": 0.012793493635077794, "epoch": 0.8533710513908533, "percentage": 4.27, "elapsed_time": "0:05:41", "remaining_time": "2:07:53", "throughput": 5305.33, "total_tokens": 1814400} +{"current_steps": 1815, "total_steps": 42420, "loss": 0.3987, "lr": 0.012828854314002828, "epoch": 0.8557284299858557, "percentage": 4.28, "elapsed_time": "0:05:42", "remaining_time": "2:07:51", "throughput": 5305.42, "total_tokens": 1819296} +{"current_steps": 1820, "total_steps": 42420, "loss": 0.3624, "lr": 0.012864214992927864, "epoch": 0.858085808580858, "percentage": 4.29, "elapsed_time": "0:05:43", "remaining_time": "2:07:49", "throughput": 5305.55, "total_tokens": 1824160} +{"current_steps": 1825, "total_steps": 42420, "loss": 0.3478, "lr": 0.0128995756718529, "epoch": 0.8604431871758604, "percentage": 4.3, "elapsed_time": "0:05:44", "remaining_time": "2:07:51", "throughput": 5306.53, "total_tokens": 1830240} +{"current_steps": 1830, "total_steps": 42420, "loss": 0.3678, "lr": 0.012934936350777934, "epoch": 0.8628005657708628, "percentage": 4.31, "elapsed_time": "0:05:45", "remaining_time": "2:07:49", "throughput": 5306.08, "total_tokens": 1834752} +{"current_steps": 1835, "total_steps": 42420, "loss": 0.3418, "lr": 0.01297029702970297, "epoch": 0.8651579443658651, "percentage": 4.33, "elapsed_time": "0:05:46", "remaining_time": "2:07:48", "throughput": 5306.39, "total_tokens": 1839936} +{"current_steps": 1840, "total_steps": 42420, "loss": 0.2603, "lr": 0.013005657708628004, "epoch": 0.8675153229608675, "percentage": 4.34, "elapsed_time": "0:05:47", "remaining_time": "2:07:46", "throughput": 5306.01, "total_tokens": 1844448} +{"current_steps": 1845, "total_steps": 42420, "loss": 0.3845, "lr": 0.013041018387553041, "epoch": 0.8698727015558698, "percentage": 4.35, "elapsed_time": "0:05:48", "remaining_time": "2:07:43", "throughput": 5305.34, "total_tokens": 1848704} +{"current_steps": 1850, "total_steps": 42420, "loss": 0.3111, "lr": 0.013076379066478077, "epoch": 0.8722300801508722, "percentage": 4.36, "elapsed_time": "0:05:49", "remaining_time": "2:07:43", "throughput": 5305.71, "total_tokens": 1854144} +{"current_steps": 1855, "total_steps": 42420, "loss": 0.3834, "lr": 0.013111739745403111, "epoch": 0.8745874587458746, "percentage": 4.37, "elapsed_time": "0:05:50", "remaining_time": "2:07:42", "throughput": 5306.04, "total_tokens": 1859232} +{"current_steps": 1860, "total_steps": 42420, "loss": 0.3793, "lr": 0.013147100424328147, "epoch": 0.8769448373408769, "percentage": 4.38, "elapsed_time": "0:05:51", "remaining_time": "2:07:42", "throughput": 5306.82, "total_tokens": 1864736} +{"current_steps": 1865, "total_steps": 42420, "loss": 0.3731, "lr": 0.013182461103253182, "epoch": 0.8793022159358793, "percentage": 4.4, "elapsed_time": "0:05:52", "remaining_time": "2:07:42", "throughput": 5307.5, "total_tokens": 1870336} +{"current_steps": 1870, "total_steps": 42420, "loss": 0.3542, "lr": 0.013217821782178217, "epoch": 0.8816595945308816, "percentage": 4.41, "elapsed_time": "0:05:53", "remaining_time": "2:07:43", "throughput": 5308.22, "total_tokens": 1875872} +{"current_steps": 1875, "total_steps": 42420, "loss": 0.3713, "lr": 0.013253182461103253, "epoch": 0.884016973125884, "percentage": 4.42, "elapsed_time": "0:05:54", "remaining_time": "2:07:40", "throughput": 5307.97, "total_tokens": 1880288} +{"current_steps": 1880, "total_steps": 42420, "loss": 0.364, "lr": 0.013288543140028287, "epoch": 0.8863743517208864, "percentage": 4.43, "elapsed_time": "0:05:55", "remaining_time": "2:07:39", "throughput": 5308.19, "total_tokens": 1885376} +{"current_steps": 1885, "total_steps": 42420, "loss": 0.3324, "lr": 0.013323903818953323, "epoch": 0.8887317303158887, "percentage": 4.44, "elapsed_time": "0:05:56", "remaining_time": "2:07:37", "throughput": 5308.37, "total_tokens": 1890272} +{"current_steps": 1890, "total_steps": 42420, "loss": 0.3543, "lr": 0.013359264497878357, "epoch": 0.8910891089108911, "percentage": 4.46, "elapsed_time": "0:05:56", "remaining_time": "2:07:35", "throughput": 5308.17, "total_tokens": 1894976} +{"current_steps": 1895, "total_steps": 42420, "loss": 0.3282, "lr": 0.013394625176803393, "epoch": 0.8934464875058934, "percentage": 4.47, "elapsed_time": "0:05:58", "remaining_time": "2:07:37", "throughput": 5309.08, "total_tokens": 1900992} +{"current_steps": 1900, "total_steps": 42420, "loss": 0.3386, "lr": 0.013429985855728431, "epoch": 0.8958038661008958, "percentage": 4.48, "elapsed_time": "0:05:59", "remaining_time": "2:07:36", "throughput": 5308.98, "total_tokens": 1905984} +{"current_steps": 1905, "total_steps": 42420, "loss": 0.3021, "lr": 0.013465346534653465, "epoch": 0.8981612446958982, "percentage": 4.49, "elapsed_time": "0:05:59", "remaining_time": "2:07:34", "throughput": 5308.95, "total_tokens": 1910848} +{"current_steps": 1910, "total_steps": 42420, "loss": 0.4387, "lr": 0.013500707213578501, "epoch": 0.9005186232909005, "percentage": 4.5, "elapsed_time": "0:06:00", "remaining_time": "2:07:35", "throughput": 5309.71, "total_tokens": 1916448} +{"current_steps": 1915, "total_steps": 42420, "loss": 0.3076, "lr": 0.013536067892503535, "epoch": 0.9028760018859029, "percentage": 4.51, "elapsed_time": "0:06:01", "remaining_time": "2:07:33", "throughput": 5309.94, "total_tokens": 1921440} +{"current_steps": 1920, "total_steps": 42420, "loss": 0.3356, "lr": 0.013571428571428571, "epoch": 0.9052333804809052, "percentage": 4.53, "elapsed_time": "0:06:02", "remaining_time": "2:07:31", "throughput": 5309.53, "total_tokens": 1925984} +{"current_steps": 1925, "total_steps": 42420, "loss": 0.3315, "lr": 0.013606789250353607, "epoch": 0.9075907590759076, "percentage": 4.54, "elapsed_time": "0:06:03", "remaining_time": "2:07:33", "throughput": 5310.62, "total_tokens": 1932096} +{"current_steps": 1930, "total_steps": 42420, "loss": 0.3311, "lr": 0.013642149929278641, "epoch": 0.90994813767091, "percentage": 4.55, "elapsed_time": "0:06:04", "remaining_time": "2:07:31", "throughput": 5310.32, "total_tokens": 1936640} +{"current_steps": 1935, "total_steps": 42420, "loss": 0.3198, "lr": 0.013677510608203677, "epoch": 0.9123055162659123, "percentage": 4.56, "elapsed_time": "0:06:05", "remaining_time": "2:07:29", "throughput": 5310.05, "total_tokens": 1941472} +{"current_steps": 1940, "total_steps": 42420, "loss": 0.3173, "lr": 0.013712871287128711, "epoch": 0.9146628948609147, "percentage": 4.57, "elapsed_time": "0:06:06", "remaining_time": "2:07:28", "throughput": 5310.03, "total_tokens": 1946528} +{"current_steps": 1945, "total_steps": 42420, "loss": 0.3504, "lr": 0.013748231966053747, "epoch": 0.917020273455917, "percentage": 4.59, "elapsed_time": "0:06:07", "remaining_time": "2:07:30", "throughput": 5310.66, "total_tokens": 1952352} +{"current_steps": 1950, "total_steps": 42420, "loss": 0.2887, "lr": 0.013783592644978785, "epoch": 0.9193776520509194, "percentage": 4.6, "elapsed_time": "0:06:08", "remaining_time": "2:07:29", "throughput": 5310.65, "total_tokens": 1957344} +{"current_steps": 1955, "total_steps": 42420, "loss": 0.464, "lr": 0.013818953323903819, "epoch": 0.9217350306459218, "percentage": 4.61, "elapsed_time": "0:06:09", "remaining_time": "2:07:26", "throughput": 5310.25, "total_tokens": 1961824} +{"current_steps": 1960, "total_steps": 42420, "loss": 0.4098, "lr": 0.013854314002828855, "epoch": 0.9240924092409241, "percentage": 4.62, "elapsed_time": "0:06:10", "remaining_time": "2:07:24", "throughput": 5309.99, "total_tokens": 1966368} +{"current_steps": 1965, "total_steps": 42420, "loss": 0.3376, "lr": 0.013889674681753889, "epoch": 0.9264497878359265, "percentage": 4.63, "elapsed_time": "0:06:11", "remaining_time": "2:07:29", "throughput": 5311.85, "total_tokens": 1973600} +{"current_steps": 1970, "total_steps": 42420, "loss": 0.3183, "lr": 0.013925035360678925, "epoch": 0.9288071664309288, "percentage": 4.64, "elapsed_time": "0:06:12", "remaining_time": "2:07:28", "throughput": 5312.12, "total_tokens": 1978880} +{"current_steps": 1975, "total_steps": 42420, "loss": 0.3227, "lr": 0.01396039603960396, "epoch": 0.9311645450259312, "percentage": 4.66, "elapsed_time": "0:06:13", "remaining_time": "2:07:30", "throughput": 5312.8, "total_tokens": 1984864} +{"current_steps": 1980, "total_steps": 42420, "loss": 0.4489, "lr": 0.013995756718528995, "epoch": 0.9335219236209336, "percentage": 4.67, "elapsed_time": "0:06:14", "remaining_time": "2:07:31", "throughput": 5313.61, "total_tokens": 1990592} +{"current_steps": 1985, "total_steps": 42420, "loss": 0.334, "lr": 0.01403111739745403, "epoch": 0.9358793022159358, "percentage": 4.68, "elapsed_time": "0:06:15", "remaining_time": "2:07:32", "throughput": 5314.42, "total_tokens": 1996512} +{"current_steps": 1990, "total_steps": 42420, "loss": 0.3503, "lr": 0.014066478076379065, "epoch": 0.9382366808109383, "percentage": 4.69, "elapsed_time": "0:06:16", "remaining_time": "2:07:30", "throughput": 5314.07, "total_tokens": 2000960} +{"current_steps": 1995, "total_steps": 42420, "loss": 0.2989, "lr": 0.0141018387553041, "epoch": 0.9405940594059405, "percentage": 4.7, "elapsed_time": "0:06:17", "remaining_time": "2:07:26", "throughput": 5313.24, "total_tokens": 2005056} +{"current_steps": 2000, "total_steps": 42420, "loss": 0.4749, "lr": 0.014137199434229137, "epoch": 0.9429514380009429, "percentage": 4.71, "elapsed_time": "0:06:18", "remaining_time": "2:07:24", "throughput": 5312.81, "total_tokens": 2009472} +{"current_steps": 2005, "total_steps": 42420, "loss": 0.3704, "lr": 0.014172560113154173, "epoch": 0.9453088165959453, "percentage": 4.73, "elapsed_time": "0:06:19", "remaining_time": "2:07:21", "throughput": 5312.49, "total_tokens": 2013888} +{"current_steps": 2010, "total_steps": 42420, "loss": 0.3773, "lr": 0.014207920792079208, "epoch": 0.9476661951909476, "percentage": 4.74, "elapsed_time": "0:06:20", "remaining_time": "2:07:22", "throughput": 5313.1, "total_tokens": 2019808} +{"current_steps": 2015, "total_steps": 42420, "loss": 0.3359, "lr": 0.014243281471004243, "epoch": 0.95002357378595, "percentage": 4.75, "elapsed_time": "0:06:21", "remaining_time": "2:07:23", "throughput": 5313.76, "total_tokens": 2025440} +{"current_steps": 2020, "total_steps": 42420, "loss": 0.3669, "lr": 0.014278642149929278, "epoch": 0.9523809523809523, "percentage": 4.76, "elapsed_time": "0:06:22", "remaining_time": "2:07:22", "throughput": 5313.81, "total_tokens": 2030464} +{"current_steps": 2025, "total_steps": 42420, "loss": 0.3339, "lr": 0.014314002828854314, "epoch": 0.9547383309759547, "percentage": 4.77, "elapsed_time": "0:06:23", "remaining_time": "2:07:20", "throughput": 5313.78, "total_tokens": 2035328} +{"current_steps": 2030, "total_steps": 42420, "loss": 0.2298, "lr": 0.014349363507779348, "epoch": 0.9570957095709571, "percentage": 4.79, "elapsed_time": "0:06:23", "remaining_time": "2:07:17", "throughput": 5313.12, "total_tokens": 2039616} +{"current_steps": 2035, "total_steps": 42420, "loss": 0.4437, "lr": 0.014384724186704384, "epoch": 0.9594530881659594, "percentage": 4.8, "elapsed_time": "0:06:24", "remaining_time": "2:07:18", "throughput": 5313.91, "total_tokens": 2045408} +{"current_steps": 2040, "total_steps": 42420, "loss": 0.3528, "lr": 0.014420084865629419, "epoch": 0.9618104667609618, "percentage": 4.81, "elapsed_time": "0:06:25", "remaining_time": "2:07:19", "throughput": 5313.92, "total_tokens": 2050816} +{"current_steps": 2045, "total_steps": 42420, "loss": 0.3609, "lr": 0.014455445544554454, "epoch": 0.9641678453559641, "percentage": 4.82, "elapsed_time": "0:06:26", "remaining_time": "2:07:18", "throughput": 5314.32, "total_tokens": 2056128} +{"current_steps": 2050, "total_steps": 42420, "loss": 0.3496, "lr": 0.01449080622347949, "epoch": 0.9665252239509665, "percentage": 4.83, "elapsed_time": "0:06:27", "remaining_time": "2:07:17", "throughput": 5314.37, "total_tokens": 2061120} +{"current_steps": 2055, "total_steps": 42420, "loss": 0.3456, "lr": 0.014526166902404526, "epoch": 0.9688826025459689, "percentage": 4.84, "elapsed_time": "0:06:28", "remaining_time": "2:07:17", "throughput": 5314.67, "total_tokens": 2066400} +{"current_steps": 2060, "total_steps": 42420, "loss": 0.3119, "lr": 0.014561527581329562, "epoch": 0.9712399811409712, "percentage": 4.86, "elapsed_time": "0:06:29", "remaining_time": "2:07:15", "throughput": 5314.3, "total_tokens": 2071200} +{"current_steps": 2065, "total_steps": 42420, "loss": 0.3765, "lr": 0.014596888260254596, "epoch": 0.9735973597359736, "percentage": 4.87, "elapsed_time": "0:06:30", "remaining_time": "2:07:15", "throughput": 5314.47, "total_tokens": 2076320} +{"current_steps": 2070, "total_steps": 42420, "loss": 0.3587, "lr": 0.014632248939179632, "epoch": 0.9759547383309759, "percentage": 4.88, "elapsed_time": "0:06:31", "remaining_time": "2:07:15", "throughput": 5315.14, "total_tokens": 2082016} +{"current_steps": 2075, "total_steps": 42420, "loss": 0.3608, "lr": 0.014667609618104668, "epoch": 0.9783121169259783, "percentage": 4.89, "elapsed_time": "0:06:32", "remaining_time": "2:07:14", "throughput": 5315.17, "total_tokens": 2087136} +{"current_steps": 2080, "total_steps": 42420, "loss": 0.3445, "lr": 0.014702970297029702, "epoch": 0.9806694955209807, "percentage": 4.9, "elapsed_time": "0:06:33", "remaining_time": "2:07:14", "throughput": 5315.51, "total_tokens": 2092352} +{"current_steps": 2085, "total_steps": 42420, "loss": 0.3522, "lr": 0.014738330975954738, "epoch": 0.983026874115983, "percentage": 4.92, "elapsed_time": "0:06:34", "remaining_time": "2:07:11", "throughput": 5314.9, "total_tokens": 2096576} +{"current_steps": 2090, "total_steps": 42420, "loss": 0.3461, "lr": 0.014773691654879772, "epoch": 0.9853842527109854, "percentage": 4.93, "elapsed_time": "0:06:35", "remaining_time": "2:07:09", "throughput": 5314.99, "total_tokens": 2101472} +{"current_steps": 2095, "total_steps": 42420, "loss": 0.3136, "lr": 0.014809052333804808, "epoch": 0.9877416313059877, "percentage": 4.94, "elapsed_time": "0:06:36", "remaining_time": "2:07:07", "throughput": 5314.91, "total_tokens": 2106144} +{"current_steps": 2100, "total_steps": 42420, "loss": 0.4114, "lr": 0.014844413012729844, "epoch": 0.9900990099009901, "percentage": 4.95, "elapsed_time": "0:06:37", "remaining_time": "2:07:05", "throughput": 5314.9, "total_tokens": 2110880} +{"current_steps": 2105, "total_steps": 42420, "loss": 0.3379, "lr": 0.014879773691654878, "epoch": 0.9924563884959925, "percentage": 4.96, "elapsed_time": "0:06:38", "remaining_time": "2:07:03", "throughput": 5314.89, "total_tokens": 2115712} +{"current_steps": 2110, "total_steps": 42420, "loss": 0.3784, "lr": 0.014915134370579916, "epoch": 0.9948137670909948, "percentage": 4.97, "elapsed_time": "0:06:38", "remaining_time": "2:07:01", "throughput": 5314.44, "total_tokens": 2120192} +{"current_steps": 2115, "total_steps": 42420, "loss": 0.3532, "lr": 0.01495049504950495, "epoch": 0.9971711456859972, "percentage": 4.99, "elapsed_time": "0:06:39", "remaining_time": "2:07:01", "throughput": 5314.88, "total_tokens": 2125728} +{"current_steps": 2120, "total_steps": 42420, "loss": 0.2872, "lr": 0.014985855728429986, "epoch": 0.9995285242809995, "percentage": 5.0, "elapsed_time": "0:06:40", "remaining_time": "2:07:00", "throughput": 5315.01, "total_tokens": 2130624} +{"current_steps": 2121, "total_steps": 42420, "eval_loss": 0.33909040689468384, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:07:00", "remaining_time": "2:13:12", "throughput": 5068.17, "total_tokens": 2131904} +{"current_steps": 2125, "total_steps": 42420, "loss": 0.4374, "lr": 0.01502121640735502, "epoch": 1.0018859028760019, "percentage": 5.01, "elapsed_time": "0:07:02", "remaining_time": "2:13:36", "throughput": 5053.0, "total_tokens": 2136160} +{"current_steps": 2130, "total_steps": 42420, "loss": 0.3515, "lr": 0.015056577086280056, "epoch": 1.0042432814710043, "percentage": 5.02, "elapsed_time": "0:07:03", "remaining_time": "2:13:32", "throughput": 5052.87, "total_tokens": 2140320} +{"current_steps": 2135, "total_steps": 42420, "loss": 0.3734, "lr": 0.015091937765205092, "epoch": 1.0066006600660067, "percentage": 5.03, "elapsed_time": "0:07:04", "remaining_time": "2:13:31", "throughput": 5054.03, "total_tokens": 2145952} +{"current_steps": 2140, "total_steps": 42420, "loss": 0.3045, "lr": 0.015127298444130128, "epoch": 1.0089580386610089, "percentage": 5.04, "elapsed_time": "0:07:05", "remaining_time": "2:13:32", "throughput": 5055.27, "total_tokens": 2151936}