diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,441 @@ +{"current_steps": 1, "total_steps": 440, "loss": 2.5462, "lr": 4.999936276068748e-05, "epoch": 0.011347517730496455, "percentage": 0.23, "elapsed_time": "0:00:26", "remaining_time": "3:10:31", "throughput": 10067.36, "total_tokens": 262144} +{"current_steps": 2, "total_steps": 440, "loss": 4.367, "lr": 4.9997451075235834e-05, "epoch": 0.02269503546099291, "percentage": 0.45, "elapsed_time": "0:00:50", "remaining_time": "3:05:12", "throughput": 10332.36, "total_tokens": 524288} +{"current_steps": 3, "total_steps": 440, "loss": 3.7754, "lr": 4.999426504110115e-05, "epoch": 0.03404255319148936, "percentage": 0.68, "elapsed_time": "0:01:15", "remaining_time": "3:02:40", "throughput": 10451.58, "total_tokens": 786432} +{"current_steps": 4, "total_steps": 440, "loss": 3.4412, "lr": 4.9989804820704735e-05, "epoch": 0.04539007092198582, "percentage": 0.91, "elapsed_time": "0:01:39", "remaining_time": "3:01:11", "throughput": 10512.89, "total_tokens": 1048576} +{"current_steps": 5, "total_steps": 440, "loss": 2.5369, "lr": 4.99840706414248e-05, "epoch": 0.05673758865248227, "percentage": 1.14, "elapsed_time": "0:02:04", "remaining_time": "3:00:07", "throughput": 10550.89, "total_tokens": 1310720} +{"current_steps": 6, "total_steps": 440, "loss": 2.531, "lr": 4.9977062795584893e-05, "epoch": 0.06808510638297872, "percentage": 1.36, "elapsed_time": "0:02:28", "remaining_time": "2:59:19", "throughput": 10573.62, "total_tokens": 1572864} +{"current_steps": 7, "total_steps": 440, "loss": 2.2971, "lr": 4.9968781640439026e-05, "epoch": 0.07943262411347518, "percentage": 1.59, "elapsed_time": "0:02:53", "remaining_time": "2:58:35", "throughput": 10592.77, "total_tokens": 1835008} +{"current_steps": 8, "total_steps": 440, "loss": 2.2175, "lr": 4.995922759815339e-05, "epoch": 0.09078014184397164, "percentage": 1.82, "elapsed_time": "0:03:17", "remaining_time": "2:57:57", "throughput": 10605.93, "total_tokens": 2097152} +{"current_steps": 9, "total_steps": 440, "loss": 2.0184, "lr": 4.9948401155784904e-05, "epoch": 0.10212765957446808, "percentage": 2.05, "elapsed_time": "0:03:42", "remaining_time": "2:57:21", "throughput": 10617.47, "total_tokens": 2359296} +{"current_steps": 10, "total_steps": 440, "loss": 1.97, "lr": 4.993630286525634e-05, "epoch": 0.11347517730496454, "percentage": 2.27, "elapsed_time": "0:04:06", "remaining_time": "2:56:45", "throughput": 10628.3, "total_tokens": 2621440} +{"current_steps": 11, "total_steps": 440, "loss": 1.9201, "lr": 4.99229333433282e-05, "epoch": 0.12482269503546099, "percentage": 2.5, "elapsed_time": "0:04:31", "remaining_time": "2:56:13", "throughput": 10635.64, "total_tokens": 2883584} +{"current_steps": 12, "total_steps": 440, "loss": 1.8835, "lr": 4.9908293271567286e-05, "epoch": 0.13617021276595745, "percentage": 2.73, "elapsed_time": "0:04:55", "remaining_time": "2:55:40", "throughput": 10644.06, "total_tokens": 3145728} +{"current_steps": 13, "total_steps": 440, "loss": 1.808, "lr": 4.9892383396311934e-05, "epoch": 0.1475177304964539, "percentage": 2.95, "elapsed_time": "0:05:19", "remaining_time": "2:55:10", "throughput": 10649.76, "total_tokens": 3407872} +{"current_steps": 14, "total_steps": 440, "loss": 1.7956, "lr": 4.987520452863399e-05, "epoch": 0.15886524822695036, "percentage": 3.18, "elapsed_time": "0:05:44", "remaining_time": "2:54:40", "throughput": 10655.58, "total_tokens": 3670016} +{"current_steps": 15, "total_steps": 440, "loss": 1.781, "lr": 4.985675754429744e-05, "epoch": 0.1702127659574468, "percentage": 3.41, "elapsed_time": "0:06:08", "remaining_time": "2:54:12", "throughput": 10658.41, "total_tokens": 3932160} +{"current_steps": 16, "total_steps": 440, "loss": 1.7132, "lr": 4.9837043383713753e-05, "epoch": 0.18156028368794327, "percentage": 3.64, "elapsed_time": "0:06:33", "remaining_time": "2:53:45", "throughput": 10661.23, "total_tokens": 4194304} +{"current_steps": 17, "total_steps": 440, "loss": 1.7316, "lr": 4.981606305189401e-05, "epoch": 0.19290780141843972, "percentage": 3.86, "elapsed_time": "0:06:57", "remaining_time": "2:53:18", "throughput": 10663.47, "total_tokens": 4456448} +{"current_steps": 18, "total_steps": 440, "loss": 1.7198, "lr": 4.979381761839757e-05, "epoch": 0.20425531914893616, "percentage": 4.09, "elapsed_time": "0:07:22", "remaining_time": "2:52:51", "throughput": 10666.4, "total_tokens": 4718592} +{"current_steps": 19, "total_steps": 440, "loss": 1.6976, "lr": 4.9770308217277614e-05, "epoch": 0.21560283687943263, "percentage": 4.32, "elapsed_time": "0:07:46", "remaining_time": "2:52:23", "throughput": 10669.61, "total_tokens": 4980736} +{"current_steps": 20, "total_steps": 440, "loss": 1.7159, "lr": 4.9745536047023324e-05, "epoch": 0.22695035460992907, "percentage": 4.55, "elapsed_time": "0:08:11", "remaining_time": "2:51:57", "throughput": 10671.62, "total_tokens": 5242880} +{"current_steps": 21, "total_steps": 440, "loss": 1.6871, "lr": 4.971950237049874e-05, "epoch": 0.23829787234042554, "percentage": 4.77, "elapsed_time": "0:08:35", "remaining_time": "2:51:30", "throughput": 10673.79, "total_tokens": 5505024} +{"current_steps": 22, "total_steps": 440, "loss": 1.641, "lr": 4.9692208514878444e-05, "epoch": 0.24964539007092199, "percentage": 5.0, "elapsed_time": "0:09:00", "remaining_time": "2:51:04", "throughput": 10675.66, "total_tokens": 5767168} +{"current_steps": 23, "total_steps": 440, "loss": 1.6336, "lr": 4.966365587157986e-05, "epoch": 0.26099290780141843, "percentage": 5.23, "elapsed_time": "0:09:24", "remaining_time": "2:50:37", "throughput": 10677.82, "total_tokens": 6029312} +{"current_steps": 24, "total_steps": 440, "loss": 1.6184, "lr": 4.963384589619233e-05, "epoch": 0.2723404255319149, "percentage": 5.45, "elapsed_time": "0:09:49", "remaining_time": "2:50:11", "throughput": 10679.71, "total_tokens": 6291456} +{"current_steps": 25, "total_steps": 440, "loss": 1.6175, "lr": 4.96027801084029e-05, "epoch": 0.28368794326241137, "percentage": 5.68, "elapsed_time": "0:10:13", "remaining_time": "2:49:45", "throughput": 10680.69, "total_tokens": 6553600} +{"current_steps": 26, "total_steps": 440, "loss": 1.6145, "lr": 4.957046009191889e-05, "epoch": 0.2950354609929078, "percentage": 5.91, "elapsed_time": "0:10:38", "remaining_time": "2:49:20", "throughput": 10681.27, "total_tokens": 6815744} +{"current_steps": 27, "total_steps": 440, "loss": 1.5905, "lr": 4.95368874943871e-05, "epoch": 0.30638297872340425, "percentage": 6.14, "elapsed_time": "0:11:02", "remaining_time": "2:48:54", "throughput": 10682.93, "total_tokens": 7077888} +{"current_steps": 28, "total_steps": 440, "loss": 1.5847, "lr": 4.9502064027309836e-05, "epoch": 0.3177304964539007, "percentage": 6.36, "elapsed_time": "0:11:27", "remaining_time": "2:48:28", "throughput": 10684.01, "total_tokens": 7340032} +{"current_steps": 29, "total_steps": 440, "loss": 1.5862, "lr": 4.946599146595769e-05, "epoch": 0.32907801418439714, "percentage": 6.59, "elapsed_time": "0:11:51", "remaining_time": "2:48:03", "throughput": 10685.35, "total_tokens": 7602176} +{"current_steps": 30, "total_steps": 440, "loss": 1.5856, "lr": 4.942867164927899e-05, "epoch": 0.3404255319148936, "percentage": 6.82, "elapsed_time": "0:12:15", "remaining_time": "2:47:37", "throughput": 10686.36, "total_tokens": 7864320} +{"current_steps": 31, "total_steps": 440, "loss": 1.5462, "lr": 4.9390106479806085e-05, "epoch": 0.3517730496453901, "percentage": 7.05, "elapsed_time": "0:12:40", "remaining_time": "2:47:12", "throughput": 10686.7, "total_tokens": 8126464} +{"current_steps": 32, "total_steps": 440, "loss": 1.5519, "lr": 4.935029792355834e-05, "epoch": 0.36312056737588655, "percentage": 7.27, "elapsed_time": "0:13:04", "remaining_time": "2:46:47", "throughput": 10687.07, "total_tokens": 8388608} +{"current_steps": 33, "total_steps": 440, "loss": 1.5426, "lr": 4.9309248009941914e-05, "epoch": 0.37446808510638296, "percentage": 7.5, "elapsed_time": "0:13:29", "remaining_time": "2:46:22", "throughput": 10688.43, "total_tokens": 8650752} +{"current_steps": 34, "total_steps": 440, "loss": 1.5179, "lr": 4.9266958831646315e-05, "epoch": 0.38581560283687943, "percentage": 7.73, "elapsed_time": "0:13:53", "remaining_time": "2:45:57", "throughput": 10688.73, "total_tokens": 8912896} +{"current_steps": 35, "total_steps": 440, "loss": 1.5046, "lr": 4.922343254453768e-05, "epoch": 0.3971631205673759, "percentage": 7.95, "elapsed_time": "0:14:18", "remaining_time": "2:45:31", "throughput": 10689.53, "total_tokens": 9175040} +{"current_steps": 36, "total_steps": 440, "loss": 1.5147, "lr": 4.917867136754893e-05, "epoch": 0.4085106382978723, "percentage": 8.18, "elapsed_time": "0:14:42", "remaining_time": "2:45:07", "throughput": 10689.63, "total_tokens": 9437184} +{"current_steps": 37, "total_steps": 440, "loss": 1.5326, "lr": 4.913267758256658e-05, "epoch": 0.4198581560283688, "percentage": 8.41, "elapsed_time": "0:15:07", "remaining_time": "2:44:42", "throughput": 10690.06, "total_tokens": 9699328} +{"current_steps": 38, "total_steps": 440, "loss": 1.5253, "lr": 4.9085453534314476e-05, "epoch": 0.43120567375886526, "percentage": 8.64, "elapsed_time": "0:15:31", "remaining_time": "2:44:17", "throughput": 10690.23, "total_tokens": 9961472} +{"current_steps": 39, "total_steps": 440, "loss": 1.5003, "lr": 4.9037001630234215e-05, "epoch": 0.4425531914893617, "percentage": 8.86, "elapsed_time": "0:15:56", "remaining_time": "2:43:53", "throughput": 10690.23, "total_tokens": 10223616} +{"current_steps": 40, "total_steps": 440, "loss": 1.5021, "lr": 4.898732434036244e-05, "epoch": 0.45390070921985815, "percentage": 9.09, "elapsed_time": "0:16:20", "remaining_time": "2:43:28", "throughput": 10690.66, "total_tokens": 10485760} +{"current_steps": 41, "total_steps": 440, "loss": 1.4748, "lr": 4.893642419720491e-05, "epoch": 0.4652482269503546, "percentage": 9.32, "elapsed_time": "0:16:45", "remaining_time": "2:43:03", "throughput": 10691.41, "total_tokens": 10747904} +{"current_steps": 42, "total_steps": 440, "loss": 1.5064, "lr": 4.888430379560742e-05, "epoch": 0.4765957446808511, "percentage": 9.55, "elapsed_time": "0:17:09", "remaining_time": "2:42:37", "throughput": 10692.17, "total_tokens": 11010048} +{"current_steps": 43, "total_steps": 440, "loss": 1.4787, "lr": 4.883096579262346e-05, "epoch": 0.4879432624113475, "percentage": 9.77, "elapsed_time": "0:17:34", "remaining_time": "2:42:13", "throughput": 10692.52, "total_tokens": 11272192} +{"current_steps": 44, "total_steps": 440, "loss": 1.5032, "lr": 4.877641290737884e-05, "epoch": 0.49929078014184397, "percentage": 10.0, "elapsed_time": "0:17:58", "remaining_time": "2:41:47", "throughput": 10693.29, "total_tokens": 11534336} +{"current_steps": 45, "total_steps": 440, "loss": 1.5017, "lr": 4.872064792093299e-05, "epoch": 0.5106382978723404, "percentage": 10.23, "elapsed_time": "0:18:23", "remaining_time": "2:41:23", "throughput": 10693.65, "total_tokens": 11796480} +{"current_steps": 46, "total_steps": 440, "loss": 1.4899, "lr": 4.866367367613725e-05, "epoch": 0.5219858156028369, "percentage": 10.45, "elapsed_time": "0:18:47", "remaining_time": "2:40:58", "throughput": 10694.1, "total_tokens": 12058624} +{"current_steps": 47, "total_steps": 440, "loss": 1.4501, "lr": 4.86054930774899e-05, "epoch": 0.5333333333333333, "percentage": 10.68, "elapsed_time": "0:19:12", "remaining_time": "2:40:33", "throughput": 10694.46, "total_tokens": 12320768} +{"current_steps": 48, "total_steps": 440, "loss": 1.4729, "lr": 4.854610909098812e-05, "epoch": 0.5446808510638298, "percentage": 10.91, "elapsed_time": "0:19:36", "remaining_time": "2:40:08", "throughput": 10694.71, "total_tokens": 12582912} +{"current_steps": 49, "total_steps": 440, "loss": 1.4639, "lr": 4.848552474397676e-05, "epoch": 0.5560283687943263, "percentage": 11.14, "elapsed_time": "0:20:01", "remaining_time": "2:39:44", "throughput": 10694.44, "total_tokens": 12845056} +{"current_steps": 50, "total_steps": 440, "loss": 1.4626, "lr": 4.842374312499405e-05, "epoch": 0.5673758865248227, "percentage": 11.36, "elapsed_time": "0:20:25", "remaining_time": "2:39:19", "throughput": 10694.78, "total_tokens": 13107200} +{"current_steps": 51, "total_steps": 440, "loss": 1.4767, "lr": 4.836076738361408e-05, "epoch": 0.5787234042553191, "percentage": 11.59, "elapsed_time": "0:20:50", "remaining_time": "2:38:54", "throughput": 10695.28, "total_tokens": 13369344} +{"current_steps": 52, "total_steps": 440, "loss": 1.453, "lr": 4.829660073028631e-05, "epoch": 0.5900709219858156, "percentage": 11.82, "elapsed_time": "0:21:14", "remaining_time": "2:38:29", "throughput": 10695.67, "total_tokens": 13631488} +{"current_steps": 53, "total_steps": 440, "loss": 1.4406, "lr": 4.823124643617187e-05, "epoch": 0.601418439716312, "percentage": 12.05, "elapsed_time": "0:21:38", "remaining_time": "2:38:04", "throughput": 10696.58, "total_tokens": 13893632} +{"current_steps": 54, "total_steps": 440, "loss": 1.4498, "lr": 4.8164707832976783e-05, "epoch": 0.6127659574468085, "percentage": 12.27, "elapsed_time": "0:22:03", "remaining_time": "2:37:39", "throughput": 10697.41, "total_tokens": 14155776} +{"current_steps": 55, "total_steps": 440, "loss": 1.4288, "lr": 4.8096988312782174e-05, "epoch": 0.624113475177305, "percentage": 12.5, "elapsed_time": "0:22:27", "remaining_time": "2:37:14", "throughput": 10697.39, "total_tokens": 14417920} +{"current_steps": 56, "total_steps": 440, "loss": 1.4267, "lr": 4.802809132787125e-05, "epoch": 0.6354609929078014, "percentage": 12.73, "elapsed_time": "0:22:52", "remaining_time": "2:36:49", "throughput": 10697.79, "total_tokens": 14680064} +{"current_steps": 57, "total_steps": 440, "loss": 1.4775, "lr": 4.7958020390553426e-05, "epoch": 0.6468085106382979, "percentage": 12.95, "elapsed_time": "0:23:16", "remaining_time": "2:36:24", "throughput": 10698.21, "total_tokens": 14942208} +{"current_steps": 58, "total_steps": 440, "loss": 1.4387, "lr": 4.7886779072985156e-05, "epoch": 0.6581560283687943, "percentage": 13.18, "elapsed_time": "0:23:41", "remaining_time": "2:35:59", "throughput": 10698.77, "total_tokens": 15204352} +{"current_steps": 59, "total_steps": 440, "loss": 1.4093, "lr": 4.78143710069879e-05, "epoch": 0.6695035460992907, "percentage": 13.41, "elapsed_time": "0:24:05", "remaining_time": "2:35:35", "throughput": 10699.09, "total_tokens": 15466496} +{"current_steps": 60, "total_steps": 440, "loss": 1.421, "lr": 4.774079988386296e-05, "epoch": 0.6808510638297872, "percentage": 13.64, "elapsed_time": "0:24:30", "remaining_time": "2:35:10", "throughput": 10699.56, "total_tokens": 15728640} +{"current_steps": 61, "total_steps": 440, "loss": 1.4411, "lr": 4.766606945420329e-05, "epoch": 0.6921985815602837, "percentage": 13.86, "elapsed_time": "0:24:54", "remaining_time": "2:34:45", "throughput": 10700.3, "total_tokens": 15990784} +{"current_steps": 62, "total_steps": 440, "loss": 1.4283, "lr": 4.759018352770229e-05, "epoch": 0.7035460992907802, "percentage": 14.09, "elapsed_time": "0:25:18", "remaining_time": "2:34:20", "throughput": 10700.48, "total_tokens": 16252928} +{"current_steps": 63, "total_steps": 440, "loss": 1.4526, "lr": 4.751314597295963e-05, "epoch": 0.7148936170212766, "percentage": 14.32, "elapsed_time": "0:25:43", "remaining_time": "2:33:55", "throughput": 10701.12, "total_tokens": 16515072} +{"current_steps": 64, "total_steps": 440, "loss": 1.4148, "lr": 4.743496071728396e-05, "epoch": 0.7262411347517731, "percentage": 14.55, "elapsed_time": "0:26:07", "remaining_time": "2:33:30", "throughput": 10701.65, "total_tokens": 16777216} +{"current_steps": 65, "total_steps": 440, "loss": 1.3976, "lr": 4.735563174649278e-05, "epoch": 0.7375886524822695, "percentage": 14.77, "elapsed_time": "0:26:32", "remaining_time": "2:33:05", "throughput": 10701.7, "total_tokens": 17039360} +{"current_steps": 66, "total_steps": 440, "loss": 1.4137, "lr": 4.72751631047092e-05, "epoch": 0.7489361702127659, "percentage": 15.0, "elapsed_time": "0:26:56", "remaining_time": "2:32:41", "throughput": 10701.91, "total_tokens": 17301504} +{"current_steps": 67, "total_steps": 440, "loss": 1.3951, "lr": 4.719355889415576e-05, "epoch": 0.7602836879432624, "percentage": 15.23, "elapsed_time": "0:27:21", "remaining_time": "2:32:16", "throughput": 10702.18, "total_tokens": 17563648} +{"current_steps": 68, "total_steps": 440, "loss": 1.4049, "lr": 4.711082327494536e-05, "epoch": 0.7716312056737589, "percentage": 15.45, "elapsed_time": "0:27:45", "remaining_time": "2:31:51", "throughput": 10702.61, "total_tokens": 17825792} +{"current_steps": 69, "total_steps": 440, "loss": 1.4167, "lr": 4.7026960464869116e-05, "epoch": 0.7829787234042553, "percentage": 15.68, "elapsed_time": "0:28:10", "remaining_time": "2:31:27", "throughput": 10702.61, "total_tokens": 18087936} +{"current_steps": 70, "total_steps": 440, "loss": 1.4048, "lr": 4.6941974739181395e-05, "epoch": 0.7943262411347518, "percentage": 15.91, "elapsed_time": "0:28:34", "remaining_time": "2:31:02", "throughput": 10703.11, "total_tokens": 18350080} +{"current_steps": 71, "total_steps": 440, "loss": 1.4083, "lr": 4.6855870430381816e-05, "epoch": 0.8056737588652483, "percentage": 16.14, "elapsed_time": "0:28:58", "remaining_time": "2:30:37", "throughput": 10703.29, "total_tokens": 18612224} +{"current_steps": 72, "total_steps": 440, "loss": 1.3906, "lr": 4.6768651927994434e-05, "epoch": 0.8170212765957446, "percentage": 16.36, "elapsed_time": "0:29:23", "remaining_time": "2:30:12", "throughput": 10703.46, "total_tokens": 18874368} +{"current_steps": 73, "total_steps": 440, "loss": 1.3973, "lr": 4.668032367834392e-05, "epoch": 0.8283687943262411, "percentage": 16.59, "elapsed_time": "0:29:47", "remaining_time": "2:29:48", "throughput": 10703.26, "total_tokens": 19136512} +{"current_steps": 74, "total_steps": 440, "loss": 1.3918, "lr": 4.6590890184328925e-05, "epoch": 0.8397163120567376, "percentage": 16.82, "elapsed_time": "0:30:12", "remaining_time": "2:29:24", "throughput": 10703.21, "total_tokens": 19398656} +{"current_steps": 75, "total_steps": 440, "loss": 1.3819, "lr": 4.6500356005192514e-05, "epoch": 0.851063829787234, "percentage": 17.05, "elapsed_time": "0:30:36", "remaining_time": "2:28:59", "throughput": 10703.1, "total_tokens": 19660800} +{"current_steps": 76, "total_steps": 440, "loss": 1.3933, "lr": 4.640872575628973e-05, "epoch": 0.8624113475177305, "percentage": 17.27, "elapsed_time": "0:31:01", "remaining_time": "2:28:35", "throughput": 10703.2, "total_tokens": 19922944} +{"current_steps": 77, "total_steps": 440, "loss": 1.4081, "lr": 4.6316004108852305e-05, "epoch": 0.873758865248227, "percentage": 17.5, "elapsed_time": "0:31:25", "remaining_time": "2:28:10", "throughput": 10703.16, "total_tokens": 20185088} +{"current_steps": 78, "total_steps": 440, "loss": 1.3801, "lr": 4.622219578975057e-05, "epoch": 0.8851063829787233, "percentage": 17.73, "elapsed_time": "0:31:50", "remaining_time": "2:27:45", "throughput": 10703.86, "total_tokens": 20447232} +{"current_steps": 79, "total_steps": 440, "loss": 1.3655, "lr": 4.6127305581252414e-05, "epoch": 0.8964539007092198, "percentage": 17.95, "elapsed_time": "0:32:14", "remaining_time": "2:27:20", "throughput": 10704.05, "total_tokens": 20709376} +{"current_steps": 80, "total_steps": 440, "loss": 1.3896, "lr": 4.6031338320779534e-05, "epoch": 0.9078014184397163, "percentage": 18.18, "elapsed_time": "0:32:39", "remaining_time": "2:26:56", "throughput": 10704.47, "total_tokens": 20971520} +{"current_steps": 81, "total_steps": 440, "loss": 1.405, "lr": 4.593429890066082e-05, "epoch": 0.9191489361702128, "percentage": 18.41, "elapsed_time": "0:33:03", "remaining_time": "2:26:31", "throughput": 10704.63, "total_tokens": 21233664} +{"current_steps": 82, "total_steps": 440, "loss": 1.3843, "lr": 4.583619226788294e-05, "epoch": 0.9304964539007092, "percentage": 18.64, "elapsed_time": "0:33:28", "remaining_time": "2:26:06", "throughput": 10704.95, "total_tokens": 21495808} +{"current_steps": 83, "total_steps": 440, "loss": 1.3698, "lr": 4.573702342383816e-05, "epoch": 0.9418439716312057, "percentage": 18.86, "elapsed_time": "0:33:52", "remaining_time": "2:25:42", "throughput": 10704.95, "total_tokens": 21757952} +{"current_steps": 84, "total_steps": 440, "loss": 1.3806, "lr": 4.563679742406935e-05, "epoch": 0.9531914893617022, "percentage": 19.09, "elapsed_time": "0:34:16", "remaining_time": "2:25:17", "throughput": 10705.24, "total_tokens": 22020096} +{"current_steps": 85, "total_steps": 440, "loss": 1.3715, "lr": 4.5535519378012295e-05, "epoch": 0.9645390070921985, "percentage": 19.32, "elapsed_time": "0:34:41", "remaining_time": "2:24:52", "throughput": 10705.34, "total_tokens": 22282240} +{"current_steps": 86, "total_steps": 440, "loss": 1.3718, "lr": 4.543319444873517e-05, "epoch": 0.975886524822695, "percentage": 19.55, "elapsed_time": "0:35:05", "remaining_time": "2:24:28", "throughput": 10705.7, "total_tokens": 22544384} +{"current_steps": 87, "total_steps": 440, "loss": 1.3564, "lr": 4.532982785267541e-05, "epoch": 0.9872340425531915, "percentage": 19.77, "elapsed_time": "0:35:30", "remaining_time": "2:24:03", "throughput": 10705.89, "total_tokens": 22806528} +{"current_steps": 88, "total_steps": 440, "loss": 1.3744, "lr": 4.522542485937369e-05, "epoch": 0.9985815602836879, "percentage": 20.0, "elapsed_time": "0:35:54", "remaining_time": "2:23:38", "throughput": 10706.22, "total_tokens": 23068672} +{"current_steps": 89, "total_steps": 440, "loss": 1.2363, "lr": 4.511999079120534e-05, "epoch": 1.0, "percentage": 20.23, "elapsed_time": "0:35:57", "remaining_time": "2:21:49", "throughput": 10706.58, "total_tokens": 23101440} +{"current_steps": 90, "total_steps": 440, "loss": 1.0013, "lr": 4.5013531023109014e-05, "epoch": 1.0113475177304965, "percentage": 20.45, "elapsed_time": "0:36:22", "remaining_time": "2:21:26", "throughput": 10706.57, "total_tokens": 23363584} +{"current_steps": 91, "total_steps": 440, "loss": 1.0396, "lr": 4.4906050982312664e-05, "epoch": 1.022695035460993, "percentage": 20.68, "elapsed_time": "0:36:46", "remaining_time": "2:21:03", "throughput": 10706.17, "total_tokens": 23625728} +{"current_steps": 92, "total_steps": 440, "loss": 0.967, "lr": 4.479755614805688e-05, "epoch": 1.0340425531914894, "percentage": 20.91, "elapsed_time": "0:37:11", "remaining_time": "2:20:39", "throughput": 10706.2, "total_tokens": 23887872} +{"current_steps": 93, "total_steps": 440, "loss": 1.0097, "lr": 4.4688052051315545e-05, "epoch": 1.0453900709219859, "percentage": 21.14, "elapsed_time": "0:37:35", "remaining_time": "2:20:16", "throughput": 10706.36, "total_tokens": 24150016} +{"current_steps": 94, "total_steps": 440, "loss": 0.9699, "lr": 4.457754427451389e-05, "epoch": 1.0567375886524824, "percentage": 21.36, "elapsed_time": "0:38:00", "remaining_time": "2:19:52", "throughput": 10706.25, "total_tokens": 24412160} +{"current_steps": 95, "total_steps": 440, "loss": 0.9548, "lr": 4.446603845124388e-05, "epoch": 1.0680851063829788, "percentage": 21.59, "elapsed_time": "0:38:24", "remaining_time": "2:19:29", "throughput": 10706.48, "total_tokens": 24674304} +{"current_steps": 96, "total_steps": 440, "loss": 0.9504, "lr": 4.4353540265977064e-05, "epoch": 1.0794326241134753, "percentage": 21.82, "elapsed_time": "0:38:49", "remaining_time": "2:19:05", "throughput": 10706.71, "total_tokens": 24936448} +{"current_steps": 97, "total_steps": 440, "loss": 0.9807, "lr": 4.4240055453774734e-05, "epoch": 1.0907801418439715, "percentage": 22.05, "elapsed_time": "0:39:13", "remaining_time": "2:18:42", "throughput": 10706.59, "total_tokens": 25198592} +{"current_steps": 98, "total_steps": 440, "loss": 0.9363, "lr": 4.412558979999558e-05, "epoch": 1.102127659574468, "percentage": 22.27, "elapsed_time": "0:39:37", "remaining_time": "2:18:18", "throughput": 10706.91, "total_tokens": 25460736} +{"current_steps": 99, "total_steps": 440, "loss": 0.968, "lr": 4.401014914000078e-05, "epoch": 1.1134751773049645, "percentage": 22.5, "elapsed_time": "0:40:02", "remaining_time": "2:17:55", "throughput": 10706.87, "total_tokens": 25722880} +{"current_steps": 100, "total_steps": 440, "loss": 0.9428, "lr": 4.389373935885646e-05, "epoch": 1.124822695035461, "percentage": 22.73, "elapsed_time": "0:40:26", "remaining_time": "2:17:31", "throughput": 10706.82, "total_tokens": 25985024} +{"current_steps": 101, "total_steps": 440, "loss": 0.921, "lr": 4.3776366391033746e-05, "epoch": 1.1361702127659574, "percentage": 22.95, "elapsed_time": "0:40:51", "remaining_time": "2:17:07", "throughput": 10707.09, "total_tokens": 26247168} +{"current_steps": 102, "total_steps": 440, "loss": 0.9368, "lr": 4.365803622010618e-05, "epoch": 1.147517730496454, "percentage": 23.18, "elapsed_time": "0:41:15", "remaining_time": "2:16:44", "throughput": 10707.18, "total_tokens": 26509312} +{"current_steps": 103, "total_steps": 440, "loss": 0.9424, "lr": 4.35387548784447e-05, "epoch": 1.1588652482269504, "percentage": 23.41, "elapsed_time": "0:41:40", "remaining_time": "2:16:20", "throughput": 10707.05, "total_tokens": 26771456} +{"current_steps": 104, "total_steps": 440, "loss": 0.9395, "lr": 4.341852844691012e-05, "epoch": 1.1702127659574468, "percentage": 23.64, "elapsed_time": "0:42:04", "remaining_time": "2:15:57", "throughput": 10706.99, "total_tokens": 27033600} +{"current_steps": 105, "total_steps": 440, "loss": 0.9575, "lr": 4.329736305454314e-05, "epoch": 1.1815602836879433, "percentage": 23.86, "elapsed_time": "0:42:29", "remaining_time": "2:15:33", "throughput": 10707.11, "total_tokens": 27295744} +{"current_steps": 106, "total_steps": 440, "loss": 0.9087, "lr": 4.3175264878251845e-05, "epoch": 1.1929078014184398, "percentage": 24.09, "elapsed_time": "0:42:53", "remaining_time": "2:15:09", "throughput": 10707.31, "total_tokens": 27557888} +{"current_steps": 107, "total_steps": 440, "loss": 0.9613, "lr": 4.305224014249688e-05, "epoch": 1.2042553191489362, "percentage": 24.32, "elapsed_time": "0:43:18", "remaining_time": "2:14:46", "throughput": 10706.82, "total_tokens": 27820032} +{"current_steps": 108, "total_steps": 440, "loss": 0.9336, "lr": 4.292829511897409e-05, "epoch": 1.2156028368794327, "percentage": 24.55, "elapsed_time": "0:43:42", "remaining_time": "2:14:23", "throughput": 10706.35, "total_tokens": 28082176} +{"current_steps": 109, "total_steps": 440, "loss": 0.9444, "lr": 4.280343612629479e-05, "epoch": 1.226950354609929, "percentage": 24.77, "elapsed_time": "0:44:07", "remaining_time": "2:13:59", "throughput": 10706.15, "total_tokens": 28344320} +{"current_steps": 110, "total_steps": 440, "loss": 0.9054, "lr": 4.267766952966369e-05, "epoch": 1.2382978723404254, "percentage": 25.0, "elapsed_time": "0:44:31", "remaining_time": "2:13:35", "throughput": 10706.08, "total_tokens": 28606464} +{"current_steps": 111, "total_steps": 440, "loss": 0.9391, "lr": 4.255100174055434e-05, "epoch": 1.249645390070922, "percentage": 25.23, "elapsed_time": "0:44:56", "remaining_time": "2:13:12", "throughput": 10706.21, "total_tokens": 28868608} +{"current_steps": 112, "total_steps": 440, "loss": 0.9232, "lr": 4.242343921638234e-05, "epoch": 1.2609929078014184, "percentage": 25.45, "elapsed_time": "0:45:20", "remaining_time": "2:12:48", "throughput": 10706.16, "total_tokens": 29130752} +{"current_steps": 113, "total_steps": 440, "loss": 0.9383, "lr": 4.22949884601761e-05, "epoch": 1.2723404255319148, "percentage": 25.68, "elapsed_time": "0:45:45", "remaining_time": "2:12:24", "throughput": 10706.27, "total_tokens": 29392896} +{"current_steps": 114, "total_steps": 440, "loss": 0.921, "lr": 4.2165656020245336e-05, "epoch": 1.2836879432624113, "percentage": 25.91, "elapsed_time": "0:46:09", "remaining_time": "2:12:00", "throughput": 10706.23, "total_tokens": 29655040} +{"current_steps": 115, "total_steps": 440, "loss": 0.9525, "lr": 4.2035448489847284e-05, "epoch": 1.2950354609929078, "percentage": 26.14, "elapsed_time": "0:46:34", "remaining_time": "2:11:37", "throughput": 10706.14, "total_tokens": 29917184} +{"current_steps": 116, "total_steps": 440, "loss": 0.8843, "lr": 4.1904372506850484e-05, "epoch": 1.3063829787234043, "percentage": 26.36, "elapsed_time": "0:46:58", "remaining_time": "2:11:13", "throughput": 10706.29, "total_tokens": 30179328} +{"current_steps": 117, "total_steps": 440, "loss": 0.9295, "lr": 4.1772434753396504e-05, "epoch": 1.3177304964539007, "percentage": 26.59, "elapsed_time": "0:47:23", "remaining_time": "2:10:49", "throughput": 10706.31, "total_tokens": 30441472} +{"current_steps": 118, "total_steps": 440, "loss": 0.965, "lr": 4.1639641955559205e-05, "epoch": 1.3290780141843972, "percentage": 26.82, "elapsed_time": "0:47:47", "remaining_time": "2:10:25", "throughput": 10706.39, "total_tokens": 30703616} +{"current_steps": 119, "total_steps": 440, "loss": 0.9193, "lr": 4.1506000883001875e-05, "epoch": 1.3404255319148937, "percentage": 27.05, "elapsed_time": "0:48:12", "remaining_time": "2:10:01", "throughput": 10706.29, "total_tokens": 30965760} +{"current_steps": 120, "total_steps": 440, "loss": 0.9418, "lr": 4.137151834863213e-05, "epoch": 1.3517730496453901, "percentage": 27.27, "elapsed_time": "0:48:36", "remaining_time": "2:09:37", "throughput": 10706.52, "total_tokens": 31227904} +{"current_steps": 121, "total_steps": 440, "loss": 0.9139, "lr": 4.123620120825459e-05, "epoch": 1.3631205673758866, "percentage": 27.5, "elapsed_time": "0:49:01", "remaining_time": "2:09:13", "throughput": 10706.76, "total_tokens": 31490048} +{"current_steps": 122, "total_steps": 440, "loss": 0.9378, "lr": 4.1100056360221384e-05, "epoch": 1.374468085106383, "percentage": 27.73, "elapsed_time": "0:49:25", "remaining_time": "2:08:49", "throughput": 10707.14, "total_tokens": 31752192} +{"current_steps": 123, "total_steps": 440, "loss": 0.9334, "lr": 4.096309074508046e-05, "epoch": 1.3858156028368795, "percentage": 27.95, "elapsed_time": "0:49:50", "remaining_time": "2:08:25", "throughput": 10707.13, "total_tokens": 32014336} +{"current_steps": 124, "total_steps": 440, "loss": 0.9227, "lr": 4.082531134522176e-05, "epoch": 1.397163120567376, "percentage": 28.18, "elapsed_time": "0:50:14", "remaining_time": "2:08:01", "throughput": 10707.47, "total_tokens": 32276480} +{"current_steps": 125, "total_steps": 440, "loss": 0.9232, "lr": 4.06867251845213e-05, "epoch": 1.4085106382978723, "percentage": 28.41, "elapsed_time": "0:50:38", "remaining_time": "2:07:37", "throughput": 10707.78, "total_tokens": 32538624} +{"current_steps": 126, "total_steps": 440, "loss": 0.9126, "lr": 4.054733932798306e-05, "epoch": 1.4198581560283687, "percentage": 28.64, "elapsed_time": "0:51:03", "remaining_time": "2:07:13", "throughput": 10707.86, "total_tokens": 32800768} +{"current_steps": 127, "total_steps": 440, "loss": 0.9026, "lr": 4.0407160881378824e-05, "epoch": 1.4312056737588652, "percentage": 28.86, "elapsed_time": "0:51:27", "remaining_time": "2:06:49", "throughput": 10708.1, "total_tokens": 33062912} +{"current_steps": 128, "total_steps": 440, "loss": 0.9329, "lr": 4.0266196990885955e-05, "epoch": 1.4425531914893617, "percentage": 29.09, "elapsed_time": "0:51:52", "remaining_time": "2:06:25", "throughput": 10708.13, "total_tokens": 33325056} +{"current_steps": 129, "total_steps": 440, "loss": 0.9055, "lr": 4.012445484272307e-05, "epoch": 1.4539007092198581, "percentage": 29.32, "elapsed_time": "0:52:16", "remaining_time": "2:06:01", "throughput": 10708.16, "total_tokens": 33587200} +{"current_steps": 130, "total_steps": 440, "loss": 0.9505, "lr": 3.9981941662783674e-05, "epoch": 1.4652482269503546, "percentage": 29.55, "elapsed_time": "0:52:41", "remaining_time": "2:05:37", "throughput": 10708.34, "total_tokens": 33849344} +{"current_steps": 131, "total_steps": 440, "loss": 0.9205, "lr": 3.9838664716267855e-05, "epoch": 1.476595744680851, "percentage": 29.77, "elapsed_time": "0:53:05", "remaining_time": "2:05:13", "throughput": 10708.48, "total_tokens": 34111488} +{"current_steps": 132, "total_steps": 440, "loss": 0.9757, "lr": 3.969463130731183e-05, "epoch": 1.4879432624113476, "percentage": 30.0, "elapsed_time": "0:53:29", "remaining_time": "2:04:49", "throughput": 10708.67, "total_tokens": 34373632} +{"current_steps": 133, "total_steps": 440, "loss": 0.9375, "lr": 3.954984877861565e-05, "epoch": 1.499290780141844, "percentage": 30.23, "elapsed_time": "0:53:54", "remaining_time": "2:04:25", "throughput": 10708.48, "total_tokens": 34635776} +{"current_steps": 134, "total_steps": 440, "loss": 0.9631, "lr": 3.9404324511068825e-05, "epoch": 1.5106382978723403, "percentage": 30.45, "elapsed_time": "0:54:18", "remaining_time": "2:04:01", "throughput": 10708.51, "total_tokens": 34897920} +{"current_steps": 135, "total_steps": 440, "loss": 0.9413, "lr": 3.92580659233741e-05, "epoch": 1.5219858156028367, "percentage": 30.68, "elapsed_time": "0:54:43", "remaining_time": "2:03:37", "throughput": 10708.59, "total_tokens": 35160064} +{"current_steps": 136, "total_steps": 440, "loss": 0.9436, "lr": 3.911108047166924e-05, "epoch": 1.5333333333333332, "percentage": 30.91, "elapsed_time": "0:55:07", "remaining_time": "2:03:13", "throughput": 10708.68, "total_tokens": 35422208} +{"current_steps": 137, "total_steps": 440, "loss": 0.9537, "lr": 3.8963375649146866e-05, "epoch": 1.5446808510638297, "percentage": 31.14, "elapsed_time": "0:55:32", "remaining_time": "2:02:49", "throughput": 10708.67, "total_tokens": 35684352} +{"current_steps": 138, "total_steps": 440, "loss": 0.9279, "lr": 3.881495898567257e-05, "epoch": 1.5560283687943262, "percentage": 31.36, "elapsed_time": "0:55:56", "remaining_time": "2:02:26", "throughput": 10708.61, "total_tokens": 35946496} +{"current_steps": 139, "total_steps": 440, "loss": 0.9053, "lr": 3.866583804740095e-05, "epoch": 1.5673758865248226, "percentage": 31.59, "elapsed_time": "0:56:21", "remaining_time": "2:02:01", "throughput": 10708.8, "total_tokens": 36208640} +{"current_steps": 140, "total_steps": 440, "loss": 0.9499, "lr": 3.851602043638994e-05, "epoch": 1.578723404255319, "percentage": 31.82, "elapsed_time": "0:56:45", "remaining_time": "2:01:37", "throughput": 10708.76, "total_tokens": 36470784} +{"current_steps": 141, "total_steps": 440, "loss": 0.9262, "lr": 3.8365513790213265e-05, "epoch": 1.5900709219858156, "percentage": 32.05, "elapsed_time": "0:57:10", "remaining_time": "2:01:13", "throughput": 10708.88, "total_tokens": 36732928} +{"current_steps": 142, "total_steps": 440, "loss": 0.934, "lr": 3.821432578157105e-05, "epoch": 1.601418439716312, "percentage": 32.27, "elapsed_time": "0:57:34", "remaining_time": "2:00:49", "throughput": 10709.01, "total_tokens": 36995072} +{"current_steps": 143, "total_steps": 440, "loss": 0.9588, "lr": 3.8062464117898724e-05, "epoch": 1.6127659574468085, "percentage": 32.5, "elapsed_time": "0:57:59", "remaining_time": "2:00:25", "throughput": 10708.97, "total_tokens": 37257216} +{"current_steps": 144, "total_steps": 440, "loss": 0.9616, "lr": 3.790993654097405e-05, "epoch": 1.624113475177305, "percentage": 32.73, "elapsed_time": "0:58:23", "remaining_time": "2:00:01", "throughput": 10709.05, "total_tokens": 37519360} +{"current_steps": 145, "total_steps": 440, "loss": 0.9551, "lr": 3.77567508265225e-05, "epoch": 1.6354609929078014, "percentage": 32.95, "elapsed_time": "0:58:47", "remaining_time": "1:59:37", "throughput": 10709.06, "total_tokens": 37781504} +{"current_steps": 146, "total_steps": 440, "loss": 0.9636, "lr": 3.76029147838208e-05, "epoch": 1.646808510638298, "percentage": 33.18, "elapsed_time": "0:59:12", "remaining_time": "1:59:13", "throughput": 10709.14, "total_tokens": 38043648} +{"current_steps": 147, "total_steps": 440, "loss": 0.949, "lr": 3.74484362552989e-05, "epoch": 1.6581560283687944, "percentage": 33.41, "elapsed_time": "0:59:36", "remaining_time": "1:58:49", "throughput": 10709.15, "total_tokens": 38305792} +{"current_steps": 148, "total_steps": 440, "loss": 0.9325, "lr": 3.72933231161401e-05, "epoch": 1.6695035460992909, "percentage": 33.64, "elapsed_time": "1:00:01", "remaining_time": "1:58:25", "throughput": 10709.19, "total_tokens": 38567936} +{"current_steps": 149, "total_steps": 440, "loss": 0.9175, "lr": 3.713758327387961e-05, "epoch": 1.6808510638297873, "percentage": 33.86, "elapsed_time": "1:00:25", "remaining_time": "1:58:01", "throughput": 10709.21, "total_tokens": 38830080} +{"current_steps": 150, "total_steps": 440, "loss": 0.9579, "lr": 3.6981224668001424e-05, "epoch": 1.6921985815602838, "percentage": 34.09, "elapsed_time": "1:00:50", "remaining_time": "1:57:37", "throughput": 10709.4, "total_tokens": 39092224} +{"current_steps": 151, "total_steps": 440, "loss": 0.9568, "lr": 3.682425526953359e-05, "epoch": 1.7035460992907803, "percentage": 34.32, "elapsed_time": "1:01:14", "remaining_time": "1:57:13", "throughput": 10709.38, "total_tokens": 39354368} +{"current_steps": 152, "total_steps": 440, "loss": 0.931, "lr": 3.6666683080641846e-05, "epoch": 1.7148936170212767, "percentage": 34.55, "elapsed_time": "1:01:39", "remaining_time": "1:56:49", "throughput": 10709.44, "total_tokens": 39616512} +{"current_steps": 153, "total_steps": 440, "loss": 0.9456, "lr": 3.6508516134221635e-05, "epoch": 1.7262411347517732, "percentage": 34.77, "elapsed_time": "1:02:03", "remaining_time": "1:56:24", "throughput": 10709.42, "total_tokens": 39878656} +{"current_steps": 154, "total_steps": 440, "loss": 0.9525, "lr": 3.634976249348867e-05, "epoch": 1.7375886524822695, "percentage": 35.0, "elapsed_time": "1:02:28", "remaining_time": "1:56:00", "throughput": 10709.62, "total_tokens": 40140800} +{"current_steps": 155, "total_steps": 440, "loss": 0.9254, "lr": 3.619043025156782e-05, "epoch": 1.748936170212766, "percentage": 35.23, "elapsed_time": "1:02:52", "remaining_time": "1:55:36", "throughput": 10709.84, "total_tokens": 40402944} +{"current_steps": 156, "total_steps": 440, "loss": 0.9594, "lr": 3.603052753108053e-05, "epoch": 1.7602836879432624, "percentage": 35.45, "elapsed_time": "1:03:17", "remaining_time": "1:55:12", "throughput": 10709.72, "total_tokens": 40665088} +{"current_steps": 157, "total_steps": 440, "loss": 0.9565, "lr": 3.58700624837308e-05, "epoch": 1.7716312056737589, "percentage": 35.68, "elapsed_time": "1:03:41", "remaining_time": "1:54:48", "throughput": 10709.62, "total_tokens": 40927232} +{"current_steps": 158, "total_steps": 440, "loss": 0.957, "lr": 3.5709043289889536e-05, "epoch": 1.7829787234042553, "percentage": 35.91, "elapsed_time": "1:04:05", "remaining_time": "1:54:24", "throughput": 10709.82, "total_tokens": 41189376} +{"current_steps": 159, "total_steps": 440, "loss": 0.9698, "lr": 3.554747815817756e-05, "epoch": 1.7943262411347518, "percentage": 36.14, "elapsed_time": "1:04:30", "remaining_time": "1:54:00", "throughput": 10710.0, "total_tokens": 41451520} +{"current_steps": 160, "total_steps": 440, "loss": 0.9534, "lr": 3.5385375325047166e-05, "epoch": 1.8056737588652483, "percentage": 36.36, "elapsed_time": "1:04:54", "remaining_time": "1:53:35", "throughput": 10710.02, "total_tokens": 41713664} +{"current_steps": 161, "total_steps": 440, "loss": 0.9458, "lr": 3.522274305436217e-05, "epoch": 1.8170212765957445, "percentage": 36.59, "elapsed_time": "1:05:19", "remaining_time": "1:53:11", "throughput": 10709.98, "total_tokens": 41975808} +{"current_steps": 162, "total_steps": 440, "loss": 0.9299, "lr": 3.50595896369767e-05, "epoch": 1.828368794326241, "percentage": 36.82, "elapsed_time": "1:05:43", "remaining_time": "1:52:47", "throughput": 10709.99, "total_tokens": 42237952} +{"current_steps": 163, "total_steps": 440, "loss": 0.9702, "lr": 3.4895923390312466e-05, "epoch": 1.8397163120567375, "percentage": 37.05, "elapsed_time": "1:06:08", "remaining_time": "1:52:23", "throughput": 10710.09, "total_tokens": 42500096} +{"current_steps": 164, "total_steps": 440, "loss": 0.9805, "lr": 3.4731752657934794e-05, "epoch": 1.851063829787234, "percentage": 37.27, "elapsed_time": "1:06:32", "remaining_time": "1:51:59", "throughput": 10710.21, "total_tokens": 42762240} +{"current_steps": 165, "total_steps": 440, "loss": 0.9199, "lr": 3.456708580912725e-05, "epoch": 1.8624113475177304, "percentage": 37.5, "elapsed_time": "1:06:57", "remaining_time": "1:51:35", "throughput": 10710.36, "total_tokens": 43024384} +{"current_steps": 166, "total_steps": 440, "loss": 0.9702, "lr": 3.4401931238464994e-05, "epoch": 1.8737588652482269, "percentage": 37.73, "elapsed_time": "1:07:21", "remaining_time": "1:51:10", "throughput": 10710.38, "total_tokens": 43286528} +{"current_steps": 167, "total_steps": 440, "loss": 0.9444, "lr": 3.423629736538685e-05, "epoch": 1.8851063829787233, "percentage": 37.95, "elapsed_time": "1:07:46", "remaining_time": "1:50:46", "throughput": 10710.37, "total_tokens": 43548672} +{"current_steps": 168, "total_steps": 440, "loss": 0.9559, "lr": 3.4070192633766025e-05, "epoch": 1.8964539007092198, "percentage": 38.18, "elapsed_time": "1:08:10", "remaining_time": "1:50:22", "throughput": 10710.56, "total_tokens": 43810816} +{"current_steps": 169, "total_steps": 440, "loss": 0.9547, "lr": 3.390362551147974e-05, "epoch": 1.9078014184397163, "percentage": 38.41, "elapsed_time": "1:08:34", "remaining_time": "1:49:58", "throughput": 10710.45, "total_tokens": 44072960} +{"current_steps": 170, "total_steps": 440, "loss": 0.9774, "lr": 3.3736604489977466e-05, "epoch": 1.9191489361702128, "percentage": 38.64, "elapsed_time": "1:08:59", "remaining_time": "1:49:34", "throughput": 10710.4, "total_tokens": 44335104} +{"current_steps": 171, "total_steps": 440, "loss": 0.9485, "lr": 3.356913808384807e-05, "epoch": 1.9304964539007092, "percentage": 38.86, "elapsed_time": "1:09:23", "remaining_time": "1:49:10", "throughput": 10710.29, "total_tokens": 44597248} +{"current_steps": 172, "total_steps": 440, "loss": 0.9556, "lr": 3.3401234830385756e-05, "epoch": 1.9418439716312057, "percentage": 39.09, "elapsed_time": "1:09:48", "remaining_time": "1:48:46", "throughput": 10710.25, "total_tokens": 44859392} +{"current_steps": 173, "total_steps": 440, "loss": 0.9635, "lr": 3.323290328915483e-05, "epoch": 1.9531914893617022, "percentage": 39.32, "elapsed_time": "1:10:12", "remaining_time": "1:48:22", "throughput": 10710.19, "total_tokens": 45121536} +{"current_steps": 174, "total_steps": 440, "loss": 0.9327, "lr": 3.306415204155335e-05, "epoch": 1.9645390070921986, "percentage": 39.55, "elapsed_time": "1:10:37", "remaining_time": "1:47:57", "throughput": 10710.06, "total_tokens": 45383680} +{"current_steps": 175, "total_steps": 440, "loss": 0.9274, "lr": 3.2894989690375626e-05, "epoch": 1.9758865248226951, "percentage": 39.77, "elapsed_time": "1:11:02", "remaining_time": "1:47:33", "throughput": 10709.95, "total_tokens": 45645824} +{"current_steps": 176, "total_steps": 440, "loss": 0.9402, "lr": 3.272542485937369e-05, "epoch": 1.9872340425531916, "percentage": 40.0, "elapsed_time": "1:11:26", "remaining_time": "1:47:09", "throughput": 10709.93, "total_tokens": 45907968} +{"current_steps": 177, "total_steps": 440, "loss": 0.9699, "lr": 3.255546619281765e-05, "epoch": 1.998581560283688, "percentage": 40.23, "elapsed_time": "1:11:50", "remaining_time": "1:46:45", "throughput": 10709.89, "total_tokens": 46170112} +{"current_steps": 178, "total_steps": 440, "loss": 0.7485, "lr": 3.2385122355055005e-05, "epoch": 2.0, "percentage": 40.45, "elapsed_time": "1:11:53", "remaining_time": "1:45:49", "throughput": 10710.03, "total_tokens": 46202880} +{"current_steps": 179, "total_steps": 440, "loss": 0.5128, "lr": 3.221440203006897e-05, "epoch": 2.0113475177304965, "percentage": 40.68, "elapsed_time": "1:12:18", "remaining_time": "1:45:26", "throughput": 10709.82, "total_tokens": 46465024} +{"current_steps": 180, "total_steps": 440, "loss": 0.494, "lr": 3.2043313921035743e-05, "epoch": 2.022695035460993, "percentage": 40.91, "elapsed_time": "1:12:43", "remaining_time": "1:45:02", "throughput": 10709.84, "total_tokens": 46727168} +{"current_steps": 181, "total_steps": 440, "loss": 0.4649, "lr": 3.1871866749880846e-05, "epoch": 2.0340425531914894, "percentage": 41.14, "elapsed_time": "1:13:07", "remaining_time": "1:44:38", "throughput": 10709.8, "total_tokens": 46989312} +{"current_steps": 182, "total_steps": 440, "loss": 0.4609, "lr": 3.170006925683448e-05, "epoch": 2.045390070921986, "percentage": 41.36, "elapsed_time": "1:13:31", "remaining_time": "1:44:14", "throughput": 10709.81, "total_tokens": 47251456} +{"current_steps": 183, "total_steps": 440, "loss": 0.4303, "lr": 3.152793019998594e-05, "epoch": 2.0567375886524824, "percentage": 41.59, "elapsed_time": "1:13:56", "remaining_time": "1:43:50", "throughput": 10709.91, "total_tokens": 47513600} +{"current_steps": 184, "total_steps": 440, "loss": 0.4343, "lr": 3.135545835483718e-05, "epoch": 2.068085106382979, "percentage": 41.82, "elapsed_time": "1:14:20", "remaining_time": "1:43:26", "throughput": 10709.95, "total_tokens": 47775744} +{"current_steps": 185, "total_steps": 440, "loss": 0.4224, "lr": 3.118266251385539e-05, "epoch": 2.0794326241134753, "percentage": 42.05, "elapsed_time": "1:14:45", "remaining_time": "1:43:02", "throughput": 10709.94, "total_tokens": 48037888} +{"current_steps": 186, "total_steps": 440, "loss": 0.4173, "lr": 3.100955148602481e-05, "epoch": 2.0907801418439718, "percentage": 42.27, "elapsed_time": "1:15:09", "remaining_time": "1:42:38", "throughput": 10709.92, "total_tokens": 48300032} +{"current_steps": 187, "total_steps": 440, "loss": 0.3962, "lr": 3.083613409639764e-05, "epoch": 2.1021276595744682, "percentage": 42.5, "elapsed_time": "1:15:34", "remaining_time": "1:42:14", "throughput": 10710.04, "total_tokens": 48562176} +{"current_steps": 188, "total_steps": 440, "loss": 0.393, "lr": 3.0662419185644115e-05, "epoch": 2.1134751773049647, "percentage": 42.73, "elapsed_time": "1:15:58", "remaining_time": "1:41:50", "throughput": 10710.14, "total_tokens": 48824320} +{"current_steps": 189, "total_steps": 440, "loss": 0.3826, "lr": 3.0488415609601862e-05, "epoch": 2.124822695035461, "percentage": 42.95, "elapsed_time": "1:16:23", "remaining_time": "1:41:26", "throughput": 10710.19, "total_tokens": 49086464} +{"current_steps": 190, "total_steps": 440, "loss": 0.3961, "lr": 3.0314132238824415e-05, "epoch": 2.1361702127659576, "percentage": 43.18, "elapsed_time": "1:16:47", "remaining_time": "1:41:02", "throughput": 10710.13, "total_tokens": 49348608} +{"current_steps": 191, "total_steps": 440, "loss": 0.3759, "lr": 3.013957795812902e-05, "epoch": 2.147517730496454, "percentage": 43.41, "elapsed_time": "1:17:12", "remaining_time": "1:40:38", "throughput": 10710.16, "total_tokens": 49610752} +{"current_steps": 192, "total_steps": 440, "loss": 0.3716, "lr": 2.996476166614364e-05, "epoch": 2.1588652482269506, "percentage": 43.64, "elapsed_time": "1:17:36", "remaining_time": "1:40:14", "throughput": 10709.99, "total_tokens": 49872896} +{"current_steps": 193, "total_steps": 440, "loss": 0.3875, "lr": 2.9789692274853388e-05, "epoch": 2.1702127659574466, "percentage": 43.86, "elapsed_time": "1:18:01", "remaining_time": "1:39:50", "throughput": 10710.06, "total_tokens": 50135040} +{"current_steps": 194, "total_steps": 440, "loss": 0.374, "lr": 2.9614378709146133e-05, "epoch": 2.181560283687943, "percentage": 44.09, "elapsed_time": "1:18:25", "remaining_time": "1:39:26", "throughput": 10710.06, "total_tokens": 50397184} +{"current_steps": 195, "total_steps": 440, "loss": 0.3694, "lr": 2.943882990635759e-05, "epoch": 2.1929078014184396, "percentage": 44.32, "elapsed_time": "1:18:50", "remaining_time": "1:39:02", "throughput": 10710.04, "total_tokens": 50659328} +{"current_steps": 196, "total_steps": 440, "loss": 0.3901, "lr": 2.92630548158156e-05, "epoch": 2.204255319148936, "percentage": 44.55, "elapsed_time": "1:19:14", "remaining_time": "1:38:38", "throughput": 10710.03, "total_tokens": 50921472} +{"current_steps": 197, "total_steps": 440, "loss": 0.3825, "lr": 2.9087062398384e-05, "epoch": 2.2156028368794325, "percentage": 44.77, "elapsed_time": "1:19:39", "remaining_time": "1:38:14", "throughput": 10710.1, "total_tokens": 51183616} +{"current_steps": 198, "total_steps": 440, "loss": 0.4064, "lr": 2.8910861626005776e-05, "epoch": 2.226950354609929, "percentage": 45.0, "elapsed_time": "1:20:03", "remaining_time": "1:37:50", "throughput": 10710.15, "total_tokens": 51445760} +{"current_steps": 199, "total_steps": 440, "loss": 0.4096, "lr": 2.873446148124563e-05, "epoch": 2.2382978723404254, "percentage": 45.23, "elapsed_time": "1:20:28", "remaining_time": "1:37:27", "throughput": 10709.21, "total_tokens": 51707904} +{"current_steps": 200, "total_steps": 440, "loss": 0.3814, "lr": 2.8557870956832132e-05, "epoch": 2.249645390070922, "percentage": 45.45, "elapsed_time": "1:20:53", "remaining_time": "1:37:03", "throughput": 10708.16, "total_tokens": 51970048} +{"current_steps": 201, "total_steps": 440, "loss": 0.3932, "lr": 2.8381099055199222e-05, "epoch": 2.2609929078014184, "percentage": 45.68, "elapsed_time": "1:21:17", "remaining_time": "1:36:39", "throughput": 10708.16, "total_tokens": 52232192} +{"current_steps": 202, "total_steps": 440, "loss": 0.3613, "lr": 2.8204154788027325e-05, "epoch": 2.272340425531915, "percentage": 45.91, "elapsed_time": "1:21:42", "remaining_time": "1:36:15", "throughput": 10708.26, "total_tokens": 52494336} +{"current_steps": 203, "total_steps": 440, "loss": 0.359, "lr": 2.8027047175783873e-05, "epoch": 2.2836879432624113, "percentage": 46.14, "elapsed_time": "1:22:06", "remaining_time": "1:35:51", "throughput": 10708.2, "total_tokens": 52756480} +{"current_steps": 204, "total_steps": 440, "loss": 0.3897, "lr": 2.7849785247263515e-05, "epoch": 2.295035460992908, "percentage": 46.36, "elapsed_time": "1:22:31", "remaining_time": "1:35:27", "throughput": 10708.2, "total_tokens": 53018624} +{"current_steps": 205, "total_steps": 440, "loss": 0.3945, "lr": 2.767237803912783e-05, "epoch": 2.3063829787234043, "percentage": 46.59, "elapsed_time": "1:22:56", "remaining_time": "1:35:04", "throughput": 10707.32, "total_tokens": 53280768} +{"current_steps": 206, "total_steps": 440, "loss": 0.3682, "lr": 2.7494834595444568e-05, "epoch": 2.3177304964539007, "percentage": 46.82, "elapsed_time": "1:23:20", "remaining_time": "1:34:40", "throughput": 10707.28, "total_tokens": 53542912} +{"current_steps": 207, "total_steps": 440, "loss": 0.3686, "lr": 2.731716396722672e-05, "epoch": 2.329078014184397, "percentage": 47.05, "elapsed_time": "1:23:45", "remaining_time": "1:34:16", "throughput": 10707.42, "total_tokens": 53805056} +{"current_steps": 208, "total_steps": 440, "loss": 0.3683, "lr": 2.7139375211970996e-05, "epoch": 2.3404255319148937, "percentage": 47.27, "elapsed_time": "1:24:09", "remaining_time": "1:33:52", "throughput": 10707.32, "total_tokens": 54067200} +{"current_steps": 209, "total_steps": 440, "loss": 0.3656, "lr": 2.6961477393196126e-05, "epoch": 2.35177304964539, "percentage": 47.5, "elapsed_time": "1:24:33", "remaining_time": "1:33:28", "throughput": 10707.41, "total_tokens": 54329344} +{"current_steps": 210, "total_steps": 440, "loss": 0.3659, "lr": 2.6783479579980807e-05, "epoch": 2.3631205673758866, "percentage": 47.73, "elapsed_time": "1:24:58", "remaining_time": "1:33:03", "throughput": 10707.61, "total_tokens": 54591488} +{"current_steps": 211, "total_steps": 440, "loss": 0.3581, "lr": 2.6605390846501377e-05, "epoch": 2.374468085106383, "percentage": 47.95, "elapsed_time": "1:25:22", "remaining_time": "1:32:39", "throughput": 10707.57, "total_tokens": 54853632} +{"current_steps": 212, "total_steps": 440, "loss": 0.3693, "lr": 2.6427220271569203e-05, "epoch": 2.3858156028368795, "percentage": 48.18, "elapsed_time": "1:25:47", "remaining_time": "1:32:15", "throughput": 10707.59, "total_tokens": 55115776} +{"current_steps": 213, "total_steps": 440, "loss": 0.3746, "lr": 2.624897693816785e-05, "epoch": 2.397163120567376, "percentage": 48.41, "elapsed_time": "1:26:11", "remaining_time": "1:31:51", "throughput": 10707.66, "total_tokens": 55377920} +{"current_steps": 214, "total_steps": 440, "loss": 0.3741, "lr": 2.6070669932990067e-05, "epoch": 2.4085106382978725, "percentage": 48.64, "elapsed_time": "1:26:36", "remaining_time": "1:31:27", "throughput": 10707.6, "total_tokens": 55640064} +{"current_steps": 215, "total_steps": 440, "loss": 0.3583, "lr": 2.5892308345974515e-05, "epoch": 2.419858156028369, "percentage": 48.86, "elapsed_time": "1:27:00", "remaining_time": "1:31:03", "throughput": 10707.64, "total_tokens": 55902208} +{"current_steps": 216, "total_steps": 440, "loss": 0.3622, "lr": 2.5713901269842404e-05, "epoch": 2.4312056737588654, "percentage": 49.09, "elapsed_time": "1:27:25", "remaining_time": "1:30:39", "throughput": 10707.64, "total_tokens": 56164352} +{"current_steps": 217, "total_steps": 440, "loss": 0.3588, "lr": 2.5535457799633955e-05, "epoch": 2.4425531914893615, "percentage": 49.32, "elapsed_time": "1:27:49", "remaining_time": "1:30:15", "throughput": 10707.73, "total_tokens": 56426496} +{"current_steps": 218, "total_steps": 440, "loss": 0.3614, "lr": 2.5356987032244683e-05, "epoch": 2.453900709219858, "percentage": 49.55, "elapsed_time": "1:28:14", "remaining_time": "1:29:51", "throughput": 10707.73, "total_tokens": 56688640} +{"current_steps": 219, "total_steps": 440, "loss": 0.3727, "lr": 2.5178498065961736e-05, "epoch": 2.4652482269503544, "percentage": 49.77, "elapsed_time": "1:28:38", "remaining_time": "1:29:27", "throughput": 10707.76, "total_tokens": 56950784} +{"current_steps": 220, "total_steps": 440, "loss": 0.3595, "lr": 2.5e-05, "epoch": 2.476595744680851, "percentage": 50.0, "elapsed_time": "1:29:03", "remaining_time": "1:29:03", "throughput": 10707.74, "total_tokens": 57212928} +{"current_steps": 221, "total_steps": 440, "loss": 0.3475, "lr": 2.4821501934038266e-05, "epoch": 2.4879432624113473, "percentage": 50.23, "elapsed_time": "1:29:27", "remaining_time": "1:28:39", "throughput": 10707.75, "total_tokens": 57475072} +{"current_steps": 222, "total_steps": 440, "loss": 0.373, "lr": 2.4643012967755326e-05, "epoch": 2.499290780141844, "percentage": 50.45, "elapsed_time": "1:29:52", "remaining_time": "1:28:14", "throughput": 10707.74, "total_tokens": 57737216} +{"current_steps": 223, "total_steps": 440, "loss": 0.3709, "lr": 2.446454220036605e-05, "epoch": 2.5106382978723403, "percentage": 50.68, "elapsed_time": "1:30:16", "remaining_time": "1:27:50", "throughput": 10707.72, "total_tokens": 57999360} +{"current_steps": 224, "total_steps": 440, "loss": 0.3616, "lr": 2.42860987301576e-05, "epoch": 2.5219858156028367, "percentage": 50.91, "elapsed_time": "1:30:41", "remaining_time": "1:27:26", "throughput": 10707.73, "total_tokens": 58261504} +{"current_steps": 225, "total_steps": 440, "loss": 0.3873, "lr": 2.410769165402549e-05, "epoch": 2.533333333333333, "percentage": 51.14, "elapsed_time": "1:31:05", "remaining_time": "1:27:02", "throughput": 10707.66, "total_tokens": 58523648} +{"current_steps": 226, "total_steps": 440, "loss": 0.3739, "lr": 2.3929330067009942e-05, "epoch": 2.5446808510638297, "percentage": 51.36, "elapsed_time": "1:31:30", "remaining_time": "1:26:38", "throughput": 10707.75, "total_tokens": 58785792} +{"current_steps": 227, "total_steps": 440, "loss": 0.3567, "lr": 2.3751023061832158e-05, "epoch": 2.556028368794326, "percentage": 51.59, "elapsed_time": "1:31:54", "remaining_time": "1:26:14", "throughput": 10707.83, "total_tokens": 59047936} +{"current_steps": 228, "total_steps": 440, "loss": 0.3902, "lr": 2.35727797284308e-05, "epoch": 2.5673758865248226, "percentage": 51.82, "elapsed_time": "1:32:18", "remaining_time": "1:25:50", "throughput": 10707.84, "total_tokens": 59310080} +{"current_steps": 229, "total_steps": 440, "loss": 0.3814, "lr": 2.339460915349862e-05, "epoch": 2.578723404255319, "percentage": 52.05, "elapsed_time": "1:32:43", "remaining_time": "1:25:26", "throughput": 10707.8, "total_tokens": 59572224} +{"current_steps": 230, "total_steps": 440, "loss": 0.3786, "lr": 2.3216520420019195e-05, "epoch": 2.5900709219858156, "percentage": 52.27, "elapsed_time": "1:33:07", "remaining_time": "1:25:02", "throughput": 10707.79, "total_tokens": 59834368} +{"current_steps": 231, "total_steps": 440, "loss": 0.3773, "lr": 2.303852260680388e-05, "epoch": 2.601418439716312, "percentage": 52.5, "elapsed_time": "1:33:32", "remaining_time": "1:24:37", "throughput": 10707.81, "total_tokens": 60096512} +{"current_steps": 232, "total_steps": 440, "loss": 0.3892, "lr": 2.2860624788029013e-05, "epoch": 2.6127659574468085, "percentage": 52.73, "elapsed_time": "1:33:56", "remaining_time": "1:24:13", "throughput": 10707.82, "total_tokens": 60358656} +{"current_steps": 233, "total_steps": 440, "loss": 0.3784, "lr": 2.268283603277328e-05, "epoch": 2.624113475177305, "percentage": 52.95, "elapsed_time": "1:34:21", "remaining_time": "1:23:49", "throughput": 10707.85, "total_tokens": 60620800} +{"current_steps": 234, "total_steps": 440, "loss": 0.3617, "lr": 2.250516540455543e-05, "epoch": 2.6354609929078014, "percentage": 53.18, "elapsed_time": "1:34:45", "remaining_time": "1:23:25", "throughput": 10707.83, "total_tokens": 60882944} +{"current_steps": 235, "total_steps": 440, "loss": 0.3681, "lr": 2.2327621960872187e-05, "epoch": 2.646808510638298, "percentage": 53.41, "elapsed_time": "1:35:10", "remaining_time": "1:23:01", "throughput": 10707.8, "total_tokens": 61145088} +{"current_steps": 236, "total_steps": 440, "loss": 0.3684, "lr": 2.2150214752736488e-05, "epoch": 2.6581560283687944, "percentage": 53.64, "elapsed_time": "1:35:34", "remaining_time": "1:22:37", "throughput": 10707.69, "total_tokens": 61407232} +{"current_steps": 237, "total_steps": 440, "loss": 0.3544, "lr": 2.197295282421613e-05, "epoch": 2.669503546099291, "percentage": 53.86, "elapsed_time": "1:35:59", "remaining_time": "1:22:13", "throughput": 10707.63, "total_tokens": 61669376} +{"current_steps": 238, "total_steps": 440, "loss": 0.3669, "lr": 2.179584521197268e-05, "epoch": 2.6808510638297873, "percentage": 54.09, "elapsed_time": "1:36:23", "remaining_time": "1:21:49", "throughput": 10707.55, "total_tokens": 61931520} +{"current_steps": 239, "total_steps": 440, "loss": 0.3786, "lr": 2.1618900944800777e-05, "epoch": 2.692198581560284, "percentage": 54.32, "elapsed_time": "1:36:48", "remaining_time": "1:21:24", "throughput": 10707.53, "total_tokens": 62193664} +{"current_steps": 240, "total_steps": 440, "loss": 0.3669, "lr": 2.1442129043167874e-05, "epoch": 2.7035460992907803, "percentage": 54.55, "elapsed_time": "1:37:12", "remaining_time": "1:21:00", "throughput": 10707.54, "total_tokens": 62455808} +{"current_steps": 241, "total_steps": 440, "loss": 0.3665, "lr": 2.1265538518754374e-05, "epoch": 2.7148936170212767, "percentage": 54.77, "elapsed_time": "1:37:37", "remaining_time": "1:20:36", "throughput": 10707.58, "total_tokens": 62717952} +{"current_steps": 242, "total_steps": 440, "loss": 0.392, "lr": 2.1089138373994223e-05, "epoch": 2.726241134751773, "percentage": 55.0, "elapsed_time": "1:38:01", "remaining_time": "1:20:12", "throughput": 10707.54, "total_tokens": 62980096} +{"current_steps": 243, "total_steps": 440, "loss": 0.372, "lr": 2.0912937601616005e-05, "epoch": 2.7375886524822697, "percentage": 55.23, "elapsed_time": "1:38:26", "remaining_time": "1:19:48", "throughput": 10707.62, "total_tokens": 63242240} +{"current_steps": 244, "total_steps": 440, "loss": 0.3648, "lr": 2.0736945184184405e-05, "epoch": 2.748936170212766, "percentage": 55.45, "elapsed_time": "1:38:50", "remaining_time": "1:19:24", "throughput": 10707.62, "total_tokens": 63504384} +{"current_steps": 245, "total_steps": 440, "loss": 0.3875, "lr": 2.0561170093642423e-05, "epoch": 2.7602836879432626, "percentage": 55.68, "elapsed_time": "1:39:15", "remaining_time": "1:18:59", "throughput": 10707.52, "total_tokens": 63766528} +{"current_steps": 246, "total_steps": 440, "loss": 0.3734, "lr": 2.038562129085387e-05, "epoch": 2.771631205673759, "percentage": 55.91, "elapsed_time": "1:39:39", "remaining_time": "1:18:35", "throughput": 10707.54, "total_tokens": 64028672} +{"current_steps": 247, "total_steps": 440, "loss": 0.3593, "lr": 2.0210307725146615e-05, "epoch": 2.7829787234042556, "percentage": 56.14, "elapsed_time": "1:40:04", "remaining_time": "1:18:11", "throughput": 10707.5, "total_tokens": 64290816} +{"current_steps": 248, "total_steps": 440, "loss": 0.3844, "lr": 2.003523833385637e-05, "epoch": 2.794326241134752, "percentage": 56.36, "elapsed_time": "1:40:28", "remaining_time": "1:17:47", "throughput": 10707.51, "total_tokens": 64552960} +{"current_steps": 249, "total_steps": 440, "loss": 0.3801, "lr": 1.9860422041870987e-05, "epoch": 2.8056737588652485, "percentage": 56.59, "elapsed_time": "1:40:53", "remaining_time": "1:17:23", "throughput": 10707.52, "total_tokens": 64815104} +{"current_steps": 250, "total_steps": 440, "loss": 0.3849, "lr": 1.9685867761175584e-05, "epoch": 2.8170212765957445, "percentage": 56.82, "elapsed_time": "1:41:17", "remaining_time": "1:16:59", "throughput": 10707.48, "total_tokens": 65077248} +{"current_steps": 251, "total_steps": 440, "loss": 0.3739, "lr": 1.9511584390398147e-05, "epoch": 2.828368794326241, "percentage": 57.05, "elapsed_time": "1:41:42", "remaining_time": "1:16:34", "throughput": 10707.5, "total_tokens": 65339392} +{"current_steps": 252, "total_steps": 440, "loss": 0.366, "lr": 1.9337580814355888e-05, "epoch": 2.8397163120567375, "percentage": 57.27, "elapsed_time": "1:42:06", "remaining_time": "1:16:10", "throughput": 10707.36, "total_tokens": 65601536} +{"current_steps": 253, "total_steps": 440, "loss": 0.3629, "lr": 1.9163865903602374e-05, "epoch": 2.851063829787234, "percentage": 57.5, "elapsed_time": "1:42:31", "remaining_time": "1:15:46", "throughput": 10707.33, "total_tokens": 65863680} +{"current_steps": 254, "total_steps": 440, "loss": 0.3814, "lr": 1.899044851397519e-05, "epoch": 2.8624113475177304, "percentage": 57.73, "elapsed_time": "1:42:55", "remaining_time": "1:15:22", "throughput": 10707.33, "total_tokens": 66125824} +{"current_steps": 255, "total_steps": 440, "loss": 0.3775, "lr": 1.881733748614461e-05, "epoch": 2.873758865248227, "percentage": 57.95, "elapsed_time": "1:43:20", "remaining_time": "1:14:58", "throughput": 10707.38, "total_tokens": 66387968} +{"current_steps": 256, "total_steps": 440, "loss": 0.3783, "lr": 1.8644541645162834e-05, "epoch": 2.8851063829787233, "percentage": 58.18, "elapsed_time": "1:43:44", "remaining_time": "1:14:33", "throughput": 10707.41, "total_tokens": 66650112} +{"current_steps": 257, "total_steps": 440, "loss": 0.35, "lr": 1.8472069800014068e-05, "epoch": 2.89645390070922, "percentage": 58.41, "elapsed_time": "1:44:09", "remaining_time": "1:14:09", "throughput": 10707.37, "total_tokens": 66912256} +{"current_steps": 258, "total_steps": 440, "loss": 0.3742, "lr": 1.8299930743165535e-05, "epoch": 2.9078014184397163, "percentage": 58.64, "elapsed_time": "1:44:33", "remaining_time": "1:13:45", "throughput": 10707.32, "total_tokens": 67174400} +{"current_steps": 259, "total_steps": 440, "loss": 0.3652, "lr": 1.8128133250119157e-05, "epoch": 2.9191489361702128, "percentage": 58.86, "elapsed_time": "1:44:58", "remaining_time": "1:13:21", "throughput": 10707.19, "total_tokens": 67436544} +{"current_steps": 260, "total_steps": 440, "loss": 0.3832, "lr": 1.795668607896426e-05, "epoch": 2.9304964539007092, "percentage": 59.09, "elapsed_time": "1:45:22", "remaining_time": "1:12:57", "throughput": 10707.1, "total_tokens": 67698688} +{"current_steps": 261, "total_steps": 440, "loss": 0.3807, "lr": 1.778559796993104e-05, "epoch": 2.9418439716312057, "percentage": 59.32, "elapsed_time": "1:45:47", "remaining_time": "1:12:33", "throughput": 10707.06, "total_tokens": 67960832} +{"current_steps": 262, "total_steps": 440, "loss": 0.3799, "lr": 1.7614877644945e-05, "epoch": 2.953191489361702, "percentage": 59.55, "elapsed_time": "1:46:11", "remaining_time": "1:12:08", "throughput": 10707.04, "total_tokens": 68222976} +{"current_steps": 263, "total_steps": 440, "loss": 0.3412, "lr": 1.7444533807182357e-05, "epoch": 2.9645390070921986, "percentage": 59.77, "elapsed_time": "1:46:36", "remaining_time": "1:11:44", "throughput": 10706.99, "total_tokens": 68485120} +{"current_steps": 264, "total_steps": 440, "loss": 0.3666, "lr": 1.7274575140626318e-05, "epoch": 2.975886524822695, "percentage": 60.0, "elapsed_time": "1:47:00", "remaining_time": "1:11:20", "throughput": 10706.98, "total_tokens": 68747264} +{"current_steps": 265, "total_steps": 440, "loss": 0.3787, "lr": 1.710501030962438e-05, "epoch": 2.9872340425531916, "percentage": 60.23, "elapsed_time": "1:47:25", "remaining_time": "1:10:56", "throughput": 10706.96, "total_tokens": 69009408} +{"current_steps": 266, "total_steps": 440, "loss": 0.3623, "lr": 1.6935847958446657e-05, "epoch": 2.998581560283688, "percentage": 60.45, "elapsed_time": "1:47:49", "remaining_time": "1:10:32", "throughput": 10706.94, "total_tokens": 69271552} +{"current_steps": 267, "total_steps": 440, "loss": 0.2925, "lr": 1.6767096710845174e-05, "epoch": 3.0, "percentage": 60.68, "elapsed_time": "1:47:52", "remaining_time": "1:09:53", "throughput": 10707.04, "total_tokens": 69304320} +{"current_steps": 268, "total_steps": 440, "loss": 0.1334, "lr": 1.6598765169614243e-05, "epoch": 3.0113475177304965, "percentage": 60.91, "elapsed_time": "1:48:17", "remaining_time": "1:09:29", "throughput": 10706.91, "total_tokens": 69566464} +{"current_steps": 269, "total_steps": 440, "loss": 0.1248, "lr": 1.643086191615194e-05, "epoch": 3.022695035460993, "percentage": 61.14, "elapsed_time": "1:48:41", "remaining_time": "1:09:05", "throughput": 10706.86, "total_tokens": 69828608} +{"current_steps": 270, "total_steps": 440, "loss": 0.1212, "lr": 1.6263395510022543e-05, "epoch": 3.0340425531914894, "percentage": 61.36, "elapsed_time": "1:49:06", "remaining_time": "1:08:41", "throughput": 10706.93, "total_tokens": 70090752} +{"current_steps": 271, "total_steps": 440, "loss": 0.1026, "lr": 1.6096374488520265e-05, "epoch": 3.045390070921986, "percentage": 61.59, "elapsed_time": "1:49:30", "remaining_time": "1:08:17", "throughput": 10706.97, "total_tokens": 70352896} +{"current_steps": 272, "total_steps": 440, "loss": 0.1147, "lr": 1.5929807366233977e-05, "epoch": 3.0567375886524824, "percentage": 61.82, "elapsed_time": "1:49:55", "remaining_time": "1:07:53", "throughput": 10706.98, "total_tokens": 70615040} +{"current_steps": 273, "total_steps": 440, "loss": 0.1112, "lr": 1.5763702634613152e-05, "epoch": 3.068085106382979, "percentage": 62.05, "elapsed_time": "1:50:19", "remaining_time": "1:07:29", "throughput": 10707.01, "total_tokens": 70877184} +{"current_steps": 274, "total_steps": 440, "loss": 0.1142, "lr": 1.559806876153501e-05, "epoch": 3.0794326241134753, "percentage": 62.27, "elapsed_time": "1:50:44", "remaining_time": "1:07:05", "throughput": 10707.01, "total_tokens": 71139328} +{"current_steps": 275, "total_steps": 440, "loss": 0.1094, "lr": 1.5432914190872757e-05, "epoch": 3.0907801418439718, "percentage": 62.5, "elapsed_time": "1:51:08", "remaining_time": "1:06:41", "throughput": 10707.03, "total_tokens": 71401472} +{"current_steps": 276, "total_steps": 440, "loss": 0.1024, "lr": 1.5268247342065215e-05, "epoch": 3.1021276595744682, "percentage": 62.73, "elapsed_time": "1:51:33", "remaining_time": "1:06:17", "throughput": 10707.05, "total_tokens": 71663616} +{"current_steps": 277, "total_steps": 440, "loss": 0.1023, "lr": 1.5104076609687545e-05, "epoch": 3.1134751773049647, "percentage": 62.95, "elapsed_time": "1:51:57", "remaining_time": "1:05:52", "throughput": 10707.1, "total_tokens": 71925760} +{"current_steps": 278, "total_steps": 440, "loss": 0.0978, "lr": 1.4940410363023306e-05, "epoch": 3.124822695035461, "percentage": 63.18, "elapsed_time": "1:52:22", "remaining_time": "1:05:28", "throughput": 10707.07, "total_tokens": 72187904} +{"current_steps": 279, "total_steps": 440, "loss": 0.099, "lr": 1.4777256945637834e-05, "epoch": 3.1361702127659576, "percentage": 63.41, "elapsed_time": "1:52:46", "remaining_time": "1:05:04", "throughput": 10707.04, "total_tokens": 72450048} +{"current_steps": 280, "total_steps": 440, "loss": 0.0956, "lr": 1.4614624674952842e-05, "epoch": 3.147517730496454, "percentage": 63.64, "elapsed_time": "1:53:11", "remaining_time": "1:04:40", "throughput": 10707.04, "total_tokens": 72712192} +{"current_steps": 281, "total_steps": 440, "loss": 0.0998, "lr": 1.4452521841822436e-05, "epoch": 3.1588652482269506, "percentage": 63.86, "elapsed_time": "1:53:35", "remaining_time": "1:04:16", "throughput": 10707.02, "total_tokens": 72974336} +{"current_steps": 282, "total_steps": 440, "loss": 0.0945, "lr": 1.4290956710110475e-05, "epoch": 3.1702127659574466, "percentage": 64.09, "elapsed_time": "1:54:00", "remaining_time": "1:03:52", "throughput": 10706.98, "total_tokens": 73236480} +{"current_steps": 283, "total_steps": 440, "loss": 0.0988, "lr": 1.4129937516269203e-05, "epoch": 3.181560283687943, "percentage": 64.32, "elapsed_time": "1:54:24", "remaining_time": "1:03:28", "throughput": 10707.07, "total_tokens": 73498624} +{"current_steps": 284, "total_steps": 440, "loss": 0.0979, "lr": 1.3969472468919461e-05, "epoch": 3.1929078014184396, "percentage": 64.55, "elapsed_time": "1:54:48", "remaining_time": "1:03:04", "throughput": 10707.13, "total_tokens": 73760768} +{"current_steps": 285, "total_steps": 440, "loss": 0.0937, "lr": 1.3809569748432189e-05, "epoch": 3.204255319148936, "percentage": 64.77, "elapsed_time": "1:55:13", "remaining_time": "1:02:39", "throughput": 10707.09, "total_tokens": 74022912} +{"current_steps": 286, "total_steps": 440, "loss": 0.0895, "lr": 1.3650237506511331e-05, "epoch": 3.2156028368794325, "percentage": 65.0, "elapsed_time": "1:55:37", "remaining_time": "1:02:15", "throughput": 10707.04, "total_tokens": 74285056} +{"current_steps": 287, "total_steps": 440, "loss": 0.0924, "lr": 1.3491483865778365e-05, "epoch": 3.226950354609929, "percentage": 65.23, "elapsed_time": "1:56:02", "remaining_time": "1:01:51", "throughput": 10707.04, "total_tokens": 74547200} +{"current_steps": 288, "total_steps": 440, "loss": 0.0987, "lr": 1.3333316919358157e-05, "epoch": 3.2382978723404254, "percentage": 65.45, "elapsed_time": "1:56:26", "remaining_time": "1:01:27", "throughput": 10707.15, "total_tokens": 74809344} +{"current_steps": 289, "total_steps": 440, "loss": 0.0841, "lr": 1.3175744730466408e-05, "epoch": 3.249645390070922, "percentage": 65.68, "elapsed_time": "1:56:51", "remaining_time": "1:01:03", "throughput": 10707.15, "total_tokens": 75071488} +{"current_steps": 290, "total_steps": 440, "loss": 0.0931, "lr": 1.301877533199859e-05, "epoch": 3.2609929078014184, "percentage": 65.91, "elapsed_time": "1:57:15", "remaining_time": "1:00:39", "throughput": 10707.18, "total_tokens": 75333632} +{"current_steps": 291, "total_steps": 440, "loss": 0.0918, "lr": 1.2862416726120396e-05, "epoch": 3.272340425531915, "percentage": 66.14, "elapsed_time": "1:57:40", "remaining_time": "1:00:15", "throughput": 10707.14, "total_tokens": 75595776} +{"current_steps": 292, "total_steps": 440, "loss": 0.0893, "lr": 1.2706676883859903e-05, "epoch": 3.2836879432624113, "percentage": 66.36, "elapsed_time": "1:58:04", "remaining_time": "0:59:50", "throughput": 10707.11, "total_tokens": 75857920} +{"current_steps": 293, "total_steps": 440, "loss": 0.0886, "lr": 1.2551563744701109e-05, "epoch": 3.295035460992908, "percentage": 66.59, "elapsed_time": "1:58:29", "remaining_time": "0:59:26", "throughput": 10707.11, "total_tokens": 76120064} +{"current_steps": 294, "total_steps": 440, "loss": 0.0883, "lr": 1.2397085216179208e-05, "epoch": 3.3063829787234043, "percentage": 66.82, "elapsed_time": "1:58:53", "remaining_time": "0:59:02", "throughput": 10707.15, "total_tokens": 76382208} +{"current_steps": 295, "total_steps": 440, "loss": 0.0882, "lr": 1.2243249173477513e-05, "epoch": 3.3177304964539007, "percentage": 67.05, "elapsed_time": "1:59:18", "remaining_time": "0:58:38", "throughput": 10707.18, "total_tokens": 76644352} +{"current_steps": 296, "total_steps": 440, "loss": 0.0885, "lr": 1.2090063459025955e-05, "epoch": 3.329078014184397, "percentage": 67.27, "elapsed_time": "1:59:42", "remaining_time": "0:58:14", "throughput": 10707.17, "total_tokens": 76906496} +{"current_steps": 297, "total_steps": 440, "loss": 0.0933, "lr": 1.1937535882101281e-05, "epoch": 3.3404255319148937, "percentage": 67.5, "elapsed_time": "2:00:07", "remaining_time": "0:57:50", "throughput": 10707.27, "total_tokens": 77168640} +{"current_steps": 298, "total_steps": 440, "loss": 0.0943, "lr": 1.1785674218428952e-05, "epoch": 3.35177304964539, "percentage": 67.73, "elapsed_time": "2:00:31", "remaining_time": "0:57:25", "throughput": 10707.29, "total_tokens": 77430784} +{"current_steps": 299, "total_steps": 440, "loss": 0.0883, "lr": 1.163448620978674e-05, "epoch": 3.3631205673758866, "percentage": 67.95, "elapsed_time": "2:00:56", "remaining_time": "0:57:01", "throughput": 10707.34, "total_tokens": 77692928} +{"current_steps": 300, "total_steps": 440, "loss": 0.0945, "lr": 1.148397956361007e-05, "epoch": 3.374468085106383, "percentage": 68.18, "elapsed_time": "2:01:20", "remaining_time": "0:56:37", "throughput": 10707.4, "total_tokens": 77955072} +{"current_steps": 301, "total_steps": 440, "loss": 0.0859, "lr": 1.1334161952599054e-05, "epoch": 3.3858156028368795, "percentage": 68.41, "elapsed_time": "2:01:44", "remaining_time": "0:56:13", "throughput": 10707.46, "total_tokens": 78217216} +{"current_steps": 302, "total_steps": 440, "loss": 0.0982, "lr": 1.1185041014327433e-05, "epoch": 3.397163120567376, "percentage": 68.64, "elapsed_time": "2:02:09", "remaining_time": "0:55:49", "throughput": 10707.42, "total_tokens": 78479360} +{"current_steps": 303, "total_steps": 440, "loss": 0.0891, "lr": 1.1036624350853145e-05, "epoch": 3.4085106382978725, "percentage": 68.86, "elapsed_time": "2:02:33", "remaining_time": "0:55:25", "throughput": 10707.35, "total_tokens": 78741504} +{"current_steps": 304, "total_steps": 440, "loss": 0.0905, "lr": 1.0888919528330777e-05, "epoch": 3.419858156028369, "percentage": 69.09, "elapsed_time": "2:02:58", "remaining_time": "0:55:00", "throughput": 10707.42, "total_tokens": 79003648} +{"current_steps": 305, "total_steps": 440, "loss": 0.0891, "lr": 1.0741934076625895e-05, "epoch": 3.4312056737588654, "percentage": 69.32, "elapsed_time": "2:03:22", "remaining_time": "0:54:36", "throughput": 10707.51, "total_tokens": 79265792} +{"current_steps": 306, "total_steps": 440, "loss": 0.0869, "lr": 1.059567548893118e-05, "epoch": 3.4425531914893615, "percentage": 69.55, "elapsed_time": "2:03:47", "remaining_time": "0:54:12", "throughput": 10707.61, "total_tokens": 79527936} +{"current_steps": 307, "total_steps": 440, "loss": 0.09, "lr": 1.0450151221384358e-05, "epoch": 3.453900709219858, "percentage": 69.77, "elapsed_time": "2:04:11", "remaining_time": "0:53:48", "throughput": 10707.56, "total_tokens": 79790080} +{"current_steps": 308, "total_steps": 440, "loss": 0.0876, "lr": 1.0305368692688174e-05, "epoch": 3.4652482269503544, "percentage": 70.0, "elapsed_time": "2:04:36", "remaining_time": "0:53:24", "throughput": 10707.61, "total_tokens": 80052224} +{"current_steps": 309, "total_steps": 440, "loss": 0.0875, "lr": 1.016133528373215e-05, "epoch": 3.476595744680851, "percentage": 70.23, "elapsed_time": "2:05:00", "remaining_time": "0:52:59", "throughput": 10707.65, "total_tokens": 80314368} +{"current_steps": 310, "total_steps": 440, "loss": 0.079, "lr": 1.0018058337216327e-05, "epoch": 3.4879432624113473, "percentage": 70.45, "elapsed_time": "2:05:25", "remaining_time": "0:52:35", "throughput": 10707.69, "total_tokens": 80576512} +{"current_steps": 311, "total_steps": 440, "loss": 0.0793, "lr": 9.875545157276939e-06, "epoch": 3.499290780141844, "percentage": 70.68, "elapsed_time": "2:05:49", "remaining_time": "0:52:11", "throughput": 10707.7, "total_tokens": 80838656} +{"current_steps": 312, "total_steps": 440, "loss": 0.0881, "lr": 9.733803009114045e-06, "epoch": 3.5106382978723403, "percentage": 70.91, "elapsed_time": "2:06:14", "remaining_time": "0:51:47", "throughput": 10707.63, "total_tokens": 81100800} +{"current_steps": 313, "total_steps": 440, "loss": 0.0909, "lr": 9.592839118621187e-06, "epoch": 3.5219858156028367, "percentage": 71.14, "elapsed_time": "2:06:38", "remaining_time": "0:51:23", "throughput": 10707.74, "total_tokens": 81362944} +{"current_steps": 314, "total_steps": 440, "loss": 0.0808, "lr": 9.452660672016949e-06, "epoch": 3.533333333333333, "percentage": 71.36, "elapsed_time": "2:07:02", "remaining_time": "0:50:58", "throughput": 10707.76, "total_tokens": 81625088} +{"current_steps": 315, "total_steps": 440, "loss": 0.0853, "lr": 9.313274815478698e-06, "epoch": 3.5446808510638297, "percentage": 71.59, "elapsed_time": "2:07:27", "remaining_time": "0:50:34", "throughput": 10707.75, "total_tokens": 81887232} +{"current_steps": 316, "total_steps": 440, "loss": 0.0913, "lr": 9.174688654778243e-06, "epoch": 3.556028368794326, "percentage": 71.82, "elapsed_time": "2:07:51", "remaining_time": "0:50:10", "throughput": 10707.73, "total_tokens": 82149376} +{"current_steps": 317, "total_steps": 440, "loss": 0.0851, "lr": 9.036909254919549e-06, "epoch": 3.5673758865248226, "percentage": 72.05, "elapsed_time": "2:08:16", "remaining_time": "0:49:46", "throughput": 10707.79, "total_tokens": 82411520} +{"current_steps": 318, "total_steps": 440, "loss": 0.0898, "lr": 8.899943639778619e-06, "epoch": 3.578723404255319, "percentage": 72.27, "elapsed_time": "2:08:40", "remaining_time": "0:49:22", "throughput": 10707.82, "total_tokens": 82673664} +{"current_steps": 319, "total_steps": 440, "loss": 0.0808, "lr": 8.763798791745411e-06, "epoch": 3.5900709219858156, "percentage": 72.5, "elapsed_time": "2:09:05", "remaining_time": "0:48:57", "throughput": 10707.79, "total_tokens": 82935808} +{"current_steps": 320, "total_steps": 440, "loss": 0.084, "lr": 8.628481651367876e-06, "epoch": 3.601418439716312, "percentage": 72.73, "elapsed_time": "2:09:29", "remaining_time": "0:48:33", "throughput": 10707.8, "total_tokens": 83197952} +{"current_steps": 321, "total_steps": 440, "loss": 0.0957, "lr": 8.49399911699814e-06, "epoch": 3.6127659574468085, "percentage": 72.95, "elapsed_time": "2:09:54", "remaining_time": "0:48:09", "throughput": 10707.77, "total_tokens": 83460096} +{"current_steps": 322, "total_steps": 440, "loss": 0.0893, "lr": 8.360358044440797e-06, "epoch": 3.624113475177305, "percentage": 73.18, "elapsed_time": "2:10:18", "remaining_time": "0:47:45", "throughput": 10707.86, "total_tokens": 83722240} +{"current_steps": 323, "total_steps": 440, "loss": 0.0804, "lr": 8.227565246603493e-06, "epoch": 3.6354609929078014, "percentage": 73.41, "elapsed_time": "2:10:43", "remaining_time": "0:47:21", "throughput": 10707.98, "total_tokens": 83984384} +{"current_steps": 324, "total_steps": 440, "loss": 0.0868, "lr": 8.09562749314952e-06, "epoch": 3.646808510638298, "percentage": 73.64, "elapsed_time": "2:11:07", "remaining_time": "0:46:56", "throughput": 10708.03, "total_tokens": 84246528} +{"current_steps": 325, "total_steps": 440, "loss": 0.089, "lr": 7.96455151015272e-06, "epoch": 3.6581560283687944, "percentage": 73.86, "elapsed_time": "2:11:32", "remaining_time": "0:46:32", "throughput": 10708.05, "total_tokens": 84508672} +{"current_steps": 326, "total_steps": 440, "loss": 0.0866, "lr": 7.83434397975466e-06, "epoch": 3.669503546099291, "percentage": 74.09, "elapsed_time": "2:11:56", "remaining_time": "0:46:08", "throughput": 10708.13, "total_tokens": 84770816} +{"current_steps": 327, "total_steps": 440, "loss": 0.0815, "lr": 7.705011539823911e-06, "epoch": 3.6808510638297873, "percentage": 74.32, "elapsed_time": "2:12:20", "remaining_time": "0:45:44", "throughput": 10708.11, "total_tokens": 85032960} +{"current_steps": 328, "total_steps": 440, "loss": 0.0818, "lr": 7.576560783617668e-06, "epoch": 3.692198581560284, "percentage": 74.55, "elapsed_time": "2:12:45", "remaining_time": "0:45:19", "throughput": 10708.15, "total_tokens": 85295104} +{"current_steps": 329, "total_steps": 440, "loss": 0.0857, "lr": 7.448998259445664e-06, "epoch": 3.7035460992907803, "percentage": 74.77, "elapsed_time": "2:13:09", "remaining_time": "0:44:55", "throughput": 10708.17, "total_tokens": 85557248} +{"current_steps": 330, "total_steps": 440, "loss": 0.0768, "lr": 7.3223304703363135e-06, "epoch": 3.7148936170212767, "percentage": 75.0, "elapsed_time": "2:13:34", "remaining_time": "0:44:31", "throughput": 10708.19, "total_tokens": 85819392} +{"current_steps": 331, "total_steps": 440, "loss": 0.0924, "lr": 7.196563873705209e-06, "epoch": 3.726241134751773, "percentage": 75.23, "elapsed_time": "2:13:58", "remaining_time": "0:44:07", "throughput": 10708.27, "total_tokens": 86081536} +{"current_steps": 332, "total_steps": 440, "loss": 0.0864, "lr": 7.071704881025915e-06, "epoch": 3.7375886524822697, "percentage": 75.45, "elapsed_time": "2:14:23", "remaining_time": "0:43:42", "throughput": 10708.38, "total_tokens": 86343680} +{"current_steps": 333, "total_steps": 440, "loss": 0.0887, "lr": 6.947759857503119e-06, "epoch": 3.748936170212766, "percentage": 75.68, "elapsed_time": "2:14:47", "remaining_time": "0:43:18", "throughput": 10708.37, "total_tokens": 86605824} +{"current_steps": 334, "total_steps": 440, "loss": 0.083, "lr": 6.824735121748163e-06, "epoch": 3.7602836879432626, "percentage": 75.91, "elapsed_time": "2:15:12", "remaining_time": "0:42:54", "throughput": 10708.3, "total_tokens": 86867968} +{"current_steps": 335, "total_steps": 440, "loss": 0.0783, "lr": 6.70263694545687e-06, "epoch": 3.771631205673759, "percentage": 76.14, "elapsed_time": "2:15:36", "remaining_time": "0:42:30", "throughput": 10708.32, "total_tokens": 87130112} +{"current_steps": 336, "total_steps": 440, "loss": 0.077, "lr": 6.5814715530898745e-06, "epoch": 3.7829787234042556, "percentage": 76.36, "elapsed_time": "2:16:01", "remaining_time": "0:42:06", "throughput": 10708.3, "total_tokens": 87392256} +{"current_steps": 337, "total_steps": 440, "loss": 0.0832, "lr": 6.461245121555307e-06, "epoch": 3.794326241134752, "percentage": 76.59, "elapsed_time": "2:16:25", "remaining_time": "0:41:41", "throughput": 10708.25, "total_tokens": 87654400} +{"current_steps": 338, "total_steps": 440, "loss": 0.0815, "lr": 6.341963779893828e-06, "epoch": 3.8056737588652485, "percentage": 76.82, "elapsed_time": "2:16:50", "remaining_time": "0:41:17", "throughput": 10708.19, "total_tokens": 87916544} +{"current_steps": 339, "total_steps": 440, "loss": 0.0802, "lr": 6.223633608966254e-06, "epoch": 3.8170212765957445, "percentage": 77.05, "elapsed_time": "2:17:14", "remaining_time": "0:40:53", "throughput": 10708.19, "total_tokens": 88178688} +{"current_steps": 340, "total_steps": 440, "loss": 0.0866, "lr": 6.106260641143546e-06, "epoch": 3.828368794326241, "percentage": 77.27, "elapsed_time": "2:17:39", "remaining_time": "0:40:29", "throughput": 10708.17, "total_tokens": 88440832} +{"current_steps": 341, "total_steps": 440, "loss": 0.0768, "lr": 5.989850859999227e-06, "epoch": 3.8397163120567375, "percentage": 77.5, "elapsed_time": "2:18:03", "remaining_time": "0:40:04", "throughput": 10708.14, "total_tokens": 88702976} +{"current_steps": 342, "total_steps": 440, "loss": 0.0744, "lr": 5.874410200004421e-06, "epoch": 3.851063829787234, "percentage": 77.73, "elapsed_time": "2:18:28", "remaining_time": "0:39:40", "throughput": 10708.21, "total_tokens": 88965120} +{"current_steps": 343, "total_steps": 440, "loss": 0.081, "lr": 5.759944546225271e-06, "epoch": 3.8624113475177304, "percentage": 77.95, "elapsed_time": "2:18:52", "remaining_time": "0:39:16", "throughput": 10708.16, "total_tokens": 89227264} +{"current_steps": 344, "total_steps": 440, "loss": 0.0708, "lr": 5.646459734022938e-06, "epoch": 3.873758865248227, "percentage": 78.18, "elapsed_time": "2:19:17", "remaining_time": "0:38:52", "throughput": 10708.13, "total_tokens": 89489408} +{"current_steps": 345, "total_steps": 440, "loss": 0.078, "lr": 5.533961548756128e-06, "epoch": 3.8851063829787233, "percentage": 78.41, "elapsed_time": "2:19:41", "remaining_time": "0:38:27", "throughput": 10708.09, "total_tokens": 89751552} +{"current_steps": 346, "total_steps": 440, "loss": 0.0878, "lr": 5.422455725486114e-06, "epoch": 3.89645390070922, "percentage": 78.64, "elapsed_time": "2:20:06", "remaining_time": "0:38:03", "throughput": 10708.2, "total_tokens": 90013696} +{"current_steps": 347, "total_steps": 440, "loss": 0.0825, "lr": 5.311947948684457e-06, "epoch": 3.9078014184397163, "percentage": 78.86, "elapsed_time": "2:20:30", "remaining_time": "0:37:39", "throughput": 10708.26, "total_tokens": 90275840} +{"current_steps": 348, "total_steps": 440, "loss": 0.0818, "lr": 5.202443851943126e-06, "epoch": 3.9191489361702128, "percentage": 79.09, "elapsed_time": "2:20:54", "remaining_time": "0:37:15", "throughput": 10708.23, "total_tokens": 90537984} +{"current_steps": 349, "total_steps": 440, "loss": 0.081, "lr": 5.093949017687341e-06, "epoch": 3.9304964539007092, "percentage": 79.32, "elapsed_time": "2:21:19", "remaining_time": "0:36:50", "throughput": 10708.2, "total_tokens": 90800128} +{"current_steps": 350, "total_steps": 440, "loss": 0.0747, "lr": 4.986468976890993e-06, "epoch": 3.9418439716312057, "percentage": 79.55, "elapsed_time": "2:21:43", "remaining_time": "0:36:26", "throughput": 10708.2, "total_tokens": 91062272} +{"current_steps": 351, "total_steps": 440, "loss": 0.0811, "lr": 4.880009208794667e-06, "epoch": 3.953191489361702, "percentage": 79.77, "elapsed_time": "2:22:08", "remaining_time": "0:36:02", "throughput": 10708.21, "total_tokens": 91324416} +{"current_steps": 352, "total_steps": 440, "loss": 0.0749, "lr": 4.7745751406263165e-06, "epoch": 3.9645390070921986, "percentage": 80.0, "elapsed_time": "2:22:32", "remaining_time": "0:35:38", "throughput": 10708.22, "total_tokens": 91586560} +{"current_steps": 353, "total_steps": 440, "loss": 0.0787, "lr": 4.670172147324592e-06, "epoch": 3.975886524822695, "percentage": 80.23, "elapsed_time": "2:22:57", "remaining_time": "0:35:13", "throughput": 10708.14, "total_tokens": 91848704} +{"current_steps": 354, "total_steps": 440, "loss": 0.0811, "lr": 4.566805551264827e-06, "epoch": 3.9872340425531916, "percentage": 80.45, "elapsed_time": "2:23:21", "remaining_time": "0:34:49", "throughput": 10708.1, "total_tokens": 92110848} +{"current_steps": 355, "total_steps": 440, "loss": 0.0738, "lr": 4.4644806219877184e-06, "epoch": 3.998581560283688, "percentage": 80.68, "elapsed_time": "2:23:46", "remaining_time": "0:34:25", "throughput": 10708.12, "total_tokens": 92372992} +{"current_steps": 356, "total_steps": 440, "loss": 0.0466, "lr": 4.36320257593065e-06, "epoch": 4.0, "percentage": 80.91, "elapsed_time": "2:23:49", "remaining_time": "0:33:56", "throughput": 10708.16, "total_tokens": 92405760} +{"current_steps": 357, "total_steps": 440, "loss": 0.0249, "lr": 4.262976576161842e-06, "epoch": 4.0113475177304965, "percentage": 81.14, "elapsed_time": "2:24:13", "remaining_time": "0:33:31", "throughput": 10708.17, "total_tokens": 92667904} +{"current_steps": 358, "total_steps": 440, "loss": 0.0231, "lr": 4.1638077321170646e-06, "epoch": 4.022695035460993, "percentage": 81.36, "elapsed_time": "2:24:38", "remaining_time": "0:33:07", "throughput": 10708.13, "total_tokens": 92930048} +{"current_steps": 359, "total_steps": 440, "loss": 0.0222, "lr": 4.0657010993391865e-06, "epoch": 4.034042553191489, "percentage": 81.59, "elapsed_time": "2:25:02", "remaining_time": "0:32:43", "throughput": 10708.2, "total_tokens": 93192192} +{"current_steps": 360, "total_steps": 440, "loss": 0.0197, "lr": 3.968661679220468e-06, "epoch": 4.045390070921986, "percentage": 81.82, "elapsed_time": "2:25:27", "remaining_time": "0:32:19", "throughput": 10708.24, "total_tokens": 93454336} +{"current_steps": 361, "total_steps": 440, "loss": 0.0189, "lr": 3.872694418747594e-06, "epoch": 4.056737588652482, "percentage": 82.05, "elapsed_time": "2:25:51", "remaining_time": "0:31:55", "throughput": 10708.2, "total_tokens": 93716480} +{"current_steps": 362, "total_steps": 440, "loss": 0.0176, "lr": 3.777804210249436e-06, "epoch": 4.068085106382979, "percentage": 82.27, "elapsed_time": "2:26:16", "remaining_time": "0:31:31", "throughput": 10708.22, "total_tokens": 93978624} +{"current_steps": 363, "total_steps": 440, "loss": 0.0198, "lr": 3.6839958911476957e-06, "epoch": 4.079432624113475, "percentage": 82.5, "elapsed_time": "2:26:40", "remaining_time": "0:31:06", "throughput": 10708.18, "total_tokens": 94240768} +{"current_steps": 364, "total_steps": 440, "loss": 0.0177, "lr": 3.591274243710277e-06, "epoch": 4.090780141843972, "percentage": 82.73, "elapsed_time": "2:27:05", "remaining_time": "0:30:42", "throughput": 10708.19, "total_tokens": 94502912} +{"current_steps": 365, "total_steps": 440, "loss": 0.0165, "lr": 3.499643994807486e-06, "epoch": 4.102127659574468, "percentage": 82.95, "elapsed_time": "2:27:29", "remaining_time": "0:30:18", "throughput": 10708.12, "total_tokens": 94765056} +{"current_steps": 366, "total_steps": 440, "loss": 0.0161, "lr": 3.4091098156710744e-06, "epoch": 4.113475177304965, "percentage": 83.18, "elapsed_time": "2:27:54", "remaining_time": "0:29:54", "throughput": 10708.13, "total_tokens": 95027200} +{"current_steps": 367, "total_steps": 440, "loss": 0.0156, "lr": 3.319676321656082e-06, "epoch": 4.124822695035461, "percentage": 83.41, "elapsed_time": "2:28:18", "remaining_time": "0:29:30", "throughput": 10708.14, "total_tokens": 95289344} +{"current_steps": 368, "total_steps": 440, "loss": 0.0165, "lr": 3.2313480720055745e-06, "epoch": 4.136170212765958, "percentage": 83.64, "elapsed_time": "2:28:43", "remaining_time": "0:29:05", "throughput": 10708.13, "total_tokens": 95551488} +{"current_steps": 369, "total_steps": 440, "loss": 0.0152, "lr": 3.1441295696181897e-06, "epoch": 4.147517730496454, "percentage": 83.86, "elapsed_time": "2:29:07", "remaining_time": "0:28:41", "throughput": 10708.13, "total_tokens": 95813632} +{"current_steps": 370, "total_steps": 440, "loss": 0.0149, "lr": 3.058025260818609e-06, "epoch": 4.158865248226951, "percentage": 84.09, "elapsed_time": "2:29:32", "remaining_time": "0:28:17", "throughput": 10708.11, "total_tokens": 96075776} +{"current_steps": 371, "total_steps": 440, "loss": 0.0153, "lr": 2.9730395351308866e-06, "epoch": 4.170212765957447, "percentage": 84.32, "elapsed_time": "2:29:56", "remaining_time": "0:27:53", "throughput": 10708.15, "total_tokens": 96337920} +{"current_steps": 372, "total_steps": 440, "loss": 0.0173, "lr": 2.889176725054643e-06, "epoch": 4.1815602836879435, "percentage": 84.55, "elapsed_time": "2:30:21", "remaining_time": "0:27:29", "throughput": 10708.16, "total_tokens": 96600064} +{"current_steps": 373, "total_steps": 440, "loss": 0.0148, "lr": 2.80644110584424e-06, "epoch": 4.19290780141844, "percentage": 84.77, "elapsed_time": "2:30:45", "remaining_time": "0:27:04", "throughput": 10708.23, "total_tokens": 96862208} +{"current_steps": 374, "total_steps": 440, "loss": 0.0165, "lr": 2.7248368952908053e-06, "epoch": 4.2042553191489365, "percentage": 85.0, "elapsed_time": "2:31:10", "remaining_time": "0:26:40", "throughput": 10708.23, "total_tokens": 97124352} +{"current_steps": 375, "total_steps": 440, "loss": 0.0154, "lr": 2.6443682535072177e-06, "epoch": 4.215602836879433, "percentage": 85.23, "elapsed_time": "2:31:34", "remaining_time": "0:26:16", "throughput": 10708.24, "total_tokens": 97386496} +{"current_steps": 376, "total_steps": 440, "loss": 0.0149, "lr": 2.565039282716045e-06, "epoch": 4.226950354609929, "percentage": 85.45, "elapsed_time": "2:31:59", "remaining_time": "0:25:52", "throughput": 10708.26, "total_tokens": 97648640} +{"current_steps": 377, "total_steps": 440, "loss": 0.0143, "lr": 2.486854027040375e-06, "epoch": 4.238297872340426, "percentage": 85.68, "elapsed_time": "2:32:23", "remaining_time": "0:25:27", "throughput": 10708.26, "total_tokens": 97910784} +{"current_steps": 378, "total_steps": 440, "loss": 0.016, "lr": 2.4098164722977073e-06, "epoch": 4.249645390070922, "percentage": 85.91, "elapsed_time": "2:32:47", "remaining_time": "0:25:03", "throughput": 10708.33, "total_tokens": 98172928} +{"current_steps": 379, "total_steps": 440, "loss": 0.0159, "lr": 2.333930545796717e-06, "epoch": 4.260992907801419, "percentage": 86.14, "elapsed_time": "2:33:12", "remaining_time": "0:24:39", "throughput": 10708.31, "total_tokens": 98435072} +{"current_steps": 380, "total_steps": 440, "loss": 0.0162, "lr": 2.2592001161370392e-06, "epoch": 4.272340425531915, "percentage": 86.36, "elapsed_time": "2:33:36", "remaining_time": "0:24:15", "throughput": 10708.35, "total_tokens": 98697216} +{"current_steps": 381, "total_steps": 440, "loss": 0.0144, "lr": 2.185628993012101e-06, "epoch": 4.283687943262412, "percentage": 86.59, "elapsed_time": "2:34:01", "remaining_time": "0:23:51", "throughput": 10708.33, "total_tokens": 98959360} +{"current_steps": 382, "total_steps": 440, "loss": 0.0147, "lr": 2.11322092701485e-06, "epoch": 4.295035460992908, "percentage": 86.82, "elapsed_time": "2:34:25", "remaining_time": "0:23:26", "throughput": 10708.27, "total_tokens": 99221504} +{"current_steps": 383, "total_steps": 440, "loss": 0.0149, "lr": 2.0419796094465788e-06, "epoch": 4.306382978723404, "percentage": 87.05, "elapsed_time": "2:34:50", "remaining_time": "0:23:02", "throughput": 10708.28, "total_tokens": 99483648} +{"current_steps": 384, "total_steps": 440, "loss": 0.0163, "lr": 1.97190867212875e-06, "epoch": 4.317730496453901, "percentage": 87.27, "elapsed_time": "2:35:14", "remaining_time": "0:22:38", "throughput": 10708.34, "total_tokens": 99745792} +{"current_steps": 385, "total_steps": 440, "loss": 0.0147, "lr": 1.9030116872178316e-06, "epoch": 4.329078014184397, "percentage": 87.5, "elapsed_time": "2:35:39", "remaining_time": "0:22:14", "throughput": 10708.35, "total_tokens": 100007936} +{"current_steps": 386, "total_steps": 440, "loss": 0.0142, "lr": 1.8352921670232143e-06, "epoch": 4.340425531914893, "percentage": 87.73, "elapsed_time": "2:36:03", "remaining_time": "0:21:49", "throughput": 10708.31, "total_tokens": 100270080} +{"current_steps": 387, "total_steps": 440, "loss": 0.0148, "lr": 1.768753563828135e-06, "epoch": 4.35177304964539, "percentage": 87.95, "elapsed_time": "2:36:28", "remaining_time": "0:21:25", "throughput": 10708.33, "total_tokens": 100532224} +{"current_steps": 388, "total_steps": 440, "loss": 0.0148, "lr": 1.703399269713693e-06, "epoch": 4.363120567375886, "percentage": 88.18, "elapsed_time": "2:36:52", "remaining_time": "0:21:01", "throughput": 10708.3, "total_tokens": 100794368} +{"current_steps": 389, "total_steps": 440, "loss": 0.0158, "lr": 1.6392326163859273e-06, "epoch": 4.374468085106383, "percentage": 88.41, "elapsed_time": "2:37:17", "remaining_time": "0:20:37", "throughput": 10708.25, "total_tokens": 101056512} +{"current_steps": 390, "total_steps": 440, "loss": 0.0149, "lr": 1.5762568750059604e-06, "epoch": 4.385815602836879, "percentage": 88.64, "elapsed_time": "2:37:41", "remaining_time": "0:20:13", "throughput": 10708.29, "total_tokens": 101318656} +{"current_steps": 391, "total_steps": 440, "loss": 0.0159, "lr": 1.5144752560232372e-06, "epoch": 4.397163120567376, "percentage": 88.86, "elapsed_time": "2:38:06", "remaining_time": "0:19:48", "throughput": 10708.28, "total_tokens": 101580800} +{"current_steps": 392, "total_steps": 440, "loss": 0.0137, "lr": 1.4538909090118846e-06, "epoch": 4.408510638297872, "percentage": 89.09, "elapsed_time": "2:38:30", "remaining_time": "0:19:24", "throughput": 10708.21, "total_tokens": 101842944} +{"current_steps": 393, "total_steps": 440, "loss": 0.0151, "lr": 1.3945069225101026e-06, "epoch": 4.4198581560283685, "percentage": 89.32, "elapsed_time": "2:38:55", "remaining_time": "0:19:00", "throughput": 10708.21, "total_tokens": 102105088} +{"current_steps": 394, "total_steps": 440, "loss": 0.0166, "lr": 1.3363263238627493e-06, "epoch": 4.431205673758865, "percentage": 89.55, "elapsed_time": "2:39:19", "remaining_time": "0:18:36", "throughput": 10708.21, "total_tokens": 102367232} +{"current_steps": 395, "total_steps": 440, "loss": 0.0152, "lr": 1.2793520790670116e-06, "epoch": 4.4425531914893615, "percentage": 89.77, "elapsed_time": "2:39:44", "remaining_time": "0:18:11", "throughput": 10708.25, "total_tokens": 102629376} +{"current_steps": 396, "total_steps": 440, "loss": 0.0144, "lr": 1.2235870926211619e-06, "epoch": 4.453900709219858, "percentage": 90.0, "elapsed_time": "2:40:08", "remaining_time": "0:17:47", "throughput": 10708.2, "total_tokens": 102891520} +{"current_steps": 397, "total_steps": 440, "loss": 0.0144, "lr": 1.1690342073765375e-06, "epoch": 4.465248226950354, "percentage": 90.23, "elapsed_time": "2:40:33", "remaining_time": "0:17:23", "throughput": 10708.19, "total_tokens": 103153664} +{"current_steps": 398, "total_steps": 440, "loss": 0.0158, "lr": 1.1156962043925828e-06, "epoch": 4.476595744680851, "percentage": 90.45, "elapsed_time": "2:40:57", "remaining_time": "0:16:59", "throughput": 10708.24, "total_tokens": 103415808} +{"current_steps": 399, "total_steps": 440, "loss": 0.0133, "lr": 1.0635758027950888e-06, "epoch": 4.487943262411347, "percentage": 90.68, "elapsed_time": "2:41:22", "remaining_time": "0:16:34", "throughput": 10708.21, "total_tokens": 103677952} +{"current_steps": 400, "total_steps": 440, "loss": 0.016, "lr": 1.0126756596375686e-06, "epoch": 4.499290780141844, "percentage": 90.91, "elapsed_time": "2:41:46", "remaining_time": "0:16:10", "throughput": 10708.25, "total_tokens": 103940096} +{"current_steps": 401, "total_steps": 440, "loss": 0.0165, "lr": 9.629983697657886e-07, "epoch": 4.51063829787234, "percentage": 91.14, "elapsed_time": "2:42:11", "remaining_time": "0:15:46", "throughput": 10708.28, "total_tokens": 104202240} +{"current_steps": 402, "total_steps": 440, "loss": 0.0134, "lr": 9.145464656855257e-07, "epoch": 4.521985815602837, "percentage": 91.36, "elapsed_time": "2:42:35", "remaining_time": "0:15:22", "throughput": 10708.28, "total_tokens": 104464384} +{"current_steps": 403, "total_steps": 440, "loss": 0.0132, "lr": 8.673224174334221e-07, "epoch": 4.533333333333333, "percentage": 91.59, "elapsed_time": "2:42:59", "remaining_time": "0:14:57", "throughput": 10708.28, "total_tokens": 104726528} +{"current_steps": 404, "total_steps": 440, "loss": 0.0156, "lr": 8.213286324510738e-07, "epoch": 4.54468085106383, "percentage": 91.82, "elapsed_time": "2:43:24", "remaining_time": "0:14:33", "throughput": 10708.28, "total_tokens": 104988672} +{"current_steps": 405, "total_steps": 440, "loss": 0.0165, "lr": 7.765674554623181e-07, "epoch": 4.556028368794326, "percentage": 92.05, "elapsed_time": "2:43:48", "remaining_time": "0:14:09", "throughput": 10708.36, "total_tokens": 105250816} +{"current_steps": 406, "total_steps": 440, "loss": 0.0144, "lr": 7.330411683536876e-07, "epoch": 4.567375886524823, "percentage": 92.27, "elapsed_time": "2:44:13", "remaining_time": "0:13:45", "throughput": 10708.3, "total_tokens": 105512960} +{"current_steps": 407, "total_steps": 440, "loss": 0.0153, "lr": 6.907519900580861e-07, "epoch": 4.578723404255319, "percentage": 92.5, "elapsed_time": "2:44:37", "remaining_time": "0:13:20", "throughput": 10708.33, "total_tokens": 105775104} +{"current_steps": 408, "total_steps": 440, "loss": 0.0156, "lr": 6.497020764416633e-07, "epoch": 4.590070921985816, "percentage": 92.73, "elapsed_time": "2:45:02", "remaining_time": "0:12:56", "throughput": 10708.28, "total_tokens": 106037248} +{"current_steps": 409, "total_steps": 440, "loss": 0.0136, "lr": 6.098935201939187e-07, "epoch": 4.601418439716312, "percentage": 92.95, "elapsed_time": "2:45:26", "remaining_time": "0:12:32", "throughput": 10708.27, "total_tokens": 106299392} +{"current_steps": 410, "total_steps": 440, "loss": 0.0139, "lr": 5.713283507210148e-07, "epoch": 4.6127659574468085, "percentage": 93.18, "elapsed_time": "2:45:51", "remaining_time": "0:12:08", "throughput": 10707.87, "total_tokens": 106561536} +{"current_steps": 411, "total_steps": 440, "loss": 0.0144, "lr": 5.340085340423129e-07, "epoch": 4.624113475177305, "percentage": 93.41, "elapsed_time": "2:46:16", "remaining_time": "0:11:43", "throughput": 10707.81, "total_tokens": 106823680} +{"current_steps": 412, "total_steps": 440, "loss": 0.0131, "lr": 4.979359726901639e-07, "epoch": 4.6354609929078014, "percentage": 93.64, "elapsed_time": "2:46:40", "remaining_time": "0:11:19", "throughput": 10707.85, "total_tokens": 107085824} +{"current_steps": 413, "total_steps": 440, "loss": 0.0131, "lr": 4.63112505612906e-07, "epoch": 4.646808510638298, "percentage": 93.86, "elapsed_time": "2:47:05", "remaining_time": "0:10:55", "throughput": 10707.87, "total_tokens": 107347968} +{"current_steps": 414, "total_steps": 440, "loss": 0.015, "lr": 4.2953990808111135e-07, "epoch": 4.658156028368794, "percentage": 94.09, "elapsed_time": "2:47:29", "remaining_time": "0:10:31", "throughput": 10707.93, "total_tokens": 107610112} +{"current_steps": 415, "total_steps": 440, "loss": 0.0152, "lr": 3.972198915970976e-07, "epoch": 4.669503546099291, "percentage": 94.32, "elapsed_time": "2:47:53", "remaining_time": "0:10:06", "throughput": 10708.0, "total_tokens": 107872256} +{"current_steps": 416, "total_steps": 440, "loss": 0.0153, "lr": 3.6615410380767544e-07, "epoch": 4.680851063829787, "percentage": 94.55, "elapsed_time": "2:48:18", "remaining_time": "0:09:42", "throughput": 10708.08, "total_tokens": 108134400} +{"current_steps": 417, "total_steps": 440, "loss": 0.0139, "lr": 3.3634412842014353e-07, "epoch": 4.692198581560284, "percentage": 94.77, "elapsed_time": "2:48:42", "remaining_time": "0:09:18", "throughput": 10708.0, "total_tokens": 108396544} +{"current_steps": 418, "total_steps": 440, "loss": 0.0139, "lr": 3.077914851215585e-07, "epoch": 4.70354609929078, "percentage": 95.0, "elapsed_time": "2:49:07", "remaining_time": "0:08:54", "throughput": 10707.99, "total_tokens": 108658688} +{"current_steps": 419, "total_steps": 440, "loss": 0.014, "lr": 2.804976295012612e-07, "epoch": 4.714893617021277, "percentage": 95.23, "elapsed_time": "2:49:31", "remaining_time": "0:08:29", "throughput": 10707.94, "total_tokens": 108920832} +{"current_steps": 420, "total_steps": 440, "loss": 0.0137, "lr": 2.544639529766829e-07, "epoch": 4.726241134751773, "percentage": 95.45, "elapsed_time": "2:49:56", "remaining_time": "0:08:05", "throughput": 10707.9, "total_tokens": 109182976} +{"current_steps": 421, "total_steps": 440, "loss": 0.0139, "lr": 2.2969178272238545e-07, "epoch": 4.73758865248227, "percentage": 95.68, "elapsed_time": "2:50:20", "remaining_time": "0:07:41", "throughput": 10707.91, "total_tokens": 109445120} +{"current_steps": 422, "total_steps": 440, "loss": 0.0132, "lr": 2.061823816024322e-07, "epoch": 4.748936170212766, "percentage": 95.91, "elapsed_time": "2:50:45", "remaining_time": "0:07:17", "throughput": 10707.91, "total_tokens": 109707264} +{"current_steps": 423, "total_steps": 440, "loss": 0.016, "lr": 1.8393694810599493e-07, "epoch": 4.760283687943263, "percentage": 96.14, "elapsed_time": "2:51:09", "remaining_time": "0:06:52", "throughput": 10707.89, "total_tokens": 109969408} +{"current_steps": 424, "total_steps": 440, "loss": 0.0136, "lr": 1.6295661628624447e-07, "epoch": 4.771631205673759, "percentage": 96.36, "elapsed_time": "2:51:34", "remaining_time": "0:06:28", "throughput": 10707.98, "total_tokens": 110231552} +{"current_steps": 425, "total_steps": 440, "loss": 0.0169, "lr": 1.4324245570256633e-07, "epoch": 4.782978723404256, "percentage": 96.59, "elapsed_time": "2:51:58", "remaining_time": "0:06:04", "throughput": 10707.96, "total_tokens": 110493696} +{"current_steps": 426, "total_steps": 440, "loss": 0.0133, "lr": 1.2479547136600989e-07, "epoch": 4.794326241134752, "percentage": 96.82, "elapsed_time": "2:52:23", "remaining_time": "0:05:39", "throughput": 10707.97, "total_tokens": 110755840} +{"current_steps": 427, "total_steps": 440, "loss": 0.0144, "lr": 1.0761660368806548e-07, "epoch": 4.8056737588652485, "percentage": 97.05, "elapsed_time": "2:52:47", "remaining_time": "0:05:15", "throughput": 10707.94, "total_tokens": 111017984} +{"current_steps": 428, "total_steps": 440, "loss": 0.0153, "lr": 9.170672843271666e-08, "epoch": 4.817021276595745, "percentage": 97.27, "elapsed_time": "2:53:12", "remaining_time": "0:04:51", "throughput": 10707.77, "total_tokens": 111280128} +{"current_steps": 429, "total_steps": 440, "loss": 0.0127, "lr": 7.706665667180091e-08, "epoch": 4.828368794326241, "percentage": 97.5, "elapsed_time": "2:53:37", "remaining_time": "0:04:27", "throughput": 10707.19, "total_tokens": 111542272} +{"current_steps": 430, "total_steps": 440, "loss": 0.0139, "lr": 6.369713474366212e-08, "epoch": 4.839716312056738, "percentage": 97.73, "elapsed_time": "2:54:01", "remaining_time": "0:04:02", "throughput": 10707.19, "total_tokens": 111804416} +{"current_steps": 431, "total_steps": 440, "loss": 0.0142, "lr": 5.159884421509498e-08, "epoch": 4.851063829787234, "percentage": 97.95, "elapsed_time": "2:54:26", "remaining_time": "0:03:38", "throughput": 10707.19, "total_tokens": 112066560} +{"current_steps": 432, "total_steps": 440, "loss": 0.0156, "lr": 4.07724018466088e-08, "epoch": 4.862411347517731, "percentage": 98.18, "elapsed_time": "2:54:50", "remaining_time": "0:03:14", "throughput": 10707.17, "total_tokens": 112328704} +{"current_steps": 433, "total_steps": 440, "loss": 0.0154, "lr": 3.1218359560974966e-08, "epoch": 4.873758865248227, "percentage": 98.41, "elapsed_time": "2:55:15", "remaining_time": "0:02:49", "throughput": 10707.14, "total_tokens": 112590848} +{"current_steps": 434, "total_steps": 440, "loss": 0.0151, "lr": 2.2937204415107717e-08, "epoch": 4.885106382978723, "percentage": 98.64, "elapsed_time": "2:55:40", "remaining_time": "0:02:25", "throughput": 10707.09, "total_tokens": 112852992} +{"current_steps": 435, "total_steps": 440, "loss": 0.0144, "lr": 1.5929358575206275e-08, "epoch": 4.89645390070922, "percentage": 98.86, "elapsed_time": "2:56:04", "remaining_time": "0:02:01", "throughput": 10707.13, "total_tokens": 113115136} +{"current_steps": 436, "total_steps": 440, "loss": 0.0146, "lr": 1.0195179295269252e-08, "epoch": 4.907801418439716, "percentage": 99.09, "elapsed_time": "2:56:28", "remaining_time": "0:01:37", "throughput": 10707.14, "total_tokens": 113377280} +{"current_steps": 437, "total_steps": 440, "loss": 0.0125, "lr": 5.7349588988481194e-09, "epoch": 4.919148936170213, "percentage": 99.32, "elapsed_time": "2:56:53", "remaining_time": "0:01:12", "throughput": 10707.12, "total_tokens": 113639424} +{"current_steps": 438, "total_steps": 440, "loss": 0.0129, "lr": 2.5489247641674596e-09, "epoch": 4.930496453900709, "percentage": 99.55, "elapsed_time": "2:57:17", "remaining_time": "0:00:48", "throughput": 10707.15, "total_tokens": 113901568} +{"current_steps": 439, "total_steps": 440, "loss": 0.0148, "lr": 6.372393125203546e-10, "epoch": 4.941843971631206, "percentage": 99.77, "elapsed_time": "2:57:42", "remaining_time": "0:00:24", "throughput": 10707.17, "total_tokens": 114163712} +{"current_steps": 440, "total_steps": 440, "loss": 0.0161, "lr": 0.0, "epoch": 4.953191489361702, "percentage": 100.0, "elapsed_time": "2:58:06", "remaining_time": "0:00:00", "throughput": 10707.16, "total_tokens": 114425856} +{"current_steps": 440, "total_steps": 440, "epoch": 4.953191489361702, "percentage": 100.0, "elapsed_time": "3:02:51", "remaining_time": "0:00:00", "throughput": 10429.55, "total_tokens": 114425856}