| {"current_steps": 10, "total_steps": 1500, "loss": 0.9242, "accuracy": 0.4375, "learning_rate": 4.999451708687114e-06, "epoch": 0.008072653884964682, "percentage": 0.67, "elapsed_time": "0:01:18", "remaining_time": "3:15:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.9127, "accuracy": 0.5375000238418579, "learning_rate": 4.997807075247147e-06, "epoch": 0.016145307769929364, "percentage": 1.33, "elapsed_time": "0:02:36", "remaining_time": "3:12:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9141, "accuracy": 0.4625000059604645, "learning_rate": 4.9950668210706795e-06, "epoch": 0.024217961654894045, "percentage": 2.0, "elapsed_time": "0:03:52", "remaining_time": "3:09:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9313, "accuracy": 0.5625, "learning_rate": 4.9912321481237616e-06, "epoch": 0.03229061553985873, "percentage": 2.67, "elapsed_time": "0:05:07", "remaining_time": "3:06:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9076, "accuracy": 0.4749999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.04036326942482341, "percentage": 3.33, "elapsed_time": "0:06:20", "remaining_time": "3:04:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9108895063400269, "epoch": 0.04036326942482341, "percentage": 3.33, "elapsed_time": "0:06:50", "remaining_time": "3:18:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9204, "accuracy": 0.5249999761581421, "learning_rate": 4.980286753286196e-06, "epoch": 0.04843592330978809, "percentage": 4.0, "elapsed_time": "0:08:13", "remaining_time": "3:17:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.915, "accuracy": 0.5375000238418579, "learning_rate": 4.973180832407471e-06, "epoch": 0.056508577194752774, "percentage": 4.67, "elapsed_time": "0:09:29", "remaining_time": "3:13:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9223, "accuracy": 0.637499988079071, "learning_rate": 4.964990092676263e-06, "epoch": 0.06458123107971746, "percentage": 5.33, "elapsed_time": "0:10:42", "remaining_time": "3:10:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9117, "accuracy": 0.6000000238418579, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07265388496468214, "percentage": 6.0, "elapsed_time": "0:12:01", "remaining_time": "3:08:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9162, "accuracy": 0.5249999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:18", "remaining_time": "3:06:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.900999128818512, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:48", "remaining_time": "3:13:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.8951, "accuracy": 0.699999988079071, "learning_rate": 4.933947257182901e-06, "epoch": 0.08879919273461151, "percentage": 7.33, "elapsed_time": "0:15:09", "remaining_time": "3:11:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9012, "accuracy": 0.637499988079071, "learning_rate": 4.921457902821578e-06, "epoch": 0.09687184661957618, "percentage": 8.0, "elapsed_time": "0:16:28", "remaining_time": "3:09:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.8911, "accuracy": 0.5249999761581421, "learning_rate": 4.907906416994146e-06, "epoch": 0.10494450050454086, "percentage": 8.67, "elapsed_time": "0:17:48", "remaining_time": "3:07:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.8915, "accuracy": 0.6499999761581421, "learning_rate": 4.893298743830168e-06, "epoch": 0.11301715438950555, "percentage": 9.33, "elapsed_time": "0:19:05", "remaining_time": "3:05:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.8954, "accuracy": 0.4375, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:24", "remaining_time": "3:03:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8780961036682129, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:54", "remaining_time": "3:08:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.8814, "accuracy": 0.5874999761581421, "learning_rate": 4.860940925593703e-06, "epoch": 0.12916246215943492, "percentage": 10.67, "elapsed_time": "0:22:19", "remaining_time": "3:06:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.8739, "accuracy": 0.7124999761581421, "learning_rate": 4.84320497372973e-06, "epoch": 0.13723511604439959, "percentage": 11.33, "elapsed_time": "0:23:33", "remaining_time": "3:04:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.8732, "accuracy": 0.6499999761581421, "learning_rate": 4.824441214720629e-06, "epoch": 0.14530776992936428, "percentage": 12.0, "elapsed_time": "0:24:49", "remaining_time": "3:02:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.8425, "accuracy": 0.6875, "learning_rate": 4.804657878971252e-06, "epoch": 0.15338042381432895, "percentage": 12.67, "elapsed_time": "0:26:08", "remaining_time": "3:00:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.8327, "accuracy": 0.612500011920929, "learning_rate": 4.783863644106502e-06, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:31", "remaining_time": "2:58:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8103437423706055, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:28:01", "remaining_time": "3:02:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.7877, "accuracy": 0.625, "learning_rate": 4.762067631165049e-06, "epoch": 0.16952573158425832, "percentage": 14.0, "elapsed_time": "0:29:27", "remaining_time": "3:00:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.7816, "accuracy": 0.612500011920929, "learning_rate": 4.7392794005985324e-06, "epoch": 0.17759838546922302, "percentage": 14.67, "elapsed_time": "0:30:44", "remaining_time": "2:58:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.7306, "accuracy": 0.6625000238418579, "learning_rate": 4.715508948078037e-06, "epoch": 0.1856710393541877, "percentage": 15.33, "elapsed_time": "0:32:02", "remaining_time": "2:56:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.7214, "accuracy": 0.625, "learning_rate": 4.690766700109659e-06, "epoch": 0.19374369323915236, "percentage": 16.0, "elapsed_time": "0:33:18", "remaining_time": "2:54:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.6811, "accuracy": 0.7124999761581421, "learning_rate": 4.665063509461098e-06, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:34:36", "remaining_time": "2:53:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.6842760443687439, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:35:06", "remaining_time": "2:55:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.7141, "accuracy": 0.512499988079071, "learning_rate": 4.638410650401267e-06, "epoch": 0.20988900100908173, "percentage": 17.33, "elapsed_time": "0:36:31", "remaining_time": "2:54:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.6647, "accuracy": 0.637499988079071, "learning_rate": 4.610819813755038e-06, "epoch": 0.21796165489404642, "percentage": 18.0, "elapsed_time": "0:37:50", "remaining_time": "2:52:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.5629, "accuracy": 0.637499988079071, "learning_rate": 4.582303101775249e-06, "epoch": 0.2260343087790111, "percentage": 18.67, "elapsed_time": "0:39:08", "remaining_time": "2:50:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.5544, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.2341069626639758, "percentage": 19.33, "elapsed_time": "0:40:29", "remaining_time": "2:48:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.4968, "accuracy": 0.800000011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:41:47", "remaining_time": "2:47:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.4899609684944153, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:42:17", "remaining_time": "2:49:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.5372, "accuracy": 0.699999988079071, "learning_rate": 4.491324795060491e-06, "epoch": 0.25025227043390513, "percentage": 20.67, "elapsed_time": "0:43:41", "remaining_time": "2:47:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.4974, "accuracy": 0.6875, "learning_rate": 4.4592336433146e-06, "epoch": 0.25832492431886983, "percentage": 21.33, "elapsed_time": "0:44:59", "remaining_time": "2:45:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.4777, "accuracy": 0.75, "learning_rate": 4.426283106939474e-06, "epoch": 0.26639757820383453, "percentage": 22.0, "elapsed_time": "0:46:21", "remaining_time": "2:44:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.4718, "accuracy": 0.7749999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.27447023208879917, "percentage": 22.67, "elapsed_time": "0:47:39", "remaining_time": "2:42:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.4909, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:48:53", "remaining_time": "2:40:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.44899094104766846, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:49:23", "remaining_time": "2:42:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.4561, "accuracy": 0.737500011920929, "learning_rate": 4.322421568553529e-06, "epoch": 0.29061553985872857, "percentage": 24.0, "elapsed_time": "0:50:45", "remaining_time": "2:40:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.4305, "accuracy": 0.737500011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.29868819374369326, "percentage": 24.67, "elapsed_time": "0:52:03", "remaining_time": "2:38:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.4358, "accuracy": 0.737500011920929, "learning_rate": 4.249158351283414e-06, "epoch": 0.3067608476286579, "percentage": 25.33, "elapsed_time": "0:53:18", "remaining_time": "2:37:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.4565, "accuracy": 0.7250000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.3148335015136226, "percentage": 26.0, "elapsed_time": "0:54:37", "remaining_time": "2:35:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.408, "accuracy": 0.887499988079071, "learning_rate": 4.172826515897146e-06, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:55:56", "remaining_time": "2:33:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.38578492403030396, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:56:26", "remaining_time": "2:35:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.3894, "accuracy": 0.800000011920929, "learning_rate": 4.133551509975264e-06, "epoch": 0.33097880928355194, "percentage": 27.33, "elapsed_time": "0:57:49", "remaining_time": "2:33:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.3853, "accuracy": 0.8500000238418579, "learning_rate": 4.093559974371725e-06, "epoch": 0.33905146316851664, "percentage": 28.0, "elapsed_time": "0:59:07", "remaining_time": "2:32:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.3669, "accuracy": 0.8125, "learning_rate": 4.052869450695776e-06, "epoch": 0.34712411705348134, "percentage": 28.67, "elapsed_time": "1:00:26", "remaining_time": "2:30:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.3333, "accuracy": 0.8500000238418579, "learning_rate": 4.011497787155938e-06, "epoch": 0.35519677093844604, "percentage": 29.33, "elapsed_time": "1:01:44", "remaining_time": "2:28:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.356, "accuracy": 0.875, "learning_rate": 3.969463130731183e-06, "epoch": 0.3632694248234107, "percentage": 30.0, "elapsed_time": "1:02:58", "remaining_time": "2:26:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.33659350872039795, "epoch": 0.3632694248234107, "percentage": 30.0, "elapsed_time": "1:03:28", "remaining_time": "2:28:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.3141, "accuracy": 0.824999988079071, "learning_rate": 3.92678391921108e-06, "epoch": 0.3713420787083754, "percentage": 30.67, "elapsed_time": "1:04:52", "remaining_time": "2:26:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.3298, "accuracy": 0.949999988079071, "learning_rate": 3.88347887310836e-06, "epoch": 0.3794147325933401, "percentage": 31.33, "elapsed_time": "1:06:10", "remaining_time": "2:25:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3071, "accuracy": 0.8500000238418579, "learning_rate": 3.839566987447492e-06, "epoch": 0.3874873864783047, "percentage": 32.0, "elapsed_time": "1:07:28", "remaining_time": "2:23:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.2638, "accuracy": 0.9375, "learning_rate": 3.795067523432826e-06, "epoch": 0.3955600403632694, "percentage": 32.67, "elapsed_time": "1:08:41", "remaining_time": "2:21:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.2592, "accuracy": 0.8999999761581421, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:09:57", "remaining_time": "2:19:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3161226809024811, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:10:27", "remaining_time": "2:20:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.2772, "accuracy": 0.925000011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4117053481331988, "percentage": 34.0, "elapsed_time": "1:11:48", "remaining_time": "2:19:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.2724, "accuracy": 0.925000011920929, "learning_rate": 3.658240087799655e-06, "epoch": 0.41977800201816345, "percentage": 34.67, "elapsed_time": "1:13:06", "remaining_time": "2:17:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.2616, "accuracy": 0.949999988079071, "learning_rate": 3.611587947962319e-06, "epoch": 0.42785065590312815, "percentage": 35.33, "elapsed_time": "1:14:21", "remaining_time": "2:16:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.2954, "accuracy": 0.8374999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.43592330978809285, "percentage": 36.0, "elapsed_time": "1:15:39", "remaining_time": "2:14:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.26, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:16:55", "remaining_time": "2:12:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.28268176317214966, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:17:25", "remaining_time": "2:13:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.2752, "accuracy": 0.925000011920929, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4520686175580222, "percentage": 37.33, "elapsed_time": "1:18:50", "remaining_time": "2:12:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.2666, "accuracy": 0.862500011920929, "learning_rate": 3.4203113817116955e-06, "epoch": 0.4601412714429869, "percentage": 38.0, "elapsed_time": "1:20:08", "remaining_time": "2:10:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.2362, "accuracy": 0.9624999761581421, "learning_rate": 3.3714301183045382e-06, "epoch": 0.4682139253279516, "percentage": 38.67, "elapsed_time": "1:21:23", "remaining_time": "2:09:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.2774, "accuracy": 0.862500011920929, "learning_rate": 3.3221666168464584e-06, "epoch": 0.47628657921291623, "percentage": 39.33, "elapsed_time": "1:22:39", "remaining_time": "2:07:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.3082, "accuracy": 0.9375, "learning_rate": 3.272542485937369e-06, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:23:54", "remaining_time": "2:05:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.2698034942150116, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:24:24", "remaining_time": "2:06:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.267, "accuracy": 0.8500000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.4924318869828456, "percentage": 40.67, "elapsed_time": "1:25:49", "remaining_time": "2:05:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.2849, "accuracy": 0.887499988079071, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5005045408678103, "percentage": 41.33, "elapsed_time": "1:27:11", "remaining_time": "2:03:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.2448, "accuracy": 0.887499988079071, "learning_rate": 3.121724717912138e-06, "epoch": 0.508577194752775, "percentage": 42.0, "elapsed_time": "1:28:30", "remaining_time": "2:02:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.2505, "accuracy": 0.8999999761581421, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5166498486377397, "percentage": 42.67, "elapsed_time": "1:29:43", "remaining_time": "2:00:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.2889, "accuracy": 0.9125000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:30:57", "remaining_time": "1:58:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.2533933222293854, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:31:27", "remaining_time": "1:59:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.2228, "accuracy": 0.9624999761581421, "learning_rate": 2.9684532864643123e-06, "epoch": 0.5327951564076691, "percentage": 44.0, "elapsed_time": "1:32:53", "remaining_time": "1:58:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.2443, "accuracy": 0.9624999761581421, "learning_rate": 2.9169218667902562e-06, "epoch": 0.5408678102926338, "percentage": 44.67, "elapsed_time": "1:34:10", "remaining_time": "1:56:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.2413, "accuracy": 0.887499988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 0.5489404641775983, "percentage": 45.33, "elapsed_time": "1:35:22", "remaining_time": "1:55:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.2356, "accuracy": 0.949999988079071, "learning_rate": 2.813333083910761e-06, "epoch": 0.557013118062563, "percentage": 46.0, "elapsed_time": "1:36:42", "remaining_time": "1:53:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.212, "accuracy": 0.949999988079071, "learning_rate": 2.761321158169134e-06, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:37:56", "remaining_time": "1:51:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.24302434921264648, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:38:26", "remaining_time": "1:52:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.192, "accuracy": 0.925000011920929, "learning_rate": 2.70919460833079e-06, "epoch": 0.5731584258324924, "percentage": 47.33, "elapsed_time": "1:39:46", "remaining_time": "1:51:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.2578, "accuracy": 0.8999999761581421, "learning_rate": 2.6569762988232838e-06, "epoch": 0.5812310797174571, "percentage": 48.0, "elapsed_time": "1:41:04", "remaining_time": "1:49:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.2569, "accuracy": 0.875, "learning_rate": 2.604689134322999e-06, "epoch": 0.5893037336024218, "percentage": 48.67, "elapsed_time": "1:42:17", "remaining_time": "1:47:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.205, "accuracy": 0.949999988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.5973763874873865, "percentage": 49.33, "elapsed_time": "1:43:36", "remaining_time": "1:46:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.2279, "accuracy": 0.9375, "learning_rate": 2.5e-06, "epoch": 0.6054490413723511, "percentage": 50.0, "elapsed_time": "1:44:54", "remaining_time": "1:44:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.23516784608364105, "epoch": 0.6054490413723511, "percentage": 50.0, "elapsed_time": "1:45:24", "remaining_time": "1:45:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.2413, "accuracy": 0.9750000238418579, "learning_rate": 2.447643950291608e-06, "epoch": 0.6135216952573158, "percentage": 50.67, "elapsed_time": "1:46:47", "remaining_time": "1:43:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.2045, "accuracy": 0.9624999761581421, "learning_rate": 2.3953108656770018e-06, "epoch": 0.6215943491422805, "percentage": 51.33, "elapsed_time": "1:48:04", "remaining_time": "1:42:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.2382, "accuracy": 0.949999988079071, "learning_rate": 2.3430237011767166e-06, "epoch": 0.6296670030272452, "percentage": 52.0, "elapsed_time": "1:49:22", "remaining_time": "1:40:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.2333, "accuracy": 0.949999988079071, "learning_rate": 2.290805391669212e-06, "epoch": 0.6377396569122099, "percentage": 52.67, "elapsed_time": "1:50:40", "remaining_time": "1:39:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.2555, "accuracy": 0.887499988079071, "learning_rate": 2.238678841830867e-06, "epoch": 0.6458123107971746, "percentage": 53.33, "elapsed_time": "1:52:02", "remaining_time": "1:38:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.22401823103427887, "epoch": 0.6458123107971746, "percentage": 53.33, "elapsed_time": "1:52:32", "remaining_time": "1:38:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.2228, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.6538849646821393, "percentage": 54.0, "elapsed_time": "1:53:50", "remaining_time": "1:36:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.2156, "accuracy": 0.925000011920929, "learning_rate": 2.134792428593971e-06, "epoch": 0.6619576185671039, "percentage": 54.67, "elapsed_time": "1:55:07", "remaining_time": "1:35:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.2229, "accuracy": 0.8999999761581421, "learning_rate": 2.0830781332097446e-06, "epoch": 0.6700302724520686, "percentage": 55.33, "elapsed_time": "1:56:25", "remaining_time": "1:33:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.2255, "accuracy": 0.925000011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.6781029263370333, "percentage": 56.0, "elapsed_time": "1:57:39", "remaining_time": "1:32:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.2116, "accuracy": 0.925000011920929, "learning_rate": 1.9802207729556023e-06, "epoch": 0.686175580221998, "percentage": 56.67, "elapsed_time": "1:58:53", "remaining_time": "1:30:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.21706117689609528, "epoch": 0.686175580221998, "percentage": 56.67, "elapsed_time": "1:59:23", "remaining_time": "1:31:18", "throughput": "0.00", "total_tokens": 0} | |