| {"current_steps": 10, "total_steps": 1500, "loss": 0.9221, "accuracy": 0.42500001192092896, "learning_rate": 4.999451708687114e-06, "epoch": 0.008072653884964682, "percentage": 0.67, "elapsed_time": "0:01:17", "remaining_time": "3:11:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.916, "accuracy": 0.550000011920929, "learning_rate": 4.997807075247147e-06, "epoch": 0.016145307769929364, "percentage": 1.33, "elapsed_time": "0:02:32", "remaining_time": "3:07:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.914, "accuracy": 0.48750001192092896, "learning_rate": 4.9950668210706795e-06, "epoch": 0.024217961654894045, "percentage": 2.0, "elapsed_time": "0:03:50", "remaining_time": "3:08:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9273, "accuracy": 0.6000000238418579, "learning_rate": 4.9912321481237616e-06, "epoch": 0.03229061553985873, "percentage": 2.67, "elapsed_time": "0:05:03", "remaining_time": "3:04:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9081, "accuracy": 0.48750001192092896, "learning_rate": 4.986304738420684e-06, "epoch": 0.04036326942482341, "percentage": 3.33, "elapsed_time": "0:06:18", "remaining_time": "3:03:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9080610275268555, "epoch": 0.04036326942482341, "percentage": 3.33, "elapsed_time": "0:06:48", "remaining_time": "3:17:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9195, "accuracy": 0.5, "learning_rate": 4.980286753286196e-06, "epoch": 0.04843592330978809, "percentage": 4.0, "elapsed_time": "0:08:14", "remaining_time": "3:17:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9241, "accuracy": 0.5375000238418579, "learning_rate": 4.973180832407471e-06, "epoch": 0.056508577194752774, "percentage": 4.67, "elapsed_time": "0:09:30", "remaining_time": "3:14:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9251, "accuracy": 0.637499988079071, "learning_rate": 4.964990092676263e-06, "epoch": 0.06458123107971746, "percentage": 5.33, "elapsed_time": "0:10:44", "remaining_time": "3:10:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9055, "accuracy": 0.6000000238418579, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07265388496468214, "percentage": 6.0, "elapsed_time": "0:12:00", "remaining_time": "3:08:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.911, "accuracy": 0.48750001192092896, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:10", "remaining_time": "3:04:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.8986235857009888, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:39", "remaining_time": "3:11:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.8993, "accuracy": 0.6875, "learning_rate": 4.933947257182901e-06, "epoch": 0.08879919273461151, "percentage": 7.33, "elapsed_time": "0:15:15", "remaining_time": "3:12:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.8942, "accuracy": 0.6000000238418579, "learning_rate": 4.921457902821578e-06, "epoch": 0.09687184661957618, "percentage": 8.0, "elapsed_time": "0:16:30", "remaining_time": "3:09:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.8922, "accuracy": 0.550000011920929, "learning_rate": 4.907906416994146e-06, "epoch": 0.10494450050454086, "percentage": 8.67, "elapsed_time": "0:17:46", "remaining_time": "3:07:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.8957, "accuracy": 0.612500011920929, "learning_rate": 4.893298743830168e-06, "epoch": 0.11301715438950555, "percentage": 9.33, "elapsed_time": "0:19:03", "remaining_time": "3:05:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.892, "accuracy": 0.4375, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:21", "remaining_time": "3:03:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8789658546447754, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:51", "remaining_time": "3:07:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.8789, "accuracy": 0.574999988079071, "learning_rate": 4.860940925593703e-06, "epoch": 0.12916246215943492, "percentage": 10.67, "elapsed_time": "0:22:22", "remaining_time": "3:07:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.8857, "accuracy": 0.675000011920929, "learning_rate": 4.84320497372973e-06, "epoch": 0.13723511604439959, "percentage": 11.33, "elapsed_time": "0:23:39", "remaining_time": "3:05:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.8699, "accuracy": 0.6625000238418579, "learning_rate": 4.824441214720629e-06, "epoch": 0.14530776992936428, "percentage": 12.0, "elapsed_time": "0:24:54", "remaining_time": "3:02:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.8565, "accuracy": 0.675000011920929, "learning_rate": 4.804657878971252e-06, "epoch": 0.15338042381432895, "percentage": 12.67, "elapsed_time": "0:26:10", "remaining_time": "3:00:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.8482, "accuracy": 0.5874999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:26", "remaining_time": "2:58:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8243693113327026, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:55", "remaining_time": "3:01:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.7988, "accuracy": 0.612500011920929, "learning_rate": 4.762067631165049e-06, "epoch": 0.16952573158425832, "percentage": 14.0, "elapsed_time": "0:29:17", "remaining_time": "2:59:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.796, "accuracy": 0.6000000238418579, "learning_rate": 4.7392794005985324e-06, "epoch": 0.17759838546922302, "percentage": 14.67, "elapsed_time": "0:30:32", "remaining_time": "2:57:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.7457, "accuracy": 0.637499988079071, "learning_rate": 4.715508948078037e-06, "epoch": 0.1856710393541877, "percentage": 15.33, "elapsed_time": "0:31:46", "remaining_time": "2:55:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.7453, "accuracy": 0.550000011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.19374369323915236, "percentage": 16.0, "elapsed_time": "0:32:58", "remaining_time": "2:53:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.704, "accuracy": 0.6625000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:34:13", "remaining_time": "2:51:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.6982013583183289, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:34:42", "remaining_time": "2:53:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.7149, "accuracy": 0.5249999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.20988900100908173, "percentage": 17.33, "elapsed_time": "0:36:07", "remaining_time": "2:52:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.6811, "accuracy": 0.625, "learning_rate": 4.610819813755038e-06, "epoch": 0.21796165489404642, "percentage": 18.0, "elapsed_time": "0:37:22", "remaining_time": "2:50:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.637, "accuracy": 0.625, "learning_rate": 4.582303101775249e-06, "epoch": 0.2260343087790111, "percentage": 18.67, "elapsed_time": "0:38:39", "remaining_time": "2:48:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.63, "accuracy": 0.5874999761581421, "learning_rate": 4.55287302283426e-06, "epoch": 0.2341069626639758, "percentage": 19.33, "elapsed_time": "0:39:57", "remaining_time": "2:46:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.6104, "accuracy": 0.7749999761581421, "learning_rate": 4.522542485937369e-06, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:41:16", "remaining_time": "2:45:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5781419277191162, "epoch": 0.24217961654894046, "percentage": 20.0, "elapsed_time": "0:41:45", "remaining_time": "2:47:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.5807, "accuracy": 0.6875, "learning_rate": 4.491324795060491e-06, "epoch": 0.25025227043390513, "percentage": 20.67, "elapsed_time": "0:43:23", "remaining_time": "2:46:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.5007, "accuracy": 0.6625000238418579, "learning_rate": 4.4592336433146e-06, "epoch": 0.25832492431886983, "percentage": 21.33, "elapsed_time": "0:44:40", "remaining_time": "2:44:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.4757, "accuracy": 0.75, "learning_rate": 4.426283106939474e-06, "epoch": 0.26639757820383453, "percentage": 22.0, "elapsed_time": "0:46:00", "remaining_time": "2:43:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.4581, "accuracy": 0.7749999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.27447023208879917, "percentage": 22.67, "elapsed_time": "0:47:15", "remaining_time": "2:41:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.4989, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:48:29", "remaining_time": "2:39:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.44154587388038635, "epoch": 0.28254288597376387, "percentage": 23.33, "elapsed_time": "0:48:58", "remaining_time": "2:40:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.4373, "accuracy": 0.7124999761581421, "learning_rate": 4.322421568553529e-06, "epoch": 0.29061553985872857, "percentage": 24.0, "elapsed_time": "0:50:32", "remaining_time": "2:40:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.438, "accuracy": 0.7250000238418579, "learning_rate": 4.286181699082008e-06, "epoch": 0.29868819374369326, "percentage": 24.67, "elapsed_time": "0:51:46", "remaining_time": "2:38:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.4542, "accuracy": 0.7124999761581421, "learning_rate": 4.249158351283414e-06, "epoch": 0.3067608476286579, "percentage": 25.33, "elapsed_time": "0:52:59", "remaining_time": "2:36:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.4816, "accuracy": 0.675000011920929, "learning_rate": 4.211367764821722e-06, "epoch": 0.3148335015136226, "percentage": 26.0, "elapsed_time": "0:54:15", "remaining_time": "2:34:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.4431, "accuracy": 0.7250000238418579, "learning_rate": 4.172826515897146e-06, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:55:34", "remaining_time": "2:32:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.4156961143016815, "epoch": 0.3229061553985873, "percentage": 26.67, "elapsed_time": "0:56:03", "remaining_time": "2:34:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.427, "accuracy": 0.699999988079071, "learning_rate": 4.133551509975264e-06, "epoch": 0.33097880928355194, "percentage": 27.33, "elapsed_time": "0:57:23", "remaining_time": "2:32:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.4384, "accuracy": 0.75, "learning_rate": 4.093559974371725e-06, "epoch": 0.33905146316851664, "percentage": 28.0, "elapsed_time": "0:58:38", "remaining_time": "2:30:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.3934, "accuracy": 0.6625000238418579, "learning_rate": 4.052869450695776e-06, "epoch": 0.34712411705348134, "percentage": 28.67, "elapsed_time": "0:59:48", "remaining_time": "2:28:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.4147, "accuracy": 0.737500011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.35519677093844604, "percentage": 29.33, "elapsed_time": "1:01:06", "remaining_time": "2:27:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.4354, "accuracy": 0.675000011920929, "learning_rate": 3.969463130731183e-06, "epoch": 0.3632694248234107, "percentage": 30.0, "elapsed_time": "1:02:20", "remaining_time": "2:25:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.3905698359012604, "epoch": 0.3632694248234107, "percentage": 30.0, "elapsed_time": "1:02:49", "remaining_time": "2:26:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.4023, "accuracy": 0.762499988079071, "learning_rate": 3.92678391921108e-06, "epoch": 0.3713420787083754, "percentage": 30.67, "elapsed_time": "1:04:11", "remaining_time": "2:25:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.3979, "accuracy": 0.7875000238418579, "learning_rate": 3.88347887310836e-06, "epoch": 0.3794147325933401, "percentage": 31.33, "elapsed_time": "1:05:25", "remaining_time": "2:23:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3356, "accuracy": 0.824999988079071, "learning_rate": 3.839566987447492e-06, "epoch": 0.3874873864783047, "percentage": 32.0, "elapsed_time": "1:06:41", "remaining_time": "2:21:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.3193, "accuracy": 0.875, "learning_rate": 3.795067523432826e-06, "epoch": 0.3955600403632694, "percentage": 32.67, "elapsed_time": "1:07:54", "remaining_time": "2:19:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.3103, "accuracy": 0.8125, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:09:11", "remaining_time": "2:18:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3228474259376526, "epoch": 0.4036326942482341, "percentage": 33.33, "elapsed_time": "1:09:40", "remaining_time": "2:19:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.2884, "accuracy": 0.887499988079071, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4117053481331988, "percentage": 34.0, "elapsed_time": "1:11:03", "remaining_time": "2:17:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.3093, "accuracy": 0.875, "learning_rate": 3.658240087799655e-06, "epoch": 0.41977800201816345, "percentage": 34.67, "elapsed_time": "1:12:19", "remaining_time": "2:16:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.2972, "accuracy": 0.887499988079071, "learning_rate": 3.611587947962319e-06, "epoch": 0.42785065590312815, "percentage": 35.33, "elapsed_time": "1:13:33", "remaining_time": "2:14:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.3136, "accuracy": 0.887499988079071, "learning_rate": 3.564448228912682e-06, "epoch": 0.43592330978809285, "percentage": 36.0, "elapsed_time": "1:14:49", "remaining_time": "2:13:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.2822, "accuracy": 0.8999999761581421, "learning_rate": 3.516841607689501e-06, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:16:02", "remaining_time": "2:11:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.2939932942390442, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:16:32", "remaining_time": "2:12:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.2736, "accuracy": 0.925000011920929, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4520686175580222, "percentage": 37.33, "elapsed_time": "1:18:10", "remaining_time": "2:11:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.2776, "accuracy": 0.875, "learning_rate": 3.4203113817116955e-06, "epoch": 0.4601412714429869, "percentage": 38.0, "elapsed_time": "1:19:27", "remaining_time": "2:09:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.2547, "accuracy": 0.9375, "learning_rate": 3.3714301183045382e-06, "epoch": 0.4682139253279516, "percentage": 38.67, "elapsed_time": "1:20:44", "remaining_time": "2:08:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.2839, "accuracy": 0.887499988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.47628657921291623, "percentage": 39.33, "elapsed_time": "1:21:57", "remaining_time": "2:06:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.3237, "accuracy": 0.875, "learning_rate": 3.272542485937369e-06, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:23:10", "remaining_time": "2:04:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.2827170193195343, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:23:39", "remaining_time": "2:05:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.2986, "accuracy": 0.8500000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.4924318869828456, "percentage": 40.67, "elapsed_time": "1:25:14", "remaining_time": "2:04:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.2776, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5005045408678103, "percentage": 41.33, "elapsed_time": "1:26:34", "remaining_time": "2:02:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.2688, "accuracy": 0.8374999761581421, "learning_rate": 3.121724717912138e-06, "epoch": 0.508577194752775, "percentage": 42.0, "elapsed_time": "1:27:51", "remaining_time": "2:01:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.2435, "accuracy": 0.9125000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5166498486377397, "percentage": 42.67, "elapsed_time": "1:29:02", "remaining_time": "1:59:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.2865, "accuracy": 0.8999999761581421, "learning_rate": 3.019779227044398e-06, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:30:16", "remaining_time": "1:58:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.25649499893188477, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:30:45", "remaining_time": "1:58:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.243, "accuracy": 0.949999988079071, "learning_rate": 2.9684532864643123e-06, "epoch": 0.5327951564076691, "percentage": 44.0, "elapsed_time": "1:32:04", "remaining_time": "1:57:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.266, "accuracy": 0.949999988079071, "learning_rate": 2.9169218667902562e-06, "epoch": 0.5408678102926338, "percentage": 44.67, "elapsed_time": "1:33:19", "remaining_time": "1:55:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.2356, "accuracy": 0.925000011920929, "learning_rate": 2.8652075714060296e-06, "epoch": 0.5489404641775983, "percentage": 45.33, "elapsed_time": "1:34:31", "remaining_time": "1:53:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.2286, "accuracy": 0.9375, "learning_rate": 2.813333083910761e-06, "epoch": 0.557013118062563, "percentage": 46.0, "elapsed_time": "1:35:46", "remaining_time": "1:52:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.2222, "accuracy": 0.9125000238418579, "learning_rate": 2.761321158169134e-06, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:36:56", "remaining_time": "1:50:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.24892139434814453, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:37:26", "remaining_time": "1:51:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.2153, "accuracy": 0.9375, "learning_rate": 2.70919460833079e-06, "epoch": 0.5731584258324924, "percentage": 47.33, "elapsed_time": "1:38:58", "remaining_time": "1:50:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.2422, "accuracy": 0.875, "learning_rate": 2.6569762988232838e-06, "epoch": 0.5812310797174571, "percentage": 48.0, "elapsed_time": "1:40:14", "remaining_time": "1:48:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.2694, "accuracy": 0.8500000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 0.5893037336024218, "percentage": 48.67, "elapsed_time": "1:41:31", "remaining_time": "1:47:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.2184, "accuracy": 0.9375, "learning_rate": 2.5523560497083927e-06, "epoch": 0.5973763874873865, "percentage": 49.33, "elapsed_time": "1:42:49", "remaining_time": "1:45:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.2364, "accuracy": 0.949999988079071, "learning_rate": 2.5e-06, "epoch": 0.6054490413723511, "percentage": 50.0, "elapsed_time": "1:44:02", "remaining_time": "1:44:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2374112904071808, "epoch": 0.6054490413723511, "percentage": 50.0, "elapsed_time": "1:44:31", "remaining_time": "1:44:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.2467, "accuracy": 0.925000011920929, "learning_rate": 2.447643950291608e-06, "epoch": 0.6135216952573158, "percentage": 50.67, "elapsed_time": "1:46:00", "remaining_time": "1:43:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.2287, "accuracy": 0.9750000238418579, "learning_rate": 2.3953108656770018e-06, "epoch": 0.6215943491422805, "percentage": 51.33, "elapsed_time": "1:47:17", "remaining_time": "1:41:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.259, "accuracy": 0.925000011920929, "learning_rate": 2.3430237011767166e-06, "epoch": 0.6296670030272452, "percentage": 52.0, "elapsed_time": "1:48:31", "remaining_time": "1:40:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.243, "accuracy": 0.9375, "learning_rate": 2.290805391669212e-06, "epoch": 0.6377396569122099, "percentage": 52.67, "elapsed_time": "1:49:47", "remaining_time": "1:38:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.2752, "accuracy": 0.9125000238418579, "learning_rate": 2.238678841830867e-06, "epoch": 0.6458123107971746, "percentage": 53.33, "elapsed_time": "1:51:02", "remaining_time": "1:37:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.22608846426010132, "epoch": 0.6458123107971746, "percentage": 53.33, "elapsed_time": "1:51:31", "remaining_time": "1:37:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.2267, "accuracy": 0.9375, "learning_rate": 2.186666916089239e-06, "epoch": 0.6538849646821393, "percentage": 54.0, "elapsed_time": "1:52:58", "remaining_time": "1:36:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.2079, "accuracy": 0.925000011920929, "learning_rate": 2.134792428593971e-06, "epoch": 0.6619576185671039, "percentage": 54.67, "elapsed_time": "1:54:14", "remaining_time": "1:34:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.2213, "accuracy": 0.925000011920929, "learning_rate": 2.0830781332097446e-06, "epoch": 0.6700302724520686, "percentage": 55.33, "elapsed_time": "1:55:29", "remaining_time": "1:33:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.2381, "accuracy": 0.925000011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.6781029263370333, "percentage": 56.0, "elapsed_time": "1:56:43", "remaining_time": "1:31:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.2112, "accuracy": 0.9624999761581421, "learning_rate": 1.9802207729556023e-06, "epoch": 0.686175580221998, "percentage": 56.67, "elapsed_time": "1:57:59", "remaining_time": "1:30:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.22627003490924835, "epoch": 0.686175580221998, "percentage": 56.67, "elapsed_time": "1:58:28", "remaining_time": "1:30:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.2154, "accuracy": 0.9375, "learning_rate": 1.9291228247233607e-06, "epoch": 0.6942482341069627, "percentage": 57.33, "elapsed_time": "2:00:08", "remaining_time": "1:29:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.2386, "accuracy": 0.887499988079071, "learning_rate": 1.8782752820878636e-06, "epoch": 0.7023208879919274, "percentage": 58.0, "elapsed_time": "2:01:26", "remaining_time": "1:27:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.2126, "accuracy": 0.925000011920929, "learning_rate": 1.827700448461836e-06, "epoch": 0.7103935418768921, "percentage": 58.67, "elapsed_time": "2:02:42", "remaining_time": "1:26:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.185, "accuracy": 0.949999988079071, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7184661957618567, "percentage": 59.33, "elapsed_time": "2:03:57", "remaining_time": "1:24:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 0.2383, "accuracy": 0.9750000238418579, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7265388496468214, "percentage": 60.0, "elapsed_time": "2:05:12", "remaining_time": "1:23:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.21870465576648712, "epoch": 0.7265388496468214, "percentage": 60.0, "elapsed_time": "2:05:41", "remaining_time": "1:23:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.2311, "accuracy": 0.949999988079071, "learning_rate": 1.677833383153542e-06, "epoch": 0.7346115035317861, "percentage": 60.67, "elapsed_time": "2:07:05", "remaining_time": "1:22:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.2034, "accuracy": 0.8999999761581421, "learning_rate": 1.6285698816954626e-06, "epoch": 0.7426841574167508, "percentage": 61.33, "elapsed_time": "2:08:21", "remaining_time": "1:20:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.2301, "accuracy": 0.9375, "learning_rate": 1.5796886182883053e-06, "epoch": 0.7507568113017155, "percentage": 62.0, "elapsed_time": "2:09:35", "remaining_time": "1:19:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.1898, "accuracy": 0.9375, "learning_rate": 1.5312110338697427e-06, "epoch": 0.7588294651866802, "percentage": 62.67, "elapsed_time": "2:10:52", "remaining_time": "1:17:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.1947, "accuracy": 0.9375, "learning_rate": 1.4831583923105e-06, "epoch": 0.7669021190716448, "percentage": 63.33, "elapsed_time": "2:12:10", "remaining_time": "1:16:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.2162380963563919, "epoch": 0.7669021190716448, "percentage": 63.33, "elapsed_time": "2:12:39", "remaining_time": "1:16:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.1954, "accuracy": 0.949999988079071, "learning_rate": 1.4355517710873184e-06, "epoch": 0.7749747729566094, "percentage": 64.0, "elapsed_time": "2:14:13", "remaining_time": "1:15:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.1962, "accuracy": 0.9624999761581421, "learning_rate": 1.388412052037682e-06, "epoch": 0.7830474268415741, "percentage": 64.67, "elapsed_time": "2:15:28", "remaining_time": "1:14:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.1651, "accuracy": 0.9750000238418579, "learning_rate": 1.3417599122003464e-06, "epoch": 0.7911200807265388, "percentage": 65.33, "elapsed_time": "2:16:41", "remaining_time": "1:12:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.1702, "accuracy": 0.9750000238418579, "learning_rate": 1.2956158147457116e-06, "epoch": 0.7991927346115035, "percentage": 66.0, "elapsed_time": "2:17:58", "remaining_time": "1:11:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 0.1934, "accuracy": 0.987500011920929, "learning_rate": 1.2500000000000007e-06, "epoch": 0.8072653884964682, "percentage": 66.67, "elapsed_time": "2:19:12", "remaining_time": "1:09:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.20982278883457184, "epoch": 0.8072653884964682, "percentage": 66.67, "elapsed_time": "2:19:41", "remaining_time": "1:09:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.1911, "accuracy": 0.9375, "learning_rate": 1.204932476567175e-06, "epoch": 0.8153380423814329, "percentage": 67.33, "elapsed_time": "2:21:19", "remaining_time": "1:08:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.2222, "accuracy": 0.925000011920929, "learning_rate": 1.160433012552508e-06, "epoch": 0.8234106962663976, "percentage": 68.0, "elapsed_time": "2:22:33", "remaining_time": "1:07:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.1768, "accuracy": 0.9750000238418579, "learning_rate": 1.11652112689164e-06, "epoch": 0.8314833501513622, "percentage": 68.67, "elapsed_time": "2:23:49", "remaining_time": "1:05:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.1923, "accuracy": 0.949999988079071, "learning_rate": 1.073216080788921e-06, "epoch": 0.8395560040363269, "percentage": 69.33, "elapsed_time": "2:25:04", "remaining_time": "1:04:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.1525, "accuracy": 0.987500011920929, "learning_rate": 1.0305368692688175e-06, "epoch": 0.8476286579212916, "percentage": 70.0, "elapsed_time": "2:26:18", "remaining_time": "1:02:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.20868732035160065, "epoch": 0.8476286579212916, "percentage": 70.0, "elapsed_time": "2:26:47", "remaining_time": "1:02:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.1962, "accuracy": 0.9750000238418579, "learning_rate": 9.88502212844063e-07, "epoch": 0.8557013118062563, "percentage": 70.67, "elapsed_time": "2:28:10", "remaining_time": "1:01:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.1953, "accuracy": 0.9750000238418579, "learning_rate": 9.471305493042243e-07, "epoch": 0.863773965691221, "percentage": 71.33, "elapsed_time": "2:29:31", "remaining_time": "1:00:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.1961, "accuracy": 0.925000011920929, "learning_rate": 9.064400256282757e-07, "epoch": 0.8718466195761857, "percentage": 72.0, "elapsed_time": "2:30:46", "remaining_time": "0:58:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.2107, "accuracy": 0.9624999761581421, "learning_rate": 8.664484900247363e-07, "epoch": 0.8799192734611504, "percentage": 72.67, "elapsed_time": "2:32:05", "remaining_time": "0:57:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.2103, "accuracy": 0.9125000238418579, "learning_rate": 8.271734841028553e-07, "epoch": 0.887991927346115, "percentage": 73.33, "elapsed_time": "2:33:19", "remaining_time": "0:55:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.2044122815132141, "epoch": 0.887991927346115, "percentage": 73.33, "elapsed_time": "2:33:48", "remaining_time": "0:55:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.2092, "accuracy": 0.925000011920929, "learning_rate": 7.886322351782782e-07, "epoch": 0.8960645812310797, "percentage": 74.0, "elapsed_time": "2:35:09", "remaining_time": "0:54:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.2077, "accuracy": 0.8999999761581421, "learning_rate": 7.508416487165862e-07, "epoch": 0.9041372351160444, "percentage": 74.67, "elapsed_time": "2:36:28", "remaining_time": "0:53:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.1904, "accuracy": 0.8999999761581421, "learning_rate": 7.138183009179922e-07, "epoch": 0.9122098890010091, "percentage": 75.33, "elapsed_time": "2:37:42", "remaining_time": "0:51:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.2156, "accuracy": 0.987500011920929, "learning_rate": 6.775784314464717e-07, "epoch": 0.9202825428859738, "percentage": 76.0, "elapsed_time": "2:38:59", "remaining_time": "0:50:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.2165, "accuracy": 0.9624999761581421, "learning_rate": 6.421379363065142e-07, "epoch": 0.9283551967709385, "percentage": 76.67, "elapsed_time": "2:40:16", "remaining_time": "0:48:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.19964782893657684, "epoch": 0.9283551967709385, "percentage": 76.67, "elapsed_time": "2:40:45", "remaining_time": "0:48:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.1896, "accuracy": 0.9624999761581421, "learning_rate": 6.075123608706093e-07, "epoch": 0.9364278506559032, "percentage": 77.33, "elapsed_time": "2:42:08", "remaining_time": "0:47:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.195, "accuracy": 0.9375, "learning_rate": 5.737168930605272e-07, "epoch": 0.9445005045408678, "percentage": 78.0, "elapsed_time": "2:43:26", "remaining_time": "0:46:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.171, "accuracy": 0.9125000238418579, "learning_rate": 5.407663566854008e-07, "epoch": 0.9525731584258325, "percentage": 78.67, "elapsed_time": "2:44:42", "remaining_time": "0:44:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 0.2047, "accuracy": 0.9375, "learning_rate": 5.086752049395094e-07, "epoch": 0.9606458123107972, "percentage": 79.33, "elapsed_time": "2:45:57", "remaining_time": "0:43:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.2222, "accuracy": 0.925000011920929, "learning_rate": 4.774575140626317e-07, "epoch": 0.9687184661957619, "percentage": 80.0, "elapsed_time": "2:47:12", "remaining_time": "0:41:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.2018371820449829, "epoch": 0.9687184661957619, "percentage": 80.0, "elapsed_time": "2:47:41", "remaining_time": "0:41:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1210, "total_steps": 1500, "loss": 0.18, "accuracy": 0.9624999761581421, "learning_rate": 4.4712697716573994e-07, "epoch": 0.9767911200807265, "percentage": 80.67, "elapsed_time": "2:49:03", "remaining_time": "0:40:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1220, "total_steps": 1500, "loss": 0.1536, "accuracy": 0.9750000238418579, "learning_rate": 4.1769689822475147e-07, "epoch": 0.9848637739656912, "percentage": 81.33, "elapsed_time": "2:50:17", "remaining_time": "0:39:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1230, "total_steps": 1500, "loss": 0.1782, "accuracy": 0.887499988079071, "learning_rate": 3.891801862449629e-07, "epoch": 0.992936427850656, "percentage": 82.0, "elapsed_time": "2:51:31", "remaining_time": "0:37:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1240, "total_steps": 1500, "loss": 0.2248, "accuracy": 0.929411768913269, "learning_rate": 3.615893495987335e-07, "epoch": 1.001614530776993, "percentage": 82.67, "elapsed_time": "2:52:50", "remaining_time": "0:36:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "loss": 0.1499, "accuracy": 0.9624999761581421, "learning_rate": 3.3493649053890325e-07, "epoch": 1.0096871846619577, "percentage": 83.33, "elapsed_time": "2:54:02", "remaining_time": "0:34:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.1983107328414917, "epoch": 1.0096871846619577, "percentage": 83.33, "elapsed_time": "2:54:31", "remaining_time": "0:34:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1260, "total_steps": 1500, "loss": 0.1847, "accuracy": 0.9375, "learning_rate": 3.092332998903416e-07, "epoch": 1.0177598385469222, "percentage": 84.0, "elapsed_time": "2:56:07", "remaining_time": "0:33:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1270, "total_steps": 1500, "loss": 0.1894, "accuracy": 0.949999988079071, "learning_rate": 2.844910519219632e-07, "epoch": 1.025832492431887, "percentage": 84.67, "elapsed_time": "2:57:23", "remaining_time": "0:32:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1280, "total_steps": 1500, "loss": 0.1791, "accuracy": 0.9750000238418579, "learning_rate": 2.6072059940146775e-07, "epoch": 1.0339051463168516, "percentage": 85.33, "elapsed_time": "2:58:33", "remaining_time": "0:30:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1290, "total_steps": 1500, "loss": 0.21, "accuracy": 0.949999988079071, "learning_rate": 2.3793236883495164e-07, "epoch": 1.0419778002018163, "percentage": 86.0, "elapsed_time": "2:59:46", "remaining_time": "0:29:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "loss": 0.1632, "accuracy": 0.925000011920929, "learning_rate": 2.1613635589349756e-07, "epoch": 1.050050454086781, "percentage": 86.67, "elapsed_time": "3:01:06", "remaining_time": "0:27:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.1993524730205536, "epoch": 1.050050454086781, "percentage": 86.67, "elapsed_time": "3:01:35", "remaining_time": "0:27:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1310, "total_steps": 1500, "loss": 0.2143, "accuracy": 0.949999988079071, "learning_rate": 1.95342121028749e-07, "epoch": 1.0581231079717457, "percentage": 87.33, "elapsed_time": "3:03:06", "remaining_time": "0:26:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1320, "total_steps": 1500, "loss": 0.1812, "accuracy": 0.9624999761581421, "learning_rate": 1.7555878527937164e-07, "epoch": 1.0661957618567104, "percentage": 88.0, "elapsed_time": "3:04:21", "remaining_time": "0:25:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1330, "total_steps": 1500, "loss": 0.1799, "accuracy": 0.9624999761581421, "learning_rate": 1.567950262702714e-07, "epoch": 1.074268415741675, "percentage": 88.67, "elapsed_time": "3:05:33", "remaining_time": "0:23:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1340, "total_steps": 1500, "loss": 0.1764, "accuracy": 0.987500011920929, "learning_rate": 1.3905907440629752e-07, "epoch": 1.0823410696266398, "percentage": 89.33, "elapsed_time": "3:06:48", "remaining_time": "0:22:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "loss": 0.1802, "accuracy": 0.9375, "learning_rate": 1.223587092621162e-07, "epoch": 1.0904137235116045, "percentage": 90.0, "elapsed_time": "3:08:06", "remaining_time": "0:20:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.19803538918495178, "epoch": 1.0904137235116045, "percentage": 90.0, "elapsed_time": "3:08:35", "remaining_time": "0:20:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1360, "total_steps": 1500, "loss": 0.1901, "accuracy": 0.949999988079071, "learning_rate": 1.067012561698319e-07, "epoch": 1.0984863773965692, "percentage": 90.67, "elapsed_time": "3:10:06", "remaining_time": "0:19:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1370, "total_steps": 1500, "loss": 0.1633, "accuracy": 0.9624999761581421, "learning_rate": 9.209358300585474e-08, "epoch": 1.1065590312815339, "percentage": 91.33, "elapsed_time": "3:11:24", "remaining_time": "0:18:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1380, "total_steps": 1500, "loss": 0.1756, "accuracy": 0.887499988079071, "learning_rate": 7.854209717842231e-08, "epoch": 1.1146316851664986, "percentage": 92.0, "elapsed_time": "3:12:41", "remaining_time": "0:16:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1390, "total_steps": 1500, "loss": 0.1562, "accuracy": 0.949999988079071, "learning_rate": 6.605274281709929e-08, "epoch": 1.122704339051463, "percentage": 92.67, "elapsed_time": "3:13:55", "remaining_time": "0:15:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "loss": 0.1759, "accuracy": 0.925000011920929, "learning_rate": 5.463099816548578e-08, "epoch": 1.1307769929364277, "percentage": 93.33, "elapsed_time": "3:15:14", "remaining_time": "0:13:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.19752371311187744, "epoch": 1.1307769929364277, "percentage": 93.33, "elapsed_time": "3:15:43", "remaining_time": "0:13:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1410, "total_steps": 1500, "loss": 0.1849, "accuracy": 0.949999988079071, "learning_rate": 4.428187317827848e-08, "epoch": 1.1388496468213924, "percentage": 94.0, "elapsed_time": "3:17:03", "remaining_time": "0:12:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1420, "total_steps": 1500, "loss": 0.1987, "accuracy": 0.949999988079071, "learning_rate": 3.5009907323737826e-08, "epoch": 1.1469223007063571, "percentage": 94.67, "elapsed_time": "3:18:19", "remaining_time": "0:11:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1430, "total_steps": 1500, "loss": 0.1997, "accuracy": 0.9624999761581421, "learning_rate": 2.681916759252917e-08, "epoch": 1.1549949545913218, "percentage": 95.33, "elapsed_time": "3:19:32", "remaining_time": "0:09:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1440, "total_steps": 1500, "loss": 0.1827, "accuracy": 0.9750000238418579, "learning_rate": 1.9713246713805588e-08, "epoch": 1.1630676084762865, "percentage": 96.0, "elapsed_time": "3:20:49", "remaining_time": "0:08:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "loss": 0.1823, "accuracy": 0.9125000238418579, "learning_rate": 1.3695261579316776e-08, "epoch": 1.1711402623612512, "percentage": 96.67, "elapsed_time": "3:22:06", "remaining_time": "0:06:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.1976456642150879, "epoch": 1.1711402623612512, "percentage": 96.67, "elapsed_time": "3:22:35", "remaining_time": "0:06:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1460, "total_steps": 1500, "loss": 0.2069, "accuracy": 0.9624999761581421, "learning_rate": 8.767851876239075e-09, "epoch": 1.179212916246216, "percentage": 97.33, "elapsed_time": "3:24:03", "remaining_time": "0:05:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1470, "total_steps": 1500, "loss": 0.1869, "accuracy": 0.9375, "learning_rate": 4.933178929321103e-09, "epoch": 1.1872855701311806, "percentage": 98.0, "elapsed_time": "3:25:22", "remaining_time": "0:04:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1480, "total_steps": 1500, "loss": 0.1771, "accuracy": 0.949999988079071, "learning_rate": 2.192924752854042e-09, "epoch": 1.1953582240161453, "percentage": 98.67, "elapsed_time": "3:26:38", "remaining_time": "0:02:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1490, "total_steps": 1500, "loss": 0.1743, "accuracy": 0.9750000238418579, "learning_rate": 5.48291312886251e-10, "epoch": 1.20343087790111, "percentage": 99.33, "elapsed_time": "3:27:54", "remaining_time": "0:01:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "loss": 0.1913, "accuracy": 0.925000011920929, "learning_rate": 0.0, "epoch": 1.2115035317860747, "percentage": 100.0, "elapsed_time": "3:29:07", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.19923825562000275, "epoch": 1.2115035317860747, "percentage": 100.0, "elapsed_time": "3:29:36", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "epoch": 1.2115035317860747, "percentage": 100.0, "elapsed_time": "3:29:43", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |