| {"current_steps": 10, "total_steps": 1500, "loss": 0.9377, "accuracy": 0.4000000059604645, "learning_rate": 4.999451708687114e-06, "epoch": 0.008594757198109154, "percentage": 0.67, "elapsed_time": "0:01:10", "remaining_time": "2:55:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.9352, "accuracy": 0.574999988079071, "learning_rate": 4.997807075247147e-06, "epoch": 0.017189514396218308, "percentage": 1.33, "elapsed_time": "0:02:24", "remaining_time": "2:58:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9351, "accuracy": 0.4749999940395355, "learning_rate": 4.9950668210706795e-06, "epoch": 0.02578427159432746, "percentage": 2.0, "elapsed_time": "0:03:36", "remaining_time": "2:56:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.922, "accuracy": 0.44999998807907104, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:46", "remaining_time": "2:54:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9201, "accuracy": 0.5375000238418579, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:01", "remaining_time": "2:54:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9226060509681702, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:27", "remaining_time": "3:07:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9356, "accuracy": 0.512499988079071, "learning_rate": 4.980286753286196e-06, "epoch": 0.05156854318865492, "percentage": 4.0, "elapsed_time": "0:07:48", "remaining_time": "3:07:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9257, "accuracy": 0.550000011920929, "learning_rate": 4.973180832407471e-06, "epoch": 0.060163300386764075, "percentage": 4.67, "elapsed_time": "0:09:05", "remaining_time": "3:05:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9168, "accuracy": 0.5, "learning_rate": 4.964990092676263e-06, "epoch": 0.06875805758487323, "percentage": 5.33, "elapsed_time": "0:10:21", "remaining_time": "3:03:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9273, "accuracy": 0.5249999761581421, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:38", "remaining_time": "3:02:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9009, "accuracy": 0.574999988079071, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:53", "remaining_time": "3:00:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9138591885566711, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:19", "remaining_time": "3:06:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.916, "accuracy": 0.4625000059604645, "learning_rate": 4.933947257182901e-06, "epoch": 0.09454232917920069, "percentage": 7.33, "elapsed_time": "0:14:42", "remaining_time": "3:05:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9167, "accuracy": 0.550000011920929, "learning_rate": 4.921457902821578e-06, "epoch": 0.10313708637730984, "percentage": 8.0, "elapsed_time": "0:15:55", "remaining_time": "3:03:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.9087, "accuracy": 0.5249999761581421, "learning_rate": 4.907906416994146e-06, "epoch": 0.11173184357541899, "percentage": 8.67, "elapsed_time": "0:17:09", "remaining_time": "3:00:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9053, "accuracy": 0.612500011920929, "learning_rate": 4.893298743830168e-06, "epoch": 0.12032660077352815, "percentage": 9.33, "elapsed_time": "0:18:25", "remaining_time": "2:58:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.8999, "accuracy": 0.625, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:38", "remaining_time": "2:56:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8956203460693359, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:20:03", "remaining_time": "3:00:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.8907, "accuracy": 0.5874999761581421, "learning_rate": 4.860940925593703e-06, "epoch": 0.13751611516974646, "percentage": 10.67, "elapsed_time": "0:21:28", "remaining_time": "2:59:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.8831, "accuracy": 0.612500011920929, "learning_rate": 4.84320497372973e-06, "epoch": 0.1461108723678556, "percentage": 11.33, "elapsed_time": "0:22:43", "remaining_time": "2:57:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.8736, "accuracy": 0.5375000238418579, "learning_rate": 4.824441214720629e-06, "epoch": 0.15470562956596476, "percentage": 12.0, "elapsed_time": "0:23:59", "remaining_time": "2:55:57", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.884, "accuracy": 0.625, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:25:12", "remaining_time": "2:53:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.8419, "accuracy": 0.612500011920929, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:25", "remaining_time": "2:51:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8462886810302734, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:50", "remaining_time": "2:54:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.8187, "accuracy": 0.612500011920929, "learning_rate": 4.762067631165049e-06, "epoch": 0.18048990116029223, "percentage": 14.0, "elapsed_time": "0:28:11", "remaining_time": "2:53:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.8448, "accuracy": 0.675000011920929, "learning_rate": 4.7392794005985324e-06, "epoch": 0.18908465835840138, "percentage": 14.67, "elapsed_time": "0:29:24", "remaining_time": "2:51:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.8066, "accuracy": 0.6625000238418579, "learning_rate": 4.715508948078037e-06, "epoch": 0.19767941555651053, "percentage": 15.33, "elapsed_time": "0:30:39", "remaining_time": "2:49:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.7787, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:52", "remaining_time": "2:47:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.7776, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:08", "remaining_time": "2:45:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7469337582588196, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:34", "remaining_time": "2:47:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.6981, "accuracy": 0.7124999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.22346368715083798, "percentage": 17.33, "elapsed_time": "0:34:55", "remaining_time": "2:46:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7174, "accuracy": 0.7250000238418579, "learning_rate": 4.610819813755038e-06, "epoch": 0.23205844434894715, "percentage": 18.0, "elapsed_time": "0:36:11", "remaining_time": "2:44:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.6972, "accuracy": 0.6625000238418579, "learning_rate": 4.582303101775249e-06, "epoch": 0.2406532015470563, "percentage": 18.67, "elapsed_time": "0:37:27", "remaining_time": "2:43:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.6192, "accuracy": 0.612500011920929, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:45", "remaining_time": "2:41:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.5721, "accuracy": 0.612500011920929, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:00", "remaining_time": "2:40:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5730626583099365, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:40:26", "remaining_time": "2:41:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.5091, "accuracy": 0.762499988079071, "learning_rate": 4.491324795060491e-06, "epoch": 0.2664374731413838, "percentage": 20.67, "elapsed_time": "0:41:47", "remaining_time": "2:40:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.5352, "accuracy": 0.675000011920929, "learning_rate": 4.4592336433146e-06, "epoch": 0.2750322303394929, "percentage": 21.33, "elapsed_time": "0:43:02", "remaining_time": "2:38:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.5397, "accuracy": 0.6000000238418579, "learning_rate": 4.426283106939474e-06, "epoch": 0.28362698753760207, "percentage": 22.0, "elapsed_time": "0:44:19", "remaining_time": "2:37:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.4817, "accuracy": 0.699999988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2922217447357112, "percentage": 22.67, "elapsed_time": "0:45:39", "remaining_time": "2:35:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.5098, "accuracy": 0.574999988079071, "learning_rate": 4.357862063693486e-06, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:46:54", "remaining_time": "2:34:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5162621736526489, "epoch": 0.30081650193382037, "percentage": 23.33, "elapsed_time": "0:47:20", "remaining_time": "2:35:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.5046, "accuracy": 0.675000011920929, "learning_rate": 4.322421568553529e-06, "epoch": 0.3094112591319295, "percentage": 24.0, "elapsed_time": "0:48:36", "remaining_time": "2:33:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.4526, "accuracy": 0.800000011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.31800601633003867, "percentage": 24.67, "elapsed_time": "0:49:52", "remaining_time": "2:32:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.4879, "accuracy": 0.675000011920929, "learning_rate": 4.249158351283414e-06, "epoch": 0.3266007735281478, "percentage": 25.33, "elapsed_time": "0:51:07", "remaining_time": "2:30:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.4776, "accuracy": 0.625, "learning_rate": 4.211367764821722e-06, "epoch": 0.33519553072625696, "percentage": 26.0, "elapsed_time": "0:52:21", "remaining_time": "2:29:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.4686, "accuracy": 0.6875, "learning_rate": 4.172826515897146e-06, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:53:32", "remaining_time": "2:27:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.46578800678253174, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:53:58", "remaining_time": "2:28:25", "throughput": "0.00", "total_tokens": 0} | |