| {"current_steps": 10, "total_steps": 1500, "loss": 0.9442, "accuracy": 0.4124999940395355, "learning_rate": 4.999451708687114e-06, "epoch": 0.008594757198109154, "percentage": 0.67, "elapsed_time": "0:01:09", "remaining_time": "2:51:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.928, "accuracy": 0.550000011920929, "learning_rate": 4.997807075247147e-06, "epoch": 0.017189514396218308, "percentage": 1.33, "elapsed_time": "0:02:23", "remaining_time": "2:57:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9439, "accuracy": 0.4375, "learning_rate": 4.9950668210706795e-06, "epoch": 0.02578427159432746, "percentage": 2.0, "elapsed_time": "0:03:37", "remaining_time": "2:57:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9184, "accuracy": 0.4124999940395355, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:48", "remaining_time": "2:55:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.5249999761581421, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:03", "remaining_time": "2:55:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9324354529380798, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:29", "remaining_time": "3:08:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9323, "accuracy": 0.5, "learning_rate": 4.980286753286196e-06, "epoch": 0.05156854318865492, "percentage": 4.0, "elapsed_time": "0:07:47", "remaining_time": "3:07:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9172, "accuracy": 0.48750001192092896, "learning_rate": 4.973180832407471e-06, "epoch": 0.060163300386764075, "percentage": 4.67, "elapsed_time": "0:09:01", "remaining_time": "3:04:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9245, "accuracy": 0.48750001192092896, "learning_rate": 4.964990092676263e-06, "epoch": 0.06875805758487323, "percentage": 5.33, "elapsed_time": "0:10:16", "remaining_time": "3:02:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9359, "accuracy": 0.5, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:30", "remaining_time": "3:00:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9066, "accuracy": 0.5874999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:42", "remaining_time": "2:57:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9236211180686951, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:08", "remaining_time": "3:03:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.929, "accuracy": 0.44999998807907104, "learning_rate": 4.933947257182901e-06, "epoch": 0.09454232917920069, "percentage": 7.33, "elapsed_time": "0:14:26", "remaining_time": "3:02:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9299, "accuracy": 0.5874999761581421, "learning_rate": 4.921457902821578e-06, "epoch": 0.10313708637730984, "percentage": 8.0, "elapsed_time": "0:15:43", "remaining_time": "3:00:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.9109, "accuracy": 0.5375000238418579, "learning_rate": 4.907906416994146e-06, "epoch": 0.11173184357541899, "percentage": 8.67, "elapsed_time": "0:16:56", "remaining_time": "2:58:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9138, "accuracy": 0.5625, "learning_rate": 4.893298743830168e-06, "epoch": 0.12032660077352815, "percentage": 9.33, "elapsed_time": "0:18:12", "remaining_time": "2:56:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.9157, "accuracy": 0.574999988079071, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:26", "remaining_time": "2:54:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.909102737903595, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:52", "remaining_time": "2:58:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.9, "accuracy": 0.512499988079071, "learning_rate": 4.860940925593703e-06, "epoch": 0.13751611516974646, "percentage": 10.67, "elapsed_time": "0:21:11", "remaining_time": "2:57:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.896, "accuracy": 0.637499988079071, "learning_rate": 4.84320497372973e-06, "epoch": 0.1461108723678556, "percentage": 11.33, "elapsed_time": "0:22:25", "remaining_time": "2:55:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.8911, "accuracy": 0.5625, "learning_rate": 4.824441214720629e-06, "epoch": 0.15470562956596476, "percentage": 12.0, "elapsed_time": "0:23:38", "remaining_time": "2:53:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.9002, "accuracy": 0.6000000238418579, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:24:53", "remaining_time": "2:51:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.8773, "accuracy": 0.574999988079071, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:03", "remaining_time": "2:49:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8721462488174438, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:28", "remaining_time": "2:52:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.8484, "accuracy": 0.5375000238418579, "learning_rate": 4.762067631165049e-06, "epoch": 0.18048990116029223, "percentage": 14.0, "elapsed_time": "0:27:50", "remaining_time": "2:50:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.8499, "accuracy": 0.637499988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.18908465835840138, "percentage": 14.67, "elapsed_time": "0:29:05", "remaining_time": "2:49:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.826, "accuracy": 0.6499999761581421, "learning_rate": 4.715508948078037e-06, "epoch": 0.19767941555651053, "percentage": 15.33, "elapsed_time": "0:30:18", "remaining_time": "2:47:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.7992, "accuracy": 0.637499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:33", "remaining_time": "2:45:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.7848, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:32:47", "remaining_time": "2:43:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7728626728057861, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:12", "remaining_time": "2:46:04", "throughput": "0.00", "total_tokens": 0} | |