trainer_log.jsonl

{"current_steps": 10, "total_steps": 1500, "loss": 0.9551, "accuracy": 0.4749999940395355, "learning_rate": 4.999451708687114e-06, "epoch": 0.00918800964741013, "percentage": 0.67, "elapsed_time": "0:01:19", "remaining_time": "3:16:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 20, "total_steps": 1500, "loss": 0.923, "accuracy": 0.5874999761581421, "learning_rate": 4.997807075247147e-06, "epoch": 0.01837601929482026, "percentage": 1.33, "elapsed_time": "0:02:43", "remaining_time": "3:21:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 30, "total_steps": 1500, "loss": 0.9357, "accuracy": 0.5, "learning_rate": 4.9950668210706795e-06, "epoch": 0.02756402894223039, "percentage": 2.0, "elapsed_time": "0:03:58", "remaining_time": "3:14:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 40, "total_steps": 1500, "loss": 0.9215, "accuracy": 0.5249999761581421, "learning_rate": 4.9912321481237616e-06, "epoch": 0.03675203858964052, "percentage": 2.67, "elapsed_time": "0:05:15", "remaining_time": "3:12:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 50, "total_steps": 1500, "loss": 0.9464, "accuracy": 0.4749999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.04594004823705065, "percentage": 3.33, "elapsed_time": "0:06:32", "remaining_time": "3:09:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9397181868553162, "epoch": 0.04594004823705065, "percentage": 3.33, "elapsed_time": "0:06:57", "remaining_time": "3:21:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 60, "total_steps": 1500, "loss": 0.9318, "accuracy": 0.5625, "learning_rate": 4.980286753286196e-06, "epoch": 0.05512805788446078, "percentage": 4.0, "elapsed_time": "0:08:21", "remaining_time": "3:20:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 70, "total_steps": 1500, "loss": 0.9158, "accuracy": 0.75, "learning_rate": 4.973180832407471e-06, "epoch": 0.06431606753187091, "percentage": 4.67, "elapsed_time": "0:09:38", "remaining_time": "3:17:07", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 80, "total_steps": 1500, "loss": 0.9372, "accuracy": 0.5249999761581421, "learning_rate": 4.964990092676263e-06, "epoch": 0.07350407717928104, "percentage": 5.33, "elapsed_time": "0:10:56", "remaining_time": "3:14:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 90, "total_steps": 1500, "loss": 0.9324, "accuracy": 0.5625, "learning_rate": 4.9557181268217225e-06, "epoch": 0.08269208682669117, "percentage": 6.0, "elapsed_time": "0:12:15", "remaining_time": "3:11:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 100, "total_steps": 1500, "loss": 0.9353, "accuracy": 0.637499988079071, "learning_rate": 4.9453690018345144e-06, "epoch": 0.0918800964741013, "percentage": 6.67, "elapsed_time": "0:13:28", "remaining_time": "3:08:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9324077367782593, "epoch": 0.0918800964741013, "percentage": 6.67, "elapsed_time": "0:13:53", "remaining_time": "3:14:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 110, "total_steps": 1500, "loss": 0.934, "accuracy": 0.574999988079071, "learning_rate": 4.933947257182901e-06, "epoch": 0.10106810612151143, "percentage": 7.33, "elapsed_time": "0:15:15", "remaining_time": "3:12:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 120, "total_steps": 1500, "loss": 0.9202, "accuracy": 0.4749999940395355, "learning_rate": 4.921457902821578e-06, "epoch": 0.11025611576892155, "percentage": 8.0, "elapsed_time": "0:16:32", "remaining_time": "3:10:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 130, "total_steps": 1500, "loss": 0.9266, "accuracy": 0.625, "learning_rate": 4.907906416994146e-06, "epoch": 0.11944412541633169, "percentage": 8.67, "elapsed_time": "0:17:47", "remaining_time": "3:07:29", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 140, "total_steps": 1500, "loss": 0.9185, "accuracy": 0.512499988079071, "learning_rate": 4.893298743830168e-06, "epoch": 0.12863213506374183, "percentage": 9.33, "elapsed_time": "0:19:01", "remaining_time": "3:04:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 150, "total_steps": 1500, "loss": 0.9106, "accuracy": 0.5874999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.13782014471115195, "percentage": 10.0, "elapsed_time": "0:20:16", "remaining_time": "3:02:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9164085388183594, "epoch": 0.13782014471115195, "percentage": 10.0, "elapsed_time": "0:20:40", "remaining_time": "3:06:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 160, "total_steps": 1500, "loss": 0.9094, "accuracy": 0.625, "learning_rate": 4.860940925593703e-06, "epoch": 0.14700815435856207, "percentage": 10.67, "elapsed_time": "0:22:06", "remaining_time": "3:05:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 170, "total_steps": 1500, "loss": 0.9057, "accuracy": 0.5375000238418579, "learning_rate": 4.84320497372973e-06, "epoch": 0.1561961640059722, "percentage": 11.33, "elapsed_time": "0:23:27", "remaining_time": "3:03:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 180, "total_steps": 1500, "loss": 0.8954, "accuracy": 0.5249999761581421, "learning_rate": 4.824441214720629e-06, "epoch": 0.16538417365338234, "percentage": 12.0, "elapsed_time": "0:24:46", "remaining_time": "3:01:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 190, "total_steps": 1500, "loss": 0.8875, "accuracy": 0.625, "learning_rate": 4.804657878971252e-06, "epoch": 0.17457218330079247, "percentage": 12.67, "elapsed_time": "0:26:04", "remaining_time": "2:59:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 200, "total_steps": 1500, "loss": 0.8647, "accuracy": 0.6000000238418579, "learning_rate": 4.783863644106502e-06, "epoch": 0.1837601929482026, "percentage": 13.33, "elapsed_time": "0:27:19", "remaining_time": "2:57:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8702690005302429, "epoch": 0.1837601929482026, "percentage": 13.33, "elapsed_time": "0:27:44", "remaining_time": "3:00:16", "throughput": "0.00", "total_tokens": 0}