trainer_log.jsonl

{"current_steps": 1, "total_steps": 24, "loss": 2.3656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9786121534345265e-05, "epoch": 0.11, "percentage": 4.17, "elapsed_time": "0:00:04", "remaining_time": "0:01:38"}
{"current_steps": 2, "total_steps": 24, "loss": 2.3106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.914814565722671e-05, "epoch": 0.23, "percentage": 8.33, "elapsed_time": "0:00:08", "remaining_time": "0:01:34"}
{"current_steps": 3, "total_steps": 24, "loss": 2.2921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8096988312782174e-05, "epoch": 0.34, "percentage": 12.5, "elapsed_time": "0:00:12", "remaining_time": "0:01:29"}
{"current_steps": 4, "total_steps": 24, "loss": 2.1831, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.665063509461097e-05, "epoch": 0.46, "percentage": 16.67, "elapsed_time": "0:00:16", "remaining_time": "0:01:24"}
{"current_steps": 5, "total_steps": 24, "loss": 2.2563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4833833507280884e-05, "epoch": 0.57, "percentage": 20.83, "elapsed_time": "0:00:21", "remaining_time": "0:01:20"}
{"current_steps": 6, "total_steps": 24, "loss": 2.2585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.267766952966369e-05, "epoch": 0.69, "percentage": 25.0, "elapsed_time": "0:00:25", "remaining_time": "0:01:16"}
{"current_steps": 7, "total_steps": 24, "loss": 2.3297, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.021903572521802e-05, "epoch": 0.8, "percentage": 29.17, "elapsed_time": "0:00:29", "remaining_time": "0:01:11"}
{"current_steps": 8, "total_steps": 24, "loss": 2.2337, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7500000000000003e-05, "epoch": 0.91, "percentage": 33.33, "elapsed_time": "0:00:33", "remaining_time": "0:01:07"}
{"current_steps": 9, "total_steps": 24, "loss": 2.2176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.456708580912725e-05, "epoch": 1.03, "percentage": 37.5, "elapsed_time": "0:00:38", "remaining_time": "0:01:03"}
{"current_steps": 10, "total_steps": 24, "loss": 2.2138, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.147047612756302e-05, "epoch": 1.14, "percentage": 41.67, "elapsed_time": "0:00:42", "remaining_time": "0:00:59"}
{"current_steps": 11, "total_steps": 24, "loss": 2.23, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8263154805501297e-05, "epoch": 1.26, "percentage": 45.83, "elapsed_time": "0:00:46", "remaining_time": "0:00:55"}
{"current_steps": 12, "total_steps": 24, "loss": 2.2902, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 1.37, "percentage": 50.0, "elapsed_time": "0:00:50", "remaining_time": "0:00:50"}
{"current_steps": 13, "total_steps": 24, "loss": 2.2732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.173684519449872e-05, "epoch": 1.49, "percentage": 54.17, "elapsed_time": "0:00:55", "remaining_time": "0:00:47"}
{"current_steps": 14, "total_steps": 24, "loss": 2.2587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.852952387243698e-05, "epoch": 1.6, "percentage": 58.33, "elapsed_time": "0:01:00", "remaining_time": "0:00:42"}
{"current_steps": 15, "total_steps": 24, "loss": 2.1618, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5432914190872757e-05, "epoch": 1.71, "percentage": 62.5, "elapsed_time": "0:01:04", "remaining_time": "0:00:38"}
{"current_steps": 16, "total_steps": 24, "loss": 2.2363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2500000000000006e-05, "epoch": 1.83, "percentage": 66.67, "elapsed_time": "0:01:08", "remaining_time": "0:00:34"}
{"current_steps": 17, "total_steps": 24, "loss": 2.2207, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.780964274781984e-06, "epoch": 1.94, "percentage": 70.83, "elapsed_time": "0:01:12", "remaining_time": "0:00:29"}
{"current_steps": 18, "total_steps": 24, "loss": 2.2272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.3223304703363135e-06, "epoch": 2.06, "percentage": 75.0, "elapsed_time": "0:01:16", "remaining_time": "0:00:25"}
{"current_steps": 19, "total_steps": 24, "loss": 2.2384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.166166492719124e-06, "epoch": 2.17, "percentage": 79.17, "elapsed_time": "0:01:21", "remaining_time": "0:00:21"}
{"current_steps": 20, "total_steps": 24, "loss": 2.1726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890326e-06, "epoch": 2.29, "percentage": 83.33, "elapsed_time": "0:01:24", "remaining_time": "0:00:16"}
{"current_steps": 21, "total_steps": 24, "loss": 2.1893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9030116872178316e-06, "epoch": 2.4, "percentage": 87.5, "elapsed_time": "0:01:29", "remaining_time": "0:00:12"}
{"current_steps": 22, "total_steps": 24, "loss": 2.2168, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.51854342773295e-07, "epoch": 2.51, "percentage": 91.67, "elapsed_time": "0:01:34", "remaining_time": "0:00:08"}
{"current_steps": 23, "total_steps": 24, "loss": 2.2572, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1387846565474045e-07, "epoch": 2.63, "percentage": 95.83, "elapsed_time": "0:01:38", "remaining_time": "0:00:04"}
{"current_steps": 24, "total_steps": 24, "loss": 2.2699, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 2.74, "percentage": 100.0, "elapsed_time": "0:01:42", "remaining_time": "0:00:00"}
{"current_steps": 24, "total_steps": 24, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.74, "percentage": 100.0, "elapsed_time": "0:01:42", "remaining_time": "0:00:00"}