trainer_log.jsonl

{"current_steps": 1, "total_steps": 24, "loss": 2.06, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9786121534345265e-05, "epoch": 0.11, "percentage": 4.17, "elapsed_time": "0:00:03", "remaining_time": "0:01:26"}
{"current_steps": 2, "total_steps": 24, "loss": 2.0206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.914814565722671e-05, "epoch": 0.23, "percentage": 8.33, "elapsed_time": "0:00:07", "remaining_time": "0:01:21"}
{"current_steps": 3, "total_steps": 24, "loss": 2.0372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8096988312782174e-05, "epoch": 0.34, "percentage": 12.5, "elapsed_time": "0:00:10", "remaining_time": "0:01:16"}
{"current_steps": 4, "total_steps": 24, "loss": 1.9041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.665063509461097e-05, "epoch": 0.46, "percentage": 16.67, "elapsed_time": "0:00:14", "remaining_time": "0:01:11"}
{"current_steps": 5, "total_steps": 24, "loss": 2.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4833833507280884e-05, "epoch": 0.57, "percentage": 20.83, "elapsed_time": "0:00:18", "remaining_time": "0:01:08"}
{"current_steps": 6, "total_steps": 24, "loss": 1.9804, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.267766952966369e-05, "epoch": 0.69, "percentage": 25.0, "elapsed_time": "0:00:21", "remaining_time": "0:01:04"}
{"current_steps": 7, "total_steps": 24, "loss": 2.054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.021903572521802e-05, "epoch": 0.8, "percentage": 29.17, "elapsed_time": "0:00:25", "remaining_time": "0:01:01"}
{"current_steps": 8, "total_steps": 24, "loss": 1.9366, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7500000000000003e-05, "epoch": 0.91, "percentage": 33.33, "elapsed_time": "0:00:28", "remaining_time": "0:00:57"}
{"current_steps": 9, "total_steps": 24, "loss": 1.9305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.456708580912725e-05, "epoch": 1.03, "percentage": 37.5, "elapsed_time": "0:00:32", "remaining_time": "0:00:54"}
{"current_steps": 10, "total_steps": 24, "loss": 1.9426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.147047612756302e-05, "epoch": 1.14, "percentage": 41.67, "elapsed_time": "0:00:35", "remaining_time": "0:00:50"}
{"current_steps": 11, "total_steps": 24, "loss": 1.968, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8263154805501297e-05, "epoch": 1.26, "percentage": 45.83, "elapsed_time": "0:00:39", "remaining_time": "0:00:46"}
{"current_steps": 12, "total_steps": 24, "loss": 2.0241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 1.37, "percentage": 50.0, "elapsed_time": "0:00:43", "remaining_time": "0:00:43"}
{"current_steps": 13, "total_steps": 24, "loss": 1.9506, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.173684519449872e-05, "epoch": 1.49, "percentage": 54.17, "elapsed_time": "0:00:47", "remaining_time": "0:00:39"}
{"current_steps": 14, "total_steps": 24, "loss": 2.0218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.852952387243698e-05, "epoch": 1.6, "percentage": 58.33, "elapsed_time": "0:00:50", "remaining_time": "0:00:36"}
{"current_steps": 15, "total_steps": 24, "loss": 1.896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5432914190872757e-05, "epoch": 1.71, "percentage": 62.5, "elapsed_time": "0:00:54", "remaining_time": "0:00:32"}
{"current_steps": 16, "total_steps": 24, "loss": 1.9558, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2500000000000006e-05, "epoch": 1.83, "percentage": 66.67, "elapsed_time": "0:00:57", "remaining_time": "0:00:28"}
{"current_steps": 17, "total_steps": 24, "loss": 1.935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.780964274781984e-06, "epoch": 1.94, "percentage": 70.83, "elapsed_time": "0:01:01", "remaining_time": "0:00:25"}
{"current_steps": 18, "total_steps": 24, "loss": 1.9452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.3223304703363135e-06, "epoch": 2.06, "percentage": 75.0, "elapsed_time": "0:01:04", "remaining_time": "0:00:21"}
{"current_steps": 19, "total_steps": 24, "loss": 1.9464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.166166492719124e-06, "epoch": 2.17, "percentage": 79.17, "elapsed_time": "0:01:08", "remaining_time": "0:00:18"}
{"current_steps": 20, "total_steps": 24, "loss": 1.9029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890326e-06, "epoch": 2.29, "percentage": 83.33, "elapsed_time": "0:01:11", "remaining_time": "0:00:14"}
{"current_steps": 21, "total_steps": 24, "loss": 1.9304, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9030116872178316e-06, "epoch": 2.4, "percentage": 87.5, "elapsed_time": "0:01:15", "remaining_time": "0:00:10"}
{"current_steps": 22, "total_steps": 24, "loss": 1.9514, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.51854342773295e-07, "epoch": 2.51, "percentage": 91.67, "elapsed_time": "0:01:19", "remaining_time": "0:00:07"}
{"current_steps": 23, "total_steps": 24, "loss": 1.9894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1387846565474045e-07, "epoch": 2.63, "percentage": 95.83, "elapsed_time": "0:01:22", "remaining_time": "0:00:03"}
{"current_steps": 24, "total_steps": 24, "loss": 1.9986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 2.74, "percentage": 100.0, "elapsed_time": "0:01:26", "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": "0:01:26", "remaining_time": "0:00:00"}