34b-beta-onc-v1 / trainer_log.jsonl
chenhugging's picture
Upload folder using huggingface_hub
ea729a8 verified
{"current_steps": 10, "total_steps": 203, "loss": 0.4995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.05, "percentage": 4.93, "elapsed_time": "0:02:23", "remaining_time": "0:46:02"}
{"current_steps": 20, "total_steps": 203, "loss": 0.1621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.1, "percentage": 9.85, "elapsed_time": "0:04:44", "remaining_time": "0:43:21"}
{"current_steps": 30, "total_steps": 203, "loss": 0.134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004963251406715272, "epoch": 0.15, "percentage": 14.78, "elapsed_time": "0:07:04", "remaining_time": "0:40:45"}
{"current_steps": 40, "total_steps": 203, "loss": 0.1341, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004854085994147815, "epoch": 0.2, "percentage": 19.7, "elapsed_time": "0:09:27", "remaining_time": "0:38:33"}
{"current_steps": 50, "total_steps": 203, "loss": 0.1183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00046757131025753886, "epoch": 0.25, "percentage": 24.63, "elapsed_time": "0:11:50", "remaining_time": "0:36:12"}
{"current_steps": 60, "total_steps": 203, "loss": 0.1224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00044333766942743246, "epoch": 0.29, "percentage": 29.56, "elapsed_time": "0:14:13", "remaining_time": "0:33:55"}
{"current_steps": 70, "total_steps": 203, "loss": 0.0917, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004134201186930015, "epoch": 0.34, "percentage": 34.48, "elapsed_time": "0:16:37", "remaining_time": "0:31:36"}
{"current_steps": 80, "total_steps": 203, "loss": 0.1262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00037869820037745775, "epoch": 0.39, "percentage": 39.41, "elapsed_time": "0:19:01", "remaining_time": "0:29:15"}
{"current_steps": 90, "total_steps": 203, "loss": 0.1079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003401926998041959, "epoch": 0.44, "percentage": 44.33, "elapsed_time": "0:21:21", "remaining_time": "0:26:49"}
{"current_steps": 100, "total_steps": 203, "loss": 0.0997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029903563535704927, "epoch": 0.49, "percentage": 49.26, "elapsed_time": "0:23:38", "remaining_time": "0:24:21"}
{"current_steps": 110, "total_steps": 203, "loss": 0.106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002564369784137472, "epoch": 0.54, "percentage": 54.19, "elapsed_time": "0:26:00", "remaining_time": "0:21:59"}
{"current_steps": 120, "total_steps": 203, "loss": 0.1139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021364908154907752, "epoch": 0.59, "percentage": 59.11, "elapsed_time": "0:28:32", "remaining_time": "0:19:44"}
{"current_steps": 130, "total_steps": 203, "loss": 0.1102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017192986077855136, "epoch": 0.64, "percentage": 64.04, "elapsed_time": "0:30:54", "remaining_time": "0:17:21"}
{"current_steps": 140, "total_steps": 203, "loss": 0.119, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001325058142431701, "epoch": 0.69, "percentage": 68.97, "elapsed_time": "0:33:19", "remaining_time": "0:14:59"}
{"current_steps": 150, "total_steps": 203, "loss": 0.1091, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.653596454434699e-05, "epoch": 0.74, "percentage": 73.89, "elapsed_time": "0:35:42", "remaining_time": "0:12:37"}
{"current_steps": 160, "total_steps": 203, "loss": 0.1065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.507778478375834e-05, "epoch": 0.79, "percentage": 78.82, "elapsed_time": "0:38:07", "remaining_time": "0:10:14"}
{"current_steps": 170, "total_steps": 203, "loss": 0.1032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.905611004420359e-05, "epoch": 0.84, "percentage": 83.74, "elapsed_time": "0:40:31", "remaining_time": "0:07:52"}
{"current_steps": 180, "total_steps": 203, "loss": 0.1177, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9235948278956e-05, "epoch": 0.88, "percentage": 88.67, "elapsed_time": "0:42:56", "remaining_time": "0:05:29"}
{"current_steps": 190, "total_steps": 203, "loss": 0.1115, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.199989938854372e-06, "epoch": 0.93, "percentage": 93.6, "elapsed_time": "0:45:15", "remaining_time": "0:03:05"}
{"current_steps": 200, "total_steps": 203, "loss": 0.1014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.314775287923677e-07, "epoch": 0.98, "percentage": 98.52, "elapsed_time": "0:47:38", "remaining_time": "0:00:42"}
{"current_steps": 203, "total_steps": 203, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:48:22", "remaining_time": "0:00:00"}