decilm-7b-ocn-v1 / trainer_log.jsonl
chenhugging's picture
Upload folder using huggingface_hub
c32ae89 verified
{"current_steps": 10, "total_steps": 203, "loss": 0.7395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.05, "percentage": 4.93, "elapsed_time": "0:00:37", "remaining_time": "0:12:04"}
{"current_steps": 20, "total_steps": 203, "loss": 0.1866, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004966952699028185, "epoch": 0.1, "percentage": 9.85, "elapsed_time": "0:01:13", "remaining_time": "0:11:11"}
{"current_steps": 30, "total_steps": 203, "loss": 0.1742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004868684495393958, "epoch": 0.15, "percentage": 14.78, "elapsed_time": "0:01:48", "remaining_time": "0:10:28"}
{"current_steps": 40, "total_steps": 203, "loss": 0.166, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047077933882184867, "epoch": 0.2, "percentage": 19.7, "elapsed_time": "0:02:26", "remaining_time": "0:09:56"}
{"current_steps": 50, "total_steps": 203, "loss": 0.1629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00044885329909757834, "epoch": 0.25, "percentage": 24.63, "elapsed_time": "0:03:02", "remaining_time": "0:09:19"}
{"current_steps": 60, "total_steps": 203, "loss": 0.1655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004216700075136953, "epoch": 0.29, "percentage": 29.56, "elapsed_time": "0:03:40", "remaining_time": "0:08:46"}
{"current_steps": 70, "total_steps": 203, "loss": 0.1509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00038994813160490117, "epoch": 0.34, "percentage": 34.48, "elapsed_time": "0:04:18", "remaining_time": "0:08:11"}
{"current_steps": 80, "total_steps": 203, "loss": 0.1558, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003545263292756348, "epoch": 0.39, "percentage": 39.41, "elapsed_time": "0:04:55", "remaining_time": "0:07:34"}
{"current_steps": 90, "total_steps": 203, "loss": 0.1634, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003163410764959277, "epoch": 0.44, "percentage": 44.33, "elapsed_time": "0:05:31", "remaining_time": "0:06:56"}
{"current_steps": 100, "total_steps": 203, "loss": 0.1579, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002764019088988165, "epoch": 0.49, "percentage": 49.26, "elapsed_time": "0:06:06", "remaining_time": "0:06:17"}
{"current_steps": 110, "total_steps": 203, "loss": 0.1534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023576473183801758, "epoch": 0.54, "percentage": 54.19, "elapsed_time": "0:06:43", "remaining_time": "0:05:41"}
{"current_steps": 120, "total_steps": 203, "loss": 0.1488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019550390453030946, "epoch": 0.59, "percentage": 59.11, "elapsed_time": "0:07:23", "remaining_time": "0:05:06"}
{"current_steps": 130, "total_steps": 203, "loss": 0.1505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001566838363176219, "epoch": 0.64, "percentage": 64.04, "elapsed_time": "0:08:00", "remaining_time": "0:04:29"}
{"current_steps": 140, "total_steps": 203, "loss": 0.1601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012033084598233163, "epoch": 0.69, "percentage": 68.97, "elapsed_time": "0:08:38", "remaining_time": "0:03:53"}
{"current_steps": 150, "total_steps": 203, "loss": 0.1611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.051861465390624e-05, "epoch": 0.74, "percentage": 73.89, "elapsed_time": "0:09:15", "remaining_time": "0:03:16"}
{"current_steps": 160, "total_steps": 203, "loss": 0.1447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.412305518878342e-05, "epoch": 0.79, "percentage": 78.82, "elapsed_time": "0:09:53", "remaining_time": "0:02:39"}
{"current_steps": 170, "total_steps": 203, "loss": 0.1454, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.948683851251877e-05, "epoch": 0.84, "percentage": 83.74, "elapsed_time": "0:10:31", "remaining_time": "0:02:02"}
{"current_steps": 180, "total_steps": 203, "loss": 0.1548, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0416135281218216e-05, "epoch": 0.88, "percentage": 88.67, "elapsed_time": "0:11:08", "remaining_time": "0:01:25"}
{"current_steps": 190, "total_steps": 203, "loss": 0.1504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.415133710424793e-06, "epoch": 0.93, "percentage": 93.6, "elapsed_time": "0:11:44", "remaining_time": "0:00:48"}
{"current_steps": 200, "total_steps": 203, "loss": 0.1288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.275522096146404e-07, "epoch": 0.98, "percentage": 98.52, "elapsed_time": "0:12:21", "remaining_time": "0:00:11"}
{"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": "0:12:33", "remaining_time": "0:00:00"}