mistral-7b-medwiki-v1 / trainer_log.jsonl
chenhugging's picture
Upload folder using huggingface_hub
063c372 verified
{"current_steps": 10, "total_steps": 312, "loss": 1.7079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004987337087656614, "epoch": 0.03, "percentage": 3.21, "elapsed_time": "0:01:01", "remaining_time": "0:30:51"}
{"current_steps": 20, "total_steps": 312, "loss": 1.5881, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004949476630105669, "epoch": 0.06, "percentage": 6.41, "elapsed_time": "0:01:54", "remaining_time": "0:27:57"}
{"current_steps": 30, "total_steps": 312, "loss": 1.537, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004886802166271364, "epoch": 0.1, "percentage": 9.62, "elapsed_time": "0:02:56", "remaining_time": "0:27:42"}
{"current_steps": 40, "total_steps": 312, "loss": 1.6139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004799948609147061, "epoch": 0.13, "percentage": 12.82, "elapsed_time": "0:03:48", "remaining_time": "0:25:53"}
{"current_steps": 50, "total_steps": 312, "loss": 1.5905, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000468979581391722, "epoch": 0.16, "percentage": 16.03, "elapsed_time": "0:04:38", "remaining_time": "0:24:21"}
{"current_steps": 60, "total_steps": 312, "loss": 1.5532, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004557459664734141, "epoch": 0.19, "percentage": 19.23, "elapsed_time": "0:05:38", "remaining_time": "0:23:41"}
{"current_steps": 70, "total_steps": 312, "loss": 1.5624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004404280770443398, "epoch": 0.22, "percentage": 22.44, "elapsed_time": "0:06:28", "remaining_time": "0:22:21"}
{"current_steps": 80, "total_steps": 312, "loss": 1.566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00042318108837739987, "epoch": 0.26, "percentage": 25.64, "elapsed_time": "0:07:26", "remaining_time": "0:21:34"}
{"current_steps": 90, "total_steps": 312, "loss": 1.6084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004041797181571358, "epoch": 0.29, "percentage": 28.85, "elapsed_time": "0:08:21", "remaining_time": "0:20:35"}
{"current_steps": 100, "total_steps": 312, "loss": 1.5778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00038361645653195025, "epoch": 0.32, "percentage": 32.05, "elapsed_time": "0:09:29", "remaining_time": "0:20:08"}
{"current_steps": 110, "total_steps": 312, "loss": 1.5952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003616996161254065, "epoch": 0.35, "percentage": 35.26, "elapsed_time": "0:10:35", "remaining_time": "0:19:27"}
{"current_steps": 120, "total_steps": 312, "loss": 1.526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003386512217606339, "epoch": 0.38, "percentage": 38.46, "elapsed_time": "0:11:46", "remaining_time": "0:18:50"}
{"current_steps": 130, "total_steps": 312, "loss": 1.5188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00031470476127563017, "epoch": 0.42, "percentage": 41.67, "elapsed_time": "0:12:45", "remaining_time": "0:17:51"}
{"current_steps": 140, "total_steps": 312, "loss": 1.5547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002901028202144401, "epoch": 0.45, "percentage": 44.87, "elapsed_time": "0:13:48", "remaining_time": "0:16:57"}
{"current_steps": 150, "total_steps": 312, "loss": 1.4073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026509462435557154, "epoch": 0.48, "percentage": 48.08, "elapsed_time": "0:14:41", "remaining_time": "0:15:52"}
{"current_steps": 160, "total_steps": 312, "loss": 1.543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002399335149726463, "epoch": 0.51, "percentage": 51.28, "elapsed_time": "0:15:32", "remaining_time": "0:14:45"}
{"current_steps": 170, "total_steps": 312, "loss": 1.4798, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002148743824037269, "epoch": 0.54, "percentage": 54.49, "elapsed_time": "0:16:34", "remaining_time": "0:13:50"}
{"current_steps": 180, "total_steps": 312, "loss": 1.479, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019017108392811063, "epoch": 0.58, "percentage": 57.69, "elapsed_time": "0:17:29", "remaining_time": "0:12:49"}
{"current_steps": 190, "total_steps": 312, "loss": 1.5438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016607387210834887, "epoch": 0.61, "percentage": 60.9, "elapsed_time": "0:18:31", "remaining_time": "0:11:53"}
{"current_steps": 200, "total_steps": 312, "loss": 1.5179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014282685964923643, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "0:19:30", "remaining_time": "0:10:55"}
{"current_steps": 210, "total_steps": 312, "loss": 1.4537, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012066554645558578, "epoch": 0.67, "percentage": 67.31, "elapsed_time": "0:20:35", "remaining_time": "0:09:59"}
{"current_steps": 220, "total_steps": 312, "loss": 1.5523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.981443394050524e-05, "epoch": 0.7, "percentage": 70.51, "elapsed_time": "0:21:29", "remaining_time": "0:08:59"}
{"current_steps": 230, "total_steps": 312, "loss": 1.5372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.048475075202727e-05, "epoch": 0.74, "percentage": 73.72, "elapsed_time": "0:22:23", "remaining_time": "0:07:58"}
{"current_steps": 240, "total_steps": 312, "loss": 1.5376, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.28723129572247e-05, "epoch": 0.77, "percentage": 76.92, "elapsed_time": "0:23:16", "remaining_time": "0:06:59"}
{"current_steps": 250, "total_steps": 312, "loss": 1.5009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.715554036085673e-05, "epoch": 0.8, "percentage": 80.13, "elapsed_time": "0:24:15", "remaining_time": "0:06:01"}
{"current_steps": 260, "total_steps": 312, "loss": 1.5572, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890325e-05, "epoch": 0.83, "percentage": 83.33, "elapsed_time": "0:25:07", "remaining_time": "0:05:01"}
{"current_steps": 270, "total_steps": 312, "loss": 1.5053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2025038501977485e-05, "epoch": 0.86, "percentage": 86.54, "elapsed_time": "0:26:01", "remaining_time": "0:04:02"}
{"current_steps": 280, "total_steps": 312, "loss": 1.5444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.286588951321363e-05, "epoch": 0.9, "percentage": 89.74, "elapsed_time": "0:27:01", "remaining_time": "0:03:05"}
{"current_steps": 290, "total_steps": 312, "loss": 1.5053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.108987288226536e-06, "epoch": 0.93, "percentage": 92.95, "elapsed_time": "0:27:53", "remaining_time": "0:02:06"}
{"current_steps": 300, "total_steps": 312, "loss": 1.4731, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.822781475486507e-06, "epoch": 0.96, "percentage": 96.15, "elapsed_time": "0:28:55", "remaining_time": "0:01:09"}
{"current_steps": 310, "total_steps": 312, "loss": 1.5291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.069275378746796e-08, "epoch": 0.99, "percentage": 99.36, "elapsed_time": "0:29:56", "remaining_time": "0:00:11"}
{"current_steps": 312, "total_steps": 312, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:30:08", "remaining_time": "0:00:00"}