TianyiQ's picture
Upload ./trainer_log.jsonl with huggingface_hub
dd1f4f7 verified
{"current_steps": 1, "total_steps": 48, "loss": 0.9436, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 2.08, "elapsed_time": "0:00:05", "remaining_time": "0:04:25"}
{"current_steps": 3, "total_steps": 48, "loss": 0.8831, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.5e-07, "epoch": 0.0625, "percentage": 6.25, "elapsed_time": "0:00:07", "remaining_time": "0:01:48"}
{"current_steps": 5, "total_steps": 48, "loss": null, "eval_loss": 0.9745497703552246, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.10416666666666667, "percentage": 10.42, "elapsed_time": "0:00:08", "remaining_time": "0:01:14"}
{"current_steps": 6, "total_steps": 48, "loss": 1.005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.125, "percentage": 12.5, "elapsed_time": "0:00:10", "remaining_time": "0:01:11"}
{"current_steps": 9, "total_steps": 48, "loss": 0.8656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.865909090909091e-06, "epoch": 0.1875, "percentage": 18.75, "elapsed_time": "0:00:12", "remaining_time": "0:00:53"}
{"current_steps": 10, "total_steps": 48, "loss": null, "eval_loss": 0.8130785822868347, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.20833333333333334, "percentage": 20.83, "elapsed_time": "0:00:12", "remaining_time": "0:00:49"}
{"current_steps": 12, "total_steps": 48, "loss": 0.7828, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6647727272727274e-06, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:01:00", "remaining_time": "0:03:02"}
{"current_steps": 15, "total_steps": 48, "loss": 0.834, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4636363636363635e-06, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:03", "remaining_time": "0:02:18"}
{"current_steps": 15, "total_steps": 48, "loss": null, "eval_loss": 0.802370548248291, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:03", "remaining_time": "0:02:18"}
{"current_steps": 18, "total_steps": 48, "loss": 0.7683, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2625e-06, "epoch": 0.375, "percentage": 37.5, "elapsed_time": "0:01:06", "remaining_time": "0:01:50"}
{"current_steps": 20, "total_steps": 48, "loss": null, "eval_loss": 0.7906376719474792, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 41.67, "elapsed_time": "0:01:08", "remaining_time": "0:01:35"}
{"current_steps": 21, "total_steps": 48, "loss": 0.7992, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0613636363636364e-06, "epoch": 0.4375, "percentage": 43.75, "elapsed_time": "0:01:57", "remaining_time": "0:02:30"}
{"current_steps": 24, "total_steps": 48, "loss": 0.7188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8602272727272725e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:01:59", "remaining_time": "0:01:59"}
{"current_steps": 25, "total_steps": 48, "loss": null, "eval_loss": 0.7848005294799805, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5208333333333334, "percentage": 52.08, "elapsed_time": "0:01:59", "remaining_time": "0:01:50"}
{"current_steps": 27, "total_steps": 48, "loss": 0.7912, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.659090909090909e-06, "epoch": 0.5625, "percentage": 56.25, "elapsed_time": "0:02:01", "remaining_time": "0:01:34"}
{"current_steps": 30, "total_steps": 48, "loss": 0.8186, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4579545454545454e-06, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:03", "remaining_time": "0:01:14"}
{"current_steps": 30, "total_steps": 48, "loss": null, "eval_loss": 0.7805004119873047, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:03", "remaining_time": "0:01:14"}
{"current_steps": 33, "total_steps": 48, "loss": 0.6864, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2568181818181817e-06, "epoch": 0.6875, "percentage": 68.75, "elapsed_time": "0:02:54", "remaining_time": "0:01:19"}
{"current_steps": 35, "total_steps": 48, "loss": null, "eval_loss": 0.7762691378593445, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7291666666666666, "percentage": 72.92, "elapsed_time": "0:02:55", "remaining_time": "0:01:05"}
{"current_steps": 36, "total_steps": 48, "loss": 0.7509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0556818181818182e-06, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:02:57", "remaining_time": "0:00:59"}
{"current_steps": 39, "total_steps": 48, "loss": 0.7036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.545454545454544e-07, "epoch": 0.8125, "percentage": 81.25, "elapsed_time": "0:02:59", "remaining_time": "0:00:41"}
{"current_steps": 40, "total_steps": 48, "loss": null, "eval_loss": 0.7741249203681946, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 83.33, "elapsed_time": "0:02:59", "remaining_time": "0:00:35"}
{"current_steps": 42, "total_steps": 48, "loss": 0.7763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.534090909090911e-07, "epoch": 0.875, "percentage": 87.5, "elapsed_time": "0:03:50", "remaining_time": "0:00:32"}
{"current_steps": 45, "total_steps": 48, "loss": 0.8125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.522727272727273e-07, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:52", "remaining_time": "0:00:15"}
{"current_steps": 45, "total_steps": 48, "loss": null, "eval_loss": 0.7722158432006836, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:52", "remaining_time": "0:00:15"}
{"current_steps": 48, "total_steps": 48, "loss": 0.8029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.511363636363638e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:55", "remaining_time": "0:00:00"}
{"current_steps": 48, "total_steps": 48, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:55", "remaining_time": "0:00:00"}
{"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.7741249203681946, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:04:33", "remaining_time": "0:00:00"}