| { | |
| "best_metric": 2.234222650527954, | |
| "best_model_checkpoint": "saves/ChineseLLaMA2-7B-Chat/lora/SFT/checkpoint-200", | |
| "epoch": 0.273972602739726, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000999995369868095, | |
| "loss": 4.0099, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0009999670749281082, | |
| "loss": 2.887, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000999913058797528, | |
| "loss": 2.6742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0009998333242552556, | |
| "loss": 2.7939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0009997278754032958, | |
| "loss": 2.6062, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0009995967176665461, | |
| "loss": 2.7508, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0009994398577925167, | |
| "loss": 2.547, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0009992573038509849, | |
| "loss": 2.5281, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0009990490652335784, | |
| "loss": 2.6397, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000998815152653293, | |
| "loss": 2.608, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000998555578143941, | |
| "loss": 2.4076, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009982703550595329, | |
| "loss": 2.5914, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0009979594980735896, | |
| "loss": 2.3517, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0009976230231783876, | |
| "loss": 2.4019, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0009972609476841367, | |
| "loss": 2.4481, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000996873290218089, | |
| "loss": 2.3244, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000996460070723581, | |
| "loss": 2.4821, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0009960213104590074, | |
| "loss": 2.438, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0009955570319967273, | |
| "loss": 2.2925, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0009950672592219031, | |
| "loss": 2.3052, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 2.3112449645996094, | |
| "eval_runtime": 8.9668, | |
| "eval_samples_per_second": 13.16, | |
| "eval_steps_per_second": 1.673, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.000994552017331272, | |
| "loss": 2.5839, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0009940113328318488, | |
| "loss": 2.4983, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0009934452335395637, | |
| "loss": 2.4598, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0009928537485778299, | |
| "loss": 2.4336, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0009922369083760461, | |
| "loss": 2.3799, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0009915947446680307, | |
| "loss": 2.5443, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0009909272904903897, | |
| "loss": 2.3701, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0009902345801808161, | |
| "loss": 2.2718, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0009895166493763246, | |
| "loss": 2.3402, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0009887735350114174, | |
| "loss": 2.4072, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000988005275316184, | |
| "loss": 2.3807, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000987211909814336, | |
| "loss": 2.2149, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000986393479321171, | |
| "loss": 2.2713, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0009855500259414753, | |
| "loss": 2.08, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0009846815930673563, | |
| "loss": 2.4682, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000983788225376011, | |
| "loss": 2.3328, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0009828699688274275, | |
| "loss": 2.3671, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0009819268706620196, | |
| "loss": 2.3251, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0009809589793981978, | |
| "loss": 2.4429, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0009799663448298724, | |
| "loss": 2.2499, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.234222650527954, | |
| "eval_runtime": 8.8394, | |
| "eval_samples_per_second": 13.349, | |
| "eval_steps_per_second": 1.697, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2190, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 5.897476754944819e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |