| { | |
| "best_metric": 0.9055714011192322, | |
| "best_model_checkpoint": "./lora-alpaca/checkpoint-200", | |
| "epoch": 0.5144694533762058, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.8867, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 1.8339, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.699999999999999e-05, | |
| "loss": 1.6664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000117, | |
| "loss": 1.3046, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000147, | |
| "loss": 1.115, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 1.0706, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000204, | |
| "loss": 1.0269, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000234, | |
| "loss": 1.0012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 0.9608, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.000294, | |
| "loss": 0.9563, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00029166666666666664, | |
| "loss": 0.9512, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00028125, | |
| "loss": 0.9505, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002708333333333333, | |
| "loss": 0.9326, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026041666666666666, | |
| "loss": 0.9229, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00025, | |
| "loss": 0.918, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00023958333333333332, | |
| "loss": 0.9128, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00022916666666666664, | |
| "loss": 0.9021, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00021874999999999998, | |
| "loss": 0.9115, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00020833333333333332, | |
| "loss": 0.8915, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00019791666666666663, | |
| "loss": 0.8993, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.9055714011192322, | |
| "eval_runtime": 179.4765, | |
| "eval_samples_per_second": 11.144, | |
| "eval_steps_per_second": 0.696, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 388, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.591511325704192e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |