| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "japanese-lora-alpaca/checkpoint-200", | |
| "epoch": 0.5119590432765379, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0, | |
| "loss": 1.9688795594149578e+30, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0, | |
| "loss": 1.317319656026326e+31, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0, | |
| "loss": 1.431492931568305e+30, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0, | |
| "loss": 1.2596809078781474e+29, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0, | |
| "loss": 7.78457860626805e+29, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0, | |
| "loss": 4.3205824045723626e+29, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0, | |
| "loss": 4.2652842037741146e+26, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0, | |
| "loss": 1.2042161347636073e+31, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.2e-05, | |
| "loss": 5.4732492073607035e+32, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.000102, | |
| "loss": 5.026698446384883e+28, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 104.6208, | |
| "eval_samples_per_second": 19.117, | |
| "eval_steps_per_second": 2.39, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 1170, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.59976249475072e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |