| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.8198, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9822222222222222, | |
| "eval_loss": 0.19010965526103973, | |
| "eval_runtime": 3.2652, | |
| "eval_samples_per_second": 68.909, | |
| "eval_steps_per_second": 2.45, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 16, | |
| "total_flos": 5.03347841321472e+16, | |
| "train_loss": 0.6244367808103561, | |
| "train_runtime": 54.3895, | |
| "train_samples_per_second": 37.231, | |
| "train_steps_per_second": 0.294 | |
| } | |
| ], | |
| "max_steps": 16, | |
| "num_train_epochs": 1, | |
| "total_flos": 5.03347841321472e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |