| { | |
| "best_metric": 1.3703529834747314, | |
| "best_model_checkpoint": "output/cocomelon/checkpoint-8", | |
| "epoch": 1.0, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 1.9273, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3703529834747314, | |
| "eval_runtime": 0.4903, | |
| "eval_samples_per_second": 20.397, | |
| "eval_steps_per_second": 4.079, | |
| "step": 8 | |
| } | |
| ], | |
| "max_steps": 8, | |
| "num_train_epochs": 1, | |
| "total_flos": 7577468928000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |