| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 780, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.282051282051282e-06, | |
| "loss": 0.4533, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 780, | |
| "total_flos": 813286136217600.0, | |
| "train_loss": 0.3118787203079615, | |
| "train_runtime": 82.0111, | |
| "train_samples_per_second": 151.809, | |
| "train_steps_per_second": 9.511 | |
| } | |
| ], | |
| "max_steps": 780, | |
| "num_train_epochs": 5, | |
| "total_flos": 813286136217600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |