| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.0, | |
| "global_step": 540, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 1.5518, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 540, | |
| "total_flos": 1957252753612800.0, | |
| "train_loss": 1.5197117346304434, | |
| "train_runtime": 534.2599, | |
| "train_samples_per_second": 3.931, | |
| "train_steps_per_second": 1.011 | |
| } | |
| ], | |
| "max_steps": 540, | |
| "num_train_epochs": 30, | |
| "total_flos": 1957252753612800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |