| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 992, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.994959677419355e-05, | |
| "loss": 10.8889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.4798387096774196e-05, | |
| "loss": 5.9914, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 992, | |
| "total_flos": 2400440637256200.0, | |
| "train_loss": 5.64251610059892, | |
| "train_runtime": 333.7038, | |
| "train_samples_per_second": 23.767, | |
| "train_steps_per_second": 2.973 | |
| } | |
| ], | |
| "max_steps": 992, | |
| "num_train_epochs": 1, | |
| "total_flos": 2400440637256200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |