| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.828854314002829, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0045, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.457742134484886e-05, | |
| "loss": 0.0074, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.915484268969772e-05, | |
| "loss": 0.0052, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.732264034546577e-06, | |
| "loss": 0.0022, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 2121, | |
| "num_train_epochs": 3, | |
| "total_flos": 419755402107600, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |