{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 2.139130434782609, | |
"eval_steps": 500, | |
"global_step": 48, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.06, | |
"learning_rate": 0.00013142857142857143, | |
"loss": 2.5935, | |
"step": 23 | |
}, | |
{ | |
"epoch": 2.12, | |
"learning_rate": 0.00019290322580645163, | |
"loss": 2.186, | |
"step": 46 | |
} | |
], | |
"logging_steps": 23, | |
"max_steps": 345, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 436610374041600.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |