{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.9979825151311366, | |
"eval_steps": 500, | |
"global_step": 371, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.8, | |
"learning_rate": 4.4444444444444447e-05, | |
"loss": 2.0753, | |
"step": 297 | |
} | |
], | |
"logging_steps": 297, | |
"max_steps": 371, | |
"num_train_epochs": 1, | |
"save_steps": 500, | |
"total_flos": 4.311595551125668e+17, | |
"trial_name": null, | |
"trial_params": null | |
} | |