{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.16288767266093301, | |
"global_step": 5000, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.16, | |
"learning_rate": 2.8373729476153247e-05, | |
"loss": 1.6126, | |
"step": 5000 | |
}, | |
{ | |
"epoch": 0.16, | |
"eval_exact_match": 68.15336463223787, | |
"eval_f1": 73.98256617857639, | |
"eval_loss": 1.189887523651123, | |
"eval_runtime": 1542.7266, | |
"eval_samples_per_second": 7.463, | |
"eval_steps_per_second": 3.732, | |
"step": 5000 | |
} | |
], | |
"max_steps": 92088, | |
"num_train_epochs": 3, | |
"total_flos": 1.103235145728e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |