{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 5.0, | |
"global_step": 1170, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 2.14, | |
"learning_rate": 3.130841121495327e-05, | |
"loss": 0.0728, | |
"step": 500 | |
}, | |
{ | |
"epoch": 4.27, | |
"learning_rate": 7.94392523364486e-06, | |
"loss": 0.004, | |
"step": 1000 | |
} | |
], | |
"max_steps": 1170, | |
"num_train_epochs": 5, | |
"total_flos": 8686173881157120.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |