{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 5.0, | |
"global_step": 990, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 2.53, | |
"learning_rate": 2.474747474747475e-05, | |
"loss": 0.861, | |
"step": 500 | |
}, | |
{ | |
"epoch": 5.0, | |
"step": 990, | |
"train_runtime": 467.303, | |
"train_samples_per_second": 2.119 | |
} | |
], | |
"max_steps": 990, | |
"num_train_epochs": 5, | |
"total_flos": 4316063138500608, | |
"trial_name": null, | |
"trial_params": null | |
} | |