{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.15114873035066506, | |
"global_step": 500, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.15, | |
"learning_rate": 0.0009848851269649336, | |
"loss": 0.3001, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.15, | |
"eval_loss": 0.0005047954618930817, | |
"eval_runtime": 82.2643, | |
"eval_samples_per_second": 50.933, | |
"eval_steps_per_second": 3.185, | |
"step": 500 | |
} | |
], | |
"max_steps": 33080, | |
"num_train_epochs": 10, | |
"total_flos": 2446165278720000.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |