{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"global_step": 40, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"learning_rate": 1.6000000000000003e-05, | |
"loss": 0.7052, | |
"step": 40 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_accuracy": 0.5633802816901409, | |
"eval_loss": 0.6902039051055908, | |
"eval_runtime": 0.5271, | |
"eval_samples_per_second": 134.707, | |
"eval_steps_per_second": 17.076, | |
"step": 40 | |
} | |
], | |
"max_steps": 200, | |
"num_train_epochs": 5, | |
"total_flos": 112927777720320.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |