{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"global_step": 837, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.6, | |
"learning_rate": 2e-05, | |
"loss": 34.991, | |
"step": 500 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_loss": 14.8359375, | |
"eval_runtime": 48.5288, | |
"eval_samples_per_second": 369.121, | |
"eval_steps_per_second": 11.54, | |
"step": 837 | |
} | |
], | |
"max_steps": 8370, | |
"num_train_epochs": 10, | |
"total_flos": 1.2434141312188416e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |