{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 212, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"learning_rate": 0.00019900471698113207, | |
"loss": 6.1329, | |
"step": 212 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_loss": 5.14426851272583, | |
"eval_runtime": 3.8194, | |
"eval_samples_per_second": 176.991, | |
"eval_steps_per_second": 22.255, | |
"step": 212 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 42400, | |
"num_train_epochs": 200, | |
"save_steps": 500, | |
"total_flos": 283175043047088.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |