{ | |
"best_metric": 1.631608486175537, | |
"best_model_checkpoint": "./outputs/checkpoint-100", | |
"epoch": 0.07285974499089254, | |
"eval_steps": 100, | |
"global_step": 100, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.07, | |
"learning_rate": 0.0002, | |
"loss": 1.765, | |
"step": 100 | |
}, | |
{ | |
"epoch": 0.07, | |
"eval_loss": 1.631608486175537, | |
"eval_runtime": 430.1354, | |
"eval_samples_per_second": 14.586, | |
"eval_steps_per_second": 1.825, | |
"step": 100 | |
} | |
], | |
"logging_steps": 100, | |
"max_steps": 4116, | |
"num_train_epochs": 3, | |
"save_steps": 100, | |
"total_flos": 3.240742900390195e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |