{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 250, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.4, | |
"learning_rate": 0.0003, | |
"loss": 1.9296, | |
"step": 100 | |
}, | |
{ | |
"epoch": 0.8, | |
"learning_rate": 0.0003, | |
"loss": 1.7554, | |
"step": 200 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_accuracy": 0.6093164556962025, | |
"eval_loss": 1.7939746379852295, | |
"eval_runtime": 5.0177, | |
"eval_samples_per_second": 99.648, | |
"eval_steps_per_second": 12.556, | |
"step": 250 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_exact_match": 26.0, | |
"eval_f1": 36.71136363636365, | |
"step": 250 | |
} | |
], | |
"logging_steps": 100, | |
"max_steps": 12500, | |
"num_train_epochs": 50, | |
"save_steps": 500, | |
"total_flos": 1.5945416663105536e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |