{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 88, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.57, | |
"learning_rate": 1.0000000000000002e-06, | |
"loss": 1.1548, | |
"step": 50 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_accuracy": 0.8442857142857143, | |
"eval_f1": 0.9080168776371309, | |
"eval_loss": 0.3905762732028961, | |
"eval_runtime": 83.2329, | |
"eval_samples_per_second": 8.41, | |
"eval_steps_per_second": 0.264, | |
"step": 88 | |
} | |
], | |
"logging_steps": 50, | |
"max_steps": 264, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 370908716236800.0, | |
"train_batch_size": 32, | |
"trial_name": null, | |
"trial_params": null | |
} | |