{ | |
"best_metric": 0.0, | |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069", | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 1069, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.47, | |
"learning_rate": 9.447053301406701e-07, | |
"loss": 0.6327, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.94, | |
"learning_rate": 7.702122880016472e-07, | |
"loss": 0.5907, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_loss": 0.5891121625900269, | |
"eval_matthews_correlation": 0.0, | |
"eval_runtime": 0.6963, | |
"eval_samples_per_second": 1497.889, | |
"eval_steps_per_second": 94.785, | |
"step": 1069 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 3207, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 37877396803200.0, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 1.119198372279693e-06, | |
"num_train_epochs": 3, | |
"per_device_train_batch_size": 8, | |
"seed": 19 | |
} | |
} | |