|
{ |
|
"best_metric": 0.0, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 108, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.6117144227027893, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 0.7419, |
|
"eval_samples_per_second": 1405.842, |
|
"eval_steps_per_second": 88.96, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.6092756390571594, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 0.8043, |
|
"eval_samples_per_second": 1296.819, |
|
"eval_steps_per_second": 82.061, |
|
"step": 108 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 108, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 5.958113215910997e-06, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 16, |
|
"seed": 27 |
|
} |
|
} |
|
|