|
{ |
|
"best_metric": 0.06479227964096512, |
|
"best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/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": 0.6800838708877563, |
|
"eval_matthews_correlation": 0.06479227964096512, |
|
"eval_runtime": 1.3179, |
|
"eval_samples_per_second": 791.421, |
|
"eval_steps_per_second": 50.08, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.6333577036857605, |
|
"eval_matthews_correlation": 0.06354272869611655, |
|
"eval_runtime": 1.4106, |
|
"eval_samples_per_second": 739.39, |
|
"eval_steps_per_second": 46.788, |
|
"step": 108 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 270, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 1.420124179212326e-06, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 16, |
|
"seed": 26 |
|
} |
|
} |
|
|