|
{ |
|
"best_metric": 0.5072784045554821, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-268", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 268, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.4657443165779114, |
|
"eval_matthews_correlation": 0.4751366513569292, |
|
"eval_runtime": 0.7348, |
|
"eval_samples_per_second": 1419.5, |
|
"eval_steps_per_second": 89.825, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.477949857711792, |
|
"eval_matthews_correlation": 0.5072784045554821, |
|
"eval_runtime": 0.8197, |
|
"eval_samples_per_second": 1272.339, |
|
"eval_steps_per_second": 80.512, |
|
"step": 268 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 268, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 3.3864170205221844e-05, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 64, |
|
"seed": 16 |
|
} |
|
} |
|
|