|
{ |
|
"best_metric": 0.29149823245901346, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-428", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 428, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.5878534317016602, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 1.9866, |
|
"eval_samples_per_second": 525.026, |
|
"eval_steps_per_second": 65.943, |
|
"step": 214 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.8576925992965698, |
|
"eval_matthews_correlation": 0.29149823245901346, |
|
"eval_runtime": 2.7291, |
|
"eval_samples_per_second": 382.182, |
|
"eval_steps_per_second": 48.002, |
|
"step": 428 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 428, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 4.143357679659004e-05, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 4, |
|
"seed": 6 |
|
} |
|
} |
|
|