|
{ |
|
"best_metric": 0.42854888313294803, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 5.944660653119031e-06, |
|
"loss": 0.5558, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 5.157496901381872e-06, |
|
"loss": 0.5053, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.4907635748386383, |
|
"eval_matthews_correlation": 0.42854888313294803, |
|
"eval_runtime": 0.8054, |
|
"eval_samples_per_second": 1295.012, |
|
"eval_steps_per_second": 81.947, |
|
"step": 1069 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 4276, |
|
"num_train_epochs": 4, |
|
"save_steps": 500, |
|
"total_flos": 38129912781888.0, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 6.7318244048561916e-06, |
|
"num_train_epochs": 4, |
|
"per_device_train_batch_size": 8, |
|
"seed": 14 |
|
} |
|
} |
|
|