|
{ |
|
"best_metric": 0.0, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-268", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 536, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.6024530529975891, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 0.6923, |
|
"eval_samples_per_second": 1506.579, |
|
"eval_steps_per_second": 95.335, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 8.802625776355687e-07, |
|
"loss": 0.6062, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.5769068598747253, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 0.7747, |
|
"eval_samples_per_second": 1346.272, |
|
"eval_steps_per_second": 85.191, |
|
"step": 536 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1072, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 500, |
|
"total_flos": 96433161516912.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 1.6497228727715551e-06, |
|
"num_train_epochs": 4, |
|
"per_device_train_batch_size": 32, |
|
"seed": 35 |
|
} |
|
} |
|
|