|
{ |
|
"best_metric": 0.5373623427702773, |
|
"best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-2/checkpoint-28", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 28, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.5380865335464478, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 2.528, |
|
"eval_samples_per_second": 412.584, |
|
"eval_steps_per_second": 26.108, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.450260192155838, |
|
"eval_matthews_correlation": 0.5373623427702773, |
|
"eval_runtime": 2.6414, |
|
"eval_samples_per_second": 394.87, |
|
"eval_steps_per_second": 24.987, |
|
"step": 28 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 28, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 9.62287589751255e-05, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 32, |
|
"seed": 19 |
|
} |
|
} |
|
|