| { |
| "best_metric": 0.4485416394053661, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.4677268475210477, |
| "grad_norm": 3.7690486907958984, |
| "learning_rate": 1.636868177627337e-05, |
| "loss": 0.554, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9354536950420954, |
| "grad_norm": 5.957571983337402, |
| "learning_rate": 1.4679447330837522e-05, |
| "loss": 0.5117, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.4700559079647064, |
| "eval_matthews_correlation": 0.4485416394053661, |
| "eval_runtime": 0.765, |
| "eval_samples_per_second": 1363.429, |
| "eval_steps_per_second": 86.276, |
| "step": 1069 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5345, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 37724231373504.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 1.805791622170922e-05, |
| "num_train_epochs": 5, |
| "per_device_train_batch_size": 8, |
| "seed": 35 |
| } |
| } |
|
|
