| { | |
| "best_metric": 0.0, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 56, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6070688962936401, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.8131, | |
| "eval_samples_per_second": 370.772, | |
| "eval_steps_per_second": 23.462, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.599613606929779, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.7913, | |
| "eval_samples_per_second": 373.662, | |
| "eval_steps_per_second": 23.645, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5782490372657776, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.8027, | |
| "eval_samples_per_second": 372.141, | |
| "eval_steps_per_second": 23.549, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.5808016061782837, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.7572, | |
| "eval_samples_per_second": 378.281, | |
| "eval_steps_per_second": 23.937, | |
| "step": 56 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 56, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.882860514195605e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 64, | |
| "seed": 11 | |
| } | |
| } | |