| { | |
| "best_metric": 0.4181278600904661, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-2138", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2138, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23386342376052385, | |
| "grad_norm": 9.916498184204102, | |
| "learning_rate": 1.0352460846585169e-05, | |
| "loss": 0.588, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": 2.0442557334899902, | |
| "learning_rate": 9.709610570468354e-06, | |
| "loss": 0.5642, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7015902712815716, | |
| "grad_norm": 25.158737182617188, | |
| "learning_rate": 9.066760294351542e-06, | |
| "loss": 0.5358, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 21.2142276763916, | |
| "learning_rate": 8.423910018234727e-06, | |
| "loss": 0.5288, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6297594904899597, | |
| "eval_matthews_correlation": 0.4181278600904661, | |
| "eval_runtime": 0.8372, | |
| "eval_samples_per_second": 1245.804, | |
| "eval_steps_per_second": 78.833, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8552, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 32523851074704.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.0995311122701982e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 4, | |
| "seed": 21 | |
| } | |
| } | |