| { | |
| "best_metric": 0.4219587641967578, | |
| "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": 13.482518196105957, | |
| "learning_rate": 7.034296344775407e-06, | |
| "loss": 0.5589, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 10.600051879882812, | |
| "learning_rate": 6.308362769463187e-06, | |
| "loss": 0.5047, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4949962794780731, | |
| "eval_matthews_correlation": 0.4219587641967578, | |
| "eval_runtime": 0.7754, | |
| "eval_samples_per_second": 1345.165, | |
| "eval_steps_per_second": 85.121, | |
| "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": 37738719995232.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 7.760229920087626e-06, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 8, | |
| "seed": 19 | |
| } | |
| } | |