| { | |
| "best_metric": 0.3489786582473965, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/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": 0.23, | |
| "learning_rate": 2.0303810286193334e-06, | |
| "loss": 0.6094, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.9043017297731252e-06, | |
| "loss": 0.5899, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.7782224309269175e-06, | |
| "loss": 0.5665, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.6521431320807095e-06, | |
| "loss": 0.5457, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5572062730789185, | |
| "eval_matthews_correlation": 0.3489786582473965, | |
| "eval_runtime": 0.7167, | |
| "eval_samples_per_second": 1455.295, | |
| "eval_steps_per_second": 92.09, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8552, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 32728761582000.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.1564603274655414e-06, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 4, | |
| "seed": 27 | |
| } | |
| } | |