| { | |
| "best_metric": 0.4778162027316995, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-536", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 536, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5673806071281433, | |
| "eval_matthews_correlation": 0.34158735475359947, | |
| "eval_runtime": 0.8364, | |
| "eval_samples_per_second": 1247.026, | |
| "eval_steps_per_second": 78.911, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 2.8179821968078613, | |
| "learning_rate": 5.866638175800345e-06, | |
| "loss": 0.4135, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5291661620140076, | |
| "eval_matthews_correlation": 0.4778162027316995, | |
| "eval_runtime": 0.7922, | |
| "eval_samples_per_second": 1316.659, | |
| "eval_steps_per_second": 83.317, | |
| "step": 536 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 536, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 95603170472208.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 8.734772395080514e-05, | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 32, | |
| "seed": 32 | |
| } | |
| } | |