| { |
| "best_metric": 0.3237133903096396, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 2138, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47, |
| "grad_norm": 3.3132574558258057, |
| "learning_rate": 5.3487951435688824e-05, |
| "loss": 0.6128, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 10.235213279724121, |
| "learning_rate": 4.360838892447921e-05, |
| "loss": 0.5719, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6078479886054993, |
| "eval_matthews_correlation": 0.17287049484713765, |
| "eval_runtime": 0.8538, |
| "eval_samples_per_second": 1221.595, |
| "eval_steps_per_second": 77.301, |
| "step": 1069 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 9.716071128845215, |
| "learning_rate": 3.3728826413269603e-05, |
| "loss": 0.445, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.87, |
| "grad_norm": 7.158620834350586, |
| "learning_rate": 2.3849263902059996e-05, |
| "loss": 0.4148, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.7100014090538025, |
| "eval_matthews_correlation": 0.3237133903096396, |
| "eval_runtime": 0.8592, |
| "eval_samples_per_second": 1213.872, |
| "eval_steps_per_second": 76.813, |
| "step": 2138 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3207, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 75365670622848.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 6.336751394689843e-05, |
| "num_train_epochs": 3, |
| "per_device_train_batch_size": 8, |
| "seed": 33 |
| } |
| } |
|
|
