--- library_name: transformers license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: bert-router-teacher results: [] --- # bert-router-teacher This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0528 - Accuracy: 0.9925 - Precision: 0.9927 - Recall: 0.9925 - F1: 0.9925 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| | 0.9899 | 1.0 | 52 | 0.7205 | 0.6007 | 0.8170 | 0.6007 | 0.4836 | | 0.4364 | 2.0 | 104 | 0.1168 | 0.9888 | 0.9891 | 0.9888 | 0.9888 | | 0.0749 | 3.0 | 156 | 0.0616 | 0.9888 | 0.9891 | 0.9888 | 0.9888 | | 0.0371 | 4.0 | 208 | 0.0387 | 0.9925 | 0.9927 | 0.9925 | 0.9925 | | 0.0236 | 5.0 | 260 | 0.0457 | 0.9925 | 0.9927 | 0.9925 | 0.9925 | | 0.0111 | 6.0 | 312 | 0.0546 | 0.9925 | 0.9927 | 0.9925 | 0.9925 | | 0.0129 | 7.0 | 364 | 0.0499 | 0.9925 | 0.9927 | 0.9925 | 0.9925 | | 0.0072 | 8.0 | 416 | 0.0419 | 0.9888 | 0.9889 | 0.9888 | 0.9888 | | 0.0027 | 9.0 | 468 | 0.0510 | 0.9925 | 0.9927 | 0.9925 | 0.9925 | | 0.0062 | 10.0 | 520 | 0.0528 | 0.9925 | 0.9927 | 0.9925 | 0.9925 | ### Framework versions - Transformers 4.47.1 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.21.0