| --- |
| license: mit |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: ADE-Bio_ClinicalBERT-NER |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # ADE-Bio_ClinicalBERT-NER |
| |
| This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1926 |
| - Precision: 0.7830 |
| - Recall: 0.8811 |
| - F1: 0.8291 |
| - Accuracy: 0.9437 |
| |
| ## 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: 1e-05 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 5 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | 0.2389 | 1.0 | 201 | 0.2100 | 0.7155 | 0.8292 | 0.7681 | 0.9263 | |
| | 0.0648 | 2.0 | 402 | 0.1849 | 0.7716 | 0.8711 | 0.8183 | 0.9392 | |
| | 0.2825 | 3.0 | 603 | 0.1856 | 0.7834 | 0.8788 | 0.8284 | 0.9422 | |
| | 0.199 | 4.0 | 804 | 0.1875 | 0.7796 | 0.8781 | 0.8259 | 0.9430 | |
| | 0.0404 | 5.0 | 1005 | 0.1926 | 0.7830 | 0.8811 | 0.8291 | 0.9437 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.21.0 |
| - Pytorch 1.12.0+cu113 |
| - Datasets 2.4.0 |
| - Tokenizers 0.12.1 |
| |
