| --- |
| license: apache-2.0 |
| base_model: PlanTL-GOB-ES/bsc-bio-ehr-es |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| model-index: |
| - name: vih_explainability |
| 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. --> |
|
|
| # vih_explainability |
| |
| This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3980 |
| - Roc Auc: 0.8920 |
| - Ap Score: 0.8575 |
| - Precision: 0.8926 |
| - Recall: 0.8920 |
| - F1: 0.8919 |
| |
| ## 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: 9e-06 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 10 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Roc Auc | Ap Score | Precision | Recall | F1 | |
| |:-------------:|:------:|:----:|:---------------:|:-------:|:--------:|:---------:|:------:|:------:| |
| | 0.62 | 0.5376 | 50 | 0.5331 | 0.7789 | 0.7389 | 0.7905 | 0.7789 | 0.7763 | |
| | 0.5106 | 1.0753 | 100 | 0.4343 | 0.7899 | 0.7614 | 0.8118 | 0.7899 | 0.7856 | |
| | 0.3762 | 1.6129 | 150 | 0.3364 | 0.8594 | 0.8075 | 0.8596 | 0.8594 | 0.8594 | |
| | 0.2878 | 2.1505 | 200 | 0.3582 | 0.8597 | 0.8260 | 0.8636 | 0.8597 | 0.8591 | |
| | 0.2556 | 2.6882 | 250 | 0.3121 | 0.8706 | 0.8440 | 0.8764 | 0.8706 | 0.8698 | |
| | 0.165 | 3.2258 | 300 | 0.3746 | 0.8652 | 0.8349 | 0.8699 | 0.8652 | 0.8645 | |
| | 0.2125 | 3.7634 | 350 | 0.3842 | 0.8815 | 0.8629 | 0.8898 | 0.8815 | 0.8805 | |
| | 0.1923 | 4.3011 | 400 | 0.3178 | 0.9080 | 0.8662 | 0.9086 | 0.9080 | 0.9081 | |
| | 0.1333 | 4.8387 | 450 | 0.3397 | 0.8704 | 0.8297 | 0.8709 | 0.8704 | 0.8702 | |
| | 0.137 | 5.3763 | 500 | 0.3369 | 0.9028 | 0.8718 | 0.9034 | 0.9028 | 0.9027 | |
| | 0.1103 | 5.9140 | 550 | 0.3493 | 0.9025 | 0.8545 | 0.9045 | 0.9025 | 0.9026 | |
| | 0.0896 | 6.4516 | 600 | 0.4059 | 0.8813 | 0.8507 | 0.8838 | 0.8813 | 0.8809 | |
| | 0.0573 | 6.9892 | 650 | 0.3956 | 0.8813 | 0.8470 | 0.8826 | 0.8813 | 0.8810 | |
| | 0.0716 | 7.5269 | 700 | 0.5566 | 0.8815 | 0.8674 | 0.8926 | 0.8815 | 0.8803 | |
| | 0.0893 | 8.0645 | 750 | 0.3980 | 0.8920 | 0.8575 | 0.8926 | 0.8920 | 0.8919 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.41.0 |
| - Pytorch 2.3.0+cu121 |
| - Datasets 2.19.1 |
| - Tokenizers 0.19.1 |
| |
