| --- |
| library_name: transformers |
| license: mit |
| base_model: thomas-sounack/BioClinical-ModernBERT-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| model-index: |
| - name: modernbert-en-disease-masked-50-10epochs-v1 |
| 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. --> |
|
|
| # modernbert-en-disease-masked-50-10epochs-v1 |
|
|
| This model is a fine-tuned version of [thomas-sounack/BioClinical-ModernBERT-base](https://huggingface.co/thomas-sounack/BioClinical-ModernBERT-base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.2509 |
| - Precision: 0.6313 |
| - Recall: 0.6762 |
| - F1: 0.6530 |
|
|
| ## 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: 5e-05 |
| - train_batch_size: 8 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:| |
| | 0.1581 | 1.0 | 142 | 0.1510 | 0.5315 | 0.5127 | 0.5220 | |
| | 0.111 | 2.0 | 284 | 0.1111 | 0.6396 | 0.6706 | 0.6548 | |
| | 0.0796 | 3.0 | 426 | 0.1118 | 0.6527 | 0.6647 | 0.6587 | |
| | 0.0606 | 4.0 | 568 | 0.1195 | 0.6464 | 0.7228 | 0.6824 | |
| | 0.0396 | 5.0 | 710 | 0.1538 | 0.6654 | 0.6714 | 0.6684 | |
| | 0.0179 | 6.0 | 852 | 0.1918 | 0.6476 | 0.6587 | 0.6531 | |
| | 0.0078 | 7.0 | 994 | 0.1946 | 0.6375 | 0.6961 | 0.6655 | |
| | 0.0054 | 8.0 | 1136 | 0.2340 | 0.6321 | 0.6794 | 0.6549 | |
| | 0.0021 | 9.0 | 1278 | 0.2475 | 0.6317 | 0.6782 | 0.6541 | |
| | 0.0019 | 10.0 | 1420 | 0.2509 | 0.6313 | 0.6762 | 0.6530 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.57.6 |
| - Pytorch 2.10.0+cu128 |
| - Datasets 3.6.0 |
| - Tokenizers 0.22.2 |
|
|
