<!-- 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. -->
stbl_clinical_bert_ft
This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1789
- F1: 0.8523
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.2786 | 1.0 | 95 | 0.1083 | 0.8090 |
| 0.0654 | 2.0 | 190 | 0.1005 | 0.8475 |
| 0.0299 | 3.0 | 285 | 0.1207 | 0.8481 |
| 0.0146 | 4.0 | 380 | 0.1432 | 0.8454 |
| 0.0088 | 5.0 | 475 | 0.1362 | 0.8475 |
| 0.0056 | 6.0 | 570 | 0.1527 | 0.8518 |
| 0.0037 | 7.0 | 665 | 0.1617 | 0.8519 |
| 0.0022 | 8.0 | 760 | 0.1726 | 0.8495 |
| 0.0018 | 9.0 | 855 | 0.1743 | 0.8527 |
| 0.0014 | 10.0 | 950 | 0.1750 | 0.8463 |
| 0.0014 | 11.0 | 1045 | 0.1775 | 0.8522 |
| 0.001 | 12.0 | 1140 | 0.1789 | 0.8523 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
