metadata
library_name: transformers
license: mit
base_model: emilyalsentzer/Bio_ClinicalBERT
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bio-clinical-bert-section-classification-v6
results: []
bio-clinical-bert-section-classification-v6
This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1907
- Accuracy: 0.6562
- Precision: 0.6875
- Recall: 0.6562
- F1: 0.6605
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.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: 300
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 370 | 1.3321 | 0.3722 | 0.3745 | 0.3722 | 0.3474 |
| 1.3812 | 2.0 | 740 | 1.2760 | 0.5331 | 0.5882 | 0.5331 | 0.5160 |
| 1.3012 | 3.0 | 1110 | 1.2377 | 0.6151 | 0.6802 | 0.6151 | 0.6203 |
| 1.3012 | 4.0 | 1480 | 1.2114 | 0.6593 | 0.7025 | 0.6593 | 0.6647 |
| 1.2549 | 5.0 | 1850 | 1.1960 | 0.6562 | 0.6996 | 0.6562 | 0.6618 |
| 1.2222 | 6.0 | 2220 | 1.1907 | 0.6562 | 0.6875 | 0.6562 | 0.6605 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Tokenizers 0.21.1