---
library_name: transformers
base_model: dmis-lab/biobert-base-cased-v1.2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: BioBert_pubHealth
  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. -->

# BioBert_pubHealth

This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6765
- Accuracy: 0.796
- Auc: 0.886
- Precision: 0.861
- Recall: 0.793
- F1: 0.825
- F1-macro: 0.791
- F1-micro: 0.796
- F1-weighted: 0.798

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Auc   | Precision | Recall | F1    | F1-macro | F1-micro | F1-weighted |
|:-------------:|:------:|:----:|:---------------:|:--------:|:-----:|:---------:|:------:|:-----:|:--------:|:--------:|:-----------:|
| 0.5286        | 0.3960 | 100  | 0.4608          | 0.769    | 0.855 | 0.847     | 0.756  | 0.799 | 0.764    | 0.769    | 0.771       |
| 0.4399        | 0.7921 | 200  | 0.4506          | 0.787    | 0.871 | 0.861     | 0.775  | 0.815 | 0.782    | 0.787    | 0.789       |
| 0.3929        | 1.1861 | 300  | 0.4363          | 0.791    | 0.878 | 0.829     | 0.826  | 0.828 | 0.781    | 0.791    | 0.791       |
| 0.368         | 1.5822 | 400  | 0.4003          | 0.797    | 0.884 | 0.881     | 0.77   | 0.822 | 0.794    | 0.797    | 0.8         |
| 0.3503        | 1.9782 | 500  | 0.4075          | 0.794    | 0.888 | 0.847     | 0.806  | 0.826 | 0.787    | 0.794    | 0.795       |
| 0.2828        | 2.3723 | 600  | 0.4678          | 0.798    | 0.888 | 0.898     | 0.753  | 0.819 | 0.796    | 0.798    | 0.801       |
| 0.2647        | 2.7683 | 700  | 0.4296          | 0.796    | 0.89  | 0.893     | 0.755  | 0.818 | 0.793    | 0.796    | 0.799       |
| 0.2197        | 3.1624 | 800  | 0.5130          | 0.798    | 0.889 | 0.862     | 0.795  | 0.827 | 0.793    | 0.798    | 0.8         |
| 0.1739        | 3.5584 | 900  | 0.5262          | 0.8      | 0.891 | 0.842     | 0.826  | 0.834 | 0.792    | 0.8      | 0.801       |
| 0.1517        | 3.9545 | 1000 | 0.6064          | 0.793    | 0.889 | 0.875     | 0.77   | 0.819 | 0.789    | 0.793    | 0.795       |
| 0.1189        | 4.3485 | 1100 | 0.6257          | 0.793    | 0.887 | 0.848     | 0.803  | 0.825 | 0.786    | 0.793    | 0.795       |
| 0.0976        | 4.7446 | 1200 | 0.6765          | 0.796    | 0.886 | 0.861     | 0.793  | 0.825 | 0.791    | 0.796    | 0.798       |


### Framework versions

- Transformers 4.53.0
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2