|
|
--- |
|
|
base_model: dmis-lab/biobert-base-cased-v1.2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: cause-biobert-biocause |
|
|
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. --> |
|
|
|
|
|
# cause-biobert-biocause |
|
|
|
|
|
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 an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5157 |
|
|
- Precision: 0.2230 |
|
|
- Recall: 0.4277 |
|
|
- F1: 0.2931 |
|
|
- Accuracy: 0.8241 |
|
|
- Cause P: 0.2230 |
|
|
- Cause R: 0.4277 |
|
|
- Cause F1: 0.2931 |
|
|
|
|
|
## 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: 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: 2 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Cause P | Cause R | Cause F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------:|:-------:|:--------:| |
|
|
| 0.6993 | 0.25 | 20 | 0.6314 | 0.0556 | 0.1698 | 0.0837 | 0.7587 | 0.0556 | 0.1698 | 0.0837 | |
|
|
| 0.6993 | 0.5 | 40 | 0.5747 | 0.0826 | 0.2327 | 0.1219 | 0.6524 | 0.0826 | 0.2327 | 0.1219 | |
|
|
| 0.6993 | 0.75 | 60 | 0.4896 | 0.1086 | 0.3899 | 0.1699 | 0.7420 | 0.1086 | 0.3899 | 0.1699 | |
|
|
| 0.6993 | 1.0 | 80 | 0.4554 | 0.1497 | 0.3145 | 0.2028 | 0.7840 | 0.1497 | 0.3145 | 0.2028 | |
|
|
| 0.6993 | 1.25 | 100 | 0.4952 | 0.1980 | 0.3774 | 0.2597 | 0.8353 | 0.1980 | 0.3774 | 0.2597 | |
|
|
| 0.6993 | 1.5 | 120 | 0.4837 | 0.1749 | 0.3774 | 0.2390 | 0.7984 | 0.1749 | 0.3774 | 0.2390 | |
|
|
| 0.6993 | 1.75 | 140 | 0.4786 | 0.1873 | 0.4088 | 0.2569 | 0.7991 | 0.1873 | 0.4088 | 0.2569 | |
|
|
| 0.6993 | 2.0 | 160 | 0.5157 | 0.2230 | 0.4277 | 0.2931 | 0.8241 | 0.2230 | 0.4277 | 0.2931 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.37.2 |
|
|
- Pytorch 2.3.1.post100 |
|
|
- Datasets 2.20.0 |
|
|
- Tokenizers 0.15.1 |
|
|
|
