|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: cause-bert-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-bert-biocause |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4364 |
|
- Precision: 0.1647 |
|
- Recall: 0.3459 |
|
- F1: 0.2231 |
|
- Accuracy: 0.8160 |
|
- Cause P: 0.1647 |
|
- Cause R: 0.3459 |
|
- Cause F1: 0.2231 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------:|:-------:|:--------:| |
|
| 0.6498 | 0.25 | 20 | 0.6248 | 0.0544 | 0.1698 | 0.0824 | 0.7705 | 0.0544 | 0.1698 | 0.0824 | |
|
| 0.6498 | 0.5 | 40 | 0.5229 | 0.0532 | 0.1572 | 0.0795 | 0.6600 | 0.0532 | 0.1572 | 0.0795 | |
|
| 0.6498 | 0.75 | 60 | 0.4613 | 0.1190 | 0.2327 | 0.1574 | 0.8274 | 0.1190 | 0.2327 | 0.1574 | |
|
| 0.6498 | 1.0 | 80 | 0.4376 | 0.1460 | 0.2956 | 0.1954 | 0.8145 | 0.1460 | 0.2956 | 0.1954 | |
|
| 0.6498 | 1.25 | 100 | 0.4660 | 0.1829 | 0.2956 | 0.2260 | 0.8312 | 0.1829 | 0.2956 | 0.2260 | |
|
| 0.6498 | 1.5 | 120 | 0.4523 | 0.1902 | 0.3899 | 0.2557 | 0.8148 | 0.1902 | 0.3899 | 0.2557 | |
|
| 0.6498 | 1.75 | 140 | 0.4414 | 0.1756 | 0.3711 | 0.2384 | 0.8138 | 0.1756 | 0.3711 | 0.2384 | |
|
| 0.6498 | 2.0 | 160 | 0.4364 | 0.1647 | 0.3459 | 0.2231 | 0.8160 | 0.1647 | 0.3459 | 0.2231 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.3.1.post100 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.15.1 |
|
|
