|
--- |
|
base_model: dmis-lab/biobert-v1.1 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: biobert-v1.1-text-classifier |
|
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-v1.1-text-classifier |
|
|
|
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2669 |
|
- Precision: 0.9098 |
|
- Recall: 0.9091 |
|
- Accuracy: 0.9089 |
|
- F1: 0.9089 |
|
|
|
## 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: 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:------:| |
|
| No log | 1.0 | 154 | 0.3413 | 0.8822 | 0.8813 | 0.8804 | 0.8808 | |
|
| No log | 2.0 | 308 | 0.2918 | 0.8945 | 0.8836 | 0.8845 | 0.8848 | |
|
| No log | 3.0 | 462 | 0.2669 | 0.9098 | 0.9091 | 0.9089 | 0.9089 | |
|
| 0.3597 | 4.0 | 616 | 0.2781 | 0.9175 | 0.9174 | 0.9170 | 0.9170 | |
|
| 0.3597 | 5.0 | 770 | 0.2797 | 0.9203 | 0.9206 | 0.9203 | 0.9204 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
