|
|
--- |
|
|
base_model: dmis-lab/biobert-v1.1 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- conll2002 |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: biobert-base-case-ner |
|
|
results: |
|
|
- task: |
|
|
name: Token Classification |
|
|
type: token-classification |
|
|
dataset: |
|
|
name: conll2002 |
|
|
type: conll2002 |
|
|
config: es |
|
|
split: validation |
|
|
args: es |
|
|
metrics: |
|
|
- name: Precision |
|
|
type: precision |
|
|
value: 0.7494539100043687 |
|
|
- name: Recall |
|
|
type: recall |
|
|
value: 0.7883731617647058 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.7684210526315789 |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.9629927984937011 |
|
|
--- |
|
|
|
|
|
<!-- 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-base-case-ner |
|
|
|
|
|
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the conll2002 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2531 |
|
|
- Precision: 0.7495 |
|
|
- Recall: 0.7884 |
|
|
- F1: 0.7684 |
|
|
- Accuracy: 0.9630 |
|
|
|
|
|
## 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 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.1214 | 1.0 | 1041 | 0.1681 | 0.6611 | 0.6997 | 0.6798 | 0.9523 | |
|
|
| 0.0814 | 2.0 | 2082 | 0.1652 | 0.6692 | 0.7270 | 0.6969 | 0.9540 | |
|
|
| 0.0531 | 3.0 | 3123 | 0.1628 | 0.7291 | 0.7682 | 0.7481 | 0.9624 | |
|
|
| 0.0357 | 4.0 | 4164 | 0.1799 | 0.7427 | 0.7721 | 0.7571 | 0.9620 | |
|
|
| 0.0277 | 5.0 | 5205 | 0.1963 | 0.7530 | 0.7824 | 0.7674 | 0.9627 | |
|
|
| 0.0168 | 6.0 | 6246 | 0.2115 | 0.7333 | 0.7771 | 0.7546 | 0.9615 | |
|
|
| 0.0136 | 7.0 | 7287 | 0.2311 | 0.7376 | 0.7769 | 0.7567 | 0.9613 | |
|
|
| 0.0106 | 8.0 | 8328 | 0.2450 | 0.7552 | 0.7861 | 0.7703 | 0.9626 | |
|
|
| 0.0062 | 9.0 | 9369 | 0.2572 | 0.7589 | 0.7877 | 0.7730 | 0.9622 | |
|
|
| 0.0061 | 10.0 | 10410 | 0.2531 | 0.7495 | 0.7884 | 0.7684 | 0.9630 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.41.1 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.19.2 |
|
|
- Tokenizers 0.19.1 |
|
|
|
