|
--- |
|
library_name: transformers |
|
license: cc-by-4.0 |
|
base_model: NazaGara/NER-fine-tuned-BETO |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- biobert_json |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: NER-finetuning-BETO-CM-V3 |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: biobert_json |
|
type: biobert_json |
|
config: Biobert_json |
|
split: validation |
|
args: Biobert_json |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9332171260485892 |
|
- name: Recall |
|
type: recall |
|
value: 0.9462056776759086 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9396665204036859 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9769126559714795 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# NER-finetuning-BETO-CM-V3 |
|
|
|
This model is a fine-tuned version of [NazaGara/NER-fine-tuned-BETO](https://huggingface.co/NazaGara/NER-fine-tuned-BETO) on the biobert_json dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1234 |
|
- Precision: 0.9332 |
|
- Recall: 0.9462 |
|
- F1: 0.9397 |
|
- Accuracy: 0.9769 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Use 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.3448 | 1.0 | 612 | 0.1106 | 0.9187 | 0.9255 | 0.9221 | 0.9719 | |
|
| 0.1036 | 2.0 | 1224 | 0.0990 | 0.9202 | 0.9507 | 0.9352 | 0.9763 | |
|
| 0.073 | 3.0 | 1836 | 0.0982 | 0.9356 | 0.9493 | 0.9424 | 0.9783 | |
|
| 0.057 | 4.0 | 2448 | 0.1070 | 0.9304 | 0.9493 | 0.9397 | 0.9771 | |
|
| 0.0405 | 5.0 | 3060 | 0.1034 | 0.9353 | 0.9486 | 0.9419 | 0.9783 | |
|
| 0.0361 | 6.0 | 3672 | 0.1081 | 0.9280 | 0.9474 | 0.9376 | 0.9767 | |
|
| 0.0287 | 7.0 | 4284 | 0.1106 | 0.9309 | 0.9490 | 0.9398 | 0.9777 | |
|
| 0.0284 | 8.0 | 4896 | 0.1182 | 0.9288 | 0.9463 | 0.9375 | 0.9768 | |
|
| 0.0212 | 9.0 | 5508 | 0.1195 | 0.9340 | 0.9464 | 0.9402 | 0.9774 | |
|
| 0.0191 | 10.0 | 6120 | 0.1234 | 0.9332 | 0.9462 | 0.9397 | 0.9769 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
