|
--- |
|
library_name: transformers |
|
base_model: dccuchile/bert-base-spanish-wwm-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- biobert_json |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-biobert |
|
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: 0.9479839607930497 |
|
- name: Recall |
|
type: recall |
|
value: 0.9641461342395922 |
|
- name: F1 |
|
type: f1 |
|
value: 0.95599674257954 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9768617183218656 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# bert-biobert |
|
|
|
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on the biobert_json dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1154 |
|
- Precision: 0.9480 |
|
- Recall: 0.9641 |
|
- F1: 0.9560 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.364 | 1.0 | 612 | 0.1155 | 0.9302 | 0.9525 | 0.9412 | 0.9686 | |
|
| 0.117 | 2.0 | 1224 | 0.1034 | 0.9405 | 0.9640 | 0.9521 | 0.9749 | |
|
| 0.0837 | 3.0 | 1836 | 0.0980 | 0.9469 | 0.9682 | 0.9574 | 0.9772 | |
|
| 0.066 | 4.0 | 2448 | 0.0975 | 0.9474 | 0.9678 | 0.9575 | 0.9775 | |
|
| 0.0451 | 5.0 | 3060 | 0.0982 | 0.9498 | 0.9648 | 0.9572 | 0.9770 | |
|
| 0.0405 | 6.0 | 3672 | 0.1074 | 0.9469 | 0.9643 | 0.9555 | 0.9761 | |
|
| 0.0318 | 7.0 | 4284 | 0.1104 | 0.9478 | 0.9663 | 0.9570 | 0.9771 | |
|
| 0.031 | 8.0 | 4896 | 0.1145 | 0.9495 | 0.9654 | 0.9574 | 0.9772 | |
|
| 0.0235 | 9.0 | 5508 | 0.1137 | 0.9495 | 0.9639 | 0.9566 | 0.9767 | |
|
| 0.0209 | 10.0 | 6120 | 0.1154 | 0.9480 | 0.9641 | 0.9560 | 0.9769 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
