|
|
--- |
|
|
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-V1 |
|
|
results: |
|
|
- task: |
|
|
type: token-classification |
|
|
name: Token Classification |
|
|
dataset: |
|
|
name: biobert_json |
|
|
type: biobert_json |
|
|
config: Biobert_json |
|
|
split: validation |
|
|
args: Biobert_json |
|
|
metrics: |
|
|
- type: precision |
|
|
value: 0.949653802801782 |
|
|
name: Precision |
|
|
- type: recall |
|
|
value: 0.9613670941099761 |
|
|
name: Recall |
|
|
- type: f1 |
|
|
value: 0.9554745511003105 |
|
|
name: F1 |
|
|
- type: accuracy |
|
|
value: 0.976855614973262 |
|
|
name: Accuracy |
|
|
pipeline_tag: token-classification |
|
|
--- |
|
|
|
|
|
<!-- 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-V1 |
|
|
|
|
|
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: 0.1236 |
|
|
- Precision: 0.9497 |
|
|
- Recall: 0.9614 |
|
|
- F1: 0.9555 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.3411 | 1.0 | 612 | 0.1137 | 0.9437 | 0.9474 | 0.9456 | 0.9707 | |
|
|
| 0.1072 | 2.0 | 1224 | 0.1090 | 0.9304 | 0.9685 | 0.9491 | 0.9727 | |
|
|
| 0.0757 | 3.0 | 1836 | 0.1024 | 0.9450 | 0.9692 | 0.9569 | 0.9768 | |
|
|
| 0.0589 | 4.0 | 2448 | 0.1050 | 0.9492 | 0.9666 | 0.9578 | 0.9774 | |
|
|
| 0.0419 | 5.0 | 3060 | 0.1054 | 0.9498 | 0.9621 | 0.9559 | 0.9771 | |
|
|
| 0.0365 | 6.0 | 3672 | 0.1124 | 0.9460 | 0.9583 | 0.9521 | 0.9753 | |
|
|
| 0.0299 | 7.0 | 4284 | 0.1119 | 0.9495 | 0.9632 | 0.9563 | 0.9774 | |
|
|
| 0.0282 | 8.0 | 4896 | 0.1187 | 0.9482 | 0.9625 | 0.9553 | 0.9771 | |
|
|
| 0.0221 | 9.0 | 5508 | 0.1203 | 0.9496 | 0.9608 | 0.9551 | 0.9768 | |
|
|
| 0.0192 | 10.0 | 6120 | 0.1236 | 0.9497 | 0.9614 | 0.9555 | 0.9769 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.2 |
|
|
- Pytorch 2.5.1+cu121 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
