|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilroberta-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- lener_br |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilroberta-base-finetuned-ner-lenerBr |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: lener_br |
|
type: lener_br |
|
config: lener_br |
|
split: validation |
|
args: lener_br |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.801254136909946 |
|
- name: Recall |
|
type: recall |
|
value: 0.8429540040315191 |
|
- name: F1 |
|
type: f1 |
|
value: 0.821575281300232 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9685663231476382 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distilroberta-base-finetuned-ner-lenerBr |
|
|
|
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the lener_br dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1550 |
|
- Precision: 0.8013 |
|
- Recall: 0.8430 |
|
- F1: 0.8216 |
|
- Accuracy: 0.9686 |
|
|
|
## 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: 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 490 | 0.1750 | 0.7347 | 0.6581 | 0.6942 | 0.9465 | |
|
| 0.2808 | 2.0 | 980 | 0.1642 | 0.6954 | 0.7598 | 0.7262 | 0.9538 | |
|
| 0.093 | 3.0 | 1470 | 0.1849 | 0.6708 | 0.7992 | 0.7294 | 0.9510 | |
|
| 0.0557 | 4.0 | 1960 | 0.1403 | 0.7807 | 0.8345 | 0.8067 | 0.9668 | |
|
| 0.0366 | 5.0 | 2450 | 0.1560 | 0.7775 | 0.8466 | 0.8106 | 0.9626 | |
|
| 0.027 | 6.0 | 2940 | 0.1612 | 0.7342 | 0.8239 | 0.7764 | 0.9621 | |
|
| 0.0204 | 7.0 | 3430 | 0.1632 | 0.7625 | 0.8356 | 0.7974 | 0.9644 | |
|
| 0.015 | 8.0 | 3920 | 0.1748 | 0.7375 | 0.8442 | 0.7873 | 0.9615 | |
|
| 0.0135 | 9.0 | 4410 | 0.1547 | 0.7930 | 0.8446 | 0.8180 | 0.9685 | |
|
| 0.0101 | 10.0 | 4900 | 0.1550 | 0.8013 | 0.8430 | 0.8216 | 0.9686 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
