|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilbert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- lener_br |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilbert-base-multilingual-cased-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: 0.761528608027327 |
|
- name: Recall |
|
type: recall |
|
value: 0.7616912235746316 |
|
- name: F1 |
|
type: f1 |
|
value: 0.7616099071207431 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9554657562878841 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distilbert-base-multilingual-cased-finetuned-ner-lenerBr |
|
|
|
This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the lener_br dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1792 |
|
- Precision: 0.7615 |
|
- Recall: 0.7617 |
|
- F1: 0.7616 |
|
- Accuracy: 0.9555 |
|
|
|
## 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: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 490 | 0.2100 | 0.7139 | 0.6624 | 0.6872 | 0.9394 | |
|
| 0.2608 | 2.0 | 980 | 0.1962 | 0.7059 | 0.7508 | 0.7276 | 0.9443 | |
|
| 0.0681 | 3.0 | 1470 | 0.1858 | 0.7225 | 0.7649 | 0.7431 | 0.9486 | |
|
| 0.0382 | 4.0 | 1960 | 0.1792 | 0.7615 | 0.7617 | 0.7616 | 0.9555 | |
|
| 0.0248 | 5.0 | 2450 | 0.2068 | 0.7715 | 0.8149 | 0.7926 | 0.9560 | |
|
| 0.0173 | 6.0 | 2940 | 0.2029 | 0.7112 | 0.8031 | 0.7544 | 0.9529 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
