---
library_name: transformers
license: mit
base_model: neuralmind/bert-large-portuguese-cased
tags:
- generated_from_trainer
datasets:
- lener_br
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner-bert-lenerbr-large-v1
  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: 0.865924092409241
    - name: Recall
      type: recall
      value: 0.9027956989247312
    - name: F1
      type: f1
      value: 0.8839755738050117
    - name: Accuracy
      type: accuracy
      value: 0.9754064638030079
---

<!-- 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-bert-lenerbr-large-v1

This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the lener_br dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1337
- Precision: 0.8659
- Recall: 0.9028
- F1: 0.8840
- Accuracy: 0.9754

## 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: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.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
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0521        | 1.0   | 979  | 0.1236          | 0.8260    | 0.8626 | 0.8439 | 0.9676   |
| 0.0338        | 2.0   | 1958 | 0.2221          | 0.6535    | 0.9185 | 0.7636 | 0.9536   |
| 0.0201        | 3.0   | 2937 | 0.1381          | 0.7573    | 0.9084 | 0.8260 | 0.9679   |
| 0.0163        | 4.0   | 3916 | 0.1337          | 0.8659    | 0.9028 | 0.8840 | 0.9754   |
| 0.0132        | 5.0   | 4895 | 0.1462          | 0.8392    | 0.9037 | 0.8702 | 0.9717   |
| 0.0105        | 6.0   | 5874 | 0.1423          | 0.8443    | 0.9211 | 0.8810 | 0.9738   |
| 0.0036        | 7.0   | 6853 | 0.1671          | 0.7994    | 0.9168 | 0.8541 | 0.9696   |
| 0.0055        | 8.0   | 7832 | 0.1884          | 0.7808    | 0.9161 | 0.8431 | 0.9672   |
| 0.0023        | 9.0   | 8811 | 0.1772          | 0.8182    | 0.9148 | 0.8638 | 0.9718   |
| 0.0019        | 10.0  | 9790 | 0.1788          | 0.8180    | 0.9181 | 0.8651 | 0.9718   |


### Framework versions

- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1