---
tags:
- generated_from_trainer
datasets:
- contratos_tceal
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner-bert-large-cased-pt-contratos_tceal
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: contratos_tceal
      type: contratos_tceal
      config: contratos_tceal
      split: validation
      args: contratos_tceal
    metrics:
    - name: Precision
      type: precision
      value: 0.918525703200776
    - name: Recall
      type: recall
      value: 0.9458964541368403
    - name: F1
      type: f1
      value: 0.9320101697695399
    - name: Accuracy
      type: accuracy
      value: 0.9639352869753552
---

<!-- 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-large-cased-pt-contratos_tceal

This model was trained from scratch on the contratos_tceal dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2229
- Precision: 0.9185
- Recall: 0.9459
- F1: 0.9320
- Accuracy: 0.9639

## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 363  | 0.1242          | 0.9164    | 0.9469 | 0.9314 | 0.9696   |
| 0.1307        | 2.0   | 726  | 0.1413          | 0.9197    | 0.9424 | 0.9309 | 0.9664   |
| 0.0831        | 3.0   | 1089 | 0.1366          | 0.9237    | 0.9477 | 0.9356 | 0.9682   |
| 0.0831        | 4.0   | 1452 | 0.1360          | 0.9283    | 0.9489 | 0.9385 | 0.9696   |
| 0.0646        | 5.0   | 1815 | 0.1572          | 0.9171    | 0.9427 | 0.9297 | 0.9646   |
| 0.0473        | 6.0   | 2178 | 0.1674          | 0.9069    | 0.9454 | 0.9257 | 0.9646   |
| 0.0367        | 7.0   | 2541 | 0.1783          | 0.9155    | 0.9414 | 0.9283 | 0.9644   |
| 0.0367        | 8.0   | 2904 | 0.1823          | 0.9244    | 0.9442 | 0.9342 | 0.9656   |
| 0.029         | 9.0   | 3267 | 0.1815          | 0.9190    | 0.9444 | 0.9315 | 0.9655   |
| 0.0227        | 10.0  | 3630 | 0.1945          | 0.9084    | 0.9457 | 0.9267 | 0.9617   |
| 0.0227        | 11.0  | 3993 | 0.1962          | 0.9134    | 0.9442 | 0.9285 | 0.9635   |
| 0.0188        | 12.0  | 4356 | 0.1893          | 0.9203    | 0.9442 | 0.9321 | 0.9651   |
| 0.0134        | 13.0  | 4719 | 0.1982          | 0.9181    | 0.9441 | 0.9309 | 0.9650   |
| 0.0126        | 14.0  | 5082 | 0.1962          | 0.9162    | 0.9447 | 0.9303 | 0.9667   |
| 0.0126        | 15.0  | 5445 | 0.2112          | 0.9196    | 0.9446 | 0.9319 | 0.9642   |
| 0.0099        | 16.0  | 5808 | 0.2138          | 0.9165    | 0.9449 | 0.9305 | 0.9630   |
| 0.007         | 17.0  | 6171 | 0.2110          | 0.9208    | 0.9447 | 0.9326 | 0.9652   |
| 0.0075        | 18.0  | 6534 | 0.2216          | 0.9210    | 0.9452 | 0.9330 | 0.9641   |
| 0.0075        | 19.0  | 6897 | 0.2232          | 0.9191    | 0.9461 | 0.9324 | 0.9640   |
| 0.0062        | 20.0  | 7260 | 0.2229          | 0.9185    | 0.9459 | 0.9320 | 0.9639   |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0