---
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- cnec
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: CNEC1_1_extended_xlm-roberta-large
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: cnec
      type: cnec
      config: default
      split: validation
      args: default
    metrics:
    - name: Precision
      type: precision
      value: 0.8551829268292683
    - name: Recall
      type: recall
      value: 0.8995189738107964
    - name: F1
      type: f1
      value: 0.8767908309455589
    - name: Accuracy
      type: accuracy
      value: 0.9694414756758897
---

<!-- 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. -->

# CNEC1_1_extended_xlm-roberta-large

This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2115
- Precision: 0.8552
- Recall: 0.8995
- F1: 0.8768
- Accuracy: 0.9694

## 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: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2948        | 1.72  | 500  | 0.1385          | 0.7752    | 0.8589 | 0.8149 | 0.9620   |
| 0.1185        | 3.44  | 1000 | 0.1411          | 0.8063    | 0.8808 | 0.8419 | 0.9692   |
| 0.0762        | 5.15  | 1500 | 0.1485          | 0.8252    | 0.8781 | 0.8509 | 0.9690   |
| 0.054         | 6.87  | 2000 | 0.1586          | 0.8368    | 0.8878 | 0.8615 | 0.9697   |
| 0.0357        | 8.59  | 2500 | 0.1774          | 0.8364    | 0.8990 | 0.8666 | 0.9705   |
| 0.026         | 10.31 | 3000 | 0.1869          | 0.8540    | 0.8974 | 0.8752 | 0.9700   |
| 0.0189        | 12.03 | 3500 | 0.2040          | 0.8555    | 0.8958 | 0.8752 | 0.9698   |
| 0.013         | 13.75 | 4000 | 0.2115          | 0.8552    | 0.8995 | 0.8768 | 0.9694   |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0