---
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: 0.8424273329933707
    - name: Recall
      type: recall
      value: 0.882950293960449
    - name: F1
      type: f1
      value: 0.8622129436325678
    - name: Accuracy
      type: accuracy
      value: 0.9652851996991648
---

<!-- 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: 0.2119
- Precision: 0.8424
- Recall: 0.8830
- F1: 0.8622
- Accuracy: 0.9653

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3746        | 0.86  | 500  | 0.1861          | 0.7228    | 0.8097 | 0.7638 | 0.9523   |
| 0.2127        | 1.72  | 1000 | 0.1635          | 0.7829    | 0.8461 | 0.8133 | 0.9611   |
| 0.1494        | 2.58  | 1500 | 0.1704          | 0.7579    | 0.8466 | 0.7998 | 0.9546   |
| 0.1274        | 3.44  | 2000 | 0.1800          | 0.8003    | 0.8675 | 0.8325 | 0.9615   |
| 0.0987        | 4.3   | 2500 | 0.1511          | 0.8025    | 0.8883 | 0.8432 | 0.9657   |
| 0.0827        | 5.16  | 3000 | 0.1910          | 0.8179    | 0.8739 | 0.8450 | 0.9630   |
| 0.0677        | 6.02  | 3500 | 0.1655          | 0.8374    | 0.8808 | 0.8586 | 0.9689   |
| 0.0475        | 6.88  | 4000 | 0.1793          | 0.8270    | 0.8658 | 0.8460 | 0.9633   |
| 0.0396        | 7.75  | 4500 | 0.1687          | 0.8363    | 0.8899 | 0.8622 | 0.9672   |
| 0.0256        | 8.61  | 5000 | 0.1904          | 0.8315    | 0.8808 | 0.8554 | 0.9665   |
| 0.0223        | 9.47  | 5500 | 0.2119          | 0.8424    | 0.8830 | 0.8622 | 0.9653   |


### Framework versions

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