---
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- cnec
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: CNEC1_1_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: 0.8197264815582262
    - name: Recall
      type: recall
      value: 0.873289183222958
    - name: F1
      type: f1
      value: 0.8456605386917486
    - name: Accuracy
      type: accuracy
      value: 0.9604980678402748
---

<!-- 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_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: 0.2155
- Precision: 0.8197
- Recall: 0.8733
- F1: 0.8457
- Accuracy: 0.9605

## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.7506        | 0.85  | 500  | 0.2818          | 0.6550    | 0.7687 | 0.7073 | 0.9354   |
| 0.2862        | 1.7   | 1000 | 0.2055          | 0.7555    | 0.8238 | 0.7882 | 0.9500   |
| 0.2057        | 2.56  | 1500 | 0.2090          | 0.7792    | 0.8415 | 0.8092 | 0.9534   |
| 0.1698        | 3.41  | 2000 | 0.1992          | 0.7818    | 0.8623 | 0.8201 | 0.9575   |
| 0.1366        | 4.26  | 2500 | 0.2036          | 0.8086    | 0.8746 | 0.8403 | 0.9584   |
| 0.1049        | 5.11  | 3000 | 0.2000          | 0.8062    | 0.8689 | 0.8364 | 0.9607   |
| 0.0885        | 5.96  | 3500 | 0.2087          | 0.8059    | 0.8689 | 0.8362 | 0.9571   |
| 0.0673        | 6.81  | 4000 | 0.2063          | 0.8281    | 0.8786 | 0.8526 | 0.9602   |
| 0.0628        | 7.67  | 4500 | 0.2155          | 0.8197    | 0.8733 | 0.8457 | 0.9605   |


### Framework versions

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