---
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- cnec
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: CNEC2_0_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: 0.8860882210373243
    - name: Recall
      type: recall
      value: 0.9071960297766749
    - name: F1
      type: f1
      value: 0.8965179009318294
    - name: Accuracy
      type: accuracy
      value: 0.9772540983606557
---

<!-- 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. -->

# CNEC2_0_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: 0.1919
- Precision: 0.8861
- Recall: 0.9072
- F1: 0.8965
- Accuracy: 0.9773

## 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: 15

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1664        | 1.12  | 1000  | 0.1312          | 0.8299    | 0.8521 | 0.8408 | 0.9695   |
| 0.1153        | 2.24  | 2000  | 0.1121          | 0.8283    | 0.8640 | 0.8458 | 0.9722   |
| 0.0815        | 3.36  | 3000  | 0.1159          | 0.8523    | 0.8531 | 0.8527 | 0.9735   |
| 0.0633        | 4.48  | 4000  | 0.1166          | 0.8515    | 0.8819 | 0.8664 | 0.9750   |
| 0.0472        | 5.6   | 5000  | 0.1624          | 0.8635    | 0.8918 | 0.8774 | 0.9735   |
| 0.0369        | 6.72  | 6000  | 0.1476          | 0.8710    | 0.8983 | 0.8844 | 0.9770   |
| 0.0325        | 7.84  | 7000  | 0.1590          | 0.8710    | 0.8943 | 0.8825 | 0.9752   |
| 0.0268        | 8.96  | 8000  | 0.1698          | 0.8709    | 0.9037 | 0.8870 | 0.9761   |
| 0.0236        | 10.08 | 9000  | 0.1721          | 0.8807    | 0.9087 | 0.8945 | 0.9763   |
| 0.0125        | 11.2  | 10000 | 0.1843          | 0.8781    | 0.9047 | 0.8912 | 0.9768   |
| 0.009         | 12.32 | 11000 | 0.1971          | 0.8789    | 0.9077 | 0.8931 | 0.9766   |
| 0.0097        | 13.44 | 12000 | 0.1823          | 0.8857    | 0.9077 | 0.8966 | 0.9775   |
| 0.0077        | 14.56 | 13000 | 0.1919          | 0.8861    | 0.9072 | 0.8965 | 0.9773   |


### Framework versions

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