---
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- cnec
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: CNEC2_0_Supertypes_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: 0.8359161349134002
    - name: Recall
      type: recall
      value: 0.8851351351351351
    - name: F1
      type: f1
      value: 0.8598218471636193
    - name: Accuracy
      type: accuracy
      value: 0.9700420107199769
---

<!-- 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_Supertypes_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: 0.1918
- Precision: 0.8359
- Recall: 0.8851
- F1: 0.8598
- Accuracy: 0.9700

## 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: 32
- eval_batch_size: 32
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2903        | 2.22  | 500  | 0.1438          | 0.7586    | 0.8417 | 0.7980 | 0.9626   |
| 0.1147        | 4.44  | 1000 | 0.1401          | 0.7866    | 0.8629 | 0.8230 | 0.9660   |
| 0.0796        | 6.67  | 1500 | 0.1402          | 0.7956    | 0.8755 | 0.8336 | 0.9677   |
| 0.0561        | 8.89  | 2000 | 0.1419          | 0.8094    | 0.8793 | 0.8429 | 0.9700   |
| 0.0416        | 11.11 | 2500 | 0.1562          | 0.8271    | 0.8793 | 0.8524 | 0.9687   |
| 0.0306        | 13.33 | 3000 | 0.1761          | 0.8309    | 0.8890 | 0.8589 | 0.9702   |
| 0.0233        | 15.56 | 3500 | 0.1785          | 0.8332    | 0.8798 | 0.8559 | 0.9701   |
| 0.0188        | 17.78 | 4000 | 0.1875          | 0.8362    | 0.8847 | 0.8598 | 0.9694   |
| 0.015         | 20.0  | 4500 | 0.1918          | 0.8359    | 0.8851 | 0.8598 | 0.9700   |


### Framework versions

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