---
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: 0.8675623800383877
    - name: Recall
      type: recall
      value: 0.8972704714640198
    - name: F1
      type: f1
      value: 0.8821663820444011
    - name: Accuracy
      type: accuracy
      value: 0.9754391100702576
---

<!-- 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: 0.1456
- Precision: 0.8676
- Recall: 0.8973
- F1: 0.8822
- Accuracy: 0.9754

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3439        | 0.56  | 500  | 0.1575          | 0.7882    | 0.8015 | 0.7948 | 0.9605   |
| 0.1636        | 1.12  | 1000 | 0.1242          | 0.8071    | 0.8432 | 0.8248 | 0.9699   |
| 0.1347        | 1.68  | 1500 | 0.1246          | 0.8273    | 0.8486 | 0.8378 | 0.9688   |
| 0.105         | 2.24  | 2000 | 0.1276          | 0.8428    | 0.8645 | 0.8535 | 0.9727   |
| 0.0942        | 2.8   | 2500 | 0.1263          | 0.8412    | 0.8809 | 0.8606 | 0.9734   |
| 0.0778        | 3.36  | 3000 | 0.1178          | 0.8550    | 0.8779 | 0.8663 | 0.9746   |
| 0.0696        | 3.92  | 3500 | 0.1168          | 0.8491    | 0.8878 | 0.8680 | 0.9738   |
| 0.0565        | 4.48  | 4000 | 0.1135          | 0.8377    | 0.8734 | 0.8552 | 0.9734   |
| 0.0532        | 5.04  | 4500 | 0.1218          | 0.8673    | 0.8888 | 0.8779 | 0.9752   |
| 0.0451        | 5.6   | 5000 | 0.1339          | 0.8613    | 0.8878 | 0.8744 | 0.9751   |
| 0.0396        | 6.16  | 5500 | 0.1339          | 0.8595    | 0.8864 | 0.8727 | 0.9751   |
| 0.0331        | 6.72  | 6000 | 0.1361          | 0.8617    | 0.8933 | 0.8772 | 0.9755   |
| 0.0263        | 7.28  | 6500 | 0.1450          | 0.8720    | 0.8958 | 0.8837 | 0.9758   |
| 0.0278        | 7.84  | 7000 | 0.1456          | 0.8676    | 0.8973 | 0.8822 | 0.9754   |


### Framework versions

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