---
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: 0.8456410256410256
    - name: Recall
      type: recall
      value: 0.8813468733297701
    - name: F1
      type: f1
      value: 0.8631248364302538
    - name: Accuracy
      type: accuracy
      value: 0.9673435458971619
---

<!-- 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: 0.2299
- Precision: 0.8456
- Recall: 0.8813
- F1: 0.8631
- Accuracy: 0.9673

## 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
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 500
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.5516        | 0.86  | 500  | 0.1912          | 0.7007    | 0.7857 | 0.7407 | 0.9493   |
| 0.2153        | 1.72  | 1000 | 0.1856          | 0.6609    | 0.7825 | 0.7166 | 0.9461   |
| 0.1389        | 2.58  | 1500 | 0.1711          | 0.7791    | 0.8445 | 0.8105 | 0.9574   |
| 0.1098        | 3.44  | 2000 | 0.1943          | 0.8171    | 0.8642 | 0.84   | 0.9608   |
| 0.0785        | 4.3   | 2500 | 0.2197          | 0.7919    | 0.8461 | 0.8181 | 0.9579   |
| 0.0619        | 5.16  | 3000 | 0.1877          | 0.8298    | 0.8883 | 0.8580 | 0.9660   |
| 0.043         | 6.02  | 3500 | 0.2185          | 0.8412    | 0.8803 | 0.8603 | 0.9656   |
| 0.0289        | 6.88  | 4000 | 0.1898          | 0.8422    | 0.8846 | 0.8629 | 0.9674   |
| 0.0179        | 7.75  | 4500 | 0.2061          | 0.8433    | 0.8830 | 0.8627 | 0.9674   |
| 0.0112        | 8.61  | 5000 | 0.2218          | 0.8462    | 0.8819 | 0.8636 | 0.9656   |
| 0.0074        | 9.47  | 5500 | 0.2299          | 0.8456    | 0.8813 | 0.8631 | 0.9673   |


### Framework versions

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