---
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: 0.8595505617977528
    - name: Recall
      type: recall
      value: 0.8995189738107964
    - name: F1
      type: f1
      value: 0.8790806999216505
    - name: Accuracy
      type: accuracy
      value: 0.9695206428373511
---

<!-- 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: 0.2397
- Precision: 0.8596
- Recall: 0.8995
- F1: 0.8791
- Accuracy: 0.9695

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3533        | 1.72  | 500  | 0.1415          | 0.7483    | 0.8439 | 0.7933 | 0.9609   |
| 0.1509        | 3.44  | 1000 | 0.1352          | 0.8073    | 0.8685 | 0.8368 | 0.9664   |
| 0.1072        | 5.15  | 1500 | 0.1533          | 0.8151    | 0.8739 | 0.8434 | 0.9674   |
| 0.0778        | 6.87  | 2000 | 0.1740          | 0.8400    | 0.8781 | 0.8586 | 0.9668   |
| 0.059         | 8.59  | 2500 | 0.1676          | 0.8365    | 0.8942 | 0.8644 | 0.9699   |
| 0.0475        | 10.31 | 3000 | 0.1699          | 0.8295    | 0.8813 | 0.8546 | 0.9678   |
| 0.0381        | 12.03 | 3500 | 0.1876          | 0.8418    | 0.8985 | 0.8692 | 0.9686   |
| 0.0287        | 13.75 | 4000 | 0.2100          | 0.8446    | 0.8979 | 0.8705 | 0.9681   |
| 0.0238        | 15.46 | 4500 | 0.2007          | 0.8466    | 0.8995 | 0.8722 | 0.9702   |
| 0.0186        | 17.18 | 5000 | 0.2201          | 0.8568    | 0.8926 | 0.8743 | 0.9689   |
| 0.0161        | 18.9  | 5500 | 0.2200          | 0.8573    | 0.8990 | 0.8776 | 0.9700   |
| 0.014         | 20.62 | 6000 | 0.2326          | 0.8601    | 0.8974 | 0.8784 | 0.9697   |
| 0.0104        | 22.34 | 6500 | 0.2370          | 0.8639    | 0.8990 | 0.8811 | 0.9696   |
| 0.0099        | 24.05 | 7000 | 0.2397          | 0.8596    | 0.8995 | 0.8791 | 0.9695   |


### Framework versions

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