---
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: 0.8492292870905588
    - name: Recall
      type: recall
      value: 0.8749379652605459
    - name: F1
      type: f1
      value: 0.8618919579564899
    - name: Accuracy
      type: accuracy
      value: 0.973155737704918
---

<!-- 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: 0.1467
- Precision: 0.8492
- Recall: 0.8749
- F1: 0.8619
- Accuracy: 0.9732

## 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.508         | 0.56  | 500  | 0.2177          | 0.6604    | 0.6928 | 0.6762 | 0.9423   |
| 0.2268        | 1.12  | 1000 | 0.1923          | 0.7158    | 0.7960 | 0.7538 | 0.9512   |
| 0.183         | 1.68  | 1500 | 0.1580          | 0.7825    | 0.8303 | 0.8057 | 0.9636   |
| 0.1558        | 2.24  | 2000 | 0.1548          | 0.8077    | 0.8382 | 0.8227 | 0.9676   |
| 0.1371        | 2.8   | 2500 | 0.1278          | 0.8233    | 0.8511 | 0.8370 | 0.9701   |
| 0.1225        | 3.36  | 3000 | 0.1430          | 0.8128    | 0.8531 | 0.8324 | 0.9667   |
| 0.1166        | 3.92  | 3500 | 0.1389          | 0.8307    | 0.8501 | 0.8403 | 0.9681   |
| 0.101         | 4.48  | 4000 | 0.1323          | 0.8277    | 0.8655 | 0.8462 | 0.9708   |
| 0.0928        | 5.04  | 4500 | 0.1332          | 0.8434    | 0.8660 | 0.8546 | 0.9715   |
| 0.0848        | 5.6   | 5000 | 0.1273          | 0.8382    | 0.8665 | 0.8521 | 0.9727   |
| 0.0798        | 6.16  | 5500 | 0.1281          | 0.8447    | 0.8774 | 0.8608 | 0.9716   |
| 0.0688        | 6.72  | 6000 | 0.1340          | 0.8482    | 0.8734 | 0.8606 | 0.9728   |
| 0.0638        | 7.28  | 6500 | 0.1346          | 0.8549    | 0.8744 | 0.8646 | 0.9746   |
| 0.0585        | 7.84  | 7000 | 0.1415          | 0.8442    | 0.8764 | 0.8600 | 0.9730   |
| 0.0565        | 8.4   | 7500 | 0.1487          | 0.8377    | 0.8809 | 0.8587 | 0.9730   |
| 0.0497        | 8.96  | 8000 | 0.1416          | 0.8473    | 0.8784 | 0.8626 | 0.9740   |
| 0.0484        | 9.52  | 8500 | 0.1467          | 0.8492    | 0.8749 | 0.8619 | 0.9732   |


### Framework versions

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