---
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: 0.8214447978191731
    - name: Recall
      type: recall
      value: 0.8725868725868726
    - name: F1
      type: f1
      value: 0.8462438567750995
    - name: Accuracy
      type: accuracy
      value: 0.9689700130378096
---

<!-- 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: 0.1759
- Precision: 0.8214
- Recall: 0.8726
- F1: 0.8462
- Accuracy: 0.9690

## 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
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.9224        | 0.56  | 500  | 0.2309          | 0.5594    | 0.6863 | 0.6164 | 0.9358   |
| 0.2449        | 1.11  | 1000 | 0.1960          | 0.6745    | 0.8142 | 0.7378 | 0.9525   |
| 0.204         | 1.67  | 1500 | 0.1701          | 0.7256    | 0.8079 | 0.7646 | 0.9571   |
| 0.1694        | 2.22  | 2000 | 0.1526          | 0.7605    | 0.8567 | 0.8057 | 0.9640   |
| 0.1392        | 2.78  | 2500 | 0.1607          | 0.7697    | 0.8485 | 0.8072 | 0.9620   |
| 0.1191        | 3.33  | 3000 | 0.1528          | 0.7969    | 0.8596 | 0.8270 | 0.9646   |
| 0.1128        | 3.89  | 3500 | 0.1552          | 0.7668    | 0.8711 | 0.8156 | 0.9610   |
| 0.095         | 4.44  | 4000 | 0.1678          | 0.7658    | 0.8615 | 0.8108 | 0.9632   |
| 0.0979        | 5.0   | 4500 | 0.1432          | 0.8079    | 0.8625 | 0.8343 | 0.9672   |
| 0.0764        | 5.56  | 5000 | 0.1548          | 0.8098    | 0.8528 | 0.8307 | 0.9671   |
| 0.0829        | 6.11  | 5500 | 0.1423          | 0.8128    | 0.8653 | 0.8382 | 0.9672   |
| 0.0648        | 6.67  | 6000 | 0.1548          | 0.8038    | 0.8760 | 0.8383 | 0.9673   |
| 0.0529        | 7.22  | 6500 | 0.1653          | 0.8139    | 0.8716 | 0.8418 | 0.9675   |
| 0.0483        | 7.78  | 7000 | 0.1630          | 0.8186    | 0.8649 | 0.8411 | 0.9680   |
| 0.0494        | 8.33  | 7500 | 0.1709          | 0.8233    | 0.8682 | 0.8452 | 0.9686   |
| 0.0389        | 8.89  | 8000 | 0.1757          | 0.8211    | 0.8726 | 0.8460 | 0.9687   |
| 0.0356        | 9.44  | 8500 | 0.1740          | 0.8242    | 0.8736 | 0.8482 | 0.9692   |
| 0.0337        | 10.0  | 9000 | 0.1759          | 0.8214    | 0.8726 | 0.8462 | 0.9690   |


### Framework versions

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