---
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- cnec
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: CNEC1_1_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: 0.8251895534962089
    - name: Recall
      type: recall
      value: 0.8788694481830417
    - name: F1
      type: f1
      value: 0.8511840104279819
    - name: Accuracy
      type: accuracy
      value: 0.9608493696084937
---

<!-- 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_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: 0.2044
- Precision: 0.8252
- Recall: 0.8789
- F1: 0.8512
- Accuracy: 0.9608

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.4123        | 0.85  | 500  | 0.2026          | 0.7055    | 0.8255 | 0.7608 | 0.9474   |
| 0.196         | 1.7   | 1000 | 0.1791          | 0.7699    | 0.8573 | 0.8113 | 0.9543   |
| 0.145         | 2.56  | 1500 | 0.1962          | 0.7604    | 0.8430 | 0.7996 | 0.9533   |
| 0.1184        | 3.41  | 2000 | 0.1812          | 0.7897    | 0.8708 | 0.8282 | 0.9569   |
| 0.0959        | 4.26  | 2500 | 0.1788          | 0.7989    | 0.8681 | 0.8321 | 0.9601   |
| 0.0707        | 5.11  | 3000 | 0.1868          | 0.8106    | 0.8852 | 0.8462 | 0.9616   |
| 0.0561        | 5.96  | 3500 | 0.1988          | 0.8132    | 0.8730 | 0.8421 | 0.9596   |
| 0.0404        | 6.81  | 4000 | 0.2027          | 0.8268    | 0.8847 | 0.8548 | 0.9614   |
| 0.0383        | 7.67  | 4500 | 0.2044          | 0.8252    | 0.8789 | 0.8512 | 0.9608   |


### Framework versions

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