---
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: 0.8515562649640862
    - name: Recall
      type: recall
      value: 0.8814539446509707
    - name: F1
      type: f1
      value: 0.8662472092551248
    - name: Accuracy
      type: accuracy
      value: 0.9700709836303056
---

<!-- 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: 0.2179
- Precision: 0.8516
- Recall: 0.8815
- F1: 0.8662
- Accuracy: 0.9701

## 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.267         | 1.0   | 7193  | 0.2806          | 0.7707    | 0.8009 | 0.7855 | 0.9525   |
| 0.1977        | 2.0   | 14386 | 0.1792          | 0.8151    | 0.8451 | 0.8299 | 0.9616   |
| 0.1767        | 3.0   | 21579 | 0.1935          | 0.8293    | 0.8711 | 0.8497 | 0.9662   |
| 0.0929        | 4.0   | 28772 | 0.2219          | 0.8382    | 0.8860 | 0.8614 | 0.9677   |
| 0.0788        | 5.0   | 35965 | 0.2179          | 0.8516    | 0.8815 | 0.8662 | 0.9701   |


### Framework versions

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