---
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: 0.8205234732031574
    - name: Recall
      type: recall
      value: 0.88604755495738
    - name: F1
      type: f1
      value: 0.8520276100086281
    - name: Accuracy
      type: accuracy
      value: 0.9624497443303798
---

<!-- 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: 0.1914
- Precision: 0.8205
- Recall: 0.8860
- F1: 0.8520
- Accuracy: 0.9624

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.4532        | 0.85  | 500  | 0.2036          | 0.7303    | 0.8295 | 0.7767 | 0.9476   |
| 0.2172        | 1.7   | 1000 | 0.1727          | 0.7560    | 0.8591 | 0.8043 | 0.9566   |
| 0.1572        | 2.56  | 1500 | 0.1901          | 0.7733    | 0.8690 | 0.8183 | 0.9566   |
| 0.1341        | 3.41  | 2000 | 0.1661          | 0.7905    | 0.8753 | 0.8307 | 0.9599   |
| 0.1093        | 4.26  | 2500 | 0.1747          | 0.8087    | 0.8856 | 0.8454 | 0.9610   |
| 0.0876        | 5.11  | 3000 | 0.1987          | 0.7949    | 0.8798 | 0.8352 | 0.9588   |
| 0.0752        | 5.96  | 3500 | 0.1827          | 0.8146    | 0.8834 | 0.8476 | 0.9622   |
| 0.0574        | 6.81  | 4000 | 0.1834          | 0.8221    | 0.8937 | 0.8564 | 0.9638   |
| 0.0542        | 7.67  | 4500 | 0.1914          | 0.8205    | 0.8860 | 0.8520 | 0.9624   |


### Framework versions

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