---
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: 0.8413379073756432
    - name: Recall
      type: recall
      value: 0.8802153432032301
    - name: F1
      type: f1
      value: 0.860337645253234
    - name: Accuracy
      type: accuracy
      value: 0.9612787384363168
---

<!-- 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: 0.2313
- Precision: 0.8413
- Recall: 0.8802
- F1: 0.8603
- Accuracy: 0.9613

## 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: 500
- num_epochs: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.7584        | 0.85  | 500  | 0.2266          | 0.6844    | 0.8044 | 0.7395 | 0.9401   |
| 0.2143        | 1.7   | 1000 | 0.2301          | 0.7516    | 0.8268 | 0.7874 | 0.9447   |
| 0.1472        | 2.56  | 1500 | 0.2024          | 0.7634    | 0.8452 | 0.8022 | 0.9535   |
| 0.1109        | 3.41  | 2000 | 0.1845          | 0.7719    | 0.8686 | 0.8174 | 0.9571   |
| 0.0843        | 4.26  | 2500 | 0.1853          | 0.8025    | 0.8694 | 0.8346 | 0.9585   |
| 0.0576        | 5.11  | 3000 | 0.1976          | 0.8235    | 0.8896 | 0.8553 | 0.9599   |
| 0.0403        | 5.96  | 3500 | 0.2000          | 0.8308    | 0.8766 | 0.8531 | 0.9596   |
| 0.025         | 6.81  | 4000 | 0.2242          | 0.8304    | 0.8811 | 0.8550 | 0.9602   |
| 0.0206        | 7.67  | 4500 | 0.2313          | 0.8413    | 0.8802 | 0.8603 | 0.9613   |


### Framework versions

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