---
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: 0.8314350797266514
    - name: Recall
      type: recall
      value: 0.8807915057915058
    - name: F1
      type: f1
      value: 0.8554019217248652
    - name: Accuracy
      type: accuracy
      value: 0.970911198029842
---

<!-- 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: 0.1616
- Precision: 0.8314
- Recall: 0.8808
- F1: 0.8554
- Accuracy: 0.9709

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3363        | 1.11  | 500  | 0.1563          | 0.7344    | 0.8234 | 0.7763 | 0.9607   |
| 0.1372        | 2.22  | 1000 | 0.1308          | 0.7641    | 0.8692 | 0.8133 | 0.9652   |
| 0.0998        | 3.33  | 1500 | 0.1368          | 0.7912    | 0.8668 | 0.8273 | 0.9671   |
| 0.077         | 4.44  | 2000 | 0.1360          | 0.8079    | 0.8707 | 0.8381 | 0.9690   |
| 0.0623        | 5.56  | 2500 | 0.1421          | 0.8181    | 0.8707 | 0.8436 | 0.9686   |
| 0.0458        | 6.67  | 3000 | 0.1488          | 0.8129    | 0.8764 | 0.8435 | 0.9706   |
| 0.0382        | 7.78  | 3500 | 0.1585          | 0.8320    | 0.8745 | 0.8527 | 0.9693   |
| 0.0299        | 8.89  | 4000 | 0.1585          | 0.8291    | 0.8755 | 0.8516 | 0.9705   |
| 0.0257        | 10.0  | 4500 | 0.1616          | 0.8314    | 0.8808 | 0.8554 | 0.9709   |


### Framework versions

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