---
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: 0.8375401560348784
    - name: Recall
      type: recall
      value: 0.8807915057915058
    - name: F1
      type: f1
      value: 0.8586215008233357
    - name: Accuracy
      type: accuracy
      value: 0.9697233087063596
---

<!-- 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: 0.1726
- Precision: 0.8375
- Recall: 0.8808
- F1: 0.8586
- Accuracy: 0.9697

## 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
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 500
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.6046        | 1.11  | 500  | 0.1815          | 0.6422    | 0.7693 | 0.7000 | 0.9498   |
| 0.1671        | 2.22  | 1000 | 0.1389          | 0.7436    | 0.8456 | 0.7913 | 0.9620   |
| 0.1141        | 3.33  | 1500 | 0.1455          | 0.7949    | 0.8813 | 0.8359 | 0.9686   |
| 0.0854        | 4.44  | 2000 | 0.1455          | 0.8012    | 0.8678 | 0.8332 | 0.9684   |
| 0.0716        | 5.56  | 2500 | 0.1418          | 0.7996    | 0.8663 | 0.8316 | 0.9682   |
| 0.0506        | 6.67  | 3000 | 0.1570          | 0.8138    | 0.8793 | 0.8453 | 0.9690   |
| 0.0399        | 7.78  | 3500 | 0.1701          | 0.8363    | 0.8803 | 0.8577 | 0.9689   |
| 0.0324        | 8.89  | 4000 | 0.1720          | 0.8313    | 0.8798 | 0.8549 | 0.9691   |
| 0.0265        | 10.0  | 4500 | 0.1726          | 0.8375    | 0.8808 | 0.8586 | 0.9697   |


### Framework versions

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