---
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: 0.8374155405405406
    - name: Recall
      type: recall
      value: 0.8896366083445492
    - name: F1
      type: f1
      value: 0.8627365673265174
    - name: Accuracy
      type: accuracy
      value: 0.9609274366680979
---

<!-- 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: 0.2870
- Precision: 0.8374
- Recall: 0.8896
- F1: 0.8627
- Accuracy: 0.9609

## 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: 25

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.4362        | 1.7   | 500  | 0.1915          | 0.7142    | 0.8407 | 0.7723 | 0.9498   |
| 0.1873        | 3.4   | 1000 | 0.1735          | 0.7945    | 0.8793 | 0.8348 | 0.9584   |
| 0.1395        | 5.1   | 1500 | 0.1774          | 0.7771    | 0.8681 | 0.8201 | 0.9582   |
| 0.1031        | 6.8   | 2000 | 0.1837          | 0.8025    | 0.8748 | 0.8371 | 0.9582   |
| 0.0825        | 8.5   | 2500 | 0.1937          | 0.8106    | 0.8852 | 0.8462 | 0.9585   |
| 0.0671        | 10.2  | 3000 | 0.2007          | 0.8338    | 0.8932 | 0.8625 | 0.9609   |
| 0.0538        | 11.9  | 3500 | 0.2101          | 0.8222    | 0.8901 | 0.8548 | 0.9603   |
| 0.0419        | 13.61 | 4000 | 0.2177          | 0.8186    | 0.8905 | 0.8530 | 0.9619   |
| 0.0361        | 15.31 | 4500 | 0.2299          | 0.8316    | 0.8843 | 0.8571 | 0.9612   |
| 0.0281        | 17.01 | 5000 | 0.2474          | 0.8300    | 0.8825 | 0.8554 | 0.9610   |
| 0.0234        | 18.71 | 5500 | 0.2623          | 0.8327    | 0.8843 | 0.8577 | 0.9606   |
| 0.0194        | 20.41 | 6000 | 0.2702          | 0.8311    | 0.8829 | 0.8562 | 0.9603   |
| 0.0169        | 22.11 | 6500 | 0.2781          | 0.8358    | 0.8883 | 0.8612 | 0.9608   |
| 0.0151        | 23.81 | 7000 | 0.2870          | 0.8374    | 0.8896 | 0.8627 | 0.9609   |


### Framework versions

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