---
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: 0.8222823635543527
    - name: Recall
      type: recall
      value: 0.8798262548262549
    - name: F1
      type: f1
      value: 0.8500816041035206
    - name: Accuracy
      type: accuracy
      value: 0.9681297986382732
---

<!-- 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: 0.2071
- Precision: 0.8223
- Recall: 0.8798
- F1: 0.8501
- Accuracy: 0.9681

## 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.4978        | 2.22  | 500  | 0.1737          | 0.6882    | 0.8118 | 0.7449 | 0.9548   |
| 0.149         | 4.44  | 1000 | 0.1573          | 0.7540    | 0.8552 | 0.8014 | 0.9596   |
| 0.0796        | 6.67  | 1500 | 0.1530          | 0.8024    | 0.8760 | 0.8376 | 0.9648   |
| 0.0473        | 8.89  | 2000 | 0.1539          | 0.8051    | 0.8731 | 0.8377 | 0.9675   |
| 0.0272        | 11.11 | 2500 | 0.2028          | 0.7973    | 0.8581 | 0.8266 | 0.9643   |
| 0.0154        | 13.33 | 3000 | 0.2071          | 0.8223    | 0.8798 | 0.8501 | 0.9681   |


### Framework versions

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