---
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: 0.8074141048824593
    - name: Recall
      type: recall
      value: 0.861969111969112
    - name: F1
      type: f1
      value: 0.8338001867413634
    - name: Accuracy
      type: accuracy
      value: 0.9655222367086774
---

<!-- 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: 0.2044
- Precision: 0.8074
- Recall: 0.8620
- F1: 0.8338
- Accuracy: 0.9655

## 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: 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.5564        | 1.11  | 500  | 0.1852          | 0.6302    | 0.7558 | 0.6873 | 0.9502   |
| 0.1786        | 2.22  | 1000 | 0.1552          | 0.6952    | 0.8069 | 0.7469 | 0.9568   |
| 0.1219        | 3.33  | 1500 | 0.1665          | 0.6860    | 0.8214 | 0.7476 | 0.9577   |
| 0.087         | 4.44  | 2000 | 0.1616          | 0.7572    | 0.8263 | 0.7902 | 0.9595   |
| 0.0689        | 5.56  | 2500 | 0.1679          | 0.7670    | 0.8243 | 0.7946 | 0.9616   |
| 0.0442        | 6.67  | 3000 | 0.1612          | 0.7346    | 0.8364 | 0.7822 | 0.9631   |
| 0.0353        | 7.78  | 3500 | 0.1864          | 0.8099    | 0.8576 | 0.8331 | 0.9653   |
| 0.0205        | 8.89  | 4000 | 0.1950          | 0.8026    | 0.8653 | 0.8328 | 0.9654   |
| 0.0133        | 10.0  | 4500 | 0.2044          | 0.8074    | 0.8620 | 0.8338 | 0.9655   |


### Framework versions

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