---
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: 0.8266722759781236
    - name: Recall
      type: recall
      value: 0.8815612382234186
    - name: F1
      type: f1
      value: 0.8532349109856708
    - name: Accuracy
      type: accuracy
      value: 0.961747140793942
---

<!-- 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: 0.2009
- Precision: 0.8267
- Recall: 0.8816
- F1: 0.8532
- Accuracy: 0.9617

## 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: 8
- eval_batch_size: 8
- 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: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.8866        | 0.85  | 500  | 0.2420          | 0.6729    | 0.7972 | 0.7298 | 0.9388   |
| 0.2429        | 1.7   | 1000 | 0.2028          | 0.7223    | 0.8331 | 0.7738 | 0.9491   |
| 0.1689        | 2.56  | 1500 | 0.1860          | 0.7606    | 0.8609 | 0.8077 | 0.9554   |
| 0.1427        | 3.41  | 2000 | 0.1791          | 0.7810    | 0.8672 | 0.8219 | 0.9548   |
| 0.1109        | 4.26  | 2500 | 0.1829          | 0.7876    | 0.8699 | 0.8267 | 0.9583   |
| 0.086         | 5.11  | 3000 | 0.2049          | 0.8042    | 0.8807 | 0.8407 | 0.9590   |
| 0.0706        | 5.96  | 3500 | 0.2008          | 0.8142    | 0.8730 | 0.8426 | 0.9600   |
| 0.0584        | 6.81  | 4000 | 0.1909          | 0.8253    | 0.8793 | 0.8514 | 0.9617   |
| 0.0512        | 7.67  | 4500 | 0.2009          | 0.8267    | 0.8816 | 0.8532 | 0.9617   |


### Framework versions

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