---
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: 0.8365145228215768
    - name: Recall
      type: recall
      value: 0.8912466843501327
    - name: F1
      type: f1
      value: 0.863013698630137
    - name: Accuracy
      type: accuracy
      value: 0.9635817166946407
---

<!-- 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: 0.1900
- Precision: 0.8365
- Recall: 0.8912
- F1: 0.8630
- Accuracy: 0.9636

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.7817        | 0.85  | 500  | 0.2275          | 0.7073    | 0.7918 | 0.7472 | 0.9392   |
| 0.2438        | 1.7   | 1000 | 0.1940          | 0.7138    | 0.8324 | 0.7686 | 0.9493   |
| 0.1652        | 2.56  | 1500 | 0.1722          | 0.7951    | 0.8678 | 0.8298 | 0.9577   |
| 0.1346        | 3.41  | 2000 | 0.1706          | 0.8049    | 0.8811 | 0.8413 | 0.9593   |
| 0.107         | 4.26  | 2500 | 0.1750          | 0.7991    | 0.8793 | 0.8373 | 0.9611   |
| 0.0851        | 5.11  | 3000 | 0.1976          | 0.7964    | 0.8820 | 0.8370 | 0.9591   |
| 0.0711        | 5.96  | 3500 | 0.1763          | 0.8195    | 0.8793 | 0.8484 | 0.9623   |
| 0.0528        | 6.81  | 4000 | 0.1883          | 0.8341    | 0.8912 | 0.8617 | 0.9632   |
| 0.0475        | 7.67  | 4500 | 0.1900          | 0.8365    | 0.8912 | 0.8630 | 0.9636   |


### Framework versions

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