---
license: mit
tags:
- generated_from_trainer
datasets:
- lextreme
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-mapa_coarse-ner
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: lextreme
      type: lextreme
      config: mapa_coarse
      split: test
      args: mapa_coarse
    metrics:
    - name: Precision
      type: precision
      value: 0.6624395127648923
    - name: Recall
      type: recall
      value: 0.6656606304493629
    - name: F1
      type: f1
      value: 0.6640461654261103
    - name: Accuracy
      type: accuracy
      value: 0.9872255987419513
---

<!-- 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. -->

# xlm-roberta-base-mapa_coarse-ner

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the lextreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0515
- Precision: 0.6624
- Recall: 0.6657
- F1: 0.6640
- Accuracy: 0.9872

## 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: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0584        | 1.0   | 1739  | 0.0576          | 0.6088    | 0.5790 | 0.5935 | 0.9860   |
| 0.0475        | 2.0   | 3478  | 0.0522          | 0.6455    | 0.6574 | 0.6514 | 0.9870   |
| 0.0409        | 3.0   | 5217  | 0.0517          | 0.6490    | 0.6675 | 0.6581 | 0.9871   |
| 0.04          | 4.0   | 6956  | 0.0516          | 0.6562    | 0.6720 | 0.6640 | 0.9871   |
| 0.0422        | 5.0   | 8695  | 0.0513          | 0.6573    | 0.6722 | 0.6647 | 0.9871   |
| 0.0398        | 6.0   | 10434 | 0.0515          | 0.6602    | 0.6697 | 0.6649 | 0.9872   |
| 0.0407        | 7.0   | 12173 | 0.0516          | 0.6612    | 0.6663 | 0.6638 | 0.9872   |
| 0.0382        | 8.0   | 13912 | 0.0516          | 0.6626    | 0.6648 | 0.6637 | 0.9872   |
| 0.0398        | 9.0   | 15651 | 0.0515          | 0.6627    | 0.6660 | 0.6643 | 0.9872   |
| 0.0401        | 10.0  | 17390 | 0.0515          | 0.6624    | 0.6657 | 0.6640 | 0.9872   |


### Framework versions

- Transformers 4.26.0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2