---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- lg-ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: luganda-ner-v6
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: lg-ner
      type: lg-ner
      config: lug
      split: test
      args: lug
    metrics:
    - name: Precision
      type: precision
      value: 0.8029689608636977
    - name: Recall
      type: recall
      value: 0.7991940899932841
    - name: F1
      type: f1
      value: 0.8010770784247729
    - name: Accuracy
      type: accuracy
      value: 0.9467474952809641
---

<!-- 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. -->

# luganda-ner-v6

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the lg-ner dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2811
- Precision: 0.8030
- Recall: 0.7992
- F1: 0.8011
- Accuracy: 0.9467

## 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
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 261  | 0.5150          | 0.4947    | 0.2841 | 0.3609 | 0.8692   |
| 0.6193        | 2.0   | 522  | 0.3422          | 0.7491    | 0.5393 | 0.6271 | 0.9161   |
| 0.6193        | 3.0   | 783  | 0.2737          | 0.7744    | 0.6595 | 0.7124 | 0.9306   |
| 0.2505        | 4.0   | 1044 | 0.3201          | 0.7343    | 0.7072 | 0.7205 | 0.9141   |
| 0.2505        | 5.0   | 1305 | 0.2564          | 0.7887    | 0.7569 | 0.7724 | 0.9375   |
| 0.1474        | 6.0   | 1566 | 0.2461          | 0.8173    | 0.7569 | 0.7859 | 0.9459   |
| 0.1474        | 7.0   | 1827 | 0.2739          | 0.8004    | 0.7757 | 0.7879 | 0.9434   |
| 0.0956        | 8.0   | 2088 | 0.2566          | 0.8100    | 0.7905 | 0.8001 | 0.9486   |
| 0.0956        | 9.0   | 2349 | 0.2709          | 0.7859    | 0.7938 | 0.7898 | 0.9463   |
| 0.0712        | 10.0  | 2610 | 0.2811          | 0.8030    | 0.7992 | 0.8011 | 0.9467   |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1