---
license: mit
tags:
- generated_from_trainer
datasets:
- lg-ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: luganda-ner-v1
  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: 0.9370212765957446
    - name: Recall
      type: recall
      value: 0.9359591952394446
    - name: F1
      type: f1
      value: 0.9364899347887723
    - name: Accuracy
      type: accuracy
      value: 0.9824210946863764
---

<!-- 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-v1

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: 0.0908
- Precision: 0.9370
- Recall: 0.9360
- F1: 0.9365
- Accuracy: 0.9824

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.5792        | 1.0   | 609  | 0.2463          | 0.7259    | 0.7662 | 0.7455 | 0.9406   |
| 0.2271        | 2.0   | 1218 | 0.1587          | 0.8198    | 0.8782 | 0.8480 | 0.9607   |
| 0.1652        | 3.0   | 1827 | 0.1289          | 0.8612    | 0.8918 | 0.8762 | 0.9677   |
| 0.1266        | 4.0   | 2436 | 0.1083          | 0.8990    | 0.9059 | 0.9025 | 0.9744   |
| 0.081         | 5.0   | 3045 | 0.1043          | 0.9183    | 0.9147 | 0.9165 | 0.9767   |
| 0.0676        | 6.0   | 3654 | 0.0893          | 0.9261    | 0.9334 | 0.9297 | 0.9811   |
| 0.0565        | 7.0   | 4263 | 0.0877          | 0.9389    | 0.9368 | 0.9379 | 0.9813   |
| 0.0519        | 8.0   | 4872 | 0.0919          | 0.9404    | 0.9340 | 0.9372 | 0.9819   |
| 0.047         | 9.0   | 5481 | 0.0896          | 0.9376    | 0.9360 | 0.9368 | 0.9825   |
| 0.0379        | 10.0  | 6090 | 0.0908          | 0.9370    | 0.9360 | 0.9365 | 0.9824   |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2