---
license: mit
tags:
- generated_from_trainer
datasets:
- lg-ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: luganda-ner-v2
  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: 0.9352766798418972
    - name: Recall
      type: recall
      value: 0.9288518155053974
    - name: F1
      type: f1
      value: 0.93205317577548
    - name: Accuracy
      type: accuracy
      value: 0.9817219554779573
---

<!-- 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-v2

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the lg-ner dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0955
- Precision: 0.9353
- Recall: 0.9289
- F1: 0.9321
- Accuracy: 0.9817

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.5913        | 1.0   | 609  | 0.2667          | 0.6740    | 0.7620 | 0.7153 | 0.9336   |
| 0.2461        | 2.0   | 1218 | 0.1704          | 0.7981    | 0.8437 | 0.8203 | 0.9562   |
| 0.1784        | 3.0   | 1827 | 0.1273          | 0.8578    | 0.8943 | 0.8757 | 0.9669   |
| 0.1337        | 4.0   | 2436 | 0.1048          | 0.8731    | 0.9132 | 0.8927 | 0.9726   |
| 0.0868        | 5.0   | 3045 | 0.0988          | 0.9129    | 0.9178 | 0.9153 | 0.9760   |
| 0.0736        | 6.0   | 3654 | 0.0961          | 0.9146    | 0.9225 | 0.9185 | 0.9781   |
| 0.0602        | 7.0   | 4263 | 0.0877          | 0.9270    | 0.9222 | 0.9246 | 0.9798   |
| 0.0566        | 8.0   | 4872 | 0.0948          | 0.9281    | 0.9222 | 0.9252 | 0.9807   |
| 0.0514        | 9.0   | 5481 | 0.0930          | 0.9349    | 0.9271 | 0.9310 | 0.9817   |
| 0.0395        | 10.0  | 6090 | 0.0955          | 0.9353    | 0.9289 | 0.9321 | 0.9817   |


### Framework versions

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