---
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: 0.7704421562689279
    - name: Recall
      type: recall
      value: 0.7695099818511797
    - name: F1
      type: f1
      value: 0.7699757869249395
    - name: Accuracy
      type: accuracy
      value: 0.9434371807967313
---

<!-- 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: 0.2829
- Precision: 0.7704
- Recall: 0.7695
- F1: 0.7700
- Accuracy: 0.9434

## 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  | 0.4835          | 0.5191    | 0.3037 | 0.3832 | 0.8719   |
| 0.5738        | 2.0   | 522  | 0.3454          | 0.7288    | 0.5203 | 0.6071 | 0.9117   |
| 0.5738        | 3.0   | 783  | 0.2956          | 0.7752    | 0.6612 | 0.7137 | 0.9235   |
| 0.2549        | 4.0   | 1044 | 0.2791          | 0.7537    | 0.6848 | 0.7176 | 0.9258   |
| 0.2549        | 5.0   | 1305 | 0.2801          | 0.7530    | 0.7211 | 0.7367 | 0.9335   |
| 0.1566        | 6.0   | 1566 | 0.2675          | 0.7956    | 0.7229 | 0.7575 | 0.9393   |
| 0.1566        | 7.0   | 1827 | 0.2610          | 0.7744    | 0.7350 | 0.7542 | 0.9423   |
| 0.1054        | 8.0   | 2088 | 0.2731          | 0.7614    | 0.7586 | 0.7600 | 0.9423   |
| 0.1054        | 9.0   | 2349 | 0.2763          | 0.7794    | 0.7526 | 0.7658 | 0.9434   |
| 0.0771        | 10.0  | 2610 | 0.2829          | 0.7704    | 0.7695 | 0.7700 | 0.9434   |


### Framework versions

- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2