---
license: mit
tags:
- generated_from_trainer
datasets:
- lg-ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: luganda-ner-v4
  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: 0.7849185946872322
    - name: Recall
      type: recall
      value: 0.7862660944206008
    - name: F1
      type: f1
      value: 0.7855917667238421
    - name: Accuracy
      type: accuracy
      value: 0.9542220362038296
---

<!-- 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-v4

This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the lg-ner dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2222
- Precision: 0.7849
- Recall: 0.7863
- F1: 0.7856
- Accuracy: 0.9542

## 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  | 0.3533          | 0.6141    | 0.4644 | 0.5288 | 0.9208   |
| 0.5126        | 2.0   | 522  | 0.2765          | 0.6658    | 0.6567 | 0.6612 | 0.9326   |
| 0.5126        | 3.0   | 783  | 0.2336          | 0.6834    | 0.7133 | 0.6980 | 0.9433   |
| 0.2374        | 4.0   | 1044 | 0.2207          | 0.7358    | 0.7433 | 0.7395 | 0.9489   |
| 0.2374        | 5.0   | 1305 | 0.2134          | 0.7796    | 0.7528 | 0.7659 | 0.9525   |
| 0.1646        | 6.0   | 1566 | 0.2359          | 0.7423    | 0.7665 | 0.7542 | 0.9484   |
| 0.1646        | 7.0   | 1827 | 0.2223          | 0.7807    | 0.7854 | 0.7831 | 0.9541   |
| 0.1219        | 8.0   | 2088 | 0.2300          | 0.8140    | 0.7665 | 0.7896 | 0.9557   |
| 0.1219        | 9.0   | 2349 | 0.2223          | 0.7733    | 0.7966 | 0.7848 | 0.9547   |
| 0.1016        | 10.0  | 2610 | 0.2222          | 0.7849    | 0.7863 | 0.7856 | 0.9542   |


### Framework versions

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