---
language: pt
license: mit
tags:
- question-answering
- bert
- bert-large
- pytorch
datasets:
- autogenerated
metrics:
- squad
widget:
- text: "Lucas Vázquez Iglesias ana miaka mingapi?"
  context: "Lucas Vázquez Iglesias (aliyezaliwa 1 Julai 1991) ni mchezaji wa soka wa Hispania ambaye anachezea klabu ya Real Madrid na timu ya taifa ya Hispania kama winga wa kulia."
- text: "Emil von Zelewski aliuawa katika vita gani?"
  context: "Emil von Zelewski (13 Machi 1854 - 1891) alikuwa afisa wa jeshi la Ujerumani. Alipokuwa kamanda ya kwanza wa jeshi la ulinzi la kikoloni katika Afrika ya Mashariki ya Kijerumani aliongoza jeshi hilo katika vita dhidi ya Wahehe alipouawa." 
---


# Swahili MCR & QA: a Swahili Machine Reading Comprehension and Question Answering model

## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Training](#training)
- [Evaluation](#evaluation)


## Model Details
- **Model Description:**
This is the first Swahili MCR Question Answering Model.
It is now available on Hugging Face.
- **Developed by:** Mohamed Gudle.
- **Model Type:** Fine-tuned Question Answering 
- **Language(s):** Swahili
- **Parent Model:** See the [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) for more information .
- **Resources for more information:**
  
  
## Uses
#### Direct Use
This model can be used for Machine Reading and Question Answering tasks.
## Risks, Limitations and Biases

<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->

# mgudle/bert-finetuned-swahili_qa

This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on mgudle/swahili_qa dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3585
- Epoch: 2

## 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1023, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16

### Training results

| Train Loss | Epoch |
|:----------:|:-----:|
| 1.1602     | 0     |
| 0.5513     | 1     |
| 0.3585     | 2     |


### Framework versions

- Transformers 4.20.1
- TensorFlow 2.8.2
- Datasets 2.3.2
- Tokenizers 0.12.1