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

Table of Contents

• Model Details
• Uses
• Training
• 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 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 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

Framework versions

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