metadata

base_model: Davlan/bert-base-multilingual-cased-finetuned-hausa
language: ha
widget:
  - text: Rubuta abun
tags:
  - generated_from_trainer
model-index:
  - name: hausa-distilbert
    results: []

hausa-distilbert

This model was trained on the fine-tuned Bert version of Davlan on a developed dataset.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-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: 3.0

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1