---
library_name: transformers
base_model: amidblue/mBertKE
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: AfrimBert-QA
  results: []
---

<!-- 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. -->

# AfrimBert-QA

This model is a fine-tuned version of [amidblue/mBertKE](https://huggingface.co/amidblue/mBertKE) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4343
- Model Preparation Time: 0.0029
- Start Accuracy: 0.6830
- End Accuracy: 0.6846
- F1: 0.4070

## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Start Accuracy | End Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:--------------:|:------------:|:------:|
| 1.3282        | 1.0   | 843  | 1.4711          | 0.0029                 | 0.6496         | 0.6483       | 0.3583 |
| 1.2456        | 2.0   | 1686 | 1.3864          | 0.0029                 | 0.6750         | 0.6737       | 0.3833 |
| 0.8872        | 3.0   | 2529 | 1.4020          | 0.0029                 | 0.6780         | 0.6833       | 0.3947 |
| 0.7419        | 4.0   | 3372 | 1.4343          | 0.0029                 | 0.6830         | 0.6846       | 0.4070 |


### Framework versions

- Transformers 5.0.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2