---
library_name: transformers
base_model: Mahloromela/Afriberta-Swahili-mlm_model
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: Swahili-Classifier-cola
  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. -->

# Swahili-Classifier-cola

This model is a fine-tuned version of [Mahloromela/Afriberta-Swahili-mlm_model](https://huggingface.co/Mahloromela/Afriberta-Swahili-mlm_model) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2529
- Accuracy: 0.9239
- Precision: 0.9072
- Recall: 0.9286
- F1: 0.9178

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.2814        | 1.0   | 1111 | 0.2625          | 0.9192   | 0.8940    | 0.9340 | 0.9136 |
| 0.2163        | 2.0   | 2222 | 0.2529          | 0.9239   | 0.9072    | 0.9286 | 0.9178 |
| 0.1654        | 3.0   | 3333 | 0.3101          | 0.9171   | 0.8809    | 0.9468 | 0.9127 |
| 0.1155        | 4.0   | 4444 | 0.3601          | 0.9142   | 0.9117    | 0.8996 | 0.9056 |
| 0.0844        | 5.0   | 5555 | 0.4159          | 0.9104   | 0.9000    | 0.9045 | 0.9023 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1