---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: n3wtou/mt5-small-finedtuned-4-swahili
  results: []
datasets:
- csebuetnlp/xlsum
language:
- sw
metrics:
- rouge
---

<!-- 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. -->

# n3wtou/mt5-small-finedtuned-4-swahili

This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the [csebuetnlp/xlsum](https://huggingface.co/datasets/csebuetnlp/xlsum/viewer/swahili/train) dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.0006
- Validation Loss: 2.7015
- Epoch: 9

## Model description

This model is a fined-tuned google/mt5-small for Kiswahili abstractive text generation

## 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': 'WarmUp', 'config': {'initial_learning_rate': 0.0003, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 9900, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 100, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
- training_precision: mixed_float16

### Training results

| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 7.0434     | 3.2396          | 0     |
| 4.3604     | 3.0452          | 1     |
| 3.9184     | 2.9186          | 2     |
| 3.6516     | 2.8443          | 3     |
| 3.4569     | 2.7955          | 4     |
| 3.3146     | 2.7645          | 5     |
| 3.2039     | 2.7292          | 6     |
| 3.1135     | 2.7182          | 7     |
| 3.0450     | 2.7040          | 8     |
| 3.0006     | 2.7015          | 9     |


### Framework versions

- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3