---
library_name: keras
language:
- en
pipeline_tag: text-classification
---

## Model description

NLP model for fake news classification using Roberta pre-trained model

## Intended uses & limitations

Fake news classification

## Training and evaluation data

Trained on 80% of English fake news classification dataset:
https://www.kaggle.com/datasets/sadikaljarif/fake-news-detection-dataset-english

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:

| Hyperparameters | Value |
| :-- | :-- |
| name | Adam |
| clipnorm | 0.8 |
| learning_rate | 2.9999999242136255e-05 |
| decay | 0.025 |
| beta_1 | 0.8999999761581421 |
| beta_2 | 0.9990000128746033 |
| epsilon | 9e-09 |
| amsgrad | False |
| training_precision | float32 |


 ## Model Plot

<details>
<summary>View Model Plot</summary>

![Model Image](./model.png)

</details>