---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: FYP2022
  results: []
---

<!-- 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. -->

# FYP2022

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.6016
- Train Sparse Categorical Accuracy: 0.7503
- Train Sparse Top 3 Categorical Accuracy: 0.9901
- Epoch: 5

## 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:
- optimizer: {'name': 'Adam', 'clipnorm': 1.0, 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32

### Training results

| Train Loss | Train Sparse Categorical Accuracy | Train Sparse Top 3 Categorical Accuracy | Epoch |
|:----------:|:---------------------------------:|:---------------------------------------:|:-----:|
| 0.9433     | 0.5975                            | 0.9523                                  | 0     |
| 0.8257     | 0.6498                            | 0.9704                                  | 1     |
| 0.7625     | 0.6765                            | 0.9778                                  | 2     |
| 0.7062     | 0.7014                            | 0.9832                                  | 3     |
| 0.6526     | 0.7263                            | 0.9872                                  | 4     |
| 0.6016     | 0.7503                            | 0.9901                                  | 5     |


### Framework versions

- Transformers 4.19.2
- TensorFlow 2.8.0
- Tokenizers 0.12.1