---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: NabeelShar/emotions_classifier
  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. -->

# NabeelShar/emotions_classifier

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1967
- Validation Loss: 2.2308
- Train Accuracy: 0.4125
- Epoch: 19

## 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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 3200, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
- training_precision: float32

### Training results

| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.9733     | 1.7759          | 0.4            | 0     |
| 0.9887     | 1.5178          | 0.4562         | 1     |
| 0.9215     | 1.5833          | 0.4062         | 2     |
| 0.8050     | 1.6781          | 0.3875         | 3     |
| 0.7375     | 1.6757          | 0.45           | 4     |
| 0.8264     | 1.4876          | 0.475          | 5     |
| 0.6653     | 1.5971          | 0.4813         | 6     |
| 0.5938     | 1.8312          | 0.4188         | 7     |
| 0.5813     | 1.7869          | 0.4625         | 8     |
| 0.5660     | 1.8466          | 0.4375         | 9     |
| 0.5113     | 1.8829          | 0.4437         | 10    |
| 0.4774     | 1.7442          | 0.4188         | 11    |
| 0.3519     | 2.0356          | 0.4313         | 12    |
| 0.4080     | 1.9572          | 0.4313         | 13    |
| 0.3292     | 1.9208          | 0.4437         | 14    |
| 0.2668     | 2.0447          | 0.4562         | 15    |
| 0.2678     | 2.1450          | 0.3937         | 16    |
| 0.2556     | 2.1900          | 0.4562         | 17    |
| 0.1748     | 2.1947          | 0.4625         | 18    |
| 0.1967     | 2.2308          | 0.4125         | 19    |


### Framework versions

- Transformers 4.33.1
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3