---
library_name: transformers
base_model: motheecreator/vit-Facial-Expression-Recognition
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: vit-Facial-Expression-Recognition
  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. -->

# vit-Facial-Expression-Recognition

This model is a fine-tuned version of [motheecreator/vit-Facial-Expression-Recognition](https://huggingface.co/motheecreator/vit-Facial-Expression-Recognition) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3658
- Accuracy: 0.8753
- F1: 0.8737
- Precision: 0.8749
- Recall: 0.8753

## 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 4.5618        | 0.2164 | 100  | 0.3710          | 0.8762   | 0.8746 | 0.8752    | 0.8762 |
| 4.6091        | 0.4328 | 200  | 0.3677          | 0.8761   | 0.8747 | 0.8762    | 0.8761 |
| 4.5423        | 0.6492 | 300  | 0.3695          | 0.8748   | 0.8730 | 0.8745    | 0.8748 |
| 4.6307        | 0.8656 | 400  | 0.3745          | 0.8711   | 0.8692 | 0.8730    | 0.8711 |
| 4.3953        | 1.0801 | 500  | 0.3745          | 0.8727   | 0.8711 | 0.8724    | 0.8727 |
| 4.341         | 1.2965 | 600  | 0.3803          | 0.8688   | 0.8674 | 0.8688    | 0.8688 |
| 4.5471        | 1.5128 | 700  | 0.3841          | 0.8713   | 0.8699 | 0.8710    | 0.8713 |
| 4.522         | 1.7292 | 800  | 0.3836          | 0.8679   | 0.8662 | 0.8678    | 0.8679 |
| 4.5596        | 1.9456 | 900  | 0.3885          | 0.8672   | 0.8649 | 0.8678    | 0.8672 |
| 4.1491        | 2.1601 | 1000 | 0.3849          | 0.8691   | 0.8677 | 0.8689    | 0.8691 |
| 4.1037        | 2.3765 | 1100 | 0.3906          | 0.8667   | 0.8647 | 0.8669    | 0.8667 |
| 4.0033        | 2.5929 | 1200 | 0.3784          | 0.8704   | 0.8687 | 0.8699    | 0.8704 |
| 3.9759        | 2.8093 | 1300 | 0.3677          | 0.8752   | 0.8737 | 0.8747    | 0.8752 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0