---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: emotion_classification_v1
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train[:5000]
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.59375
    - name: Precision
      type: precision
      value: 0.6599395444120348
    - name: Recall
      type: recall
      value: 0.59375
    - name: F1
      type: f1
      value: 0.5919790409999833
---

<!-- 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. -->

# emotion_classification_v1

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1926
- Accuracy: 0.5938
- Precision: 0.6599
- Recall: 0.5938
- F1: 0.5920

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log        | 1.0   | 80   | 1.6474          | 0.3375   | 0.3120    | 0.3375 | 0.2259 |
| No log        | 2.0   | 160  | 1.4434          | 0.4625   | 0.5606    | 0.4625 | 0.4112 |
| No log        | 3.0   | 240  | 1.3266          | 0.4875   | 0.5296    | 0.4875 | 0.4516 |
| No log        | 4.0   | 320  | 1.2547          | 0.5375   | 0.5836    | 0.5375 | 0.5342 |
| No log        | 5.0   | 400  | 1.2195          | 0.5875   | 0.6815    | 0.5875 | 0.5900 |
| No log        | 6.0   | 480  | 1.1895          | 0.5563   | 0.5709    | 0.5563 | 0.5424 |
| 1.2914        | 7.0   | 560  | 1.1572          | 0.5437   | 0.5607    | 0.5437 | 0.5431 |
| 1.2914        | 8.0   | 640  | 1.1822          | 0.5563   | 0.5602    | 0.5563 | 0.5515 |
| 1.2914        | 9.0   | 720  | 1.2712          | 0.55     | 0.5695    | 0.55   | 0.5530 |
| 1.2914        | 10.0  | 800  | 1.2196          | 0.5625   | 0.5701    | 0.5625 | 0.5559 |
| 1.2914        | 11.0  | 880  | 1.2460          | 0.5312   | 0.5584    | 0.5312 | 0.5357 |
| 1.2914        | 12.0  | 960  | 1.2473          | 0.5563   | 0.5710    | 0.5563 | 0.5553 |
| 0.5247        | 13.0  | 1040 | 1.2438          | 0.575    | 0.5908    | 0.575  | 0.5761 |
| 0.5247        | 14.0  | 1120 | 1.3033          | 0.5312   | 0.5391    | 0.5312 | 0.5305 |
| 0.5247        | 15.0  | 1200 | 1.2928          | 0.5625   | 0.5861    | 0.5625 | 0.5673 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1