---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-emotions-fp16
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9859375
---

<!-- 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-emotions-fp16

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: 0.0725
- Accuracy: 0.9859

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 40   | 1.3965          | 0.4938   |
| No log        | 2.0   | 80   | 1.4154          | 0.425    |
| No log        | 3.0   | 120  | 1.3729          | 0.4562   |
| No log        | 4.0   | 160  | 1.3532          | 0.4562   |
| No log        | 5.0   | 200  | 1.2993          | 0.5062   |
| No log        | 6.0   | 240  | 1.3438          | 0.4938   |
| No log        | 7.0   | 280  | 1.3741          | 0.5      |
| No log        | 8.0   | 320  | 1.5267          | 0.4313   |
| No log        | 9.0   | 360  | 1.2778          | 0.5375   |
| No log        | 10.0  | 400  | 1.3864          | 0.5062   |
| No log        | 11.0  | 440  | 1.4221          | 0.4875   |
| No log        | 12.0  | 480  | 1.5059          | 0.5062   |
| 0.7596        | 13.0  | 520  | 1.5004          | 0.5188   |
| 0.7596        | 14.0  | 560  | 1.4539          | 0.5125   |
| 0.7596        | 15.0  | 600  | 1.5219          | 0.5375   |
| 0.7596        | 16.0  | 640  | 1.6179          | 0.4813   |
| 0.7596        | 17.0  | 680  | 1.4562          | 0.55     |
| 0.7596        | 18.0  | 720  | 1.5473          | 0.4875   |
| 0.7596        | 19.0  | 760  | 1.5820          | 0.5188   |
| 0.7596        | 20.0  | 800  | 1.5877          | 0.5125   |
| 0.7596        | 21.0  | 840  | 1.4965          | 0.55     |
| 0.7596        | 22.0  | 880  | 1.5947          | 0.5375   |
| 0.7596        | 23.0  | 920  | 1.4672          | 0.5437   |
| 0.7596        | 24.0  | 960  | 1.7930          | 0.5      |
| 0.2328        | 25.0  | 1000 | 1.8033          | 0.4875   |
| 0.2328        | 26.0  | 1040 | 1.7193          | 0.5312   |
| 0.2328        | 27.0  | 1080 | 1.8072          | 0.4813   |
| 0.2328        | 28.0  | 1120 | 1.6767          | 0.5437   |
| 0.2328        | 29.0  | 1160 | 1.6138          | 0.5625   |
| 0.2328        | 30.0  | 1200 | 1.8484          | 0.4938   |
| 0.2328        | 31.0  | 1240 | 1.7691          | 0.5062   |
| 0.2328        | 32.0  | 1280 | 1.7797          | 0.5062   |
| 0.2328        | 33.0  | 1320 | 1.7575          | 0.5375   |
| 0.2328        | 34.0  | 1360 | 1.7550          | 0.5062   |
| 0.2328        | 35.0  | 1400 | 1.7933          | 0.5      |
| 0.2328        | 36.0  | 1440 | 1.7056          | 0.5563   |
| 0.2328        | 37.0  | 1480 | 1.8739          | 0.4938   |
| 0.1517        | 38.0  | 1520 | 1.7637          | 0.5188   |
| 0.1517        | 39.0  | 1560 | 1.7178          | 0.5563   |
| 0.1517        | 40.0  | 1600 | 1.9114          | 0.5      |
| 0.1517        | 41.0  | 1640 | 1.8453          | 0.5188   |
| 0.1517        | 42.0  | 1680 | 1.7571          | 0.5625   |
| 0.1517        | 43.0  | 1720 | 1.7757          | 0.5437   |
| 0.1517        | 44.0  | 1760 | 1.8389          | 0.5125   |
| 0.1517        | 45.0  | 1800 | 1.8109          | 0.5375   |
| 0.1517        | 46.0  | 1840 | 1.8537          | 0.4688   |
| 0.1517        | 47.0  | 1880 | 1.7422          | 0.5563   |
| 0.1517        | 48.0  | 1920 | 1.7807          | 0.5687   |
| 0.1517        | 49.0  | 1960 | 1.8111          | 0.525    |
| 0.1045        | 50.0  | 2000 | 1.9057          | 0.5125   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2