---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: google-vit-base-patch16-224-in21k-batch_16_epoch_4_classes_24
  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: 0.9683908045977011
---

<!-- 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. -->

# google-vit-base-patch16-224-in21k-batch_16_epoch_4_classes_24

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: 0.1385
- Accuracy: 0.9684

## 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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7768        | 0.07  | 100  | 0.7113          | 0.9282   |
| 0.3925        | 0.14  | 200  | 0.4597          | 0.8908   |
| 0.2437        | 0.21  | 300  | 0.3130          | 0.9282   |
| 0.2105        | 0.28  | 400  | 0.3497          | 0.9023   |
| 0.1744        | 0.35  | 500  | 0.3150          | 0.9124   |
| 0.167         | 0.42  | 600  | 0.2949          | 0.9239   |
| 0.1176        | 0.49  | 700  | 0.3204          | 0.9195   |
| 0.077         | 0.56  | 800  | 0.3104          | 0.9253   |
| 0.1113        | 0.63  | 900  | 0.1950          | 0.9511   |
| 0.1172        | 0.7   | 1000 | 0.2692          | 0.9239   |
| 0.0971        | 0.77  | 1100 | 0.3097          | 0.9267   |
| 0.1143        | 0.84  | 1200 | 0.2072          | 0.9454   |
| 0.1545        | 0.91  | 1300 | 0.2859          | 0.9253   |
| 0.0794        | 0.97  | 1400 | 0.2893          | 0.9224   |
| 0.0951        | 1.04  | 1500 | 0.2094          | 0.9483   |
| 0.0657        | 1.11  | 1600 | 0.2714          | 0.9353   |
| 0.0068        | 1.18  | 1700 | 0.2305          | 0.9425   |
| 0.0511        | 1.25  | 1800 | 0.1682          | 0.9555   |
| 0.0629        | 1.32  | 1900 | 0.2328          | 0.9454   |
| 0.0373        | 1.39  | 2000 | 0.3263          | 0.9310   |
| 0.0885        | 1.46  | 2100 | 0.2341          | 0.9454   |
| 0.0433        | 1.53  | 2200 | 0.2670          | 0.9397   |
| 0.0046        | 1.6   | 2300 | 0.2308          | 0.9468   |
| 0.0054        | 1.67  | 2400 | 0.3182          | 0.9296   |
| 0.0952        | 1.74  | 2500 | 0.2297          | 0.9411   |
| 0.1361        | 1.81  | 2600 | 0.2058          | 0.9454   |
| 0.1124        | 1.88  | 2700 | 0.1656          | 0.9598   |
| 0.0339        | 1.95  | 2800 | 0.1933          | 0.9526   |
| 0.0021        | 2.02  | 2900 | 0.1475          | 0.9569   |
| 0.0248        | 2.09  | 3000 | 0.1806          | 0.9583   |
| 0.0013        | 2.16  | 3100 | 0.1899          | 0.9526   |
| 0.0035        | 2.23  | 3200 | 0.1391          | 0.9641   |
| 0.0358        | 2.3   | 3300 | 0.1593          | 0.9684   |
| 0.0026        | 2.37  | 3400 | 0.1927          | 0.9612   |
| 0.001         | 2.44  | 3500 | 0.1756          | 0.9583   |
| 0.0113        | 2.51  | 3600 | 0.1512          | 0.9713   |
| 0.0009        | 2.58  | 3700 | 0.1540          | 0.9698   |
| 0.0498        | 2.65  | 3800 | 0.1498          | 0.9641   |
| 0.0084        | 2.72  | 3900 | 0.1435          | 0.9655   |
| 0.001         | 2.79  | 4000 | 0.1199          | 0.9713   |
| 0.0011        | 2.86  | 4100 | 0.1301          | 0.9655   |
| 0.003         | 2.92  | 4200 | 0.1350          | 0.9727   |
| 0.0025        | 2.99  | 4300 | 0.1764          | 0.9583   |
| 0.0006        | 3.06  | 4400 | 0.1564          | 0.9713   |
| 0.0006        | 3.13  | 4500 | 0.1524          | 0.9713   |
| 0.0006        | 3.2   | 4600 | 0.1515          | 0.9727   |
| 0.0006        | 3.27  | 4700 | 0.1633          | 0.9741   |
| 0.0005        | 3.34  | 4800 | 0.1404          | 0.9713   |
| 0.0005        | 3.41  | 4900 | 0.1586          | 0.9684   |
| 0.0005        | 3.48  | 5000 | 0.1576          | 0.9655   |
| 0.0005        | 3.55  | 5100 | 0.1505          | 0.9684   |
| 0.0153        | 3.62  | 5200 | 0.1369          | 0.9684   |
| 0.0005        | 3.69  | 5300 | 0.1579          | 0.9670   |
| 0.0005        | 3.76  | 5400 | 0.1451          | 0.9698   |
| 0.0005        | 3.83  | 5500 | 0.1417          | 0.9698   |
| 0.0005        | 3.9   | 5600 | 0.1380          | 0.9698   |
| 0.0004        | 3.97  | 5700 | 0.1385          | 0.9684   |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2