---
license: apache-2.0
base_model: google/vit-base-patch16-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: rmsProp_VitB-p16-384-1e-4-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: 0.9798850574712644
---

<!-- 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. -->

# rmsProp_VitB-p16-384-1e-4-batch_16_epoch_4_classes_24

This model is a fine-tuned version of [google/vit-base-patch16-384](https://huggingface.co/google/vit-base-patch16-384) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0907
- Accuracy: 0.9799

## 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: 0.0001
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2663        | 0.07  | 100  | 0.2025          | 0.9368   |
| 0.1384        | 0.14  | 200  | 0.2169          | 0.9382   |
| 0.0582        | 0.21  | 300  | 0.0932          | 0.9641   |
| 0.1129        | 0.28  | 400  | 0.1382          | 0.9555   |
| 0.0575        | 0.35  | 500  | 0.1204          | 0.9684   |
| 0.1027        | 0.42  | 600  | 0.0923          | 0.9684   |
| 0.0369        | 0.49  | 700  | 0.1114          | 0.9655   |
| 0.015         | 0.56  | 800  | 0.1745          | 0.9540   |
| 0.0455        | 0.63  | 900  | 0.0871          | 0.9655   |
| 0.0129        | 0.7   | 1000 | 0.1222          | 0.9626   |
| 0.0623        | 0.77  | 1100 | 0.0981          | 0.9670   |
| 0.0328        | 0.84  | 1200 | 0.0956          | 0.9655   |
| 0.0515        | 0.91  | 1300 | 0.0740          | 0.9756   |
| 0.0513        | 0.97  | 1400 | 0.0696          | 0.9756   |
| 0.0005        | 1.04  | 1500 | 0.0757          | 0.9784   |
| 0.0606        | 1.11  | 1600 | 0.0869          | 0.9784   |
| 0.0507        | 1.18  | 1700 | 0.1121          | 0.9698   |
| 0.0004        | 1.25  | 1800 | 0.0562          | 0.9813   |
| 0.0013        | 1.32  | 1900 | 0.0455          | 0.9828   |
| 0.0309        | 1.39  | 2000 | 0.0752          | 0.9799   |
| 0.0096        | 1.46  | 2100 | 0.0739          | 0.9770   |
| 0.001         | 1.53  | 2200 | 0.0536          | 0.9842   |
| 0.0892        | 1.6   | 2300 | 0.0728          | 0.9799   |
| 0.0568        | 1.67  | 2400 | 0.2331          | 0.9670   |
| 0.0049        | 1.74  | 2500 | 0.0924          | 0.9784   |
| 0.0003        | 1.81  | 2600 | 0.0922          | 0.9770   |
| 0.0004        | 1.88  | 2700 | 0.1383          | 0.9756   |
| 0.0001        | 1.95  | 2800 | 0.1568          | 0.9670   |
| 0.0001        | 2.02  | 2900 | 0.1299          | 0.9741   |
| 0.0002        | 2.09  | 3000 | 0.0976          | 0.9828   |
| 0.0           | 2.16  | 3100 | 0.0536          | 0.9885   |
| 0.004         | 2.23  | 3200 | 0.1074          | 0.9770   |
| 0.0001        | 2.3   | 3300 | 0.0702          | 0.9828   |
| 0.008         | 2.37  | 3400 | 0.1185          | 0.9756   |
| 0.0212        | 2.44  | 3500 | 0.0793          | 0.9756   |
| 0.0001        | 2.51  | 3600 | 0.1402          | 0.9698   |
| 0.0001        | 2.58  | 3700 | 0.0761          | 0.9828   |
| 0.0134        | 2.65  | 3800 | 0.1132          | 0.9741   |
| 0.0001        | 2.72  | 3900 | 0.0703          | 0.9828   |
| 0.0           | 2.79  | 4000 | 0.0764          | 0.9799   |
| 0.0           | 2.86  | 4100 | 0.0737          | 0.9828   |
| 0.0011        | 2.92  | 4200 | 0.1525          | 0.9727   |
| 0.019         | 2.99  | 4300 | 0.1078          | 0.9799   |
| 0.0           | 3.06  | 4400 | 0.0774          | 0.9828   |
| 0.0           | 3.13  | 4500 | 0.1081          | 0.9799   |
| 0.0           | 3.2   | 4600 | 0.0995          | 0.9828   |
| 0.0           | 3.27  | 4700 | 0.0861          | 0.9856   |
| 0.0           | 3.34  | 4800 | 0.0852          | 0.9856   |
| 0.0           | 3.41  | 4900 | 0.0834          | 0.9856   |
| 0.0           | 3.48  | 5000 | 0.0932          | 0.9828   |
| 0.0           | 3.55  | 5100 | 0.0837          | 0.9828   |
| 0.0           | 3.62  | 5200 | 0.0854          | 0.9813   |
| 0.0           | 3.69  | 5300 | 0.0850          | 0.9813   |
| 0.0           | 3.76  | 5400 | 0.0842          | 0.9813   |
| 0.0           | 3.83  | 5500 | 0.0911          | 0.9813   |
| 0.0           | 3.9   | 5600 | 0.0913          | 0.9813   |
| 0.0           | 3.97  | 5700 | 0.0907          | 0.9799   |


### Framework versions

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