---
license: apache-2.0
base_model: google/vit-base-patch32-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: n_rmsProp_VitB-p32-384-2e-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: 0.9597701149425287
---

<!-- 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. -->

# n_rmsProp_VitB-p32-384-2e-4-batch_16_epoch_4_classes_24

This model is a fine-tuned version of [google/vit-base-patch32-384](https://huggingface.co/google/vit-base-patch32-384) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1776
- Accuracy: 0.9598

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.8953        | 0.07  | 100  | 3.3433          | 0.1164   |
| 1.8876        | 0.14  | 200  | 2.0956          | 0.3333   |
| 0.7962        | 0.21  | 300  | 0.9204          | 0.7040   |
| 0.5319        | 0.28  | 400  | 0.5776          | 0.8118   |
| 0.3414        | 0.35  | 500  | 0.3952          | 0.8764   |
| 0.1779        | 0.42  | 600  | 0.2754          | 0.9109   |
| 0.2608        | 0.49  | 700  | 0.4758          | 0.8649   |
| 0.2218        | 0.56  | 800  | 0.2755          | 0.9152   |
| 0.1441        | 0.63  | 900  | 0.2786          | 0.9138   |
| 0.1809        | 0.7   | 1000 | 0.3369          | 0.8894   |
| 0.1212        | 0.77  | 1100 | 0.2293          | 0.9224   |
| 0.1966        | 0.84  | 1200 | 0.1879          | 0.9468   |
| 0.1587        | 0.91  | 1300 | 0.2081          | 0.9468   |
| 0.123         | 0.97  | 1400 | 0.2061          | 0.9368   |
| 0.1052        | 1.04  | 1500 | 0.2915          | 0.9181   |
| 0.0701        | 1.11  | 1600 | 0.3753          | 0.9109   |
| 0.0601        | 1.18  | 1700 | 0.2034          | 0.9382   |
| 0.0911        | 1.25  | 1800 | 0.1898          | 0.9382   |
| 0.022         | 1.32  | 1900 | 0.2885          | 0.9224   |
| 0.0805        | 1.39  | 2000 | 0.2636          | 0.9310   |
| 0.0024        | 1.46  | 2100 | 0.2271          | 0.9368   |
| 0.0056        | 1.53  | 2200 | 0.1677          | 0.9555   |
| 0.0789        | 1.6   | 2300 | 0.2369          | 0.9325   |
| 0.0935        | 1.67  | 2400 | 0.2417          | 0.9353   |
| 0.0499        | 1.74  | 2500 | 0.1791          | 0.9540   |
| 0.0375        | 1.81  | 2600 | 0.2283          | 0.9411   |
| 0.0166        | 1.88  | 2700 | 0.2564          | 0.9468   |
| 0.0166        | 1.95  | 2800 | 0.2737          | 0.9267   |
| 0.0033        | 2.02  | 2900 | 0.2508          | 0.9425   |
| 0.0144        | 2.09  | 3000 | 0.1975          | 0.9483   |
| 0.1054        | 2.16  | 3100 | 0.2073          | 0.9425   |
| 0.0004        | 2.23  | 3200 | 0.1479          | 0.9598   |
| 0.0288        | 2.3   | 3300 | 0.2287          | 0.9526   |
| 0.0066        | 2.37  | 3400 | 0.2602          | 0.9411   |
| 0.001         | 2.44  | 3500 | 0.2220          | 0.9468   |
| 0.0233        | 2.51  | 3600 | 0.2505          | 0.9382   |
| 0.0205        | 2.58  | 3700 | 0.1830          | 0.9583   |
| 0.0083        | 2.65  | 3800 | 0.2539          | 0.9368   |
| 0.0003        | 2.72  | 3900 | 0.2439          | 0.9440   |
| 0.0003        | 2.79  | 4000 | 0.2040          | 0.9555   |
| 0.019         | 2.86  | 4100 | 0.2246          | 0.9598   |
| 0.0069        | 2.92  | 4200 | 0.2520          | 0.9526   |
| 0.0003        | 2.99  | 4300 | 0.1937          | 0.9555   |
| 0.0001        | 3.06  | 4400 | 0.2040          | 0.9511   |
| 0.0004        | 3.13  | 4500 | 0.1777          | 0.9598   |
| 0.0005        | 3.2   | 4600 | 0.1956          | 0.9626   |
| 0.0001        | 3.27  | 4700 | 0.2120          | 0.9569   |
| 0.0001        | 3.34  | 4800 | 0.1936          | 0.9612   |
| 0.0001        | 3.41  | 4900 | 0.2002          | 0.9583   |
| 0.0002        | 3.48  | 5000 | 0.1795          | 0.9598   |
| 0.0001        | 3.55  | 5100 | 0.1548          | 0.9655   |
| 0.0006        | 3.62  | 5200 | 0.1931          | 0.9555   |
| 0.0001        | 3.69  | 5300 | 0.1846          | 0.9598   |
| 0.0           | 3.76  | 5400 | 0.2092          | 0.9526   |
| 0.0           | 3.83  | 5500 | 0.1927          | 0.9555   |
| 0.0           | 3.9   | 5600 | 0.1796          | 0.9555   |
| 0.0           | 3.97  | 5700 | 0.1776          | 0.9598   |


### Framework versions

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