---
license: apache-2.0
base_model: google/vit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Adam_ViTL-16_224-2e-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: 0.9683908045977011
---

<!-- 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. -->

# Adam_ViTL-16_224-2e-4-batch_16_epoch_4_classes_24

This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1211
- 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: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6934        | 0.07  | 100  | 0.4138          | 0.8477   |
| 0.4815        | 0.14  | 200  | 0.7227          | 0.8103   |
| 0.3952        | 0.21  | 300  | 0.5867          | 0.8491   |
| 0.6095        | 0.28  | 400  | 0.5975          | 0.8448   |
| 0.3448        | 0.35  | 500  | 0.4000          | 0.8721   |
| 0.2604        | 0.42  | 600  | 0.3335          | 0.9080   |
| 0.3734        | 0.49  | 700  | 0.4264          | 0.875    |
| 0.3074        | 0.56  | 800  | 0.3634          | 0.8908   |
| 0.312         | 0.63  | 900  | 0.4347          | 0.875    |
| 0.1076        | 0.7   | 1000 | 0.3203          | 0.9052   |
| 0.2001        | 0.77  | 1100 | 0.2668          | 0.9224   |
| 0.0507        | 0.84  | 1200 | 0.2265          | 0.9353   |
| 0.0767        | 0.91  | 1300 | 0.2797          | 0.9239   |
| 0.3201        | 0.97  | 1400 | 0.2977          | 0.9109   |
| 0.0293        | 1.04  | 1500 | 0.2849          | 0.9239   |
| 0.0353        | 1.11  | 1600 | 0.2918          | 0.9339   |
| 0.0787        | 1.18  | 1700 | 0.3012          | 0.9253   |
| 0.0749        | 1.25  | 1800 | 0.2383          | 0.9454   |
| 0.0233        | 1.32  | 1900 | 0.3272          | 0.9152   |
| 0.1635        | 1.39  | 2000 | 0.2857          | 0.9124   |
| 0.0586        | 1.46  | 2100 | 0.3785          | 0.9109   |
| 0.0103        | 1.53  | 2200 | 0.2032          | 0.9468   |
| 0.0082        | 1.6   | 2300 | 0.2091          | 0.9397   |
| 0.0695        | 1.67  | 2400 | 0.1739          | 0.9526   |
| 0.0253        | 1.74  | 2500 | 0.2056          | 0.9511   |
| 0.0648        | 1.81  | 2600 | 0.1803          | 0.9526   |
| 0.0286        | 1.88  | 2700 | 0.2018          | 0.9440   |
| 0.0057        | 1.95  | 2800 | 0.2332          | 0.9483   |
| 0.0056        | 2.02  | 2900 | 0.3459          | 0.9267   |
| 0.0111        | 2.09  | 3000 | 0.1954          | 0.9540   |
| 0.0001        | 2.16  | 3100 | 0.1586          | 0.9626   |
| 0.0059        | 2.23  | 3200 | 0.1716          | 0.9526   |
| 0.0063        | 2.3   | 3300 | 0.1548          | 0.9612   |
| 0.0003        | 2.37  | 3400 | 0.1813          | 0.9569   |
| 0.0006        | 2.44  | 3500 | 0.1339          | 0.9626   |
| 0.0004        | 2.51  | 3600 | 0.1492          | 0.9583   |
| 0.0004        | 2.58  | 3700 | 0.1238          | 0.9698   |
| 0.0001        | 2.65  | 3800 | 0.1156          | 0.9713   |
| 0.0001        | 2.72  | 3900 | 0.1272          | 0.9684   |
| 0.0           | 2.79  | 4000 | 0.1303          | 0.9698   |
| 0.0001        | 2.86  | 4100 | 0.1269          | 0.9684   |
| 0.0001        | 2.92  | 4200 | 0.1209          | 0.9684   |
| 0.0           | 2.99  | 4300 | 0.1211          | 0.9684   |


### Framework versions

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