---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: attraction-classifier
  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: 0.7955974842767296
---

<!-- 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. -->

# attraction-classifier

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: 0.4691
- Accuracy: 0.7956

## 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: 69
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.15
- num_epochs: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6703        | 0.34  | 15   | 0.6354          | 0.7327   |
| 0.5449        | 0.67  | 30   | 0.5836          | 0.7421   |
| 0.5407        | 1.01  | 45   | 0.5594          | 0.7421   |
| 0.5255        | 1.34  | 60   | 0.5294          | 0.7547   |
| 0.5586        | 1.68  | 75   | 0.5171          | 0.7642   |
| 0.5438        | 2.01  | 90   | 0.5212          | 0.7704   |
| 0.4807        | 2.35  | 105  | 0.5181          | 0.7390   |
| 0.6202        | 2.68  | 120  | 0.4972          | 0.7704   |
| 0.5021        | 3.02  | 135  | 0.4566          | 0.7987   |
| 0.4313        | 3.35  | 150  | 0.4852          | 0.7925   |
| 0.3532        | 3.69  | 165  | 0.4378          | 0.8113   |
| 0.3577        | 4.02  | 180  | 0.4515          | 0.8019   |
| 0.4736        | 4.36  | 195  | 0.4498          | 0.7893   |
| 0.3516        | 4.69  | 210  | 0.4408          | 0.8239   |
| 0.4437        | 5.03  | 225  | 0.4611          | 0.7799   |
| 0.3543        | 5.36  | 240  | 0.4294          | 0.8208   |
| 0.4029        | 5.7   | 255  | 0.4155          | 0.8428   |
| 0.3808        | 6.03  | 270  | 0.4116          | 0.8302   |
| 0.3211        | 6.37  | 285  | 0.4009          | 0.8302   |
| 0.2949        | 6.7   | 300  | 0.4321          | 0.8176   |
| 0.2663        | 7.04  | 315  | 0.4229          | 0.8396   |
| 0.3049        | 7.37  | 330  | 0.4110          | 0.8365   |
| 0.1303        | 7.71  | 345  | 0.4288          | 0.8333   |
| 0.2079        | 8.04  | 360  | 0.4218          | 0.8208   |
| 0.208         | 8.38  | 375  | 0.3908          | 0.8365   |
| 0.2067        | 8.72  | 390  | 0.5191          | 0.7862   |
| 0.1635        | 9.05  | 405  | 0.4691          | 0.7956   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0