---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- shoe-classification
metrics:
- accuracy
model-index:
- name: shoes_model
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: shoe-classification
      type: shoe-classification
      config: full
      split: test
      args: full
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9156626506024096
---

<!-- 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. -->

# shoes_model

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 shoe-classification dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3307
- Accuracy: 0.9157

## 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: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.0767        | 1.0   | 18   | 0.8017          | 0.8434   |
| 0.7609        | 2.0   | 36   | 0.5786          | 0.8675   |
| 0.5705        | 3.0   | 54   | 0.4855          | 0.8554   |
| 0.4423        | 4.0   | 72   | 0.4495          | 0.8675   |
| 0.3604        | 5.0   | 90   | 0.3412          | 0.8916   |
| 0.3354        | 6.0   | 108  | 0.3307          | 0.9157   |


### Framework versions

- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3