---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- food101
metrics:
- accuracy
model-index:
- name: image_cls_vit-base-patch16-224-in21k_food101_finetune
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: food101
      type: food101
      config: default
      split: train[:5000]
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.838
---

<!-- 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. -->

# image_cls_vit-base-patch16-224-in21k_food101_finetune

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 food101 dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3653
- Accuracy: 0.838

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 3.5065        | 0.99  | 31   | 3.2552          | 0.779    |
| 2.67          | 1.98  | 62   | 2.5466          | 0.833    |
| 2.3665        | 2.98  | 93   | 2.3653          | 0.838    |


### Framework versions

- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3