---
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
model-index:
- name: beit-base-patch16-224
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8966666666666666
    - name: Precision
      type: precision
      value: 0.891224605606628
    - name: Recall
      type: recall
      value: 0.8966666666666666
---

<!-- 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. -->

# beit-base-patch16-224

This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2426
- Accuracy: 0.8967
- Precision: 0.8912
- Recall: 0.8967
- F1 Score: 0.8935

## 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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
| No log        | 1.0   | 4    | 0.4160          | 0.8667   | 0.8037    | 0.8667 | 0.8160   |
| No log        | 2.0   | 8    | 0.4441          | 0.8375   | 0.7702    | 0.8375 | 0.7998   |
| No log        | 3.0   | 12   | 0.4451          | 0.8667   | 0.8559    | 0.8667 | 0.8605   |
| 0.4959        | 4.0   | 16   | 0.3299          | 0.8792   | 0.8545    | 0.8792 | 0.8551   |
| 0.4959        | 5.0   | 20   | 0.3813          | 0.8458   | 0.8776    | 0.8458 | 0.8580   |
| 0.4959        | 6.0   | 24   | 0.2802          | 0.8958   | 0.8851    | 0.8958 | 0.8881   |
| 0.4959        | 7.0   | 28   | 0.2991          | 0.8875   | 0.8830    | 0.8875 | 0.8850   |
| 0.3696        | 8.0   | 32   | 0.2565          | 0.8917   | 0.8792    | 0.8917 | 0.8825   |
| 0.3696        | 9.0   | 36   | 0.2582          | 0.9      | 0.8949    | 0.9    | 0.8970   |
| 0.3696        | 10.0  | 40   | 0.2472          | 0.9      | 0.8927    | 0.9    | 0.8954   |
| 0.3696        | 11.0  | 44   | 0.2463          | 0.9208   | 0.9179    | 0.9208 | 0.9191   |
| 0.3299        | 12.0  | 48   | 0.2474          | 0.9167   | 0.9145    | 0.9167 | 0.9155   |
| 0.3299        | 13.0  | 52   | 0.2826          | 0.8833   | 0.8971    | 0.8833 | 0.8889   |
| 0.3299        | 14.0  | 56   | 0.2720          | 0.8958   | 0.9035    | 0.8958 | 0.8991   |
| 0.3036        | 15.0  | 60   | 0.2629          | 0.9      | 0.9059    | 0.9    | 0.9025   |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3