---
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: 0.7933333333333333
    - name: Precision
      type: precision
      value: 0.7853286177424108
    - name: Recall
      type: recall
      value: 0.7933333333333333
---

<!-- 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: 0.8531
- Accuracy: 0.7933
- Precision: 0.7853
- Recall: 0.7933
- F1 Score: 0.7662

## 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    | 0.5815          | 0.7292   | 0.6273    | 0.7292 | 0.6259   |
| No log        | 2.0   | 8    | 0.5493          | 0.7333   | 0.6901    | 0.7333 | 0.6863   |
| No log        | 3.0   | 12   | 0.5545          | 0.7667   | 0.7575    | 0.7667 | 0.7147   |
| 0.5698        | 4.0   | 16   | 0.5706          | 0.7667   | 0.7503    | 0.7667 | 0.7221   |
| 0.5698        | 5.0   | 20   | 0.5800          | 0.7667   | 0.7575    | 0.7667 | 0.7147   |
| 0.5698        | 6.0   | 24   | 0.5929          | 0.7833   | 0.7772    | 0.7833 | 0.7451   |
| 0.5698        | 7.0   | 28   | 0.5783          | 0.7833   | 0.7677    | 0.7833 | 0.7672   |
| 0.2938        | 8.0   | 32   | 0.5665          | 0.7875   | 0.7793    | 0.7875 | 0.7821   |
| 0.2938        | 9.0   | 36   | 0.7751          | 0.7875   | 0.7770    | 0.7875 | 0.7571   |
| 0.2938        | 10.0  | 40   | 0.7088          | 0.7917   | 0.7816    | 0.7917 | 0.7843   |
| 0.2938        | 11.0  | 44   | 0.8799          | 0.8042   | 0.7972    | 0.8042 | 0.7808   |
| 0.0834        | 12.0  | 48   | 0.8367          | 0.7875   | 0.7793    | 0.7875 | 0.7821   |
| 0.0834        | 13.0  | 52   | 0.9200          | 0.7958   | 0.7834    | 0.7958 | 0.7758   |
| 0.0834        | 14.0  | 56   | 0.8821          | 0.8      | 0.7879    | 0.8    | 0.7869   |
| 0.0358        | 15.0  | 60   | 0.8674          | 0.7875   | 0.7753    | 0.7875 | 0.7777   |


### Framework versions

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