---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-new_dataset_50e
  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: 0.7837837837837838
---

<!-- 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. -->

# swin-tiny-patch4-window7-224-finetuned-new_dataset_50e

This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co./microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7626
- Accuracy: 0.7838

## 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: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 0.94  | 4    | 0.5406          | 0.7568   |
| No log        | 1.94  | 8    | 0.5781          | 0.7297   |
| 0.369         | 2.94  | 12   | 0.5188          | 0.7568   |
| 0.369         | 3.94  | 16   | 0.4889          | 0.7703   |
| 0.3889        | 4.94  | 20   | 0.4707          | 0.7703   |
| 0.3889        | 5.94  | 24   | 0.4914          | 0.7703   |
| 0.3889        | 6.94  | 28   | 0.6717          | 0.7432   |
| 0.3537        | 7.94  | 32   | 0.6126          | 0.7973   |
| 0.3537        | 8.94  | 36   | 0.5298          | 0.7568   |
| 0.3356        | 9.94  | 40   | 0.5882          | 0.7432   |
| 0.3356        | 10.94 | 44   | 0.5746          | 0.7432   |
| 0.3356        | 11.94 | 48   | 0.6622          | 0.7297   |
| 0.3231        | 12.94 | 52   | 0.5718          | 0.7703   |
| 0.3231        | 13.94 | 56   | 0.7128          | 0.7297   |
| 0.3732        | 14.94 | 60   | 0.5254          | 0.7838   |
| 0.3732        | 15.94 | 64   | 0.7287          | 0.7162   |
| 0.3732        | 16.94 | 68   | 0.5491          | 0.7568   |
| 0.3704        | 17.94 | 72   | 0.6270          | 0.8108   |
| 0.3704        | 18.94 | 76   | 0.5768          | 0.7973   |
| 0.3005        | 19.94 | 80   | 0.5718          | 0.7568   |
| 0.3005        | 20.94 | 84   | 0.6060          | 0.7838   |
| 0.3005        | 21.94 | 88   | 0.6006          | 0.7568   |
| 0.2739        | 22.94 | 92   | 0.5254          | 0.7703   |
| 0.2739        | 23.94 | 96   | 0.6768          | 0.7297   |
| 0.2627        | 24.94 | 100  | 0.6552          | 0.7838   |
| 0.2627        | 25.94 | 104  | 0.6359          | 0.7568   |
| 0.2627        | 26.94 | 108  | 0.6695          | 0.7568   |
| 0.2573        | 27.94 | 112  | 0.6321          | 0.7838   |
| 0.2573        | 28.94 | 116  | 0.6559          | 0.7973   |
| 0.2336        | 29.94 | 120  | 0.7345          | 0.7838   |
| 0.2336        | 30.94 | 124  | 0.6289          | 0.7703   |
| 0.2336        | 31.94 | 128  | 0.8608          | 0.6892   |
| 0.2126        | 32.94 | 132  | 0.8152          | 0.7838   |
| 0.2126        | 33.94 | 136  | 0.9124          | 0.7162   |
| 0.2           | 34.94 | 140  | 0.7841          | 0.7703   |
| 0.2           | 35.94 | 144  | 0.7741          | 0.7838   |
| 0.2           | 36.94 | 148  | 0.7580          | 0.7973   |
| 0.1858        | 37.94 | 152  | 0.7781          | 0.7973   |
| 0.1858        | 38.94 | 156  | 0.7539          | 0.7568   |
| 0.1806        | 39.94 | 160  | 0.7460          | 0.7703   |
| 0.1806        | 40.94 | 164  | 0.7814          | 0.7703   |
| 0.1806        | 41.94 | 168  | 0.7745          | 0.7973   |
| 0.1771        | 42.94 | 172  | 0.7551          | 0.7838   |
| 0.1771        | 43.94 | 176  | 0.7821          | 0.7838   |
| 0.1649        | 44.94 | 180  | 0.7822          | 0.7703   |
| 0.1649        | 45.94 | 184  | 0.7580          | 0.7838   |
| 0.1649        | 46.94 | 188  | 0.7376          | 0.7703   |
| 0.1711        | 47.94 | 192  | 0.7495          | 0.7703   |
| 0.1711        | 48.94 | 196  | 0.7561          | 0.7703   |
| 0.1579        | 49.94 | 200  | 0.7626          | 0.7838   |


### Framework versions

- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2