---
library_name: transformers
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-papsmear
  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: 0.9044117647058824
---

<!-- 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-papsmear

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: 0.2027
- Accuracy: 0.9044

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 15

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| 1.4844        | 0.9935  | 38   | 1.4298          | 0.4118   |
| 0.8905        | 1.9869  | 76   | 0.8110          | 0.6544   |
| 0.9097        | 2.9804  | 114  | 0.7109          | 0.7132   |
| 0.6238        | 4.0     | 153  | 0.9197          | 0.6544   |
| 0.4456        | 4.9935  | 191  | 0.4652          | 0.8015   |
| 0.4394        | 5.9869  | 229  | 0.5188          | 0.8015   |
| 0.3156        | 6.9804  | 267  | 0.3447          | 0.8529   |
| 0.2212        | 8.0     | 306  | 0.3509          | 0.8382   |
| 0.2402        | 8.9935  | 344  | 0.3939          | 0.8235   |
| 0.1733        | 9.9869  | 382  | 0.2444          | 0.8897   |
| 0.1953        | 10.9804 | 420  | 0.2639          | 0.8676   |
| 0.1363        | 12.0    | 459  | 0.2645          | 0.8824   |
| 0.1234        | 12.9935 | 497  | 0.2027          | 0.9044   |
| 0.1282        | 13.9869 | 535  | 0.2027          | 0.9044   |
| 0.1036        | 14.9020 | 570  | 0.2026          | 0.8897   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1