---
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swinv2-tiny-patch4-window8-256-dmae-va-U5-42B
  results: []
---

<!-- 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. -->

# swinv2-tiny-patch4-window8-256-dmae-va-U5-42B

This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9637
- Accuracy: 0.6667

## 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: 4e-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: 42

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 0.9   | 7    | 7.8663          | 0.1167   |
| 6.936         | 1.94  | 15   | 7.7572          | 0.1167   |
| 6.936         | 2.97  | 23   | 7.1790          | 0.1167   |
| 6.7016        | 4.0   | 31   | 5.9033          | 0.1167   |
| 5.5439        | 4.9   | 38   | 4.6116          | 0.1167   |
| 5.5439        | 5.94  | 46   | 3.2830          | 0.1167   |
| 3.6477        | 6.97  | 54   | 2.2014          | 0.1167   |
| 2.2506        | 8.0   | 62   | 1.5647          | 0.45     |
| 2.2506        | 8.9   | 69   | 1.3160          | 0.45     |
| 1.5088        | 9.94  | 77   | 1.3676          | 0.3333   |
| 1.3868        | 10.97 | 85   | 1.3390          | 0.45     |
| 1.3868        | 12.0  | 93   | 1.3223          | 0.3833   |
| 1.351         | 12.9  | 100  | 1.3156          | 0.45     |
| 1.3271        | 13.94 | 108  | 1.3485          | 0.4833   |
| 1.3271        | 14.97 | 116  | 1.2646          | 0.4833   |
| 1.2322        | 16.0  | 124  | 1.2308          | 0.4833   |
| 1.2322        | 16.9  | 131  | 1.2160          | 0.5      |
| 1.22          | 17.94 | 139  | 1.2015          | 0.5      |
| 1.1899        | 18.97 | 147  | 1.2008          | 0.5      |
| 1.1899        | 20.0  | 155  | 1.1606          | 0.5      |
| 1.109         | 20.9  | 162  | 1.1182          | 0.5667   |
| 1.0603        | 21.94 | 170  | 1.0855          | 0.5333   |
| 1.0603        | 22.97 | 178  | 1.0763          | 0.5667   |
| 1.0264        | 24.0  | 186  | 1.1153          | 0.5833   |
| 1.0086        | 24.9  | 193  | 1.0770          | 0.65     |
| 1.0086        | 25.94 | 201  | 1.0041          | 0.6167   |
| 0.9301        | 26.97 | 209  | 0.9637          | 0.6667   |
| 0.9077        | 28.0  | 217  | 0.9824          | 0.5833   |
| 0.9077        | 28.9  | 224  | 0.9485          | 0.6      |
| 0.8725        | 29.94 | 232  | 0.9294          | 0.6167   |
| 0.8203        | 30.97 | 240  | 0.9348          | 0.6167   |
| 0.8203        | 32.0  | 248  | 0.9295          | 0.6      |
| 0.8211        | 32.9  | 255  | 0.9167          | 0.6      |
| 0.8211        | 33.94 | 263  | 0.9281          | 0.5833   |
| 0.7916        | 34.97 | 271  | 0.8803          | 0.6333   |
| 0.7822        | 36.0  | 279  | 0.8785          | 0.6333   |
| 0.7822        | 36.9  | 286  | 0.8906          | 0.6      |
| 0.7937        | 37.94 | 294  | 0.8899          | 0.6      |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0