---
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: 0.8386
- Accuracy: 0.65

## 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    | 6.1748          | 0.1167   |
| 5.327         | 1.94  | 15   | 6.0660          | 0.1167   |
| 5.327         | 2.97  | 23   | 5.4902          | 0.1167   |
| 5.0963        | 4.0   | 31   | 4.2768          | 0.1167   |
| 3.9193        | 4.9   | 38   | 3.0013          | 0.1167   |
| 3.9193        | 5.94  | 46   | 1.9289          | 0.1167   |
| 2.2222        | 6.97  | 54   | 1.3857          | 0.1167   |
| 1.4465        | 8.0   | 62   | 1.3423          | 0.4333   |
| 1.4465        | 8.9   | 69   | 1.2786          | 0.45     |
| 1.3709        | 9.94  | 77   | 1.2654          | 0.4667   |
| 1.3511        | 10.97 | 85   | 1.2605          | 0.4667   |
| 1.3511        | 12.0  | 93   | 1.2184          | 0.4667   |
| 1.2749        | 12.9  | 100  | 1.2894          | 0.5      |
| 1.222         | 13.94 | 108  | 1.2072          | 0.5167   |
| 1.222         | 14.97 | 116  | 1.1749          | 0.5167   |
| 1.1668        | 16.0  | 124  | 1.1988          | 0.5167   |
| 1.1668        | 16.9  | 131  | 1.2306          | 0.5167   |
| 1.101         | 17.94 | 139  | 1.1432          | 0.5333   |
| 1.029         | 18.97 | 147  | 1.0208          | 0.55     |
| 1.029         | 20.0  | 155  | 0.9577          | 0.6167   |
| 0.9403        | 20.9  | 162  | 0.9479          | 0.5      |
| 0.8887        | 21.94 | 170  | 0.8910          | 0.5833   |
| 0.8887        | 22.97 | 178  | 0.9442          | 0.5333   |
| 0.8506        | 24.0  | 186  | 0.8923          | 0.6      |
| 0.8064        | 24.9  | 193  | 0.8973          | 0.6      |
| 0.8064        | 25.94 | 201  | 0.9079          | 0.55     |
| 0.7434        | 26.97 | 209  | 0.8386          | 0.65     |
| 0.7404        | 28.0  | 217  | 0.8645          | 0.6167   |
| 0.7404        | 28.9  | 224  | 0.8599          | 0.5667   |
| 0.7215        | 29.94 | 232  | 0.8420          | 0.65     |
| 0.6743        | 30.97 | 240  | 0.8553          | 0.5667   |
| 0.6743        | 32.0  | 248  | 0.8355          | 0.6167   |
| 0.6767        | 32.9  | 255  | 0.8694          | 0.5833   |
| 0.6767        | 33.94 | 263  | 0.8559          | 0.65     |
| 0.6606        | 34.97 | 271  | 0.8351          | 0.6167   |
| 0.6488        | 36.0  | 279  | 0.8287          | 0.6333   |
| 0.6488        | 36.9  | 286  | 0.8377          | 0.6167   |
| 0.6544        | 37.94 | 294  | 0.8406          | 0.6      |


### Framework versions

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