---
license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224-in22k
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: swin-base-patch4-window7-224-in22k-Kontur-competition-1.3K
  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. -->

# swin-base-patch4-window7-224-in22k-Kontur-competition-1.3K

This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0104

## 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: 48
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 192
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 0.96  | 6    | 0.4819          |
| 0.5639        | 1.92  | 12   | 0.2242          |
| 0.5639        | 2.88  | 18   | 0.0641          |
| 0.1359        | 4.0   | 25   | 0.0782          |
| 0.031         | 4.96  | 31   | 0.0250          |
| 0.031         | 5.92  | 37   | 0.0173          |
| 0.0221        | 6.88  | 43   | 0.0119          |
| 0.0144        | 8.0   | 50   | 0.0163          |
| 0.0144        | 8.96  | 56   | 0.0104          |
| 0.0144        | 9.6   | 60   | 0.0115          |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2