---
base_model: MBZUAI/swiftformer-xs
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swiftformer-xs-DMAE
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.45652173913043476
---

<!-- 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. -->

# swiftformer-xs-DMAE

This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1969
- Accuracy: 0.4565

## 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: 0.05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 40

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 0.86  | 3    | 34874.7891      | 0.1087   |
| No log        | 2.0   | 7    | 415543488.0     | 0.4565   |
| 107.6051      | 2.86  | 10   | 14879.4717      | 0.1087   |
| 107.6051      | 4.0   | 14   | 68935.1875      | 0.1087   |
| 107.6051      | 4.86  | 17   | 7599.6079       | 0.1087   |
| 61.6907       | 6.0   | 21   | 1392.9758       | 0.1304   |
| 61.6907       | 6.86  | 24   | 524.5536        | 0.1739   |
| 61.6907       | 8.0   | 28   | 367.8024        | 0.1087   |
| 9.2329        | 8.86  | 31   | 27.2661         | 0.4565   |
| 9.2329        | 10.0  | 35   | 14.2920         | 0.1087   |
| 9.2329        | 10.86 | 38   | 2.9737          | 0.3261   |
| 4.2143        | 12.0  | 42   | 114.2135        | 0.3261   |
| 4.2143        | 12.86 | 45   | 1.6271          | 0.3261   |
| 4.2143        | 14.0  | 49   | 7.7918          | 0.4348   |
| 1.8981        | 14.86 | 52   | 3.3329          | 0.3261   |
| 1.8981        | 16.0  | 56   | 2.0198          | 0.3261   |
| 1.8981        | 16.86 | 59   | 1.4194          | 0.3261   |
| 1.5139        | 18.0  | 63   | 1.3169          | 0.4565   |
| 1.5139        | 18.86 | 66   | 1.8718          | 0.3261   |
| 1.7219        | 20.0  | 70   | 2.1572          | 0.1087   |
| 1.7219        | 20.86 | 73   | 2.1683          | 0.3043   |
| 1.7219        | 22.0  | 77   | 1.6241          | 0.4565   |
| 1.5029        | 22.86 | 80   | 2.1474          | 0.4565   |
| 1.5029        | 24.0  | 84   | 1.5354          | 0.4348   |
| 1.5029        | 24.86 | 87   | 1.2864          | 0.4565   |
| 1.3532        | 26.0  | 91   | 1.3014          | 0.3261   |
| 1.3532        | 26.86 | 94   | 1.2604          | 0.4565   |
| 1.3532        | 28.0  | 98   | 1.3335          | 0.3043   |
| 1.2957        | 28.86 | 101  | 1.2444          | 0.4565   |
| 1.2957        | 30.0  | 105  | 1.2858          | 0.3261   |
| 1.2957        | 30.86 | 108  | 1.2190          | 0.4783   |
| 1.2547        | 32.0  | 112  | 1.2271          | 0.4565   |
| 1.2547        | 32.86 | 115  | 1.2194          | 0.4565   |
| 1.2547        | 34.0  | 119  | 1.1941          | 0.4565   |
| 1.2042        | 34.29 | 120  | 1.1969          | 0.4565   |


### Framework versions

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