---
base_model: MBZUAI/swiftformer-xs
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
model-index:
- name: swiftformer-xs
  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: 0.84
    - name: Precision
      type: precision
      value: 0.8326758071649712
    - name: Recall
      type: recall
      value: 0.84
---

<!-- 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

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: 0.4927
- Accuracy: 0.84
- Precision: 0.8327
- Recall: 0.84
- F1 Score: 0.8362

## 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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 | Precision | Recall | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
| No log        | 1.0   | 4    | 0.7316          | 0.4208   | 0.8091    | 0.4208 | 0.4926   |
| No log        | 2.0   | 8    | 0.6456          | 0.675    | 0.8159    | 0.675  | 0.7248   |
| No log        | 3.0   | 12   | 0.5771          | 0.7917   | 0.8229    | 0.7917 | 0.8055   |
| 0.7138        | 4.0   | 16   | 0.4992          | 0.8333   | 0.8287    | 0.8333 | 0.8310   |
| 0.7138        | 5.0   | 20   | 0.4925          | 0.8292   | 0.8406    | 0.8292 | 0.8345   |
| 0.7138        | 6.0   | 24   | 0.4964          | 0.825    | 0.8435    | 0.825  | 0.8333   |
| 0.7138        | 7.0   | 28   | 0.4998          | 0.825    | 0.8435    | 0.825  | 0.8333   |
| 0.6892        | 8.0   | 32   | 0.4999          | 0.825    | 0.8481    | 0.825  | 0.8350   |
| 0.6892        | 9.0   | 36   | 0.5067          | 0.8167   | 0.8498    | 0.8167 | 0.8304   |
| 0.6892        | 10.0  | 40   | 0.5162          | 0.8125   | 0.8484    | 0.8125 | 0.8273   |
| 0.6892        | 11.0  | 44   | 0.5315          | 0.7792   | 0.8389    | 0.7792 | 0.8026   |
| 0.6782        | 12.0  | 48   | 0.5287          | 0.7875   | 0.8411    | 0.7875 | 0.8088   |
| 0.6782        | 13.0  | 52   | 0.5404          | 0.7708   | 0.8367    | 0.7708 | 0.7965   |
| 0.6782        | 14.0  | 56   | 0.5656          | 0.7667   | 0.8457    | 0.7667 | 0.7957   |
| 0.6742        | 15.0  | 60   | 0.5479          | 0.775    | 0.8427    | 0.775  | 0.8008   |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3