---
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_3x_deit_small_sgd_001_fold4
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: test
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.87
---

<!-- 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. -->

# smids_3x_deit_small_sgd_001_fold4

This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3235
- Accuracy: 0.87

## 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: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.834         | 1.0   | 225   | 0.8192          | 0.67     |
| 0.6262        | 2.0   | 450   | 0.6329          | 0.755    |
| 0.5137        | 3.0   | 675   | 0.5393          | 0.8      |
| 0.4726        | 4.0   | 900   | 0.4881          | 0.8117   |
| 0.4753        | 5.0   | 1125  | 0.4529          | 0.825    |
| 0.3563        | 6.0   | 1350  | 0.4306          | 0.8367   |
| 0.4027        | 7.0   | 1575  | 0.4125          | 0.8317   |
| 0.4582        | 8.0   | 1800  | 0.4008          | 0.8433   |
| 0.378         | 9.0   | 2025  | 0.3888          | 0.8417   |
| 0.3387        | 10.0  | 2250  | 0.3828          | 0.84     |
| 0.366         | 11.0  | 2475  | 0.3744          | 0.8433   |
| 0.3618        | 12.0  | 2700  | 0.3690          | 0.845    |
| 0.2883        | 13.0  | 2925  | 0.3626          | 0.845    |
| 0.2516        | 14.0  | 3150  | 0.3569          | 0.8533   |
| 0.2729        | 15.0  | 3375  | 0.3543          | 0.8517   |
| 0.2661        | 16.0  | 3600  | 0.3505          | 0.8567   |
| 0.2566        | 17.0  | 3825  | 0.3484          | 0.8567   |
| 0.2958        | 18.0  | 4050  | 0.3449          | 0.86     |
| 0.2763        | 19.0  | 4275  | 0.3442          | 0.86     |
| 0.2103        | 20.0  | 4500  | 0.3404          | 0.8633   |
| 0.2473        | 21.0  | 4725  | 0.3384          | 0.8633   |
| 0.246         | 22.0  | 4950  | 0.3367          | 0.865    |
| 0.2436        | 23.0  | 5175  | 0.3379          | 0.8617   |
| 0.2089        | 24.0  | 5400  | 0.3339          | 0.8667   |
| 0.2559        | 25.0  | 5625  | 0.3325          | 0.8667   |
| 0.2143        | 26.0  | 5850  | 0.3311          | 0.8667   |
| 0.2194        | 27.0  | 6075  | 0.3314          | 0.8667   |
| 0.2076        | 28.0  | 6300  | 0.3304          | 0.865    |
| 0.1951        | 29.0  | 6525  | 0.3306          | 0.8633   |
| 0.2173        | 30.0  | 6750  | 0.3289          | 0.87     |
| 0.2138        | 31.0  | 6975  | 0.3276          | 0.8667   |
| 0.1666        | 32.0  | 7200  | 0.3279          | 0.8683   |
| 0.2362        | 33.0  | 7425  | 0.3284          | 0.8667   |
| 0.2048        | 34.0  | 7650  | 0.3267          | 0.8683   |
| 0.1835        | 35.0  | 7875  | 0.3262          | 0.8717   |
| 0.2278        | 36.0  | 8100  | 0.3250          | 0.8683   |
| 0.2162        | 37.0  | 8325  | 0.3259          | 0.8683   |
| 0.2267        | 38.0  | 8550  | 0.3242          | 0.8717   |
| 0.2006        | 39.0  | 8775  | 0.3241          | 0.8683   |
| 0.2205        | 40.0  | 9000  | 0.3240          | 0.87     |
| 0.1797        | 41.0  | 9225  | 0.3251          | 0.8683   |
| 0.1988        | 42.0  | 9450  | 0.3237          | 0.87     |
| 0.2045        | 43.0  | 9675  | 0.3237          | 0.8717   |
| 0.2456        | 44.0  | 9900  | 0.3239          | 0.87     |
| 0.1971        | 45.0  | 10125 | 0.3237          | 0.87     |
| 0.2036        | 46.0  | 10350 | 0.3240          | 0.8683   |
| 0.1749        | 47.0  | 10575 | 0.3238          | 0.8683   |
| 0.1994        | 48.0  | 10800 | 0.3236          | 0.87     |
| 0.2429        | 49.0  | 11025 | 0.3236          | 0.87     |
| 0.2034        | 50.0  | 11250 | 0.3235          | 0.87     |


### Framework versions

- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2