---
license: apache-2.0
base_model: facebook/deit-base-distilled-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: deit-base-distilled-patch16-224-hasta-65-fold1
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6388888888888888
---

<!-- 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. -->

# deit-base-distilled-patch16-224-hasta-65-fold1

This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9265
- Accuracy: 0.6389

## 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: 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: 100

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log        | 0.5714  | 1    | 1.3178          | 0.2222   |
| No log        | 1.7143  | 3    | 1.4014          | 0.2778   |
| No log        | 2.8571  | 5    | 1.3535          | 0.2778   |
| No log        | 4.0     | 7    | 1.1299          | 0.3056   |
| No log        | 4.5714  | 8    | 1.0860          | 0.4722   |
| 1.0868        | 5.7143  | 10   | 1.1121          | 0.3333   |
| 1.0868        | 6.8571  | 12   | 1.0691          | 0.3611   |
| 1.0868        | 8.0     | 14   | 1.0270          | 0.5      |
| 1.0868        | 8.5714  | 15   | 1.0360          | 0.5      |
| 1.0868        | 9.7143  | 17   | 1.0385          | 0.3889   |
| 1.0868        | 10.8571 | 19   | 0.9951          | 0.4167   |
| 0.9487        | 12.0    | 21   | 1.0029          | 0.4444   |
| 0.9487        | 12.5714 | 22   | 1.0134          | 0.4722   |
| 0.9487        | 13.7143 | 24   | 0.9599          | 0.4444   |
| 0.9487        | 14.8571 | 26   | 0.9117          | 0.5278   |
| 0.9487        | 16.0    | 28   | 0.8856          | 0.5278   |
| 0.9487        | 16.5714 | 29   | 0.9275          | 0.4722   |
| 0.7942        | 17.7143 | 31   | 0.9041          | 0.5278   |
| 0.7942        | 18.8571 | 33   | 0.8999          | 0.4722   |
| 0.7942        | 20.0    | 35   | 0.8832          | 0.5833   |
| 0.7942        | 20.5714 | 36   | 0.8864          | 0.5556   |
| 0.7942        | 21.7143 | 38   | 0.8551          | 0.5      |
| 0.5911        | 22.8571 | 40   | 0.8242          | 0.6111   |
| 0.5911        | 24.0    | 42   | 0.9265          | 0.6389   |
| 0.5911        | 24.5714 | 43   | 0.8674          | 0.5833   |
| 0.5911        | 25.7143 | 45   | 0.7892          | 0.5556   |
| 0.5911        | 26.8571 | 47   | 0.8005          | 0.5833   |
| 0.5911        | 28.0    | 49   | 0.8302          | 0.5833   |
| 0.4865        | 28.5714 | 50   | 0.8893          | 0.6111   |
| 0.4865        | 29.7143 | 52   | 0.9043          | 0.6111   |
| 0.4865        | 30.8571 | 54   | 0.8433          | 0.5833   |
| 0.4865        | 32.0    | 56   | 0.8677          | 0.5833   |
| 0.4865        | 32.5714 | 57   | 0.9008          | 0.5833   |
| 0.4865        | 33.7143 | 59   | 0.9533          | 0.6111   |
| 0.4007        | 34.8571 | 61   | 0.9175          | 0.6111   |
| 0.4007        | 36.0    | 63   | 0.9090          | 0.5833   |
| 0.4007        | 36.5714 | 64   | 1.0004          | 0.5      |
| 0.4007        | 37.7143 | 66   | 1.0393          | 0.5      |
| 0.4007        | 38.8571 | 68   | 0.9196          | 0.5833   |
| 0.3691        | 40.0    | 70   | 0.9505          | 0.6389   |
| 0.3691        | 40.5714 | 71   | 0.9634          | 0.6389   |
| 0.3691        | 41.7143 | 73   | 0.9718          | 0.5278   |
| 0.3691        | 42.8571 | 75   | 0.9257          | 0.5278   |
| 0.3691        | 44.0    | 77   | 0.9020          | 0.5      |
| 0.3691        | 44.5714 | 78   | 0.9132          | 0.5556   |
| 0.3278        | 45.7143 | 80   | 1.0340          | 0.5556   |
| 0.3278        | 46.8571 | 82   | 1.0933          | 0.5833   |
| 0.3278        | 48.0    | 84   | 1.0231          | 0.5      |
| 0.3278        | 48.5714 | 85   | 0.9826          | 0.5278   |
| 0.3278        | 49.7143 | 87   | 0.9329          | 0.5278   |
| 0.3278        | 50.8571 | 89   | 0.9280          | 0.5278   |
| 0.2909        | 52.0    | 91   | 0.9312          | 0.5556   |
| 0.2909        | 52.5714 | 92   | 0.9359          | 0.5556   |
| 0.2909        | 53.7143 | 94   | 0.9495          | 0.5833   |
| 0.2909        | 54.8571 | 96   | 0.9607          | 0.5833   |
| 0.2909        | 56.0    | 98   | 0.9685          | 0.5833   |
| 0.2909        | 56.5714 | 99   | 0.9703          | 0.5833   |
| 0.2697        | 57.1429 | 100  | 0.9713          | 0.5833   |


### Framework versions

- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1