Hugging Face's logo

hkivancoral
/
hushem_40x_deit_base_sgd_001_fold3

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Model card Files Community
1
hushem_40x_deit_base_sgd_001_fold3 / README.md
hkivancoral's picture
hkivancoral
End of training
630a707
preview code
|
raw
history blame contribute delete
4.87 kB
metadata
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_40x_deit_base_sgd_001_fold3
    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: 0.7674418604651163

hushem_40x_deit_base_sgd_001_fold3

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4834
  • Accuracy: 0.7674

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
1.2567 1.0 217 1.3908 0.3023
1.1156 2.0 434 1.3183 0.4186
0.9891 3.0 651 1.2352 0.5116
0.902 4.0 868 1.1401 0.5814
0.7383 5.0 1085 1.0533 0.6047
0.6659 6.0 1302 0.9783 0.6279
0.577 7.0 1519 0.9088 0.6047
0.5084 8.0 1736 0.8504 0.6512
0.4618 9.0 1953 0.8112 0.6512
0.3986 10.0 2170 0.7644 0.6744
0.3262 11.0 2387 0.7405 0.6744
0.3187 12.0 2604 0.7073 0.7442
0.287 13.0 2821 0.6756 0.7442
0.2667 14.0 3038 0.6524 0.7674
0.2566 15.0 3255 0.6373 0.7674
0.2206 16.0 3472 0.6121 0.7674
0.1851 17.0 3689 0.6018 0.7674
0.1802 18.0 3906 0.5901 0.7674
0.1691 19.0 4123 0.5735 0.7674
0.1555 20.0 4340 0.5642 0.7674
0.1532 21.0 4557 0.5647 0.7907
0.1287 22.0 4774 0.5473 0.7907
0.1172 23.0 4991 0.5337 0.7907
0.1215 24.0 5208 0.5344 0.7907
0.1 25.0 5425 0.5177 0.7907
0.1218 26.0 5642 0.5181 0.7907
0.0935 27.0 5859 0.5065 0.7907
0.0833 28.0 6076 0.4985 0.7907
0.0714 29.0 6293 0.4998 0.7907
0.0825 30.0 6510 0.4944 0.7907
0.0754 31.0 6727 0.4956 0.7674
0.0765 32.0 6944 0.4881 0.7674
0.0774 33.0 7161 0.4958 0.7674
0.057 34.0 7378 0.4894 0.7674
0.0663 35.0 7595 0.4882 0.7674
0.059 36.0 7812 0.4848 0.7674
0.0537 37.0 8029 0.4865 0.7674
0.0454 38.0 8246 0.4882 0.7674
0.0514 39.0 8463 0.4854 0.7674
0.0629 40.0 8680 0.4861 0.7674
0.0453 41.0 8897 0.4865 0.7674
0.0447 42.0 9114 0.4837 0.7674
0.0452 43.0 9331 0.4805 0.7907
0.0545 44.0 9548 0.4818 0.7907
0.0444 45.0 9765 0.4816 0.7907
0.0454 46.0 9982 0.4835 0.7674
0.0369 47.0 10199 0.4841 0.7674
0.0401 48.0 10416 0.4827 0.7907
0.0524 49.0 10633 0.4835 0.7674
0.0394 50.0 10850 0.4834 0.7674

Framework versions

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