Hugging Face's logo

hkivancoral
/
hushem_40x_deit_tiny_sgd_00001_fold4

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hushem_40x_deit_tiny_sgd_00001_fold4 / README.md
hkivancoral's picture
hkivancoral
End of training
7128f9a
preview code
|
raw
history blame contribute delete
4.87 kB
metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_40x_deit_tiny_sgd_00001_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: 0.14285714285714285

hushem_40x_deit_tiny_sgd_00001_fold4

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

  • Loss: 1.5700
  • Accuracy: 0.1429

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: 1e-05
  • 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
1.5195 1.0 219 1.6573 0.1429
1.4299 2.0 438 1.6538 0.1429
1.5002 3.0 657 1.6502 0.1429
1.4923 4.0 876 1.6467 0.1429
1.4507 5.0 1095 1.6433 0.1667
1.4843 6.0 1314 1.6398 0.1667
1.4439 7.0 1533 1.6365 0.1667
1.461 8.0 1752 1.6332 0.1667
1.4438 9.0 1971 1.6299 0.1667
1.421 10.0 2190 1.6268 0.1667
1.3797 11.0 2409 1.6238 0.1667
1.4481 12.0 2628 1.6208 0.1429
1.37 13.0 2847 1.6179 0.1429
1.4257 14.0 3066 1.6150 0.1429
1.3565 15.0 3285 1.6123 0.1429
1.3893 16.0 3504 1.6097 0.1429
1.4087 17.0 3723 1.6071 0.1429
1.3822 18.0 3942 1.6047 0.1429
1.3943 19.0 4161 1.6023 0.1429
1.4156 20.0 4380 1.6000 0.1429
1.397 21.0 4599 1.5977 0.1429
1.3921 22.0 4818 1.5956 0.1429
1.345 23.0 5037 1.5936 0.1429
1.3941 24.0 5256 1.5916 0.1429
1.3428 25.0 5475 1.5898 0.1429
1.3959 26.0 5694 1.5880 0.1429
1.3527 27.0 5913 1.5863 0.1429
1.3622 28.0 6132 1.5847 0.1429
1.3233 29.0 6351 1.5833 0.1429
1.3602 30.0 6570 1.5819 0.1429
1.3369 31.0 6789 1.5805 0.1429
1.3891 32.0 7008 1.5793 0.1429
1.3567 33.0 7227 1.5782 0.1429
1.3341 34.0 7446 1.5771 0.1429
1.3827 35.0 7665 1.5761 0.1429
1.3365 36.0 7884 1.5752 0.1429
1.3545 37.0 8103 1.5744 0.1429
1.3874 38.0 8322 1.5736 0.1429
1.3749 39.0 8541 1.5729 0.1429
1.3026 40.0 8760 1.5724 0.1429
1.3806 41.0 8979 1.5718 0.1429
1.3467 42.0 9198 1.5714 0.1429
1.3584 43.0 9417 1.5710 0.1429
1.3511 44.0 9636 1.5707 0.1429
1.3397 45.0 9855 1.5704 0.1429
1.35 46.0 10074 1.5703 0.1429
1.328 47.0 10293 1.5701 0.1429
1.3922 48.0 10512 1.5700 0.1429
1.3345 49.0 10731 1.5700 0.1429
1.3302 50.0 10950 1.5700 0.1429

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.1.1+cu121
  • Datasets 2.12.0
  • Tokenizers 0.13.2