Hugging Face's logo

hkivancoral
/
smids_5x_deit_tiny_sgd_001_fold1

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
smids_5x_deit_tiny_sgd_001_fold1 / README.md
hkivancoral's picture
hkivancoral
End of training
9873806
preview code
|
raw history blame
No virus
4.86 kB
metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_tiny_sgd_001_fold1
    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: 0.8714524207011686

smids_5x_deit_tiny_sgd_001_fold1

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: 0.3293
  • Accuracy: 0.8715

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
0.7747 1.0 376 0.8081 0.6327
0.5327 2.0 752 0.5949 0.7462
0.4332 3.0 1128 0.5030 0.7846
0.4359 4.0 1504 0.4457 0.8097
0.3937 5.0 1880 0.4107 0.8164
0.3325 6.0 2256 0.3873 0.8297
0.2877 7.0 2632 0.3645 0.8347
0.2962 8.0 3008 0.3585 0.8397
0.3002 9.0 3384 0.3450 0.8414
0.2749 10.0 3760 0.3357 0.8514
0.2826 11.0 4136 0.3303 0.8614
0.2607 12.0 4512 0.3246 0.8664
0.2479 13.0 4888 0.3195 0.8731
0.209 14.0 5264 0.3192 0.8698
0.2492 15.0 5640 0.3190 0.8631
0.2421 16.0 6016 0.3201 0.8664
0.2313 17.0 6392 0.3123 0.8731
0.2635 18.0 6768 0.3189 0.8715
0.22 19.0 7144 0.3169 0.8698
0.1933 20.0 7520 0.3154 0.8715
0.1972 21.0 7896 0.3125 0.8748
0.2184 22.0 8272 0.3238 0.8681
0.2395 23.0 8648 0.3208 0.8715
0.2148 24.0 9024 0.3152 0.8681
0.2046 25.0 9400 0.3215 0.8698
0.2137 26.0 9776 0.3154 0.8681
0.1523 27.0 10152 0.3167 0.8731
0.1766 28.0 10528 0.3160 0.8715
0.1896 29.0 10904 0.3190 0.8715
0.157 30.0 11280 0.3195 0.8698
0.1522 31.0 11656 0.3183 0.8731
0.1888 32.0 12032 0.3211 0.8715
0.1615 33.0 12408 0.3233 0.8681
0.1503 34.0 12784 0.3209 0.8731
0.1481 35.0 13160 0.3244 0.8698
0.1788 36.0 13536 0.3242 0.8681
0.1497 37.0 13912 0.3239 0.8748
0.1343 38.0 14288 0.3226 0.8748
0.1659 39.0 14664 0.3268 0.8748
0.1781 40.0 15040 0.3250 0.8698
0.1644 41.0 15416 0.3283 0.8731
0.1354 42.0 15792 0.3269 0.8731
0.1533 43.0 16168 0.3272 0.8731
0.1541 44.0 16544 0.3272 0.8748
0.2043 45.0 16920 0.3294 0.8731
0.2146 46.0 17296 0.3299 0.8731
0.154 47.0 17672 0.3285 0.8715
0.1593 48.0 18048 0.3296 0.8731
0.1388 49.0 18424 0.3295 0.8731
0.1123 50.0 18800 0.3293 0.8715

Framework versions

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