smids_3x_deit_small_rms_00001_fold5
This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9898
- Accuracy: 0.8933
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 |
|---|---|---|---|---|
| 0.2981 | 1.0 | 225 | 0.3128 | 0.8667 |
| 0.1441 | 2.0 | 450 | 0.2643 | 0.895 |
| 0.112 | 3.0 | 675 | 0.3212 | 0.8817 |
| 0.0406 | 4.0 | 900 | 0.3851 | 0.8983 |
| 0.0366 | 5.0 | 1125 | 0.4872 | 0.8767 |
| 0.0159 | 6.0 | 1350 | 0.5831 | 0.8817 |
| 0.0669 | 7.0 | 1575 | 0.5966 | 0.8833 |
| 0.0217 | 8.0 | 1800 | 0.7066 | 0.89 |
| 0.0482 | 9.0 | 2025 | 0.7260 | 0.8917 |
| 0.003 | 10.0 | 2250 | 0.6702 | 0.9017 |
| 0.0029 | 11.0 | 2475 | 0.6212 | 0.9133 |
| 0.0459 | 12.0 | 2700 | 0.7442 | 0.8967 |
| 0.0005 | 13.0 | 2925 | 0.7171 | 0.9 |
| 0.0 | 14.0 | 3150 | 0.7165 | 0.905 |
| 0.0001 | 15.0 | 3375 | 0.7191 | 0.9017 |
| 0.0236 | 16.0 | 3600 | 0.6965 | 0.8967 |
| 0.0 | 17.0 | 3825 | 0.7247 | 0.9 |
| 0.0002 | 18.0 | 4050 | 0.8019 | 0.89 |
| 0.0206 | 19.0 | 4275 | 0.7794 | 0.9 |
| 0.0023 | 20.0 | 4500 | 0.7187 | 0.9017 |
| 0.0 | 21.0 | 4725 | 0.8080 | 0.9017 |
| 0.0033 | 22.0 | 4950 | 0.9120 | 0.885 |
| 0.0 | 23.0 | 5175 | 0.9403 | 0.88 |
| 0.0076 | 24.0 | 5400 | 0.8853 | 0.8917 |
| 0.0 | 25.0 | 5625 | 0.8438 | 0.8983 |
| 0.0 | 26.0 | 5850 | 0.8326 | 0.8983 |
| 0.0 | 27.0 | 6075 | 0.9235 | 0.8867 |
| 0.0023 | 28.0 | 6300 | 0.8353 | 0.9 |
| 0.0039 | 29.0 | 6525 | 0.9907 | 0.8883 |
| 0.0 | 30.0 | 6750 | 0.9749 | 0.885 |
| 0.0 | 31.0 | 6975 | 0.9599 | 0.8917 |
| 0.0 | 32.0 | 7200 | 0.9273 | 0.8883 |
| 0.0038 | 33.0 | 7425 | 0.9025 | 0.9 |
| 0.0 | 34.0 | 7650 | 0.9166 | 0.9 |
| 0.0036 | 35.0 | 7875 | 0.9319 | 0.9017 |
| 0.0 | 36.0 | 8100 | 0.9400 | 0.89 |
| 0.0042 | 37.0 | 8325 | 0.9533 | 0.895 |
| 0.0 | 38.0 | 8550 | 0.9627 | 0.8883 |
| 0.0 | 39.0 | 8775 | 0.9661 | 0.8967 |
| 0.0 | 40.0 | 9000 | 0.9682 | 0.89 |
| 0.0 | 41.0 | 9225 | 0.9782 | 0.89 |
| 0.0 | 42.0 | 9450 | 0.9830 | 0.89 |
| 0.0028 | 43.0 | 9675 | 0.9854 | 0.8917 |
| 0.0 | 44.0 | 9900 | 0.9812 | 0.8917 |
| 0.0 | 45.0 | 10125 | 0.9848 | 0.8917 |
| 0.0 | 46.0 | 10350 | 0.9870 | 0.895 |
| 0.0 | 47.0 | 10575 | 0.9891 | 0.8917 |
| 0.0 | 48.0 | 10800 | 0.9895 | 0.8933 |
| 0.0 | 49.0 | 11025 | 0.9898 | 0.8933 |
| 0.0 | 50.0 | 11250 | 0.9898 | 0.8933 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2