smids_1x_deit_small_sgd_001_fold1
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: 0.3767
- Accuracy: 0.8614
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 |
|---|---|---|---|---|
| 0.9992 | 1.0 | 76 | 0.9734 | 0.5159 |
| 0.868 | 2.0 | 152 | 0.8565 | 0.6578 |
| 0.7395 | 3.0 | 228 | 0.7685 | 0.7112 |
| 0.6957 | 4.0 | 304 | 0.6964 | 0.7329 |
| 0.6074 | 5.0 | 380 | 0.6430 | 0.7546 |
| 0.5254 | 6.0 | 456 | 0.6017 | 0.7763 |
| 0.5109 | 7.0 | 532 | 0.5681 | 0.7930 |
| 0.4805 | 8.0 | 608 | 0.5426 | 0.7963 |
| 0.5102 | 9.0 | 684 | 0.5230 | 0.7980 |
| 0.3976 | 10.0 | 760 | 0.5054 | 0.8047 |
| 0.4427 | 11.0 | 836 | 0.4905 | 0.8130 |
| 0.4239 | 12.0 | 912 | 0.4775 | 0.8230 |
| 0.3866 | 13.0 | 988 | 0.4665 | 0.8247 |
| 0.3955 | 14.0 | 1064 | 0.4585 | 0.8264 |
| 0.3407 | 15.0 | 1140 | 0.4495 | 0.8314 |
| 0.3573 | 16.0 | 1216 | 0.4427 | 0.8347 |
| 0.3641 | 17.0 | 1292 | 0.4365 | 0.8364 |
| 0.3346 | 18.0 | 1368 | 0.4307 | 0.8397 |
| 0.3763 | 19.0 | 1444 | 0.4260 | 0.8414 |
| 0.3869 | 20.0 | 1520 | 0.4209 | 0.8481 |
| 0.3653 | 21.0 | 1596 | 0.4169 | 0.8497 |
| 0.3686 | 22.0 | 1672 | 0.4141 | 0.8548 |
| 0.3341 | 23.0 | 1748 | 0.4097 | 0.8531 |
| 0.3374 | 24.0 | 1824 | 0.4075 | 0.8564 |
| 0.2762 | 25.0 | 1900 | 0.4048 | 0.8548 |
| 0.3405 | 26.0 | 1976 | 0.4003 | 0.8548 |
| 0.2508 | 27.0 | 2052 | 0.3979 | 0.8581 |
| 0.3194 | 28.0 | 2128 | 0.3965 | 0.8531 |
| 0.2863 | 29.0 | 2204 | 0.3942 | 0.8598 |
| 0.2965 | 30.0 | 2280 | 0.3922 | 0.8614 |
| 0.3328 | 31.0 | 2356 | 0.3904 | 0.8614 |
| 0.2682 | 32.0 | 2432 | 0.3879 | 0.8614 |
| 0.27 | 33.0 | 2508 | 0.3869 | 0.8631 |
| 0.3255 | 34.0 | 2584 | 0.3856 | 0.8598 |
| 0.5893 | 35.0 | 2660 | 0.3845 | 0.8614 |
| 0.2978 | 36.0 | 2736 | 0.3831 | 0.8614 |
| 0.3197 | 37.0 | 2812 | 0.3822 | 0.8631 |
| 0.2821 | 38.0 | 2888 | 0.3814 | 0.8631 |
| 0.2797 | 39.0 | 2964 | 0.3806 | 0.8631 |
| 0.3067 | 40.0 | 3040 | 0.3796 | 0.8631 |
| 0.2337 | 41.0 | 3116 | 0.3790 | 0.8648 |
| 0.2989 | 42.0 | 3192 | 0.3784 | 0.8631 |
| 0.2792 | 43.0 | 3268 | 0.3779 | 0.8631 |
| 0.2985 | 44.0 | 3344 | 0.3775 | 0.8631 |
| 0.2895 | 45.0 | 3420 | 0.3772 | 0.8614 |
| 0.2249 | 46.0 | 3496 | 0.3770 | 0.8614 |
| 0.2475 | 47.0 | 3572 | 0.3768 | 0.8631 |
| 0.2872 | 48.0 | 3648 | 0.3767 | 0.8631 |
| 0.2536 | 49.0 | 3724 | 0.3767 | 0.8614 |
| 0.3607 | 50.0 | 3800 | 0.3767 | 0.8614 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0