hushem_5x_deit_small_adamax_0001_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: 1.4651
- Accuracy: 0.7111
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: 0.0001
- 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 |
|---|---|---|---|---|
| 0.6869 | 1.0 | 27 | 0.8756 | 0.6444 |
| 0.1015 | 2.0 | 54 | 0.6480 | 0.7556 |
| 0.0313 | 3.0 | 81 | 0.6884 | 0.7556 |
| 0.0043 | 4.0 | 108 | 1.0483 | 0.7333 |
| 0.0008 | 5.0 | 135 | 1.6044 | 0.6667 |
| 0.0003 | 6.0 | 162 | 1.1582 | 0.7556 |
| 0.0003 | 7.0 | 189 | 1.2707 | 0.7333 |
| 0.0002 | 8.0 | 216 | 1.3227 | 0.7333 |
| 0.0002 | 9.0 | 243 | 1.2990 | 0.7333 |
| 0.0001 | 10.0 | 270 | 1.3357 | 0.7333 |
| 0.0001 | 11.0 | 297 | 1.3446 | 0.7111 |
| 0.0001 | 12.0 | 324 | 1.3631 | 0.7111 |
| 0.0001 | 13.0 | 351 | 1.3596 | 0.7111 |
| 0.0001 | 14.0 | 378 | 1.3708 | 0.7111 |
| 0.0001 | 15.0 | 405 | 1.3642 | 0.7111 |
| 0.0001 | 16.0 | 432 | 1.3759 | 0.7111 |
| 0.0001 | 17.0 | 459 | 1.3779 | 0.7111 |
| 0.0001 | 18.0 | 486 | 1.3841 | 0.7111 |
| 0.0001 | 19.0 | 513 | 1.3945 | 0.7111 |
| 0.0001 | 20.0 | 540 | 1.3969 | 0.7111 |
| 0.0001 | 21.0 | 567 | 1.4051 | 0.7111 |
| 0.0001 | 22.0 | 594 | 1.4058 | 0.7111 |
| 0.0001 | 23.0 | 621 | 1.4088 | 0.7111 |
| 0.0001 | 24.0 | 648 | 1.4158 | 0.7111 |
| 0.0001 | 25.0 | 675 | 1.4194 | 0.7111 |
| 0.0001 | 26.0 | 702 | 1.4258 | 0.7111 |
| 0.0001 | 27.0 | 729 | 1.4287 | 0.7111 |
| 0.0001 | 28.0 | 756 | 1.4297 | 0.7111 |
| 0.0001 | 29.0 | 783 | 1.4322 | 0.7111 |
| 0.0001 | 30.0 | 810 | 1.4390 | 0.7111 |
| 0.0001 | 31.0 | 837 | 1.4403 | 0.7111 |
| 0.0001 | 32.0 | 864 | 1.4424 | 0.7111 |
| 0.0001 | 33.0 | 891 | 1.4435 | 0.7111 |
| 0.0001 | 34.0 | 918 | 1.4462 | 0.7111 |
| 0.0001 | 35.0 | 945 | 1.4501 | 0.7111 |
| 0.0001 | 36.0 | 972 | 1.4516 | 0.7111 |
| 0.0 | 37.0 | 999 | 1.4541 | 0.7111 |
| 0.0 | 38.0 | 1026 | 1.4558 | 0.7111 |
| 0.0 | 39.0 | 1053 | 1.4579 | 0.7111 |
| 0.0 | 40.0 | 1080 | 1.4592 | 0.7111 |
| 0.0 | 41.0 | 1107 | 1.4601 | 0.7111 |
| 0.0 | 42.0 | 1134 | 1.4620 | 0.7111 |
| 0.0 | 43.0 | 1161 | 1.4630 | 0.7111 |
| 0.0 | 44.0 | 1188 | 1.4638 | 0.7111 |
| 0.0 | 45.0 | 1215 | 1.4644 | 0.7111 |
| 0.0 | 46.0 | 1242 | 1.4647 | 0.7111 |
| 0.0 | 47.0 | 1269 | 1.4650 | 0.7111 |
| 0.0 | 48.0 | 1296 | 1.4651 | 0.7111 |
| 0.0 | 49.0 | 1323 | 1.4651 | 0.7111 |
| 0.0 | 50.0 | 1350 | 1.4651 | 0.7111 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0