smids_1x_deit_small_sgd_00001_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: 1.0403
- Accuracy: 0.4775
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 |
|---|---|---|---|---|
| 1.0855 | 1.0 | 76 | 1.0750 | 0.4424 |
| 1.0478 | 2.0 | 152 | 1.0731 | 0.4391 |
| 1.0766 | 3.0 | 228 | 1.0714 | 0.4391 |
| 1.0629 | 4.0 | 304 | 1.0697 | 0.4357 |
| 1.094 | 5.0 | 380 | 1.0680 | 0.4341 |
| 1.0477 | 6.0 | 456 | 1.0665 | 0.4391 |
| 1.0623 | 7.0 | 532 | 1.0650 | 0.4441 |
| 1.0732 | 8.0 | 608 | 1.0636 | 0.4457 |
| 1.0667 | 9.0 | 684 | 1.0622 | 0.4491 |
| 1.0551 | 10.0 | 760 | 1.0610 | 0.4491 |
| 1.0356 | 11.0 | 836 | 1.0597 | 0.4491 |
| 1.0548 | 12.0 | 912 | 1.0586 | 0.4508 |
| 1.0615 | 13.0 | 988 | 1.0574 | 0.4591 |
| 1.0286 | 14.0 | 1064 | 1.0564 | 0.4574 |
| 1.0112 | 15.0 | 1140 | 1.0553 | 0.4558 |
| 1.0377 | 16.0 | 1216 | 1.0543 | 0.4574 |
| 1.0367 | 17.0 | 1292 | 1.0534 | 0.4608 |
| 1.0315 | 18.0 | 1368 | 1.0524 | 0.4608 |
| 1.0307 | 19.0 | 1444 | 1.0516 | 0.4608 |
| 1.0759 | 20.0 | 1520 | 1.0507 | 0.4658 |
| 1.0618 | 21.0 | 1596 | 1.0499 | 0.4674 |
| 1.0607 | 22.0 | 1672 | 1.0492 | 0.4691 |
| 1.0436 | 23.0 | 1748 | 1.0485 | 0.4741 |
| 1.0498 | 24.0 | 1824 | 1.0478 | 0.4758 |
| 1.0615 | 25.0 | 1900 | 1.0471 | 0.4741 |
| 1.0688 | 26.0 | 1976 | 1.0465 | 0.4741 |
| 1.0336 | 27.0 | 2052 | 1.0459 | 0.4741 |
| 1.0515 | 28.0 | 2128 | 1.0454 | 0.4741 |
| 1.042 | 29.0 | 2204 | 1.0449 | 0.4775 |
| 1.0112 | 30.0 | 2280 | 1.0444 | 0.4791 |
| 1.0359 | 31.0 | 2356 | 1.0439 | 0.4791 |
| 1.0424 | 32.0 | 2432 | 1.0435 | 0.4791 |
| 1.0133 | 33.0 | 2508 | 1.0431 | 0.4808 |
| 1.0411 | 34.0 | 2584 | 1.0427 | 0.4791 |
| 1.0158 | 35.0 | 2660 | 1.0424 | 0.4775 |
| 1.0378 | 36.0 | 2736 | 1.0421 | 0.4775 |
| 1.0599 | 37.0 | 2812 | 1.0418 | 0.4791 |
| 1.0074 | 38.0 | 2888 | 1.0416 | 0.4775 |
| 1.0149 | 39.0 | 2964 | 1.0413 | 0.4775 |
| 1.0618 | 40.0 | 3040 | 1.0411 | 0.4775 |
| 1.0242 | 41.0 | 3116 | 1.0409 | 0.4775 |
| 1.0268 | 42.0 | 3192 | 1.0408 | 0.4775 |
| 1.0441 | 43.0 | 3268 | 1.0407 | 0.4758 |
| 1.0356 | 44.0 | 3344 | 1.0406 | 0.4775 |
| 1.0273 | 45.0 | 3420 | 1.0405 | 0.4775 |
| 1.0473 | 46.0 | 3496 | 1.0404 | 0.4775 |
| 1.0225 | 47.0 | 3572 | 1.0404 | 0.4775 |
| 1.0411 | 48.0 | 3648 | 1.0404 | 0.4775 |
| 1.0464 | 49.0 | 3724 | 1.0403 | 0.4775 |
| 1.0229 | 50.0 | 3800 | 1.0403 | 0.4775 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0