smids_1x_deit_tiny_rms_00001_fold4
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: 1.2549
- Accuracy: 0.8583
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 |
|---|---|---|---|---|
| 0.4697 | 1.0 | 75 | 0.4183 | 0.8233 |
| 0.3312 | 2.0 | 150 | 0.3681 | 0.8533 |
| 0.2321 | 3.0 | 225 | 0.4033 | 0.8517 |
| 0.1334 | 4.0 | 300 | 0.3968 | 0.8617 |
| 0.1233 | 5.0 | 375 | 0.4520 | 0.8567 |
| 0.0584 | 6.0 | 450 | 0.5293 | 0.8467 |
| 0.0835 | 7.0 | 525 | 0.5619 | 0.8533 |
| 0.0113 | 8.0 | 600 | 0.7080 | 0.8483 |
| 0.0326 | 9.0 | 675 | 0.7194 | 0.86 |
| 0.0108 | 10.0 | 750 | 0.7779 | 0.8583 |
| 0.0133 | 11.0 | 825 | 0.7881 | 0.8617 |
| 0.0052 | 12.0 | 900 | 0.8341 | 0.87 |
| 0.0272 | 13.0 | 975 | 0.8910 | 0.8617 |
| 0.0077 | 14.0 | 1050 | 0.9561 | 0.8433 |
| 0.0002 | 15.0 | 1125 | 0.9039 | 0.8617 |
| 0.0001 | 16.0 | 1200 | 0.9956 | 0.86 |
| 0.032 | 17.0 | 1275 | 0.9953 | 0.8667 |
| 0.018 | 18.0 | 1350 | 0.9816 | 0.8633 |
| 0.0282 | 19.0 | 1425 | 1.1776 | 0.8467 |
| 0.0002 | 20.0 | 1500 | 1.0796 | 0.8583 |
| 0.0001 | 21.0 | 1575 | 1.1308 | 0.8567 |
| 0.0001 | 22.0 | 1650 | 1.1869 | 0.8467 |
| 0.0001 | 23.0 | 1725 | 1.1953 | 0.86 |
| 0.0134 | 24.0 | 1800 | 1.1511 | 0.85 |
| 0.0197 | 25.0 | 1875 | 1.2279 | 0.8517 |
| 0.0 | 26.0 | 1950 | 1.2715 | 0.8483 |
| 0.0011 | 27.0 | 2025 | 1.2389 | 0.85 |
| 0.0034 | 28.0 | 2100 | 1.2470 | 0.85 |
| 0.0076 | 29.0 | 2175 | 1.1531 | 0.8617 |
| 0.0 | 30.0 | 2250 | 1.2325 | 0.85 |
| 0.0 | 31.0 | 2325 | 1.2009 | 0.8633 |
| 0.0 | 32.0 | 2400 | 1.2311 | 0.85 |
| 0.0 | 33.0 | 2475 | 1.2487 | 0.8583 |
| 0.0 | 34.0 | 2550 | 1.2363 | 0.8567 |
| 0.0 | 35.0 | 2625 | 1.2306 | 0.8567 |
| 0.0 | 36.0 | 2700 | 1.2366 | 0.86 |
| 0.0048 | 37.0 | 2775 | 1.2202 | 0.8567 |
| 0.0 | 38.0 | 2850 | 1.2263 | 0.86 |
| 0.0 | 39.0 | 2925 | 1.2319 | 0.8617 |
| 0.0 | 40.0 | 3000 | 1.2616 | 0.8533 |
| 0.0038 | 41.0 | 3075 | 1.2358 | 0.8583 |
| 0.0 | 42.0 | 3150 | 1.2473 | 0.8583 |
| 0.0 | 43.0 | 3225 | 1.2419 | 0.8567 |
| 0.0 | 44.0 | 3300 | 1.2543 | 0.8583 |
| 0.0 | 45.0 | 3375 | 1.2531 | 0.8567 |
| 0.0 | 46.0 | 3450 | 1.2531 | 0.8583 |
| 0.0 | 47.0 | 3525 | 1.2531 | 0.8583 |
| 0.0 | 48.0 | 3600 | 1.2543 | 0.8583 |
| 0.0 | 49.0 | 3675 | 1.2544 | 0.8583 |
| 0.0 | 50.0 | 3750 | 1.2549 | 0.8583 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0