<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit-base-patch16-224-Trial006-007-008-YEL_STEM4
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1729
- Accuracy: 0.9355
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: 5e-05
- train_batch_size: 60
- eval_batch_size: 60
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 240
- 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 |
|---|---|---|---|---|
| 0.6572 | 1.0 | 6 | 0.6719 | 0.5677 |
| 0.6279 | 2.0 | 12 | 0.6436 | 0.6516 |
| 0.5282 | 3.0 | 18 | 0.5677 | 0.7871 |
| 0.5405 | 4.0 | 24 | 0.4718 | 0.8258 |
| 0.5276 | 5.0 | 30 | 0.4959 | 0.7419 |
| 0.412 | 6.0 | 36 | 0.3081 | 0.8581 |
| 0.3011 | 7.0 | 42 | 0.2542 | 0.8839 |
| 0.3329 | 8.0 | 48 | 0.2350 | 0.8774 |
| 0.4478 | 9.0 | 54 | 0.1743 | 0.9290 |
| 0.268 | 10.0 | 60 | 0.1708 | 0.9161 |
| 0.2177 | 11.0 | 66 | 0.1729 | 0.9355 |
| 0.2675 | 12.0 | 72 | 0.1913 | 0.8968 |
| 0.4784 | 13.0 | 78 | 0.1826 | 0.9032 |
| 0.2456 | 14.0 | 84 | 0.1774 | 0.9032 |
| 0.6229 | 15.0 | 90 | 0.2196 | 0.8968 |
| 0.2561 | 16.0 | 96 | 0.1823 | 0.9226 |
| 0.3785 | 17.0 | 102 | 0.1770 | 0.9032 |
| 0.2334 | 18.0 | 108 | 0.2056 | 0.8903 |
| 0.1904 | 19.0 | 114 | 0.1564 | 0.9097 |
| 0.2256 | 20.0 | 120 | 0.1407 | 0.9226 |
| 0.2547 | 21.0 | 126 | 0.1552 | 0.9032 |
| 0.3468 | 22.0 | 132 | 0.1819 | 0.8968 |
| 0.4116 | 23.0 | 138 | 0.1537 | 0.9290 |
| 0.3689 | 24.0 | 144 | 0.1645 | 0.9097 |
| 0.3541 | 25.0 | 150 | 0.1527 | 0.9290 |
| 0.2498 | 26.0 | 156 | 0.1670 | 0.9161 |
| 0.3625 | 27.0 | 162 | 0.1522 | 0.9161 |
| 0.2463 | 28.0 | 168 | 0.1552 | 0.9226 |
| 0.3447 | 29.0 | 174 | 0.1510 | 0.9097 |
| 0.205 | 30.0 | 180 | 0.1924 | 0.9032 |
| 0.2023 | 31.0 | 186 | 0.1376 | 0.9355 |
| 0.3617 | 32.0 | 192 | 0.1518 | 0.9097 |
| 0.3515 | 33.0 | 198 | 0.1473 | 0.9097 |
| 0.1927 | 34.0 | 204 | 0.1544 | 0.9097 |
| 0.4567 | 35.0 | 210 | 0.1528 | 0.9097 |
| 0.3113 | 36.0 | 216 | 0.1510 | 0.9226 |
| 0.3475 | 37.0 | 222 | 0.1594 | 0.9161 |
| 0.1889 | 38.0 | 228 | 0.1448 | 0.9290 |
| 0.1979 | 39.0 | 234 | 0.1533 | 0.9226 |
| 0.3578 | 40.0 | 240 | 0.1627 | 0.9097 |
| 0.2004 | 41.0 | 246 | 0.1620 | 0.9161 |
| 0.3567 | 42.0 | 252 | 0.1475 | 0.9226 |
| 0.192 | 43.0 | 258 | 0.1504 | 0.9032 |
| 0.1872 | 44.0 | 264 | 0.1535 | 0.9097 |
| 0.2079 | 45.0 | 270 | 0.1490 | 0.9161 |
| 0.1503 | 46.0 | 276 | 0.1459 | 0.9161 |
| 0.169 | 47.0 | 282 | 0.1506 | 0.8968 |
| 0.1884 | 48.0 | 288 | 0.1556 | 0.8968 |
| 0.1638 | 49.0 | 294 | 0.1573 | 0.8968 |
| 0.1921 | 50.0 | 300 | 0.1570 | 0.8968 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
