<!-- 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-Trial007-008-YEL_STEM
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: 0.0544
- Accuracy: 0.9872
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 |
|---|---|---|---|---|
| 0.7518 | 1.0 | 3 | 0.7841 | 0.4231 |
| 0.6744 | 2.0 | 6 | 0.6798 | 0.6154 |
| 0.5724 | 3.0 | 9 | 0.5060 | 0.7949 |
| 0.4443 | 4.0 | 12 | 0.4107 | 0.8462 |
| 0.4108 | 5.0 | 15 | 0.2686 | 0.9103 |
| 0.3192 | 6.0 | 18 | 0.1890 | 0.9231 |
| 0.2776 | 7.0 | 21 | 0.2280 | 0.8974 |
| 0.2738 | 8.0 | 24 | 0.0880 | 0.9487 |
| 0.2878 | 9.0 | 27 | 0.1754 | 0.9231 |
| 0.2974 | 10.0 | 30 | 0.0761 | 0.9744 |
| 0.2261 | 11.0 | 33 | 0.1195 | 0.9359 |
| 0.2443 | 12.0 | 36 | 0.0544 | 0.9872 |
| 0.2232 | 13.0 | 39 | 0.1409 | 0.9359 |
| 0.2066 | 14.0 | 42 | 0.0429 | 0.9872 |
| 0.2199 | 15.0 | 45 | 0.2464 | 0.8974 |
| 0.1938 | 16.0 | 48 | 0.0417 | 0.9872 |
| 0.199 | 17.0 | 51 | 0.0372 | 0.9872 |
| 0.2295 | 18.0 | 54 | 0.1006 | 0.9487 |
| 0.2323 | 19.0 | 57 | 0.0421 | 0.9872 |
| 0.2151 | 20.0 | 60 | 0.0463 | 0.9744 |
| 0.1702 | 21.0 | 63 | 0.1073 | 0.9487 |
| 0.1716 | 22.0 | 66 | 0.0337 | 0.9872 |
| 0.1859 | 23.0 | 69 | 0.0331 | 0.9872 |
| 0.2446 | 24.0 | 72 | 0.1184 | 0.9487 |
| 0.1794 | 25.0 | 75 | 0.0543 | 0.9744 |
| 0.1634 | 26.0 | 78 | 0.0310 | 0.9872 |
| 0.2456 | 27.0 | 81 | 0.0851 | 0.9615 |
| 0.1766 | 28.0 | 84 | 0.1577 | 0.9231 |
| 0.2139 | 29.0 | 87 | 0.0311 | 0.9872 |
| 0.1745 | 30.0 | 90 | 0.0300 | 0.9872 |
| 0.2111 | 31.0 | 93 | 0.0612 | 0.9615 |
| 0.1557 | 32.0 | 96 | 0.1366 | 0.9487 |
| 0.2181 | 33.0 | 99 | 0.0396 | 0.9872 |
| 0.2138 | 34.0 | 102 | 0.0322 | 0.9872 |
| 0.2423 | 35.0 | 105 | 0.0355 | 0.9872 |
| 0.2077 | 36.0 | 108 | 0.0401 | 0.9872 |
| 0.1993 | 37.0 | 111 | 0.0330 | 0.9872 |
| 0.1896 | 38.0 | 114 | 0.0352 | 0.9872 |
| 0.1998 | 39.0 | 117 | 0.0433 | 0.9872 |
| 0.2008 | 40.0 | 120 | 0.0391 | 0.9872 |
| 0.1624 | 41.0 | 123 | 0.0402 | 0.9872 |
| 0.1781 | 42.0 | 126 | 0.0355 | 0.9872 |
| 0.2293 | 43.0 | 129 | 0.0294 | 0.9872 |
| 0.174 | 44.0 | 132 | 0.0286 | 0.9872 |
| 0.1922 | 45.0 | 135 | 0.0292 | 0.9872 |
| 0.1639 | 46.0 | 138 | 0.0293 | 0.9872 |
| 0.2198 | 47.0 | 141 | 0.0286 | 0.9872 |
| 0.2052 | 48.0 | 144 | 0.0297 | 0.9872 |
| 0.2021 | 49.0 | 147 | 0.0324 | 0.9872 |
| 0.1954 | 50.0 | 150 | 0.0337 | 0.9872 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
