<!-- 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_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: 0.1548
- Accuracy: 0.9641
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 |
|---|---|---|---|---|
| 0.6972 | 0.96 | 6 | 0.7597 | 0.5150 |
| 0.6634 | 1.92 | 12 | 0.6285 | 0.6647 |
| 0.6401 | 2.88 | 18 | 0.5843 | 0.6766 |
| 0.5423 | 4.0 | 25 | 0.4757 | 0.7904 |
| 0.4909 | 4.96 | 31 | 0.4218 | 0.8204 |
| 0.4766 | 5.92 | 37 | 0.3822 | 0.8084 |
| 0.5227 | 6.88 | 43 | 0.3823 | 0.8263 |
| 0.4523 | 8.0 | 50 | 0.3504 | 0.8383 |
| 0.3411 | 8.96 | 56 | 0.3301 | 0.8683 |
| 0.385 | 9.92 | 62 | 0.3218 | 0.8503 |
| 0.3507 | 10.88 | 68 | 0.2988 | 0.8922 |
| 0.4034 | 12.0 | 75 | 0.3166 | 0.8683 |
| 0.3936 | 12.96 | 81 | 0.3123 | 0.8683 |
| 0.3858 | 13.92 | 87 | 0.3433 | 0.8443 |
| 0.3484 | 14.88 | 93 | 0.3273 | 0.8563 |
| 0.3207 | 16.0 | 100 | 0.2371 | 0.9102 |
| 0.286 | 16.96 | 106 | 0.2244 | 0.9162 |
| 0.3368 | 17.92 | 112 | 0.1985 | 0.9341 |
| 0.3379 | 18.88 | 118 | 0.2134 | 0.9401 |
| 0.4299 | 20.0 | 125 | 0.2277 | 0.8982 |
| 0.3141 | 20.96 | 131 | 0.2133 | 0.9102 |
| 0.3257 | 21.92 | 137 | 0.2207 | 0.9281 |
| 0.3188 | 22.88 | 143 | 0.1802 | 0.9222 |
| 0.3031 | 24.0 | 150 | 0.1725 | 0.9341 |
| 0.2989 | 24.96 | 156 | 0.2016 | 0.9222 |
| 0.2779 | 25.92 | 162 | 0.1858 | 0.9461 |
| 0.249 | 26.88 | 168 | 0.1767 | 0.9281 |
| 0.337 | 28.0 | 175 | 0.1675 | 0.9341 |
| 0.3142 | 28.96 | 181 | 0.1997 | 0.9281 |
| 0.3011 | 29.92 | 187 | 0.1548 | 0.9641 |
| 0.3194 | 30.88 | 193 | 0.1652 | 0.9521 |
| 0.3037 | 32.0 | 200 | 0.1635 | 0.9521 |
| 0.2949 | 32.96 | 206 | 0.1573 | 0.9461 |
| 0.2744 | 33.92 | 212 | 0.1909 | 0.9162 |
| 0.2505 | 34.88 | 218 | 0.2062 | 0.9222 |
| 0.2829 | 36.0 | 225 | 0.1593 | 0.9461 |
| 0.2557 | 36.96 | 231 | 0.2157 | 0.8982 |
| 0.3073 | 37.92 | 237 | 0.1491 | 0.9521 |
| 0.2683 | 38.88 | 243 | 0.1597 | 0.9401 |
| 0.27 | 40.0 | 250 | 0.1385 | 0.9521 |
| 0.283 | 40.96 | 256 | 0.1382 | 0.9581 |
| 0.2802 | 41.92 | 262 | 0.1302 | 0.9641 |
| 0.2374 | 42.88 | 268 | 0.1399 | 0.9461 |
| 0.293 | 44.0 | 275 | 0.1203 | 0.9641 |
| 0.2319 | 44.96 | 281 | 0.1226 | 0.9521 |
| 0.2672 | 45.92 | 287 | 0.1227 | 0.9641 |
| 0.2484 | 46.88 | 293 | 0.1266 | 0.9641 |
| 0.2573 | 48.0 | 300 | 0.1228 | 0.9641 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
