<!-- 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-YEL_STEM2
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: 0.0168
- Accuracy: 1.0
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 |
|---|---|---|---|---|
| 0.7513 | 1.0 | 2 | 0.7189 | 0.4717 |
| 0.6809 | 2.0 | 4 | 0.7181 | 0.5283 |
| 0.6215 | 3.0 | 6 | 0.6232 | 0.6604 |
| 0.5532 | 4.0 | 8 | 0.5307 | 0.7358 |
| 0.4625 | 5.0 | 10 | 0.5317 | 0.6415 |
| 0.3877 | 6.0 | 12 | 0.3571 | 0.8491 |
| 0.3372 | 7.0 | 14 | 0.2507 | 0.9057 |
| 0.2913 | 8.0 | 16 | 0.2065 | 0.9434 |
| 0.2853 | 9.0 | 18 | 0.1859 | 0.9623 |
| 0.288 | 10.0 | 20 | 0.1413 | 0.9434 |
| 0.2707 | 11.0 | 22 | 0.3137 | 0.8302 |
| 0.2567 | 12.0 | 24 | 0.0865 | 0.9811 |
| 0.241 | 13.0 | 26 | 0.1032 | 0.9623 |
| 0.1507 | 14.0 | 28 | 0.0897 | 0.9434 |
| 0.1923 | 15.0 | 30 | 0.1375 | 0.9623 |
| 0.1349 | 16.0 | 32 | 0.1575 | 0.9623 |
| 0.1524 | 17.0 | 34 | 0.0880 | 0.9623 |
| 0.1508 | 18.0 | 36 | 0.0767 | 0.9623 |
| 0.1457 | 19.0 | 38 | 0.5316 | 0.8302 |
| 0.1717 | 20.0 | 40 | 0.0495 | 0.9811 |
| 0.2475 | 21.0 | 42 | 0.0168 | 1.0 |
| 0.1328 | 22.0 | 44 | 0.0941 | 0.9245 |
| 0.1542 | 23.0 | 46 | 0.0247 | 0.9811 |
| 0.1531 | 24.0 | 48 | 0.0149 | 1.0 |
| 0.1383 | 25.0 | 50 | 0.0273 | 1.0 |
| 0.1085 | 26.0 | 52 | 0.1121 | 0.9434 |
| 0.1257 | 27.0 | 54 | 0.1325 | 0.9245 |
| 0.1503 | 28.0 | 56 | 0.0369 | 0.9811 |
| 0.1298 | 29.0 | 58 | 0.0700 | 0.9811 |
| 0.1485 | 30.0 | 60 | 0.0237 | 1.0 |
| 0.101 | 31.0 | 62 | 0.0207 | 1.0 |
| 0.1285 | 32.0 | 64 | 0.0439 | 0.9811 |
| 0.1226 | 33.0 | 66 | 0.0532 | 0.9811 |
| 0.1316 | 34.0 | 68 | 0.0232 | 0.9811 |
| 0.0864 | 35.0 | 70 | 0.0479 | 0.9623 |
| 0.1559 | 36.0 | 72 | 0.0086 | 1.0 |
| 0.1263 | 37.0 | 74 | 0.0223 | 0.9811 |
| 0.085 | 38.0 | 76 | 0.0151 | 1.0 |
| 0.1602 | 39.0 | 78 | 0.0366 | 0.9623 |
| 0.1232 | 40.0 | 80 | 0.1279 | 0.9623 |
| 0.1073 | 41.0 | 82 | 0.1756 | 0.9623 |
| 0.0984 | 42.0 | 84 | 0.1029 | 0.9623 |
| 0.1229 | 43.0 | 86 | 0.0228 | 1.0 |
| 0.108 | 44.0 | 88 | 0.0082 | 1.0 |
| 0.1172 | 45.0 | 90 | 0.0077 | 1.0 |
| 0.0835 | 46.0 | 92 | 0.0075 | 1.0 |
| 0.1112 | 47.0 | 94 | 0.0105 | 1.0 |
| 0.1202 | 48.0 | 96 | 0.0232 | 1.0 |
| 0.1191 | 49.0 | 98 | 0.0283 | 0.9811 |
| 0.1414 | 50.0 | 100 | 0.0279 | 0.9811 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
