<!-- 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_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: 0.1221
- Accuracy: 0.9688
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 |
|---|---|---|---|---|
| 0.7092 | 1.0 | 6 | 0.6454 | 0.6312 |
| 0.6029 | 2.0 | 12 | 0.5650 | 0.7125 |
| 0.6078 | 3.0 | 18 | 0.4996 | 0.7875 |
| 0.4686 | 4.0 | 24 | 0.4078 | 0.8438 |
| 0.4057 | 5.0 | 30 | 0.3520 | 0.9 |
| 0.4014 | 6.0 | 36 | 0.3402 | 0.8562 |
| 0.3302 | 7.0 | 42 | 0.2707 | 0.925 |
| 0.3111 | 8.0 | 48 | 0.2063 | 0.9375 |
| 0.2762 | 9.0 | 54 | 0.1970 | 0.9375 |
| 0.3059 | 10.0 | 60 | 0.2004 | 0.9313 |
| 0.1938 | 11.0 | 66 | 0.2721 | 0.9062 |
| 0.2729 | 12.0 | 72 | 0.1821 | 0.9563 |
| 0.2676 | 13.0 | 78 | 0.2085 | 0.95 |
| 0.2561 | 14.0 | 84 | 0.1609 | 0.9563 |
| 0.1853 | 15.0 | 90 | 0.1741 | 0.9563 |
| 0.2703 | 16.0 | 96 | 0.2052 | 0.9375 |
| 0.2326 | 17.0 | 102 | 0.1851 | 0.9563 |
| 0.2158 | 18.0 | 108 | 0.1410 | 0.9563 |
| 0.322 | 19.0 | 114 | 0.1979 | 0.9375 |
| 0.2194 | 20.0 | 120 | 0.1746 | 0.9625 |
| 0.2836 | 21.0 | 126 | 0.1400 | 0.9625 |
| 0.2309 | 22.0 | 132 | 0.1503 | 0.9625 |
| 0.2131 | 23.0 | 138 | 0.1221 | 0.9688 |
| 0.2164 | 24.0 | 144 | 0.1280 | 0.9688 |
| 0.2039 | 25.0 | 150 | 0.2217 | 0.9313 |
| 0.2123 | 26.0 | 156 | 0.1596 | 0.9563 |
| 0.2178 | 27.0 | 162 | 0.1463 | 0.95 |
| 0.2425 | 28.0 | 168 | 0.1494 | 0.95 |
| 0.2031 | 29.0 | 174 | 0.1659 | 0.9563 |
| 0.1802 | 30.0 | 180 | 0.1549 | 0.9688 |
| 0.2075 | 31.0 | 186 | 0.1275 | 0.9688 |
| 0.1897 | 32.0 | 192 | 0.1163 | 0.9688 |
| 0.2013 | 33.0 | 198 | 0.1244 | 0.9688 |
| 0.2696 | 34.0 | 204 | 0.1243 | 0.9688 |
| 0.2229 | 35.0 | 210 | 0.1259 | 0.9688 |
| 0.2017 | 36.0 | 216 | 0.1258 | 0.9625 |
| 0.1953 | 37.0 | 222 | 0.1189 | 0.9688 |
| 0.189 | 38.0 | 228 | 0.1578 | 0.9563 |
| 0.2301 | 39.0 | 234 | 0.1981 | 0.9375 |
| 0.2022 | 40.0 | 240 | 0.1368 | 0.9625 |
| 0.1851 | 41.0 | 246 | 0.1452 | 0.9625 |
| 0.1791 | 42.0 | 252 | 0.1379 | 0.9625 |
| 0.1685 | 43.0 | 258 | 0.1218 | 0.9625 |
| 0.1917 | 44.0 | 264 | 0.1218 | 0.9688 |
| 0.1997 | 45.0 | 270 | 0.1293 | 0.9688 |
| 0.2274 | 46.0 | 276 | 0.1339 | 0.9625 |
| 0.1721 | 47.0 | 282 | 0.1354 | 0.9625 |
| 0.188 | 48.0 | 288 | 0.1339 | 0.9625 |
| 0.2042 | 49.0 | 294 | 0.1355 | 0.9688 |
| 0.1689 | 50.0 | 300 | 0.1361 | 0.9688 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
