<!-- 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-YEL_STEM1
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: 0.1027
- 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 |
|---|---|---|---|---|
| 0.7044 | 0.57 | 1 | 0.6796 | 0.5532 |
| 0.6409 | 1.71 | 3 | 0.5322 | 0.6809 |
| 0.4808 | 2.86 | 5 | 0.3867 | 0.8936 |
| 0.3793 | 4.0 | 7 | 0.2469 | 0.9149 |
| 0.266 | 4.57 | 8 | 0.1974 | 0.9362 |
| 0.1602 | 5.71 | 10 | 0.1027 | 1.0 |
| 0.1368 | 6.86 | 12 | 0.0519 | 1.0 |
| 0.1277 | 8.0 | 14 | 0.0318 | 1.0 |
| 0.1268 | 8.57 | 15 | 0.0297 | 1.0 |
| 0.1303 | 9.71 | 17 | 0.0267 | 1.0 |
| 0.0967 | 10.86 | 19 | 0.0206 | 1.0 |
| 0.1281 | 12.0 | 21 | 0.0299 | 0.9787 |
| 0.1098 | 12.57 | 22 | 0.0378 | 0.9787 |
| 0.1122 | 13.71 | 24 | 0.0369 | 0.9787 |
| 0.1315 | 14.86 | 26 | 0.0242 | 1.0 |
| 0.0754 | 16.0 | 28 | 0.0198 | 1.0 |
| 0.0785 | 16.57 | 29 | 0.0190 | 1.0 |
| 0.1232 | 17.71 | 31 | 0.0240 | 1.0 |
| 0.0642 | 18.86 | 33 | 0.0390 | 0.9787 |
| 0.0729 | 20.0 | 35 | 0.0478 | 0.9787 |
| 0.0789 | 20.57 | 36 | 0.0431 | 0.9787 |
| 0.0678 | 21.71 | 38 | 0.0505 | 0.9787 |
| 0.0792 | 22.86 | 40 | 0.0347 | 0.9787 |
| 0.0868 | 24.0 | 42 | 0.0143 | 1.0 |
| 0.0921 | 24.57 | 43 | 0.0124 | 1.0 |
| 0.0575 | 25.71 | 45 | 0.0124 | 1.0 |
| 0.0508 | 26.86 | 47 | 0.0126 | 1.0 |
| 0.0652 | 28.0 | 49 | 0.0128 | 1.0 |
| 0.0782 | 28.57 | 50 | 0.0127 | 1.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
