<!-- 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_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: 0.0299
- 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 |
|---|---|---|---|---|
| 0.915 | 0.57 | 1 | 0.9268 | 0.2174 |
| 0.783 | 1.71 | 3 | 0.6175 | 0.6957 |
| 0.5331 | 2.86 | 5 | 0.4358 | 0.8913 |
| 0.3435 | 4.0 | 7 | 0.2875 | 0.9348 |
| 0.3079 | 4.57 | 8 | 0.2418 | 0.9348 |
| 0.2427 | 5.71 | 10 | 0.1828 | 0.9565 |
| 0.1838 | 6.86 | 12 | 0.1664 | 0.9348 |
| 0.1349 | 8.0 | 14 | 0.0918 | 0.9783 |
| 0.1791 | 8.57 | 15 | 0.1036 | 0.9565 |
| 0.1264 | 9.71 | 17 | 0.0906 | 0.9783 |
| 0.1161 | 10.86 | 19 | 0.0507 | 0.9783 |
| 0.0942 | 12.0 | 21 | 0.0683 | 0.9783 |
| 0.1284 | 12.57 | 22 | 0.0676 | 0.9783 |
| 0.0862 | 13.71 | 24 | 0.0299 | 1.0 |
| 0.1011 | 14.86 | 26 | 0.0319 | 1.0 |
| 0.0675 | 16.0 | 28 | 0.0186 | 1.0 |
| 0.0814 | 16.57 | 29 | 0.0275 | 0.9783 |
| 0.0656 | 17.71 | 31 | 0.0740 | 0.9783 |
| 0.0837 | 18.86 | 33 | 0.0673 | 0.9783 |
| 0.108 | 20.0 | 35 | 0.0287 | 0.9783 |
| 0.0954 | 20.57 | 36 | 0.0180 | 1.0 |
| 0.1017 | 21.71 | 38 | 0.0116 | 1.0 |
| 0.0752 | 22.86 | 40 | 0.0124 | 1.0 |
| 0.0491 | 24.0 | 42 | 0.0113 | 1.0 |
| 0.0639 | 24.57 | 43 | 0.0103 | 1.0 |
| 0.088 | 25.71 | 45 | 0.0103 | 1.0 |
| 0.0705 | 26.86 | 47 | 0.0102 | 1.0 |
| 0.0871 | 28.0 | 49 | 0.0099 | 1.0 |
| 0.0486 | 28.57 | 50 | 0.0097 | 1.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
