<!-- 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_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: 0.0945
- Accuracy: 0.9787
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 |
|---|---|---|---|---|
| 0.7565 | 0.57 | 1 | 0.7156 | 0.4894 |
| 0.669 | 1.71 | 3 | 0.5962 | 0.7021 |
| 0.5341 | 2.86 | 5 | 0.4221 | 0.8511 |
| 0.3936 | 4.0 | 7 | 0.3294 | 0.8298 |
| 0.3071 | 4.57 | 8 | 0.2988 | 0.8511 |
| 0.2252 | 5.71 | 10 | 0.2180 | 0.8723 |
| 0.266 | 6.86 | 12 | 0.2028 | 0.8936 |
| 0.2337 | 8.0 | 14 | 0.1789 | 0.9362 |
| 0.2581 | 8.57 | 15 | 0.1293 | 0.9574 |
| 0.2143 | 9.71 | 17 | 0.2647 | 0.8936 |
| 0.1516 | 10.86 | 19 | 0.1180 | 0.9574 |
| 0.2007 | 12.0 | 21 | 0.1280 | 0.9574 |
| 0.1668 | 12.57 | 22 | 0.0945 | 0.9787 |
| 0.1335 | 13.71 | 24 | 0.1312 | 0.9574 |
| 0.1651 | 14.86 | 26 | 0.1289 | 0.9574 |
| 0.1273 | 16.0 | 28 | 0.1308 | 0.9574 |
| 0.1251 | 16.57 | 29 | 0.1287 | 0.9574 |
| 0.1315 | 17.71 | 31 | 0.0927 | 0.9574 |
| 0.1054 | 18.86 | 33 | 0.0696 | 0.9787 |
| 0.0924 | 20.0 | 35 | 0.0628 | 0.9787 |
| 0.1239 | 20.57 | 36 | 0.0623 | 0.9787 |
| 0.0891 | 21.71 | 38 | 0.0652 | 0.9787 |
| 0.0956 | 22.86 | 40 | 0.0729 | 0.9574 |
| 0.0969 | 24.0 | 42 | 0.0752 | 0.9574 |
| 0.1472 | 24.57 | 43 | 0.0769 | 0.9787 |
| 0.092 | 25.71 | 45 | 0.0788 | 0.9787 |
| 0.0916 | 26.86 | 47 | 0.0800 | 0.9787 |
| 0.0962 | 28.0 | 49 | 0.0800 | 0.9787 |
| 0.1077 | 28.57 | 50 | 0.0799 | 0.9787 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
