<!-- 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_STEM3
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: 0.4074
- Accuracy: 0.8511
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 |
|---|---|---|---|---|
| 0.6144 | 0.57 | 1 | 0.6248 | 0.6596 |
| 0.5456 | 1.71 | 3 | 0.5613 | 0.7660 |
| 0.4291 | 2.86 | 5 | 0.5608 | 0.7872 |
| 0.4118 | 4.0 | 7 | 0.4317 | 0.8298 |
| 0.37 | 4.57 | 8 | 0.4074 | 0.8511 |
| 0.2912 | 5.71 | 10 | 0.4789 | 0.8511 |
| 0.3042 | 6.86 | 12 | 0.3958 | 0.8511 |
| 0.2819 | 8.0 | 14 | 0.3650 | 0.8511 |
| 0.2623 | 8.57 | 15 | 0.3636 | 0.8511 |
| 0.29 | 9.71 | 17 | 0.3705 | 0.8511 |
| 0.2187 | 10.86 | 19 | 0.3750 | 0.8511 |
| 0.2477 | 12.0 | 21 | 0.3615 | 0.8511 |
| 0.2185 | 12.57 | 22 | 0.3520 | 0.8511 |
| 0.2162 | 13.71 | 24 | 0.3471 | 0.8511 |
| 0.2377 | 14.86 | 26 | 0.3532 | 0.8511 |
| 0.2439 | 16.0 | 28 | 0.3551 | 0.8511 |
| 0.1815 | 16.57 | 29 | 0.3613 | 0.8511 |
| 0.2353 | 17.71 | 31 | 0.3597 | 0.8511 |
| 0.1909 | 18.86 | 33 | 0.3529 | 0.8511 |
| 0.245 | 20.0 | 35 | 0.3476 | 0.8511 |
| 0.2527 | 20.57 | 36 | 0.3426 | 0.8511 |
| 0.1868 | 21.71 | 38 | 0.3468 | 0.8511 |
| 0.1774 | 22.86 | 40 | 0.3482 | 0.8511 |
| 0.2354 | 24.0 | 42 | 0.3569 | 0.8511 |
| 0.2408 | 24.57 | 43 | 0.3567 | 0.8511 |
| 0.1957 | 25.71 | 45 | 0.3630 | 0.8511 |
| 0.176 | 26.86 | 47 | 0.3633 | 0.8511 |
| 0.1903 | 28.0 | 49 | 0.3627 | 0.8511 |
| 0.246 | 28.57 | 50 | 0.3622 | 0.8511 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
