<!-- 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-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: 0.0418
- 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 |
|---|---|---|---|---|
| 0.7217 | 1.0 | 2 | 0.6974 | 0.4694 |
| 0.7049 | 2.0 | 4 | 0.6528 | 0.5714 |
| 0.6646 | 3.0 | 6 | 0.5808 | 0.7143 |
| 0.577 | 4.0 | 8 | 0.5096 | 0.8367 |
| 0.4962 | 5.0 | 10 | 0.5132 | 0.7347 |
| 0.4069 | 6.0 | 12 | 0.3272 | 0.8980 |
| 0.3052 | 7.0 | 14 | 0.4960 | 0.7143 |
| 0.3311 | 8.0 | 16 | 0.2824 | 0.8980 |
| 0.3748 | 9.0 | 18 | 0.1813 | 0.9184 |
| 0.1955 | 10.0 | 20 | 0.4383 | 0.7755 |
| 0.2198 | 11.0 | 22 | 0.1332 | 0.9388 |
| 0.2894 | 12.0 | 24 | 0.1237 | 0.9592 |
| 0.2434 | 13.0 | 26 | 0.4626 | 0.7959 |
| 0.2176 | 14.0 | 28 | 0.2051 | 0.9184 |
| 0.1928 | 15.0 | 30 | 0.1328 | 0.9592 |
| 0.1879 | 16.0 | 32 | 0.0949 | 0.9592 |
| 0.1573 | 17.0 | 34 | 0.1845 | 0.9388 |
| 0.1698 | 18.0 | 36 | 0.0908 | 0.9796 |
| 0.1489 | 19.0 | 38 | 0.0782 | 0.9592 |
| 0.1759 | 20.0 | 40 | 0.0742 | 0.9796 |
| 0.1677 | 21.0 | 42 | 0.1205 | 0.9388 |
| 0.126 | 22.0 | 44 | 0.0689 | 0.9796 |
| 0.1388 | 23.0 | 46 | 0.0727 | 0.9796 |
| 0.1277 | 24.0 | 48 | 0.0725 | 0.9592 |
| 0.1276 | 25.0 | 50 | 0.0581 | 0.9592 |
| 0.0948 | 26.0 | 52 | 0.0536 | 0.9592 |
| 0.101 | 27.0 | 54 | 0.0503 | 0.9592 |
| 0.0661 | 28.0 | 56 | 0.0958 | 0.9388 |
| 0.1274 | 29.0 | 58 | 0.1171 | 0.9388 |
| 0.0996 | 30.0 | 60 | 0.0408 | 0.9796 |
| 0.1088 | 31.0 | 62 | 0.0655 | 0.9796 |
| 0.0911 | 32.0 | 64 | 0.0832 | 0.9796 |
| 0.0983 | 33.0 | 66 | 0.0634 | 0.9592 |
| 0.1063 | 34.0 | 68 | 0.0736 | 0.9796 |
| 0.0644 | 35.0 | 70 | 0.0801 | 0.9796 |
| 0.0996 | 36.0 | 72 | 0.0835 | 0.9592 |
| 0.1564 | 37.0 | 74 | 0.0962 | 0.9592 |
| 0.1067 | 38.0 | 76 | 0.0948 | 0.9388 |
| 0.1357 | 39.0 | 78 | 0.0871 | 0.9592 |
| 0.1129 | 40.0 | 80 | 0.0755 | 0.9592 |
| 0.0858 | 41.0 | 82 | 0.0640 | 0.9592 |
| 0.0874 | 42.0 | 84 | 0.0624 | 0.9796 |
| 0.0709 | 43.0 | 86 | 0.0597 | 0.9796 |
| 0.1438 | 44.0 | 88 | 0.0561 | 0.9796 |
| 0.0645 | 45.0 | 90 | 0.0500 | 0.9796 |
| 0.1112 | 46.0 | 92 | 0.0449 | 0.9796 |
| 0.0891 | 47.0 | 94 | 0.0428 | 0.9796 |
| 0.1461 | 48.0 | 96 | 0.0418 | 1.0 |
| 0.1886 | 49.0 | 98 | 0.0413 | 1.0 |
| 0.0963 | 50.0 | 100 | 0.0412 | 0.9796 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
