Downloads · 30 days
3
1% of all-time downloads
vit-base-patch16-224-Trial007-008-YEL_STEM1
sbaner24/vit-base-patch16-224-Trial007-008-YEL_STEM1
vit-base-patch16-224-Trial007-008-YEL_STEM1 is a image classification model from sbaner24. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
238
Public
Repo size
16.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Aug 28, 2023
- Updated
- Aug 28, 2023
- SHA
- 8066e1b9
Datasets
Model card
From the Hugging Face model README
<!-- 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-Trial007-008-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: 0.0456
- 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 |
|---|---|---|---|---|
| 0.7332 | 1.0 | 3 | 0.6494 | 0.6026 |
| 0.6264 | 2.0 | 6 | 0.5840 | 0.6667 |
| 0.5628 | 3.0 | 9 | 0.4136 | 0.8974 |
| 0.4492 | 4.0 | 12 | 0.3312 | 0.8846 |
| 0.3883 | 5.0 | 15 | 0.2472 | 0.9487 |
| 0.2958 | 6.0 | 18 | 0.2020 | 0.9359 |
| 0.2385 | 7.0 | 21 | 0.1272 | 0.9872 |
| 0.2359 | 8.0 | 24 | 0.1009 | 0.9872 |
| 0.2642 | 9.0 | 27 | 0.0896 | 0.9872 |
| 0.1856 | 10.0 | 30 | 0.0456 | 1.0 |
| 0.2115 | 11.0 | 33 | 0.0447 | 1.0 |
| 0.2067 | 12.0 | 36 | 0.0467 | 1.0 |
| 0.2059 | 13.0 | 39 | 0.0448 | 1.0 |
| 0.2108 | 14.0 | 42 | 0.0611 | 1.0 |
| 0.173 | 15.0 | 45 | 0.0410 | 1.0 |
| 0.2053 | 16.0 | 48 | 0.0445 | 1.0 |
| 0.1619 | 17.0 | 51 | 0.0521 | 1.0 |
| 0.2343 | 18.0 | 54 | 0.0318 | 1.0 |
| 0.2097 | 19.0 | 57 | 0.0438 | 1.0 |
| 0.1832 | 20.0 | 60 | 0.0538 | 1.0 |
| 0.1687 | 21.0 | 63 | 0.0375 | 1.0 |
| 0.145 | 22.0 | 66 | 0.0340 | 1.0 |
| 0.1398 | 23.0 | 69 | 0.0394 | 1.0 |
| 0.1898 | 24.0 | 72 | 0.0450 | 1.0 |
| 0.194 | 25.0 | 75 | 0.0515 | 1.0 |
| 0.1884 | 26.0 | 78 | 0.0494 | 1.0 |
| 0.1733 | 27.0 | 81 | 0.0374 | 1.0 |
| 0.1465 | 28.0 | 84 | 0.0385 | 1.0 |
| 0.156 | 29.0 | 87 | 0.0419 | 1.0 |
| 0.1929 | 30.0 | 90 | 0.0522 | 1.0 |
| 0.1189 | 31.0 | 93 | 0.0406 | 1.0 |
| 0.1605 | 32.0 | 96 | 0.0325 | 1.0 |
| 0.1543 | 33.0 | 99 | 0.0336 | 1.0 |
| 0.175 | 34.0 | 102 | 0.0456 | 1.0 |
| 0.1542 | 35.0 | 105 | 0.0547 | 1.0 |
| 0.1957 | 36.0 | 108 | 0.0529 | 1.0 |
| 0.1671 | 37.0 | 111 | 0.0453 | 1.0 |
| 0.1826 | 38.0 | 114 | 0.0388 | 1.0 |
| 0.1804 | 39.0 | 117 | 0.0391 | 1.0 |
| 0.1346 | 40.0 | 120 | 0.0390 | 1.0 |
| 0.1684 | 41.0 | 123 | 0.0400 | 1.0 |
| 0.143 | 42.0 | 126 | 0.0418 | 1.0 |
| 0.1588 | 43.0 | 129 | 0.0415 | 1.0 |
| 0.1403 | 44.0 | 132 | 0.0425 | 1.0 |
| 0.194 | 45.0 | 135 | 0.0422 | 1.0 |
| 0.1139 | 46.0 | 138 | 0.0421 | 1.0 |
| 0.1788 | 47.0 | 141 | 0.0419 | 1.0 |
| 0.1531 | 48.0 | 144 | 0.0416 | 1.0 |
| 0.187 | 49.0 | 147 | 0.0417 | 1.0 |
| 0.1564 | 50.0 | 150 | 0.0416 | 1.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Aug 28, 2023
- Updated
- Aug 28, 2023