Downloads · 30 days
7
2% of all-time downloads
vit-base-beans_50
sarabi1005/vit-base-beans_50
vit-base-beans_50 is a image classification model from sarabi1005. 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
427
Public
Repo size
4.5 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
- Nov 3, 2023
- Updated
- Nov 3, 2023
- SHA
- 90de2a59
Base models
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-beans_50
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1514
- Accuracy: 0.9439
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 468 | 0.1514 | 0.9439 |
| 0.2863 | 2.0 | 936 | 0.1917 | 0.9303 |
| 0.2377 | 3.0 | 1404 | 0.1725 | 0.9333 |
| 0.2142 | 4.0 | 1872 | 0.1782 | 0.9288 |
| 0.2058 | 5.0 | 2340 | 0.1788 | 0.9273 |
| 0.1899 | 6.0 | 2808 | 0.1824 | 0.9318 |
| 0.1838 | 7.0 | 3276 | 0.1879 | 0.9333 |
| 0.1757 | 8.0 | 3744 | 0.2391 | 0.9333 |
| 0.1852 | 9.0 | 4212 | 0.1725 | 0.9409 |
| 0.1634 | 10.0 | 4680 | 0.1762 | 0.9394 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Nov 3, 2023
- Updated
- Nov 3, 2023