Downloads · 30 days
11
2% of all-time downloads
vit-base-5e-4
vuongnhathien/vit-base-5e-4
vit-base-5e-4 is a image classification model from vuongnhathien. 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
499
Public
Parameters
85.8M
3.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- May 21, 2024
- Updated
- May 21, 2024
- SHA
- ccb0d48a
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-5e-4
This model is a fine-tuned version of google/vit-base-patch16-224 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:
- Loss: 0.6221
- Accuracy: 0.8683
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7552 | 1.0 | 275 | 0.7489 | 0.7849 |
| 0.4161 | 2.0 | 550 | 0.6816 | 0.8127 |
| 0.2389 | 3.0 | 825 | 0.6486 | 0.8326 |
| 0.1523 | 4.0 | 1100 | 0.6459 | 0.8414 |
| 0.0917 | 5.0 | 1375 | 0.7039 | 0.8382 |
| 0.0492 | 6.0 | 1650 | 0.7023 | 0.8425 |
| 0.0175 | 7.0 | 1925 | 0.6089 | 0.8664 |
| 0.009 | 8.0 | 2200 | 0.5864 | 0.8775 |
| 0.0026 | 9.0 | 2475 | 0.5646 | 0.8783 |
| 0.0037 | 10.0 | 2750 | 0.5681 | 0.8803 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- May 21, 2024
- Updated
- May 21, 2024