Downloads · 30 days
17
3% of all-time downloads
food101-vit-dinov3
merve/food101-vit-dinov3
food101-vit-dinov3 is a image classification model from merve. Use it when you need a label for an image. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
571
Public
Parameters
85.7M
3.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- other
- Model type
- timm_wrapper
- Access
- Public
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026
- SHA
- 5dbf45a8
Base models
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. -->
food101-vit-dinov3
This model is a fine-tuned version of timm/vit_base_patch16_dinov3.lvd1689m on the ethz/food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0491
- Accuracy: 0.9865
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7454 | 1.0 | 237 | 0.2419 | 0.9493 |
| 0.3067 | 2.0 | 474 | 0.1198 | 0.9671 |
| 0.2526 | 3.0 | 711 | 0.0859 | 0.9747 |
| 0.1810 | 4.0 | 948 | 0.0706 | 0.9802 |
| 0.1365 | 5.0 | 1185 | 0.0621 | 0.9802 |
| 0.1284 | 6.0 | 1422 | 0.0648 | 0.9814 |
| 0.1034 | 7.0 | 1659 | 0.0523 | 0.9830 |
| 0.0815 | 8.0 | 1896 | 0.0566 | 0.9834 |
| 0.0810 | 9.0 | 2133 | 0.0503 | 0.9861 |
| 0.0597 | 10.0 | 2370 | 0.0491 | 0.9865 |
Framework versions
- Transformers 5.3.0.dev0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2
- Task
- Image Classification
- Library
- transformers
- Type
- timm_wrapper
- License
- other
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026