Downloads · 30 days
4
3% of all-time downloads
dinov2-base-finetuned-SkinDisease
RushnaFathima/dinov2-base-finetuned-SkinDisease
dinov2-base-finetuned-SkinDisease is a image classification model from RushnaFathima. 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
145
Public
Parameters
86.6M
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors347 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- dinov2
- Access
- Public
- Created
- Jun 10, 2026
- Updated
- Jun 10, 2026
- SHA
- ebee8247
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. -->
dinov2-base-finetuned-SkinDisease
This model is a fine-tuned version of facebook/dinov2-base on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0419
- Accuracy: 0.8739
- Precision: 0.8857
- Recall: 0.8674
- F1 Macro: 0.8739
- F1 Weighted: 0.873
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Macro | F1 Weighted |
|---|---|---|---|---|---|---|---|---|
| 4.4724 | 1.0 | 83 | 1.5323 | 0.6862 | 0.7616 | 0.7242 | 0.6951 | 0.6781 |
| 3.4639 | 2.0 | 166 | 1.2999 | 0.7933 | 0.8467 | 0.8179 | 0.8146 | 0.7985 |
| 3.1461 | 3.0 | 249 | 1.1596 | 0.824 | 0.8302 | 0.8288 | 0.8207 | 0.8216 |
| 2.9459 | 4.0 | 332 | 1.1939 | 0.8372 | 0.8607 | 0.8284 | 0.834 | 0.8292 |
| 2.8444 | 5.0 | 415 | 1.1071 | 0.8548 | 0.8714 | 0.8574 | 0.8595 | 0.8563 |
| 2.8095 | 6.0 | 498 | 1.0869 | 0.8666 | 0.8708 | 0.8573 | 0.8615 | 0.8655 |
| 2.7422 | 7.0 | 581 | 1.0986 | 0.8578 | 0.8766 | 0.8504 | 0.8575 | 0.8564 |
| 2.7111 | 8.0 | 664 | 1.0545 | 0.8739 | 0.8856 | 0.8736 | 0.877 | 0.8725 |
| 2.6990 | 9.0 | 747 | 1.0656 | 0.871 | 0.8829 | 0.8608 | 0.8673 | 0.8692 |
| 2.4949 | 10.0 | 830 | 1.0419 | 0.8739 | 0.8857 | 0.8674 | 0.8739 | 0.873 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.10.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2
- Task
- Image Classification
- Library
- transformers
- Type
- dinov2
- License
- apache-2.0
- Created
- Jun 10, 2026
- Updated
- Jun 10, 2026