Downloads · 30 days
10
21% of all-time downloads
output_dinov2_v1
buddhadeb33/output_dinov2_v1
output_dinov2_v1 is a image classification model from buddhadeb33. 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
48
Public
Parameters
86.6M
346 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors346 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- dinov2
- Access
- Public
- Created
- Feb 2, 2026
- Updated
- Feb 2, 2026
- SHA
- 69a8ba1e
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. -->
output_dinov2_v1
This model is a fine-tuned version of facebook/dinov2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1976
- Precision: 0.9810
- Recall: 0.9769
- F1: 0.9789
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 1.0519 | 1.0 | 145 | 0.3207 | 0.8797 | 0.9296 | 0.9040 |
| 0.3290 | 2.0 | 290 | 0.1270 | 0.9210 | 0.9800 | 0.9496 |
| 0.1709 | 3.0 | 435 | 0.1169 | 0.96 | 0.9832 | 0.9715 |
| 0.0549 | 4.0 | 580 | 0.1629 | 0.9718 | 0.9790 | 0.9754 |
| 0.1591 | 5.0 | 725 | 0.1887 | 0.9789 | 0.9748 | 0.9768 |
| 0.5929 | 6.0 | 870 | 0.1558 | 0.9810 | 0.9779 | 0.9795 |
| 0.2396 | 7.0 | 1015 | 0.1923 | 0.9768 | 0.9737 | 0.9753 |
| 0.0075 | 8.0 | 1160 | 0.1979 | 0.9789 | 0.9758 | 0.9774 |
| 0.1968 | 9.0 | 1305 | 0.2093 | 0.9820 | 0.9727 | 0.9773 |
| 0.0308 | 10.0 | 1450 | 0.1976 | 0.9810 | 0.9769 | 0.9789 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Task
- Image Classification
- Library
- transformers
- Type
- dinov2
- License
- apache-2.0
- Created
- Feb 2, 2026
- Updated
- Feb 2, 2026