Downloads · 30 days
82
61% of all-time downloads
algae-detr-dinov3
poglicious/algae-detr-dinov3
algae-detr-dinov3 is a object detection model from poglicious. Use it when you need objects located in an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
134
Public
Parameters
214M
16.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors857 MB · 100%
At a glance
- Task
- Object Detection
- Library
- transformers
- Model type
- detr
- Access
- Public
- Created
- Dec 2, 2025
- Updated
- Dec 4, 2025
- SHA
- be994059
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. -->
algae-detr-dinov3
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.1502
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: 1e-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: 125
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 2.0492 | 125 | 9.0295 |
| No log | 4.0984 | 250 | 8.3572 |
| No log | 6.1475 | 375 | 7.9395 |
| 7.7729 | 8.1967 | 500 | 7.5209 |
| 7.7729 | 10.2459 | 625 | 7.3253 |
| 7.7729 | 12.2951 | 750 | 7.4211 |
| 7.7729 | 14.3443 | 875 | 7.4970 |
| 4.8593 | 16.3934 | 1000 | 7.3769 |
| 4.8593 | 18.4426 | 1125 | 7.3811 |
| 4.8593 | 20.4918 | 1250 | 7.3434 |
| 4.8593 | 22.5410 | 1375 | 7.3463 |
| 3.9879 | 24.5902 | 1500 | 7.4509 |
| 3.9879 | 26.6393 | 1625 | 7.3332 |
| 3.9879 | 28.6885 | 1750 | 7.2705 |
| 3.9879 | 30.7377 | 1875 | 7.1949 |
| 3.7833 | 32.7869 | 2000 | 7.3268 |
| 3.7833 | 34.8361 | 2125 | 7.2636 |
| 3.7833 | 36.8852 | 2250 | 7.2168 |
| 3.7833 | 38.9344 | 2375 | 7.2514 |
| 3.6853 | 40.9836 | 2500 | 7.1643 |
| 3.6853 | 43.0328 | 2625 | 7.2198 |
| 3.6853 | 45.0820 | 2750 | 7.1966 |
| 3.6853 | 47.1311 | 2875 | 7.1910 |
| 3.6303 | 49.1803 | 3000 | 7.1502 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1
- Task
- Object Detection
- Library
- transformers
- Type
- detr
- Created
- Dec 2, 2025
- Updated
- Dec 4, 2025