dinov2
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: 0.1138
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: 16
- eval_batch_size: 16
- 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9473 | 1.0 | 77 | 0.7374 |
| 0.6697 | 2.0 | 154 | 0.7297 |
| 0.5216 | 3.0 | 231 | 0.3634 |
| 0.4556 | 4.0 | 308 | 0.2862 |
| 0.4327 | 5.0 | 385 | 0.2512 |
| 0.3648 | 6.0 | 462 | 0.1751 |
| 0.3502 | 7.0 | 539 | 0.2137 |
| 0.3050 | 8.0 | 616 | 0.1458 |
| 0.2986 | 9.0 | 693 | 0.1499 |
| 0.2415 | 10.0 | 770 | 0.1138 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2