dinov2-small-imagenet1k-1-layer-finetuned-noh
This model is a fine-tuned version of facebook/dinov2-small-imagenet1k-1-layer on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3366
- Accuracy: 0.8982
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4924 | 1.0 | 23 | 0.5212 | 0.8325 |
| 0.5732 | 2.0 | 46 | 0.3366 | 0.8982 |
| 0.5639 | 3.0 | 69 | 0.3907 | 0.8489 |
| 0.4759 | 4.0 | 92 | 0.3482 | 0.8818 |
| 0.3757 | 5.0 | 115 | 0.3921 | 0.8276 |
| 0.3356 | 6.0 | 138 | 0.3184 | 0.8966 |
| 0.2521 | 7.0 | 161 | 0.3992 | 0.8571 |
| 0.2981 | 8.0 | 184 | 0.3904 | 0.8703 |
| 0.2302 | 9.0 | 207 | 0.3987 | 0.8719 |
| 0.1979 | 9.5778 | 220 | 0.4129 | 0.8604 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.21.0