dinov2-Base-finetuned-food101
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: 0.0924
- Accuracy: 0.98
- F1: 0.9809
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 | F1 |
|---|---|---|---|---|---|
| 0.675 | 1.0 | 625 | 0.1778 | 0.938 | 0.9399 |
| 0.5284 | 2.0 | 1250 | 0.1248 | 0.9613 | 0.9615 |
| 0.3455 | 3.0 | 1875 | 0.1548 | 0.9513 | 0.9523 |
| 0.1915 | 4.0 | 2500 | 0.1321 | 0.9567 | 0.9586 |
| 0.1953 | 5.0 | 3125 | 0.0772 | 0.978 | 0.9784 |
| 0.183 | 6.0 | 3750 | 0.0829 | 0.9773 | 0.9781 |
| 0.1513 | 7.0 | 4375 | 0.1134 | 0.972 | 0.9735 |
| 0.1222 | 8.0 | 5000 | 0.1164 | 0.972 | 0.9729 |
| 0.2001 | 9.0 | 5625 | 0.0865 | 0.9773 | 0.9783 |
| 0.0618 | 10.0 | 6250 | 0.0924 | 0.98 | 0.9809 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1