swin-tiny-patch4-window7-224-finetuned-food
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8634
- Accuracy: 0.7658
- Precision: 0.7666
- Recall: 0.7658
- F1: 0.7642
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.5913 | 1.0 | 533 | 1.3114 | 0.6644 | 0.6822 | 0.6644 | 0.6647 |
| 1.1933 | 2.0 | 1066 | 1.0088 | 0.7316 | 0.7387 | 0.7316 | 0.7295 |
| 1.1155 | 3.0 | 1599 | 0.8975 | 0.7597 | 0.7627 | 0.7597 | 0.7582 |
| 1.0423 | 4.0 | 2132 | 0.8634 | 0.7658 | 0.7666 | 0.7658 | 0.7642 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4