2025-01-21-15-57-43-swin-base-patch4-window7-224
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0384
- Precision: 0.9928
- Recall: 0.9926
- F1: 0.9926
- Accuracy: 0.992
- Top1 Accuracy: 0.9926
- Error Rate: 0.0080
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 3407
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|---|---|---|---|---|---|---|---|---|---|
| 0.732 | 1.0 | 34 | 0.3980 | 0.9165 | 0.8741 | 0.8590 | 0.8649 | 0.8741 | 0.1351 |
| 0.2462 | 2.0 | 68 | 0.1051 | 0.9538 | 0.9481 | 0.9484 | 0.9499 | 0.9481 | 0.0501 |
| 0.1991 | 3.0 | 102 | 0.0384 | 0.9928 | 0.9926 | 0.9926 | 0.992 | 0.9926 | 0.0080 |
| 0.1559 | 4.0 | 136 | 0.0890 | 0.9802 | 0.9778 | 0.9780 | 0.9777 | 0.9778 | 0.0223 |
| 0.1024 | 5.0 | 170 | 0.1092 | 0.9863 | 0.9852 | 0.9852 | 0.9846 | 0.9852 | 0.0154 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3