2025-02-05-15-01-55-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: 0.0147
- Precision: 0.9953
- Recall: 0.9951
- F1: 0.9951
- Accuracy: 0.9947
- Top1 Accuracy: 0.9951
- Error Rate: 0.0053
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.8621 | 1.0 | 103 | 0.2049 | 0.9405 | 0.9220 | 0.9233 | 0.9284 | 0.9220 | 0.0716 |
| 0.3112 | 2.0 | 206 | 0.1944 | 0.9579 | 0.9537 | 0.9511 | 0.9419 | 0.9537 | 0.0581 |
| 0.1598 | 3.0 | 309 | 0.1673 | 0.9635 | 0.9610 | 0.9610 | 0.9627 | 0.9610 | 0.0373 |
| 0.1019 | 4.0 | 412 | 0.0472 | 0.9856 | 0.9854 | 0.9853 | 0.9858 | 0.9854 | 0.0142 |
| 0.0779 | 5.0 | 515 | 0.3869 | 0.9388 | 0.9268 | 0.9246 | 0.9236 | 0.9268 | 0.0764 |
| 0.0519 | 6.0 | 618 | 0.0224 | 0.9858 | 0.9854 | 0.9852 | 0.9852 | 0.9854 | 0.0148 |
| 0.0477 | 7.0 | 721 | 0.0402 | 0.9887 | 0.9878 | 0.9879 | 0.9885 | 0.9878 | 0.0115 |
| 0.0086 | 8.0 | 824 | 0.0147 | 0.9953 | 0.9951 | 0.9951 | 0.9947 | 0.9951 | 0.0053 |
| 0.0052 | 9.0 | 927 | 0.0177 | 0.9953 | 0.9951 | 0.9951 | 0.9947 | 0.9951 | 0.0053 |
| 0.0022 | 10.0 | 1030 | 0.0180 | 0.9953 | 0.9951 | 0.9951 | 0.9947 | 0.9951 | 0.0053 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.3