swin-tiny-patch4-window7-224-finetuned-landscape
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2104
- Accuracy: 0.9313
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.3423 | 0.9684 | 23 | 2.8014 | 0.2867 |
| 0.9369 | 1.9789 | 47 | 0.3964 | 0.8758 |
| 0.4031 | 2.9895 | 71 | 0.2710 | 0.9168 |
| 0.3021 | 4.0 | 95 | 0.2255 | 0.9260 |
| 0.248 | 4.9684 | 118 | 0.2175 | 0.9300 |
| 0.2465 | 5.9789 | 142 | 0.2207 | 0.9207 |
| 0.1814 | 6.9895 | 166 | 0.2162 | 0.9207 |
| 0.1806 | 8.0 | 190 | 0.1954 | 0.9392 |
| 0.1839 | 8.9684 | 213 | 0.1863 | 0.9353 |
| 0.1699 | 9.9789 | 237 | 0.1898 | 0.9366 |
| 0.1493 | 10.9895 | 261 | 0.1981 | 0.9313 |
| 0.128 | 12.0 | 285 | 0.2112 | 0.9300 |
| 0.1473 | 12.9684 | 308 | 0.2174 | 0.9353 |
| 0.1304 | 13.9789 | 332 | 0.2083 | 0.9353 |
| 0.12 | 14.9895 | 356 | 0.2050 | 0.9379 |
| 0.0987 | 16.0 | 380 | 0.2054 | 0.9339 |
| 0.1187 | 16.9684 | 403 | 0.2136 | 0.9353 |
| 0.1187 | 17.9789 | 427 | 0.2136 | 0.9326 |
| 0.1325 | 18.9895 | 451 | 0.2089 | 0.9313 |
| 0.1071 | 19.3684 | 460 | 0.2104 | 0.9313 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1