swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-2000
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: 1.2884
- Accuracy: 0.575
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6771 | 0.9912 | 28 | 0.7267 | 0.5225 |
0.519 | 1.9823 | 56 | 0.9883 | 0.5275 |
0.3645 | 2.9735 | 84 | 1.1386 | 0.5575 |
0.3797 | 4.0 | 113 | 2.1208 | 0.525 |
0.3047 | 4.9912 | 141 | 1.2884 | 0.575 |
0.3335 | 5.9823 | 169 | 2.0830 | 0.5325 |
0.3022 | 6.9735 | 197 | 1.8196 | 0.5375 |
0.2444 | 8.0 | 226 | 1.6744 | 0.5475 |
0.2283 | 8.9912 | 254 | 2.3540 | 0.535 |
0.2282 | 9.9115 | 280 | 2.3509 | 0.535 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 21