Boya1_RMSProp_1-e5_10Epoch_Swin-tiny-patch4-window16-256_fold3
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: 1.1006
- Accuracy: 0.6394
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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 |
---|---|---|---|---|
1.4066 | 1.0 | 923 | 1.4690 | 0.5053 |
1.2505 | 2.0 | 1846 | 1.2639 | 0.5659 |
1.3322 | 3.0 | 2769 | 1.1878 | 0.5875 |
1.0204 | 4.0 | 3692 | 1.1180 | 0.6208 |
0.8658 | 5.0 | 4615 | 1.0999 | 0.6235 |
0.7473 | 6.0 | 5538 | 1.1081 | 0.6273 |
0.7722 | 7.0 | 6461 | 1.0998 | 0.6316 |
0.6986 | 8.0 | 7384 | 1.1011 | 0.6375 |
0.7559 | 9.0 | 8307 | 1.1088 | 0.6311 |
0.7831 | 10.0 | 9230 | 1.1006 | 0.6394 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 14