Boya1_RMSProp_1-e5_10Epoch_swinv2-tiny-patch4-window16-256_fold3
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window16-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0008
- Accuracy: 0.6562
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 |
---|---|---|---|---|
1.495 | 1.0 | 923 | 1.4345 | 0.5207 |
1.3175 | 2.0 | 1846 | 1.2061 | 0.5953 |
1.2659 | 3.0 | 2769 | 1.1111 | 0.6154 |
1.0775 | 4.0 | 3692 | 1.0599 | 0.6343 |
0.9198 | 5.0 | 4615 | 1.0400 | 0.6443 |
0.9183 | 6.0 | 5538 | 1.0344 | 0.6440 |
0.869 | 7.0 | 6461 | 1.0165 | 0.6546 |
0.8871 | 8.0 | 7384 | 1.0264 | 0.6451 |
0.9047 | 9.0 | 8307 | 0.9953 | 0.6567 |
0.8868 | 10.0 | 9230 | 1.0008 | 0.6562 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 6