Boya1_RMSProp_1-e5_10Epoch_Swin-tiny-patch4-window16-256_fold2
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: 1.1016
- Accuracy: 0.6365
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 |
---|---|---|---|---|
1.5087 | 1.0 | 923 | 1.4733 | 0.5070 |
1.337 | 2.0 | 1846 | 1.2429 | 0.5814 |
1.1304 | 3.0 | 2769 | 1.1472 | 0.6165 |
1.1096 | 4.0 | 3692 | 1.1410 | 0.6168 |
1.0389 | 5.0 | 4615 | 1.0969 | 0.6281 |
0.9849 | 6.0 | 5538 | 1.1056 | 0.6276 |
0.7723 | 7.0 | 6461 | 1.1130 | 0.6268 |
0.761 | 8.0 | 7384 | 1.0933 | 0.6354 |
0.7654 | 9.0 | 8307 | 1.1156 | 0.6368 |
0.6736 | 10.0 | 9230 | 1.1016 | 0.6365 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 2