Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224-in22k_fold1
This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1301
- Accuracy: 0.6725
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 |
---|---|---|---|---|
1.1237 | 1.0 | 924 | 1.1144 | 0.6155 |
0.9104 | 2.0 | 1848 | 1.0071 | 0.6573 |
0.9378 | 3.0 | 2772 | 0.9651 | 0.6594 |
0.6329 | 4.0 | 3696 | 1.0109 | 0.6586 |
0.5953 | 5.0 | 4620 | 0.9971 | 0.6706 |
0.5464 | 6.0 | 5544 | 1.0303 | 0.6733 |
0.3752 | 7.0 | 6468 | 1.0788 | 0.6727 |
0.3097 | 8.0 | 7392 | 1.1089 | 0.6632 |
0.2989 | 9.0 | 8316 | 1.1196 | 0.6670 |
0.2507 | 10.0 | 9240 | 1.1301 | 0.6725 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 6