Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224-in22k_fold4
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: 1.1431
- Accuracy: 0.6724
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 |
---|---|---|---|---|
1.1565 | 1.0 | 924 | 1.1090 | 0.6212 |
0.952 | 2.0 | 1848 | 0.9958 | 0.6527 |
0.7659 | 3.0 | 2772 | 0.9710 | 0.6689 |
0.7157 | 4.0 | 3696 | 0.9729 | 0.6716 |
0.6176 | 5.0 | 4620 | 0.9826 | 0.6741 |
0.4164 | 6.0 | 5544 | 1.0267 | 0.6781 |
0.4123 | 7.0 | 6468 | 1.0495 | 0.6792 |
0.3897 | 8.0 | 7392 | 1.1038 | 0.6722 |
0.3475 | 9.0 | 8316 | 1.1150 | 0.6771 |
0.2993 | 10.0 | 9240 | 1.1431 | 0.6724 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 19