Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224-in22k_fold2
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: 1.1153
- Accuracy: 0.6673
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 |
---|---|---|---|---|
1.1906 | 1.0 | 923 | 1.1736 | 0.6035 |
0.9493 | 2.0 | 1846 | 1.0241 | 0.6451 |
0.7701 | 3.0 | 2769 | 0.9552 | 0.6622 |
0.7441 | 4.0 | 3692 | 0.9760 | 0.6686 |
0.7385 | 5.0 | 4615 | 0.9832 | 0.6662 |
0.514 | 6.0 | 5538 | 1.0344 | 0.6630 |
0.4253 | 7.0 | 6461 | 1.0648 | 0.6697 |
0.3522 | 8.0 | 7384 | 1.0932 | 0.6635 |
0.3081 | 9.0 | 8307 | 1.1085 | 0.6624 |
0.2112 | 10.0 | 9230 | 1.1153 | 0.6673 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 6