swin-base-patch4-window7-224-in22k-Kontur-competition-1.2K
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0200
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
|---|---|---|---|
| No log | 0.94 | 4 | 0.5851 |
| No log | 1.88 | 8 | 0.2724 |
| 0.5032 | 2.82 | 12 | 0.1171 |
| 0.5032 | 4.0 | 17 | 0.0423 |
| 0.0697 | 4.94 | 21 | 0.0949 |
| 0.0697 | 5.88 | 25 | 0.0200 |
| 0.0697 | 6.82 | 29 | 0.0771 |
| 0.0221 | 8.0 | 34 | 0.1412 |
| 0.0221 | 8.94 | 38 | 0.1106 |
| 0.0131 | 9.41 | 40 | 0.1085 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2