--- license: apache-2.0 base_model: microsoft/swin-base-patch4-window7-224-in22k tags: - generated_from_trainer datasets: - imagefolder model-index: - name: swin-base-patch4-window7-224-in22k-Kontur-competition-1.3K results: [] --- # swin-base-patch4-window7-224-in22k-Kontur-competition-1.3K This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0036 ## 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 | |:-------------:|:-----:|:----:|:---------------:| | 0.0593 | 0.99 | 55 | 0.0294 | | 0.0098 | 1.99 | 111 | 0.0315 | | 0.0066 | 3.0 | 167 | 0.0322 | | 0.0179 | 4.0 | 223 | 0.0068 | | 0.0078 | 4.99 | 278 | 0.0033 | | 0.0015 | 5.99 | 334 | 0.0008 | | 0.0017 | 7.0 | 390 | 0.0078 | | 0.0008 | 8.0 | 446 | 0.0027 | | 0.0019 | 8.99 | 501 | 0.0011 | | 0.0014 | 9.87 | 550 | 0.0036 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2