--- license: apache-2.0 base_model: microsoft/swin-tiny-patch4-window7-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-cp3 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.6964285714285714 --- # swin-tiny-patch4-window7-224-finetuned-cp3 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.7260 - Accuracy: 0.6964 ## 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: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 9 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 4 | 0.8084 | 0.6786 | | No log | 2.0 | 8 | 0.8043 | 0.6964 | | 0.7014 | 3.0 | 12 | 0.8072 | 0.6964 | | 0.7014 | 4.0 | 16 | 0.7646 | 0.7321 | | 0.5379 | 5.0 | 20 | 0.7575 | 0.6964 | | 0.5379 | 6.0 | 24 | 0.6960 | 0.75 | | 0.5379 | 7.0 | 28 | 0.7306 | 0.6964 | | 0.5404 | 8.0 | 32 | 0.7448 | 0.6964 | | 0.5404 | 9.0 | 36 | 0.7260 | 0.6964 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0