--- 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-isic217 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: 0.5 --- # swin-tiny-patch4-window7-224-finetuned-isic217 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: 2.5371 - Accuracy: 0.5 ## 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: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 2.2404 | 0.9796 | 24 | 2.1527 | 0.1364 | | 2.0749 | 2.0 | 49 | 2.1159 | 0.1364 | | 1.947 | 2.9796 | 73 | 2.1723 | 0.1364 | | 1.732 | 4.0 | 98 | 2.1545 | 0.0909 | | 1.446 | 4.9796 | 122 | 2.2918 | 0.1818 | | 1.1175 | 6.0 | 147 | 1.9291 | 0.3182 | | 1.1069 | 6.9796 | 171 | 1.9551 | 0.3636 | | 0.7932 | 8.0 | 196 | 2.0534 | 0.4091 | | 0.5994 | 8.9796 | 220 | 1.8135 | 0.3636 | | 0.4671 | 10.0 | 245 | 1.7822 | 0.5455 | | 0.4612 | 10.9796 | 269 | 2.2530 | 0.5 | | 0.4016 | 12.0 | 294 | 1.8438 | 0.4091 | | 0.3947 | 12.9796 | 318 | 1.8610 | 0.5 | | 0.5033 | 14.0 | 343 | 1.8615 | 0.4545 | | 0.2846 | 14.9796 | 367 | 1.5479 | 0.5 | | 0.2828 | 16.0 | 392 | 1.6410 | 0.5455 | | 0.3426 | 16.9796 | 416 | 1.9147 | 0.3636 | | 0.3108 | 18.0 | 441 | 1.4794 | 0.5455 | | 0.2129 | 18.9796 | 465 | 1.7765 | 0.4091 | | 0.1946 | 20.0 | 490 | 2.1665 | 0.4545 | | 0.1255 | 20.9796 | 514 | 1.8522 | 0.5455 | | 0.2301 | 22.0 | 539 | 2.0289 | 0.4545 | | 0.0909 | 22.9796 | 563 | 2.0512 | 0.4091 | | 0.1724 | 24.0 | 588 | 2.3411 | 0.4091 | | 0.2256 | 24.9796 | 612 | 2.1626 | 0.5 | | 0.2471 | 26.0 | 637 | 2.0552 | 0.4091 | | 0.0671 | 26.9796 | 661 | 1.9339 | 0.5455 | | 0.2563 | 28.0 | 686 | 2.2507 | 0.4545 | | 0.1865 | 28.9796 | 710 | 2.0704 | 0.5 | | 0.0477 | 30.0 | 735 | 2.8395 | 0.3182 | | 0.0931 | 30.9796 | 759 | 2.9484 | 0.3636 | | 0.047 | 32.0 | 784 | 2.5486 | 0.4545 | | 0.165 | 32.9796 | 808 | 2.6011 | 0.4545 | | 0.0203 | 34.0 | 833 | 2.3598 | 0.5 | | 0.0143 | 34.9796 | 857 | 2.5892 | 0.4091 | | 0.0248 | 36.0 | 882 | 2.8362 | 0.4091 | | 0.0812 | 36.9796 | 906 | 2.4658 | 0.4091 | | 0.0662 | 38.0 | 931 | 2.6403 | 0.4091 | | 0.1855 | 38.9796 | 955 | 2.6042 | 0.4545 | | 0.03 | 40.0 | 980 | 2.5595 | 0.5 | | 0.1117 | 40.9796 | 1004 | 2.4716 | 0.5 | | 0.0466 | 42.0 | 1029 | 2.3257 | 0.5 | | 0.1349 | 42.9796 | 1053 | 2.5545 | 0.4545 | | 0.0069 | 44.0 | 1078 | 2.5815 | 0.5 | | 0.0468 | 44.9796 | 1102 | 2.3667 | 0.5 | | 0.1807 | 46.0 | 1127 | 2.4729 | 0.5 | | 0.0667 | 46.9796 | 1151 | 2.4969 | 0.5 | | 0.0199 | 48.0 | 1176 | 2.5521 | 0.5 | | 0.2716 | 48.9796 | 1200 | 2.5371 | 0.5 | ### Framework versions - Transformers 4.42.0.dev0 - Pytorch 2.3.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1