--- library_name: transformers 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-papsmear 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: 0.9779411764705882 --- # swin-tiny-patch4-window7-224-finetuned-papsmear 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: 0.2644 - Accuracy: 0.9779 ## 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: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 1.7081 | 0.9935 | 38 | 1.6642 | 0.2868 | | 1.4025 | 1.9869 | 76 | 1.3761 | 0.4632 | | 1.0918 | 2.9804 | 114 | 1.0276 | 0.5515 | | 0.8051 | 4.0 | 153 | 0.7679 | 0.6691 | | 0.635 | 4.9935 | 191 | 0.5928 | 0.7868 | | 0.6051 | 5.9869 | 229 | 0.6957 | 0.75 | | 0.5539 | 6.9804 | 267 | 0.5016 | 0.7941 | | 0.4683 | 8.0 | 306 | 0.4733 | 0.8235 | | 0.4153 | 8.9935 | 344 | 0.4835 | 0.8529 | | 0.3954 | 9.9869 | 382 | 0.5431 | 0.8309 | | 0.3524 | 10.9804 | 420 | 0.4061 | 0.8235 | | 0.3546 | 12.0 | 459 | 0.4925 | 0.8382 | | 0.2922 | 12.9935 | 497 | 0.3637 | 0.875 | | 0.2342 | 13.9869 | 535 | 0.3286 | 0.8971 | | 0.2083 | 14.9804 | 573 | 0.3271 | 0.8824 | | 0.2704 | 16.0 | 612 | 0.3700 | 0.8824 | | 0.1871 | 16.9935 | 650 | 0.3447 | 0.8971 | | 0.226 | 17.9869 | 688 | 0.4280 | 0.8603 | | 0.245 | 18.9804 | 726 | 0.6445 | 0.8088 | | 0.1545 | 20.0 | 765 | 0.4180 | 0.8603 | | 0.0981 | 20.9935 | 803 | 0.3208 | 0.9044 | | 0.1455 | 21.9869 | 841 | 0.4256 | 0.8603 | | 0.2405 | 22.9804 | 879 | 0.3474 | 0.8971 | | 0.1549 | 24.0 | 918 | 0.3940 | 0.9044 | | 0.1721 | 24.9935 | 956 | 0.4279 | 0.8824 | | 0.1378 | 25.9869 | 994 | 0.3871 | 0.9044 | | 0.0924 | 26.9804 | 1032 | 0.7301 | 0.8456 | | 0.1325 | 28.0 | 1071 | 0.3712 | 0.9044 | | 0.1426 | 28.9935 | 1109 | 0.4400 | 0.8603 | | 0.0866 | 29.9869 | 1147 | 0.2779 | 0.9412 | | 0.0659 | 30.9804 | 1185 | 0.3207 | 0.9412 | | 0.1175 | 32.0 | 1224 | 0.4339 | 0.9044 | | 0.0455 | 32.9935 | 1262 | 0.4537 | 0.9265 | | 0.1006 | 33.9869 | 1300 | 0.6521 | 0.875 | | 0.033 | 34.9804 | 1338 | 0.5616 | 0.9044 | | 0.0979 | 36.0 | 1377 | 0.3718 | 0.9191 | | 0.1045 | 36.9935 | 1415 | 0.2529 | 0.9632 | | 0.0815 | 37.9869 | 1453 | 0.3511 | 0.9338 | | 0.0761 | 38.9804 | 1491 | 0.3114 | 0.9338 | | 0.0747 | 40.0 | 1530 | 0.2837 | 0.9338 | | 0.0545 | 40.9935 | 1568 | 0.4269 | 0.9412 | | 0.0796 | 41.9869 | 1606 | 0.2331 | 0.9412 | | 0.055 | 42.9804 | 1644 | 0.2900 | 0.9485 | | 0.0706 | 44.0 | 1683 | 0.3368 | 0.9632 | | 0.0505 | 44.9935 | 1721 | 0.3780 | 0.9485 | | 0.0698 | 45.9869 | 1759 | 0.4822 | 0.9191 | | 0.0275 | 46.9804 | 1797 | 0.3434 | 0.9632 | | 0.0641 | 48.0 | 1836 | 0.3387 | 0.9706 | | 0.0484 | 48.9935 | 1874 | 0.5350 | 0.9191 | | 0.0388 | 49.9869 | 1912 | 0.3826 | 0.9118 | | 0.0347 | 50.9804 | 1950 | 0.3739 | 0.9559 | | 0.1046 | 52.0 | 1989 | 0.3075 | 0.9118 | | 0.0298 | 52.9935 | 2027 | 0.3558 | 0.9559 | | 0.0478 | 53.9869 | 2065 | 0.3056 | 0.9706 | | 0.0285 | 54.9804 | 2103 | 0.2851 | 0.9632 | | 0.0407 | 56.0 | 2142 | 0.3223 | 0.9559 | | 0.0459 | 56.9935 | 2180 | 0.4575 | 0.9485 | | 0.0409 | 57.9869 | 2218 | 0.2930 | 0.9632 | | 0.0743 | 58.9804 | 2256 | 0.4032 | 0.9485 | | 0.0346 | 60.0 | 2295 | 0.3738 | 0.9412 | | 0.0302 | 60.9935 | 2333 | 0.3597 | 0.9485 | | 0.0488 | 61.9869 | 2371 | 0.2595 | 0.9559 | | 0.0562 | 62.9804 | 2409 | 0.3764 | 0.9412 | | 0.0216 | 64.0 | 2448 | 0.2644 | 0.9779 | | 0.0219 | 64.9935 | 2486 | 0.3092 | 0.9632 | | 0.0272 | 65.9869 | 2524 | 0.2898 | 0.9632 | | 0.027 | 66.9804 | 2562 | 0.2693 | 0.9632 | | 0.0397 | 68.0 | 2601 | 0.3843 | 0.9412 | | 0.0154 | 68.9935 | 2639 | 0.3051 | 0.9485 | | 0.0004 | 69.9869 | 2677 | 0.3909 | 0.9412 | | 0.0651 | 70.9804 | 2715 | 0.2977 | 0.9485 | | 0.016 | 72.0 | 2754 | 0.2695 | 0.9632 | | 0.0351 | 72.9935 | 2792 | 0.2720 | 0.9706 | | 0.0206 | 73.9869 | 2830 | 0.2549 | 0.9706 | | 0.0109 | 74.9804 | 2868 | 0.2412 | 0.9706 | | 0.0012 | 76.0 | 2907 | 0.3494 | 0.9779 | | 0.0418 | 76.9935 | 2945 | 0.3729 | 0.9632 | | 0.0165 | 77.9869 | 2983 | 0.3471 | 0.9632 | | 0.0163 | 78.9804 | 3021 | 0.2973 | 0.9706 | | 0.0202 | 80.0 | 3060 | 0.3730 | 0.9559 | | 0.0368 | 80.9935 | 3098 | 0.2877 | 0.9706 | | 0.0374 | 81.9869 | 3136 | 0.4143 | 0.9632 | | 0.0296 | 82.9804 | 3174 | 0.2895 | 0.9779 | | 0.0405 | 84.0 | 3213 | 0.2927 | 0.9559 | | 0.0097 | 84.9935 | 3251 | 0.3179 | 0.9632 | | 0.0182 | 85.9869 | 3289 | 0.3047 | 0.9706 | | 0.0207 | 86.9804 | 3327 | 0.3018 | 0.9779 | | 0.0207 | 88.0 | 3366 | 0.3321 | 0.9632 | | 0.003 | 88.9935 | 3404 | 0.3086 | 0.9706 | | 0.0157 | 89.9869 | 3442 | 0.2948 | 0.9706 | | 0.0428 | 90.9804 | 3480 | 0.3175 | 0.9706 | | 0.0189 | 92.0 | 3519 | 0.3240 | 0.9632 | | 0.0046 | 92.9935 | 3557 | 0.3414 | 0.9632 | | 0.0057 | 93.9869 | 3595 | 0.3329 | 0.9632 | | 0.0165 | 94.9804 | 3633 | 0.3240 | 0.9632 | | 0.006 | 96.0 | 3672 | 0.3180 | 0.9706 | | 0.0172 | 96.9935 | 3710 | 0.3103 | 0.9779 | | 0.0109 | 97.9869 | 3748 | 0.3035 | 0.9779 | | 0.0172 | 98.9804 | 3786 | 0.3034 | 0.9779 | | 0.0219 | 99.3464 | 3800 | 0.3036 | 0.9779 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.0+cu118 - Datasets 2.21.0 - Tokenizers 0.19.1