--- license: apache-2.0 base_model: google/vit-base-patch16-224 tags: - generated_from_trainer datasets: - stanford-dogs metrics: - accuracy - f1 - precision - recall model-index: - name: google-vit-base-patch16-224-batch32-lr5e-05-standford-dogs results: - task: name: Image Classification type: image-classification dataset: name: stanford-dogs type: stanford-dogs config: default split: full args: default metrics: - name: Accuracy type: accuracy value: 0.8865403304178814 - name: F1 type: f1 value: 0.8829055367708631 - name: Precision type: precision value: 0.8892817099907323 - name: Recall type: recall value: 0.8836513270735221 --- # google-vit-base-patch16-224-batch32-lr5e-05-standford-dogs This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co./google/vit-base-patch16-224) on the stanford-dogs dataset. It achieves the following results on the evaluation set: - Loss: 0.4497 - Accuracy: 0.8865 - F1: 0.8829 - Precision: 0.8893 - Recall: 0.8837 ## 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 - training_steps: 1000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| | 4.7916 | 0.0777 | 10 | 4.5904 | 0.0328 | 0.0240 | 0.0321 | 0.0343 | | 4.5526 | 0.1553 | 20 | 4.2901 | 0.1118 | 0.0891 | 0.1068 | 0.1134 | | 4.2946 | 0.2330 | 30 | 3.9659 | 0.2602 | 0.2124 | 0.2287 | 0.2522 | | 3.9673 | 0.3107 | 40 | 3.6288 | 0.4351 | 0.3666 | 0.4093 | 0.4189 | | 3.69 | 0.3883 | 50 | 3.3225 | 0.5394 | 0.4751 | 0.5232 | 0.5244 | | 3.4705 | 0.4660 | 60 | 3.0343 | 0.6261 | 0.5750 | 0.6563 | 0.6139 | | 3.2239 | 0.5437 | 70 | 2.7671 | 0.6842 | 0.6503 | 0.7272 | 0.6743 | | 2.9986 | 0.6214 | 80 | 2.5191 | 0.7262 | 0.6971 | 0.7601 | 0.7161 | | 2.7575 | 0.6990 | 90 | 2.2953 | 0.7430 | 0.7162 | 0.7735 | 0.7333 | | 2.5923 | 0.7767 | 100 | 2.1008 | 0.7694 | 0.7470 | 0.7956 | 0.7600 | | 2.4265 | 0.8544 | 110 | 1.9250 | 0.7949 | 0.7762 | 0.8094 | 0.7863 | | 2.3049 | 0.9320 | 120 | 1.7636 | 0.8054 | 0.7861 | 0.8173 | 0.7971 | | 2.1243 | 1.0097 | 130 | 1.6290 | 0.8200 | 0.8056 | 0.8382 | 0.8125 | | 1.9721 | 1.0874 | 140 | 1.5121 | 0.8226 | 0.8084 | 0.8396 | 0.8149 | | 1.848 | 1.1650 | 150 | 1.4282 | 0.8163 | 0.8002 | 0.8362 | 0.8083 | | 1.775 | 1.2427 | 160 | 1.3034 | 0.8304 | 0.8171 | 0.8438 | 0.8238 | | 1.717 | 1.3204 | 170 | 1.2343 | 0.8275 | 0.8126 | 0.8460 | 0.8207 | | 1.6203 | 1.3981 | 180 | 1.1554 | 0.8387 | 0.8259 | 0.8552 | 0.8323 | | 1.5739 | 1.4757 | 190 | 1.0944 | 0.8484 | 0.8384 | 0.8593 | 0.8420 | | 1.5508 | 1.5534 | 200 | 1.0400 | 0.8484 | 0.8394 | 0.8574 | 0.8431 | | 1.4549 | 1.6311 | 210 | 0.9943 | 0.8452 | 0.8340 | 0.8497 | 0.8399 | | 1.3907 | 1.7087 | 220 | 0.9427 | 0.8596 | 0.8480 | 0.8627 | 0.8542 | | 1.3497 | 1.7864 | 230 | 0.8936 | 0.8569 | 0.8461 | 0.8647 | 0.8516 | | 1.2618 | 1.8641 | 240 | 0.8619 | 0.8613 | 0.8503 | 0.8671 | 0.8560 | | 1.3014 | 1.9417 | 250 | 0.8324 | 0.8603 | 0.8508 | 0.8737 | 0.8553 | | 1.2209 | 2.0194 | 260 | 0.8015 | 0.8591 | 0.8503 | 0.8645 | 0.8537 | | 1.2139 | 2.0971 | 270 | 0.7824 | 0.8596 | 0.8517 | 0.8656 | 0.8544 | | 1.1364 | 2.1748 | 280 | 0.7544 | 0.8603 | 0.8513 | 0.8611 | 0.8556 | | 1.1811 | 2.2524 | 290 | 0.7283 | 0.8683 | 0.8605 | 0.8785 | 0.8637 | | 1.1316 | 2.3301 | 300 | 0.7169 | 0.8635 | 0.8550 | 0.8653 | 0.8590 | | 1.1246 | 2.4078 | 310 | 0.6900 | 0.8686 | 0.8610 | 0.8739 | 0.8645 | | 1.1027 | 2.4854 | 320 | 0.6862 | 0.8627 | 0.8548 | 0.8730 | 0.8582 | | 1.0911 | 2.5631 | 330 | 0.6667 | 0.8693 | 0.8632 | 0.8730 | 0.8653 | | 1.0158 | 2.6408 | 340 | 0.6544 | 0.8695 | 0.8628 | 0.8751 | 0.8651 | | 1.0805 | 2.7184 | 350 | 0.6342 | 0.8703 | 0.8634 | 0.8733 | 0.8663 | | 1.0679 | 2.7961 | 360 | 0.6276 | 0.8754 | 0.8689 | 0.8797 | 0.8713 | | 1.0611 | 2.8738 | 370 | 0.6223 | 0.8746 | 0.8692 | 0.8807 | 0.8705 | | 0.9996 | 2.9515 | 380 | 0.6055 | 0.8724 | 0.8661 | 0.8758 | 0.8683 | | 1.0838 | 3.0291 | 390 | 0.6039 | 0.8715 | 0.8652 | 0.8769 | 0.8677 | | 0.9396 | 3.1068 | 400 | 0.5946 | 0.8737 | 0.8676 | 0.8791 | 0.8699 | | 0.8466 | 3.1845 | 410 | 0.5810 | 0.8717 | 0.8653 | 0.8775 | 0.8673 | | 0.9588 | 3.2621 | 420 | 0.5819 | 0.8710 | 0.8651 | 0.8766 | 0.8671 | | 0.9784 | 3.3398 | 430 | 0.5742 | 0.8754 | 0.8684 | 0.8788 | 0.8716 | | 0.9289 | 3.4175 | 440 | 0.5667 | 0.8768 | 0.8703 | 0.8792 | 0.8731 | | 0.8917 | 3.4951 | 450 | 0.5615 | 0.8724 | 0.8672 | 0.8762 | 0.8690 | | 0.8646 | 3.5728 | 460 | 0.5537 | 0.8737 | 0.8681 | 0.8761 | 0.8702 | | 0.9029 | 3.6505 | 470 | 0.5538 | 0.8732 | 0.8694 | 0.8771 | 0.8698 | | 0.9551 | 3.7282 | 480 | 0.5440 | 0.8766 | 0.8720 | 0.8809 | 0.8735 | | 0.8787 | 3.8058 | 490 | 0.5448 | 0.8751 | 0.8704 | 0.8791 | 0.8712 | | 0.9128 | 3.8835 | 500 | 0.5354 | 0.8751 | 0.8701 | 0.8799 | 0.8712 | | 0.8566 | 3.9612 | 510 | 0.5262 | 0.8776 | 0.8715 | 0.8846 | 0.8738 | | 0.8624 | 4.0388 | 520 | 0.5252 | 0.8754 | 0.8692 | 0.8840 | 0.8715 | | 0.799 | 4.1165 | 530 | 0.5197 | 0.8763 | 0.8702 | 0.8817 | 0.8723 | | 0.7912 | 4.1942 | 540 | 0.5213 | 0.8751 | 0.8695 | 0.8815 | 0.8709 | | 0.874 | 4.2718 | 550 | 0.5142 | 0.8778 | 0.8730 | 0.8862 | 0.8742 | | 0.766 | 4.3495 | 560 | 0.5019 | 0.8817 | 0.8770 | 0.8864 | 0.8783 | | 0.8902 | 4.4272 | 570 | 0.5011 | 0.8831 | 0.8785 | 0.8887 | 0.8798 | | 0.8038 | 4.5049 | 580 | 0.5014 | 0.8800 | 0.8742 | 0.8878 | 0.8762 | | 0.8893 | 4.5825 | 590 | 0.5062 | 0.8797 | 0.8744 | 0.8851 | 0.8759 | | 0.7868 | 4.6602 | 600 | 0.4926 | 0.8827 | 0.8785 | 0.8867 | 0.8791 | | 0.7733 | 4.7379 | 610 | 0.4957 | 0.8783 | 0.8749 | 0.8816 | 0.8755 | | 0.8275 | 4.8155 | 620 | 0.4871 | 0.8817 | 0.8781 | 0.8847 | 0.8785 | | 0.7944 | 4.8932 | 630 | 0.4855 | 0.8858 | 0.8823 | 0.8880 | 0.8829 | | 0.8483 | 4.9709 | 640 | 0.4849 | 0.8836 | 0.8797 | 0.8858 | 0.8803 | | 0.7297 | 5.0485 | 650 | 0.4833 | 0.8814 | 0.8779 | 0.8845 | 0.8784 | | 0.754 | 5.1262 | 660 | 0.4824 | 0.8814 | 0.8775 | 0.8844 | 0.8782 | | 0.698 | 5.2039 | 670 | 0.4806 | 0.8851 | 0.8818 | 0.8878 | 0.8821 | | 0.7515 | 5.2816 | 680 | 0.4777 | 0.8824 | 0.8791 | 0.8855 | 0.8796 | | 0.7527 | 5.3592 | 690 | 0.4711 | 0.8841 | 0.8806 | 0.8869 | 0.8808 | | 0.7287 | 5.4369 | 700 | 0.4718 | 0.8853 | 0.8819 | 0.8873 | 0.8824 | | 0.8134 | 5.5146 | 710 | 0.4680 | 0.8856 | 0.8826 | 0.8885 | 0.8828 | | 0.7655 | 5.5922 | 720 | 0.4688 | 0.8836 | 0.8795 | 0.8862 | 0.8800 | | 0.7904 | 5.6699 | 730 | 0.4671 | 0.8878 | 0.8841 | 0.8901 | 0.8846 | | 0.7257 | 5.7476 | 740 | 0.4704 | 0.8824 | 0.8790 | 0.8872 | 0.8796 | | 0.7342 | 5.8252 | 750 | 0.4641 | 0.8841 | 0.8802 | 0.8889 | 0.8810 | | 0.7075 | 5.9029 | 760 | 0.4654 | 0.8824 | 0.8782 | 0.8865 | 0.8791 | | 0.7924 | 5.9806 | 770 | 0.4619 | 0.8868 | 0.8829 | 0.8899 | 0.8839 | | 0.7176 | 6.0583 | 780 | 0.4597 | 0.8861 | 0.8815 | 0.8889 | 0.8829 | | 0.6768 | 6.1359 | 790 | 0.4595 | 0.8858 | 0.8820 | 0.8910 | 0.8827 | | 0.722 | 6.2136 | 800 | 0.4605 | 0.8836 | 0.8796 | 0.8882 | 0.8803 | | 0.7429 | 6.2913 | 810 | 0.4594 | 0.8865 | 0.8823 | 0.8912 | 0.8833 | | 0.6904 | 6.3689 | 820 | 0.4611 | 0.8856 | 0.8821 | 0.8892 | 0.8825 | | 0.7617 | 6.4466 | 830 | 0.4592 | 0.8856 | 0.8816 | 0.8879 | 0.8826 | | 0.7285 | 6.5243 | 840 | 0.4576 | 0.8863 | 0.8822 | 0.8895 | 0.8832 | | 0.686 | 6.6019 | 850 | 0.4561 | 0.8875 | 0.8834 | 0.8923 | 0.8844 | | 0.6546 | 6.6796 | 860 | 0.4561 | 0.8865 | 0.8824 | 0.8903 | 0.8835 | | 0.6526 | 6.7573 | 870 | 0.4543 | 0.8875 | 0.8830 | 0.8917 | 0.8844 | | 0.7534 | 6.8350 | 880 | 0.4537 | 0.8885 | 0.8845 | 0.8927 | 0.8855 | | 0.7065 | 6.9126 | 890 | 0.4535 | 0.8870 | 0.8831 | 0.8912 | 0.8841 | | 0.774 | 6.9903 | 900 | 0.4528 | 0.8878 | 0.8842 | 0.8924 | 0.8849 | | 0.7185 | 7.0680 | 910 | 0.4516 | 0.8880 | 0.8840 | 0.8913 | 0.8849 | | 0.6321 | 7.1456 | 920 | 0.4526 | 0.8868 | 0.8830 | 0.8900 | 0.8838 | | 0.6957 | 7.2233 | 930 | 0.4517 | 0.8865 | 0.8825 | 0.8901 | 0.8834 | | 0.6774 | 7.3010 | 940 | 0.4523 | 0.8863 | 0.8823 | 0.8895 | 0.8833 | | 0.6915 | 7.3786 | 950 | 0.4528 | 0.8853 | 0.8814 | 0.8890 | 0.8822 | | 0.6738 | 7.4563 | 960 | 0.4520 | 0.8868 | 0.8829 | 0.8901 | 0.8838 | | 0.7021 | 7.5340 | 970 | 0.4510 | 0.8863 | 0.8826 | 0.8897 | 0.8834 | | 0.7053 | 7.6117 | 980 | 0.4501 | 0.8863 | 0.8827 | 0.8885 | 0.8835 | | 0.7241 | 7.6893 | 990 | 0.4498 | 0.8865 | 0.8829 | 0.8893 | 0.8837 | | 0.703 | 7.7670 | 1000 | 0.4497 | 0.8865 | 0.8829 | 0.8893 | 0.8837 | ### Framework versions - Transformers 4.40.2 - Pytorch 2.3.0 - Datasets 2.19.1 - Tokenizers 0.19.1