--- 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-batch64-lr0.005-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: 0.8826530612244898 - name: F1 type: f1 value: 0.8783883535916327 - name: Precision type: precision value: 0.8844388034156533 - name: Recall type: recall value: 0.8790517542275398 --- # google-vit-base-patch16-224-batch64-lr0.005-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: 0.4279 - Accuracy: 0.8827 - F1: 0.8784 - Precision: 0.8844 - Recall: 0.8791 ## 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 - training_steps: 1000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| | 4.7972 | 0.1550 | 10 | 4.5522 | 0.0510 | 0.0368 | 0.0394 | 0.0471 | | 4.4634 | 0.3101 | 20 | 4.1231 | 0.1919 | 0.1378 | 0.1493 | 0.1771 | | 4.0593 | 0.4651 | 30 | 3.6920 | 0.4014 | 0.3301 | 0.3884 | 0.3787 | | 3.6865 | 0.6202 | 40 | 3.2802 | 0.5620 | 0.5020 | 0.5568 | 0.5395 | | 3.3661 | 0.7752 | 50 | 2.9159 | 0.6489 | 0.6004 | 0.6552 | 0.6310 | | 3.0631 | 0.9302 | 60 | 2.5874 | 0.7065 | 0.6721 | 0.7353 | 0.6925 | | 2.7493 | 1.0853 | 70 | 2.3189 | 0.7320 | 0.7025 | 0.7660 | 0.7177 | | 2.5223 | 1.2403 | 80 | 2.0780 | 0.7621 | 0.7376 | 0.7863 | 0.7497 | | 2.3107 | 1.3953 | 90 | 1.8651 | 0.7760 | 0.7547 | 0.8037 | 0.7643 | | 2.079 | 1.5504 | 100 | 1.6706 | 0.7952 | 0.7776 | 0.8150 | 0.7850 | | 2.0001 | 1.7054 | 110 | 1.5130 | 0.8044 | 0.7880 | 0.8117 | 0.7951 | | 1.8082 | 1.8605 | 120 | 1.3746 | 0.8144 | 0.8036 | 0.8295 | 0.8068 | | 1.6836 | 2.0155 | 130 | 1.2598 | 0.8275 | 0.8146 | 0.8381 | 0.8200 | | 1.5852 | 2.1705 | 140 | 1.1557 | 0.8311 | 0.8203 | 0.8400 | 0.8235 | | 1.4695 | 2.3256 | 150 | 1.0706 | 0.8377 | 0.8290 | 0.8492 | 0.8303 | | 1.3991 | 2.4806 | 160 | 1.0125 | 0.8426 | 0.8327 | 0.8526 | 0.8357 | | 1.3486 | 2.6357 | 170 | 0.9519 | 0.8423 | 0.8331 | 0.8464 | 0.8364 | | 1.3257 | 2.7907 | 180 | 0.9015 | 0.8467 | 0.8365 | 0.8517 | 0.8404 | | 1.3175 | 2.9457 | 190 | 0.8607 | 0.8482 | 0.8403 | 0.8545 | 0.8424 | | 1.2188 | 3.1008 | 200 | 0.8220 | 0.8494 | 0.8400 | 0.8561 | 0.8432 | | 1.1733 | 3.2558 | 210 | 0.7847 | 0.8535 | 0.8471 | 0.8594 | 0.8483 | | 1.1245 | 3.4109 | 220 | 0.7571 | 0.8523 | 0.8467 | 0.8586 | 0.8466 | | 1.0503 | 3.5659 | 230 | 0.7358 | 0.8545 | 0.8459 | 0.8617 | 0.8492 | | 1.0812 | 3.7209 | 240 | 0.7087 | 0.8554 | 0.8455 | 0.8622 | 0.8491 | | 1.1002 | 3.8760 | 250 | 0.6906 | 0.8547 | 0.8469 | 0.8588 | 0.8490 | | 1.0258 | 4.0310 | 260 | 0.6617 | 0.8690 | 0.8634 | 0.8756 | 0.8641 | | 0.9731 | 4.1860 | 270 | 0.6541 | 0.8632 | 0.8549 | 0.8669 | 0.8577 | | 0.9641 | 4.3411 | 280 | 0.6383 | 0.8630 | 0.8556 | 0.8686 | 0.8580 | | 0.9656 | 4.4961 | 290 | 0.6161 | 0.8661 | 0.8594 | 0.8719 | 0.8611 | | 0.9798 | 4.6512 | 300 | 0.6060 | 0.8652 | 0.8609 | 0.8703 | 0.8609 | | 0.935 | 4.8062 | 310 | 0.5934 | 0.8649 | 0.8599 | 0.8694 | 0.8603 | | 0.9218 | 4.9612 | 320 | 0.5911 | 0.8659 | 0.8621 | 0.8698 | 0.8614 | | 0.9105 | 5.1163 | 330 | 0.5750 | 0.8669 | 0.8622 | 0.8689 | 0.8624 | | 0.8954 | 5.2713 | 340 | 0.5639 | 0.8690 | 0.8630 | 0.8720 | 0.8644 | | 0.8363 | 5.4264 | 350 | 0.5637 | 0.8705 | 0.8651 | 0.8714 | 0.8663 | | 0.8548 | 5.5814 | 360 | 0.5581 | 0.8654 | 0.8599 | 0.8701 | 0.8607 | | 0.7945 | 5.7364 | 370 | 0.5430 | 0.8681 | 0.8620 | 0.8692 | 0.8634 | | 0.8321 | 5.8915 | 380 | 0.5394 | 0.8698 | 0.8645 | 0.8723 | 0.8654 | | 0.8032 | 6.0465 | 390 | 0.5291 | 0.8763 | 0.8705 | 0.8776 | 0.8720 | | 0.8116 | 6.2016 | 400 | 0.5252 | 0.8688 | 0.8634 | 0.8697 | 0.8647 | | 0.7665 | 6.3566 | 410 | 0.5244 | 0.8717 | 0.8671 | 0.8739 | 0.8675 | | 0.7807 | 6.5116 | 420 | 0.5148 | 0.8734 | 0.8692 | 0.8745 | 0.8694 | | 0.7796 | 6.6667 | 430 | 0.5035 | 0.8734 | 0.8693 | 0.8761 | 0.8691 | | 0.7669 | 6.8217 | 440 | 0.5016 | 0.8756 | 0.8698 | 0.8764 | 0.8715 | | 0.78 | 6.9767 | 450 | 0.5031 | 0.8739 | 0.8686 | 0.8790 | 0.8696 | | 0.7408 | 7.1318 | 460 | 0.4984 | 0.8717 | 0.8666 | 0.8800 | 0.8681 | | 0.73 | 7.2868 | 470 | 0.4917 | 0.8737 | 0.8687 | 0.8761 | 0.8701 | | 0.7057 | 7.4419 | 480 | 0.4912 | 0.8766 | 0.8706 | 0.8795 | 0.8725 | | 0.7325 | 7.5969 | 490 | 0.4839 | 0.8795 | 0.8753 | 0.8841 | 0.8756 | | 0.6938 | 7.7519 | 500 | 0.4840 | 0.8788 | 0.8755 | 0.8834 | 0.8756 | | 0.7084 | 7.9070 | 510 | 0.4817 | 0.8744 | 0.8705 | 0.8783 | 0.8708 | | 0.7342 | 8.0620 | 520 | 0.4761 | 0.8771 | 0.8735 | 0.8798 | 0.8741 | | 0.6689 | 8.2171 | 530 | 0.4767 | 0.8746 | 0.8701 | 0.8788 | 0.8709 | | 0.6857 | 8.3721 | 540 | 0.4768 | 0.8741 | 0.8701 | 0.8774 | 0.8703 | | 0.694 | 8.5271 | 550 | 0.4723 | 0.8729 | 0.8683 | 0.8760 | 0.8688 | | 0.6821 | 8.6822 | 560 | 0.4671 | 0.8763 | 0.8727 | 0.8795 | 0.8731 | | 0.6752 | 8.8372 | 570 | 0.4618 | 0.8771 | 0.8724 | 0.8785 | 0.8733 | | 0.7315 | 8.9922 | 580 | 0.4632 | 0.8768 | 0.8721 | 0.8791 | 0.8730 | | 0.6561 | 9.1473 | 590 | 0.4552 | 0.8807 | 0.8765 | 0.8843 | 0.8768 | | 0.6302 | 9.3023 | 600 | 0.4560 | 0.8793 | 0.8751 | 0.8822 | 0.8758 | | 0.6376 | 9.4574 | 610 | 0.4586 | 0.8800 | 0.8757 | 0.8817 | 0.8769 | | 0.6397 | 9.6124 | 620 | 0.4586 | 0.8776 | 0.8730 | 0.8797 | 0.8740 | | 0.6883 | 9.7674 | 630 | 0.4532 | 0.8785 | 0.8740 | 0.8805 | 0.8748 | | 0.614 | 9.9225 | 640 | 0.4571 | 0.8763 | 0.8722 | 0.8797 | 0.8728 | | 0.6666 | 10.0775 | 650 | 0.4572 | 0.8761 | 0.8728 | 0.8801 | 0.8733 | | 0.6014 | 10.2326 | 660 | 0.4493 | 0.8812 | 0.8770 | 0.8847 | 0.8775 | | 0.6254 | 10.3876 | 670 | 0.4516 | 0.8776 | 0.8733 | 0.8808 | 0.8741 | | 0.6449 | 10.5426 | 680 | 0.4435 | 0.8810 | 0.8765 | 0.8829 | 0.8774 | | 0.6585 | 10.6977 | 690 | 0.4434 | 0.8829 | 0.8786 | 0.8854 | 0.8792 | | 0.6371 | 10.8527 | 700 | 0.4409 | 0.8812 | 0.8774 | 0.8838 | 0.8776 | | 0.6408 | 11.0078 | 710 | 0.4397 | 0.8844 | 0.8810 | 0.8867 | 0.8812 | | 0.6098 | 11.1628 | 720 | 0.4407 | 0.8824 | 0.8783 | 0.8850 | 0.8788 | | 0.5738 | 11.3178 | 730 | 0.4404 | 0.8793 | 0.8747 | 0.8811 | 0.8757 | | 0.591 | 11.4729 | 740 | 0.4399 | 0.8822 | 0.8782 | 0.8836 | 0.8788 | | 0.631 | 11.6279 | 750 | 0.4368 | 0.8812 | 0.8777 | 0.8838 | 0.8780 | | 0.5467 | 11.7829 | 760 | 0.4363 | 0.8827 | 0.8792 | 0.8852 | 0.8796 | | 0.6188 | 11.9380 | 770 | 0.4372 | 0.8817 | 0.8782 | 0.8845 | 0.8786 | | 0.6116 | 12.0930 | 780 | 0.4368 | 0.8810 | 0.8778 | 0.8836 | 0.8779 | | 0.5964 | 12.2481 | 790 | 0.4365 | 0.8814 | 0.8776 | 0.8841 | 0.8779 | | 0.547 | 12.4031 | 800 | 0.4352 | 0.8785 | 0.8742 | 0.8797 | 0.8750 | | 0.6151 | 12.5581 | 810 | 0.4331 | 0.8814 | 0.8779 | 0.8841 | 0.8784 | | 0.5889 | 12.7132 | 820 | 0.4317 | 0.8819 | 0.8786 | 0.8850 | 0.8786 | | 0.5662 | 12.8682 | 830 | 0.4301 | 0.8841 | 0.8811 | 0.8879 | 0.8810 | | 0.5806 | 13.0233 | 840 | 0.4315 | 0.8805 | 0.8768 | 0.8834 | 0.8770 | | 0.5863 | 13.1783 | 850 | 0.4291 | 0.8819 | 0.8778 | 0.8837 | 0.8787 | | 0.5704 | 13.3333 | 860 | 0.4295 | 0.8824 | 0.8786 | 0.8845 | 0.8791 | | 0.5879 | 13.4884 | 870 | 0.4293 | 0.8831 | 0.8797 | 0.8860 | 0.8797 | | 0.5824 | 13.6434 | 880 | 0.4286 | 0.8822 | 0.8784 | 0.8845 | 0.8786 | | 0.5525 | 13.7984 | 890 | 0.4289 | 0.8817 | 0.8776 | 0.8842 | 0.8780 | | 0.5781 | 13.9535 | 900 | 0.4286 | 0.8824 | 0.8783 | 0.8845 | 0.8788 | | 0.5929 | 14.1085 | 910 | 0.4282 | 0.8814 | 0.8777 | 0.8840 | 0.8779 | | 0.5374 | 14.2636 | 920 | 0.4283 | 0.8819 | 0.8779 | 0.8840 | 0.8783 | | 0.5691 | 14.4186 | 930 | 0.4297 | 0.8810 | 0.8765 | 0.8823 | 0.8774 | | 0.5406 | 14.5736 | 940 | 0.4280 | 0.8810 | 0.8767 | 0.8825 | 0.8774 | | 0.5387 | 14.7287 | 950 | 0.4274 | 0.8812 | 0.8771 | 0.8831 | 0.8778 | | 0.5501 | 14.8837 | 960 | 0.4278 | 0.8822 | 0.8780 | 0.8841 | 0.8787 | | 0.5729 | 15.0388 | 970 | 0.4280 | 0.8827 | 0.8783 | 0.8844 | 0.8791 | | 0.5373 | 15.1938 | 980 | 0.4280 | 0.8831 | 0.8789 | 0.8849 | 0.8795 | | 0.537 | 15.3488 | 990 | 0.4279 | 0.8827 | 0.8784 | 0.8844 | 0.8791 | | 0.5463 | 15.5039 | 1000 | 0.4279 | 0.8827 | 0.8784 | 0.8844 | 0.8791 | ### Framework versions - Transformers 4.40.2 - Pytorch 2.3.0 - Datasets 2.19.1 - Tokenizers 0.19.1