--- license: apache-2.0 base_model: google/vit-base-patch16-224-in21k tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: meat_calssify_fresh_crop_fixed_epoch100_V_0_4 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: 0.8417721518987342 --- # meat_calssify_fresh_crop_fixed_epoch100_V_0_4 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.5888 - Accuracy: 0.8418 ## 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 - 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.0919 | 1.0 | 10 | 1.0799 | 0.3481 | | 1.0793 | 2.0 | 20 | 1.0692 | 0.4051 | | 1.0529 | 3.0 | 30 | 1.0517 | 0.4620 | | 1.0236 | 4.0 | 40 | 1.0159 | 0.5 | | 0.9714 | 5.0 | 50 | 0.9742 | 0.5506 | | 0.9373 | 6.0 | 60 | 0.9423 | 0.5949 | | 0.8579 | 7.0 | 70 | 0.9193 | 0.5443 | | 0.8111 | 8.0 | 80 | 0.8724 | 0.6329 | | 0.7735 | 9.0 | 90 | 0.8477 | 0.6329 | | 0.7259 | 10.0 | 100 | 0.8027 | 0.6329 | | 0.6595 | 11.0 | 110 | 0.7633 | 0.6646 | | 0.6254 | 12.0 | 120 | 0.7865 | 0.6582 | | 0.5348 | 13.0 | 130 | 0.7159 | 0.7025 | | 0.5617 | 14.0 | 140 | 0.8024 | 0.6519 | | 0.577 | 15.0 | 150 | 0.8290 | 0.6582 | | 0.48 | 16.0 | 160 | 0.8198 | 0.6139 | | 0.4578 | 17.0 | 170 | 0.7113 | 0.7215 | | 0.4349 | 18.0 | 180 | 0.7722 | 0.6835 | | 0.3965 | 19.0 | 190 | 0.6600 | 0.7152 | | 0.3775 | 20.0 | 200 | 0.7357 | 0.7089 | | 0.3396 | 21.0 | 210 | 0.7999 | 0.6392 | | 0.3559 | 22.0 | 220 | 0.7464 | 0.7342 | | 0.3271 | 23.0 | 230 | 0.7684 | 0.6709 | | 0.3522 | 24.0 | 240 | 0.6659 | 0.7025 | | 0.2631 | 25.0 | 250 | 0.7284 | 0.6899 | | 0.2456 | 26.0 | 260 | 0.5699 | 0.7848 | | 0.2557 | 27.0 | 270 | 0.6237 | 0.7722 | | 0.2807 | 28.0 | 280 | 0.7020 | 0.7152 | | 0.2434 | 29.0 | 290 | 0.8912 | 0.6519 | | 0.2591 | 30.0 | 300 | 0.6464 | 0.7658 | | 0.2519 | 31.0 | 310 | 0.7927 | 0.6899 | | 0.2253 | 32.0 | 320 | 0.6960 | 0.7468 | | 0.1842 | 33.0 | 330 | 0.6849 | 0.7278 | | 0.2762 | 34.0 | 340 | 0.6524 | 0.7532 | | 0.1925 | 35.0 | 350 | 0.6154 | 0.7532 | | 0.175 | 36.0 | 360 | 0.7486 | 0.7215 | | 0.2422 | 37.0 | 370 | 0.7183 | 0.7342 | | 0.1908 | 38.0 | 380 | 0.5739 | 0.7595 | | 0.1694 | 39.0 | 390 | 0.7914 | 0.7152 | | 0.1955 | 40.0 | 400 | 0.7209 | 0.7089 | | 0.2208 | 41.0 | 410 | 0.9125 | 0.6709 | | 0.2009 | 42.0 | 420 | 0.6512 | 0.7595 | | 0.2089 | 43.0 | 430 | 0.7874 | 0.7152 | | 0.1622 | 44.0 | 440 | 0.6903 | 0.7342 | | 0.1685 | 45.0 | 450 | 0.6869 | 0.7658 | | 0.1322 | 46.0 | 460 | 0.7294 | 0.7722 | | 0.1475 | 47.0 | 470 | 0.6547 | 0.7848 | | 0.155 | 48.0 | 480 | 0.6317 | 0.8038 | | 0.1491 | 49.0 | 490 | 0.8127 | 0.7152 | | 0.1534 | 50.0 | 500 | 0.7171 | 0.7595 | | 0.1721 | 51.0 | 510 | 0.6840 | 0.7658 | | 0.1408 | 52.0 | 520 | 0.6608 | 0.7785 | | 0.1512 | 53.0 | 530 | 0.7649 | 0.7405 | | 0.1279 | 54.0 | 540 | 0.6965 | 0.7595 | | 0.1338 | 55.0 | 550 | 0.7497 | 0.7342 | | 0.1249 | 56.0 | 560 | 0.6094 | 0.8038 | | 0.1358 | 57.0 | 570 | 0.6515 | 0.7785 | | 0.1105 | 58.0 | 580 | 0.5354 | 0.8038 | | 0.1222 | 59.0 | 590 | 0.6427 | 0.7848 | | 0.1137 | 60.0 | 600 | 0.5940 | 0.7975 | | 0.0942 | 61.0 | 610 | 0.8780 | 0.7278 | | 0.1082 | 62.0 | 620 | 0.6781 | 0.7785 | | 0.1017 | 63.0 | 630 | 0.6201 | 0.7848 | | 0.0803 | 64.0 | 640 | 0.6029 | 0.7785 | | 0.111 | 65.0 | 650 | 0.7350 | 0.7532 | | 0.1146 | 66.0 | 660 | 0.4995 | 0.8228 | | 0.115 | 67.0 | 670 | 0.6887 | 0.7911 | | 0.1038 | 68.0 | 680 | 0.4541 | 0.8418 | | 0.0999 | 69.0 | 690 | 0.6961 | 0.7722 | | 0.0891 | 70.0 | 700 | 0.4988 | 0.8228 | | 0.0928 | 71.0 | 710 | 0.5811 | 0.7848 | | 0.0926 | 72.0 | 720 | 0.5424 | 0.8354 | | 0.0798 | 73.0 | 730 | 0.6707 | 0.7975 | | 0.0724 | 74.0 | 740 | 0.5846 | 0.8038 | | 0.0853 | 75.0 | 750 | 0.5979 | 0.8101 | | 0.0822 | 76.0 | 760 | 0.6966 | 0.7595 | | 0.0805 | 77.0 | 770 | 0.6735 | 0.7595 | | 0.1131 | 78.0 | 780 | 0.7966 | 0.7532 | | 0.0709 | 79.0 | 790 | 0.6752 | 0.7975 | | 0.0726 | 80.0 | 800 | 0.5556 | 0.8038 | | 0.1127 | 81.0 | 810 | 0.5609 | 0.7975 | | 0.0558 | 82.0 | 820 | 0.6215 | 0.8101 | | 0.1057 | 83.0 | 830 | 0.6139 | 0.7848 | | 0.0702 | 84.0 | 840 | 0.6602 | 0.7975 | | 0.0641 | 85.0 | 850 | 0.5445 | 0.8354 | | 0.0511 | 86.0 | 860 | 0.6324 | 0.8228 | | 0.0728 | 87.0 | 870 | 0.6474 | 0.8101 | | 0.0724 | 88.0 | 880 | 0.6492 | 0.7848 | | 0.0552 | 89.0 | 890 | 0.5549 | 0.8291 | | 0.0587 | 90.0 | 900 | 0.5619 | 0.8228 | | 0.0539 | 91.0 | 910 | 0.5222 | 0.8481 | | 0.0524 | 92.0 | 920 | 0.6652 | 0.7911 | | 0.0499 | 93.0 | 930 | 0.7568 | 0.7658 | | 0.0717 | 94.0 | 940 | 0.6916 | 0.7911 | | 0.0481 | 95.0 | 950 | 0.5951 | 0.8228 | | 0.0599 | 96.0 | 960 | 0.5053 | 0.8418 | | 0.0655 | 97.0 | 970 | 0.6685 | 0.7785 | | 0.0621 | 98.0 | 980 | 0.5767 | 0.8291 | | 0.0543 | 99.0 | 990 | 0.5964 | 0.8101 | | 0.0451 | 100.0 | 1000 | 0.5888 | 0.8418 | ### Framework versions - Transformers 4.41.2 - Pytorch 2.3.1 - Datasets 2.20.0 - Tokenizers 0.19.1