--- library_name: transformers license: other base_model: apple/mobilevit-small tags: - generated_from_trainer metrics: - accuracy model-index: - name: my_awesome_food_model results: [] --- # my_awesome_food_model This model is a fine-tuned version of [apple/mobilevit-small](https://huggingface.co./apple/mobilevit-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.5132 - Accuracy: 0.8636 ## 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 - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 4.614 | 0.9829 | 43 | 4.6167 | 0.01 | | 4.5907 | 1.9886 | 87 | 4.5880 | 0.0214 | | 4.5382 | 2.9943 | 131 | 4.5343 | 0.105 | | 4.4551 | 4.0 | 175 | 4.4235 | 0.3043 | | 4.287 | 4.9829 | 218 | 4.2081 | 0.5043 | | 3.885 | 5.9886 | 262 | 3.8133 | 0.5307 | | 3.4412 | 6.9943 | 306 | 3.3131 | 0.4907 | | 2.8825 | 8.0 | 350 | 2.8045 | 0.4871 | | 2.5521 | 8.9829 | 393 | 2.3834 | 0.4671 | | 2.2911 | 9.9886 | 437 | 2.0563 | 0.5186 | | 2.0126 | 10.9943 | 481 | 1.8029 | 0.5679 | | 1.8294 | 12.0 | 525 | 1.6611 | 0.605 | | 1.745 | 12.9829 | 568 | 1.4988 | 0.6257 | | 1.6162 | 13.9886 | 612 | 1.3868 | 0.62 | | 1.5084 | 14.9943 | 656 | 1.2984 | 0.6429 | | 1.4441 | 16.0 | 700 | 1.2081 | 0.6457 | | 1.3625 | 16.9829 | 743 | 1.1554 | 0.6814 | | 1.2752 | 17.9886 | 787 | 1.0955 | 0.6929 | | 1.224 | 18.9943 | 831 | 1.0373 | 0.7164 | | 1.2096 | 20.0 | 875 | 1.0375 | 0.7164 | | 1.1551 | 20.9829 | 918 | 0.9842 | 0.7414 | | 1.1079 | 21.9886 | 962 | 0.9645 | 0.7571 | | 1.0669 | 22.9943 | 1006 | 0.9150 | 0.77 | | 1.0206 | 24.0 | 1050 | 0.8508 | 0.7836 | | 0.9963 | 24.9829 | 1093 | 0.8458 | 0.7743 | | 0.9132 | 25.9886 | 1137 | 0.7838 | 0.7971 | | 0.863 | 26.9943 | 1181 | 0.7590 | 0.8057 | | 0.8669 | 28.0 | 1225 | 0.7646 | 0.785 | | 0.8776 | 28.9829 | 1268 | 0.7084 | 0.8157 | | 0.793 | 29.9886 | 1312 | 0.6862 | 0.82 | | 0.7941 | 30.9943 | 1356 | 0.6971 | 0.8143 | | 0.7863 | 32.0 | 1400 | 0.6135 | 0.8314 | | 0.7344 | 32.9829 | 1443 | 0.5961 | 0.8407 | | 0.6888 | 33.9886 | 1487 | 0.6304 | 0.845 | | 0.6693 | 34.9943 | 1531 | 0.6011 | 0.8364 | | 0.6736 | 36.0 | 1575 | 0.5917 | 0.8364 | | 0.6739 | 36.9829 | 1618 | 0.5933 | 0.8336 | | 0.6595 | 37.9886 | 1662 | 0.5824 | 0.8357 | | 0.641 | 38.9943 | 1706 | 0.5232 | 0.8579 | | 0.576 | 40.0 | 1750 | 0.5700 | 0.8393 | | 0.6097 | 40.9829 | 1793 | 0.5384 | 0.8471 | | 0.6016 | 41.9886 | 1837 | 0.5824 | 0.8379 | | 0.6017 | 42.9943 | 1881 | 0.5511 | 0.8443 | | 0.5937 | 44.0 | 1925 | 0.5095 | 0.8621 | | 0.5674 | 44.9829 | 1968 | 0.5299 | 0.8536 | | 0.5575 | 45.9886 | 2012 | 0.5106 | 0.8507 | | 0.5709 | 46.9943 | 2056 | 0.5445 | 0.8507 | | 0.5046 | 48.0 | 2100 | 0.4848 | 0.855 | | 0.5485 | 48.9829 | 2143 | 0.5097 | 0.8564 | | 0.4865 | 49.9886 | 2187 | 0.5227 | 0.8471 | | 0.5505 | 50.9943 | 2231 | 0.5127 | 0.8507 | | 0.4827 | 52.0 | 2275 | 0.5253 | 0.8493 | | 0.5121 | 52.9829 | 2318 | 0.5095 | 0.8636 | | 0.4879 | 53.9886 | 2362 | 0.5053 | 0.8621 | | 0.5008 | 54.9943 | 2406 | 0.5196 | 0.8521 | | 0.489 | 56.0 | 2450 | 0.4834 | 0.8657 | | 0.5019 | 56.9829 | 2493 | 0.4714 | 0.8614 | | 0.4828 | 57.9886 | 2537 | 0.5019 | 0.8571 | | 0.4373 | 58.9943 | 2581 | 0.4894 | 0.8679 | | 0.4444 | 60.0 | 2625 | 0.5093 | 0.8657 | | 0.4178 | 60.9829 | 2668 | 0.5058 | 0.8614 | | 0.4081 | 61.9886 | 2712 | 0.4996 | 0.8586 | | 0.4311 | 62.9943 | 2756 | 0.4973 | 0.8557 | | 0.425 | 64.0 | 2800 | 0.4627 | 0.8743 | | 0.4147 | 64.9829 | 2843 | 0.4875 | 0.865 | | 0.4505 | 65.9886 | 2887 | 0.4918 | 0.8636 | | 0.3621 | 66.9943 | 2931 | 0.4903 | 0.86 | | 0.4072 | 68.0 | 2975 | 0.4983 | 0.8564 | | 0.3883 | 68.9829 | 3018 | 0.4635 | 0.8743 | | 0.4284 | 69.9886 | 3062 | 0.4582 | 0.8686 | | 0.3891 | 70.9943 | 3106 | 0.4456 | 0.8793 | | 0.4255 | 72.0 | 3150 | 0.4760 | 0.87 | | 0.425 | 72.9829 | 3193 | 0.4905 | 0.8721 | | 0.4301 | 73.9886 | 3237 | 0.4942 | 0.8643 | | 0.3666 | 74.9943 | 3281 | 0.4824 | 0.8629 | | 0.4275 | 76.0 | 3325 | 0.4638 | 0.8671 | | 0.4161 | 76.9829 | 3368 | 0.4859 | 0.8621 | | 0.3773 | 77.9886 | 3412 | 0.4918 | 0.8521 | | 0.3591 | 78.9943 | 3456 | 0.4881 | 0.8729 | | 0.4018 | 80.0 | 3500 | 0.4681 | 0.8707 | | 0.404 | 80.9829 | 3543 | 0.4882 | 0.86 | | 0.3987 | 81.9886 | 3587 | 0.4796 | 0.8657 | | 0.3546 | 82.9943 | 3631 | 0.4945 | 0.8643 | | 0.3795 | 84.0 | 3675 | 0.4638 | 0.8679 | | 0.4007 | 84.9829 | 3718 | 0.4624 | 0.8729 | | 0.3783 | 85.9886 | 3762 | 0.4693 | 0.8729 | | 0.3498 | 86.9943 | 3806 | 0.4980 | 0.8621 | | 0.3477 | 88.0 | 3850 | 0.4705 | 0.8671 | | 0.4022 | 88.9829 | 3893 | 0.4817 | 0.86 | | 0.3697 | 89.9886 | 3937 | 0.4763 | 0.8629 | | 0.3828 | 90.9943 | 3981 | 0.4867 | 0.8671 | | 0.3842 | 92.0 | 4025 | 0.4911 | 0.865 | | 0.3562 | 92.9829 | 4068 | 0.4562 | 0.875 | | 0.3343 | 93.9886 | 4112 | 0.4573 | 0.8786 | | 0.3521 | 94.9943 | 4156 | 0.4481 | 0.8843 | | 0.3788 | 96.0 | 4200 | 0.4793 | 0.8721 | | 0.3518 | 96.9829 | 4243 | 0.4802 | 0.8693 | | 0.3491 | 97.9886 | 4287 | 0.4740 | 0.8686 | | 0.4063 | 98.2857 | 4300 | 0.5132 | 0.8636 | ### Framework versions - Transformers 4.45.1 - Pytorch 2.4.0 - Datasets 3.0.1 - Tokenizers 0.20.0