--- license: apache-2.0 base_model: google/vit-base-patch16-224-in21k tags: - generated_from_trainer metrics: - accuracy model-index: - name: FASHION-vision results: [] --- # FASHION-vision This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3565 - Accuracy: 0.9122 ## 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 | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 1.463 | 1.0 | 375 | 1.4452 | 0.7076 | | 0.8341 | 2.0 | 750 | 0.8374 | 0.7926 | | 0.6173 | 3.0 | 1125 | 0.6483 | 0.8257 | | 0.5593 | 4.0 | 1500 | 0.5328 | 0.8436 | | 0.4456 | 5.0 | 1875 | 0.4808 | 0.8488 | | 0.3895 | 6.0 | 2250 | 0.4191 | 0.8617 | | 0.3257 | 7.0 | 2625 | 0.3950 | 0.8638 | | 0.3644 | 8.0 | 3000 | 0.3657 | 0.8733 | | 0.3603 | 9.0 | 3375 | 0.3515 | 0.878 | | 0.3574 | 10.0 | 3750 | 0.3482 | 0.8782 | | 0.2885 | 11.0 | 4125 | 0.3352 | 0.8823 | | 0.3217 | 12.0 | 4500 | 0.3236 | 0.8833 | | 0.2861 | 13.0 | 4875 | 0.3292 | 0.8811 | | 0.263 | 14.0 | 5250 | 0.3083 | 0.8944 | | 0.2265 | 15.0 | 5625 | 0.3035 | 0.8938 | | 0.2407 | 16.0 | 6000 | 0.3094 | 0.8897 | | 0.251 | 17.0 | 6375 | 0.3113 | 0.8894 | | 0.2251 | 18.0 | 6750 | 0.2934 | 0.8951 | | 0.2124 | 19.0 | 7125 | 0.3084 | 0.895 | | 0.1974 | 20.0 | 7500 | 0.3144 | 0.8936 | | 0.1907 | 21.0 | 7875 | 0.3048 | 0.8972 | | 0.1857 | 22.0 | 8250 | 0.3046 | 0.896 | | 0.1696 | 23.0 | 8625 | 0.3014 | 0.8982 | | 0.2066 | 24.0 | 9000 | 0.2943 | 0.8985 | | 0.2106 | 25.0 | 9375 | 0.3057 | 0.8984 | | 0.2036 | 26.0 | 9750 | 0.3103 | 0.8968 | | 0.1629 | 27.0 | 10125 | 0.3100 | 0.9003 | | 0.1711 | 28.0 | 10500 | 0.3112 | 0.8978 | | 0.144 | 29.0 | 10875 | 0.3285 | 0.897 | | 0.1738 | 30.0 | 11250 | 0.3250 | 0.8968 | | 0.1616 | 31.0 | 11625 | 0.3205 | 0.8979 | | 0.1504 | 32.0 | 12000 | 0.3321 | 0.8947 | | 0.1894 | 33.0 | 12375 | 0.3121 | 0.8963 | | 0.1346 | 34.0 | 12750 | 0.3079 | 0.9017 | | 0.1538 | 35.0 | 13125 | 0.3131 | 0.9045 | | 0.1453 | 36.0 | 13500 | 0.3180 | 0.9042 | | 0.1467 | 37.0 | 13875 | 0.3125 | 0.9042 | | 0.1667 | 38.0 | 14250 | 0.3107 | 0.9035 | | 0.1149 | 39.0 | 14625 | 0.3427 | 0.899 | | 0.1248 | 40.0 | 15000 | 0.3152 | 0.9033 | | 0.155 | 41.0 | 15375 | 0.3235 | 0.9015 | | 0.1321 | 42.0 | 15750 | 0.3220 | 0.9065 | | 0.156 | 43.0 | 16125 | 0.3326 | 0.9024 | | 0.1511 | 44.0 | 16500 | 0.3351 | 0.8988 | | 0.1039 | 45.0 | 16875 | 0.3309 | 0.9052 | | 0.1277 | 46.0 | 17250 | 0.3552 | 0.9001 | | 0.1147 | 47.0 | 17625 | 0.3462 | 0.9032 | | 0.13 | 48.0 | 18000 | 0.3374 | 0.9009 | | 0.1348 | 49.0 | 18375 | 0.3475 | 0.9006 | | 0.1188 | 50.0 | 18750 | 0.3419 | 0.9067 | | 0.1532 | 51.0 | 19125 | 0.3444 | 0.9025 | | 0.1173 | 52.0 | 19500 | 0.3387 | 0.9034 | | 0.1189 | 53.0 | 19875 | 0.3407 | 0.9033 | | 0.13 | 54.0 | 20250 | 0.3614 | 0.9016 | | 0.1206 | 55.0 | 20625 | 0.3404 | 0.9047 | | 0.0989 | 56.0 | 21000 | 0.3560 | 0.903 | | 0.1036 | 57.0 | 21375 | 0.3462 | 0.9056 | | 0.1095 | 58.0 | 21750 | 0.3497 | 0.9031 | | 0.143 | 59.0 | 22125 | 0.3364 | 0.9064 | | 0.0889 | 60.0 | 22500 | 0.3544 | 0.9047 | | 0.1008 | 61.0 | 22875 | 0.3510 | 0.904 | | 0.1343 | 62.0 | 23250 | 0.3461 | 0.9069 | | 0.1019 | 63.0 | 23625 | 0.3365 | 0.9058 | | 0.1125 | 64.0 | 24000 | 0.3372 | 0.9086 | | 0.143 | 65.0 | 24375 | 0.3433 | 0.9072 | | 0.0971 | 66.0 | 24750 | 0.3390 | 0.9102 | | 0.1147 | 67.0 | 25125 | 0.3493 | 0.9091 | | 0.0931 | 68.0 | 25500 | 0.3469 | 0.9093 | | 0.1127 | 69.0 | 25875 | 0.3421 | 0.9069 | | 0.0935 | 70.0 | 26250 | 0.3535 | 0.9058 | | 0.1152 | 71.0 | 26625 | 0.3313 | 0.9093 | | 0.1288 | 72.0 | 27000 | 0.3661 | 0.9069 | | 0.1244 | 73.0 | 27375 | 0.3405 | 0.9103 | | 0.1158 | 74.0 | 27750 | 0.3345 | 0.9104 | | 0.1255 | 75.0 | 28125 | 0.3367 | 0.9091 | | 0.0886 | 76.0 | 28500 | 0.3657 | 0.9096 | | 0.1008 | 77.0 | 28875 | 0.3468 | 0.9086 | | 0.1209 | 78.0 | 29250 | 0.3489 | 0.9096 | | 0.0944 | 79.0 | 29625 | 0.3511 | 0.9058 | | 0.0928 | 80.0 | 30000 | 0.3509 | 0.9097 | | 0.0932 | 81.0 | 30375 | 0.3485 | 0.9097 | | 0.0973 | 82.0 | 30750 | 0.3584 | 0.9075 | | 0.0964 | 83.0 | 31125 | 0.3459 | 0.9107 | | 0.1262 | 84.0 | 31500 | 0.3648 | 0.9107 | | 0.113 | 85.0 | 31875 | 0.3483 | 0.9083 | | 0.0828 | 86.0 | 32250 | 0.3396 | 0.9116 | | 0.1104 | 87.0 | 32625 | 0.3370 | 0.9119 | | 0.0804 | 88.0 | 33000 | 0.3596 | 0.9117 | | 0.0905 | 89.0 | 33375 | 0.3538 | 0.912 | | 0.1064 | 90.0 | 33750 | 0.3497 | 0.9112 | | 0.0917 | 91.0 | 34125 | 0.3392 | 0.9139 | | 0.0813 | 92.0 | 34500 | 0.3561 | 0.9109 | | 0.074 | 93.0 | 34875 | 0.3475 | 0.9098 | | 0.0922 | 94.0 | 35250 | 0.3482 | 0.9114 | | 0.0752 | 95.0 | 35625 | 0.3751 | 0.9097 | | 0.0751 | 96.0 | 36000 | 0.3530 | 0.9103 | | 0.0818 | 97.0 | 36375 | 0.3477 | 0.9137 | | 0.0677 | 98.0 | 36750 | 0.3495 | 0.9115 | | 0.0838 | 99.0 | 37125 | 0.3533 | 0.9114 | | 0.0772 | 100.0 | 37500 | 0.3565 | 0.9122 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.2 - Datasets 2.19.0 - Tokenizers 0.19.1