--- license: apache-2.0 base_model: microsoft/beit-base-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: hushem_5x_beit_base_rms_001_fold4 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: test args: default metrics: - name: Accuracy type: accuracy value: 0.7619047619047619 --- # hushem_5x_beit_base_rms_001_fold4 This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.5372 - Accuracy: 0.7619 ## 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: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - 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: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.4749 | 1.0 | 28 | 1.3999 | 0.2381 | | 1.39 | 2.0 | 56 | 1.4010 | 0.2619 | | 1.4057 | 3.0 | 84 | 1.3886 | 0.2381 | | 1.3953 | 4.0 | 112 | 1.3773 | 0.2381 | | 1.3855 | 5.0 | 140 | 1.3607 | 0.2619 | | 1.3721 | 6.0 | 168 | 1.1238 | 0.5 | | 1.2199 | 7.0 | 196 | 1.2305 | 0.4762 | | 1.1505 | 8.0 | 224 | 0.9832 | 0.4762 | | 1.1076 | 9.0 | 252 | 0.9145 | 0.5476 | | 1.04 | 10.0 | 280 | 0.9689 | 0.5476 | | 0.9947 | 11.0 | 308 | 0.8866 | 0.6429 | | 1.0266 | 12.0 | 336 | 0.8639 | 0.6905 | | 0.9955 | 13.0 | 364 | 0.8959 | 0.6190 | | 0.9564 | 14.0 | 392 | 0.8608 | 0.6667 | | 0.9123 | 15.0 | 420 | 0.7711 | 0.6905 | | 0.9391 | 16.0 | 448 | 0.7070 | 0.7619 | | 0.9117 | 17.0 | 476 | 0.7366 | 0.7619 | | 0.902 | 18.0 | 504 | 0.7650 | 0.7143 | | 0.8479 | 19.0 | 532 | 0.7181 | 0.7381 | | 0.8138 | 20.0 | 560 | 0.8337 | 0.6667 | | 0.7593 | 21.0 | 588 | 0.8325 | 0.6905 | | 0.8558 | 22.0 | 616 | 0.7211 | 0.8095 | | 0.8609 | 23.0 | 644 | 0.7758 | 0.7619 | | 0.7997 | 24.0 | 672 | 0.8535 | 0.7143 | | 0.6915 | 25.0 | 700 | 0.8962 | 0.7381 | | 0.7445 | 26.0 | 728 | 0.7116 | 0.7619 | | 0.6818 | 27.0 | 756 | 0.9464 | 0.5714 | | 0.6812 | 28.0 | 784 | 0.6802 | 0.7143 | | 0.662 | 29.0 | 812 | 1.0464 | 0.5476 | | 0.6161 | 30.0 | 840 | 0.7154 | 0.7857 | | 0.5942 | 31.0 | 868 | 0.6122 | 0.7619 | | 0.571 | 32.0 | 896 | 0.6263 | 0.7857 | | 0.5357 | 33.0 | 924 | 0.8564 | 0.8095 | | 0.4815 | 34.0 | 952 | 0.9986 | 0.7381 | | 0.5261 | 35.0 | 980 | 0.9173 | 0.8095 | | 0.3508 | 36.0 | 1008 | 1.0846 | 0.7619 | | 0.3469 | 37.0 | 1036 | 0.9412 | 0.8333 | | 0.3024 | 38.0 | 1064 | 0.9602 | 0.8333 | | 0.2908 | 39.0 | 1092 | 1.1234 | 0.8333 | | 0.2222 | 40.0 | 1120 | 1.1275 | 0.8095 | | 0.2149 | 41.0 | 1148 | 1.4618 | 0.7381 | | 0.2207 | 42.0 | 1176 | 1.3470 | 0.7857 | | 0.094 | 43.0 | 1204 | 1.5389 | 0.7619 | | 0.1227 | 44.0 | 1232 | 1.3819 | 0.7857 | | 0.0713 | 45.0 | 1260 | 1.5287 | 0.7619 | | 0.0383 | 46.0 | 1288 | 1.5676 | 0.8095 | | 0.0259 | 47.0 | 1316 | 1.4966 | 0.7857 | | 0.023 | 48.0 | 1344 | 1.5355 | 0.7619 | | 0.0304 | 49.0 | 1372 | 1.5372 | 0.7619 | | 0.0233 | 50.0 | 1400 | 1.5372 | 0.7619 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0