--- 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_adamax_001_fold1 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: 0.4444444444444444 --- # hushem_5x_beit_base_adamax_001_fold1 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: 6.2787 - Accuracy: 0.4444 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.4418 | 1.0 | 27 | 1.4079 | 0.2444 | | 1.2606 | 2.0 | 54 | 1.4566 | 0.4 | | 1.1141 | 3.0 | 81 | 1.4147 | 0.3111 | | 0.9738 | 4.0 | 108 | 1.7371 | 0.3556 | | 0.7887 | 5.0 | 135 | 1.5516 | 0.3778 | | 0.7198 | 6.0 | 162 | 1.3626 | 0.4 | | 0.8269 | 7.0 | 189 | 1.5448 | 0.3778 | | 0.8171 | 8.0 | 216 | 1.4576 | 0.4 | | 0.7255 | 9.0 | 243 | 2.3915 | 0.3778 | | 0.6369 | 10.0 | 270 | 1.6627 | 0.3778 | | 0.6809 | 11.0 | 297 | 1.5201 | 0.3556 | | 0.6237 | 12.0 | 324 | 1.3289 | 0.4222 | | 0.6768 | 13.0 | 351 | 1.6115 | 0.3556 | | 0.6336 | 14.0 | 378 | 2.0397 | 0.3778 | | 0.5238 | 15.0 | 405 | 1.5857 | 0.3778 | | 0.5016 | 16.0 | 432 | 1.4047 | 0.4444 | | 0.4321 | 17.0 | 459 | 2.2039 | 0.3556 | | 0.4791 | 18.0 | 486 | 2.3823 | 0.3778 | | 0.484 | 19.0 | 513 | 1.4706 | 0.4222 | | 0.4812 | 20.0 | 540 | 1.6485 | 0.4222 | | 0.4413 | 21.0 | 567 | 1.7092 | 0.4 | | 0.4306 | 22.0 | 594 | 1.8582 | 0.4 | | 0.37 | 23.0 | 621 | 1.8653 | 0.3778 | | 0.3048 | 24.0 | 648 | 1.6342 | 0.4444 | | 0.3515 | 25.0 | 675 | 1.5211 | 0.4889 | | 0.3558 | 26.0 | 702 | 1.9714 | 0.4222 | | 0.2599 | 27.0 | 729 | 1.7243 | 0.4667 | | 0.267 | 28.0 | 756 | 1.7049 | 0.5111 | | 0.2625 | 29.0 | 783 | 2.1704 | 0.4222 | | 0.2368 | 30.0 | 810 | 2.2942 | 0.4667 | | 0.2036 | 31.0 | 837 | 2.0691 | 0.4667 | | 0.1938 | 32.0 | 864 | 2.7340 | 0.4 | | 0.1597 | 33.0 | 891 | 3.0661 | 0.4 | | 0.1166 | 34.0 | 918 | 2.8536 | 0.4667 | | 0.1248 | 35.0 | 945 | 2.9508 | 0.4444 | | 0.121 | 36.0 | 972 | 3.2153 | 0.4667 | | 0.0801 | 37.0 | 999 | 3.0021 | 0.4222 | | 0.0529 | 38.0 | 1026 | 3.3247 | 0.4222 | | 0.0434 | 39.0 | 1053 | 4.0394 | 0.4667 | | 0.0599 | 40.0 | 1080 | 4.1062 | 0.4889 | | 0.0437 | 41.0 | 1107 | 5.3485 | 0.4667 | | 0.0045 | 42.0 | 1134 | 5.3122 | 0.4667 | | 0.0368 | 43.0 | 1161 | 5.1937 | 0.4667 | | 0.0032 | 44.0 | 1188 | 5.6803 | 0.4889 | | 0.0061 | 45.0 | 1215 | 5.8620 | 0.4444 | | 0.0035 | 46.0 | 1242 | 5.9016 | 0.4889 | | 0.0011 | 47.0 | 1269 | 6.3136 | 0.4444 | | 0.0277 | 48.0 | 1296 | 6.2816 | 0.4444 | | 0.0067 | 49.0 | 1323 | 6.2787 | 0.4444 | | 0.0372 | 50.0 | 1350 | 6.2787 | 0.4444 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0