--- license: apache-2.0 base_model: facebook/deit-small-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: hushem_1x_deit_small_adamax_00001_fold3 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: 0.6511627906976745 --- # hushem_1x_deit_small_adamax_00001_fold3 This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.6553 - Accuracy: 0.6512 ## 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: 1e-05 - 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 6 | 1.3641 | 0.3953 | | 1.3358 | 2.0 | 12 | 1.2934 | 0.4186 | | 1.3358 | 3.0 | 18 | 1.2307 | 0.4419 | | 1.1053 | 4.0 | 24 | 1.1728 | 0.5814 | | 0.9503 | 5.0 | 30 | 1.1200 | 0.5814 | | 0.9503 | 6.0 | 36 | 1.0691 | 0.5814 | | 0.8249 | 7.0 | 42 | 1.0268 | 0.6047 | | 0.8249 | 8.0 | 48 | 1.0002 | 0.6279 | | 0.6991 | 9.0 | 54 | 0.9588 | 0.6279 | | 0.62 | 10.0 | 60 | 0.9254 | 0.6279 | | 0.62 | 11.0 | 66 | 0.8988 | 0.6744 | | 0.5003 | 12.0 | 72 | 0.8718 | 0.6279 | | 0.5003 | 13.0 | 78 | 0.8636 | 0.6279 | | 0.4251 | 14.0 | 84 | 0.8486 | 0.6279 | | 0.3584 | 15.0 | 90 | 0.8228 | 0.6279 | | 0.3584 | 16.0 | 96 | 0.8029 | 0.6512 | | 0.2955 | 17.0 | 102 | 0.7980 | 0.6279 | | 0.2955 | 18.0 | 108 | 0.7871 | 0.6047 | | 0.2345 | 19.0 | 114 | 0.7646 | 0.6279 | | 0.2022 | 20.0 | 120 | 0.7571 | 0.6279 | | 0.2022 | 21.0 | 126 | 0.7433 | 0.6512 | | 0.1667 | 22.0 | 132 | 0.7314 | 0.6744 | | 0.1667 | 23.0 | 138 | 0.7263 | 0.6279 | | 0.1461 | 24.0 | 144 | 0.7221 | 0.6744 | | 0.1251 | 25.0 | 150 | 0.7120 | 0.6512 | | 0.1251 | 26.0 | 156 | 0.6954 | 0.6512 | | 0.1033 | 27.0 | 162 | 0.6904 | 0.6512 | | 0.1033 | 28.0 | 168 | 0.6870 | 0.6744 | | 0.0941 | 29.0 | 174 | 0.6821 | 0.6744 | | 0.0792 | 30.0 | 180 | 0.6785 | 0.6744 | | 0.0792 | 31.0 | 186 | 0.6761 | 0.6744 | | 0.0681 | 32.0 | 192 | 0.6723 | 0.6744 | | 0.0681 | 33.0 | 198 | 0.6679 | 0.6744 | | 0.0621 | 34.0 | 204 | 0.6648 | 0.6512 | | 0.0554 | 35.0 | 210 | 0.6628 | 0.6512 | | 0.0554 | 36.0 | 216 | 0.6584 | 0.6744 | | 0.0533 | 37.0 | 222 | 0.6569 | 0.6744 | | 0.0533 | 38.0 | 228 | 0.6569 | 0.6512 | | 0.0487 | 39.0 | 234 | 0.6565 | 0.6512 | | 0.0478 | 40.0 | 240 | 0.6552 | 0.6512 | | 0.0478 | 41.0 | 246 | 0.6553 | 0.6512 | | 0.0459 | 42.0 | 252 | 0.6553 | 0.6512 | | 0.0459 | 43.0 | 258 | 0.6553 | 0.6512 | | 0.0488 | 44.0 | 264 | 0.6553 | 0.6512 | | 0.0454 | 45.0 | 270 | 0.6553 | 0.6512 | | 0.0454 | 46.0 | 276 | 0.6553 | 0.6512 | | 0.0445 | 47.0 | 282 | 0.6553 | 0.6512 | | 0.0445 | 48.0 | 288 | 0.6553 | 0.6512 | | 0.0487 | 49.0 | 294 | 0.6553 | 0.6512 | | 0.0463 | 50.0 | 300 | 0.6553 | 0.6512 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1