--- license: apache-2.0 base_model: facebook/deit-small-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: hushem_40x_deit_small_adamax_0001_fold2 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: 0.7777777777777778 --- # hushem_40x_deit_small_adamax_0001_fold2 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: 2.3727 - Accuracy: 0.7778 ## 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: 0.0001 - 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 | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.0173 | 1.0 | 215 | 1.0013 | 0.8222 | | 0.0269 | 2.0 | 430 | 1.2649 | 0.8 | | 0.0002 | 3.0 | 645 | 1.2781 | 0.7778 | | 0.0001 | 4.0 | 860 | 1.3529 | 0.8444 | | 0.0 | 5.0 | 1075 | 1.4404 | 0.7778 | | 0.0 | 6.0 | 1290 | 1.4900 | 0.7778 | | 0.0 | 7.0 | 1505 | 1.5042 | 0.7778 | | 0.0 | 8.0 | 1720 | 1.5235 | 0.8 | | 0.0 | 9.0 | 1935 | 1.5456 | 0.8 | | 0.0 | 10.0 | 2150 | 1.5663 | 0.8 | | 0.0 | 11.0 | 2365 | 1.5868 | 0.8 | | 0.0 | 12.0 | 2580 | 1.6070 | 0.8 | | 0.0 | 13.0 | 2795 | 1.6276 | 0.8 | | 0.0 | 14.0 | 3010 | 1.6480 | 0.8 | | 0.0 | 15.0 | 3225 | 1.6681 | 0.8 | | 0.0 | 16.0 | 3440 | 1.6904 | 0.8 | | 0.0 | 17.0 | 3655 | 1.7113 | 0.8 | | 0.0 | 18.0 | 3870 | 1.7306 | 0.8 | | 0.0 | 19.0 | 4085 | 1.7537 | 0.8 | | 0.0 | 20.0 | 4300 | 1.7734 | 0.8 | | 0.0 | 21.0 | 4515 | 1.7960 | 0.8 | | 0.0 | 22.0 | 4730 | 1.8166 | 0.8 | | 0.0 | 23.0 | 4945 | 1.8372 | 0.7778 | | 0.0 | 24.0 | 5160 | 1.8608 | 0.7778 | | 0.0 | 25.0 | 5375 | 1.8855 | 0.7778 | | 0.0 | 26.0 | 5590 | 1.9093 | 0.7778 | | 0.0 | 27.0 | 5805 | 1.9324 | 0.7778 | | 0.0 | 28.0 | 6020 | 1.9540 | 0.7778 | | 0.0 | 29.0 | 6235 | 1.9776 | 0.7778 | | 0.0 | 30.0 | 6450 | 2.0038 | 0.7778 | | 0.0 | 31.0 | 6665 | 2.0284 | 0.7778 | | 0.0 | 32.0 | 6880 | 2.0516 | 0.7778 | | 0.0 | 33.0 | 7095 | 2.0714 | 0.7778 | | 0.0 | 34.0 | 7310 | 2.0980 | 0.7778 | | 0.0 | 35.0 | 7525 | 2.1240 | 0.7778 | | 0.0 | 36.0 | 7740 | 2.1547 | 0.7778 | | 0.0 | 37.0 | 7955 | 2.1788 | 0.7778 | | 0.0 | 38.0 | 8170 | 2.2033 | 0.7778 | | 0.0 | 39.0 | 8385 | 2.2233 | 0.7778 | | 0.0 | 40.0 | 8600 | 2.2485 | 0.7778 | | 0.0 | 41.0 | 8815 | 2.2722 | 0.7778 | | 0.0 | 42.0 | 9030 | 2.2942 | 0.7778 | | 0.0 | 43.0 | 9245 | 2.3070 | 0.7778 | | 0.0 | 44.0 | 9460 | 2.3255 | 0.7778 | | 0.0 | 45.0 | 9675 | 2.3404 | 0.7778 | | 0.0 | 46.0 | 9890 | 2.3482 | 0.7778 | | 0.0 | 47.0 | 10105 | 2.3577 | 0.7778 | | 0.0 | 48.0 | 10320 | 2.3666 | 0.7778 | | 0.0 | 49.0 | 10535 | 2.3708 | 0.7778 | | 0.0 | 50.0 | 10750 | 2.3727 | 0.7778 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.1.0+cu121 - Datasets 2.12.0 - Tokenizers 0.13.2