--- license: apache-2.0 base_model: facebook/deit-base-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: hushem_40x_deit_base_rms_0001_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: 0.9523809523809523 --- # hushem_40x_deit_base_rms_0001_fold4 This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.3583 - Accuracy: 0.9524 ## 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 | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.104 | 1.0 | 219 | 0.2949 | 0.9286 | | 0.01 | 2.0 | 438 | 0.1700 | 0.9524 | | 0.0196 | 3.0 | 657 | 0.6452 | 0.8571 | | 0.0007 | 4.0 | 876 | 0.1624 | 0.9762 | | 0.0273 | 5.0 | 1095 | 0.4258 | 0.9048 | | 0.0129 | 6.0 | 1314 | 0.1517 | 0.9524 | | 0.0582 | 7.0 | 1533 | 0.6754 | 0.9048 | | 0.0004 | 8.0 | 1752 | 0.2532 | 0.9286 | | 0.0 | 9.0 | 1971 | 0.2443 | 0.9286 | | 0.0 | 10.0 | 2190 | 0.2524 | 0.9286 | | 0.0 | 11.0 | 2409 | 0.2616 | 0.9286 | | 0.0 | 12.0 | 2628 | 0.2792 | 0.9286 | | 0.0 | 13.0 | 2847 | 0.2936 | 0.9524 | | 0.0 | 14.0 | 3066 | 0.3043 | 0.9524 | | 0.0 | 15.0 | 3285 | 0.3082 | 0.9524 | | 0.0 | 16.0 | 3504 | 0.3110 | 0.9524 | | 0.0 | 17.0 | 3723 | 0.3145 | 0.9524 | | 0.0 | 18.0 | 3942 | 0.3171 | 0.9524 | | 0.0 | 19.0 | 4161 | 0.3231 | 0.9524 | | 0.0 | 20.0 | 4380 | 0.3294 | 0.9524 | | 0.0 | 21.0 | 4599 | 0.3348 | 0.9524 | | 0.0 | 22.0 | 4818 | 0.3389 | 0.9524 | | 0.0 | 23.0 | 5037 | 0.3420 | 0.9524 | | 0.0 | 24.0 | 5256 | 0.3443 | 0.9524 | | 0.0 | 25.0 | 5475 | 0.3462 | 0.9524 | | 0.0 | 26.0 | 5694 | 0.3477 | 0.9524 | | 0.0 | 27.0 | 5913 | 0.3490 | 0.9524 | | 0.0 | 28.0 | 6132 | 0.3502 | 0.9524 | | 0.0 | 29.0 | 6351 | 0.3512 | 0.9524 | | 0.0 | 30.0 | 6570 | 0.3521 | 0.9524 | | 0.0 | 31.0 | 6789 | 0.3528 | 0.9524 | | 0.0 | 32.0 | 7008 | 0.3535 | 0.9524 | | 0.0 | 33.0 | 7227 | 0.3541 | 0.9524 | | 0.0 | 34.0 | 7446 | 0.3547 | 0.9524 | | 0.0 | 35.0 | 7665 | 0.3552 | 0.9524 | | 0.0 | 36.0 | 7884 | 0.3556 | 0.9524 | | 0.0 | 37.0 | 8103 | 0.3560 | 0.9524 | | 0.0 | 38.0 | 8322 | 0.3564 | 0.9524 | | 0.0 | 39.0 | 8541 | 0.3567 | 0.9524 | | 0.0 | 40.0 | 8760 | 0.3570 | 0.9524 | | 0.0 | 41.0 | 8979 | 0.3573 | 0.9524 | | 0.0 | 42.0 | 9198 | 0.3575 | 0.9524 | | 0.0 | 43.0 | 9417 | 0.3577 | 0.9524 | | 0.0 | 44.0 | 9636 | 0.3578 | 0.9524 | | 0.0 | 45.0 | 9855 | 0.3580 | 0.9524 | | 0.0 | 46.0 | 10074 | 0.3581 | 0.9524 | | 0.0 | 47.0 | 10293 | 0.3582 | 0.9524 | | 0.0 | 48.0 | 10512 | 0.3582 | 0.9524 | | 0.0 | 49.0 | 10731 | 0.3583 | 0.9524 | | 0.0 | 50.0 | 10950 | 0.3583 | 0.9524 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.1.0+cu121 - Datasets 2.12.0 - Tokenizers 0.13.2