--- license: apache-2.0 base_model: facebook/deit-tiny-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: hushem_40x_deit_tiny_rms_0001_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: 0.7777777777777778 --- # hushem_40x_deit_tiny_rms_0001_fold1 This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.8879 - 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 | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.0915 | 1.0 | 215 | 0.6993 | 0.7556 | | 0.0445 | 2.0 | 430 | 1.0894 | 0.8 | | 0.0994 | 3.0 | 645 | 1.3749 | 0.7333 | | 0.0599 | 4.0 | 860 | 1.2197 | 0.8222 | | 0.123 | 5.0 | 1075 | 1.0909 | 0.7333 | | 0.0208 | 6.0 | 1290 | 1.5815 | 0.7778 | | 0.0152 | 7.0 | 1505 | 1.3429 | 0.7556 | | 0.1165 | 8.0 | 1720 | 1.4059 | 0.8222 | | 0.0038 | 9.0 | 1935 | 2.1318 | 0.6889 | | 0.0001 | 10.0 | 2150 | 1.8677 | 0.7556 | | 0.0 | 11.0 | 2365 | 1.9514 | 0.7556 | | 0.0 | 12.0 | 2580 | 2.1201 | 0.7556 | | 0.0 | 13.0 | 2795 | 2.2375 | 0.7556 | | 0.0 | 14.0 | 3010 | 2.3713 | 0.7556 | | 0.0 | 15.0 | 3225 | 2.4919 | 0.7556 | | 0.0 | 16.0 | 3440 | 2.5759 | 0.7556 | | 0.0 | 17.0 | 3655 | 2.6720 | 0.7556 | | 0.0 | 18.0 | 3870 | 2.7211 | 0.7556 | | 0.0 | 19.0 | 4085 | 2.7243 | 0.7778 | | 0.0 | 20.0 | 4300 | 2.7162 | 0.7778 | | 0.0 | 21.0 | 4515 | 2.7396 | 0.7778 | | 0.0 | 22.0 | 4730 | 2.8636 | 0.7556 | | 0.0 | 23.0 | 4945 | 2.7180 | 0.7778 | | 0.0 | 24.0 | 5160 | 2.5977 | 0.7778 | | 0.0 | 25.0 | 5375 | 2.4267 | 0.7778 | | 0.0 | 26.0 | 5590 | 2.3791 | 0.7778 | | 0.0 | 27.0 | 5805 | 2.3560 | 0.7778 | | 0.0 | 28.0 | 6020 | 2.2693 | 0.7778 | | 0.0 | 29.0 | 6235 | 2.3818 | 0.7778 | | 0.0 | 30.0 | 6450 | 2.1093 | 0.7778 | | 0.0 | 31.0 | 6665 | 2.1403 | 0.7778 | | 0.0 | 32.0 | 6880 | 2.0697 | 0.7778 | | 0.0 | 33.0 | 7095 | 2.1077 | 0.7778 | | 0.0 | 34.0 | 7310 | 1.9838 | 0.7778 | | 0.0 | 35.0 | 7525 | 2.0013 | 0.7778 | | 0.0 | 36.0 | 7740 | 1.9512 | 0.7778 | | 0.0 | 37.0 | 7955 | 1.9785 | 0.7778 | | 0.0 | 38.0 | 8170 | 1.9833 | 0.7778 | | 0.0 | 39.0 | 8385 | 1.9247 | 0.7778 | | 0.0 | 40.0 | 8600 | 1.9583 | 0.7778 | | 0.0 | 41.0 | 8815 | 1.9257 | 0.7778 | | 0.0 | 42.0 | 9030 | 1.9718 | 0.7778 | | 0.0 | 43.0 | 9245 | 1.9220 | 0.7778 | | 0.0 | 44.0 | 9460 | 1.9083 | 0.7778 | | 0.0 | 45.0 | 9675 | 1.9217 | 0.7778 | | 0.0 | 46.0 | 9890 | 1.8800 | 0.7778 | | 0.0 | 47.0 | 10105 | 1.8880 | 0.7778 | | 0.0 | 48.0 | 10320 | 1.8890 | 0.7778 | | 0.0 | 49.0 | 10535 | 1.8815 | 0.7778 | | 0.0 | 50.0 | 10750 | 1.8879 | 0.7778 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.1.1+cu121 - Datasets 2.12.0 - Tokenizers 0.13.2