--- license: apache-2.0 base_model: facebook/deit-base-distilled-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: deit-base-distilled-patch16-224-65-fold4 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.8732394366197183 --- # deit-base-distilled-patch16-224-65-fold4 This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.4832 - Accuracy: 0.8732 ## 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: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | No log | 0.9231 | 3 | 0.7219 | 0.5493 | | No log | 1.8462 | 6 | 0.6863 | 0.5493 | | No log | 2.7692 | 9 | 0.6578 | 0.5493 | | 0.6825 | 4.0 | 13 | 0.6293 | 0.6338 | | 0.6825 | 4.9231 | 16 | 0.6186 | 0.6761 | | 0.6825 | 5.8462 | 19 | 0.6135 | 0.7042 | | 0.6206 | 6.7692 | 22 | 0.6163 | 0.6479 | | 0.6206 | 8.0 | 26 | 0.6350 | 0.6479 | | 0.6206 | 8.9231 | 29 | 0.6078 | 0.6901 | | 0.5728 | 9.8462 | 32 | 0.6873 | 0.6761 | | 0.5728 | 10.7692 | 35 | 0.6771 | 0.6761 | | 0.5728 | 12.0 | 39 | 0.5912 | 0.6620 | | 0.5329 | 12.9231 | 42 | 0.5524 | 0.7465 | | 0.5329 | 13.8462 | 45 | 0.5923 | 0.7183 | | 0.5329 | 14.7692 | 48 | 0.6650 | 0.6761 | | 0.4279 | 16.0 | 52 | 0.5183 | 0.7746 | | 0.4279 | 16.9231 | 55 | 0.4761 | 0.7887 | | 0.4279 | 17.8462 | 58 | 0.5590 | 0.7183 | | 0.4055 | 18.7692 | 61 | 0.5320 | 0.7465 | | 0.4055 | 20.0 | 65 | 0.6605 | 0.7183 | | 0.4055 | 20.9231 | 68 | 0.5821 | 0.7465 | | 0.3478 | 21.8462 | 71 | 0.5589 | 0.7465 | | 0.3478 | 22.7692 | 74 | 0.6247 | 0.7465 | | 0.3478 | 24.0 | 78 | 0.7006 | 0.6620 | | 0.3769 | 24.9231 | 81 | 0.7575 | 0.7183 | | 0.3769 | 25.8462 | 84 | 0.5367 | 0.7746 | | 0.3769 | 26.7692 | 87 | 0.5335 | 0.7746 | | 0.2957 | 28.0 | 91 | 0.5914 | 0.7606 | | 0.2957 | 28.9231 | 94 | 0.6780 | 0.7465 | | 0.2957 | 29.8462 | 97 | 0.5345 | 0.7746 | | 0.2463 | 30.7692 | 100 | 0.6132 | 0.7606 | | 0.2463 | 32.0 | 104 | 0.5758 | 0.7887 | | 0.2463 | 32.9231 | 107 | 0.7236 | 0.7324 | | 0.2323 | 33.8462 | 110 | 0.5247 | 0.8169 | | 0.2323 | 34.7692 | 113 | 0.6018 | 0.7183 | | 0.2323 | 36.0 | 117 | 0.5366 | 0.8028 | | 0.1921 | 36.9231 | 120 | 0.6314 | 0.7465 | | 0.1921 | 37.8462 | 123 | 0.5763 | 0.7746 | | 0.1921 | 38.7692 | 126 | 0.5574 | 0.8028 | | 0.1686 | 40.0 | 130 | 0.6261 | 0.7887 | | 0.1686 | 40.9231 | 133 | 0.6525 | 0.7887 | | 0.1686 | 41.8462 | 136 | 0.5726 | 0.8169 | | 0.1686 | 42.7692 | 139 | 0.8200 | 0.7042 | | 0.2073 | 44.0 | 143 | 0.4798 | 0.7887 | | 0.2073 | 44.9231 | 146 | 0.5342 | 0.7887 | | 0.2073 | 45.8462 | 149 | 0.4834 | 0.7887 | | 0.1702 | 46.7692 | 152 | 0.6101 | 0.7465 | | 0.1702 | 48.0 | 156 | 0.4779 | 0.8169 | | 0.1702 | 48.9231 | 159 | 0.5048 | 0.7887 | | 0.153 | 49.8462 | 162 | 0.6298 | 0.7465 | | 0.153 | 50.7692 | 165 | 0.5995 | 0.7606 | | 0.153 | 52.0 | 169 | 0.6475 | 0.7042 | | 0.1508 | 52.9231 | 172 | 0.4888 | 0.8028 | | 0.1508 | 53.8462 | 175 | 0.4954 | 0.8310 | | 0.1508 | 54.7692 | 178 | 0.4390 | 0.8028 | | 0.1293 | 56.0 | 182 | 0.4778 | 0.8592 | | 0.1293 | 56.9231 | 185 | 0.4888 | 0.8310 | | 0.1293 | 57.8462 | 188 | 0.4832 | 0.8732 | | 0.1489 | 58.7692 | 191 | 0.5277 | 0.8310 | | 0.1489 | 60.0 | 195 | 0.6217 | 0.7324 | | 0.1489 | 60.9231 | 198 | 0.6090 | 0.7465 | | 0.1487 | 61.8462 | 201 | 0.5424 | 0.8451 | | 0.1487 | 62.7692 | 204 | 0.5570 | 0.8451 | | 0.1487 | 64.0 | 208 | 0.7248 | 0.7183 | | 0.1456 | 64.9231 | 211 | 0.5841 | 0.7887 | | 0.1456 | 65.8462 | 214 | 0.5905 | 0.8310 | | 0.1456 | 66.7692 | 217 | 0.5609 | 0.8310 | | 0.1284 | 68.0 | 221 | 0.5470 | 0.8028 | | 0.1284 | 68.9231 | 224 | 0.5473 | 0.8310 | | 0.1284 | 69.8462 | 227 | 0.5813 | 0.8310 | | 0.1225 | 70.7692 | 230 | 0.5683 | 0.8451 | | 0.1225 | 72.0 | 234 | 0.5581 | 0.8310 | | 0.1225 | 72.9231 | 237 | 0.5717 | 0.7887 | | 0.1233 | 73.8462 | 240 | 0.6054 | 0.7606 | | 0.1233 | 74.7692 | 243 | 0.5910 | 0.7887 | | 0.1233 | 76.0 | 247 | 0.5707 | 0.8169 | | 0.1234 | 76.9231 | 250 | 0.5733 | 0.8028 | | 0.1234 | 77.8462 | 253 | 0.5748 | 0.8028 | | 0.1234 | 78.7692 | 256 | 0.5723 | 0.7887 | | 0.1219 | 80.0 | 260 | 0.5503 | 0.8169 | | 0.1219 | 80.9231 | 263 | 0.5532 | 0.8028 | | 0.1219 | 81.8462 | 266 | 0.5828 | 0.7746 | | 0.1219 | 82.7692 | 269 | 0.6062 | 0.7746 | | 0.1075 | 84.0 | 273 | 0.5752 | 0.8028 | | 0.1075 | 84.9231 | 276 | 0.5748 | 0.8028 | | 0.1075 | 85.8462 | 279 | 0.5776 | 0.8169 | | 0.1013 | 86.7692 | 282 | 0.5844 | 0.8028 | | 0.1013 | 88.0 | 286 | 0.5930 | 0.8028 | | 0.1013 | 88.9231 | 289 | 0.6020 | 0.7887 | | 0.1092 | 89.8462 | 292 | 0.6055 | 0.7746 | | 0.1092 | 90.7692 | 295 | 0.6075 | 0.7746 | | 0.1092 | 92.0 | 299 | 0.6080 | 0.7746 | | 0.1096 | 92.3077 | 300 | 0.6081 | 0.7746 | ### Framework versions - Transformers 4.41.0 - Pytorch 2.3.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1