--- 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-hasta-85-fold5 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: 0.7272727272727273 --- # deit-base-distilled-patch16-224-hasta-85-fold5 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: 0.7292 - Accuracy: 0.7273 ## 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 | 1.0 | 1 | 1.3530 | 0.2727 | | No log | 2.0 | 2 | 1.1775 | 0.2727 | | No log | 3.0 | 3 | 0.9128 | 0.5455 | | No log | 4.0 | 4 | 0.7292 | 0.7273 | | No log | 5.0 | 5 | 0.7753 | 0.7273 | | No log | 6.0 | 6 | 0.9952 | 0.7273 | | No log | 7.0 | 7 | 1.1799 | 0.7273 | | No log | 8.0 | 8 | 1.2699 | 0.7273 | | No log | 9.0 | 9 | 1.2729 | 0.7273 | | 0.38 | 10.0 | 10 | 1.2451 | 0.7273 | | 0.38 | 11.0 | 11 | 1.2341 | 0.7273 | | 0.38 | 12.0 | 12 | 1.2153 | 0.7273 | | 0.38 | 13.0 | 13 | 1.1847 | 0.7273 | | 0.38 | 14.0 | 14 | 1.1903 | 0.7273 | | 0.38 | 15.0 | 15 | 1.2128 | 0.7273 | | 0.38 | 16.0 | 16 | 1.1724 | 0.7273 | | 0.38 | 17.0 | 17 | 1.0705 | 0.7273 | | 0.38 | 18.0 | 18 | 1.0106 | 0.7273 | | 0.38 | 19.0 | 19 | 1.0238 | 0.7273 | | 0.1729 | 20.0 | 20 | 1.0594 | 0.7273 | | 0.1729 | 21.0 | 21 | 1.1695 | 0.7273 | | 0.1729 | 22.0 | 22 | 1.2466 | 0.7273 | | 0.1729 | 23.0 | 23 | 1.2861 | 0.7273 | | 0.1729 | 24.0 | 24 | 1.2790 | 0.7273 | | 0.1729 | 25.0 | 25 | 1.3177 | 0.7273 | | 0.1729 | 26.0 | 26 | 1.4130 | 0.7273 | | 0.1729 | 27.0 | 27 | 1.5155 | 0.7273 | | 0.1729 | 28.0 | 28 | 1.6224 | 0.7273 | | 0.1729 | 29.0 | 29 | 1.5918 | 0.7273 | | 0.0904 | 30.0 | 30 | 1.4099 | 0.7273 | | 0.0904 | 31.0 | 31 | 1.2681 | 0.7273 | | 0.0904 | 32.0 | 32 | 1.1371 | 0.7273 | | 0.0904 | 33.0 | 33 | 1.0387 | 0.7273 | | 0.0904 | 34.0 | 34 | 1.0128 | 0.7273 | | 0.0904 | 35.0 | 35 | 1.0423 | 0.7273 | | 0.0904 | 36.0 | 36 | 1.1730 | 0.7273 | | 0.0904 | 37.0 | 37 | 1.3305 | 0.7273 | | 0.0904 | 38.0 | 38 | 1.3820 | 0.7273 | | 0.0904 | 39.0 | 39 | 1.3682 | 0.7273 | | 0.0591 | 40.0 | 40 | 1.2854 | 0.7273 | | 0.0591 | 41.0 | 41 | 1.2000 | 0.7273 | | 0.0591 | 42.0 | 42 | 1.2079 | 0.7273 | | 0.0591 | 43.0 | 43 | 1.2967 | 0.7273 | | 0.0591 | 44.0 | 44 | 1.3672 | 0.7273 | | 0.0591 | 45.0 | 45 | 1.3709 | 0.7273 | | 0.0591 | 46.0 | 46 | 1.4370 | 0.7273 | | 0.0591 | 47.0 | 47 | 1.4863 | 0.7273 | | 0.0591 | 48.0 | 48 | 1.5696 | 0.7273 | | 0.0591 | 49.0 | 49 | 1.5678 | 0.7273 | | 0.0289 | 50.0 | 50 | 1.5444 | 0.7273 | | 0.0289 | 51.0 | 51 | 1.5086 | 0.7273 | | 0.0289 | 52.0 | 52 | 1.4333 | 0.7273 | | 0.0289 | 53.0 | 53 | 1.3644 | 0.7273 | | 0.0289 | 54.0 | 54 | 1.3099 | 0.7273 | | 0.0289 | 55.0 | 55 | 1.3355 | 0.7273 | | 0.0289 | 56.0 | 56 | 1.4286 | 0.7273 | | 0.0289 | 57.0 | 57 | 1.6121 | 0.7273 | | 0.0289 | 58.0 | 58 | 1.8074 | 0.7273 | | 0.0289 | 59.0 | 59 | 1.9461 | 0.7273 | | 0.0342 | 60.0 | 60 | 2.0314 | 0.7273 | | 0.0342 | 61.0 | 61 | 2.0408 | 0.7273 | | 0.0342 | 62.0 | 62 | 2.0476 | 0.7273 | | 0.0342 | 63.0 | 63 | 2.0517 | 0.7273 | | 0.0342 | 64.0 | 64 | 2.0217 | 0.7273 | | 0.0342 | 65.0 | 65 | 1.9582 | 0.7273 | | 0.0342 | 66.0 | 66 | 1.8825 | 0.7273 | | 0.0342 | 67.0 | 67 | 1.8085 | 0.7273 | | 0.0342 | 68.0 | 68 | 1.7880 | 0.7273 | | 0.0342 | 69.0 | 69 | 1.7796 | 0.7273 | | 0.0203 | 70.0 | 70 | 1.7929 | 0.7273 | | 0.0203 | 71.0 | 71 | 1.8213 | 0.7273 | | 0.0203 | 72.0 | 72 | 1.8388 | 0.7273 | | 0.0203 | 73.0 | 73 | 1.8488 | 0.7273 | | 0.0203 | 74.0 | 74 | 1.8753 | 0.7273 | | 0.0203 | 75.0 | 75 | 1.9079 | 0.7273 | | 0.0203 | 76.0 | 76 | 1.9396 | 0.7273 | | 0.0203 | 77.0 | 77 | 1.9556 | 0.7273 | | 0.0203 | 78.0 | 78 | 1.9591 | 0.7273 | | 0.0203 | 79.0 | 79 | 1.9668 | 0.7273 | | 0.0324 | 80.0 | 80 | 1.9865 | 0.7273 | | 0.0324 | 81.0 | 81 | 2.0098 | 0.7273 | | 0.0324 | 82.0 | 82 | 2.0384 | 0.7273 | | 0.0324 | 83.0 | 83 | 2.0659 | 0.7273 | | 0.0324 | 84.0 | 84 | 2.0952 | 0.7273 | | 0.0324 | 85.0 | 85 | 2.1069 | 0.7273 | | 0.0324 | 86.0 | 86 | 2.1130 | 0.7273 | | 0.0324 | 87.0 | 87 | 2.1181 | 0.7273 | | 0.0324 | 88.0 | 88 | 2.1180 | 0.7273 | | 0.0324 | 89.0 | 89 | 2.1173 | 0.7273 | | 0.0244 | 90.0 | 90 | 2.1193 | 0.7273 | | 0.0244 | 91.0 | 91 | 2.1226 | 0.7273 | | 0.0244 | 92.0 | 92 | 2.1256 | 0.7273 | | 0.0244 | 93.0 | 93 | 2.1312 | 0.7273 | | 0.0244 | 94.0 | 94 | 2.1333 | 0.7273 | | 0.0244 | 95.0 | 95 | 2.1371 | 0.7273 | | 0.0244 | 96.0 | 96 | 2.1413 | 0.7273 | | 0.0244 | 97.0 | 97 | 2.1438 | 0.7273 | | 0.0244 | 98.0 | 98 | 2.1454 | 0.7273 | | 0.0244 | 99.0 | 99 | 2.1451 | 0.7273 | | 0.027 | 100.0 | 100 | 2.1448 | 0.7273 | ### Framework versions - Transformers 4.41.0 - Pytorch 2.3.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1