--- license: cc-by-nc-sa-4.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-28_went_gates_exitloss results: [] --- # EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-28_went_gates_exitloss This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0216 - Accuracy: 0.74 - Exit 0 Accuracy: 0.0675 - Exit 1 Accuracy: 0.1175 - Exit 2 Accuracy: 0.08 - Exit 3 Accuracy: 0.09 - Exit 4 Accuracy: 0.0625 ## 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: 2e-05 - train_batch_size: 16 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 12 - total_train_batch_size: 192 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 60 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:| | No log | 0.96 | 4 | 2.7344 | 0.1275 | 0.0625 | 0.0925 | 0.0825 | 0.0625 | 0.0625 | | No log | 1.96 | 8 | 2.6660 | 0.1725 | 0.0625 | 0.1025 | 0.085 | 0.0625 | 0.0625 | | No log | 2.96 | 12 | 2.6216 | 0.1975 | 0.065 | 0.1075 | 0.085 | 0.0625 | 0.0625 | | No log | 3.96 | 16 | 2.5682 | 0.2275 | 0.0675 | 0.1075 | 0.0775 | 0.0625 | 0.0625 | | No log | 4.96 | 20 | 2.4979 | 0.2475 | 0.055 | 0.1125 | 0.08 | 0.0625 | 0.0625 | | No log | 5.96 | 24 | 2.4354 | 0.255 | 0.05 | 0.115 | 0.065 | 0.0625 | 0.0625 | | No log | 6.96 | 28 | 2.3502 | 0.2925 | 0.055 | 0.115 | 0.065 | 0.0625 | 0.0625 | | No log | 7.96 | 32 | 2.2675 | 0.3175 | 0.0475 | 0.115 | 0.0675 | 0.0625 | 0.0625 | | No log | 8.96 | 36 | 2.1872 | 0.335 | 0.05 | 0.11 | 0.0625 | 0.0625 | 0.0625 | | No log | 9.96 | 40 | 2.0887 | 0.39 | 0.06 | 0.1075 | 0.07 | 0.0625 | 0.0625 | | No log | 10.96 | 44 | 1.9727 | 0.455 | 0.0625 | 0.1075 | 0.0675 | 0.0625 | 0.0625 | | No log | 11.96 | 48 | 1.8812 | 0.5075 | 0.065 | 0.105 | 0.0675 | 0.0625 | 0.0625 | | No log | 12.96 | 52 | 1.7404 | 0.5675 | 0.0675 | 0.1 | 0.07 | 0.0625 | 0.0625 | | No log | 13.96 | 56 | 1.6448 | 0.58 | 0.07 | 0.1125 | 0.0675 | 0.0625 | 0.0625 | | No log | 14.96 | 60 | 1.5322 | 0.62 | 0.07 | 0.1125 | 0.065 | 0.0625 | 0.0625 | | No log | 15.96 | 64 | 1.4430 | 0.63 | 0.0675 | 0.1125 | 0.07 | 0.0625 | 0.0625 | | No log | 16.96 | 68 | 1.3651 | 0.665 | 0.0675 | 0.1125 | 0.0725 | 0.0625 | 0.0625 | | No log | 17.96 | 72 | 1.2921 | 0.685 | 0.065 | 0.1125 | 0.0775 | 0.0625 | 0.0625 | | No log | 18.96 | 76 | 1.2430 | 0.69 | 0.0625 | 0.1125 | 0.0875 | 0.0625 | 0.0625 | | No log | 19.96 | 80 | 1.2040 | 0.695 | 0.045 | 0.1125 | 0.09 | 0.0625 | 0.0625 | | No log | 20.96 | 84 | 1.1557 | 0.7 | 0.0525 | 0.1125 | 0.09 | 0.0625 | 0.0625 | | No log | 21.96 | 88 | 1.1138 | 0.72 | 0.05 | 0.1125 | 0.09 | 0.0625 | 0.0625 | | No log | 22.96 | 92 | 1.0827 | 0.7075 | 0.0525 | 0.1125 | 0.09 | 0.0625 | 0.0625 | | No log | 23.96 | 96 | 1.0557 | 0.7275 | 0.05 | 0.1125 | 0.0875 | 0.0625 | 0.0625 | | No log | 24.96 | 100 | 1.0222 | 0.73 | 0.05 | 0.1125 | 0.085 | 0.0625 | 0.0625 | | No log | 25.96 | 104 | 1.0071 | 0.7325 | 0.055 | 0.1125 | 0.0775 | 0.0625 | 0.0625 | | No log | 26.96 | 108 | 1.0107 | 0.74 | 0.0575 | 0.1125 | 0.0825 | 0.0625 | 0.0625 | | No log | 27.96 | 112 | 0.9814 | 0.76 | 0.0575 | 0.115 | 0.08 | 0.0625 | 0.0625 | | No log | 28.96 | 116 | 1.0000 | 0.7475 | 0.0575 | 0.1175 | 0.0725 | 0.0625 | 0.0625 | | No log | 29.96 | 120 | 0.9703 | 0.7425 | 0.055 | 0.1175 | 0.0775 | 0.0625 | 0.0625 | | No log | 30.96 | 124 | 0.9749 | 0.7375 | 0.0575 | 0.1175 | 0.075 | 0.0625 | 0.0625 | | No log | 31.96 | 128 | 0.9573 | 0.745 | 0.05 | 0.1175 | 0.0675 | 0.0625 | 0.0625 | | No log | 32.96 | 132 | 0.9704 | 0.75 | 0.0525 | 0.12 | 0.065 | 0.0625 | 0.0625 | | No log | 33.96 | 136 | 0.9573 | 0.7425 | 0.055 | 0.12 | 0.065 | 0.065 | 0.0625 | | No log | 34.96 | 140 | 0.9600 | 0.7475 | 0.06 | 0.12 | 0.0625 | 0.0625 | 0.0625 | | No log | 35.96 | 144 | 0.9606 | 0.74 | 0.055 | 0.12 | 0.065 | 0.065 | 0.0625 | | No log | 36.96 | 148 | 0.9969 | 0.7275 | 0.055 | 0.12 | 0.0675 | 0.065 | 0.0625 | | No log | 37.96 | 152 | 0.9712 | 0.7325 | 0.055 | 0.12 | 0.0725 | 0.07 | 0.0625 | | No log | 38.96 | 156 | 0.9625 | 0.75 | 0.055 | 0.12 | 0.0725 | 0.07 | 0.0625 | | No log | 39.96 | 160 | 0.9814 | 0.7475 | 0.0575 | 0.12 | 0.0725 | 0.075 | 0.0625 | | No log | 40.96 | 164 | 0.9793 | 0.74 | 0.0575 | 0.12 | 0.0725 | 0.075 | 0.0625 | | No log | 41.96 | 168 | 1.0000 | 0.745 | 0.0625 | 0.12 | 0.0725 | 0.075 | 0.0625 | | No log | 42.96 | 172 | 0.9928 | 0.7425 | 0.06 | 0.12 | 0.0725 | 0.075 | 0.0625 | | No log | 43.96 | 176 | 0.9755 | 0.75 | 0.07 | 0.12 | 0.08 | 0.075 | 0.0625 | | No log | 44.96 | 180 | 0.9917 | 0.74 | 0.07 | 0.12 | 0.0775 | 0.075 | 0.0625 | | No log | 45.96 | 184 | 0.9878 | 0.7425 | 0.065 | 0.1175 | 0.08 | 0.075 | 0.0625 | | No log | 46.96 | 188 | 0.9984 | 0.7425 | 0.065 | 0.1175 | 0.08 | 0.0775 | 0.0625 | | No log | 47.96 | 192 | 0.9991 | 0.7425 | 0.065 | 0.1175 | 0.0775 | 0.0775 | 0.0625 | | No log | 48.96 | 196 | 0.9940 | 0.74 | 0.0625 | 0.1175 | 0.08 | 0.075 | 0.0625 | | No log | 49.96 | 200 | 1.0055 | 0.7475 | 0.0625 | 0.1175 | 0.08 | 0.0825 | 0.0625 | | No log | 50.96 | 204 | 1.0244 | 0.7425 | 0.0625 | 0.1175 | 0.0775 | 0.0825 | 0.0625 | | No log | 51.96 | 208 | 1.0175 | 0.7425 | 0.065 | 0.1175 | 0.08 | 0.085 | 0.0625 | | No log | 52.96 | 212 | 1.0089 | 0.745 | 0.065 | 0.1175 | 0.085 | 0.0875 | 0.0625 | | No log | 53.96 | 216 | 1.0229 | 0.7375 | 0.065 | 0.1175 | 0.0775 | 0.0875 | 0.0625 | | No log | 54.96 | 220 | 1.0285 | 0.74 | 0.0675 | 0.1175 | 0.0775 | 0.09 | 0.0625 | | No log | 55.96 | 224 | 1.0219 | 0.7425 | 0.0675 | 0.1175 | 0.0775 | 0.0875 | 0.0625 | | No log | 56.96 | 228 | 1.0184 | 0.74 | 0.0675 | 0.1175 | 0.0775 | 0.0875 | 0.0625 | | No log | 57.96 | 232 | 1.0187 | 0.7425 | 0.0675 | 0.1175 | 0.08 | 0.09 | 0.0625 | | No log | 58.96 | 236 | 1.0204 | 0.7425 | 0.0675 | 0.1175 | 0.08 | 0.09 | 0.0625 | | No log | 59.96 | 240 | 1.0216 | 0.74 | 0.0675 | 0.1175 | 0.08 | 0.09 | 0.0625 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2