--- tags: - generated_from_trainer datasets: - funsd model-index: - name: layoutlm-funsd results: [] --- # layoutlm-funsd This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset. It achieves the following results on the evaluation set: - Loss: 0.6865 - Answer: {'precision': 0.6990185387131952, 'recall': 0.792336217552534, 'f1': 0.7427578215527232, 'number': 809} - Header: {'precision': 0.3416666666666667, 'recall': 0.3445378151260504, 'f1': 0.34309623430962344, 'number': 119} - Question: {'precision': 0.7904085257548845, 'recall': 0.8356807511737089, 'f1': 0.8124144226380648, 'number': 1065} - Overall Precision: 0.7268 - Overall Recall: 0.7888 - Overall F1: 0.7565 - Overall Accuracy: 0.8047 ## 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: 3e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 15 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 1.7784 | 1.0 | 10 | 1.6271 | {'precision': 0.01841620626151013, 'recall': 0.012360939431396786, 'f1': 0.014792899408284023, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.11462450592885376, 'recall': 0.054460093896713614, 'f1': 0.07383831954169319, 'number': 1065} | 0.0648 | 0.0341 | 0.0447 | 0.3258 | | 1.4893 | 2.0 | 20 | 1.2865 | {'precision': 0.18452935694315004, 'recall': 0.24474660074165636, 'f1': 0.21041445270988307, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4293563579277865, 'recall': 0.5136150234741784, 'f1': 0.4677212483967507, 'number': 1065} | 0.3174 | 0.3738 | 0.3433 | 0.5703 | | 1.1173 | 3.0 | 30 | 0.9566 | {'precision': 0.4382845188284519, 'recall': 0.5179233621755254, 'f1': 0.4747875354107649, 'number': 809} | {'precision': 0.045454545454545456, 'recall': 0.01680672268907563, 'f1': 0.024539877300613498, 'number': 119} | {'precision': 0.5686113393590797, 'recall': 0.6497652582159624, 'f1': 0.6064855390008765, 'number': 1065} | 0.5020 | 0.5585 | 0.5287 | 0.6883 | | 0.8579 | 4.0 | 40 | 0.8042 | {'precision': 0.5834932821497121, 'recall': 0.7515451174289246, 'f1': 0.6569421934089681, 'number': 809} | {'precision': 0.18055555555555555, 'recall': 0.1092436974789916, 'f1': 0.13612565445026178, 'number': 119} | {'precision': 0.6401480111008325, 'recall': 0.6497652582159624, 'f1': 0.6449207828518173, 'number': 1065} | 0.5982 | 0.6588 | 0.6270 | 0.7438 | | 0.711 | 5.0 | 50 | 0.7251 | {'precision': 0.6355140186915887, 'recall': 0.7564894932014833, 'f1': 0.6907449209932279, 'number': 809} | {'precision': 0.25252525252525254, 'recall': 0.21008403361344538, 'f1': 0.22935779816513763, 'number': 119} | {'precision': 0.6740237691001698, 'recall': 0.7455399061032864, 'f1': 0.7079803834150691, 'number': 1065} | 0.6388 | 0.7180 | 0.6761 | 0.7764 | | 0.5916 | 6.0 | 60 | 0.6914 | {'precision': 0.6471204188481675, 'recall': 0.7639060568603214, 'f1': 0.7006802721088435, 'number': 809} | {'precision': 0.325, 'recall': 0.2184873949579832, 'f1': 0.26130653266331655, 'number': 119} | {'precision': 0.6792452830188679, 'recall': 0.8112676056338028, 'f1': 0.7394094993581515, 'number': 1065} | 0.6537 | 0.7566 | 0.7014 | 0.7820 | | 0.5253 | 7.0 | 70 | 0.6778 | {'precision': 0.6542056074766355, 'recall': 0.7787391841779975, 'f1': 0.711060948081264, 'number': 809} | {'precision': 0.3047619047619048, 'recall': 0.2689075630252101, 'f1': 0.28571428571428575, 'number': 119} | {'precision': 0.739247311827957, 'recall': 0.7746478873239436, 'f1': 0.7565337001375517, 'number': 1065} | 0.6809 | 0.7461 | 0.7120 | 0.7896 | | 0.4705 | 8.0 | 80 | 0.6586 | {'precision': 0.6659751037344398, 'recall': 0.7935723114956736, 'f1': 0.7241962774957698, 'number': 809} | {'precision': 0.30392156862745096, 'recall': 0.2605042016806723, 'f1': 0.28054298642533937, 'number': 119} | {'precision': 0.7257093723129837, 'recall': 0.7924882629107981, 'f1': 0.7576301615798923, 'number': 1065} | 0.6806 | 0.7612 | 0.7186 | 0.7966 | | 0.4214 | 9.0 | 90 | 0.6588 | {'precision': 0.6852846401718582, 'recall': 0.788627935723115, 'f1': 0.7333333333333334, 'number': 809} | {'precision': 0.2755905511811024, 'recall': 0.29411764705882354, 'f1': 0.2845528455284553, 'number': 119} | {'precision': 0.7396907216494846, 'recall': 0.8084507042253521, 'f1': 0.7725437415881561, 'number': 1065} | 0.6904 | 0.7697 | 0.7279 | 0.7992 | | 0.3765 | 10.0 | 100 | 0.6598 | {'precision': 0.6825053995680346, 'recall': 0.7812113720642769, 'f1': 0.7285302593659942, 'number': 809} | {'precision': 0.32142857142857145, 'recall': 0.3025210084033613, 'f1': 0.3116883116883117, 'number': 119} | {'precision': 0.7658833768494343, 'recall': 0.8262910798122066, 'f1': 0.7949412827461607, 'number': 1065} | 0.7078 | 0.7767 | 0.7407 | 0.8013 | | 0.3331 | 11.0 | 110 | 0.6659 | {'precision': 0.6778947368421052, 'recall': 0.796044499381953, 'f1': 0.7322342239909039, 'number': 809} | {'precision': 0.3157894736842105, 'recall': 0.3025210084033613, 'f1': 0.30901287553648066, 'number': 119} | {'precision': 0.772566371681416, 'recall': 0.819718309859155, 'f1': 0.7954441913439636, 'number': 1065} | 0.7078 | 0.7792 | 0.7418 | 0.8033 | | 0.3192 | 12.0 | 120 | 0.6782 | {'precision': 0.6885069817400644, 'recall': 0.792336217552534, 'f1': 0.7367816091954023, 'number': 809} | {'precision': 0.3170731707317073, 'recall': 0.3277310924369748, 'f1': 0.32231404958677684, 'number': 119} | {'precision': 0.7828418230563002, 'recall': 0.8225352112676056, 'f1': 0.8021978021978022, 'number': 1065} | 0.7161 | 0.7807 | 0.7470 | 0.8015 | | 0.3012 | 13.0 | 130 | 0.6835 | {'precision': 0.6929637526652452, 'recall': 0.8034610630407911, 'f1': 0.7441327990841443, 'number': 809} | {'precision': 0.3252032520325203, 'recall': 0.33613445378151263, 'f1': 0.3305785123966942, 'number': 119} | {'precision': 0.7847652790079717, 'recall': 0.831924882629108, 'f1': 0.8076572470373746, 'number': 1065} | 0.7196 | 0.7908 | 0.7535 | 0.8025 | | 0.2867 | 14.0 | 140 | 0.6851 | {'precision': 0.7003257328990228, 'recall': 0.7972805933250927, 'f1': 0.7456647398843931, 'number': 809} | {'precision': 0.3445378151260504, 'recall': 0.3445378151260504, 'f1': 0.3445378151260504, 'number': 119} | {'precision': 0.7884444444444444, 'recall': 0.8328638497652582, 'f1': 0.8100456621004566, 'number': 1065} | 0.7266 | 0.7893 | 0.7566 | 0.8029 | | 0.2827 | 15.0 | 150 | 0.6865 | {'precision': 0.6990185387131952, 'recall': 0.792336217552534, 'f1': 0.7427578215527232, 'number': 809} | {'precision': 0.3416666666666667, 'recall': 0.3445378151260504, 'f1': 0.34309623430962344, 'number': 119} | {'precision': 0.7904085257548845, 'recall': 0.8356807511737089, 'f1': 0.8124144226380648, 'number': 1065} | 0.7268 | 0.7888 | 0.7565 | 0.8047 | ### Framework versions - Transformers 4.27.4 - Pytorch 2.0.0+cu118 - Datasets 2.11.0 - Tokenizers 0.13.3