--- 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: 0.6633 - Answer: {'precision': 0.7068004459308808, 'recall': 0.7836835599505563, 'f1': 0.7432590855803048, 'number': 809} - Header: {'precision': 0.3025210084033613, 'recall': 0.3025210084033613, 'f1': 0.3025210084033613, 'number': 119} - Question: {'precision': 0.757679180887372, 'recall': 0.8338028169014085, 'f1': 0.7939204291461779, 'number': 1065} - Overall Precision: 0.7121 - Overall Recall: 0.7817 - Overall F1: 0.7453 - Overall Accuracy: 0.8174 ## 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 ### Training results | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 1.8218 | 1.0 | 10 | 1.6340 | {'precision': 0.012857142857142857, 'recall': 0.011124845488257108, 'f1': 0.011928429423459244, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.22849807445442877, 'recall': 0.1671361502347418, 'f1': 0.19305856832971802, 'number': 1065} | 0.1264 | 0.0938 | 0.1077 | 0.3314 | | 1.4842 | 2.0 | 20 | 1.2777 | {'precision': 0.18856447688564476, 'recall': 0.1915945611866502, 'f1': 0.19006744328632738, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.44694533762057875, 'recall': 0.5220657276995305, 'f1': 0.48159376353399735, 'number': 1065} | 0.3441 | 0.3567 | 0.3503 | 0.5691 | | 1.1045 | 3.0 | 30 | 0.9751 | {'precision': 0.44747612551159616, 'recall': 0.4054388133498146, 'f1': 0.42542153047989617, 'number': 809} | {'precision': 0.05555555555555555, 'recall': 0.01680672268907563, 'f1': 0.025806451612903226, 'number': 119} | {'precision': 0.6208445642407907, 'recall': 0.6488262910798122, 'f1': 0.6345270890725436, 'number': 1065} | 0.5425 | 0.5123 | 0.5270 | 0.6860 | | 0.833 | 4.0 | 40 | 0.7763 | {'precision': 0.6252609603340292, 'recall': 0.7404202719406675, 'f1': 0.677985285795133, 'number': 809} | {'precision': 0.1935483870967742, 'recall': 0.10084033613445378, 'f1': 0.13259668508287292, 'number': 119} | {'precision': 0.6614583333333334, 'recall': 0.7154929577464789, 'f1': 0.6874154262516915, 'number': 1065} | 0.6321 | 0.6889 | 0.6593 | 0.7559 | | 0.6773 | 5.0 | 50 | 0.7051 | {'precision': 0.6295918367346939, 'recall': 0.7626699629171817, 'f1': 0.6897708216880939, 'number': 809} | {'precision': 0.29069767441860467, 'recall': 0.21008403361344538, 'f1': 0.24390243902439027, 'number': 119} | {'precision': 0.6980802792321117, 'recall': 0.7511737089201878, 'f1': 0.7236544549977386, 'number': 1065} | 0.6519 | 0.7235 | 0.6859 | 0.7788 | | 0.5627 | 6.0 | 60 | 0.6598 | {'precision': 0.6423432682425488, 'recall': 0.7725587144622992, 'f1': 0.7014590347923682, 'number': 809} | {'precision': 0.32098765432098764, 'recall': 0.2184873949579832, 'f1': 0.26, 'number': 119} | {'precision': 0.7032878909382518, 'recall': 0.8234741784037559, 'f1': 0.7586505190311419, 'number': 1065} | 0.6641 | 0.7667 | 0.7117 | 0.7947 | | 0.4959 | 7.0 | 70 | 0.6625 | {'precision': 0.6652267818574514, 'recall': 0.761433868974042, 'f1': 0.7100864553314121, 'number': 809} | {'precision': 0.2761904761904762, 'recall': 0.24369747899159663, 'f1': 0.2589285714285714, 'number': 119} | {'precision': 0.7452504317789291, 'recall': 0.8103286384976526, 'f1': 0.7764282501124606, 'number': 1065} | 0.6889 | 0.7566 | 0.7212 | 0.7945 | | 0.4473 | 8.0 | 80 | 0.6402 | {'precision': 0.6684491978609626, 'recall': 0.7725587144622992, 'f1': 0.7167431192660552, 'number': 809} | {'precision': 0.25961538461538464, 'recall': 0.226890756302521, 'f1': 0.242152466367713, 'number': 119} | {'precision': 0.7415540540540541, 'recall': 0.8244131455399061, 'f1': 0.7807914628723877, 'number': 1065} | 0.6883 | 0.7677 | 0.7258 | 0.8046 | | 0.3997 | 9.0 | 90 | 0.6381 | {'precision': 0.6879120879120879, 'recall': 0.7737948084054388, 'f1': 0.7283304246655031, 'number': 809} | {'precision': 0.27350427350427353, 'recall': 0.2689075630252101, 'f1': 0.2711864406779661, 'number': 119} | {'precision': 0.7418817651956703, 'recall': 0.8366197183098592, 'f1': 0.7864077669902912, 'number': 1065} | 0.6952 | 0.7772 | 0.7339 | 0.8095 | | 0.3597 | 10.0 | 100 | 0.6481 | {'precision': 0.6959910913140311, 'recall': 0.7725587144622992, 'f1': 0.7322788517867603, 'number': 809} | {'precision': 0.25984251968503935, 'recall': 0.2773109243697479, 'f1': 0.2682926829268293, 'number': 119} | {'precision': 0.7495769881556683, 'recall': 0.831924882629108, 'f1': 0.7886070315976857, 'number': 1065} | 0.6996 | 0.7747 | 0.7352 | 0.8094 | | 0.3241 | 11.0 | 110 | 0.6649 | {'precision': 0.6960893854748603, 'recall': 0.7700865265760197, 'f1': 0.7312206572769954, 'number': 809} | {'precision': 0.32075471698113206, 'recall': 0.2857142857142857, 'f1': 0.30222222222222217, 'number': 119} | {'precision': 0.7689625108979947, 'recall': 0.828169014084507, 'f1': 0.7974683544303798, 'number': 1065} | 0.7165 | 0.7722 | 0.7433 | 0.8115 | | 0.3111 | 12.0 | 120 | 0.6584 | {'precision': 0.7083333333333334, 'recall': 0.7985166872682324, 'f1': 0.7507263219058687, 'number': 809} | {'precision': 0.29310344827586204, 'recall': 0.2857142857142857, 'f1': 0.2893617021276596, 'number': 119} | {'precision': 0.7658833768494343, 'recall': 0.8262910798122066, 'f1': 0.7949412827461607, 'number': 1065} | 0.7166 | 0.7827 | 0.7482 | 0.8134 | | 0.2896 | 13.0 | 130 | 0.6736 | {'precision': 0.7007963594994312, 'recall': 0.761433868974042, 'f1': 0.7298578199052134, 'number': 809} | {'precision': 0.2536231884057971, 'recall': 0.29411764705882354, 'f1': 0.2723735408560311, 'number': 119} | {'precision': 0.7527993109388458, 'recall': 0.8206572769953052, 'f1': 0.7852650494159928, 'number': 1065} | 0.7002 | 0.7652 | 0.7312 | 0.8091 | | 0.278 | 14.0 | 140 | 0.6619 | {'precision': 0.7066666666666667, 'recall': 0.7861557478368356, 'f1': 0.7442949093036864, 'number': 809} | {'precision': 0.30973451327433627, 'recall': 0.29411764705882354, 'f1': 0.3017241379310345, 'number': 119} | {'precision': 0.7631806395851339, 'recall': 0.8291079812206573, 'f1': 0.7947794779477948, 'number': 1065} | 0.7161 | 0.7797 | 0.7466 | 0.8172 | | 0.2785 | 15.0 | 150 | 0.6633 | {'precision': 0.7068004459308808, 'recall': 0.7836835599505563, 'f1': 0.7432590855803048, 'number': 809} | {'precision': 0.3025210084033613, 'recall': 0.3025210084033613, 'f1': 0.3025210084033613, 'number': 119} | {'precision': 0.757679180887372, 'recall': 0.8338028169014085, 'f1': 0.7939204291461779, 'number': 1065} | 0.7121 | 0.7817 | 0.7453 | 0.8174 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3