--- license: mit base_model: microsoft/layoutlm-base-uncased tags: - generated_from_trainer datasets: - funsd model-index: - name: layout-lm results: [] --- # layout-lm 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: 0.6696 - Answer: {'precision': 0.7092896174863388, 'recall': 0.8022249690976514, 'f1': 0.7529002320185615, 'number': 809} - Header: {'precision': 0.26618705035971224, 'recall': 0.31092436974789917, 'f1': 0.2868217054263566, 'number': 119} - Question: {'precision': 0.7788632326820604, 'recall': 0.8234741784037559, 'f1': 0.8005476951163851, 'number': 1065} - Overall Precision: 0.7170 - Overall Recall: 0.7842 - Overall F1: 0.7491 - Overall Accuracy: 0.8090 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 1.7756 | 1.0 | 10 | 1.5443 | {'precision': 0.022977022977022976, 'recall': 0.02843016069221261, 'f1': 0.025414364640883976, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.18486486486486486, 'recall': 0.16056338028169015, 'f1': 0.17185929648241205, 'number': 1065} | 0.1007 | 0.0973 | 0.0990 | 0.3934 | | 1.4156 | 2.0 | 20 | 1.2218 | {'precision': 0.2844311377245509, 'recall': 0.3522867737948084, 'f1': 0.3147432357813363, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4658151765589782, 'recall': 0.5821596244131455, 'f1': 0.5175292153589315, 'number': 1065} | 0.3879 | 0.4541 | 0.4184 | 0.5974 | | 1.0947 | 3.0 | 30 | 0.9351 | {'precision': 0.45348837209302323, 'recall': 0.5784919653893696, 'f1': 0.5084193373166758, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.5731800766283525, 'recall': 0.7023474178403756, 'f1': 0.6312236286919831, 'number': 1065} | 0.5155 | 0.6101 | 0.5588 | 0.7042 | | 0.8401 | 4.0 | 40 | 0.8011 | {'precision': 0.5671361502347417, 'recall': 0.7466007416563659, 'f1': 0.6446104589114193, 'number': 809} | {'precision': 0.03636363636363636, 'recall': 0.01680672268907563, 'f1': 0.022988505747126436, 'number': 119} | {'precision': 0.6641285956006768, 'recall': 0.7370892018779343, 'f1': 0.6987093902981754, 'number': 1065} | 0.6043 | 0.6979 | 0.6477 | 0.7447 | | 0.6784 | 5.0 | 50 | 0.7088 | {'precision': 0.6298568507157464, 'recall': 0.761433868974042, 'f1': 0.689423614997202, 'number': 809} | {'precision': 0.13333333333333333, 'recall': 0.08403361344537816, 'f1': 0.10309278350515463, 'number': 119} | {'precision': 0.6869009584664537, 'recall': 0.8075117370892019, 'f1': 0.7423392317652138, 'number': 1065} | 0.6447 | 0.7456 | 0.6915 | 0.7832 | | 0.5803 | 6.0 | 60 | 0.6837 | {'precision': 0.632512315270936, 'recall': 0.7935723114956736, 'f1': 0.7039473684210525, 'number': 809} | {'precision': 0.17, 'recall': 0.14285714285714285, 'f1': 0.15525114155251143, 'number': 119} | {'precision': 0.7255244755244755, 'recall': 0.7793427230046949, 'f1': 0.7514712539610684, 'number': 1065} | 0.6591 | 0.7471 | 0.7004 | 0.7899 | | 0.5058 | 7.0 | 70 | 0.6616 | {'precision': 0.6632337796086509, 'recall': 0.796044499381953, 'f1': 0.7235955056179776, 'number': 809} | {'precision': 0.22935779816513763, 'recall': 0.21008403361344538, 'f1': 0.2192982456140351, 'number': 119} | {'precision': 0.7556917688266199, 'recall': 0.8103286384976526, 'f1': 0.7820570910738559, 'number': 1065} | 0.6895 | 0.7687 | 0.7269 | 0.8049 | | 0.4504 | 8.0 | 80 | 0.6497 | {'precision': 0.6694045174537988, 'recall': 0.8059332509270705, 'f1': 0.7313516545148627, 'number': 809} | {'precision': 0.24778761061946902, 'recall': 0.23529411764705882, 'f1': 0.2413793103448276, 'number': 119} | {'precision': 0.7757255936675461, 'recall': 0.828169014084507, 'f1': 0.8010899182561309, 'number': 1065} | 0.7023 | 0.7837 | 0.7408 | 0.8126 | | 0.4046 | 9.0 | 90 | 0.6455 | {'precision': 0.6864406779661016, 'recall': 0.8009888751545118, 'f1': 0.7393040501996578, 'number': 809} | {'precision': 0.25396825396825395, 'recall': 0.2689075630252101, 'f1': 0.2612244897959184, 'number': 119} | {'precision': 0.7812223206377326, 'recall': 0.828169014084507, 'f1': 0.8040109389243391, 'number': 1065} | 0.7103 | 0.7837 | 0.7452 | 0.8152 | | 0.3936 | 10.0 | 100 | 0.6659 | {'precision': 0.6867088607594937, 'recall': 0.8046971569839307, 'f1': 0.7410358565737052, 'number': 809} | {'precision': 0.24193548387096775, 'recall': 0.25210084033613445, 'f1': 0.2469135802469136, 'number': 119} | {'precision': 0.7786811201445348, 'recall': 0.8093896713615023, 'f1': 0.7937384898710865, 'number': 1065} | 0.7081 | 0.7742 | 0.7397 | 0.8078 | | 0.3364 | 11.0 | 110 | 0.6591 | {'precision': 0.6890308839190629, 'recall': 0.799752781211372, 'f1': 0.7402745995423341, 'number': 809} | {'precision': 0.2824427480916031, 'recall': 0.31092436974789917, 'f1': 0.29600000000000004, 'number': 119} | {'precision': 0.7735682819383259, 'recall': 0.8244131455399061, 'f1': 0.7981818181818181, 'number': 1065} | 0.7084 | 0.7837 | 0.7442 | 0.8115 | | 0.3265 | 12.0 | 120 | 0.6682 | {'precision': 0.6912393162393162, 'recall': 0.799752781211372, 'f1': 0.7415472779369628, 'number': 809} | {'precision': 0.26666666666666666, 'recall': 0.3025210084033613, 'f1': 0.28346456692913385, 'number': 119} | {'precision': 0.7784697508896797, 'recall': 0.8215962441314554, 'f1': 0.7994518044769301, 'number': 1065} | 0.7098 | 0.7817 | 0.7440 | 0.8077 | | 0.3079 | 13.0 | 130 | 0.6711 | {'precision': 0.7035830618892508, 'recall': 0.8009888751545118, 'f1': 0.7491329479768787, 'number': 809} | {'precision': 0.26717557251908397, 'recall': 0.29411764705882354, 'f1': 0.28, 'number': 119} | {'precision': 0.7762114537444934, 'recall': 0.8272300469483568, 'f1': 0.8009090909090909, 'number': 1065} | 0.7151 | 0.7847 | 0.7483 | 0.8090 | | 0.2868 | 14.0 | 140 | 0.6677 | {'precision': 0.704225352112676, 'recall': 0.8034610630407911, 'f1': 0.7505773672055426, 'number': 809} | {'precision': 0.2835820895522388, 'recall': 0.31932773109243695, 'f1': 0.30039525691699603, 'number': 119} | {'precision': 0.7804444444444445, 'recall': 0.8244131455399061, 'f1': 0.8018264840182647, 'number': 1065} | 0.7177 | 0.7858 | 0.7502 | 0.8111 | | 0.2863 | 15.0 | 150 | 0.6696 | {'precision': 0.7092896174863388, 'recall': 0.8022249690976514, 'f1': 0.7529002320185615, 'number': 809} | {'precision': 0.26618705035971224, 'recall': 0.31092436974789917, 'f1': 0.2868217054263566, 'number': 119} | {'precision': 0.7788632326820604, 'recall': 0.8234741784037559, 'f1': 0.8005476951163851, 'number': 1065} | 0.7170 | 0.7842 | 0.7491 | 0.8090 | ### Framework versions - Transformers 4.43.2 - Pytorch 2.3.1+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1