--- library_name: transformers license: mit base_model: microsoft/layoutlm-base-uncased 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: 0.6701 - Answer: {'precision': 0.6956043956043956, 'recall': 0.7824474660074165, 'f1': 0.7364746945898778, 'number': 809} - Header: {'precision': 0.2846715328467153, 'recall': 0.3277310924369748, 'f1': 0.3046875, 'number': 119} - Question: {'precision': 0.7870289219982471, 'recall': 0.8431924882629108, 'f1': 0.8141432456935629, 'number': 1065} - Overall Precision: 0.7176 - Overall Recall: 0.7878 - Overall F1: 0.7510 - Overall Accuracy: 0.8157 ## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - 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 | |:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 1.8085 | 1.0 | 10 | 1.6056 | {'precision': 0.033630069238377844, 'recall': 0.042027194066749075, 'f1': 0.03736263736263736, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.2052679382379655, 'recall': 0.21220657276995306, 'f1': 0.20867959372114497, 'number': 1065} | 0.1231 | 0.1305 | 0.1267 | 0.3778 | | 1.4421 | 2.0 | 20 | 1.2735 | {'precision': 0.16164383561643836, 'recall': 0.14585908529048208, 'f1': 0.1533463287849253, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4393530997304582, 'recall': 0.4591549295774648, 'f1': 0.4490358126721763, 'number': 1065} | 0.3294 | 0.3046 | 0.3165 | 0.5551 | | 1.0974 | 3.0 | 30 | 0.9812 | {'precision': 0.4577114427860697, 'recall': 0.45488257107540175, 'f1': 0.45629262244265345, 'number': 809} | {'precision': 0.03571428571428571, 'recall': 0.008403361344537815, 'f1': 0.013605442176870748, 'number': 119} | {'precision': 0.5671521035598706, 'recall': 0.6582159624413145, 'f1': 0.6093003042155585, 'number': 1065} | 0.5174 | 0.5369 | 0.5270 | 0.7087 | | 0.8437 | 4.0 | 40 | 0.8026 | {'precision': 0.6002214839424141, 'recall': 0.6699629171817059, 'f1': 0.6331775700934579, 'number': 809} | {'precision': 0.2698412698412698, 'recall': 0.14285714285714285, 'f1': 0.18681318681318682, 'number': 119} | {'precision': 0.6771378708551483, 'recall': 0.7286384976525822, 'f1': 0.7019448213478063, 'number': 1065} | 0.6321 | 0.6698 | 0.6504 | 0.7593 | | 0.6743 | 5.0 | 50 | 0.7231 | {'precision': 0.6385281385281385, 'recall': 0.7292954264524104, 'f1': 0.6809001731102134, 'number': 809} | {'precision': 0.28735632183908044, 'recall': 0.21008403361344538, 'f1': 0.24271844660194175, 'number': 119} | {'precision': 0.6861022364217252, 'recall': 0.8065727699530516, 'f1': 0.7414760466119981, 'number': 1065} | 0.6513 | 0.7396 | 0.6927 | 0.7851 | | 0.5721 | 6.0 | 60 | 0.6909 | {'precision': 0.6521739130434783, 'recall': 0.7787391841779975, 'f1': 0.7098591549295774, 'number': 809} | {'precision': 0.25287356321839083, 'recall': 0.18487394957983194, 'f1': 0.21359223300970878, 'number': 119} | {'precision': 0.7174657534246576, 'recall': 0.7868544600938967, 'f1': 0.7505597850425437, 'number': 1065} | 0.6709 | 0.7476 | 0.7072 | 0.7896 | | 0.4865 | 7.0 | 70 | 0.6542 | {'precision': 0.6832432432432433, 'recall': 0.7812113720642769, 'f1': 0.7289504036908883, 'number': 809} | {'precision': 0.2975206611570248, 'recall': 0.3025210084033613, 'f1': 0.3, 'number': 119} | {'precision': 0.7537379067722075, 'recall': 0.8046948356807512, 'f1': 0.7783832879200727, 'number': 1065} | 0.6986 | 0.7652 | 0.7304 | 0.8039 | | 0.4318 | 8.0 | 80 | 0.6547 | {'precision': 0.6796536796536796, 'recall': 0.7762669962917181, 'f1': 0.7247547605308712, 'number': 809} | {'precision': 0.26515151515151514, 'recall': 0.29411764705882354, 'f1': 0.2788844621513944, 'number': 119} | {'precision': 0.764402407566638, 'recall': 0.8347417840375587, 'f1': 0.7980251346499103, 'number': 1065} | 0.6994 | 0.7787 | 0.7369 | 0.8061 | | 0.3734 | 9.0 | 90 | 0.6533 | {'precision': 0.6978260869565217, 'recall': 0.7935723114956736, 'f1': 0.742625795257374, 'number': 809} | {'precision': 0.2971014492753623, 'recall': 0.3445378151260504, 'f1': 0.31906614785992216, 'number': 119} | {'precision': 0.7701543739279588, 'recall': 0.8431924882629108, 'f1': 0.8050201703272075, 'number': 1065} | 0.7109 | 0.7933 | 0.7498 | 0.8063 | | 0.3735 | 10.0 | 100 | 0.6473 | {'precision': 0.7034178610804851, 'recall': 0.788627935723115, 'f1': 0.7435897435897435, 'number': 809} | {'precision': 0.3220338983050847, 'recall': 0.31932773109243695, 'f1': 0.32067510548523204, 'number': 119} | {'precision': 0.7897526501766784, 'recall': 0.8394366197183099, 'f1': 0.8138370505234409, 'number': 1065} | 0.7279 | 0.7878 | 0.7566 | 0.8158 | | 0.3068 | 11.0 | 110 | 0.6692 | {'precision': 0.6868250539956804, 'recall': 0.7861557478368356, 'f1': 0.7331412103746396, 'number': 809} | {'precision': 0.2866666666666667, 'recall': 0.36134453781512604, 'f1': 0.3197026022304833, 'number': 119} | {'precision': 0.7710843373493976, 'recall': 0.8413145539906103, 'f1': 0.8046699595868883, 'number': 1065} | 0.7038 | 0.7903 | 0.7445 | 0.8045 | | 0.2884 | 12.0 | 120 | 0.6608 | {'precision': 0.7064116985376828, 'recall': 0.7762669962917181, 'f1': 0.7396937573616018, 'number': 809} | {'precision': 0.3076923076923077, 'recall': 0.33613445378151263, 'f1': 0.321285140562249, 'number': 119} | {'precision': 0.7878521126760564, 'recall': 0.8403755868544601, 'f1': 0.8132666969559291, 'number': 1065} | 0.7253 | 0.7842 | 0.7536 | 0.8147 | | 0.273 | 13.0 | 130 | 0.6682 | {'precision': 0.6948408342480791, 'recall': 0.7824474660074165, 'f1': 0.7360465116279069, 'number': 809} | {'precision': 0.29927007299270075, 'recall': 0.3445378151260504, 'f1': 0.3203125, 'number': 119} | {'precision': 0.7893805309734513, 'recall': 0.8375586854460094, 'f1': 0.812756264236902, 'number': 1065} | 0.7190 | 0.7858 | 0.7509 | 0.8152 | | 0.2539 | 14.0 | 140 | 0.6689 | {'precision': 0.6976744186046512, 'recall': 0.7787391841779975, 'f1': 0.7359813084112149, 'number': 809} | {'precision': 0.2826086956521739, 'recall': 0.3277310924369748, 'f1': 0.3035019455252918, 'number': 119} | {'precision': 0.787215411558669, 'recall': 0.844131455399061, 'f1': 0.8146805618486633, 'number': 1065} | 0.7183 | 0.7868 | 0.7510 | 0.8158 | | 0.2552 | 15.0 | 150 | 0.6701 | {'precision': 0.6956043956043956, 'recall': 0.7824474660074165, 'f1': 0.7364746945898778, 'number': 809} | {'precision': 0.2846715328467153, 'recall': 0.3277310924369748, 'f1': 0.3046875, 'number': 119} | {'precision': 0.7870289219982471, 'recall': 0.8431924882629108, 'f1': 0.8141432456935629, 'number': 1065} | 0.7176 | 0.7878 | 0.7510 | 0.8157 | ### Framework versions - Transformers 4.50.0.dev0 - Pytorch 2.5.1+cu124 - Datasets 3.3.2 - Tokenizers 0.21.0