--- license: mit base_model: microsoft/layoutlm-base-uncased tags: - generated_from_trainer datasets: - funsd model-index: - name: layoutlm-funsd2 results: [] --- # layoutlm-funsd2 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: 0.6965 - Answer: {'precision': 0.7010869565217391, 'recall': 0.7972805933250927, 'f1': 0.746096009253904, 'number': 809} - Header: {'precision': 0.3305785123966942, 'recall': 0.33613445378151263, 'f1': 0.33333333333333337, 'number': 119} - Question: {'precision': 0.7692307692307693, 'recall': 0.8262910798122066, 'f1': 0.7967406066093254, 'number': 1065} - Overall Precision: 0.7162 - Overall Recall: 0.7852 - Overall F1: 0.7492 - Overall Accuracy: 0.8006 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 1.8343 | 1.0 | 10 | 1.5921 | {'precision': 0.006666666666666667, 'recall': 0.006180469715698393, 'f1': 0.006414368184733804, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.22067901234567902, 'recall': 0.13427230046948357, 'f1': 0.166958552247519, 'number': 1065} | 0.1059 | 0.0743 | 0.0873 | 0.3510 | | 1.4828 | 2.0 | 20 | 1.2849 | {'precision': 0.2738799661876585, 'recall': 0.4004944375772559, 'f1': 0.32530120481927705, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.38058114812189936, 'recall': 0.504225352112676, 'f1': 0.43376413570274636, 'number': 1065} | 0.3314 | 0.4320 | 0.3751 | 0.5951 | | 1.1444 | 3.0 | 30 | 0.9563 | {'precision': 0.4725897920604915, 'recall': 0.6180469715698393, 'f1': 0.5356186395286556, 'number': 809} | {'precision': 0.041666666666666664, 'recall': 0.01680672268907563, 'f1': 0.02395209580838323, 'number': 119} | {'precision': 0.5378020265003897, 'recall': 0.647887323943662, 'f1': 0.5877342419080069, 'number': 1065} | 0.4990 | 0.5981 | 0.5440 | 0.6955 | | 0.8658 | 4.0 | 40 | 0.7885 | {'precision': 0.5757009345794393, 'recall': 0.761433868974042, 'f1': 0.6556679084619478, 'number': 809} | {'precision': 0.1388888888888889, 'recall': 0.08403361344537816, 'f1': 0.10471204188481677, 'number': 119} | {'precision': 0.6567299006323396, 'recall': 0.6826291079812207, 'f1': 0.6694290976058932, 'number': 1065} | 0.6016 | 0.6789 | 0.6379 | 0.7601 | | 0.6833 | 5.0 | 50 | 0.7124 | {'precision': 0.64375, 'recall': 0.7639060568603214, 'f1': 0.6986998304126625, 'number': 809} | {'precision': 0.35, 'recall': 0.23529411764705882, 'f1': 0.28140703517587945, 'number': 119} | {'precision': 0.6729354047424366, 'recall': 0.7727699530516432, 'f1': 0.7194055944055944, 'number': 1065} | 0.6491 | 0.7371 | 0.6903 | 0.7810 | | 0.5898 | 6.0 | 60 | 0.6874 | {'precision': 0.6227141482194418, 'recall': 0.799752781211372, 'f1': 0.7002164502164502, 'number': 809} | {'precision': 0.3411764705882353, 'recall': 0.24369747899159663, 'f1': 0.28431372549019607, 'number': 119} | {'precision': 0.7236492471213464, 'recall': 0.7671361502347418, 'f1': 0.7447584320875114, 'number': 1065} | 0.6627 | 0.7491 | 0.7033 | 0.7851 | | 0.5126 | 7.0 | 70 | 0.6599 | {'precision': 0.6705632306057385, 'recall': 0.7799752781211372, 'f1': 0.7211428571428572, 'number': 809} | {'precision': 0.32673267326732675, 'recall': 0.2773109243697479, 'f1': 0.30000000000000004, 'number': 119} | {'precision': 0.7427821522309711, 'recall': 0.7971830985915493, 'f1': 0.7690217391304347, 'number': 1065} | 0.6924 | 0.7592 | 0.7243 | 0.7963 | | 0.4534 | 8.0 | 80 | 0.6562 | {'precision': 0.670490093847758, 'recall': 0.7948084054388134, 'f1': 0.7273755656108597, 'number': 809} | {'precision': 0.2966101694915254, 'recall': 0.29411764705882354, 'f1': 0.2953586497890296, 'number': 119} | {'precision': 0.7476475620188195, 'recall': 0.8206572769953052, 'f1': 0.7824529991047449, 'number': 1065} | 0.6910 | 0.7787 | 0.7322 | 0.7954 | | 0.3984 | 9.0 | 90 | 0.6561 | {'precision': 0.6838709677419355, 'recall': 0.7861557478368356, 'f1': 0.7314548591144335, 'number': 809} | {'precision': 0.3333333333333333, 'recall': 0.3025210084033613, 'f1': 0.3171806167400881, 'number': 119} | {'precision': 0.7555555555555555, 'recall': 0.8300469483568075, 'f1': 0.7910514541387024, 'number': 1065} | 0.7047 | 0.7807 | 0.7408 | 0.7986 | | 0.3865 | 10.0 | 100 | 0.6673 | {'precision': 0.6877005347593583, 'recall': 0.7948084054388134, 'f1': 0.7373853211009175, 'number': 809} | {'precision': 0.31666666666666665, 'recall': 0.31932773109243695, 'f1': 0.3179916317991632, 'number': 119} | {'precision': 0.7613240418118467, 'recall': 0.8206572769953052, 'f1': 0.7898779936737461, 'number': 1065} | 0.7059 | 0.7802 | 0.7412 | 0.8019 | | 0.3343 | 11.0 | 110 | 0.6761 | {'precision': 0.6853220696937699, 'recall': 0.8022249690976514, 'f1': 0.7391799544419134, 'number': 809} | {'precision': 0.336283185840708, 'recall': 0.31932773109243695, 'f1': 0.32758620689655166, 'number': 119} | {'precision': 0.7692307692307693, 'recall': 0.8262910798122066, 'f1': 0.7967406066093254, 'number': 1065} | 0.7110 | 0.7863 | 0.7467 | 0.7998 | | 0.314 | 12.0 | 120 | 0.6772 | {'precision': 0.6989130434782609, 'recall': 0.7948084054388134, 'f1': 0.7437825332562175, 'number': 809} | {'precision': 0.34545454545454546, 'recall': 0.31932773109243695, 'f1': 0.3318777292576419, 'number': 119} | {'precision': 0.7698343504795118, 'recall': 0.8291079812206573, 'f1': 0.7983725135623869, 'number': 1065} | 0.7184 | 0.7847 | 0.7501 | 0.8053 | | 0.3008 | 13.0 | 130 | 0.6878 | {'precision': 0.7048648648648649, 'recall': 0.8059332509270705, 'f1': 0.7520184544405998, 'number': 809} | {'precision': 0.33620689655172414, 'recall': 0.3277310924369748, 'f1': 0.33191489361702126, 'number': 119} | {'precision': 0.7689594356261023, 'recall': 0.8187793427230047, 'f1': 0.793087767166894, 'number': 1065} | 0.7186 | 0.7842 | 0.75 | 0.8033 | | 0.2797 | 14.0 | 140 | 0.6948 | {'precision': 0.7027322404371584, 'recall': 0.7948084054388134, 'f1': 0.7459396751740139, 'number': 809} | {'precision': 0.31746031746031744, 'recall': 0.33613445378151263, 'f1': 0.32653061224489793, 'number': 119} | {'precision': 0.7661996497373029, 'recall': 0.8215962441314554, 'f1': 0.7929315813321249, 'number': 1065} | 0.7137 | 0.7817 | 0.7462 | 0.8017 | | 0.2722 | 15.0 | 150 | 0.6965 | {'precision': 0.7010869565217391, 'recall': 0.7972805933250927, 'f1': 0.746096009253904, 'number': 809} | {'precision': 0.3305785123966942, 'recall': 0.33613445378151263, 'f1': 0.33333333333333337, 'number': 119} | {'precision': 0.7692307692307693, 'recall': 0.8262910798122066, 'f1': 0.7967406066093254, 'number': 1065} | 0.7162 | 0.7852 | 0.7492 | 0.8006 | ### Framework versions - Transformers 4.41.2 - Pytorch 2.3.1+cu121 - Datasets 2.19.2 - Tokenizers 0.19.1