--- 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: 0.7403 - Answer: {'precision': 0.73, 'recall': 0.8121137206427689, 'f1': 0.7688706846108836, 'number': 809} - Header: {'precision': 0.3611111111111111, 'recall': 0.4369747899159664, 'f1': 0.3954372623574144, 'number': 119} - Question: {'precision': 0.7853962600178095, 'recall': 0.828169014084507, 'f1': 0.8062157221206582, 'number': 1065} - Overall Precision: 0.7342 - Overall Recall: 0.7983 - Overall F1: 0.7649 - Overall Accuracy: 0.8101 ## 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: 16 ### Training results | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 1.3197 | 1.0 | 10 | 1.0997 | {'precision': 0.34190231362467866, 'recall': 0.3288009888751545, 'f1': 0.3352236925015753, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.5646958011996572, 'recall': 0.6187793427230047, 'f1': 0.5905017921146953, 'number': 1065} | 0.4756 | 0.4641 | 0.4698 | 0.6432 | | 0.9556 | 2.0 | 20 | 0.8488 | {'precision': 0.5481481481481482, 'recall': 0.6402966625463535, 'f1': 0.5906499429874572, 'number': 809} | {'precision': 0.038461538461538464, 'recall': 0.008403361344537815, 'f1': 0.013793103448275862, 'number': 119} | {'precision': 0.6639566395663956, 'recall': 0.6901408450704225, 'f1': 0.6767955801104972, 'number': 1065} | 0.6035 | 0.6292 | 0.6161 | 0.7343 | | 0.7263 | 3.0 | 30 | 0.7385 | {'precision': 0.645397489539749, 'recall': 0.7626699629171817, 'f1': 0.6991501416430596, 'number': 809} | {'precision': 0.11320754716981132, 'recall': 0.05042016806722689, 'f1': 0.06976744186046512, 'number': 119} | {'precision': 0.7092013888888888, 'recall': 0.7671361502347418, 'f1': 0.7370320252593595, 'number': 1065} | 0.6664 | 0.7225 | 0.6933 | 0.7743 | | 0.5842 | 4.0 | 40 | 0.6892 | {'precision': 0.6642487046632124, 'recall': 0.792336217552534, 'f1': 0.7226606538895153, 'number': 809} | {'precision': 0.21686746987951808, 'recall': 0.15126050420168066, 'f1': 0.1782178217821782, 'number': 119} | {'precision': 0.7226027397260274, 'recall': 0.7924882629107981, 'f1': 0.7559337214509628, 'number': 1065} | 0.6782 | 0.7541 | 0.7142 | 0.7964 | | 0.4945 | 5.0 | 50 | 0.6673 | {'precision': 0.6974416017797553, 'recall': 0.7750309023485785, 'f1': 0.734192037470726, 'number': 809} | {'precision': 0.30337078651685395, 'recall': 0.226890756302521, 'f1': 0.2596153846153846, 'number': 119} | {'precision': 0.7408637873754153, 'recall': 0.8375586854460094, 'f1': 0.7862494490965183, 'number': 1065} | 0.7053 | 0.7757 | 0.7388 | 0.8033 | | 0.4343 | 6.0 | 60 | 0.6592 | {'precision': 0.6962962962962963, 'recall': 0.8133498145859085, 'f1': 0.750285062713797, 'number': 809} | {'precision': 0.29411764705882354, 'recall': 0.25210084033613445, 'f1': 0.27149321266968324, 'number': 119} | {'precision': 0.7504173622704507, 'recall': 0.844131455399061, 'f1': 0.7945205479452054, 'number': 1065} | 0.7069 | 0.7963 | 0.7489 | 0.8077 | | 0.3681 | 7.0 | 70 | 0.6624 | {'precision': 0.7049891540130152, 'recall': 0.8034610630407911, 'f1': 0.7510109763142693, 'number': 809} | {'precision': 0.30158730158730157, 'recall': 0.31932773109243695, 'f1': 0.310204081632653, 'number': 119} | {'precision': 0.7659758203799655, 'recall': 0.8328638497652582, 'f1': 0.7980206927575348, 'number': 1065} | 0.7140 | 0.7903 | 0.7502 | 0.8090 | | 0.3312 | 8.0 | 80 | 0.6825 | {'precision': 0.7097826086956521, 'recall': 0.8071693448702101, 'f1': 0.7553499132446501, 'number': 809} | {'precision': 0.32142857142857145, 'recall': 0.37815126050420167, 'f1': 0.3474903474903475, 'number': 119} | {'precision': 0.7703056768558952, 'recall': 0.828169014084507, 'f1': 0.7981900452488688, 'number': 1065} | 0.7166 | 0.7928 | 0.7527 | 0.8078 | | 0.2955 | 9.0 | 90 | 0.7009 | {'precision': 0.7141316073354909, 'recall': 0.8182941903584673, 'f1': 0.7626728110599078, 'number': 809} | {'precision': 0.3493150684931507, 'recall': 0.42857142857142855, 'f1': 0.38490566037735846, 'number': 119} | {'precision': 0.7753108348134992, 'recall': 0.819718309859155, 'f1': 0.7968963943404839, 'number': 1065} | 0.7212 | 0.7958 | 0.7567 | 0.8034 | | 0.2888 | 10.0 | 100 | 0.6894 | {'precision': 0.7125813449023861, 'recall': 0.8121137206427689, 'f1': 0.7590987868284228, 'number': 809} | {'precision': 0.37272727272727274, 'recall': 0.3445378151260504, 'f1': 0.35807860262008734, 'number': 119} | {'precision': 0.7917783735478106, 'recall': 0.831924882629108, 'f1': 0.8113553113553114, 'number': 1065} | 0.7364 | 0.7948 | 0.7645 | 0.8140 | | 0.2482 | 11.0 | 110 | 0.7131 | {'precision': 0.7191854233654876, 'recall': 0.8294190358467244, 'f1': 0.7703788748564868, 'number': 809} | {'precision': 0.3, 'recall': 0.40336134453781514, 'f1': 0.34408602150537637, 'number': 119} | {'precision': 0.7843833185448092, 'recall': 0.8300469483568075, 'f1': 0.8065693430656934, 'number': 1065} | 0.7221 | 0.8043 | 0.7610 | 0.8084 | | 0.2297 | 12.0 | 120 | 0.7189 | {'precision': 0.7373167981961668, 'recall': 0.8084054388133498, 'f1': 0.7712264150943396, 'number': 809} | {'precision': 0.3484848484848485, 'recall': 0.3865546218487395, 'f1': 0.3665338645418326, 'number': 119} | {'precision': 0.7730434782608696, 'recall': 0.8347417840375587, 'f1': 0.8027088036117382, 'number': 1065} | 0.7326 | 0.7973 | 0.7636 | 0.8125 | | 0.2168 | 13.0 | 130 | 0.7283 | {'precision': 0.723986856516977, 'recall': 0.8170580964153276, 'f1': 0.7677119628339142, 'number': 809} | {'precision': 0.33793103448275863, 'recall': 0.4117647058823529, 'f1': 0.37121212121212116, 'number': 119} | {'precision': 0.7878245299910475, 'recall': 0.8262910798122066, 'f1': 0.8065994500458296, 'number': 1065} | 0.7310 | 0.7978 | 0.7630 | 0.8099 | | 0.2011 | 14.0 | 140 | 0.7318 | {'precision': 0.7338530066815144, 'recall': 0.8145859085290482, 'f1': 0.7721148213239603, 'number': 809} | {'precision': 0.3493150684931507, 'recall': 0.42857142857142855, 'f1': 0.38490566037735846, 'number': 119} | {'precision': 0.7833775419982316, 'recall': 0.831924882629108, 'f1': 0.8069216757741348, 'number': 1065} | 0.7338 | 0.8008 | 0.7658 | 0.8112 | | 0.1948 | 15.0 | 150 | 0.7391 | {'precision': 0.7216721672167217, 'recall': 0.8108776266996292, 'f1': 0.7636786961583235, 'number': 809} | {'precision': 0.3561643835616438, 'recall': 0.4369747899159664, 'f1': 0.39245283018867927, 'number': 119} | {'precision': 0.7848214285714286, 'recall': 0.8253521126760563, 'f1': 0.8045766590389016, 'number': 1065} | 0.7297 | 0.7963 | 0.7615 | 0.8076 | | 0.1955 | 16.0 | 160 | 0.7403 | {'precision': 0.73, 'recall': 0.8121137206427689, 'f1': 0.7688706846108836, 'number': 809} | {'precision': 0.3611111111111111, 'recall': 0.4369747899159664, 'f1': 0.3954372623574144, 'number': 119} | {'precision': 0.7853962600178095, 'recall': 0.828169014084507, 'f1': 0.8062157221206582, 'number': 1065} | 0.7342 | 0.7983 | 0.7649 | 0.8101 | ### Framework versions - Transformers 4.42.4 - Pytorch 2.3.1+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1