metadata
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 on the funsd dataset. It achieves the following results on the evaluation set:
- Loss: 0.7271
- Answer: {'precision': 0.7209821428571429, 'recall': 0.7985166872682324, 'f1': 0.7577712609970675, 'number': 809}
- Header: {'precision': 0.3308270676691729, 'recall': 0.3697478991596639, 'f1': 0.3492063492063492, 'number': 119}
- Question: {'precision': 0.7732049036777583, 'recall': 0.8291079812206573, 'f1': 0.8001812415043046, 'number': 1065}
- Overall Precision: 0.7246
- Overall Recall: 0.7893
- Overall F1: 0.7555
- Overall Accuracy: 0.8054
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 |
|---|---|---|---|---|---|---|---|---|---|---|
| 1.8393 | 1.0 | 10 | 1.5994 | {'precision': 0.02424942263279446, 'recall': 0.02595797280593325, 'f1': 0.02507462686567164, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.22250639386189258, 'recall': 0.16338028169014085, 'f1': 0.18841364374661615, 'number': 1065} | 0.1183 | 0.0978 | 0.1071 | 0.3781 |
| 1.4614 | 2.0 | 20 | 1.2520 | {'precision': 0.121765601217656, 'recall': 0.09888751545117429, 'f1': 0.10914051841746247, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.47543713572023316, 'recall': 0.536150234741784, 'f1': 0.503971756398941, 'number': 1065} | 0.3504 | 0.3266 | 0.3381 | 0.5844 |
| 1.1144 | 3.0 | 30 | 0.9610 | {'precision': 0.5, 'recall': 0.5278121137206427, 'f1': 0.513529765484065, 'number': 809} | {'precision': 0.037037037037037035, 'recall': 0.008403361344537815, 'f1': 0.0136986301369863, 'number': 119} | {'precision': 0.6224758560140474, 'recall': 0.6657276995305165, 'f1': 0.6433756805807623, 'number': 1065} | 0.5629 | 0.5705 | 0.5667 | 0.7246 |
| 0.8509 | 4.0 | 40 | 0.7961 | {'precision': 0.5943396226415094, 'recall': 0.7008652657601978, 'f1': 0.6432217810550198, 'number': 809} | {'precision': 0.3, 'recall': 0.12605042016806722, 'f1': 0.17751479289940827, 'number': 119} | {'precision': 0.6532188841201717, 'recall': 0.7145539906103286, 'f1': 0.6825112107623318, 'number': 1065} | 0.6192 | 0.6739 | 0.6454 | 0.7543 |
| 0.6724 | 5.0 | 50 | 0.7346 | {'precision': 0.6362683438155137, 'recall': 0.7503090234857849, 'f1': 0.6885989790130459, 'number': 809} | {'precision': 0.3466666666666667, 'recall': 0.2184873949579832, 'f1': 0.26804123711340205, 'number': 119} | {'precision': 0.6597444089456869, 'recall': 0.7755868544600939, 'f1': 0.7129909365558912, 'number': 1065} | 0.6396 | 0.7321 | 0.6827 | 0.7797 |
| 0.5743 | 6.0 | 60 | 0.7086 | {'precision': 0.6481481481481481, 'recall': 0.7787391841779975, 'f1': 0.7074677147669849, 'number': 809} | {'precision': 0.3424657534246575, 'recall': 0.21008403361344538, 'f1': 0.2604166666666667, 'number': 119} | {'precision': 0.7128116938950989, 'recall': 0.7784037558685446, 'f1': 0.7441651705565528, 'number': 1065} | 0.6721 | 0.7446 | 0.7065 | 0.7845 |
| 0.4963 | 7.0 | 70 | 0.6881 | {'precision': 0.6866952789699571, 'recall': 0.7911001236093943, 'f1': 0.7352096496266514, 'number': 809} | {'precision': 0.30392156862745096, 'recall': 0.2605042016806723, 'f1': 0.28054298642533937, 'number': 119} | {'precision': 0.7263249348392702, 'recall': 0.7849765258215963, 'f1': 0.7545126353790614, 'number': 1065} | 0.6897 | 0.7561 | 0.7214 | 0.7926 |
| 0.4392 | 8.0 | 80 | 0.7116 | {'precision': 0.6779487179487179, 'recall': 0.8170580964153276, 'f1': 0.741031390134529, 'number': 809} | {'precision': 0.28431372549019607, 'recall': 0.24369747899159663, 'f1': 0.26244343891402716, 'number': 119} | {'precision': 0.7322175732217573, 'recall': 0.8215962441314554, 'f1': 0.7743362831858407, 'number': 1065} | 0.6888 | 0.7852 | 0.7339 | 0.7886 |
| 0.3945 | 9.0 | 90 | 0.7000 | {'precision': 0.7060737527114967, 'recall': 0.8046971569839307, 'f1': 0.7521663778162911, 'number': 809} | {'precision': 0.2920353982300885, 'recall': 0.2773109243697479, 'f1': 0.28448275862068967, 'number': 119} | {'precision': 0.7502183406113537, 'recall': 0.8065727699530516, 'f1': 0.7773755656108599, 'number': 1065} | 0.7078 | 0.7742 | 0.7395 | 0.7989 |
| 0.3825 | 10.0 | 100 | 0.7006 | {'precision': 0.717607973421927, 'recall': 0.8009888751545118, 'f1': 0.7570093457943926, 'number': 809} | {'precision': 0.29464285714285715, 'recall': 0.2773109243697479, 'f1': 0.28571428571428575, 'number': 119} | {'precision': 0.7642418930762489, 'recall': 0.8187793427230047, 'f1': 0.7905711695376247, 'number': 1065} | 0.7203 | 0.7792 | 0.7486 | 0.8053 |
| 0.327 | 11.0 | 110 | 0.7180 | {'precision': 0.6969376979936642, 'recall': 0.8158220024721878, 'f1': 0.7517084282460138, 'number': 809} | {'precision': 0.2975206611570248, 'recall': 0.3025210084033613, 'f1': 0.3, 'number': 119} | {'precision': 0.7572898799313894, 'recall': 0.8291079812206573, 'f1': 0.7915732855221873, 'number': 1065} | 0.7068 | 0.7923 | 0.7471 | 0.7969 |
| 0.3136 | 12.0 | 120 | 0.7147 | {'precision': 0.7283950617283951, 'recall': 0.8022249690976514, 'f1': 0.7635294117647059, 'number': 809} | {'precision': 0.3305084745762712, 'recall': 0.3277310924369748, 'f1': 0.32911392405063294, 'number': 119} | {'precision': 0.7831111111111111, 'recall': 0.8272300469483568, 'f1': 0.8045662100456622, 'number': 1065} | 0.7352 | 0.7873 | 0.7604 | 0.8059 |
| 0.2943 | 13.0 | 130 | 0.7297 | {'precision': 0.7136659436008677, 'recall': 0.8133498145859085, 'f1': 0.7602541883304449, 'number': 809} | {'precision': 0.34210526315789475, 'recall': 0.3277310924369748, 'f1': 0.33476394849785407, 'number': 119} | {'precision': 0.7785588752196837, 'recall': 0.831924882629108, 'f1': 0.8043576940535634, 'number': 1065} | 0.7282 | 0.7943 | 0.7598 | 0.8001 |
| 0.2727 | 14.0 | 140 | 0.7284 | {'precision': 0.7275784753363229, 'recall': 0.8022249690976514, 'f1': 0.7630805408583187, 'number': 809} | {'precision': 0.3333333333333333, 'recall': 0.3697478991596639, 'f1': 0.350597609561753, 'number': 119} | {'precision': 0.7732049036777583, 'recall': 0.8291079812206573, 'f1': 0.8001812415043046, 'number': 1065} | 0.7276 | 0.7908 | 0.7579 | 0.8046 |
| 0.2753 | 15.0 | 150 | 0.7271 | {'precision': 0.7209821428571429, 'recall': 0.7985166872682324, 'f1': 0.7577712609970675, 'number': 809} | {'precision': 0.3308270676691729, 'recall': 0.3697478991596639, 'f1': 0.3492063492063492, 'number': 119} | {'precision': 0.7732049036777583, 'recall': 0.8291079812206573, 'f1': 0.8001812415043046, 'number': 1065} | 0.7246 | 0.7893 | 0.7555 | 0.8054 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1