layoutlm-FUNSD-only-1fold

pabloma09/layoutlm-FUNSD-only-1fold

layoutlm-FUNSD-only-1fold is a token classification model from pabloma09. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

24% of all-time downloads

All-time downloads

Public

Parameters

113M

6.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors451 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: layoutlm
Access: Public
Created: Mar 6, 2025
Updated: Mar 6, 2025
SHA: ec783919

Try a prompt

Base models

microsoft/layoutlm-base-uncased

Datasets

funsd

Model card

From the Hugging Face model README

layoutlm-FUNSD-only-1fold

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: 0.6561
Eader: {'precision': 0.3770491803278688, 'recall': 0.27710843373493976, 'f1': 0.3194444444444444, 'number': 83}
Nswer: {'precision': 0.5213675213675214, 'recall': 0.5951219512195122, 'f1': 0.5558086560364465, 'number': 205}
Uestion: {'precision': 0.3722627737226277, 'recall': 0.44155844155844154, 'f1': 0.40396039603960393, 'number': 231}
Overall Precision: 0.4341
Overall Recall: 0.4759
Overall F1: 0.4540
Overall Accuracy: 0.7927

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 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	Eader	Nswer	Uestion	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
1.2996	1.0	8	1.0787	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 83}	{'precision': 0.0748502994011976, 'recall': 0.24390243902439024, 'f1': 0.11454753722794961, 'number': 205}	{'precision': 0.0704647676161919, 'recall': 0.20346320346320346, 'f1': 0.10467706013363029, 'number': 231}	0.0727	0.1869	0.1046	0.6075
1.0224	2.0	16	0.8740	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 83}	{'precision': 0.20823798627002288, 'recall': 0.44390243902439025, 'f1': 0.2834890965732087, 'number': 205}	{'precision': 0.17551963048498845, 'recall': 0.329004329004329, 'f1': 0.2289156626506024, 'number': 231}	0.1920	0.3218	0.2405	0.7001
0.8193	3.0	24	0.6924	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 83}	{'precision': 0.310126582278481, 'recall': 0.47804878048780486, 'f1': 0.3761996161228407, 'number': 205}	{'precision': 0.25671641791044775, 'recall': 0.3722943722943723, 'f1': 0.30388692579505294, 'number': 231}	0.2759	0.3545	0.3103	0.7519
0.6764	4.0	32	0.6312	{'precision': 0.14285714285714285, 'recall': 0.04819277108433735, 'f1': 0.07207207207207209, 'number': 83}	{'precision': 0.3914590747330961, 'recall': 0.5365853658536586, 'f1': 0.45267489711934156, 'number': 205}	{'precision': 0.36, 'recall': 0.42857142857142855, 'f1': 0.391304347826087, 'number': 231}	0.3647	0.4104	0.3862	0.7634
0.5456	5.0	40	0.5856	{'precision': 0.3, 'recall': 0.18072289156626506, 'f1': 0.2255639097744361, 'number': 83}	{'precision': 0.42424242424242425, 'recall': 0.5463414634146342, 'f1': 0.47761194029850745, 'number': 205}	{'precision': 0.38022813688212925, 'recall': 0.4329004329004329, 'f1': 0.4048582995951417, 'number': 231}	0.3934	0.4374	0.4142	0.7846
0.4547	6.0	48	0.5899	{'precision': 0.4074074074074074, 'recall': 0.26506024096385544, 'f1': 0.32116788321167883, 'number': 83}	{'precision': 0.44129554655870445, 'recall': 0.5317073170731708, 'f1': 0.4823008849557522, 'number': 205}	{'precision': 0.35094339622641507, 'recall': 0.4025974025974026, 'f1': 0.37500000000000006, 'number': 231}	0.3958	0.4316	0.4129	0.7827
0.3815	7.0	56	0.5921	{'precision': 0.3888888888888889, 'recall': 0.25301204819277107, 'f1': 0.3065693430656934, 'number': 83}	{'precision': 0.483739837398374, 'recall': 0.5804878048780487, 'f1': 0.5277161862527716, 'number': 205}	{'precision': 0.34657039711191334, 'recall': 0.4155844155844156, 'f1': 0.3779527559055118, 'number': 231}	0.4090	0.4547	0.4307	0.7893
0.324	8.0	64	0.5872	{'precision': 0.5, 'recall': 0.26506024096385544, 'f1': 0.3464566929133859, 'number': 83}	{'precision': 0.4957983193277311, 'recall': 0.5756097560975609, 'f1': 0.5327313769751693, 'number': 205}	{'precision': 0.39543726235741444, 'recall': 0.45021645021645024, 'f1': 0.42105263157894735, 'number': 231}	0.4477	0.4701	0.4586	0.7989
0.284	9.0	72	0.6026	{'precision': 0.3968253968253968, 'recall': 0.30120481927710846, 'f1': 0.34246575342465757, 'number': 83}	{'precision': 0.4717741935483871, 'recall': 0.5707317073170731, 'f1': 0.5165562913907285, 'number': 205}	{'precision': 0.35789473684210527, 'recall': 0.44155844155844154, 'f1': 0.39534883720930236, 'number': 231}	0.4094	0.4701	0.4377	0.7897
0.249	10.0	80	0.6137	{'precision': 0.4423076923076923, 'recall': 0.27710843373493976, 'f1': 0.34074074074074073, 'number': 83}	{'precision': 0.5041322314049587, 'recall': 0.5951219512195122, 'f1': 0.5458612975391499, 'number': 205}	{'precision': 0.3607142857142857, 'recall': 0.43722943722943725, 'f1': 0.39530332681017616, 'number': 231}	0.4286	0.4740	0.4501	0.7981
0.2288	11.0	88	0.6367	{'precision': 0.38571428571428573, 'recall': 0.3253012048192771, 'f1': 0.35294117647058826, 'number': 83}	{'precision': 0.48717948717948717, 'recall': 0.5560975609756098, 'f1': 0.5193621867881548, 'number': 205}	{'precision': 0.38267148014440433, 'recall': 0.4588744588744589, 'f1': 0.4173228346456693, 'number': 231}	0.4251	0.4759	0.4491	0.7912
0.2031	12.0	96	0.6401	{'precision': 0.46, 'recall': 0.27710843373493976, 'f1': 0.3458646616541353, 'number': 83}	{'precision': 0.497907949790795, 'recall': 0.5804878048780487, 'f1': 0.536036036036036, 'number': 205}	{'precision': 0.3800738007380074, 'recall': 0.4458874458874459, 'f1': 0.4103585657370518, 'number': 231}	0.4375	0.4721	0.4541	0.7985
0.193	13.0	104	0.6539	{'precision': 0.37142857142857144, 'recall': 0.3132530120481928, 'f1': 0.33986928104575165, 'number': 83}	{'precision': 0.5321100917431193, 'recall': 0.5658536585365853, 'f1': 0.5484633569739952, 'number': 205}	{'precision': 0.3969465648854962, 'recall': 0.45021645021645024, 'f1': 0.4219066937119675, 'number': 231}	0.4473	0.4740	0.4602	0.7904
0.1895	14.0	112	0.6557	{'precision': 0.39344262295081966, 'recall': 0.2891566265060241, 'f1': 0.3333333333333333, 'number': 83}	{'precision': 0.5429864253393665, 'recall': 0.5853658536585366, 'f1': 0.5633802816901408, 'number': 205}	{'precision': 0.3916349809885932, 'recall': 0.4458874458874459, 'f1': 0.41700404858299595, 'number': 231}	0.4532	0.4759	0.4643	0.7904
0.1775	15.0	120	0.6561	{'precision': 0.3770491803278688, 'recall': 0.27710843373493976, 'f1': 0.3194444444444444, 'number': 83}	{'precision': 0.5213675213675214, 'recall': 0.5951219512195122, 'f1': 0.5558086560364465, 'number': 205}	{'precision': 0.3722627737226277, 'recall': 0.44155844155844154, 'f1': 0.40396039603960393, 'number': 231}	0.4341	0.4759	0.4540	0.7927

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.3.2
Tokenizers 0.21.0

Task: Token Classification
Library: transformers
Type: layoutlm
License: mit
Created: Mar 6, 2025
Updated: Mar 6, 2025