layoutlmv2-sroie-finetunev1

trng1305/layoutlmv2-sroie-finetunev1

layoutlmv2-sroie-finetunev1 is a machine learning model from trng1305. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

113

Public

Repo size

9.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin451 MB · 100%

At a glance

Library: transformers
Model type: layoutlm
Access: Public
Created: Dec 13, 2023
Updated: Dec 13, 2023
SHA: 484d3778

Model card

From the Hugging Face model README

layoutlmv2-sroie-finetunev1

This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1271
Address: {'precision': 0.9885554425228891, 'recall': 0.9948809828512926, 'f1': 0.9917081260364842, 'number': 3907}
Company: {'precision': 0.974934036939314, 'recall': 0.9912810194500336, 'f1': 0.9830395743265714, 'number': 1491}
Date: {'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}
Total: {'precision': 0.8826666666666667, 'recall': 0.8921832884097035, 'f1': 0.8873994638069707, 'number': 371}
Overall Precision: 0.9794
Overall Recall: 0.9873
Overall F1: 0.9833
Overall Accuracy: 0.9949

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: 20
label_smoothing_factor: 0.02

Training results

Training Loss	Epoch	Step	Validation Loss	Address	Company	Date	Total	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.2409	1.0	40	0.1537	{'precision': 0.9862804878048781, 'recall': 0.9936012285641157, 'f1': 0.9899273237281654, 'number': 3907}	{'precision': 0.908923076923077, 'recall': 0.9906103286384976, 'f1': 0.94801026957638, 'number': 1491}	{'precision': 0.9414414414414415, 'recall': 0.9766355140186916, 'f1': 0.9587155963302753, 'number': 428}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 371}	0.9620	0.9322	0.9469	0.9843
0.1402	2.0	80	0.1343	{'precision': 0.9860476915271436, 'recall': 0.9948809828512926, 'f1': 0.9904446426296343, 'number': 3907}	{'precision': 0.946257197696737, 'recall': 0.9919517102615694, 'f1': 0.9685658153241651, 'number': 1491}	{'precision': 0.9813519813519813, 'recall': 0.9836448598130841, 'f1': 0.9824970828471412, 'number': 428}	{'precision': 0.6899038461538461, 'recall': 0.7735849056603774, 'f1': 0.7293519695044473, 'number': 371}	0.9565	0.9802	0.9682	0.9903
0.1259	3.0	120	0.1262	{'precision': 0.9918200408997955, 'recall': 0.9930893268492449, 'f1': 0.9924542780406702, 'number': 3907}	{'precision': 0.9800266311584553, 'recall': 0.9872568745808182, 'f1': 0.9836284664216505, 'number': 1491}	{'precision': 0.9928741092636579, 'recall': 0.9766355140186916, 'f1': 0.9846878680800941, 'number': 428}	{'precision': 0.819672131147541, 'recall': 0.8086253369272237, 'f1': 0.814111261872456, 'number': 371}	0.9789	0.9795	0.9792	0.9937
0.1198	4.0	160	0.1245	{'precision': 0.9913309535951046, 'recall': 0.9951369337087279, 'f1': 0.9932302976114447, 'number': 3907}	{'precision': 0.9774535809018567, 'recall': 0.98859825620389, 'f1': 0.9829943314438147, 'number': 1491}	{'precision': 0.997624703087886, 'recall': 0.9813084112149533, 'f1': 0.9893992932862191, 'number': 428}	{'precision': 0.7985257985257985, 'recall': 0.876010781671159, 'f1': 0.8354755784061697, 'number': 371}	0.9759	0.9855	0.9807	0.9941
0.1168	5.0	200	0.1249	{'precision': 0.9918242207460398, 'recall': 0.9936012285641157, 'f1': 0.9927119294207902, 'number': 3907}	{'precision': 0.9679319371727748, 'recall': 0.9919517102615694, 'f1': 0.9797946339847631, 'number': 1491}	{'precision': 0.990632318501171, 'recall': 0.9883177570093458, 'f1': 0.9894736842105264, 'number': 428}	{'precision': 0.8372093023255814, 'recall': 0.8733153638814016, 'f1': 0.8548812664907651, 'number': 371}	0.9763	0.9856	0.9810	0.9943
0.1142	6.0	240	0.1250	{'precision': 0.9923175416133163, 'recall': 0.991809572562068, 'f1': 0.9920634920634921, 'number': 3907}	{'precision': 0.9813581890812251, 'recall': 0.98859825620389, 'f1': 0.9849649181423321, 'number': 1491}	{'precision': 1.0, 'recall': 0.9813084112149533, 'f1': 0.9905660377358491, 'number': 428}	{'precision': 0.8802228412256268, 'recall': 0.8517520215633423, 'f1': 0.8657534246575341, 'number': 371}	0.9837	0.9819	0.9828	0.9948
0.113	7.0	280	0.1244	{'precision': 0.9908139831589691, 'recall': 0.993857179421551, 'f1': 0.9923332481472016, 'number': 3907}	{'precision': 0.9788079470198675, 'recall': 0.9912810194500336, 'f1': 0.9850049983338888, 'number': 1491}	{'precision': 1.0, 'recall': 0.985981308411215, 'f1': 0.9929411764705882, 'number': 428}	{'precision': 0.9054441260744985, 'recall': 0.8517520215633423, 'f1': 0.8777777777777778, 'number': 371}	0.9837	0.9842	0.9839	0.9952
0.112	8.0	320	0.1259	{'precision': 0.988552531162554, 'recall': 0.9946250319938572, 'f1': 0.9915794845623884, 'number': 3907}	{'precision': 0.9730617608409987, 'recall': 0.9932930918846412, 'f1': 0.9830733488217724, 'number': 1491}	{'precision': 1.0, 'recall': 0.9836448598130841, 'f1': 0.9917550058892814, 'number': 428}	{'precision': 0.8663101604278075, 'recall': 0.8733153638814016, 'f1': 0.8697986577181209, 'number': 371}	0.9782	0.9863	0.9822	0.9946
0.1105	9.0	360	0.1262	{'precision': 0.9880559085133418, 'recall': 0.9951369337087279, 'f1': 0.991583779648049, 'number': 3907}	{'precision': 0.9788219722038385, 'recall': 0.9919517102615694, 'f1': 0.9853431045969354, 'number': 1491}	{'precision': 1.0, 'recall': 0.985981308411215, 'f1': 0.9929411764705882, 'number': 428}	{'precision': 0.8895027624309392, 'recall': 0.8679245283018868, 'f1': 0.878581173260573, 'number': 371}	0.9809	0.9861	0.9835	0.9950
0.1102	10.0	400	0.1258	{'precision': 0.9905346635968278, 'recall': 0.991041719989762, 'f1': 0.9907881269191403, 'number': 3907}	{'precision': 0.9710716633793557, 'recall': 0.9906103286384976, 'f1': 0.9807436918990704, 'number': 1491}	{'precision': 0.9976415094339622, 'recall': 0.9883177570093458, 'f1': 0.9929577464788731, 'number': 428}	{'precision': 0.8605263157894737, 'recall': 0.8814016172506739, 'f1': 0.8708388814913449, 'number': 371}	0.9783	0.9842	0.9813	0.9945
0.1091	11.0	440	0.1263	{'precision': 0.990316004077472, 'recall': 0.9946250319938572, 'f1': 0.9924658408887755, 'number': 3907}	{'precision': 0.9724409448818898, 'recall': 0.993963782696177, 'f1': 0.9830845771144279, 'number': 1491}	{'precision': 1.0, 'recall': 0.985981308411215, 'f1': 0.9929411764705882, 'number': 428}	{'precision': 0.8491048593350383, 'recall': 0.894878706199461, 'f1': 0.8713910761154856, 'number': 371}	0.9778	0.9879	0.9828	0.9948
0.1092	12.0	480	0.1277	{'precision': 0.9885437881873728, 'recall': 0.993857179421551, 'f1': 0.991193363114231, 'number': 3907}	{'precision': 0.965472312703583, 'recall': 0.993963782696177, 'f1': 0.9795109054857898, 'number': 1491}	{'precision': 0.9976359338061466, 'recall': 0.985981308411215, 'f1': 0.991774383078731, 'number': 428}	{'precision': 0.8907103825136612, 'recall': 0.8787061994609164, 'f1': 0.8846675712347355, 'number': 371}	0.9778	0.9864	0.9821	0.9946
0.1082	13.0	520	0.1271	{'precision': 0.9890501655207538, 'recall': 0.9941131302789864, 'f1': 0.9915751850906306, 'number': 3907}	{'precision': 0.9794019933554817, 'recall': 0.98859825620389, 'f1': 0.9839786381842456, 'number': 1491}	{'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}	{'precision': 0.8477157360406091, 'recall': 0.9002695417789758, 'f1': 0.8732026143790849, 'number': 371}	0.9782	0.9866	0.9824	0.9947
0.1079	14.0	560	0.1274	{'precision': 0.9888040712468193, 'recall': 0.9946250319938572, 'f1': 0.991706009952788, 'number': 3907}	{'precision': 0.974934036939314, 'recall': 0.9912810194500336, 'f1': 0.9830395743265714, 'number': 1491}	{'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}	{'precision': 0.8691099476439791, 'recall': 0.894878706199461, 'f1': 0.8818061088977424, 'number': 371}	0.9786	0.9873	0.9829	0.9948
0.1076	15.0	600	0.1268	{'precision': 0.9887983706720977, 'recall': 0.9941131302789864, 'f1': 0.9914486279514996, 'number': 3907}	{'precision': 0.9749009247027741, 'recall': 0.9899396378269618, 'f1': 0.9823627287853578, 'number': 1491}	{'precision': 0.9976359338061466, 'recall': 0.985981308411215, 'f1': 0.991774383078731, 'number': 428}	{'precision': 0.8840970350404312, 'recall': 0.8840970350404312, 'f1': 0.8840970350404312, 'number': 371}	0.9798	0.9860	0.9829	0.9948
0.1076	16.0	640	0.1268	{'precision': 0.988552531162554, 'recall': 0.9946250319938572, 'f1': 0.9915794845623884, 'number': 3907}	{'precision': 0.97556142668428, 'recall': 0.9906103286384976, 'f1': 0.9830282861896837, 'number': 1491}	{'precision': 0.9976359338061466, 'recall': 0.985981308411215, 'f1': 0.991774383078731, 'number': 428}	{'precision': 0.8934426229508197, 'recall': 0.8814016172506739, 'f1': 0.8873812754409769, 'number': 371}	0.9804	0.9863	0.9833	0.9949
0.1073	17.0	680	0.1268	{'precision': 0.9895541401273885, 'recall': 0.9941131302789864, 'f1': 0.9918283963227783, 'number': 3907}	{'precision': 0.974917491749175, 'recall': 0.9906103286384976, 'f1': 0.9827012641383899, 'number': 1491}	{'precision': 0.9976359338061466, 'recall': 0.985981308411215, 'f1': 0.991774383078731, 'number': 428}	{'precision': 0.8921832884097035, 'recall': 0.8921832884097035, 'f1': 0.8921832884097035, 'number': 371}	0.9808	0.9866	0.9837	0.9950
0.1071	18.0	720	0.1265	{'precision': 0.9895568008150789, 'recall': 0.9943690811364219, 'f1': 0.9919571045576407, 'number': 3907}	{'precision': 0.9761904761904762, 'recall': 0.9899396378269618, 'f1': 0.983016983016983, 'number': 1491}	{'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}	{'precision': 0.8873994638069705, 'recall': 0.8921832884097035, 'f1': 0.8897849462365591, 'number': 371}	0.9806	0.9866	0.9836	0.9950
0.1072	19.0	760	0.1271	{'precision': 0.9885554425228891, 'recall': 0.9948809828512926, 'f1': 0.9917081260364842, 'number': 3907}	{'precision': 0.974934036939314, 'recall': 0.9912810194500336, 'f1': 0.9830395743265714, 'number': 1491}	{'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}	{'precision': 0.8756613756613757, 'recall': 0.8921832884097035, 'f1': 0.8838451268357811, 'number': 371}	0.9789	0.9873	0.9830	0.9948
0.1072	20.0	800	0.1271	{'precision': 0.9885554425228891, 'recall': 0.9948809828512926, 'f1': 0.9917081260364842, 'number': 3907}	{'precision': 0.974934036939314, 'recall': 0.9912810194500336, 'f1': 0.9830395743265714, 'number': 1491}	{'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}	{'precision': 0.8826666666666667, 'recall': 0.8921832884097035, 'f1': 0.8873994638069707, 'number': 371}	0.9794	0.9873	0.9833	0.9949

Framework versions

Transformers 4.28.0
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.13.3

Library: transformers
Type: layoutlm
Created: Dec 13, 2023
Updated: Dec 13, 2023