layoutlmv2-sroie-test

trng1305/layoutlmv2-sroie-test

layoutlmv2-sroie-test is a token classification model from trng1305. Use it when you need labels on individual words, such as names. It is set up for transformers.

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

Downloads · 30 days

1% of all-time downloads

All-time downloads

511

Public

Repo size

7.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin451 MB · 100%

At a glance

Task: Token Classification
Library: transformers
Model type: layoutlm
Access: Public
Created: Nov 23, 2023
Updated: Nov 23, 2023
SHA: 935777bc

Try a prompt

Model card

From the Hugging Face model README

layoutlmv2-sroie-test

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: 0.0312
Address: {'precision': 0.9915751850906306, 'recall': 0.9941131302789864, 'f1': 0.992842535787321, 'number': 3907}
Company: {'precision': 0.966491458607096, 'recall': 0.9865861837692823, 'f1': 0.9764354463989379, 'number': 1491}
Date: {'precision': 1.0, 'recall': 0.985981308411215, 'f1': 0.9929411764705882, 'number': 428}
Total: {'precision': 0.8783068783068783, 'recall': 0.894878706199461, 'f1': 0.8865153538050735, 'number': 371}
Overall Precision: 0.9792
Overall Recall: 0.9858
Overall F1: 0.9825
Overall Accuracy: 0.9947

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

Training results

Training Loss	Epoch	Step	Validation Loss	Address	Company	Date	Total	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.3558	1.0	40	0.0698	{'precision': 0.9855256475368207, 'recall': 0.9933452777066804, 'f1': 0.9894200127469727, 'number': 3907}	{'precision': 0.8677685950413223, 'recall': 0.9859154929577465, 'f1': 0.9230769230769231, 'number': 1491}	{'precision': 0.8384458077709611, 'recall': 0.9579439252336449, 'f1': 0.8942202835332607, 'number': 428}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 371}	0.9412	0.9296	0.9354	0.9808
0.0489	2.0	80	0.0374	{'precision': 0.9917547023962896, 'recall': 0.9851548502687484, 'f1': 0.9884437596302004, 'number': 3907}	{'precision': 0.92625, 'recall': 0.993963782696177, 'f1': 0.9589129731478485, 'number': 1491}	{'precision': 0.9699074074074074, 'recall': 0.9789719626168224, 'f1': 0.9744186046511628, 'number': 428}	{'precision': 0.7655367231638418, 'recall': 0.7304582210242587, 'f1': 0.7475862068965516, 'number': 371}	0.9607	0.9716	0.9661	0.9899
0.0282	3.0	120	0.0277	{'precision': 0.9913198876691346, 'recall': 0.993857179421551, 'f1': 0.9925869120654397, 'number': 3907}	{'precision': 0.9633986928104575, 'recall': 0.98859825620389, 'f1': 0.9758358159549818, 'number': 1491}	{'precision': 0.9929078014184397, 'recall': 0.9813084112149533, 'f1': 0.9870740305522915, 'number': 428}	{'precision': 0.8376068376068376, 'recall': 0.7924528301886793, 'f1': 0.8144044321329641, 'number': 371}	0.9759	0.9797	0.9778	0.9933
0.0194	4.0	160	0.0259	{'precision': 0.990063694267516, 'recall': 0.9946250319938572, 'f1': 0.9923391215526048, 'number': 3907}	{'precision': 0.9754152823920266, 'recall': 0.9845741113346748, 'f1': 0.9799732977303072, 'number': 1491}	{'precision': 0.9929245283018868, 'recall': 0.9836448598130841, 'f1': 0.9882629107981221, 'number': 428}	{'precision': 0.8320209973753281, 'recall': 0.8544474393530997, 'f1': 0.8430851063829787, 'number': 371}	0.9771	0.9831	0.9801	0.9939
0.0148	5.0	200	0.0259	{'precision': 0.990316004077472, 'recall': 0.9946250319938572, 'f1': 0.9924658408887755, 'number': 3907}	{'precision': 0.9597141000649773, 'recall': 0.9906103286384976, 'f1': 0.9749174917491749, 'number': 1491}	{'precision': 0.9952941176470588, 'recall': 0.9883177570093458, 'f1': 0.9917936694021102, 'number': 428}	{'precision': 0.8621621621621621, 'recall': 0.8598382749326146, 'f1': 0.8609986504723346, 'number': 371}	0.9756	0.9852	0.9803	0.9940
0.0113	6.0	240	0.0255	{'precision': 0.9910714285714286, 'recall': 0.9943690811364219, 'f1': 0.9927175162897662, 'number': 3907}	{'precision': 0.9659239842726082, 'recall': 0.98859825620389, 'f1': 0.9771295989393438, 'number': 1491}	{'precision': 0.9976415094339622, 'recall': 0.9883177570093458, 'f1': 0.9929577464788731, 'number': 428}	{'precision': 0.9008746355685131, 'recall': 0.8328840970350404, 'f1': 0.8655462184873949, 'number': 371}	0.9804	0.9829	0.9816	0.9944
0.0094	7.0	280	0.0267	{'precision': 0.9908233494774408, 'recall': 0.9948809828512926, 'f1': 0.9928480204342274, 'number': 3907}	{'precision': 0.9627450980392157, 'recall': 0.9879275653923542, 'f1': 0.9751737835153922, 'number': 1491}	{'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}	{'precision': 0.8787878787878788, 'recall': 0.8598382749326146, 'f1': 0.8692098092643051, 'number': 371}	0.9777	0.9845	0.9811	0.9942
0.0082	8.0	320	0.0274	{'precision': 0.9915751850906306, 'recall': 0.9941131302789864, 'f1': 0.992842535787321, 'number': 3907}	{'precision': 0.9671268902038133, 'recall': 0.9865861837692823, 'f1': 0.9767596281540504, 'number': 1491}	{'precision': 0.9929577464788732, 'recall': 0.9883177570093458, 'f1': 0.990632318501171, 'number': 428}	{'precision': 0.8898071625344353, 'recall': 0.8706199460916442, 'f1': 0.880108991825613, 'number': 371}	0.9798	0.9845	0.9821	0.9946
0.0069	9.0	360	0.0273	{'precision': 0.9915751850906306, 'recall': 0.9941131302789864, 'f1': 0.992842535787321, 'number': 3907}	{'precision': 0.972203838517538, 'recall': 0.9852448021462106, 'f1': 0.9786808794137242, 'number': 1491}	{'precision': 1.0, 'recall': 0.9813084112149533, 'f1': 0.9905660377358491, 'number': 428}	{'precision': 0.88, 'recall': 0.889487870619946, 'f1': 0.8847184986595173, 'number': 371}	0.9807	0.9848	0.9828	0.9948
0.0055	10.0	400	0.0291	{'precision': 0.9905636317266003, 'recall': 0.9941131302789864, 'f1': 0.9923352069494124, 'number': 3907}	{'precision': 0.9671268902038133, 'recall': 0.9865861837692823, 'f1': 0.9767596281540504, 'number': 1491}	{'precision': 0.9976359338061466, 'recall': 0.985981308411215, 'f1': 0.991774383078731, 'number': 428}	{'precision': 0.9025787965616046, 'recall': 0.8490566037735849, 'f1': 0.875, 'number': 371}	0.9804	0.9831	0.9817	0.9944
0.0045	11.0	440	0.0292	{'precision': 0.9915751850906306, 'recall': 0.9941131302789864, 'f1': 0.992842535787321, 'number': 3907}	{'precision': 0.9696169088507266, 'recall': 0.9845741113346748, 'f1': 0.9770382695507488, 'number': 1491}	{'precision': 1.0, 'recall': 0.985981308411215, 'f1': 0.9929411764705882, 'number': 428}	{'precision': 0.8817204301075269, 'recall': 0.8840970350404312, 'f1': 0.882907133243607, 'number': 371}	0.9802	0.9847	0.9825	0.9947
0.0042	12.0	480	0.0310	{'precision': 0.9913221031138336, 'recall': 0.9941131302789864, 'f1': 0.9927156549520767, 'number': 3907}	{'precision': 0.9683794466403162, 'recall': 0.9859154929577465, 'f1': 0.9770687936191426, 'number': 1491}	{'precision': 1.0, 'recall': 0.9836448598130841, 'f1': 0.9917550058892814, 'number': 428}	{'precision': 0.8763440860215054, 'recall': 0.8787061994609164, 'f1': 0.8775235531628534, 'number': 371}	0.9795	0.9845	0.9820	0.9945
0.0038	13.0	520	0.0316	{'precision': 0.9915751850906306, 'recall': 0.9941131302789864, 'f1': 0.992842535787321, 'number': 3907}	{'precision': 0.9652230971128609, 'recall': 0.9865861837692823, 'f1': 0.9757877280265339, 'number': 1491}	{'precision': 0.9952830188679245, 'recall': 0.985981308411215, 'f1': 0.9906103286384976, 'number': 428}	{'precision': 0.8649350649350649, 'recall': 0.8975741239892183, 'f1': 0.8809523809523809, 'number': 371}	0.9776	0.9860	0.9818	0.9944
0.0035	14.0	560	0.0311	{'precision': 0.9915751850906306, 'recall': 0.9941131302789864, 'f1': 0.992842535787321, 'number': 3907}	{'precision': 0.9658568614576494, 'recall': 0.9865861837692823, 'f1': 0.9761114797611148, 'number': 1491}	{'precision': 1.0, 'recall': 0.985981308411215, 'f1': 0.9929411764705882, 'number': 428}	{'precision': 0.8790322580645161, 'recall': 0.8814016172506739, 'f1': 0.8802153432032301, 'number': 371}	0.9791	0.9850	0.9821	0.9945
0.0032	15.0	600	0.0312	{'precision': 0.9915751850906306, 'recall': 0.9941131302789864, 'f1': 0.992842535787321, 'number': 3907}	{'precision': 0.966491458607096, 'recall': 0.9865861837692823, 'f1': 0.9764354463989379, 'number': 1491}	{'precision': 1.0, 'recall': 0.985981308411215, 'f1': 0.9929411764705882, 'number': 428}	{'precision': 0.8783068783068783, 'recall': 0.894878706199461, 'f1': 0.8865153538050735, 'number': 371}	0.9792	0.9858	0.9825	0.9947

Framework versions

Transformers 4.28.0
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.13.3

Task: Token Classification
Library: transformers
Type: layoutlm
Created: Nov 23, 2023
Updated: Nov 23, 2023