lmv2-g-w9-2018-148-doc-07-07_1

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0160
• Address Precision: 0.9667
• Address Recall: 0.9667
• Address F1: 0.9667
• Address Number: 30
• Business Name Precision: 1.0
• Business Name Recall: 1.0
• Business Name F1: 1.0
• Business Name Number: 29
• City State Zip Code Precision: 1.0
• City State Zip Code Recall: 1.0
• City State Zip Code F1: 1.0
• City State Zip Code Number: 30
• Ein Precision: 0.0
• Ein Recall: 0.0
• Ein F1: 0.0
• Ein Number: 1
• List Account Number Precision: 1.0
• List Account Number Recall: 1.0
• List Account Number F1: 1.0
• List Account Number Number: 11
• Name Precision: 1.0
• Name Recall: 1.0
• Name F1: 1.0
• Name Number: 30
• Ssn Precision: 0.8333
• Ssn Recall: 1.0
• Ssn F1: 0.9091
• Ssn Number: 10
• Overall Precision: 0.9789
• Overall Recall: 0.9858
• Overall F1: 0.9823
• Overall Accuracy: 0.9995

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: 4e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Address Precision	Address Recall	Address F1	Address Number	Business Name Precision	Business Name Recall	Business Name F1	Business Name Number	City State Zip Code Precision	City State Zip Code Recall	City State Zip Code F1	City State Zip Code Number	Ein Precision	Ein Recall	Ein F1	Ein Number	List Account Number Precision	List Account Number Recall	List Account Number F1	List Account Number Number	Name Precision	Name Recall	Name F1	Name Number	Ssn Precision	Ssn Recall	Ssn F1	Ssn Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
1.5672	1.0	118	1.1527	0.0	0.0	0.0	30	0.0	0.0	0.0	29	0.0	0.0	0.0	30	0.0	0.0	0.0	1	0.0	0.0	0.0	11	0.0	0.0	0.0	30	0.0	0.0	0.0	10	0.0	0.0	0.0	0.9642
0.8804	2.0	236	0.5661	0.2095	0.7333	0.3259	30	0.0	0.0	0.0	29	0.0	0.0	0.0	30	0.0	0.0	0.0	1	0.0	0.0	0.0	11	0.0	0.0	0.0	30	0.0	0.0	0.0	10	0.2095	0.1560	0.1789	0.9704
0.3739	3.0	354	0.2118	0.9375	1.0	0.9677	30	0.7143	0.1724	0.2778	29	0.9375	1.0	0.9677	30	0.0	0.0	0.0	1	0.8182	0.8182	0.8182	11	0.5	1.0	0.6667	30	0.75	0.9	0.8182	10	0.7338	0.8014	0.7661	0.9932
0.1626	4.0	472	0.1155	0.9375	1.0	0.9677	30	0.8710	0.9310	0.9	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	0.6923	0.8182	0.7500	11	1.0	1.0	1.0	30	0.7	0.7	0.7	10	0.9110	0.9433	0.9268	0.9976
0.1031	5.0	590	0.0817	0.9355	0.9667	0.9508	30	0.8125	0.8966	0.8525	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	0.6923	0.8182	0.7500	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9048	0.9433	0.9236	0.9981
0.0769	6.0	708	0.0634	0.9355	0.9667	0.9508	30	0.9333	0.9655	0.9492	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	0.6923	0.8182	0.7500	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9310	0.9574	0.9441	0.9984
0.0614	7.0	826	0.0518	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	0.6923	0.8182	0.7500	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9510	0.9645	0.9577	0.9991
0.0509	8.0	944	0.0432	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	0.8333	0.9091	0.8696	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9648	0.9716	0.9682	0.9994
0.0431	9.0	1062	0.0369	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9787	0.9787	0.9787	0.9994
0.037	10.0	1180	0.0313	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9787	0.9787	0.9787	0.9994
0.0328	11.0	1298	0.0281	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.7143	1.0	0.8333	10	0.9653	0.9858	0.9754	0.9994
0.0295	12.0	1416	0.0246	0.7429	0.8667	0.8	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.6667	0.8	0.7273	10	0.9116	0.9504	0.9306	0.9991
0.0251	13.0	1534	0.0207	0.9677	1.0	0.9836	30	0.9333	0.9655	0.9492	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9653	0.9858	0.9754	0.9994
0.0231	14.0	1652	0.0210	0.9667	0.9667	0.9667	30	1.0	0.9655	0.9825	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9787	0.9787	0.9787	0.9991
0.0184	15.0	1770	0.0160	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9789	0.9858	0.9823	0.9995
0.0162	16.0	1888	0.0142	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9789	0.9858	0.9823	0.9995
0.0142	17.0	2006	0.0127	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9789	0.9858	0.9823	0.9995
0.0123	18.0	2124	0.0114	0.9667	0.9667	0.9667	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9789	0.9858	0.9823	0.9995
0.0118	19.0	2242	0.0152	0.9677	1.0	0.9836	30	0.6765	0.7931	0.7302	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	0.8333	0.9091	0.8696	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.8859	0.9362	0.9103	0.9986
0.0104	20.0	2360	0.0125	0.9677	1.0	0.9836	30	1.0	0.9655	0.9825	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.9091	1.0	0.9524	10	0.9789	0.9858	0.9823	0.9992
0.0092	21.0	2478	0.0113	0.9677	1.0	0.9836	30	1.0	0.9655	0.9825	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9653	0.9858	0.9754	0.9993
0.0089	22.0	2596	0.0111	0.9677	1.0	0.9836	30	1.0	0.9655	0.9825	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9789	0.9858	0.9823	0.9992
0.0076	23.0	2714	0.0107	0.9677	1.0	0.9836	30	0.9310	0.9310	0.9310	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8333	1.0	0.9091	10	0.9650	0.9787	0.9718	0.9991
0.0074	24.0	2832	0.0105	0.9677	1.0	0.9836	30	0.9310	0.9310	0.9310	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9514	0.9716	0.9614	0.9990
0.007	25.0	2950	0.0092	0.9677	1.0	0.9836	30	1.0	0.9655	0.9825	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.7692	1.0	0.8696	10	0.9720	0.9858	0.9789	0.9991
0.0062	26.0	3068	0.0061	0.9677	1.0	0.9836	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.7143	1.0	0.8333	10	0.9655	0.9929	0.9790	0.9994
0.0057	27.0	3186	0.0056	0.9677	1.0	0.9836	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.8182	0.9	0.8571	10	0.9720	0.9858	0.9789	0.9995
0.0047	28.0	3304	0.0054	0.9677	1.0	0.9836	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.7143	1.0	0.8333	10	0.9655	0.9929	0.9790	0.9994
0.0042	29.0	3422	0.0052	0.9677	1.0	0.9836	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.7143	1.0	0.8333	10	0.9655	0.9929	0.9790	0.9994
0.0039	30.0	3540	0.0049	0.9677	1.0	0.9836	30	1.0	1.0	1.0	29	1.0	1.0	1.0	30	0.0	0.0	0.0	1	1.0	1.0	1.0	11	1.0	1.0	1.0	30	0.7143	1.0	0.8333	10	0.9655	0.9929	0.9790	0.9994

Framework versions

• Transformers 4.21.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1