layoutlm-base-uncased-finetuned-invoices-2

This model is a fine-tuned version of riteshbehera857/layoutlm-base-uncased-finetuned-invoices-1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0342
• B-adress: {'precision': 0.9669491525423729, 'recall': 0.971063829787234, 'f1': 0.9690021231422504, 'number': 1175}
• B-name: {'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}
• Gst no: {'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}
• Invoice no: {'precision': 0.9702970297029703, 'recall': 0.9607843137254902, 'f1': 0.9655172413793103, 'number': 102}
• Order date: {'precision': 0.9672131147540983, 'recall': 0.9752066115702479, 'f1': 0.9711934156378601, 'number': 121}
• Order id: {'precision': 0.9770992366412213, 'recall': 0.9922480620155039, 'f1': 0.9846153846153846, 'number': 129}
• S-adress: {'precision': 0.978021978021978, 'recall': 0.9941489361702127, 'f1': 0.9860195199155896, 'number': 1880}
• S-name: {'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}
• Total gross: {'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}
• Total net: {'precision': 0.9923076923076923, 'recall': 1.0, 'f1': 0.9961389961389961, 'number': 129}
• Overall Precision: 0.9761
• Overall Recall: 0.9808
• Overall F1: 0.9784
• Overall Accuracy: 0.9944

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: 5e-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
• lr_scheduler_warmup_steps: 10
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	B-adress	B-name	Gst no	Invoice no	Order date	Order id	S-adress	S-name	Total gross	Total net	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0192	1.0	19	0.0257	{'precision': 0.9559322033898305, 'recall': 0.96, 'f1': 0.9579617834394905, 'number': 1175}	{'precision': 0.9713467048710601, 'recall': 0.9826086956521739, 'f1': 0.9769452449567723, 'number': 345}	{'precision': 1.0, 'recall': 0.9844961240310077, 'f1': 0.9921875, 'number': 129}	{'precision': 0.9615384615384616, 'recall': 0.9803921568627451, 'f1': 0.970873786407767, 'number': 102}	{'precision': 0.9752066115702479, 'recall': 0.9752066115702479, 'f1': 0.9752066115702479, 'number': 121}	{'precision': 0.9696969696969697, 'recall': 0.9922480620155039, 'f1': 0.9808429118773947, 'number': 129}	{'precision': 0.9789251844046365, 'recall': 0.9882978723404255, 'f1': 0.9835892006352567, 'number': 1880}	{'precision': 0.9899396378269618, 'recall': 0.9498069498069498, 'f1': 0.9694581280788177, 'number': 518}	{'precision': 0.8688524590163934, 'recall': 1.0, 'f1': 0.9298245614035088, 'number': 53}	{'precision': 1.0, 'recall': 0.9922480620155039, 'f1': 0.9961089494163424, 'number': 129}	0.9726	0.9760	0.9743	0.9932
0.0179	2.0	38	0.0272	{'precision': 0.9562657695542472, 'recall': 0.9676595744680851, 'f1': 0.9619289340101522, 'number': 1175}	{'precision': 0.9740634005763689, 'recall': 0.9797101449275363, 'f1': 0.976878612716763, 'number': 345}	{'precision': 1.0, 'recall': 0.9844961240310077, 'f1': 0.9921875, 'number': 129}	{'precision': 0.9705882352941176, 'recall': 0.9705882352941176, 'f1': 0.9705882352941176, 'number': 102}	{'precision': 0.9754098360655737, 'recall': 0.9834710743801653, 'f1': 0.9794238683127573, 'number': 121}	{'precision': 0.9770992366412213, 'recall': 0.9922480620155039, 'f1': 0.9846153846153846, 'number': 129}	{'precision': 0.982086406743941, 'recall': 0.9914893617021276, 'f1': 0.9867654843832716, 'number': 1880}	{'precision': 0.9900199600798403, 'recall': 0.9575289575289575, 'f1': 0.9735034347399412, 'number': 518}	{'precision': 0.8833333333333333, 'recall': 1.0, 'f1': 0.9380530973451328, 'number': 53}	{'precision': 1.0, 'recall': 0.9922480620155039, 'f1': 0.9961089494163424, 'number': 129}	0.9748	0.9799	0.9774	0.9940
0.0149	3.0	57	0.0284	{'precision': 0.9647766323024055, 'recall': 0.9557446808510638, 'f1': 0.960239418554938, 'number': 1175}	{'precision': 0.9794117647058823, 'recall': 0.9652173913043478, 'f1': 0.9722627737226278, 'number': 345}	{'precision': 1.0, 'recall': 0.9844961240310077, 'f1': 0.9921875, 'number': 129}	{'precision': 0.9611650485436893, 'recall': 0.9705882352941176, 'f1': 0.9658536585365853, 'number': 102}	{'precision': 0.9754098360655737, 'recall': 0.9834710743801653, 'f1': 0.9794238683127573, 'number': 121}	{'precision': 0.9770992366412213, 'recall': 0.9922480620155039, 'f1': 0.9846153846153846, 'number': 129}	{'precision': 0.9744791666666667, 'recall': 0.9952127659574468, 'f1': 0.9847368421052631, 'number': 1880}	{'precision': 0.99, 'recall': 0.9555984555984556, 'f1': 0.9724950884086443, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9743	0.9773	0.9758	0.9935
0.0135	4.0	76	0.0295	{'precision': 0.9531380753138076, 'recall': 0.9693617021276596, 'f1': 0.9611814345991562, 'number': 1175}	{'precision': 0.9796511627906976, 'recall': 0.9768115942028985, 'f1': 0.9782293178519593, 'number': 345}	{'precision': 1.0, 'recall': 0.9767441860465116, 'f1': 0.988235294117647, 'number': 129}	{'precision': 0.9705882352941176, 'recall': 0.9705882352941176, 'f1': 0.9705882352941176, 'number': 102}	{'precision': 0.9672131147540983, 'recall': 0.9752066115702479, 'f1': 0.9711934156378601, 'number': 121}	{'precision': 0.9552238805970149, 'recall': 0.9922480620155039, 'f1': 0.9733840304182508, 'number': 129}	{'precision': 0.9760166840458812, 'recall': 0.9957446808510638, 'f1': 0.985781990521327, 'number': 1880}	{'precision': 0.988, 'recall': 0.9536679536679536, 'f1': 0.9705304518664047, 'number': 518}	{'precision': 0.9137931034482759, 'recall': 1.0, 'f1': 0.9549549549549551, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9708	0.9812	0.9760	0.9936
0.01	5.0	95	0.0308	{'precision': 0.9619611158072696, 'recall': 0.9685106382978723, 'f1': 0.9652247667514843, 'number': 1175}	{'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}	{'precision': 1.0, 'recall': 0.9767441860465116, 'f1': 0.988235294117647, 'number': 129}	{'precision': 0.9519230769230769, 'recall': 0.9705882352941176, 'f1': 0.9611650485436893, 'number': 102}	{'precision': 0.9752066115702479, 'recall': 0.9752066115702479, 'f1': 0.9752066115702479, 'number': 121}	{'precision': 0.9770992366412213, 'recall': 0.9922480620155039, 'f1': 0.9846153846153846, 'number': 129}	{'precision': 0.9739311783107404, 'recall': 0.9936170212765958, 'f1': 0.9836756187467087, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9727	0.9804	0.9765	0.9938
0.009	6.0	114	0.0315	{'precision': 0.9667235494880546, 'recall': 0.9642553191489361, 'f1': 0.9654878568385172, 'number': 1175}	{'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9705882352941176, 'recall': 0.9705882352941176, 'f1': 0.9705882352941176, 'number': 102}	{'precision': 0.9672131147540983, 'recall': 0.9752066115702479, 'f1': 0.9711934156378601, 'number': 121}	{'precision': 0.9624060150375939, 'recall': 0.9922480620155039, 'f1': 0.9770992366412213, 'number': 129}	{'precision': 0.9714434060228453, 'recall': 0.9952127659574468, 'f1': 0.9831844456121913, 'number': 1880}	{'precision': 0.9860557768924303, 'recall': 0.9555984555984556, 'f1': 0.9705882352941176, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9727	0.9795	0.9761	0.9936
0.0081	7.0	133	0.0322	{'precision': 0.966893039049236, 'recall': 0.9693617021276596, 'f1': 0.9681257968550786, 'number': 1175}	{'precision': 0.9739130434782609, 'recall': 0.9739130434782609, 'f1': 0.9739130434782609, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9607843137254902, 'recall': 0.9607843137254902, 'f1': 0.9607843137254902, 'number': 102}	{'precision': 0.9672131147540983, 'recall': 0.9752066115702479, 'f1': 0.9711934156378601, 'number': 121}	{'precision': 0.9624060150375939, 'recall': 0.9922480620155039, 'f1': 0.9770992366412213, 'number': 129}	{'precision': 0.9785002621919245, 'recall': 0.9925531914893617, 'f1': 0.9854766305782942, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9750	0.9797	0.9774	0.9940
0.0069	8.0	152	0.0324	{'precision': 0.9658994032395567, 'recall': 0.9642553191489361, 'f1': 0.9650766609880749, 'number': 1175}	{'precision': 0.9767441860465116, 'recall': 0.9739130434782609, 'f1': 0.9753265602322205, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9702970297029703, 'recall': 0.9607843137254902, 'f1': 0.9655172413793103, 'number': 102}	{'precision': 0.959349593495935, 'recall': 0.9752066115702479, 'f1': 0.9672131147540983, 'number': 121}	{'precision': 0.9696969696969697, 'recall': 0.9922480620155039, 'f1': 0.9808429118773947, 'number': 129}	{'precision': 0.9769633507853404, 'recall': 0.9925531914893617, 'f1': 0.9846965699208443, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9746	0.9784	0.9765	0.9938
0.0064	9.0	171	0.0344	{'precision': 0.9636209813874789, 'recall': 0.9693617021276596, 'f1': 0.9664828171404328, 'number': 1175}	{'precision': 0.9767441860465116, 'recall': 0.9739130434782609, 'f1': 0.9753265602322205, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9705882352941176, 'recall': 0.9705882352941176, 'f1': 0.9705882352941176, 'number': 102}	{'precision': 0.9672131147540983, 'recall': 0.9752066115702479, 'f1': 0.9711934156378601, 'number': 121}	{'precision': 0.9696969696969697, 'recall': 0.9922480620155039, 'f1': 0.9808429118773947, 'number': 129}	{'precision': 0.9744791666666667, 'recall': 0.9952127659574468, 'f1': 0.9847368421052631, 'number': 1880}	{'precision': 0.9860557768924303, 'recall': 0.9555984555984556, 'f1': 0.9705882352941176, 'number': 518}	{'precision': 0.9137931034482759, 'recall': 1.0, 'f1': 0.9549549549549551, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9729	0.9808	0.9768	0.9940
0.0058	10.0	190	0.0338	{'precision': 0.9652836579170194, 'recall': 0.9702127659574468, 'f1': 0.9677419354838709, 'number': 1175}	{'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9607843137254902, 'recall': 0.9607843137254902, 'f1': 0.9607843137254902, 'number': 102}	{'precision': 0.959349593495935, 'recall': 0.9752066115702479, 'f1': 0.9672131147540983, 'number': 121}	{'precision': 0.9624060150375939, 'recall': 0.9922480620155039, 'f1': 0.9770992366412213, 'number': 129}	{'precision': 0.9785115303983228, 'recall': 0.9930851063829788, 'f1': 0.9857444561774024, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9748	0.9801	0.9775	0.9941
0.0057	11.0	209	0.0342	{'precision': 0.9669491525423729, 'recall': 0.971063829787234, 'f1': 0.9690021231422504, 'number': 1175}	{'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9702970297029703, 'recall': 0.9607843137254902, 'f1': 0.9655172413793103, 'number': 102}	{'precision': 0.9672131147540983, 'recall': 0.9752066115702479, 'f1': 0.9711934156378601, 'number': 121}	{'precision': 0.9770992366412213, 'recall': 0.9922480620155039, 'f1': 0.9846153846153846, 'number': 129}	{'precision': 0.978021978021978, 'recall': 0.9941489361702127, 'f1': 0.9860195199155896, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9923076923076923, 'recall': 1.0, 'f1': 0.9961389961389961, 'number': 129}	0.9761	0.9808	0.9784	0.9944
0.0051	12.0	228	0.0352	{'precision': 0.964527027027027, 'recall': 0.9719148936170213, 'f1': 0.9682068673166595, 'number': 1175}	{'precision': 0.9739130434782609, 'recall': 0.9739130434782609, 'f1': 0.9739130434782609, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9702970297029703, 'recall': 0.9607843137254902, 'f1': 0.9655172413793103, 'number': 102}	{'precision': 0.9672131147540983, 'recall': 0.9752066115702479, 'f1': 0.9711934156378601, 'number': 121}	{'precision': 0.9770992366412213, 'recall': 0.9922480620155039, 'f1': 0.9846153846153846, 'number': 129}	{'precision': 0.9785340314136126, 'recall': 0.9941489361702127, 'f1': 0.9862796833773088, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9137931034482759, 'recall': 1.0, 'f1': 0.9549549549549551, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9748	0.9810	0.9779	0.9943
0.0051	13.0	247	0.0352	{'precision': 0.9638047138047138, 'recall': 0.9744680851063829, 'f1': 0.9691070672873465, 'number': 1175}	{'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9702970297029703, 'recall': 0.9607843137254902, 'f1': 0.9655172413793103, 'number': 102}	{'precision': 0.9291338582677166, 'recall': 0.9752066115702479, 'f1': 0.9516129032258065, 'number': 121}	{'precision': 0.9624060150375939, 'recall': 0.9922480620155039, 'f1': 0.9770992366412213, 'number': 129}	{'precision': 0.9790356394129979, 'recall': 0.9936170212765958, 'f1': 0.9862724392819429, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9298245614035088, 'recall': 1.0, 'f1': 0.9636363636363636, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9740	0.9814	0.9777	0.9942
0.0046	14.0	266	0.0356	{'precision': 0.9605373635600336, 'recall': 0.9736170212765958, 'f1': 0.967032967032967, 'number': 1175}	{'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9702970297029703, 'recall': 0.9607843137254902, 'f1': 0.9655172413793103, 'number': 102}	{'precision': 0.959349593495935, 'recall': 0.9752066115702479, 'f1': 0.9672131147540983, 'number': 121}	{'precision': 0.9624060150375939, 'recall': 0.9922480620155039, 'f1': 0.9770992366412213, 'number': 129}	{'precision': 0.9790246460409019, 'recall': 0.9930851063829788, 'f1': 0.9860047531027197, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9137931034482759, 'recall': 1.0, 'f1': 0.9549549549549551, 'number': 53}	{'precision': 0.9847328244274809, 'recall': 1.0, 'f1': 0.9923076923076923, 'number': 129}	0.9738	0.9810	0.9774	0.9941
0.0044	15.0	285	0.0355	{'precision': 0.9613445378151261, 'recall': 0.9736170212765958, 'f1': 0.9674418604651164, 'number': 1175}	{'precision': 0.9795918367346939, 'recall': 0.9739130434782609, 'f1': 0.9767441860465117, 'number': 345}	{'precision': 1.0, 'recall': 0.9689922480620154, 'f1': 0.9842519685039369, 'number': 129}	{'precision': 0.9702970297029703, 'recall': 0.9607843137254902, 'f1': 0.9655172413793103, 'number': 102}	{'precision': 0.959349593495935, 'recall': 0.9752066115702479, 'f1': 0.9672131147540983, 'number': 121}	{'precision': 0.9624060150375939, 'recall': 0.9922480620155039, 'f1': 0.9770992366412213, 'number': 129}	{'precision': 0.9790246460409019, 'recall': 0.9930851063829788, 'f1': 0.9860047531027197, 'number': 1880}	{'precision': 0.9860834990059643, 'recall': 0.9575289575289575, 'f1': 0.9715964740450539, 'number': 518}	{'precision': 0.9137931034482759, 'recall': 1.0, 'f1': 0.9549549549549551, 'number': 53}	{'precision': 0.9923076923076923, 'recall': 1.0, 'f1': 0.9961389961389961, 'number': 129}	0.9742	0.9810	0.9776	0.9942

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1