model

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: 0.0428
• B-adress: {'precision': 0.9269102990033222, 'recall': 0.9370277078085643, 'f1': 0.9319415448851774, 'number': 1191}
• B-name: {'precision': 0.9577039274924471, 'recall': 0.9378698224852071, 'f1': 0.9476831091180866, 'number': 338}
• Gst no: {'precision': 0.9689922480620154, 'recall': 0.984251968503937, 'f1': 0.9765625, 'number': 127}
• Invoice no: {'precision': 0.9583333333333334, 'recall': 0.9484536082474226, 'f1': 0.9533678756476685, 'number': 97}
• Order date: {'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}
• Order id: {'precision': 0.9618320610687023, 'recall': 0.984375, 'f1': 0.9729729729729729, 'number': 128}
• S-adress: {'precision': 0.9809656453110492, 'recall': 0.9957587181903864, 'f1': 0.988306828811974, 'number': 2122}
• S-name: {'precision': 0.9888268156424581, 'recall': 0.9943820224719101, 'f1': 0.9915966386554622, 'number': 534}
• Total gross: {'precision': 0.9354838709677419, 'recall': 0.9206349206349206, 'f1': 0.9279999999999999, 'number': 63}
• Total net: {'precision': 0.9253731343283582, 'recall': 0.9763779527559056, 'f1': 0.9501915708812261, 'number': 127}
• Overall Precision: 0.9633
• Overall Recall: 0.9738
• Overall F1: 0.9685
• Overall Accuracy: 0.9898

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
1.1762	1.0	19	0.6066	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1191}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 338}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 127}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 97}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 122}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 128}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2122}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 127}	0.0	0.0	0.0	0.8194
0.4823	2.0	38	0.3283	{'precision': 0.5819354838709677, 'recall': 0.3786733837111671, 'f1': 0.4587995930824008, 'number': 1191}	{'precision': 0.8347107438016529, 'recall': 0.2988165680473373, 'f1': 0.440087145969499, 'number': 338}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 127}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 97}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 122}	{'precision': 1.0, 'recall': 0.03125, 'f1': 0.06060606060606061, 'number': 128}	{'precision': 0.8914764788076386, 'recall': 0.9019792648444863, 'f1': 0.8966971187631764, 'number': 2122}	{'precision': 0.9348958333333334, 'recall': 0.6722846441947565, 'f1': 0.7821350762527233, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 127}	0.8245	0.5834	0.6833	0.9098
0.2723	3.0	57	0.1988	{'precision': 0.6759189797449362, 'recall': 0.7565071368597817, 'f1': 0.7139461172741679, 'number': 1191}	{'precision': 0.7060301507537688, 'recall': 0.8313609467455622, 'f1': 0.7635869565217391, 'number': 338}	{'precision': 0.9259259259259259, 'recall': 0.7874015748031497, 'f1': 0.851063829787234, 'number': 127}	{'precision': 0.922077922077922, 'recall': 0.7319587628865979, 'f1': 0.8160919540229885, 'number': 97}	{'precision': 0.9066666666666666, 'recall': 0.5573770491803278, 'f1': 0.6903553299492385, 'number': 122}	{'precision': 0.9333333333333333, 'recall': 0.765625, 'f1': 0.8412017167381974, 'number': 128}	{'precision': 0.9612778315585673, 'recall': 0.9359095193213949, 'f1': 0.9484240687679083, 'number': 2122}	{'precision': 0.9844054580896686, 'recall': 0.9456928838951311, 'f1': 0.9646609360076408, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 127}	0.8578	0.8270	0.8421	0.9492
0.1825	4.0	76	0.1596	{'precision': 0.6635916359163592, 'recall': 0.9059613769941226, 'f1': 0.7660631877884273, 'number': 1191}	{'precision': 0.7792207792207793, 'recall': 0.8875739644970414, 'f1': 0.8298755186721992, 'number': 338}	{'precision': 0.954954954954955, 'recall': 0.8346456692913385, 'f1': 0.8907563025210083, 'number': 127}	{'precision': 0.8631578947368421, 'recall': 0.845360824742268, 'f1': 0.8541666666666666, 'number': 97}	{'precision': 0.8725490196078431, 'recall': 0.7295081967213115, 'f1': 0.7946428571428572, 'number': 122}	{'precision': 0.9519230769230769, 'recall': 0.7734375, 'f1': 0.853448275862069, 'number': 128}	{'precision': 0.9807881773399014, 'recall': 0.9382657869934025, 'f1': 0.9590558766859345, 'number': 2122}	{'precision': 0.9865900383141762, 'recall': 0.9644194756554307, 'f1': 0.975378787878788, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 127}	0.8565	0.8787	0.8675	0.9558
0.1356	5.0	95	0.1106	{'precision': 0.7638888888888888, 'recall': 0.9235936188077246, 'f1': 0.8361839604713037, 'number': 1191}	{'precision': 0.9381107491856677, 'recall': 0.8520710059171598, 'f1': 0.8930232558139536, 'number': 338}	{'precision': 0.9375, 'recall': 0.8267716535433071, 'f1': 0.8786610878661089, 'number': 127}	{'precision': 0.9222222222222223, 'recall': 0.8556701030927835, 'f1': 0.8877005347593583, 'number': 97}	{'precision': 0.8584070796460177, 'recall': 0.7950819672131147, 'f1': 0.825531914893617, 'number': 122}	{'precision': 0.9528301886792453, 'recall': 0.7890625, 'f1': 0.8632478632478633, 'number': 128}	{'precision': 0.9829706717123936, 'recall': 0.9792648444863337, 'f1': 0.9811142587346553, 'number': 2122}	{'precision': 0.9961685823754789, 'recall': 0.9737827715355806, 'f1': 0.9848484848484848, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 127}	0.9101	0.9016	0.9058	0.9685
0.0936	6.0	114	0.0877	{'precision': 0.9464094319399786, 'recall': 0.7413937867338372, 'f1': 0.8314500941619587, 'number': 1191}	{'precision': 0.9203539823008849, 'recall': 0.9230769230769231, 'f1': 0.9217134416543575, 'number': 338}	{'precision': 0.9649122807017544, 'recall': 0.8661417322834646, 'f1': 0.9128630705394191, 'number': 127}	{'precision': 0.9325842696629213, 'recall': 0.8556701030927835, 'f1': 0.8924731182795699, 'number': 97}	{'precision': 0.9145299145299145, 'recall': 0.8770491803278688, 'f1': 0.895397489539749, 'number': 122}	{'precision': 0.943089430894309, 'recall': 0.90625, 'f1': 0.9243027888446216, 'number': 128}	{'precision': 0.9736111111111111, 'recall': 0.9910461828463714, 'f1': 0.9822512844465203, 'number': 2122}	{'precision': 0.9925233644859813, 'recall': 0.9943820224719101, 'f1': 0.9934518241347053, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.8, 'recall': 0.031496062992125984, 'f1': 0.06060606060606061, 'number': 127}	0.9624	0.8763	0.9173	0.9728
0.0711	7.0	133	0.0721	{'precision': 0.8949652777777778, 'recall': 0.8656591099916037, 'f1': 0.8800682885189928, 'number': 1191}	{'precision': 0.8815426997245179, 'recall': 0.9467455621301775, 'f1': 0.9129814550641939, 'number': 338}	{'precision': 0.9609375, 'recall': 0.968503937007874, 'f1': 0.9647058823529412, 'number': 127}	{'precision': 0.9157894736842105, 'recall': 0.8969072164948454, 'f1': 0.9062499999999999, 'number': 97}	{'precision': 0.937007874015748, 'recall': 0.9754098360655737, 'f1': 0.9558232931726907, 'number': 122}	{'precision': 0.9538461538461539, 'recall': 0.96875, 'f1': 0.9612403100775193, 'number': 128}	{'precision': 0.9839849269901083, 'recall': 0.9844486333647502, 'f1': 0.9842167255594817, 'number': 2122}	{'precision': 0.9851024208566108, 'recall': 0.9906367041198502, 'f1': 0.9878618113912231, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.5061728395061729, 'recall': 0.6456692913385826, 'f1': 0.5674740484429066, 'number': 127}	0.9350	0.9289	0.9319	0.9785
0.0543	8.0	152	0.0551	{'precision': 0.9027661357921207, 'recall': 0.9042821158690176, 'f1': 0.9035234899328859, 'number': 1191}	{'precision': 0.9516616314199395, 'recall': 0.9319526627218935, 'f1': 0.9417040358744395, 'number': 338}	{'precision': 0.9612403100775194, 'recall': 0.9763779527559056, 'f1': 0.9687500000000001, 'number': 127}	{'precision': 0.9368421052631579, 'recall': 0.9175257731958762, 'f1': 0.9270833333333333, 'number': 97}	{'precision': 0.9596774193548387, 'recall': 0.9754098360655737, 'f1': 0.9674796747967479, 'number': 122}	{'precision': 0.9612403100775194, 'recall': 0.96875, 'f1': 0.9649805447470817, 'number': 128}	{'precision': 0.9831697054698457, 'recall': 0.9910461828463714, 'f1': 0.9870922318704529, 'number': 2122}	{'precision': 0.9925093632958801, 'recall': 0.9925093632958801, 'f1': 0.9925093632958801, 'number': 534}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 63}	{'precision': 0.5714285714285714, 'recall': 0.7559055118110236, 'f1': 0.6508474576271186, 'number': 127}	0.9453	0.9439	0.9446	0.9831
0.04	9.0	171	0.0536	{'precision': 0.8660508083140878, 'recall': 0.9445843828715366, 'f1': 0.9036144578313253, 'number': 1191}	{'precision': 0.9279538904899135, 'recall': 0.9526627218934911, 'f1': 0.9401459854014598, 'number': 338}	{'precision': 0.9618320610687023, 'recall': 0.9921259842519685, 'f1': 0.9767441860465117, 'number': 127}	{'precision': 0.92, 'recall': 0.9484536082474226, 'f1': 0.9340101522842639, 'number': 97}	{'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}	{'precision': 0.9618320610687023, 'recall': 0.984375, 'f1': 0.9729729729729729, 'number': 128}	{'precision': 0.9809390980939098, 'recall': 0.9943449575871819, 'f1': 0.9875965363912943, 'number': 2122}	{'precision': 0.9833024118738405, 'recall': 0.9925093632958801, 'f1': 0.9878844361602983, 'number': 534}	{'precision': 0.8947368421052632, 'recall': 0.2698412698412698, 'f1': 0.4146341463414634, 'number': 63}	{'precision': 0.6228571428571429, 'recall': 0.8582677165354331, 'f1': 0.7218543046357615, 'number': 127}	0.9324	0.9645	0.9482	0.9838
0.034	10.0	190	0.0461	{'precision': 0.9100572363041701, 'recall': 0.9345088161209067, 'f1': 0.9221209610604806, 'number': 1191}	{'precision': 0.9546827794561934, 'recall': 0.9349112426035503, 'f1': 0.9446935724962632, 'number': 338}	{'precision': 0.9767441860465116, 'recall': 0.9921259842519685, 'f1': 0.9843749999999999, 'number': 127}	{'precision': 0.9578947368421052, 'recall': 0.9381443298969072, 'f1': 0.9479166666666666, 'number': 97}	{'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}	{'precision': 0.9618320610687023, 'recall': 0.984375, 'f1': 0.9729729729729729, 'number': 128}	{'precision': 0.9809390980939098, 'recall': 0.9943449575871819, 'f1': 0.9875965363912943, 'number': 2122}	{'precision': 0.9962406015037594, 'recall': 0.9925093632958801, 'f1': 0.9943714821763602, 'number': 534}	{'precision': 0.9512195121951219, 'recall': 0.6190476190476191, 'f1': 0.7500000000000001, 'number': 63}	{'precision': 0.8273381294964028, 'recall': 0.905511811023622, 'f1': 0.8646616541353382, 'number': 127}	0.9571	0.9664	0.9617	0.9879
0.0291	11.0	209	0.0451	{'precision': 0.928390901432182, 'recall': 0.9252728799328296, 'f1': 0.926829268292683, 'number': 1191}	{'precision': 0.9358600583090378, 'recall': 0.9497041420118343, 'f1': 0.9427312775330395, 'number': 338}	{'precision': 0.9765625, 'recall': 0.984251968503937, 'f1': 0.9803921568627452, 'number': 127}	{'precision': 0.9484536082474226, 'recall': 0.9484536082474226, 'f1': 0.9484536082474226, 'number': 97}	{'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}	{'precision': 0.9545454545454546, 'recall': 0.984375, 'f1': 0.9692307692307692, 'number': 128}	{'precision': 0.9764325323475046, 'recall': 0.9957587181903864, 'f1': 0.9860009332711154, 'number': 2122}	{'precision': 0.9906716417910447, 'recall': 0.9943820224719101, 'f1': 0.9925233644859812, 'number': 534}	{'precision': 0.9482758620689655, 'recall': 0.873015873015873, 'f1': 0.9090909090909091, 'number': 63}	{'precision': 0.8413793103448276, 'recall': 0.9606299212598425, 'f1': 0.8970588235294117, 'number': 127}	0.9579	0.9707	0.9643	0.9883
0.0268	12.0	228	0.0443	{'precision': 0.9251471825063078, 'recall': 0.9235936188077246, 'f1': 0.9243697478991596, 'number': 1191}	{'precision': 0.9413489736070382, 'recall': 0.9497041420118343, 'f1': 0.9455081001472754, 'number': 338}	{'precision': 0.9689922480620154, 'recall': 0.984251968503937, 'f1': 0.9765625, 'number': 127}	{'precision': 0.9387755102040817, 'recall': 0.9484536082474226, 'f1': 0.9435897435897437, 'number': 97}	{'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}	{'precision': 0.9618320610687023, 'recall': 0.984375, 'f1': 0.9729729729729729, 'number': 128}	{'precision': 0.9826941066417212, 'recall': 0.9901036757775683, 'f1': 0.9863849765258215, 'number': 2122}	{'precision': 0.9888268156424581, 'recall': 0.9943820224719101, 'f1': 0.9915966386554622, 'number': 534}	{'precision': 0.9491525423728814, 'recall': 0.8888888888888888, 'f1': 0.9180327868852458, 'number': 63}	{'precision': 0.8857142857142857, 'recall': 0.9763779527559056, 'f1': 0.9288389513108615, 'number': 127}	0.9611	0.9684	0.9648	0.9887
0.0236	13.0	247	0.0435	{'precision': 0.9211175020542317, 'recall': 0.9412258606213266, 'f1': 0.9310631229235881, 'number': 1191}	{'precision': 0.954954954954955, 'recall': 0.9408284023668639, 'f1': 0.9478390461997019, 'number': 338}	{'precision': 0.984251968503937, 'recall': 0.984251968503937, 'f1': 0.984251968503937, 'number': 127}	{'precision': 0.9484536082474226, 'recall': 0.9484536082474226, 'f1': 0.9484536082474226, 'number': 97}	{'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}	{'precision': 0.9618320610687023, 'recall': 0.984375, 'f1': 0.9729729729729729, 'number': 128}	{'precision': 0.9809390980939098, 'recall': 0.9943449575871819, 'f1': 0.9875965363912943, 'number': 2122}	{'precision': 0.9925093632958801, 'recall': 0.9925093632958801, 'f1': 0.9925093632958801, 'number': 534}	{'precision': 0.9508196721311475, 'recall': 0.9206349206349206, 'f1': 0.9354838709677418, 'number': 63}	{'precision': 0.9185185185185185, 'recall': 0.9763779527559056, 'f1': 0.9465648854961832, 'number': 127}	0.9621	0.9742	0.9681	0.9896
0.0214	14.0	266	0.0446	{'precision': 0.9249793899422918, 'recall': 0.9420654911838791, 'f1': 0.9334442595673876, 'number': 1191}	{'precision': 0.9494047619047619, 'recall': 0.9437869822485208, 'f1': 0.9465875370919882, 'number': 338}	{'precision': 0.9689922480620154, 'recall': 0.984251968503937, 'f1': 0.9765625, 'number': 127}	{'precision': 0.9387755102040817, 'recall': 0.9484536082474226, 'f1': 0.9435897435897437, 'number': 97}	{'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}	{'precision': 0.9545454545454546, 'recall': 0.984375, 'f1': 0.9692307692307692, 'number': 128}	{'precision': 0.9764325323475046, 'recall': 0.9957587181903864, 'f1': 0.9860009332711154, 'number': 2122}	{'precision': 0.9833333333333333, 'recall': 0.9943820224719101, 'f1': 0.9888268156424581, 'number': 534}	{'precision': 0.8923076923076924, 'recall': 0.9206349206349206, 'f1': 0.90625, 'number': 63}	{'precision': 0.8732394366197183, 'recall': 0.9763779527559056, 'f1': 0.9219330855018587, 'number': 127}	0.9569	0.9755	0.9661	0.9890
0.0199	15.0	285	0.0428	{'precision': 0.9269102990033222, 'recall': 0.9370277078085643, 'f1': 0.9319415448851774, 'number': 1191}	{'precision': 0.9577039274924471, 'recall': 0.9378698224852071, 'f1': 0.9476831091180866, 'number': 338}	{'precision': 0.9689922480620154, 'recall': 0.984251968503937, 'f1': 0.9765625, 'number': 127}	{'precision': 0.9583333333333334, 'recall': 0.9484536082474226, 'f1': 0.9533678756476685, 'number': 97}	{'precision': 0.967741935483871, 'recall': 0.9836065573770492, 'f1': 0.975609756097561, 'number': 122}	{'precision': 0.9618320610687023, 'recall': 0.984375, 'f1': 0.9729729729729729, 'number': 128}	{'precision': 0.9809656453110492, 'recall': 0.9957587181903864, 'f1': 0.988306828811974, 'number': 2122}	{'precision': 0.9888268156424581, 'recall': 0.9943820224719101, 'f1': 0.9915966386554622, 'number': 534}	{'precision': 0.9354838709677419, 'recall': 0.9206349206349206, 'f1': 0.9279999999999999, 'number': 63}	{'precision': 0.9253731343283582, 'recall': 0.9763779527559056, 'f1': 0.9501915708812261, 'number': 127}	0.9633	0.9738	0.9685	0.9898

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1