Edit model card

all_final_layoutlmv3-base-ner

This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4992
  • Footer: {'precision': 0.9660942316160281, 'recall': 0.962280701754386, 'f1': 0.9641836958910129, 'number': 2280}
  • Header: {'precision': 0.8500527983104541, 'recall': 0.8464773922187171, 'f1': 0.8482613277133825, 'number': 951}
  • Able: {'precision': 0.6867305061559508, 'recall': 0.820932134096484, 'f1': 0.7478584729981377, 'number': 1223}
  • Aption: {'precision': 0.8540609137055838, 'recall': 0.8157575757575758, 'f1': 0.8344699318040918, 'number': 825}
  • Ext: {'precision': 0.7446111869031378, 'recall': 0.7724313614491933, 'f1': 0.7582661850514032, 'number': 3533}
  • Icture: {'precision': 0.5221238938053098, 'recall': 0.5822368421052632, 'f1': 0.5505443234836703, 'number': 608}
  • Itle: {'precision': 0.6068376068376068, 'recall': 0.5966386554621849, 'f1': 0.6016949152542374, 'number': 119}
  • Ootnote: {'precision': 0.8503401360544217, 'recall': 0.8620689655172413, 'f1': 0.8561643835616437, 'number': 145}
  • Ormula: {'precision': 0.8461538461538461, 'recall': 0.9472222222222222, 'f1': 0.8938401048492791, 'number': 360}
  • Overall Precision: 0.7918
  • Overall Recall: 0.8260
  • Overall F1: 0.8085
  • Overall Accuracy: 0.9414

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: 8
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Footer Header Able Aption Ext Icture Itle Ootnote Ormula Overall Precision Overall Recall Overall F1 Overall Accuracy
0.1878 1.0 6851 0.3842 {'precision': 0.9633318243549117, 'recall': 0.9333333333333333, 'f1': 0.948095344174649, 'number': 2280} {'precision': 0.7953296703296703, 'recall': 0.6088328075709779, 'f1': 0.6896962477665276, 'number': 951} {'precision': 0.4947542794036444, 'recall': 0.7326246933769419, 'f1': 0.5906394199077125, 'number': 1223} {'precision': 0.8165517241379311, 'recall': 0.7175757575757575, 'f1': 0.7638709677419355, 'number': 825} {'precision': 0.6012542461458061, 'recall': 0.6512878573450326, 'f1': 0.6252717391304349, 'number': 3533} {'precision': 0.4029363784665579, 'recall': 0.40625, 'f1': 0.40458640458640466, 'number': 608} {'precision': 0.7555555555555555, 'recall': 0.2857142857142857, 'f1': 0.41463414634146345, 'number': 119} {'precision': 0.5217391304347826, 'recall': 0.41379310344827586, 'f1': 0.4615384615384615, 'number': 145} {'precision': 0.6575963718820862, 'recall': 0.8055555555555556, 'f1': 0.7240948813982523, 'number': 360} 0.6779 0.7096 0.6934 0.9274
0.0984 2.0 13702 0.2675 {'precision': 0.9493287137288869, 'recall': 0.9614035087719298, 'f1': 0.9553279581608194, 'number': 2280} {'precision': 0.8330058939096268, 'recall': 0.8916929547844374, 'f1': 0.8613509395632302, 'number': 951} {'precision': 0.5959723096286973, 'recall': 0.7743254292722813, 'f1': 0.6735419630156473, 'number': 1223} {'precision': 0.8536585365853658, 'recall': 0.7636363636363637, 'f1': 0.8061420345489444, 'number': 825} {'precision': 0.6965589155370178, 'recall': 0.7562977639399944, 'f1': 0.725200162844348, 'number': 3533} {'precision': 0.4162371134020619, 'recall': 0.53125, 'f1': 0.4667630057803468, 'number': 608} {'precision': 0.8028169014084507, 'recall': 0.4789915966386555, 'f1': 0.6000000000000001, 'number': 119} {'precision': 0.8055555555555556, 'recall': 0.8, 'f1': 0.8027681660899654, 'number': 145} {'precision': 0.8200514138817481, 'recall': 0.8861111111111111, 'f1': 0.8518024032042723, 'number': 360} 0.7455 0.8068 0.7750 0.9415
0.0734 3.0 20553 0.3427 {'precision': 0.9673289183222958, 'recall': 0.9609649122807018, 'f1': 0.9641364136413642, 'number': 2280} {'precision': 0.8236434108527132, 'recall': 0.8937960042060988, 'f1': 0.8572869389813415, 'number': 951} {'precision': 0.6429503916449086, 'recall': 0.8053965658217498, 'f1': 0.7150635208711434, 'number': 1223} {'precision': 0.8019441069258809, 'recall': 0.8, 'f1': 0.8009708737864076, 'number': 825} {'precision': 0.7178800856531049, 'recall': 0.7591282196433626, 'f1': 0.7379281881964507, 'number': 3533} {'precision': 0.4699853587115666, 'recall': 0.5279605263157895, 'f1': 0.4972889233152594, 'number': 608} {'precision': 0.6941176470588235, 'recall': 0.4957983193277311, 'f1': 0.5784313725490197, 'number': 119} {'precision': 0.8467153284671532, 'recall': 0.8, 'f1': 0.8226950354609929, 'number': 145} {'precision': 0.7995110024449877, 'recall': 0.9083333333333333, 'f1': 0.8504551365409623, 'number': 360} 0.7654 0.8155 0.7896 0.9398
0.0562 4.0 27404 0.3282 {'precision': 0.9607493309545049, 'recall': 0.9447368421052632, 'f1': 0.9526758071649712, 'number': 2280} {'precision': 0.8263598326359832, 'recall': 0.8307045215562566, 'f1': 0.8285264813843733, 'number': 951} {'precision': 0.6615074024226111, 'recall': 0.803761242845462, 'f1': 0.7257290513104466, 'number': 1223} {'precision': 0.7624861265260822, 'recall': 0.8327272727272728, 'f1': 0.7960602549246814, 'number': 825} {'precision': 0.7137466307277628, 'recall': 0.7495046702519106, 'f1': 0.7311887339500207, 'number': 3533} {'precision': 0.4671875, 'recall': 0.4917763157894737, 'f1': 0.47916666666666663, 'number': 608} {'precision': 0.5688073394495413, 'recall': 0.5210084033613446, 'f1': 0.543859649122807, 'number': 119} {'precision': 0.8907563025210085, 'recall': 0.7310344827586207, 'f1': 0.8030303030303031, 'number': 145} {'precision': 0.8196286472148541, 'recall': 0.8583333333333333, 'f1': 0.8385345997286294, 'number': 360} 0.7626 0.8003 0.7810 0.9399
0.0413 5.0 34255 0.3534 {'precision': 0.9620978404583517, 'recall': 0.9574561403508772, 'f1': 0.9597713783249064, 'number': 2280} {'precision': 0.8567041965199591, 'recall': 0.8801261829652997, 'f1': 0.8682572614107884, 'number': 951} {'precision': 0.6488095238095238, 'recall': 0.8021259198691741, 'f1': 0.7173674588665446, 'number': 1223} {'precision': 0.8273736128236745, 'recall': 0.8133333333333334, 'f1': 0.8202933985330073, 'number': 825} {'precision': 0.7264, 'recall': 0.7710161335975092, 'f1': 0.7480433887134423, 'number': 3533} {'precision': 0.4946401225114854, 'recall': 0.53125, 'f1': 0.5122918318794607, 'number': 608} {'precision': 0.5426356589147286, 'recall': 0.5882352941176471, 'f1': 0.5645161290322581, 'number': 119} {'precision': 0.7677419354838709, 'recall': 0.8206896551724138, 'f1': 0.7933333333333332, 'number': 145} {'precision': 0.8656330749354005, 'recall': 0.9305555555555556, 'f1': 0.896921017402945, 'number': 360} 0.7745 0.8207 0.7969 0.9442
0.0304 6.0 41106 0.4328 {'precision': 0.9694960212201591, 'recall': 0.9618421052631579, 'f1': 0.965653896961691, 'number': 2280} {'precision': 0.8734939759036144, 'recall': 0.9148264984227129, 'f1': 0.8936825885978429, 'number': 951} {'precision': 0.6484018264840182, 'recall': 0.812755519215045, 'f1': 0.7213352685050799, 'number': 1223} {'precision': 0.8534370946822308, 'recall': 0.7975757575757576, 'f1': 0.8245614035087719, 'number': 825} {'precision': 0.7543478260869565, 'recall': 0.785734503255024, 'f1': 0.7697213364758074, 'number': 3533} {'precision': 0.48439821693907875, 'recall': 0.5361842105263158, 'f1': 0.508977361436378, 'number': 608} {'precision': 0.6111111111111112, 'recall': 0.5546218487394958, 'f1': 0.5814977973568282, 'number': 119} {'precision': 0.8872180451127819, 'recall': 0.8137931034482758, 'f1': 0.8489208633093526, 'number': 145} {'precision': 0.8829787234042553, 'recall': 0.9222222222222223, 'f1': 0.9021739130434783, 'number': 360} 0.7912 0.8296 0.8100 0.9388
0.0199 7.0 47957 0.3676 {'precision': 0.9600347523892268, 'recall': 0.9692982456140351, 'f1': 0.9646442601484069, 'number': 2280} {'precision': 0.8231441048034934, 'recall': 0.7928496319663512, 'f1': 0.8077129084092126, 'number': 951} {'precision': 0.6872852233676976, 'recall': 0.8176614881439084, 'f1': 0.7468259895444361, 'number': 1223} {'precision': 0.7914252607184241, 'recall': 0.8278787878787879, 'f1': 0.8092417061611374, 'number': 825} {'precision': 0.7416034669555797, 'recall': 0.7749787715822247, 'f1': 0.757923875432526, 'number': 3533} {'precision': 0.4984375, 'recall': 0.524671052631579, 'f1': 0.5112179487179488, 'number': 608} {'precision': 0.7777777777777778, 'recall': 0.5882352941176471, 'f1': 0.6698564593301436, 'number': 119} {'precision': 0.8823529411764706, 'recall': 0.8275862068965517, 'f1': 0.8540925266903915, 'number': 145} {'precision': 0.8871391076115486, 'recall': 0.9388888888888889, 'f1': 0.9122807017543859, 'number': 360} 0.7859 0.8196 0.8024 0.9438
0.0132 8.0 54808 0.4376 {'precision': 0.96, 'recall': 0.9578947368421052, 'f1': 0.9589462129527992, 'number': 2280} {'precision': 0.8481404958677686, 'recall': 0.8633017875920084, 'f1': 0.8556539864512768, 'number': 951} {'precision': 0.6822880771881461, 'recall': 0.8094848732624693, 'f1': 0.7404637247569185, 'number': 1223} {'precision': 0.8098086124401914, 'recall': 0.8206060606060606, 'f1': 0.8151715833835039, 'number': 825} {'precision': 0.7253596164091636, 'recall': 0.7707330880271723, 'f1': 0.7473583093179635, 'number': 3533} {'precision': 0.5070422535211268, 'recall': 0.5328947368421053, 'f1': 0.5196471531676022, 'number': 608} {'precision': 0.6194690265486725, 'recall': 0.5882352941176471, 'f1': 0.603448275862069, 'number': 119} {'precision': 0.8145695364238411, 'recall': 0.8482758620689655, 'f1': 0.8310810810810811, 'number': 145} {'precision': 0.8596491228070176, 'recall': 0.9527777777777777, 'f1': 0.9038208168642952, 'number': 360} 0.7798 0.8219 0.8003 0.9414
0.0084 9.0 61659 0.4624 {'precision': 0.9685562444641276, 'recall': 0.9592105263157895, 'f1': 0.9638607315998237, 'number': 2280} {'precision': 0.8442714126807565, 'recall': 0.7981072555205048, 'f1': 0.8205405405405405, 'number': 951} {'precision': 0.6707152496626181, 'recall': 0.812755519215045, 'f1': 0.7349353049907579, 'number': 1223} {'precision': 0.8192771084337349, 'recall': 0.8242424242424242, 'f1': 0.8217522658610271, 'number': 825} {'precision': 0.7267348036578806, 'recall': 0.764789131050099, 'f1': 0.7452765135843331, 'number': 3533} {'precision': 0.5121212121212121, 'recall': 0.555921052631579, 'f1': 0.5331230283911672, 'number': 608} {'precision': 0.7070707070707071, 'recall': 0.5882352941176471, 'f1': 0.6422018348623852, 'number': 119} {'precision': 0.8541666666666666, 'recall': 0.8482758620689655, 'f1': 0.8512110726643598, 'number': 145} {'precision': 0.868020304568528, 'recall': 0.95, 'f1': 0.9071618037135278, 'number': 360} 0.7817 0.8159 0.7984 0.9408
0.0053 10.0 68510 0.4992 {'precision': 0.9660942316160281, 'recall': 0.962280701754386, 'f1': 0.9641836958910129, 'number': 2280} {'precision': 0.8500527983104541, 'recall': 0.8464773922187171, 'f1': 0.8482613277133825, 'number': 951} {'precision': 0.6867305061559508, 'recall': 0.820932134096484, 'f1': 0.7478584729981377, 'number': 1223} {'precision': 0.8540609137055838, 'recall': 0.8157575757575758, 'f1': 0.8344699318040918, 'number': 825} {'precision': 0.7446111869031378, 'recall': 0.7724313614491933, 'f1': 0.7582661850514032, 'number': 3533} {'precision': 0.5221238938053098, 'recall': 0.5822368421052632, 'f1': 0.5505443234836703, 'number': 608} {'precision': 0.6068376068376068, 'recall': 0.5966386554621849, 'f1': 0.6016949152542374, 'number': 119} {'precision': 0.8503401360544217, 'recall': 0.8620689655172413, 'f1': 0.8561643835616437, 'number': 145} {'precision': 0.8461538461538461, 'recall': 0.9472222222222222, 'f1': 0.8938401048492791, 'number': 360} 0.7918 0.8260 0.8085 0.9414

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.12.1
  • Datasets 2.9.0
  • Tokenizers 0.13.2
Downloads last month
2
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.