Loss: 0.0036
Article Number: {'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}
Building Number: {'precision': 0.9876543209876543, 'recall': 1.0, 'f1': 0.9937888198757764, 'number': 80}
Coord X: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}
Coord Y: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}
Distrito: {'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}
Distrito Code: {'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}
Floor Division: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 79}
Locality: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 88}
Municipality: {'precision': 0.9833333333333333, 'recall': 0.9672131147540983, 'f1': 0.9752066115702478, 'number': 61}
Municipality Code: {'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}
Owner Name: {'precision': 0.98, 'recall': 1.0, 'f1': 0.98989898989899, 'number': 98}
Owner Nif: {'precision': 0.9880952380952381, 'recall': 1.0, 'f1': 0.9940119760479043, 'number': 83}
Parish: {'precision': 0.9864864864864865, 'recall': 0.9733333333333334, 'f1': 0.9798657718120806, 'number': 75}
Parish Code: {'precision': 0.9814814814814815, 'recall': 0.9814814814814815, 'f1': 0.9814814814814815, 'number': 54}
Postal Code: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 80}
Property Fraction: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 75}
Registry City: {'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}
Registry Number: {'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}
Street Name: {'precision': 0.9901960784313726, 'recall': 0.9901960784313726, 'f1': 0.9901960784313726, 'number': 102}
Overall Precision: 0.9937
Overall Recall: 0.9906
Overall F1: 0.9922
Overall Accuracy: 0.9994

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: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Article Number	Building Number	Coord X	Coord Y	Distrito	Distrito Code	Floor Division	Locality	Municipality	Municipality Code	Owner Name	Owner Nif	Parish	Parish Code	Postal Code	Property Fraction	Registry City	Registry Number	Street Name	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0098	1.0	769	0.0090	{'precision': 1.0, 'recall': 0.9629629629629629, 'f1': 0.9811320754716981, 'number': 54}	{'precision': 1.0, 'recall': 0.9875, 'f1': 0.9937106918238994, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 0.9629629629629629, 'recall': 0.9454545454545454, 'f1': 0.9541284403669724, 'number': 55}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 79}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 88}	{'precision': 0.95, 'recall': 0.9344262295081968, 'f1': 0.9421487603305784, 'number': 61}	{'precision': 0.9814814814814815, 'recall': 0.9814814814814815, 'f1': 0.9814814814814815, 'number': 54}	{'precision': 0.9607843137254902, 'recall': 1.0, 'f1': 0.98, 'number': 98}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 83}	{'precision': 0.948051948051948, 'recall': 0.9733333333333334, 'f1': 0.9605263157894737, 'number': 75}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 75}	{'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54}	{'precision': 0.9595959595959596, 'recall': 0.9313725490196079, 'f1': 0.945273631840796, 'number': 102}	0.9859	0.9821	0.9840	0.9991
0.0024	2.0	1538	0.0050	{'precision': 0.9814814814814815, 'recall': 0.9814814814814815, 'f1': 0.9814814814814815, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 0.9818181818181818, 'recall': 0.9818181818181818, 'f1': 0.9818181818181818, 'number': 55}	{'precision': 0.9814814814814815, 'recall': 0.9814814814814815, 'f1': 0.9814814814814815, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 79}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 88}	{'precision': 0.9655172413793104, 'recall': 0.9180327868852459, 'f1': 0.9411764705882353, 'number': 61}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.98, 'recall': 1.0, 'f1': 0.98989898989899, 'number': 98}	{'precision': 1.0, 'recall': 0.9879518072289156, 'f1': 0.993939393939394, 'number': 83}	{'precision': 0.972972972972973, 'recall': 0.96, 'f1': 0.9664429530201343, 'number': 75}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 80}	{'precision': 1.0, 'recall': 0.9866666666666667, 'f1': 0.9932885906040269, 'number': 75}	{'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 0.9901960784313726, 'f1': 0.9950738916256158, 'number': 102}	0.9929	0.9867	0.9898	0.9994
0.0012	3.0	2307	0.0061	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.9875, 'recall': 0.9875, 'f1': 0.9875, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 1.0, 'recall': 0.9636363636363636, 'f1': 0.9814814814814815, 'number': 55}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 79}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 88}	{'precision': 0.9672131147540983, 'recall': 0.9672131147540983, 'f1': 0.9672131147540983, 'number': 61}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 98}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 83}	{'precision': 1.0, 'recall': 0.9733333333333334, 'f1': 0.9864864864864865, 'number': 75}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 80}	{'precision': 1.0, 'recall': 0.9866666666666667, 'f1': 0.9932885906040269, 'number': 75}	{'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 0.9901960784313726, 'f1': 0.9950738916256158, 'number': 102}	0.9976	0.9883	0.9930	0.9994
0.0032	4.0	3076	0.0041	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.9876543209876543, 'recall': 1.0, 'f1': 0.9937888198757764, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 0.9821428571428571, 'recall': 1.0, 'f1': 0.9909909909909909, 'number': 55}	{'precision': 0.9814814814814815, 'recall': 0.9814814814814815, 'f1': 0.9814814814814815, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 79}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 88}	{'precision': 0.9827586206896551, 'recall': 0.9344262295081968, 'f1': 0.9579831932773109, 'number': 61}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.98, 'recall': 1.0, 'f1': 0.98989898989899, 'number': 98}	{'precision': 0.9880952380952381, 'recall': 1.0, 'f1': 0.9940119760479043, 'number': 83}	{'precision': 0.9605263157894737, 'recall': 0.9733333333333334, 'f1': 0.9668874172185431, 'number': 75}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 75}	{'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.9901960784313726, 'recall': 0.9901960784313726, 'f1': 0.9901960784313726, 'number': 102}	0.9914	0.9899	0.9906	0.9993
0.0009	5.0	3845	0.0036	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.9876543209876543, 'recall': 1.0, 'f1': 0.9937888198757764, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 41}	{'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 79}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 88}	{'precision': 0.9833333333333333, 'recall': 0.9672131147540983, 'f1': 0.9752066115702478, 'number': 61}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.98, 'recall': 1.0, 'f1': 0.98989898989899, 'number': 98}	{'precision': 0.9880952380952381, 'recall': 1.0, 'f1': 0.9940119760479043, 'number': 83}	{'precision': 0.9864864864864865, 'recall': 0.9733333333333334, 'f1': 0.9798657718120806, 'number': 75}	{'precision': 0.9814814814814815, 'recall': 0.9814814814814815, 'f1': 0.9814814814814815, 'number': 54}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 80}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 75}	{'precision': 1.0, 'recall': 0.9818181818181818, 'f1': 0.9908256880733944, 'number': 55}	{'precision': 1.0, 'recall': 0.9814814814814815, 'f1': 0.9906542056074767, 'number': 54}	{'precision': 0.9901960784313726, 'recall': 0.9901960784313726, 'f1': 0.9901960784313726, 'number': 102}	0.9937	0.9906	0.9922	0.9994

Framework versions

Transformers 4.51.3
Pytorch 2.7.1+cu128
Datasets 3.5.1
Tokenizers 0.21.1

HenriqueLin/pt-property-record-layoutlmv3-ner

property_record

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

HenriqueLin/
pt-property-record-layoutlmv3-ner