Layouttest

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: 0.9183
• F1: 0.7396
• Recall: 0.7132
• Precision: 0.7681
• Pred Bestellnummer: 148
• Percentage Pred Act Bestellnummer: 1.0350
• Pred Kundennr.: 49
• Percentage Pred Act Kundennr.: 1.0208
• Pred Bezug 1: 26
• Percentage Pred Act Bezug 1: 1.8571
• Pred Modell 1: 115
• Percentage Pred Act Modell 1: 1.1616
• Pred Menge1: 35
• Percentage Pred Act Menge1: 1.6667
• Pred Menge4: 5
• Percentage Pred Act Menge4: 0.5
• Pred Möbelhaus: 97
• Percentage Pred Act Möbelhaus: 1.0659
• Pred Termin kundenwunsch - kw: 28
• Percentage Pred Act Termin kundenwunsch - kw: 0.875
• Pred Kommission: 53
• Percentage Pred Act Kommission: 0.9138
• Pred Holz 1: 23
• Percentage Pred Act Holz 1: 1.2105
• Pred Menge2: 17
• Percentage Pred Act Menge2: 0.9444
• Pred Modell 2: 64
• Percentage Pred Act Modell 2: 1.0323
• Pred Zusatz 1: 14
• Percentage Pred Act Zusatz 1: 1.0
• Pred La-anschrift: 5
• Percentage Pred Act La-anschrift: 0.8333
• Pred Holz 2: 30
• Percentage Pred Act Holz 2: 1.4286
• Pred Menge3: 13
• Percentage Pred Act Menge3: 0.5909
• Pred Modell 3: 71
• Percentage Pred Act Modell 3: 1.0758
• Pred Bezug 4: 1
• Percentage Pred Act Bezug 4: 0.1429
• Pred Bezug 3: 11
• Percentage Pred Act Bezug 3: 2.75
• Pred Var-ausf 1: 4
• Percentage Pred Act Var-ausf 1: 0.5
• Act Bestellnummer: 143
• Act Kundennr.: 48
• Act Bezug 1: 14
• Act Modell 1: 99
• Act Menge1: 21
• Act Menge4: 10
• Act Möbelhaus: 91
• Act Bezug 2: 13
• Act Zusatz 2: 1
• Act Termin kundenwunsch - kw: 32
• Act Kommission: 58
• Act Holz 1: 19
• Act Menge3: 22
• Act Modell 2: 62
• Act Modell 3: 66
• Act Modell 4: 6
• Act Bezug 4: 7
• Act Zusatz 3: 1
• Act Holz 2: 21
• Act Menge2: 18
• Act Bezug 3: 4
• Act Var-ausf 1: 8
• Act Holz 3: 5
• Act Zusatz 1: 14
• Act Var-ausf. 2: 7
• Act Var-ausf. 3: 4
• Act Pv 3: 1
• Act Holz 4: 1
• Act Var-ausf. 5: 1
• Act Modell 5: 5
• Act La-anschrift: 6
• Act Menge5: 1

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.53.0.dev0
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1