lilt-invoices

This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0031
• Endorname: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 177}
• Escription: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 183}
• Illingaddress: {'precision': 1.0, 'recall': 0.9937888198757764, 'f1': 0.9968847352024921, 'number': 161}
• Mount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 175}
• Nitprice: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 156}
• Nvoicedate: {'precision': 0.9941520467836257, 'recall': 1.0, 'f1': 0.9970674486803519, 'number': 170}
• Nvoicetotal: {'precision': 0.9946808510638298, 'recall': 0.9946808510638298, 'f1': 0.9946808510638298, 'number': 188}
• Otaltax: {'precision': 1.0, 'recall': 0.9927007299270073, 'f1': 0.9963369963369962, 'number': 137}
• Uantity: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 167}
• Ubtotal: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 151}
• Overall Precision: 0.9988
• Overall Recall: 0.9982
• Overall F1: 0.9985
• 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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Endorname	Escription	Illingaddress	Mount	Nitprice	Nvoicedate	Nvoicetotal	Otaltax	Uantity	Ubtotal	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.1736	21.74	500	0.0031	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 177}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 183}	{'precision': 1.0, 'recall': 0.9937888198757764, 'f1': 0.9968847352024921, 'number': 161}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 175}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 156}	{'precision': 0.9941520467836257, 'recall': 1.0, 'f1': 0.9970674486803519, 'number': 170}	{'precision': 0.9946808510638298, 'recall': 0.9946808510638298, 'f1': 0.9946808510638298, 'number': 188}	{'precision': 1.0, 'recall': 0.9927007299270073, 'f1': 0.9963369963369962, 'number': 137}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 167}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 151}	0.9988	0.9982	0.9985	0.9994

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3