layoutlm-funsd

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: 0.0754
• Ignal: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}
• Oise: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}
• Overall Precision: 0.0
• Overall Recall: 0.0
• Overall F1: 0.0
• Overall Accuracy: 0.9670

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Ignal	Oise	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.7198	1.0	1	0.7152	{'precision': 0.010416666666666666, 'recall': 0.09090909090909091, 'f1': 0.018691588785046728, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0052	0.0435	0.0093	0.5024
0.7121	2.0	2	0.7152	{'precision': 0.010416666666666666, 'recall': 0.09090909090909091, 'f1': 0.018691588785046728, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0052	0.0435	0.0093	0.5024
0.7191	3.0	3	0.4802	{'precision': 0.045454545454545456, 'recall': 0.09090909090909091, 'f1': 0.060606060606060615, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0222	0.0435	0.0294	0.9245
0.4799	4.0	4	0.3268	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9646
0.3263	5.0	5	0.2246	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.2269	6.0	6	0.1598	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.1625	7.0	7	0.1227	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.1246	8.0	8	0.1030	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.1042	9.0	9	0.0937	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.0942	10.0	10	0.0892	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.0888	11.0	11	0.0861	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.0834	12.0	12	0.0832	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.0768	13.0	13	0.0805	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.0745	14.0	14	0.0778	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670
0.071	15.0	15	0.0754	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}	0.0	0.0	0.0	0.9670

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0