layoutlm-sroie_synthetic_runpod

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

• Loss: 0.0653
• Ate: {'precision': 0.9176470588235294, 'recall': 0.975, 'f1': 0.9454545454545454, 'number': 80}
• Ddress: {'precision': 0.8518518518518519, 'recall': 0.8625, 'f1': 0.8571428571428572, 'number': 80}
• Ompany: {'precision': 0.8095238095238095, 'recall': 0.85, 'f1': 0.8292682926829269, 'number': 80}
• Otal: {'precision': 0.4666666666666667, 'recall': 0.2625, 'f1': 0.336, 'number': 80}
• Overall Precision: 0.8
• Overall Recall: 0.7375
• Overall F1: 0.7675
• Overall Accuracy: 0.9825

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 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Ate	Ddress	Ompany	Otal	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.4865	1.0	33	0.1149	{'precision': 0.6702127659574468, 'recall': 0.7875, 'f1': 0.7241379310344828, 'number': 80}	{'precision': 0.7926829268292683, 'recall': 0.8125, 'f1': 0.8024691358024691, 'number': 80}	{'precision': 0.6551724137931034, 'recall': 0.7125, 'f1': 0.6826347305389221, 'number': 80}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 80}	0.7034	0.5781	0.6346	0.9741
0.0712	2.0	66	0.0681	{'precision': 0.9069767441860465, 'recall': 0.975, 'f1': 0.9397590361445783, 'number': 80}	{'precision': 0.8625, 'recall': 0.8625, 'f1': 0.8625, 'number': 80}	{'precision': 0.7840909090909091, 'recall': 0.8625, 'f1': 0.8214285714285715, 'number': 80}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 80}	0.8504	0.675	0.7526	0.9829
0.0452	3.0	99	0.0623	{'precision': 0.9176470588235294, 'recall': 0.975, 'f1': 0.9454545454545454, 'number': 80}	{'precision': 0.8625, 'recall': 0.8625, 'f1': 0.8625, 'number': 80}	{'precision': 0.8072289156626506, 'recall': 0.8375, 'f1': 0.8220858895705521, 'number': 80}	{'precision': 0.25, 'recall': 0.0375, 'f1': 0.06521739130434782, 'number': 80}	0.8346	0.6781	0.7483	0.9826
0.0371	4.0	132	0.0653	{'precision': 0.9176470588235294, 'recall': 0.975, 'f1': 0.9454545454545454, 'number': 80}	{'precision': 0.8518518518518519, 'recall': 0.8625, 'f1': 0.8571428571428572, 'number': 80}	{'precision': 0.8095238095238095, 'recall': 0.85, 'f1': 0.8292682926829269, 'number': 80}	{'precision': 0.4666666666666667, 'recall': 0.2625, 'f1': 0.336, 'number': 80}	0.8	0.7375	0.7675	0.9825

Framework versions

• Transformers 4.50.0
• Pytorch 2.1.0+cu118
• Datasets 3.4.1
• Tokenizers 0.21.1