layoutlm-synth2

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: 0.0270
• Ank Address: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}
• Ank Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}
• Ayee Address: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}
• Ayee Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}
• Icr: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}
• Mount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}
• Overall Precision: 1.0
• Overall Recall: 1.0
• Overall F1: 1.0
• Overall Accuracy: 1.0

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: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Ank Address	Ank Name	Ayee Address	Ayee Name	Icr	Mount	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
1.4218	1.0	10	0.9682	{'precision': 0.03225806451612903, 'recall': 0.1, 'f1': 0.04878048780487805, 'number': 20}	{'precision': 0.3333333333333333, 'recall': 0.05, 'f1': 0.08695652173913045, 'number': 20}	{'precision': 0.03125, 'recall': 0.1, 'f1': 0.047619047619047616, 'number': 20}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 20}	{'precision': 1.0, 'recall': 0.7, 'f1': 0.8235294117647058, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	0.2393	0.325	0.2756	0.5811
0.7362	2.0	20	0.3668	{'precision': 0.8636363636363636, 'recall': 0.95, 'f1': 0.9047619047619048, 'number': 20}	{'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 20}	{'precision': 0.8571428571428571, 'recall': 0.9, 'f1': 0.8780487804878048, 'number': 20}	{'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	0.904	0.9417	0.9224	0.9855
0.2488	3.0	30	0.0892	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	1.0	1.0	1.0	1.0
0.0877	4.0	40	0.0373	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	1.0	1.0	1.0	1.0
0.0491	5.0	50	0.0270	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 20}	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.27.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2