layoutlm-sroie_syntheticXsroie

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: 0.0420
• Ate: {'precision': 0.935064935064935, 'recall': 0.96, 'f1': 0.9473684210526316, 'number': 150}
• Ddress: {'precision': 0.9, 'recall': 0.9060402684563759, 'f1': 0.903010033444816, 'number': 149}
• Ompany: {'precision': 0.8544303797468354, 'recall': 0.9, 'f1': 0.8766233766233766, 'number': 150}
• Otal: {'precision': 0.48, 'recall': 0.56, 'f1': 0.5169230769230769, 'number': 150}
• Overall Precision: 0.7818
• Overall Recall: 0.8314
• Overall F1: 0.8058
• Overall Accuracy: 0.9857

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
0.3549	1.0	60	0.0863	{'precision': 0.8630952380952381, 'recall': 0.9666666666666667, 'f1': 0.9119496855345911, 'number': 150}	{'precision': 0.7639751552795031, 'recall': 0.825503355704698, 'f1': 0.7935483870967742, 'number': 149}	{'precision': 0.7391304347826086, 'recall': 0.7933333333333333, 'f1': 0.7652733118971061, 'number': 150}	{'precision': 0.2777777777777778, 'recall': 0.16666666666666666, 'f1': 0.20833333333333334, 'number': 150}	0.7103	0.6878	0.6989	0.9771
0.049	2.0	120	0.0530	{'precision': 0.9050632911392406, 'recall': 0.9533333333333334, 'f1': 0.9285714285714286, 'number': 150}	{'precision': 0.8993288590604027, 'recall': 0.8993288590604027, 'f1': 0.8993288590604027, 'number': 149}	{'precision': 0.8214285714285714, 'recall': 0.7666666666666667, 'f1': 0.793103448275862, 'number': 150}	{'precision': 0.43617021276595747, 'recall': 0.2733333333333333, 'f1': 0.3360655737704918, 'number': 150}	0.8004	0.7229	0.7596	0.9808
0.0313	3.0	180	0.0438	{'precision': 0.9285714285714286, 'recall': 0.9533333333333334, 'f1': 0.9407894736842105, 'number': 150}	{'precision': 0.8807947019867549, 'recall': 0.8926174496644296, 'f1': 0.8866666666666666, 'number': 149}	{'precision': 0.8481012658227848, 'recall': 0.8933333333333333, 'f1': 0.8701298701298702, 'number': 150}	{'precision': 0.4659090909090909, 'recall': 0.5466666666666666, 'f1': 0.5030674846625767, 'number': 150}	0.7700	0.8214	0.7948	0.9851
0.0248	4.0	240	0.0420	{'precision': 0.935064935064935, 'recall': 0.96, 'f1': 0.9473684210526316, 'number': 150}	{'precision': 0.9, 'recall': 0.9060402684563759, 'f1': 0.903010033444816, 'number': 149}	{'precision': 0.8544303797468354, 'recall': 0.9, 'f1': 0.8766233766233766, 'number': 150}	{'precision': 0.48, 'recall': 0.56, 'f1': 0.5169230769230769, 'number': 150}	0.7818	0.8314	0.8058	0.9857

Framework versions

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