layoutlm-sroie_only

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: 0.0629
• Ate: {'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}
• Ddress: {'precision': 0.86, 'recall': 0.86, 'f1': 0.8599999999999999, 'number': 50}
• Ompany: {'precision': 0.7777777777777778, 'recall': 0.84, 'f1': 0.8076923076923077, 'number': 50}
• Otal: {'precision': 0.4166666666666667, 'recall': 0.3, 'f1': 0.3488372093023256, 'number': 50}
• Overall Precision: 0.7692
• Overall Recall: 0.75
• Overall F1: 0.7595
• Overall Accuracy: 0.9820

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
0.5019	1.0	36	0.1120	{'precision': 0.671875, 'recall': 0.86, 'f1': 0.7543859649122807, 'number': 50}	{'precision': 0.7454545454545455, 'recall': 0.82, 'f1': 0.780952380952381, 'number': 50}	{'precision': 0.5344827586206896, 'recall': 0.62, 'f1': 0.574074074074074, 'number': 50}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 50}	0.6497	0.575	0.6101	0.9739
0.0635	2.0	72	0.0728	{'precision': 0.8448275862068966, 'recall': 0.98, 'f1': 0.9074074074074074, 'number': 50}	{'precision': 0.86, 'recall': 0.86, 'f1': 0.8599999999999999, 'number': 50}	{'precision': 0.7924528301886793, 'recall': 0.84, 'f1': 0.8155339805825242, 'number': 50}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 50}	0.8272	0.67	0.7403	0.9818
0.0429	3.0	108	0.0650	{'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}	{'precision': 0.86, 'recall': 0.86, 'f1': 0.8599999999999999, 'number': 50}	{'precision': 0.7924528301886793, 'recall': 0.84, 'f1': 0.8155339805825242, 'number': 50}	{'precision': 0.4117647058823529, 'recall': 0.28, 'f1': 0.3333333333333333, 'number': 50}	0.7760	0.745	0.7602	0.9818
0.0341	4.0	144	0.0629	{'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}	{'precision': 0.86, 'recall': 0.86, 'f1': 0.8599999999999999, 'number': 50}	{'precision': 0.7777777777777778, 'recall': 0.84, 'f1': 0.8076923076923077, 'number': 50}	{'precision': 0.4166666666666667, 'recall': 0.3, 'f1': 0.3488372093023256, 'number': 50}	0.7692	0.75	0.7595	0.9820

Framework versions

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