layoutlm-SROIE-tf

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:

• Train Loss: 0.0151
• Validation Loss: 0.0289
• Train Overall Precision: 0.9110
• Train Overall Recall: 0.9438
• Train Overall F1: 0.9271
• Train Overall Accuracy: 0.9942
• Epoch: 7

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Train Overall Precision	Train Overall Recall	Train Overall F1	Train Overall Accuracy	Epoch
0.4238	0.1257	0.7483	0.6535	0.6977	0.9684	0
0.0943	0.0549	0.9101	0.7075	0.7961	0.9863	1
0.0500	0.0403	0.8310	0.8573	0.8440	0.9891	2
0.0344	0.0344	0.8468	0.9042	0.8746	0.9916	3
0.0282	0.0346	0.8417	0.9344	0.8856	0.9918	4
0.0222	0.0296	0.9155	0.9207	0.9181	0.9938	5
0.0168	0.0328	0.8756	0.9431	0.9081	0.9931	6
0.0151	0.0289	0.9110	0.9438	0.9271	0.9942	7

Framework versions

• Transformers 4.48.3
• TensorFlow 2.18.0
• Datasets 3.3.2
• Tokenizers 0.21.0