layoutlm-funsd-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: 0.6164
• Validation Loss: 1.0914
• Train Overall Precision: 0.4921
• Train Overall Recall: 0.5178
• Train Overall F1: 0.5046
• Train Overall Accuracy: 0.6136
• 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': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Overall Precision	Train Overall Recall	Train Overall F1	Train Overall Accuracy	Epoch
1.6889	1.4840	0.1755	0.3307	0.2293	0.3586	0
1.3467	1.2410	0.3182	0.4827	0.3836	0.4680	1
1.1412	1.1634	0.3303	0.5028	0.3986	0.5209	2
1.0429	1.1068	0.3727	0.5289	0.4373	0.5592	3
0.8937	1.0652	0.4460	0.5569	0.4953	0.6060	4
0.7579	1.0765	0.4660	0.5640	0.5103	0.5983	5
0.7126	1.1322	0.4677	0.5845	0.5196	0.6209	6
0.6164	1.0914	0.4921	0.5178	0.5046	0.6136	7

Framework versions

• Transformers 4.38.1
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2