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: 0.2552
• Validation Loss: 0.6563
• Train Overall Precision: 0.7174
• Train Overall Recall: 0.7988
• Train Overall F1: 0.7559
• Train Overall Accuracy: 0.8073
• 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: mixed_float16

Training results

Train Loss	Validation Loss	Train Overall Precision	Train Overall Recall	Train Overall F1	Train Overall Accuracy	Epoch
1.7065	1.3937	0.2463	0.2418	0.2441	0.5476	0
1.1571	0.8921	0.6122	0.6352	0.6235	0.7318	1
0.7498	0.6885	0.6740	0.7376	0.7044	0.7816	2
0.5523	0.6299	0.6752	0.7852	0.7260	0.8011	3
0.4503	0.6387	0.6913	0.7943	0.7392	0.8010	4
0.3554	0.6279	0.7121	0.7792	0.7441	0.8110	5
0.3005	0.6507	0.7201	0.7782	0.7480	0.8085	6
0.2552	0.6563	0.7174	0.7988	0.7559	0.8073	7

Framework versions

• Transformers 4.34.0
• TensorFlow 2.12.0
• Datasets 2.14.5
• Tokenizers 0.14.0