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: 0.2451
• Validation Loss: 0.7339
• Train Overall Precision: 0.7247
• Train Overall Recall: 0.8058
• Train Overall F1: 0.7631
• Train Overall Accuracy: 0.7976
• 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
1.6758	1.4035	0.2734	0.3191	0.2945	0.5113	0
1.1350	0.8802	0.5626	0.6538	0.6048	0.7313	1
0.7417	0.6927	0.6604	0.7602	0.7068	0.7805	2
0.5568	0.6715	0.7039	0.7501	0.7263	0.7823	3
0.4493	0.6464	0.7073	0.7782	0.7410	0.7980	4
0.3732	0.6112	0.7108	0.7858	0.7464	0.8182	5
0.2949	0.6429	0.7123	0.7988	0.7531	0.8070	6
0.2451	0.7339	0.7247	0.8058	0.7631	0.7976	7

Framework versions

• Transformers 4.26.0
• TensorFlow 2.9.2
• Datasets 2.9.0
• Tokenizers 0.13.2