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: 0.2062
• Validation Loss: 0.7277
• Train Overall Precision: 0.6941
• Train Overall Recall: 0.7913
• Train Overall F1: 0.7395
• Train Overall Accuracy: 0.7950
• 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
1.1741	0.9133	0.5563	0.6468	0.5981	0.7059	0
0.7871	0.7492	0.6158	0.7486	0.6757	0.7665	1
0.5857	0.6867	0.6406	0.7602	0.6953	0.7780	2
0.4573	0.6551	0.6806	0.7752	0.7248	0.7982	3
0.3599	0.6462	0.7016	0.7692	0.7338	0.8092	4
0.3038	0.6978	0.7318	0.7587	0.7450	0.8006	5
0.2455	0.6850	0.7242	0.7787	0.7505	0.8019	6
0.2062	0.7277	0.6941	0.7913	0.7395	0.7950	7

Framework versions

• Transformers 4.47.1
• TensorFlow 2.18.0
• Datasets 3.2.0
• Tokenizers 0.21.0