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: 0.2511
• Validation Loss: 0.6882
• Train Overall Precision: 0.7189
• Train Overall Recall: 0.7878
• Train Overall F1: 0.7517
• Train Overall Accuracy: 0.8039
• 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
1.6546	1.3264	0.3384	0.3708	0.3538	0.5774	0
1.0901	0.8303	0.6013	0.6508	0.6251	0.7392	1
0.7169	0.6666	0.6778	0.7441	0.7094	0.7864	2
0.5285	0.6429	0.6859	0.7702	0.7256	0.8022	3
0.4270	0.6216	0.7089	0.7832	0.7442	0.8092	4
0.3451	0.6699	0.7038	0.7832	0.7414	0.7972	5
0.2867	0.6886	0.7203	0.7868	0.7520	0.7965	6
0.2511	0.6882	0.7189	0.7878	0.7517	0.8039	7

Framework versions

• Transformers 4.41.0
• TensorFlow 2.15.0
• Datasets 2.19.1
• Tokenizers 0.19.1