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: 0.6688
• Validation Loss: 1.0205
• Train Overall Precision: 0.4820
• Train Overall Recall: 0.5640
• Train Overall F1: 0.5198
• Train Overall Accuracy: 0.6662
• 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
1.7446	1.5046	0.1515	0.1912	0.1690	0.3736	0
1.4357	1.3277	0.2590	0.4295	0.3231	0.4314	1
1.2564	1.2248	0.3028	0.4907	0.3745	0.4767	2
1.1340	1.1044	0.3433	0.4802	0.4003	0.5769	3
1.0126	1.0670	0.4183	0.5519	0.4759	0.5820	4
0.8976	1.0148	0.3816	0.5273	0.4428	0.6186	5
0.7552	1.0872	0.4571	0.5449	0.4971	0.6268	6
0.6688	1.0205	0.4820	0.5640	0.5198	0.6662	7

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2