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: 0.2612
• Validation Loss: 0.6785
• Train Overall Precision: 0.7279
• Train Overall Recall: 0.8038
• Train Overall F1: 0.7639
• Train Overall Accuracy: 0.8047
• 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
1.7332	1.4190	0.2417	0.2669	0.2537	0.5168	0
1.1874	0.9479	0.5511	0.5524	0.5517	0.7008	1
0.7973	0.7664	0.6409	0.6869	0.6631	0.7499	2
0.6030	0.6373	0.7067	0.7461	0.7259	0.7985	3
0.4735	0.6158	0.7182	0.7878	0.7514	0.8117	4
0.3720	0.6051	0.7093	0.7923	0.7485	0.8178	5
0.2951	0.6249	0.7227	0.8003	0.7595	0.8186	6
0.2612	0.6785	0.7279	0.8038	0.7639	0.8047	7

Framework versions

• Transformers 4.35.2
• TensorFlow 2.14.0
• Datasets 2.15.0
• Tokenizers 0.15.0