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: 0.2406
• Validation Loss: 0.7155
• Train Overall Precision: 0.7459
• Train Overall Recall: 0.7893
• Train Overall F1: 0.7669
• Train Overall Accuracy: 0.8064
• 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: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': 2.9999999242136255e-05, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Train Overall Precision	Train Overall Recall	Train Overall F1	Train Overall Accuracy	Epoch
1.7115	1.4279	0.2575	0.2965	0.2757	0.4884	0
1.1520	0.8490	0.5994	0.6854	0.6395	0.7372	1
0.7816	0.7069	0.6391	0.7471	0.6889	0.7808	2
0.5815	0.6601	0.7089	0.7672	0.7369	0.7992	3
0.4460	0.6306	0.7093	0.7787	0.7424	0.8060	4
0.3658	0.6575	0.7372	0.7812	0.7586	0.8111	5
0.2926	0.6658	0.7240	0.7832	0.7525	0.8096	6
0.2406	0.7155	0.7459	0.7893	0.7669	0.8064	7

Framework versions

• Transformers 4.41.2
• TensorFlow 2.16.1
• Datasets 2.19.2
• Tokenizers 0.19.1