layoutlm-ttform

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: 0.8035
• Validation Loss: 0.6094
• Train Overall Precision: 0.8793
• Train Overall Recall: 0.7969
• Train Overall F1: 0.8361
• Train Overall Accuracy: 0.9204
• 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
1.9166	1.6851	0.125	0.1562	0.1389	0.6567	0
1.7084	1.4917	0.3793	0.3438	0.3607	0.7811	1
1.5343	1.3162	0.4151	0.3438	0.3761	0.7811	2
1.3620	1.1511	0.4528	0.375	0.4103	0.8159	3
1.2149	0.9970	0.5818	0.5	0.5378	0.8358	4
1.0742	0.8546	0.8393	0.7344	0.7833	0.8905	5
0.9422	0.7259	0.8393	0.7344	0.7833	0.9154	6
0.8035	0.6094	0.8793	0.7969	0.8361	0.9204	7

Framework versions

• Transformers 4.26.0
• TensorFlow 2.9.2
• Datasets 2.9.0
• Tokenizers 0.13.2