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: 0.2471
• Validation Loss: 0.6741
• Train Overall Precision: 0.7311
• Train Overall Recall: 0.7858
• Train Overall F1: 0.7574
• Train Overall Accuracy: 0.8104
• 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
1.7162	1.4302	0.2735	0.3026	0.2873	0.4851	0
1.1601	0.8705	0.5728	0.6708	0.6180	0.7254	1
0.7538	0.7479	0.6533	0.7055	0.6784	0.7572	2
0.5704	0.6795	0.6686	0.7582	0.7106	0.7936	3
0.4379	0.6239	0.7022	0.7762	0.7374	0.8062	4
0.3470	0.6538	0.7226	0.7842	0.7522	0.7986	5
0.2908	0.6827	0.7033	0.7777	0.7386	0.7971	6
0.2471	0.6741	0.7311	0.7858	0.7574	0.8104	7

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.0