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: 0.2920
• Validation Loss: 0.6882
• Train Overall Precision: 0.7061
• Train Overall Recall: 0.7943
• Train Overall F1: 0.7476
• Train Overall Accuracy: 0.7966
• 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
1.7368	1.4201	0.2646	0.3051	0.2834	0.5163	0
1.2040	0.9290	0.5253	0.6051	0.5624	0.7138	1
0.8330	0.8307	0.5912	0.7010	0.6414	0.7294	2
0.6119	0.6724	0.6667	0.7697	0.7145	0.7902	3
0.4706	0.6231	0.6905	0.7883	0.7362	0.8068	4
0.3759	0.6366	0.7203	0.7933	0.7550	0.8077	5
0.3043	0.7168	0.6989	0.7953	0.7440	0.7937	6
0.2920	0.6882	0.7061	0.7943	0.7476	0.7966	7

Framework versions

• Transformers 4.28.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3