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: 0.2445
• Validation Loss: 0.6550
• Train Overall Precision: 0.7272
• Train Overall Recall: 0.7893
• Train Overall F1: 0.7570
• Train Overall Accuracy: 0.8195
• 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
1.6675	1.3532	0.3327	0.3477	0.3400	0.5549	0
1.0883	0.8340	0.6022	0.6713	0.6349	0.7466	1
0.7296	0.6953	0.6452	0.7501	0.6937	0.7836	2
0.5398	0.6647	0.6832	0.7672	0.7228	0.7895	3
0.4379	0.6258	0.7092	0.7697	0.7382	0.8069	4
0.3622	0.6494	0.7240	0.8003	0.7602	0.8095	5
0.3033	0.6519	0.7096	0.7983	0.7514	0.8111	6
0.2445	0.6550	0.7272	0.7893	0.7570	0.8195	7

Framework versions

• Transformers 4.26.1
• TensorFlow 2.11.0
• Datasets 2.9.0
• Tokenizers 0.13.2