layoutlm-funsd

This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the funsd dataset. It achieves the following results on the evaluation set:

• Loss: 1.5315
• Answer: {'precision': 0.03470437017994859, 'recall': 0.03337453646477132, 'f1': 0.03402646502835539, 'number': 809}
• Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
• Question: {'precision': 0.3425827107790822, 'recall': 0.30140845070422534, 'f1': 0.32067932067932065, 'number': 1065}
• Overall Precision: 0.2029
• Overall Recall: 0.1746
• Overall F1: 0.1877
• Overall Accuracy: 0.3869

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:

• learning_rate: 3e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Answer	Header	Question	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
1.7866	1.0	10	1.6364	{'precision': 0.014164305949008499, 'recall': 0.012360939431396786, 'f1': 0.0132013201320132, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.20684931506849316, 'recall': 0.14178403755868543, 'f1': 0.16824512534818942, 'number': 1065}	0.1121	0.0808	0.0939	0.3375
1.5665	2.0	20	1.5315	{'precision': 0.03470437017994859, 'recall': 0.03337453646477132, 'f1': 0.03402646502835539, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.3425827107790822, 'recall': 0.30140845070422534, 'f1': 0.32067932067932065, 'number': 1065}	0.2029	0.1746	0.1877	0.3869

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3