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: 1.7205
• Answer: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}
• Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
• Question: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}
• Overall Precision: 0.0
• Overall Recall: 0.0
• Overall F1: 0.0
• Overall Accuracy: 0.2854

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: 8
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Answer	Header	Question	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
1.8104	1.0	19	1.7227	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7658	2.0	38	1.7254	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7511	3.0	57	1.7137	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7532	4.0	76	1.7184	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7589	5.0	95	1.7141	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.748	6.0	114	1.7016	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7487	7.0	133	1.7239	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7483	8.0	152	1.7207	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7465	9.0	171	1.7119	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7458	10.0	190	1.7169	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7419	11.0	209	1.7125	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7425	12.0	228	1.7218	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7424	13.0	247	1.7250	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7412	14.0	266	1.7232	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854
1.7389	15.0	285	1.7205	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1070}	0.0	0.0	0.0	0.2854

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3