layoutlm-funsd

This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.7407
• Education: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5}
• Email: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}
• Github: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}
• Location: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
• Name: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}
• Name : {'precision': 0.2, 'recall': 0.5, 'f1': 0.28571428571428575, 'number': 2}
• Phone Number: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}
• Soft Skills: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}
• Technical Skills: {'precision': 0.2, 'recall': 0.35714285714285715, 'f1': 0.25641025641025644, 'number': 14}
• Overall Precision: 0.1176
• Overall Recall: 0.2
• Overall F1: 0.1481
• Overall Accuracy: 0.1475

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

Training results

Training Loss	Epoch	Step	Validation Loss	Education	Email	Github	Linkedin	Location	Name	Name	Phone Number	Soft Skills	Technical Skills	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
2.9387	1.0	2	2.8701	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.14285714285714285, 'recall': 0.5, 'f1': 0.22222222222222224, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 14}	0.0185	0.0333	0.0238	0.0328
2.6716	2.0	4	2.7798	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.2, 'recall': 0.5, 'f1': 0.28571428571428575, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}	{'precision': 0.10526315789473684, 'recall': 0.14285714285714285, 'f1': 0.12121212121212122, 'number': 14}	0.0612	0.1	0.0759	0.1311
2.5524	3.0	6	2.7407	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.2, 'recall': 0.5, 'f1': 0.28571428571428575, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 0}	{'precision': 0.2, 'recall': 0.35714285714285715, 'f1': 0.25641025641025644, 'number': 14}	0.1176	0.2	0.1481	0.1475

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1