LayoutLM-v3 model fine-tuned on invoice dataset

This model is a fine-tuned version of microsoft/layoutlmv3-base on the Rhenus dataset.

We use Microsoft’s LayoutLMv3 trained on Eurocorporation Dataset to predict the labels. To use it, simply upload an image. Results will show up in a few seconds.

It achieves the following results on the evaluation set:

• Loss: 0.0012
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Accuracy: 1.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

All the training codes are available from the below GitHub link.

The model can be evaluated at the HuggingFace Spaces link:

https://huggingface.co/DataIntelligenceTeam/Rhenus

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 5
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Framework versions

• Transformers 4.20.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1