layoutlmv3-finetuned-funsd
This model is a fine-tuned version of microsoft/layoutlmv3-base on the pierreguillou/DocLayNet-large using bounding boxes and categories for lines (not for for paragraphs). It achieves the following results on the evaluation set:
- Loss: 0.33888205885887146,
- Precision: 0.8478835766832817,
- Recall: 0.8934488524091807,
- F1: 0.8700700634847538,
- Accuracy: 0.9574140990541197
The script for training can be found here: https://github.com/huggingface/transformers/tree/main/examples/research_projects/layoutlmv3
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- training_steps: 100000
Framework versions
- Transformers 4.33.3
- Pytorch 1.11.0+cu115
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 69
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Kwan0/layoutlmv3-base-finetune-DocLayNet-100k
Base model
microsoft/layoutlmv3-base
Finetuned
this model
Dataset used to train Kwan0/layoutlmv3-base-finetune-DocLayNet-100k
Evaluation results
- Precision on pierreguillou/DocLayNet-largeself-reported0.847
- Recall on pierreguillou/DocLayNet-largeself-reported0.893
- F1 on pierreguillou/DocLayNet-largeself-reported0.870
- Accuracy on pierreguillou/DocLayNet-largeself-reported0.957