layoutlmv3-finetuned-invoice

This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0018
  • 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

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
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 2000

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 2.0 100 0.0967 0.958 0.9716 0.9648 0.9956
No log 4.0 200 0.0222 0.972 0.9858 0.9789 0.9971
No log 6.0 300 0.0171 0.972 0.9858 0.9789 0.9971
No log 8.0 400 0.0136 0.972 0.9858 0.9789 0.9971
0.1307 10.0 500 0.0117 0.964 0.9777 0.9708 0.9962
0.1307 12.0 600 0.0099 0.972 0.9858 0.9789 0.9971
0.1307 14.0 700 0.0094 0.972 0.9858 0.9789 0.9971
0.1307 16.0 800 0.0071 0.9918 0.9838 0.9878 0.9983
0.1307 18.0 900 0.0026 0.9980 0.9980 0.9980 0.9998
0.0089 20.0 1000 0.0018 1.0 1.0 1.0 1.0
0.0089 22.0 1100 0.0016 1.0 1.0 1.0 1.0
0.0089 24.0 1200 0.0015 1.0 0.9980 0.9990 0.9998
0.0089 26.0 1300 0.0015 0.9980 0.9980 0.9980 0.9998
0.0089 28.0 1400 0.0014 0.9980 0.9980 0.9980 0.9998
0.0025 30.0 1500 0.0011 1.0 1.0 1.0 1.0
0.0025 32.0 1600 0.0012 1.0 1.0 1.0 1.0
0.0025 34.0 1700 0.0011 1.0 1.0 1.0 1.0
0.0025 36.0 1800 0.0010 1.0 1.0 1.0 1.0
0.0025 38.0 1900 0.0010 1.0 1.0 1.0 1.0
0.0019 40.0 2000 0.0011 1.0 1.0 1.0 1.0

Framework versions

  • Transformers 4.21.0.dev0
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1
Downloads last month
73
Safetensors
Model size
126M params
Tensor type
I64
ยท
F32
ยท
Inference Examples
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.

Space using oussama/layoutlmv3-finetuned-invoice 1

Evaluation results