Team Ai
Modelpublic

Mit1208/layoutlmv3-finetuned-DocLayNet

sourceHugging Facecc-by-nc-sa-4.0updated 3y agoView on Hugging Face
1likes54downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

layoutlmv3-finetuned-DocLayNet

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

  • —Loss: 0.5644
  • —Precision: 0.6179
  • —Recall: 0.7238
  • —F1: 0.6667
  • —Accuracy: 0.8720

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
  • —trainbatchsize: 2
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —training_steps: 1000

Training results

Training LossEpochStepValidation LossPrecisionRecallF1Accuracy
1.33830.582000.83580.30070.43810.35660.7724
0.83081.164000.67350.46340.54290.50.8084
0.5181.746000.57060.53730.68570.60250.8399
0.38562.338000.63030.60320.72380.65800.8648
0.25582.9110000.56440.61790.72380.66670.8720

Framework versions

  • —Transformers 4.27.3
  • —Pytorch 1.13.1+cu116
  • —Datasets 2.10.1
  • —Tokenizers 0.13.2

How to Train & Inference:

Check this out this repo: https://github.com/mit1280/Document-AI