Team Ai
Modelpublic

shubh1608/donut_pdf_ocr

sourceHugging Faceupdated 3y agoView on Hugging Face
5likes34downloads
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. -->

donutpdfocr

This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0443

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: 2e-05
  • —trainbatchsize: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.08291.0470.1157
0.01842.0940.1660
0.05333.01410.0765
0.07654.01880.0530
0.1015.02350.0481
0.09366.02820.0494
0.10327.03290.0524
0.00338.03760.0460
0.01859.04230.0440
0.004410.04700.0443

Framework versions

  • —Transformers 4.28.1
  • —Pytorch 2.0.0+cu118
  • —Datasets 2.11.0
  • —Tokenizers 0.13.3