vishnu027's picture
End of training
c660cf1
metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: donut_marriage_RT_001
    results: []

donut_marriage_RT_001

This model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3953

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
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.0315 1.0 163 0.9688
0.5694 2.0 326 0.5084
0.5065 3.0 489 0.4196
0.1008 4.0 652 0.3998
0.1531 5.0 815 0.3687
0.1606 6.0 978 0.3642
0.1383 7.0 1141 0.3745
0.0956 8.0 1304 0.3856
0.0331 9.0 1467 0.3850
0.0032 10.0 1630 0.3920
0.0164 11.0 1793 0.3953

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0