Hugging Face's logo

tedad09
/
DDTdonut-CTS-577img-5Epochs

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DDTdonut-CTS-577img-5Epochs / README.md
tedad09's picture
tedad09
End of training
0e47653 verified
preview code
|
raw
history blame
1.59 kB
metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: DDTdonut-CTS-577img-5Epochs
    results: []

DDTdonut-CTS-577img-5Epochs

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: 0.0416

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: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.6058 1.0 288 0.2755
0.606 2.0 576 0.1188
0.364 3.0 864 0.0971
0.2438 4.0 1152 0.0955
0.2051 5.0 1440 0.0416

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2