Hugging Face's logo

tedad09
/
donut-3epochs-Data2

Image-Text-to-Text
Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
donut-3epochs-Data2 / README.md
tedad09's picture
tedad09
Donut-Epochs3-Data2
d2d1185 verified
preview code
|
raw
history blame contribute delete
1.48 kB
metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: donut-3epochs-Data2
    results: []

donut-3epochs-Data2

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: 0.9544

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: 1
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.9082 1.0 400 1.2407
1.2139 2.0 800 1.0075
0.9291 3.0 1200 0.9544

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2