Hugging Face's logo

squantumengine
/
donut-stnk-v5_4_2-left

Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
donut-stnk-v5_4_2-left / README.md
asrulsibaoel's picture
asrulsibaoel
End of training
b96323a verified
preview code
|
raw history blame contribute delete
No virus
1.64 kB
metadata
license: mit
base_model: naver-clova-ix/donut-base-finetuned-cord-v2
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: donut-stnk-v5_4_2-left
    results: []

donut-stnk-v5_4_2-left

This model is a fine-tuned version of naver-clova-ix/donut-base-finetuned-cord-v2 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1521

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: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5307 1.0 206 0.2188
0.2471 2.0 412 0.1535
0.1678 3.0 618 0.1577
0.1152 4.0 824 0.1521
0.0629 5.0 1030 0.1563

Framework versions

  • Transformers 4.37.2
  • Pytorch 1.13.1+cu117
  • Datasets 2.16.1
  • Tokenizers 0.15.1