invoice_extraction_20240808_base_non_0_retrain

This model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.

Model description

Trained from Donut base model (naver-clova-ix/donut-base) with type 2 invoice data with original Gregorian date instead of ROC date with Chinese characters

Intended uses & limitations

More information needed

Training and evaluation data

Train data: 192 samples of type 2 images with invoice date

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-06
  • 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: 20

Training results

TrainOutput(global_step=2420, training_loss=1.0457300442309418, metrics={'train_runtime': 9844.8278, 'train_samples_per_second': 0.49, 'train_steps_per_second': 0.246, 'total_flos': 6.47612717723136e+18, 'train_loss': 1.0457300442309418, 'epoch': 20.0})

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.15.2
Downloads last month
9
Safetensors
Model size
202M params
Tensor type
I64
·
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for michaeljcliao/invoice_extraction_20240815_base_type_2_retrain

Finetuned
(367)
this model