Hugging Face's logo

tedad09
/
donut-5epochs-Data3

Transformers
Safetensors
vision-encoder-decoder
generated_from_trainer
Inference Endpoints
Model card Files Community
donut-5epochs-Data3 / README.md
tedad09's picture
tedad09
Donut-Epochs5-Data3
f70f38c verified
preview code
|
raw history blame contribute delete
No virus
1.58 kB
metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: donut-5epochs-Data3
    results: []

donut-5epochs-Data3

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: 0.2999

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
1.2709 1.0 291 0.4459
0.4925 2.0 582 0.3522
0.3777 3.0 873 0.3139
0.3121 4.0 1164 0.3049
0.276 5.0 1455 0.2999

Framework versions

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