Hugging Face's logo

squantumengine
/
donut-stnk-v5_2-left

Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
donut-stnk-v5_2-left / README.md
asrulsibaoel's picture
asrulsibaoel
End of training
b276b3f verified
preview code
|
raw history blame contribute delete
No virus
1.55 kB
metadata
base_model: squantumengine/donut-stnk-v3_5_left
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: donut-stnk-v5_2-left
    results: []

donut-stnk-v5_2-left

This model is a fine-tuned version of squantumengine/donut-stnk-v3_5_left on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1520

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
0.1579 1.0 134 0.1520
0.1036 2.0 268 0.1597
0.0451 3.0 402 0.1700
0.0489 4.0 536 0.1753

Framework versions

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