Model Performance Metrics

Training Parameters

{'max_length': '40', 'num_epochs': '3', 'image_size': '[1344, 896]', 'learning_rate': '1e-05', 'model_name': 'naver-clova-ix/donut-base'}

Training Results

  • Final Training Loss: 0.2364
  • Average Loss per Epoch: [0.27357653977342267, 0.27357653977342267, 0.27357653977342267]

Evaluation Results

  • Mean Accuracy: 0.8381
  • Number of evaluated samples: 105.0

MLflow Experiment Details

  • Run ID: 426def82555940048815e1682ceda8d8
  • Experiment Name: 0

Last Updated

2025-01-10 23:08:29

Learning Curves

You can find detailed learning curves and metrics in MLflow UI by running:

mlflow ui
Downloads last month
12
Safetensors
Model size
202M params
Tensor type
I64
·
F32
·
Inference API
Unable to determine this model's library. Check the docs .