bertje-dutch-cola / README.md
bylin's picture
Update README.md
93477c6 verified
metadata
language:
  - nl
tags:
  - generated_from_trainer
base_model: GroNLP/bert-base-dutch-cased
datasets:
  - GroNLP/dutch-cola
metrics:
  - accuracy
widget:
  - text: Jan wandelt zijn schoenen.
  - text: Oud genoeg voor de disco is Marie nog niet.
model-index:
  - name: bertje-dutch-cola
    results: []

bertje-dutch-cola

This model is a fine-tuned version of GroNLP/bert-base-dutch-cased on Dutch CoLA. It achieves the following results on the evaluation set:

  • Loss: 0.7208
  • Accuracy: 0.7792

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5395 1.0 622 0.6046 0.7346
0.3626 2.0 1244 0.5864 0.7808
0.261 3.0 1866 0.7208 0.7792

Framework versions

  • Transformers 4.39.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.15.2