Hugging Face's logo

dunlp
/
GWW

Fill-Mask
Transformers
PyTorch
TensorBoard
bert
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
1
GWW / README.md
dunlp's picture
dunlp
Update README.md
37b2823
preview code
|
raw history blame contribute delete
No virus
1.48 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: GWW
    results: []

GWW

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

  • Loss: 2.7097

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: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
3.7179 1.0 78 3.1185
3.1134 2.0 156 2.8528
2.9327 3.0 234 2.7249
2.8377 4.0 312 2.7255
2.7888 5.0 390 2.6737

Framework versions

  • Transformers 4.19.4
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1