metadata
base_model: GroNLP/bert-base-dutch-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: model_compleet_wie_mask_red2
results: []
model_compleet_wie_mask_red2
This model is a fine-tuned version of GroNLP/bert-base-dutch-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4347
- Accuracy: 0.8547
- F1: 0.8134
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.661 | 0.77 | 50 | 0.6058 | 0.7006 | 0.6308 |
| 0.4353 | 1.54 | 100 | 0.3687 | 0.8401 | 0.7955 |
| 0.2514 | 2.31 | 150 | 0.4347 | 0.8547 | 0.8134 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Tokenizers 0.15.2