metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- recall
- accuracy
model-index:
- name: robbert0410_lrate5b16
results: []
robbert0410_lrate5b16
This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4327
- Precisions: 0.8044
- Recall: 0.7739
- F-measure: 0.7866
- Accuracy: 0.9059
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.6621 | 1.0 | 236 | 0.3874 | 0.8592 | 0.6840 | 0.6964 | 0.8788 |
| 0.3365 | 2.0 | 472 | 0.3512 | 0.8078 | 0.7402 | 0.7478 | 0.8916 |
| 0.2033 | 3.0 | 708 | 0.3476 | 0.8061 | 0.7621 | 0.7617 | 0.9055 |
| 0.132 | 4.0 | 944 | 0.3896 | 0.8035 | 0.7465 | 0.7632 | 0.9042 |
| 0.0793 | 5.0 | 1180 | 0.4327 | 0.8044 | 0.7739 | 0.7866 | 0.9059 |
| 0.0554 | 6.0 | 1416 | 0.4909 | 0.8386 | 0.7609 | 0.7774 | 0.9072 |
| 0.0378 | 7.0 | 1652 | 0.4867 | 0.7892 | 0.7651 | 0.7743 | 0.9070 |
| 0.0244 | 8.0 | 1888 | 0.5016 | 0.8046 | 0.7651 | 0.7756 | 0.9090 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0