metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- recall
- accuracy
model-index:
- name: robbert0210_lrate5b4
results: []
robbert0210_lrate5b4
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: 0.3947
- Precisions: 0.7931
- Recall: 0.7419
- F-measure: 0.7620
- Accuracy: 0.8995
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|
| 0.71 | 1.0 | 942 | 0.4675 | 0.8146 | 0.6895 | 0.6795 | 0.8713 |
| 0.3587 | 2.0 | 1884 | 0.3947 | 0.7931 | 0.7419 | 0.7620 | 0.8995 |
| 0.2221 | 3.0 | 2826 | 0.5259 | 0.7885 | 0.7682 | 0.7650 | 0.9021 |
| 0.1455 | 4.0 | 3768 | 0.5330 | 0.8071 | 0.7500 | 0.7698 | 0.9051 |
| 0.0775 | 5.0 | 4710 | 0.5904 | 0.7773 | 0.7806 | 0.7768 | 0.9035 |
| 0.0465 | 6.0 | 5652 | 0.6671 | 0.8375 | 0.7689 | 0.7890 | 0.9038 |
| 0.0329 | 7.0 | 6594 | 0.6634 | 0.8002 | 0.7764 | 0.7864 | 0.9073 |
| 0.0245 | 8.0 | 7536 | 0.6707 | 0.8325 | 0.7928 | 0.8087 | 0.9118 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3