metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- recall
- accuracy
model-index:
- name: robbert0410_lrate7.5b32
results: []
robbert0410_lrate7.5b32
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: 0.4559
- Precisions: 0.8283
- Recall: 0.8004
- F-measure: 0.8131
- Accuracy: 0.9159
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: 7.5e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2719 | 1.0 | 118 | 0.4068 | 0.8731 | 0.7017 | 0.7281 | 0.8921 |
| 0.2306 | 2.0 | 236 | 0.3380 | 0.7819 | 0.7690 | 0.7699 | 0.9017 |
| 0.1268 | 3.0 | 354 | 0.3740 | 0.7908 | 0.7845 | 0.7790 | 0.9060 |
| 0.0858 | 4.0 | 472 | 0.3834 | 0.7983 | 0.7651 | 0.7763 | 0.9092 |
| 0.0586 | 5.0 | 590 | 0.4200 | 0.8225 | 0.7933 | 0.8045 | 0.9094 |
| 0.0349 | 6.0 | 708 | 0.4474 | 0.8328 | 0.7926 | 0.8094 | 0.9107 |
| 0.0209 | 7.0 | 826 | 0.4559 | 0.8283 | 0.8004 | 0.8131 | 0.9159 |
| 0.013 | 8.0 | 944 | 0.4614 | 0.8175 | 0.8034 | 0.8097 | 0.9144 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0