metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: robbertfinetuned2209
results: []
robbertfinetuned2209
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: 0.3479
- Precision: 0.7445
- Recall: 0.7657
- F1: 0.7550
- Accuracy: 0.9055
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 236 | 0.3944 | 0.6565 | 0.6282 | 0.6420 | 0.8781 |
| No log | 2.0 | 472 | 0.3546 | 0.6938 | 0.7354 | 0.7140 | 0.8901 |
| 0.479 | 3.0 | 708 | 0.3479 | 0.7445 | 0.7657 | 0.7550 | 0.9055 |
| 0.479 | 4.0 | 944 | 0.3944 | 0.7523 | 0.7733 | 0.7626 | 0.9049 |
| 0.1591 | 5.0 | 1180 | 0.4177 | 0.7812 | 0.7657 | 0.7734 | 0.9082 |
| 0.1591 | 6.0 | 1416 | 0.4467 | 0.7817 | 0.7931 | 0.7874 | 0.9121 |
| 0.0594 | 7.0 | 1652 | 0.4706 | 0.7985 | 0.7873 | 0.7928 | 0.9125 |
| 0.0594 | 8.0 | 1888 | 0.4751 | 0.7860 | 0.7960 | 0.7910 | 0.9140 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3