metadata
license: cc-by-4.0
base_model: vesteinn/DanskBERT
tags:
- generated_from_trainer
model-index:
- name: MeMo_BERT-SA_DanskBERT
results: []
MeMo_BERT-SA_DanskBERT
This model is a fine-tuned version of vesteinn/DanskBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1703
- F1-score: 0.7724
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1-score |
|---|---|---|---|---|
| No log | 1.0 | 297 | 0.6759 | 0.7155 |
| 0.6468 | 2.0 | 594 | 1.2492 | 0.6745 |
| 0.6468 | 3.0 | 891 | 1.2268 | 0.7040 |
| 0.3433 | 4.0 | 1188 | 1.2735 | 0.7694 |
| 0.3433 | 5.0 | 1485 | 1.5214 | 0.7112 |
| 0.1732 | 6.0 | 1782 | 1.9239 | 0.7325 |
| 0.0436 | 7.0 | 2079 | 1.7480 | 0.7567 |
| 0.0436 | 8.0 | 2376 | 2.1543 | 0.7439 |
| 0.0191 | 9.0 | 2673 | 2.1873 | 0.7528 |
| 0.0191 | 10.0 | 2970 | 2.1828 | 0.7528 |
| 0.0168 | 11.0 | 3267 | 2.2822 | 0.7482 |
| 0.0117 | 12.0 | 3564 | 2.2565 | 0.7456 |
| 0.0117 | 13.0 | 3861 | 2.1703 | 0.7724 |
| 0.0085 | 14.0 | 4158 | 2.4034 | 0.7404 |
| 0.0085 | 15.0 | 4455 | 2.3810 | 0.7374 |
| 0.0043 | 16.0 | 4752 | 2.2340 | 0.7510 |
| 0.0087 | 17.0 | 5049 | 2.2798 | 0.7712 |
| 0.0087 | 18.0 | 5346 | 2.2541 | 0.7683 |
| 0.0026 | 19.0 | 5643 | 2.3661 | 0.7563 |
| 0.0026 | 20.0 | 5940 | 2.3710 | 0.7563 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2