metadata
license: cc-by-4.0
base_model: vesteinn/DanskBERT
tags:
- generated_from_trainer
model-index:
- name: danskbert_1_ND
results: []
danskbert_1_ND
This model is a fine-tuned version of vesteinn/DanskBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3183
- F1-score: 0.8920
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1-score |
|---|---|---|---|---|
| No log | 1.0 | 223 | 0.3557 | 0.8496 |
| No log | 2.0 | 446 | 0.3183 | 0.8920 |
| 0.3559 | 3.0 | 669 | 0.4009 | 0.8864 |
| 0.3559 | 4.0 | 892 | 0.4993 | 0.8772 |
| 0.2054 | 5.0 | 1115 | 0.6132 | 0.8694 |
| 0.2054 | 6.0 | 1338 | 0.6709 | 0.8573 |
| 0.1135 | 7.0 | 1561 | 0.7118 | 0.8681 |
| 0.1135 | 8.0 | 1784 | 0.6778 | 0.8684 |
| 0.0501 | 9.0 | 2007 | 0.8188 | 0.8713 |
| 0.0501 | 10.0 | 2230 | 0.8687 | 0.8637 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1