metadata
library_name: transformers
license: cc-by-4.0
base_model: NbAiLab/nb-bert-base
tags:
- generated_from_trainer
model-index:
- name: nbbert_ED1
results: []
nbbert_ED1
This model is a fine-tuned version of NbAiLab/nb-bert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4723
- F1-score: 0.8930
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 | 69 | 0.3745 | 0.8771 |
| No log | 2.0 | 138 | 0.4001 | 0.8605 |
| No log | 3.0 | 207 | 0.4723 | 0.8930 |
| No log | 4.0 | 276 | 0.6866 | 0.8442 |
| No log | 5.0 | 345 | 0.6563 | 0.8597 |
| No log | 6.0 | 414 | 0.9802 | 0.8328 |
| No log | 7.0 | 483 | 0.6917 | 0.8688 |
| 0.2309 | 8.0 | 552 | 0.6327 | 0.8759 |
| 0.2309 | 9.0 | 621 | 0.6371 | 0.8759 |
| 0.2309 | 10.0 | 690 | 0.6340 | 0.8765 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1