metadata
license: agpl-3.0
base_model: vesteinn/ScandiBERT
tags:
- generated_from_trainer
model-index:
- name: MeMo_BERT-SA_ScandiBERT
results: []
MeMo_BERT-SA_ScandiBERT
This model is a fine-tuned version of vesteinn/ScandiBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2243
- F1-score: 0.7419
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 | 0.9412 | 0.6171 |
| 0.9566 | 2.0 | 594 | 0.8714 | 0.6663 |
| 0.9566 | 3.0 | 891 | 0.8782 | 0.6326 |
| 0.7393 | 4.0 | 1188 | 1.0449 | 0.7003 |
| 0.7393 | 5.0 | 1485 | 0.9099 | 0.7046 |
| 0.5862 | 6.0 | 1782 | 0.8663 | 0.7145 |
| 0.4349 | 7.0 | 2079 | 1.3081 | 0.6875 |
| 0.4349 | 8.0 | 2376 | 1.3457 | 0.7119 |
| 0.3452 | 9.0 | 2673 | 1.2243 | 0.7419 |
| 0.3452 | 10.0 | 2970 | 1.3430 | 0.7227 |
| 0.2313 | 11.0 | 3267 | 1.5762 | 0.7273 |
| 0.1486 | 12.0 | 3564 | 1.5626 | 0.7295 |
| 0.1486 | 13.0 | 3861 | 1.8689 | 0.7113 |
| 0.0888 | 14.0 | 4158 | 1.9944 | 0.7161 |
| 0.0888 | 15.0 | 4455 | 1.9063 | 0.7115 |
| 0.0647 | 16.0 | 4752 | 2.0000 | 0.7283 |
| 0.0288 | 17.0 | 5049 | 2.0464 | 0.7278 |
| 0.0288 | 18.0 | 5346 | 2.0158 | 0.7319 |
| 0.0334 | 19.0 | 5643 | 2.0396 | 0.7324 |
| 0.0334 | 20.0 | 5940 | 2.0772 | 0.7245 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2