metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: SloBertAA_Top20_WithoutOOC_082023
results: []
SloBertAA_Top20_WithoutOOC_082023
This model is a fine-tuned version of EMBEDDIA/sloberta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8485
- Accuracy: 0.8909
- F1: 0.8908
- Precision: 0.8914
- Recall: 0.8909
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: 2e-05
- train_batch_size: 12
- eval_batch_size: 12
- 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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5035 | 1.0 | 22717 | 0.4645 | 0.8498 | 0.8495 | 0.8603 | 0.8498 |
| 0.3863 | 2.0 | 45434 | 0.4249 | 0.8679 | 0.8680 | 0.8703 | 0.8679 |
| 0.3005 | 3.0 | 68151 | 0.4785 | 0.8695 | 0.8700 | 0.8743 | 0.8695 |
| 0.2094 | 4.0 | 90868 | 0.5345 | 0.8771 | 0.8769 | 0.8801 | 0.8771 |
| 0.1878 | 5.0 | 113585 | 0.6158 | 0.8793 | 0.8792 | 0.8817 | 0.8793 |
| 0.1256 | 6.0 | 136302 | 0.6737 | 0.8847 | 0.8847 | 0.8860 | 0.8847 |
| 0.0999 | 7.0 | 159019 | 0.7364 | 0.8855 | 0.8857 | 0.8870 | 0.8855 |
| 0.0633 | 8.0 | 181736 | 0.8041 | 0.8863 | 0.8862 | 0.8874 | 0.8863 |
| 0.0338 | 9.0 | 204453 | 0.8479 | 0.8877 | 0.8877 | 0.8891 | 0.8877 |
| 0.0178 | 10.0 | 227170 | 0.8485 | 0.8909 | 0.8908 | 0.8914 | 0.8909 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.8.0
- Datasets 2.10.1
- Tokenizers 0.13.2