PRE-deberta-v3-large-finetuned-augmentation
This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1785
- F1: 0.7708
- Roc Auc: 0.8731
- Accuracy: 0.7941
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.2094 | 1.0 | 389 | 0.2261 | 0.5045 | 0.7268 | 0.6795 |
| 0.1726 | 2.0 | 778 | 0.1668 | 0.6900 | 0.8176 | 0.7445 |
| 0.1256 | 3.0 | 1167 | 0.1908 | 0.6485 | 0.7896 | 0.7336 |
| 0.1098 | 4.0 | 1556 | 0.1716 | 0.7544 | 0.8494 | 0.7876 |
| 0.0629 | 5.0 | 1945 | 0.1785 | 0.7708 | 0.8731 | 0.7941 |
| 0.0208 | 6.0 | 2334 | 0.2220 | 0.7648 | 0.8618 | 0.7889 |
| 0.02 | 7.0 | 2723 | 0.2273 | 0.7666 | 0.8513 | 0.7941 |
| 0.0121 | 8.0 | 3112 | 0.2406 | 0.7510 | 0.8517 | 0.7934 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0