<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
DeBERTa-NepCov19SA
This model is a fine-tuned version of Sakonii/deberta-base-nepali on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5239
- Validation Loss: 0.5506
- Epoch: 5
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0001}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.8850 | 0.6920 | 0 |
| 0.6661 | 0.6118 | 1 |
| 0.6067 | 0.5850 | 2 |
| 0.5703 | 0.5684 | 3 |
| 0.5438 | 0.5560 | 4 |
| 0.5239 | 0.5506 | 5 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
