DeBERTa-v3_qa_model
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0962
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2056 | 1.0 | 1000 | 1.0022 |
| 0.7035 | 2.0 | 2000 | 0.9728 |
| 0.4364 | 3.0 | 3000 | 1.0962 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu118
- Datasets 3.4.1
- Tokenizers 0.21.1