Downloads · 30 days
4
11% of all-time downloads
DeBERTa-V3_SQuAD
RyyDer/DeBERTa-V3_SQuAD
DeBERTa-V3_SQuAD is a question answering model from RyyDer. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
36
Public
Parameters
184M
4.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors735 MB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Mar 23, 2025
- Updated
- Mar 23, 2025
- SHA
- 781070aa
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
DeBERTa-V3_SQuAD
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: 0.9575
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 |
|---|---|---|---|
| 1.0735 | 1.0 | 1000 | 0.7966 |
| 0.6548 | 2.0 | 2000 | 0.8066 |
| 0.4139 | 3.0 | 3000 | 0.9575 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu118
- Datasets 3.4.1
- Tokenizers 0.21.1
- Task
- Question Answering
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Mar 23, 2025
- Updated
- Mar 23, 2025