Downloads · 30 days
7
10% of all-time downloads
mdeberta-threestage-fiqhqa-ML-512
mhdafifan/mdeberta-threestage-fiqhqa-ML-512
mdeberta-threestage-fiqhqa-ML-512 is a question answering model from mhdafifan. 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
73
Public
Parameters
278M
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- May 31, 2026
- Updated
- Jun 2, 2026
- SHA
- e2864182
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. -->
mdeberta-threestage-fiqhqa-ML-512
This model is a fine-tuned version of mhdafifan/mdeberta-squad-qasina-LR-5e-06-BS-16-ML-384 on the FiqhQA dataset. It achieves the following results on the evaluation set:
- Loss: 1.2436
- F1: 52.84
- Exact Match: 26.21
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Exact Match |
|---|---|---|---|---|---|
| 1.1451 | 1.0 | 176 | 1.1765 | 54.56 | 24.27 |
| 0.98 | 2.0 | 352 | 1.1467 | 55.46 | 24.27 |
| 0.8399 | 3.0 | 528 | 1.2394 | 52.51 | 25.24 |
| 0.7676 | 4.0 | 704 | 1.2436 | 52.84 | 26.21 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1
- Task
- Question Answering
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Languages
- id
- Created
- May 31, 2026
- Updated
- Jun 2, 2026