Downloads · 30 days
6
7% of all-time downloads
mdeberta-squad-id-LR-2e-05-BS-16-ML-384
mhdafifan/mdeberta-squad-id-LR-2e-05-BS-16-ML-384
mdeberta-squad-id-LR-2e-05-BS-16-ML-384 is a question answering model from mhdafifan. Use it when the input is a question plus a passage. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
88
Public
Parameters
278M
1.1 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
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- May 29, 2026
- Updated
- May 29, 2026
- SHA
- e1a0f12a
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-squad-id-LR-2e-05-BS-16-ML-384
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the squad_v2_id dataset. It achieves the following results on the evaluation set:
- Loss: 1.1408
- F1: 72.0042
- Exact Match: 65.6026
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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Exact Match |
|---|---|---|---|---|---|
| 1.1526 | 1.0 | 8486 | 0.9945 | 69.8195 | 63.8508 |
| 0.9584 | 2.0 | 16972 | 0.9459 | 71.5594 | 65.3331 |
| 0.7987 | 3.0 | 25458 | 0.9673 | 72.1666 | 66.0827 |
| 0.6637 | 4.0 | 33944 | 1.0320 | 72.5758 | 66.209 |
| 0.5379 | 5.0 | 42430 | 1.1408 | 72.0042 | 65.6026 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.5.1+cu121
- Datasets 4.4.1
- Tokenizers 0.19.1
- Task
- Question Answering
- Type
- deberta-v2
- License
- mit
- Languages
- id
- Created
- May 29, 2026
- Updated
- May 29, 2026