Downloads · 30 days
91
63% of all-time downloads
mhdafifan/xlm-roberta-threestage-fiqhqa-ML-512
xlm-roberta-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. --
Downloads · 30 days
91
63% of all-time downloads
All-time downloads
145
Public
Parameters
277M
2.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 98%
From the Hugging Face model README
This model is a fine-tuned version of mhdafifan/xlm-roberta-squad-qasina-LR-1e-05-BS-16-ML-384 on the FiqhQA dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | F1 | Exact Match |
|---|---|---|---|---|---|
| 1.7672 | 1.0 | 141 | 1.3776 | 52.1 | 27.18 |
| 1.2653 | 2.0 | 282 | 1.3651 | 53.04 | 27.18 |
| 1.1314 | 3.0 | 423 | 1.2873 | 55.41 | 32.04 |
| 0.9895 | 4.0 | 564 | 1.2921 | 53.7 | 27.18 |
| 0.8869 | 5.0 | 705 | 1.3189 | 52.59 | 27.18 |