Downloads · 30 days
11
6% of all-time downloads
Z-Jafari/bert-fa-base-uncased-finetuned-PersianQuAD-finetuned-pquad-3epochs
bert-fa-base-uncased-finetuned-PersianQuAD-finetuned-pquad-3epochs is a question answering model from Z-Jafari. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
11
6% of all-time downloads
All-time downloads
192
Public
Parameters
162M
15.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors649 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of Z-Jafari/bert-fa-base-uncased-finetuned-PersianQuAD-3epochs on an unknown dataset. It achieves the following results on the evaluation set:
{'exact': 75.21869532616846, 'f1': 87.71708896094634, 'total': 8002, 'HasAns_exact': 69.92444152431011, 'HasAns_f1': 86.35219215924648, 'HasAns_total': 6088, 'NoAns_exact': 92.05851619644723, 'NoAns_f1': 92.05851619644723, 'NoAns_total': 1914, 'best_exact': 75.21869532616846, 'best_exact_thresh': 0.0, 'best_f1': 87.71708896094681, 'best_f1_thresh': 0.0}
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7179 | 1.0 | 4000 | 0.7750 |
| 0.458 | 2.0 | 8000 | 0.7864 |
| 0.2851 | 3.0 | 12000 | 0.9244 |