Downloads · 30 days
3
5% of all-time downloads
leonardoschluter/bert-base-uncased-finetuned-nq-finetuned-squad
bert-base-uncased-finetuned-nq-finetuned-squad is a question answering model from leonardoschluter. Use it when the input is a question plus a passage. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
3
5% of all-time downloads
All-time downloads
56
Public
Repo size
22.7 GB
Likes
0
Public
Click a slice to open those files.
.bin436 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of eibakke/bert-finetuned-on-nq-short on the squad 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 |
|---|---|---|---|
| 1.0087 | 1.0 | 5533 | 0.9909 |
| 0.7635 | 2.0 | 11066 | 1.0440 |
| 0.529 | 3.0 | 16599 | 1.2022 |