Downloads · 30 days
4
8% of all-time downloads
multi-qa-mpnet-base-dot-v1-finetuned-squad2-all
haddadalwi/multi-qa-mpnet-base-dot-v1-finetuned-squad2-all
multi-qa-mpnet-base-dot-v1-finetuned-squad2-all is a question answering model from haddadalwi. 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. --
All-time downloads
52
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin436 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- mpnet
- Access
- Public
- Created
- Jun 27, 2023
- Updated
- Jun 27, 2023
- SHA
- 20554d00
Try a prompt
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. -->
multi-qa-mpnet-base-dot-v1-finetuned-squad2-all
This model is a fine-tuned version of sentence-transformers/multi-qa-mpnet-base-dot-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0718
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8521 | 1.0 | 840 | 1.3531 |
| 1.2732 | 2.0 | 1680 | 1.0718 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Task
- Question Answering
- Library
- transformers
- Type
- mpnet
- Created
- Jun 27, 2023
- Updated
- Jun 27, 2023