Downloads · 30 days
11
3% of all-time downloads
nb-bert-base-qa-norquad
eanderson/nb-bert-base-qa-norquad
nb-bert-base-qa-norquad is a question answering model from eanderson. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as cc-by-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
344
Public
Repo size
10.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin709 MB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- cc-by-4.0
- Model type
- bert
- Access
- Public
- Created
- Jan 24, 2024
- Updated
- Jan 25, 2024
- SHA
- b144cd26
Base models
Datasets
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. -->
nb-bert-base-qa-norquad
This model is a fine-tuned version of NbAiLab/nb-bert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9546
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
model : eanderson/nb-bert-base-qa-norquad language : norwegian
dataset: eanderson/NorQuAD["text"] dataset_size: 472
exact_match : 59.110169491525426, f1 : 71.37800143052715
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5595 | 1.0 | 3808 | 1.6062 |
| 0.9856 | 2.0 | 7616 | 1.7905 |
| 0.4723 | 3.0 | 11424 | 1.9546 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- License
- cc-by-4.0
- Languages
- no
- Created
- Jan 24, 2024
- Updated
- Jan 25, 2024