Downloads · 30 days
11
3% of all-time downloads
IceBERT-finetuned-NQiIv.1.1
gudjonk93/IceBERT-finetuned-NQiIv.1.1
IceBERT-finetuned-NQiIv.1.1 is a question answering model from gudjonk93. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as agpl-3.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
327
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin495 MB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- agpl-3.0
- Model type
- roberta
- Access
- Public
- Created
- Jan 28, 2023
- Updated
- Jan 28, 2023
- SHA
- b2b6820e
Try a prompt
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. -->
IceBERT-finetuned-squad
This model is a fine-tuned version of mideind/IceBERT on the icelandic-qa-n_qi_i dataset. It achieves the following results on the evaluation set:
- Loss: 1.5873
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 293 | 1.7911 |
| 2.0115 | 2.0 | 586 | 1.5817 |
| 2.0115 | 3.0 | 879 | 1.5305 |
| 1.0251 | 4.0 | 1172 | 1.5244 |
| 1.0251 | 5.0 | 1465 | 1.5873 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Question Answering
- Library
- transformers
- Type
- roberta
- License
- agpl-3.0
- Created
- Jan 28, 2023
- Updated
- Jan 28, 2023