Downloads · 30 days
4
1% of all-time downloads
fewshot-qa-003-20230614-001
intanm/fewshot-qa-003-20230614-001
fewshot-qa-003-20230614-001 is a question answering model from intanm. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
328
Public
Repo size
6.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Jun 14, 2023
- Updated
- Jun 14, 2023
- SHA
- 74933bcb
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. -->
fewshot-qa-003-20230614-001
This model is a fine-tuned version of timpal0l/mdeberta-v3-base-squad2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.7024
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 208 | 2.2878 |
| No log | 2.0 | 416 | 2.2958 |
| 2.2174 | 3.0 | 624 | 2.4204 |
| 2.2174 | 4.0 | 832 | 2.6886 |
| 1.1542 | 5.0 | 1040 | 3.0044 |
| 1.1542 | 6.0 | 1248 | 3.2229 |
| 1.1542 | 7.0 | 1456 | 3.4833 |
| 0.6136 | 8.0 | 1664 | 3.5356 |
| 0.6136 | 9.0 | 1872 | 3.6634 |
| 0.3843 | 10.0 | 2080 | 3.7024 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Question Answering
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Jun 14, 2023
- Updated
- Jun 14, 2023