Downloads · 30 days
17
30% of all-time downloads
klue-mrc_koelectra_qa_model
ScatterRaven/klue-mrc_koelectra_qa_model
klue-mrc_koelectra_qa_model is a question answering model from ScatterRaven. 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
56
Public
Parameters
13.7M
54.8 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors54.8 MB · 98%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- electra
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- a446acff
Try a prompt
Base models
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. -->
klue-mrc_koelectra_qa_model
This model is a fine-tuned version of monologg/koelectra-small-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.4108
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 150 | 5.1590 |
| No log | 2.0 | 300 | 4.6278 |
| No log | 3.0 | 450 | 4.4715 |
| 4.9398 | 4.0 | 600 | 4.4186 |
| 4.9398 | 5.0 | 750 | 4.4108 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4
- Task
- Question Answering
- Library
- transformers
- Type
- electra
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025