Downloads · 30 days
29
4% of all-time downloads
kobert-finetuned-klue-v2
Seongmi/kobert-finetuned-klue-v2
kobert-finetuned-klue-v2 is a question answering model from Seongmi. 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
711
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin366 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Oct 6, 2022
- Updated
- Oct 6, 2022
- SHA
- 9eda1db0
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. -->
kobert-finetuned-klue-v2
This model is a fine-tuned version of monologg/kobert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.3234
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.5898 | 1.08 | 500 | 5.2618 |
| 5.217 | 2.16 | 1000 | 5.1505 |
| 5.1044 | 3.24 | 1500 | 5.0895 |
| 5.0048 | 4.32 | 2000 | 5.0649 |
| 4.8292 | 5.4 | 2500 | 4.9589 |
| 4.5451 | 6.48 | 3000 | 4.8549 |
| 4.2284 | 7.56 | 3500 | 4.8801 |
| 3.9195 | 8.64 | 4000 | 4.8797 |
| 3.6506 | 9.72 | 4500 | 4.8009 |
| 3.4175 | 10.8 | 5000 | 4.8996 |
| 3.1964 | 11.88 | 5500 | 4.9734 |
| 3.0401 | 12.96 | 6000 | 4.9378 |
| 2.8965 | 14.04 | 6500 | 5.3631 |
| 2.7672 | 15.12 | 7000 | 5.3234 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- Created
- Oct 6, 2022
- Updated
- Oct 6, 2022