Downloads · 30 days
20
26% of all-time downloads
2tina/kobert-lm-finetuned-klue-v2
kobert-lm-finetuned-klue-v2 is a question answering model from 2tina. 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. --
Downloads · 30 days
20
26% of all-time downloads
All-time downloads
78
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.bin366 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of monologg/kobert-lm on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.7641 | 0.52 | 500 | 5.6079 |
| 5.5176 | 1.04 | 1000 | 5.4635 |
| 5.4401 | 1.57 | 1500 | 5.3370 |
| 5.2919 | 2.09 | 2000 | 5.2396 |
| 5.1756 | 2.61 | 2500 | 5.2675 |
| 5.0793 | 3.13 | 3000 | 5.1546 |
| 4.8933 | 3.66 | 3500 | 5.0728 |
| 4.7273 | 4.18 | 4000 | 5.0165 |
| 4.5473 | 4.7 | 4500 | 4.9679 |