Downloads · 30 days
16
22% of all-time downloads
byc3230/koelectra-small-v2-discriminator-finetuned-korspeech-step
koelectra-small-v2-discriminator-finetuned-korspeech-step is a text classification model from byc3230. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
16
22% of all-time downloads
All-time downloads
72
Public
Repo size
1.2 GB
Likes
0
Public
Click a slice to open those files.
.bin55.1 MB · 98%
From the Hugging Face model README
This model is a fine-tuned version of monologg/koelectra-small-v2-discriminator on an unknown 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 | Macro F1 | Accuracy | Weighted f1 | Micro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.0661 | 0.57 | 100 | 0.8942 | 0.6723 | 0.6818 | 0.6723 | 0.6818 | 0.6818 | 0.6818 | 0.6818 | 0.6754 | 0.6818 | 0.6754 |
| 0.872 | 1.13 | 200 | 0.7197 | 0.7352 | 0.7322 | 0.7352 | 0.7322 | 0.7322 | 0.7322 | 0.7322 | 0.7415 | 0.7322 | 0.7415 |
| 0.7092 | 1.7 | 300 | 0.6572 | 0.7518 | 0.7528 | 0.7518 | 0.7528 | 0.7528 | 0.7528 | 0.7528 | 0.7624 | 0.7528 | 0.7624 |
| 0.5971 | 2.27 | 400 | 0.6379 | 0.7635 | 0.7628 | 0.7635 | 0.7628 | 0.7628 | 0.7628 | 0.7628 | 0.7710 | 0.7628 | 0.7710 |
| 0.543 | 2.84 | 500 | 0.6091 | 0.7791 | 0.7770 | 0.7791 | 0.7770 | 0.7770 | 0.7770 | 0.7770 | 0.7836 | 0.7770 | 0.7836 |
| 0.4953 | 3.4 | 600 | 0.6025 | 0.7867 | 0.7876 | 0.7867 | 0.7876 | 0.7876 | 0.7876 | 0.7876 | 0.7877 | 0.7876 | 0.7877 |
| 0.4473 | 3.97 | 700 | 0.6006 | 0.7841 | 0.7827 | 0.7841 | 0.7827 | 0.7827 | 0.7827 | 0.7827 | 0.7901 | 0.7827 | 0.7901 |
| 0.4067 | 4.54 | 800 | 0.5991 | 0.7899 | 0.7891 | 0.7899 | 0.7891 | 0.7891 | 0.7891 | 0.7891 | 0.7919 | 0.7891 | 0.7919 |
| 0.3849 | 5.11 | 900 | 0.6101 | 0.7817 | 0.7812 | 0.7817 | 0.7812 | 0.7812 | 0.7812 | 0.7812 | 0.7843 | 0.7812 | 0.7843 |
| 0.3623 | 5.67 | 1000 | 0.6069 | 0.7923 | 0.7933 | 0.7923 | 0.7933 | 0.7933 | 0.7933 | 0.7933 | 0.7935 | 0.7933 | 0.7935 |