koelectra-sts-v0.5

Ketzu/koelectra-sts-v0.5

koelectra-sts-v0.5 is a text classification model from Ketzu. 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

3% of all-time downloads

All-time downloads

576

Public

Repo size

1.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin452 MB · 100%

At a glance

Task: Text Classification
Library: transformers
Model type: electra
Access: Public
Created: Mar 19, 2022
Updated: Mar 19, 2022
SHA: e85f9d26

Try a prompt

Model card

From the Hugging Face model README

koelectra-sts-v0.5

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0213
Pearson: 0.9958
Spearmanr: 0.8703

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr
0.058	1.0	6250	0.0428	0.9915	0.8702
0.0433	2.0	12500	0.0448	0.9911	0.8685
0.0362	3.0	18750	0.0261	0.9950	0.8705
0.0107	4.0	25000	0.0234	0.9953	0.8702
0.0075	5.0	31250	0.0213	0.9958	0.8703

Framework versions

Transformers 4.10.0
Pytorch 1.10.1+cu113
Datasets 1.17.0
Tokenizers 0.10.3

Task: Text Classification
Library: transformers
Type: electra
Created: Mar 19, 2022
Updated: Mar 19, 2022