koelectra-base-v3-discriminator-finetuned-ner

JoonJoon/koelectra-base-v3-discriminator-finetuned-ner

koelectra-base-v3-discriminator-finetuned-ner is a token classification model from JoonJoon. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

849

Public

Repo size

1.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin449 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: electra
Access: Public
Created: Jul 15, 2022
Updated: Jul 15, 2022
SHA: 29e2af05

Try a prompt

Datasets

klue

Model card

From the Hugging Face model README

koelectra-base-v3-discriminator-finetuned-ner

This model is a fine-tuned version of monologg/koelectra-base-v3-discriminator on the klue dataset. It achieves the following results on the evaluation set:

Loss: 0.1957
Precision: 0.6665
Recall: 0.7350
F1: 0.6991
Accuracy: 0.9396

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: 48
eval_batch_size: 48
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	438	0.2588	0.5701	0.6655	0.6141	0.9212
0.4333	2.0	876	0.2060	0.6671	0.7134	0.6895	0.9373
0.1944	3.0	1314	0.1957	0.6665	0.7350	0.6991	0.9396

Framework versions

Transformers 4.11.3
Pytorch 1.12.0+cu102
Datasets 1.14.0
Tokenizers 0.10.3

Task: Token Classification
Library: transformers
Type: electra
License: apache-2.0
Created: Jul 15, 2022
Updated: Jul 15, 2022