Edit model card

bert-base-cased-Korean-sentiment

This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2338
  • Accuracy: 0.9234
  • F1: 0.9238

Model description

This is a fine-tuned model for a sentiment analysis for the Korean language based on customer reviews in the Korean language

Intended uses & limitations

from transformers import pipeline

sentiment_model = pipeline(model="WhitePeak/bert-base-cased-Korean-sentiment")
sentiment_mode("매우 좋아")

Result:

LABEL_0: negative
LABEL_1: positive

Training and evaluation data

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: 2

Training results

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
2,501
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for WhitePeak/bert-base-cased-Korean-sentiment

Finetuned
(511)
this model