Hyeonseo's picture
update model card README.md
6ef3544
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ko-clickbait_news_classifier-KcELECTRA-base
    results: []

ko-clickbait_news_classifier-KcELECTRA-base

This model is a fine-tuned version of beomi/KcELECTRA-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9632
  • Accuracy: 0.5687

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 Accuracy
1.0044 1.0 2934 0.9792 0.5264
0.9388 2.0 5868 0.9557 0.5461
0.8859 3.0 8802 0.9333 0.5654
0.8146 4.0 11736 0.9551 0.5636
0.7607 5.0 14670 0.9632 0.5687

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.13.3