Hyeonseo's picture
update model card README.md
ef4954e
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ko-clickbait_news_classifier-KcELECTRA
    results: []

ko-clickbait_news_classifier-KcELECTRA

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: 1.3208
  • Accuracy: 0.6730

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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.8481 1.0 8801 0.8283 0.6204
0.7795 2.0 17602 0.8188 0.6412
0.6952 3.0 26403 0.7544 0.6736
0.6298 4.0 35204 0.7742 0.6732
0.551 5.0 44005 0.8243 0.6821
0.4795 6.0 52806 0.8783 0.6760
0.3991 7.0 61607 0.9993 0.6761
0.3368 8.0 70408 1.0973 0.6713
0.3043 9.0 79209 1.2049 0.6747
0.2488 10.0 88010 1.3208 0.6730

Framework versions

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