category4 / README.md
kyungmin011029's picture
Upload TFBertForSequenceClassification
711f59f
metadata
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
  - generated_from_keras_callback
model-index:
  - name: category4
    results: []

category4

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

  • Train Loss: 0.2658
  • Train Accuracy: 1.0
  • Validation Loss: 0.3699
  • Validation Accuracy: 0.9485
  • Epoch: 5

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:

  • optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Train Accuracy Validation Loss Validation Accuracy Epoch
3.5847 0.1529 3.1016 0.3402 0
2.5797 0.5701 2.1027 0.7216 1
1.5816 0.8793 1.1963 0.9175 2
0.8647 0.9690 0.7416 0.9381 3
0.4668 0.9954 0.5027 0.9485 4
0.2658 1.0 0.3699 0.9485 5

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.12.0
  • Tokenizers 0.13.3