muhammadravi251001's picture
update model card README.md
0754ca8
metadata
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: fine-tuned-KoreanIndoNLI-KorNLI-with-bert-base
    results: []

fine-tuned-KoreanIndoNLI-KorNLI-with-bert-base

This model is a fine-tuned version of klue/bert-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4897
  • Accuracy: 0.8032
  • F1: 0.8034

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: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 128
  • 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 F1
0.5126 0.5 3654 0.5759 0.7522 0.7552
0.4707 1.0 7308 0.5278 0.7828 0.7845
0.4301 1.5 10962 0.4908 0.8006 0.8010
0.4223 2.0 14616 0.4839 0.8051 0.8059
0.3922 2.5 18270 0.4916 0.8038 0.8051
0.3923 3.0 21924 0.4832 0.8051 0.8052
0.339 3.5 25578 0.4897 0.8032 0.8034

Framework versions

  • Transformers 4.31.0
  • Pytorch 1.13.1
  • Datasets 2.14.4
  • Tokenizers 0.13.3