README.md

---
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: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

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

This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/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