metadata
library_name: transformers
language:
- ko
license: apache-2.0
base_model: monologg/koelectra-base-v3-discriminator
tags:
- text-classification
- KoELECTRA
- Korean-NLP
- topic-classification
- news-classification
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: ynat_model
results: []
ynat_model
This model is a fine-tuned version of monologg/koelectra-base-v3-discriminator on the klue-ynat dataset. It achieves the following results on the evaluation set:
- Loss: 0.4102
- Accuracy: 0.8601
- Precision: 0.8494
- Recall: 0.8746
- F1-score: 0.8612
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1-score |
|---|---|---|---|---|---|---|---|
| 0.4002 | 1.0 | 714 | 0.4580 | 0.8396 | 0.8205 | 0.8736 | 0.8435 |
| 0.2917 | 2.0 | 1428 | 0.3983 | 0.8585 | 0.8512 | 0.8726 | 0.8606 |
| 0.2227 | 3.0 | 2142 | 0.4102 | 0.8601 | 0.8494 | 0.8746 | 0.8612 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1