| --- |
| library_name: transformers |
| base_model: monologg/koelectra-small-v3-discriminator |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: koelectra |
| 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. --> |
|
|
| # koelectra |
|
|
| This model is a fine-tuned version of [monologg/koelectra-small-v3-discriminator](https://huggingface.co/monologg/koelectra-small-v3-discriminator) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.5056 |
| - Accuracy: 0.7975 |
|
|
| ## 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: 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: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | No log | 1.0 | 100 | 0.6845 | 0.6675 | |
| | No log | 2.0 | 200 | 0.5746 | 0.7575 | |
| | No log | 3.0 | 300 | 0.4979 | 0.7875 | |
| | No log | 4.0 | 400 | 0.4853 | 0.795 | |
| | 0.5347 | 5.0 | 500 | 0.4678 | 0.8 | |
| | 0.5347 | 6.0 | 600 | 0.5199 | 0.7725 | |
| | 0.5347 | 7.0 | 700 | 0.4832 | 0.7975 | |
| | 0.5347 | 8.0 | 800 | 0.5078 | 0.7925 | |
| | 0.5347 | 9.0 | 900 | 0.5008 | 0.795 | |
| | 0.2996 | 10.0 | 1000 | 0.5056 | 0.7975 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.0.0 |
| - Pytorch 2.10.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
| |
