metadata
library_name: transformers
language:
- ko
license: mit
base_model: beomi/KcELECTRA-base-v2022
tags:
- absa
- sentiment-analysis
- aspect-based-sentiment-analysis
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: kcELECTRA-absa
results: []
kcELECTRA-absa
This model is a fine-tuned version of beomi/KcELECTRA-base-v2022 on the AI Hub Kor ABSA Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.5211
- Accuracy: 0.8060
- F1: 0.6220
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: 3e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5858 | 1.0 | 772 | 0.6595 | 0.7101 | 0.4422 |
| 0.426 | 2.0 | 1544 | 0.4981 | 0.7973 | 0.6054 |
| 0.3829 | 3.0 | 2316 | 0.5211 | 0.8060 | 0.6220 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1