metadata
library_name: transformers
base_model: monologg/koelectra-small-finetuned-sentiment
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: koelectra_emotion_v4
results: []
koelectra_emotion_v4
This model is a fine-tuned version of monologg/koelectra-small-finetuned-sentiment on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3443
- Accuracy: 0.5678
- F1: 0.5658
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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.8003 | 1.0 | 598 | 1.5736 | 0.4017 | 0.3661 |
| 1.4448 | 2.0 | 1196 | 1.3784 | 0.4973 | 0.4848 |
| 1.2459 | 3.0 | 1794 | 1.2953 | 0.5323 | 0.5219 |
| 1.1153 | 4.0 | 2392 | 1.2637 | 0.5536 | 0.5506 |
| 1.0145 | 5.0 | 2990 | 1.2860 | 0.5585 | 0.5543 |
| 0.9391 | 6.0 | 3588 | 1.2813 | 0.5650 | 0.5642 |
| 0.8732 | 7.0 | 4186 | 1.3113 | 0.5662 | 0.5644 |
| 0.8311 | 8.0 | 4784 | 1.3305 | 0.5681 | 0.5676 |
| 0.807 | 9.0 | 5382 | 1.3444 | 0.5679 | 0.5659 |
| 0.7933 | 10.0 | 5980 | 1.3443 | 0.5678 | 0.5658 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0