grow_classification_kcbert2
This model is a fine-tuned version of beomi/kcbert-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4690
- Accuracy: 0.9188
- F1: 0.9176
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.291 | 1.0 | 407 | 0.4767 | 0.8945 | 0.8914 |
| 0.0441 | 2.0 | 814 | 0.4839 | 0.9077 | 0.9058 |
| 0.016 | 3.0 | 1221 | 0.4690 | 0.9188 | 0.9176 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3