metadata
base_model: snunlp/KR-Medium
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_model
results: []
test_model
This model is a fine-tuned version of snunlp/KR-Medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3382
- Accuracy: 0.6372
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0161 | 0.5 | 100 | 0.8929 | 0.6428 |
| 0.8861 | 1.0 | 200 | 0.8755 | 0.6526 |
| 0.6894 | 1.49 | 300 | 0.8906 | 0.6435 |
| 0.6773 | 1.99 | 400 | 0.8928 | 0.6585 |
| 0.4686 | 2.49 | 500 | 1.0231 | 0.6340 |
| 0.4645 | 2.99 | 600 | 1.0166 | 0.6424 |
| 0.295 | 3.48 | 700 | 1.1859 | 0.6351 |
| 0.2764 | 3.98 | 800 | 1.2167 | 0.6368 |
| 0.185 | 4.48 | 900 | 1.3204 | 0.6312 |
| 0.1775 | 4.98 | 1000 | 1.3382 | 0.6372 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.13.3