klue-mrc_koelectra_qa_model
This model is a fine-tuned version of monologg/koelectra-small-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5647
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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.8469 | 1.0 | 50 | 5.7571 |
| 5.612 | 2.0 | 100 | 5.4824 |
| 5.3119 | 3.0 | 150 | 5.1945 |
| 5.0362 | 4.0 | 200 | 4.9599 |
| 4.7995 | 5.0 | 250 | 4.7934 |
| 4.6322 | 6.0 | 300 | 4.6802 |
| 4.5037 | 7.0 | 350 | 4.6203 |
| 4.4093 | 8.0 | 400 | 4.5894 |
| 4.357 | 9.0 | 450 | 4.5701 |
| 4.3299 | 10.0 | 500 | 4.5647 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4
- Downloads last month
- 1
Model tree for dbwlsgh000/klue-mrc_koelectra_qa_model
Base model
monologg/koelectra-small-discriminator