<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
koelectra-base-v3-discriminator-finetuned-klue-v4
This model is a fine-tuned version of monologg/koelectra-base-v3-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6219
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.4979 | 0.33 | 500 | 4.0470 |
| 3.2001 | 0.65 | 1000 | 2.3172 |
| 2.215 | 0.98 | 1500 | 1.9043 |
| 1.7849 | 1.31 | 2000 | 1.7181 |
| 1.6156 | 1.63 | 2500 | 1.5955 |
| 1.5295 | 1.96 | 3000 | 1.5071 |
| 1.2147 | 2.29 | 3500 | 1.5872 |
| 1.1727 | 2.61 | 4000 | 1.5104 |
| 1.1467 | 2.94 | 4500 | 1.6059 |
| 0.9972 | 3.27 | 5000 | 1.6523 |
| 0.9791 | 3.59 | 5500 | 1.6219 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.12.1
