<!-- 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-small-v3-discriminator-finetuned
This model is a fine-tuned version of monologg/koelectra-small-v3-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4324
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.4466 | 1.0 | 702 | 3.0850 |
| 3.1639 | 2.0 | 1404 | 2.5210 |
| 2.3734 | 3.0 | 2106 | 2.1738 |
| 2.0019 | 4.0 | 2808 | 1.7048 |
| 1.5426 | 5.0 | 3510 | 1.5741 |
| 1.4233 | 6.0 | 4212 | 1.5246 |
| 1.3254 | 7.0 | 4914 | 1.4860 |
| 1.2166 | 8.0 | 5616 | 1.4525 |
| 1.1515 | 9.0 | 6318 | 1.4354 |
| 1.0863 | 10.0 | 7020 | 1.4480 |
| 1.0471 | 11.0 | 7722 | 1.4549 |
| 0.9938 | 12.0 | 8424 | 1.4586 |
| 0.9645 | 13.0 | 9126 | 1.4276 |
| 0.957 | 14.0 | 9828 | 1.4289 |
| 0.9322 | 15.0 | 10530 | 1.4324 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1
