<!-- 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. -->
kobert-finetuned-klue-v2
This model is a fine-tuned version of monologg/kobert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.2678
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 |
|---|---|---|---|
| 5.6289 | 0.54 | 500 | 5.3024 |
| 5.3083 | 1.08 | 1000 | 5.3707 |
| 5.3518 | 1.62 | 1500 | 5.3039 |
| 5.2912 | 2.16 | 2000 | 5.2800 |
| 5.2282 | 2.7 | 2500 | 5.2301 |
| 5.1498 | 3.24 | 3000 | 5.2435 |
| 5.079 | 3.78 | 3500 | 5.1997 |
| 4.8886 | 4.32 | 4000 | 5.1350 |
| 4.8166 | 4.86 | 4500 | 5.1441 |
| 4.5615 | 5.4 | 5000 | 5.1485 |
| 4.4183 | 5.94 | 5500 | 5.0775 |
| 4.1282 | 6.48 | 6000 | 5.0402 |
| 4.1214 | 7.02 | 6500 | 5.1331 |
| 3.7792 | 7.56 | 7000 | 5.1314 |
| 3.7455 | 8.1 | 7500 | 5.1936 |
| 3.5369 | 8.64 | 8000 | 5.1931 |
| 3.4832 | 9.18 | 8500 | 5.2678 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
