<!-- 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-finetuned-korquad-finetuned-klue5
This model is a fine-tuned version of monologg/koelectra-base-v3-finetuned-korquad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0979
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: 7
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.8314 | 0.36 | 500 | 1.5168 |
1.5231 | 0.71 | 1000 | 1.4084 |
1.3849 | 1.07 | 1500 | 1.4020 |
1.0592 | 1.42 | 2000 | 1.4384 |
1.0728 | 1.78 | 2500 | 1.3936 |
0.9789 | 2.14 | 3000 | 1.6275 |
0.8857 | 2.49 | 3500 | 1.5426 |
0.8928 | 2.85 | 4000 | 1.5594 |
0.8502 | 3.21 | 4500 | 1.6085 |
0.8375 | 3.56 | 5000 | 1.6470 |
0.8507 | 3.92 | 5500 | 1.7148 |
0.7725 | 4.27 | 6000 | 1.8683 |
0.7574 | 4.63 | 6500 | 1.7876 |
0.8021 | 4.99 | 7000 | 1.8254 |
0.7435 | 5.34 | 7500 | 2.0119 |
0.7409 | 5.7 | 8000 | 2.0003 |
0.7355 | 6.05 | 8500 | 2.0860 |
0.6941 | 6.41 | 9000 | 2.1488 |
0.6914 | 6.77 | 9500 | 2.0979 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1