<!-- 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-klue-ner
This model is a fine-tuned version of monologg/koelectra-base-v3-discriminator on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.1427
- Precision: 0.7710
- Recall: 0.8124
- F1: 0.7911
- Accuracy: 0.9588
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1647 | 1.0 | 2626 | 0.1678 | 0.7258 | 0.7518 | 0.7386 | 0.9494 |
| 0.111 | 2.0 | 5252 | 0.1447 | 0.7460 | 0.8002 | 0.7721 | 0.9557 |
| 0.0785 | 3.0 | 7878 | 0.1427 | 0.7710 | 0.8124 | 0.7911 | 0.9588 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cpu
- Datasets 2.12.0
- Tokenizers 0.11.0
