kogpt2-base-v2-finetuned-klue-ner
This model is a fine-tuned version of skt/kogpt2-base-v2 on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5377
- F1: 0.4294
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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
0.6149 | 1.0 | 876 | 0.5522 | 0.1925 |
0.4204 | 2.0 | 1752 | 0.5182 | 0.2602 |
0.3368 | 3.0 | 2628 | 0.4434 | 0.3151 |
0.2808 | 4.0 | 3504 | 0.4554 | 0.3265 |
0.2422 | 5.0 | 4380 | 0.4239 | 0.3567 |
0.208 | 6.0 | 5256 | 0.4563 | 0.3930 |
0.1792 | 7.0 | 6132 | 0.4853 | 0.3849 |
0.1564 | 8.0 | 7008 | 0.4942 | 0.3964 |
0.1322 | 9.0 | 7884 | 0.5034 | 0.4216 |
0.1136 | 10.0 | 8760 | 0.5377 | 0.4294 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.