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: 0.5125
- F1: 0.4083
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: 8
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
0.6197 | 1.0 | 1313 | 0.5497 | 0.2008 |
0.4235 | 2.0 | 2626 | 0.5097 | 0.2676 |
0.3374 | 3.0 | 3939 | 0.4515 | 0.3353 |
0.2796 | 4.0 | 5252 | 0.4399 | 0.3547 |
0.2337 | 5.0 | 6565 | 0.4481 | 0.3540 |
0.1967 | 6.0 | 7878 | 0.4657 | 0.3781 |
0.1635 | 7.0 | 9191 | 0.4846 | 0.3942 |
0.1356 | 8.0 | 10504 | 0.5125 | 0.4083 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 3
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.