kogpt2-base-v2-8-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: 0.5168
- F1: 0.5292
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.6242 | 1.0 | 876 | 0.5671 | 0.3289 |
| 0.4158 | 2.0 | 1752 | 0.5766 | 0.3565 |
| 0.3305 | 3.0 | 2628 | 0.4438 | 0.4400 |
| 0.266 | 4.0 | 3504 | 0.4983 | 0.4341 |
| 0.2231 | 5.0 | 4380 | 0.4501 | 0.4778 |
| 0.1845 | 6.0 | 5256 | 0.4614 | 0.5056 |
| 0.151 | 7.0 | 6132 | 0.4946 | 0.5263 |
| 0.1247 | 8.0 | 7008 | 0.5168 | 0.5292 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 10
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.