ko_roberta_small_model
This model is a fine-tuned version of hyeonseo/ko_roberta_small_model on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.1864
- Precision: 0.6827
- Recall: 0.7254
- F1: 0.7034
- Accuracy: 0.9404
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: 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: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2341 | 1.0 | 1313 | 0.2069 | 0.6516 | 0.6999 | 0.6749 | 0.9336 |
0.16 | 2.0 | 2626 | 0.1864 | 0.6827 | 0.7254 | 0.7034 | 0.9404 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 5
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.
Dataset used to train Hyeonseo/ko_roberta_small_model
Evaluation results
- Precision on kluevalidation set self-reported0.683
- Recall on kluevalidation set self-reported0.725
- F1 on kluevalidation set self-reported0.703
- Accuracy on kluevalidation set self-reported0.940