klue_ynat_roberta_base_model
This model is a fine-tuned version of klue/roberta-base on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3747
- F1: 0.8720
Model description
Pretrained RoBERTa Model on Korean Language. See Github and Paper for more details.
Intended uses & limitations
Pretrained RoBERTa Model on Korean Language. See Github and Paper for more details.
Training and evaluation data
How to use
NOTE: Use BertTokenizer
instead of RobertaTokenizer. (AutoTokenizer
will load BertTokenizer
)
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("klue/roberta-base")
tokenizer = AutoTokenizer.from_pretrained("klue/roberta-base")
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
No log | 1.0 | 179 | 0.4838 | 0.8444 |
No log | 2.0 | 358 | 0.3848 | 0.8659 |
0.4203 | 3.0 | 537 | 0.3778 | 0.8690 |
0.4203 | 4.0 | 716 | 0.3762 | 0.8702 |
0.4203 | 5.0 | 895 | 0.3747 | 0.8720 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 21
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.