klue-roberta-large-klue-ner
This model is a fine-tuned version of klue/roberta-large on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.1279
- Precision: 0.8292
- Recall: 0.8439
- F1: 0.8365
- Accuracy: 0.9664
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1246 | 1.0 | 2626 | 0.1629 | 0.7891 | 0.7725 | 0.7807 | 0.9539 |
| 0.0744 | 2.0 | 5252 | 0.1194 | 0.8124 | 0.8345 | 0.8233 | 0.9642 |
| 0.0401 | 3.0 | 7878 | 0.1279 | 0.8292 | 0.8439 | 0.8365 | 0.9664 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.2