<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
klue-roberta-base-ner
This model is a fine-tuned version of klue/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0291
- Precision: 0.9517
- Recall: 0.9492
- F1: 0.9505
- Accuracy: 0.9951
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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 357 | 0.0533 | 0.7734 | 0.8187 | 0.7954 | 0.9891 |
0.16 | 2.0 | 714 | 0.0389 | 0.9122 | 0.9370 | 0.9244 | 0.9915 |
0.0336 | 3.0 | 1071 | 0.0317 | 0.9330 | 0.9273 | 0.9302 | 0.9930 |
0.0336 | 4.0 | 1428 | 0.0265 | 0.9164 | 0.9405 | 0.9283 | 0.9939 |
0.0165 | 5.0 | 1785 | 0.0286 | 0.9325 | 0.9431 | 0.9377 | 0.9944 |
0.0109 | 6.0 | 2142 | 0.0326 | 0.9458 | 0.9466 | 0.9462 | 0.9947 |
0.0109 | 7.0 | 2499 | 0.0291 | 0.9517 | 0.9492 | 0.9505 | 0.9951 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3