metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: korean_disease_ner
results: []
korean_disease_ner
This model is a fine-tuned version of klue/bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0422
- Precision: 0.9558
- Recall: 0.9581
- F1: 0.9569
- Accuracy: 0.9897
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0445 | 1.0 | 3025 | 0.0378 | 0.9408 | 0.9585 | 0.9496 | 0.9875 |
0.0253 | 2.0 | 6050 | 0.0351 | 0.9510 | 0.9564 | 0.9537 | 0.9890 |
0.0175 | 3.0 | 9075 | 0.0338 | 0.9546 | 0.9571 | 0.9558 | 0.9895 |
0.0123 | 4.0 | 12100 | 0.0372 | 0.9510 | 0.9640 | 0.9575 | 0.9896 |
0.0091 | 5.0 | 15125 | 0.0422 | 0.9558 | 0.9581 | 0.9569 | 0.9897 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2