metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner-ko
results: []
bert-finetuned-ner-ko
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: 0.0083
- Precision: 0.9859
- Recall: 0.9913
- F1: 0.9886
- Accuracy: 0.9980
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 |
|---|---|---|---|---|---|---|---|
| 0.0649 | 1.0 | 1250 | 0.0295 | 0.9468 | 0.9679 | 0.9572 | 0.9919 |
| 0.0275 | 2.0 | 2500 | 0.0132 | 0.9777 | 0.9870 | 0.9823 | 0.9966 |
| 0.0141 | 3.0 | 3750 | 0.0083 | 0.9859 | 0.9913 | 0.9886 | 0.9980 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.13.2