vitus9988's picture
Update README.md
403d2dc verified
|
raw
history blame
1.99 kB
metadata
base_model: klue/roberta-base
tags:
  - generated_from_trainer
widget:
  - text: >-
      저는 김철수입니다. 집은 서울특별시 강남대로이고 전화번호는 010-1234-5678, 주민등록번호는
      123456-1234567입니다.메일주소는 hugging@face.com입니다. 저는 10월 25일에 출국할 예정입니다.
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: klue-roberta-base-ner-identified
    results: []
language:
  - ko

klue-roberta-base-ner-identified

This model is a fine-tuned version of klue/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0167
  • Precision: 0.9865
  • Recall: 0.9938
  • F1: 0.9901
  • Accuracy: 0.9982

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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • 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
No log 1.0 61 0.0293 0.9462 0.9802 0.9629 0.9954
No log 2.0 122 0.0194 0.9901 0.9913 0.9907 0.9976
No log 3.0 183 0.0167 0.9865 0.9938 0.9901 0.9982

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1