bongsoo / klue-sbert-v1

klue-sbert-v1

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

klue/bert-base 모델을 sentencebert로 파인튜닝한 모델

Evaluation Results

• 성능 측정을 위한 말뭉치는, 아래 한국어 (kor), 영어(en) 평가 말뭉치를 이용함
  한국어 : korsts(1,379쌍문장) 와 klue-sts(519쌍문장)
  영어 : stsb_multi_mt (1,376쌍문장) 와 glue:stsb (1,500쌍문장)
• 성능 지표는 cosin.spearman
• 평가 측정 코드는 여기 참조

• 모델	korsts	klue-sts	glue(stsb)	stsb_multi_mt(en)
  distiluse-base-multilingual-cased-v2	0.7475	0.7855	0.8193	0.8075
  paraphrase-multilingual-mpnet-base-v2	0.8201	0.7993	0.8907	0.8682
  bongsoo/albert-small-kor-sbert-v1	0.8305	0.8588	0.8419	0.7965
  bongsoo/kpf-sbert-v1.0	0.8590	0.8924	0.8840	0.8531
  bongsoo/klue-sbert-v1.0	0.8529	0.8952	0.8813	0.8469

For an automated evaluation of this model, see the Sentence Embeddings Benchmark : https://seb.sbert.net

Training

• klue/bert-base 모델을 sts(10)-distil(10)-nli(3)-sts(10) 훈련 시킴

The model was trained with the parameters:

공통

• do_lower_case=1, correct_bios=0, polling_mode=mean

1.STS

• 말뭉치 : korsts(5,749) + kluestsV1.1(11,668) + stsb_multi_mt(5,749) + mteb/sickr-sts(9,927) + glue stsb(5,749) (총:38,842)
• Param : lr: 1e-4, eps: 1e-6, warm_step=10%, epochs: 10, train_batch: 128, eval_batch: 64, max_token_len: 72
• 훈련코드 여기 참조

2.distilation

• 교사 모델 : paraphrase-multilingual-mpnet-base-v2(max_token_len:128)
• 말뭉치 : news_talk_en_ko_train.tsv (영어-한국어 대화-뉴스 병렬 말뭉치 : 1.38M)
• Param : lr: 5e-5, eps: 1e-8, epochs: 10, train_batch: 128, eval/test_batch: 64, max_token_len: 128(교사모델이 128이므로 맟춰줌)
• 훈련코드 여기 참조

3.NLI - 말뭉치 : 훈련(967,852) : kornli(550,152), kluenli(24,998), glue-mnli(392,702) / 평가(3,519) : korsts(1,500), kluests(519), gluests(1,500) () - HyperParameter : lr: 3e-5, eps: 1e-8, warm_step=10%, epochs: 3, train/eval_batch: 64, max_token_len: 128 - 훈련코드 여기 참조

Citing & Authors

bongsoo