목표에서, 입력값은 트랜스포머 층들을 통과하며 모든 토큰에 대한 확률 분포 형태의 최종 출
력을 생성합니다. 훈련 과정에서는 이 출력 분포와 정답을 비교해 손실을 계산합니다. 정답 분
포는 정답 토큰에는
1
을, 나머지 모든 토큰에는
0
을 할당합니다.
출력과 정답 사이의 차이를 수치화하는 다양한 방법이 있습니다. 그중 가장 널리 사용하는 방
법은 교차 엔트로피
cross
-
entropy
로, 다음 공식으로 계산됩니다.
교차 엔트로피 = -∑(정답 확률)×
log
(출력 확률)
예를 들어 다음 문장을 생각해 봅시다.
‘
His
pizza
tasted
______’
정답 토큰이 ‘
good
’이고, 모델의 출력 확률 분포가 (
terrible
:
0
.
65
,
bad
:
0
.
12
,
good
:
0
.
11
,
...)이라고 가정해 봅시다.
교차 엔트로피는 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.