charieswei
/
Build-A-Large-Language-Model-CN
mirror of https://github.com/skindhu/Build-A-Large-Language-Model-CN.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #9 from dblate/patch-8 

Update 5.在无标记数据集上进行预训练.md
This commit is contained in:
long_long_ago 2025-04-17 09:42:30 +08:00 committed by GitHub
parent c2d2eb24ea 1ba8e31763
commit 9b70bd6ab2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cn-Book/5.在无标记数据集上进行预训练.md
View File

@ -328,7 +328,7 @@ neg_avg_log_probas = avg_log_probas * -1
print(neg_avg_log_probas) print(neg_avg_log_probas)
``` ```
结算的结果为：`tensor(-10.7940)`。 结算的结果为：`tensor(10.7940)`。
这种将负值 -10.7940 转化为正值 10.7940 的操作在深度学习中称为交叉熵损失。 这种将负值 -10.7940 转化为正值 10.7940 的操作在深度学习中称为交叉熵损失。