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
commit 9b70bd6ab2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions

View File

@ -328,7 +328,7 @@ neg_avg_log_probas = avg_log_probas * -1
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。