Skip to content

Commit 4d3b805

Browse files
committed
Update blog
1 parent f33a902 commit 4d3b805

1 file changed

Lines changed: 1 addition & 1 deletion

File tree

source/_posts/2025/07/大语言模型训练原理与实践(七):grpo算法.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -229,7 +229,7 @@ def __getitem__(self, idx):
229229

230230
{% endgallery %}
231231

232-
最终,博主将迭代了400个step的模型与未训了的初始模型进行了测试与对比,结果如下:
232+
最终,博主将迭代了400个step的模型与未经过训练的初始模型进行了测试与对比,结果如下:
233233

234234
```raw
235235
Qwen Accuracy: 0.4314 Formatted: 0.6088 GRPO Accuracy: 0.5610 Formatted: 0.9121

0 commit comments

Comments
 (0)