[RL] Refoctor code and add comments #10565
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
greycooker
reviewed
May 7, 2025
paddlenlp/rl/utils/reshard_utils.py
Outdated
| @@ -140,6 +191,24 @@ def mp_reshard( | |||
|
|
|||
|
|
|||
| def init_reshard_mappings(model, training_args, pp_rank, pp_group): | |||
| """ | |||
| 初始化重新分片映射，并返回全局的元数据字典。如果模型是在多个水平并行度下训练，则会设置管道名称映射。 | |||
Codecov ReportAttention: Patch coverage is
❌ Your patch check has failed because the patch coverage (0.00%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## develop #10565 +/- ##
===========================================
- Coverage 46.98% 46.97% -0.02%
===========================================
Files 799 799
Lines 132246 132282 +36
===========================================
- Hits 62135 62133 -2
- Misses 70111 70149 +38 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
DrownFish19
commented
May 12, 2025
Comment on lines
+95
to
+113
| if not isinstance(arg_name_values, list) and not isinstance(args, list): | ||
| arg_name_values = [arg_name_values] | ||
| args = [args] | ||
| elif isinstance(arg_name_values, list) and isinstance(args, list): | ||
| pass | ||
| else: | ||
| raise ValueError("args and arg_name_values should be both list or both not list") | ||
|
|
||
| for i in range(len(args)): | ||
| for k, v in arg_name_values[i].items(): | ||
| old_value = getattr(args[i], k, None) | ||
| setattr(args[i], k, v) | ||
| arg_name_values[i][k] = old_value | ||
| yield | ||
| for k, v in arg_name_values.items(): | ||
| old_value = getattr(args, k) | ||
| setattr(args, k, v) | ||
| arg_name_values[k] = old_value | ||
| for i in range(len(args)): | ||
| for k, v in arg_name_values[i].items(): | ||
| old_value = getattr(args[i], k) | ||
| setattr(args[i], k, v) | ||
| arg_name_values[i][k] = old_value |
…nFish19/PaddleNLP into dev_20250506_add_comment_rl
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Before submitting
testsfolder. If there are codecov issues, please add tests cases first.PR types
Others
PR changes
Docs
Description
Refoctor code (with minimal changes) and add comments.