Add Contrastive Learning #10097
Open
Add Contrastive Learning #10097
+1,126
−6
Conversation
This file contains 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! |
ZHUI
reviewed
Mar 12, 2025
| @@ -0,0 +1,238 @@ | |||
| from paddlenlp.transformers import AutoModel, AutoConfig | |||
| import paddle | ||
| import numpy as np | ||
|
|
||
| class Embedding_Evaluation: |
| neg_passage_path = './toy_data/toy_dev_neg.json' | ||
| eval = Embedding_Evaluation(model_path, tokenizer_path, query_pos_passage_path, neg_passage_path) | ||
| print(eval.evaluate()) | ||
| ``` |
There was a problem hiding this comment.
这个可以评估 mteb 的话，可以加一段如何评估的。加一个得分
|
|
||
| ## 2.训练 | ||
| Embedding Model训练代码位置详见： | ||
| - [run_embedding.py](../../../../llm/../PaddleNLP_zhangjie/llm/run_embedding.py) |
|
|
||
| ### 1.1 Query清洗 | ||
| Embedding Model进行对比学习时，数据质量尤为重要。通过多卡推理与faiss库，快速高效地对数据中的query进行清洗，能够有效去除低质量数据，避免出现过多的相似query，对模型训练造成干扰，影响训练效果。 | ||
|
|
| ``` | ||
|
|
||
| ### 1.2 负样本挖掘 | ||
| 高质量的负样本数据，能够提高对比学习的效率，加快模型的收敛速度。通过多卡推理与faiss库，可以快速高效地挖掘数据中的负样本。 |
Codecov ReportAll modified and coverable lines are covered by tests ✅
❌ Your project check has failed because the head coverage (49.99%) is below the target coverage (58.00%). You can increase the head coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## develop #10097 +/- ##
===========================================
- Coverage 52.11% 49.99% -2.12%
===========================================
Files 730 757 +27
Lines 116557 122442 +5885
===========================================
+ Hits 60744 61219 +475
- Misses 55813 61223 +5410 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
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
New features
PR changes
Others
Description
1.增加对比学习相关目录与介绍；
2.增加Embedding Model训练时需要应用的数据处理和评估脚本：
3.适配多卡推理和faiss库，有效提高运行速度