Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

【Hackathon 5th No.64】PaddleNLP套件模型接入动转静训练功能 -part #7576

Merged
merged 4 commits into from
Dec 18, 2023

Conversation

MayYouBeProsperous
Copy link
Contributor

@MayYouBeProsperous MayYouBeProsperous commented Dec 4, 2023

PR types

Others

PR changes

Others

Description

模型动转静支持情况

依赖 paddle 版本:develop

模型名称 SOT模式 AST模式 测试结果
electra #7575
ernie-1.0 #7640 (comment)
ernie-3.0 #7640 (comment)
ernie-doc #7652
ernie-gen #7656
ernie-health #7640 (comment)
ernie-layout #7640 (comment)
ernie-m #7640 (comment)
ernie-tiny #7640 (comment)
uie #7640 (comment)
gpt #7640 (comment)
gpt-3 #7640 (comment)
glm #7640 (comment)
chatglm #7640 (comment)
ernie-3.5-se 显存不足 显存不足 #7640 (comment)
llama #7640 (comment)
opt #7640 (comment)
qwen #7640 (comment)

相关 PR:

Copy link

paddle-bot bot commented Dec 4, 2023

Thanks for your contribution!

Copy link

codecov bot commented Dec 4, 2023

Codecov Report

Attention: 152 lines in your changes are missing coverage. Please review.

Comparison is base (10ff94a) 58.23% compared to head (4a27ea5) 57.58%.
Report is 84 commits behind head on develop.

Files Patch % Lines
paddlenlp/trainer/training_args.py 4.54% 84 Missing ⚠️
paddlenlp/transformers/llama/modeling_auto.py 14.28% 66 Missing ⚠️
paddlenlp/trainer/trainer.py 33.33% 2 Missing ⚠️
Additional details and impacted files
@@             Coverage Diff             @@
##           develop    #7576      +/-   ##
===========================================
- Coverage    58.23%   57.58%   -0.65%     
===========================================
  Files          579      582       +3     
  Lines        85819    86933    +1114     
===========================================
+ Hits         49973    50064      +91     
- Misses       35846    36869    +1023     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@MayYouBeProsperous MayYouBeProsperous changed the title [WIP]【Hackathon 5th No.64】PaddleNLP套件模型接入动转静训练功能 【Hackathon 5th No.64】PaddleNLP套件模型接入动转静训练功能 Dec 18, 2023
@@ -65,7 +65,6 @@ python -m paddle.distributed.launch --gpus "0" run_pretrain.py \
--weight_decay 1e-2 \
--adam_epsilon 1e-6 \
--warmup_steps 10000 \
--num_train_epochs 3 \
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

num_train_epochs 参数脚本中未用到,设了会报错,所以删了

Copy link
Contributor

@2742195759 2742195759 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Contributor

@w5688414 w5688414 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@w5688414 w5688414 merged commit dba73aa into PaddlePaddle:develop Dec 18, 2023
9 checks passed
@Ligoml Ligoml changed the title 【Hackathon 5th No.64】PaddleNLP套件模型接入动转静训练功能 【Hackathon 5th No.64】PaddleNLP套件模型接入动转静训练功能 -part Dec 20, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants