Skip to content

fix finetune RMSE and memory issue#2860

Merged
wanghan-iapcm merged 3 commits intodeepmodeling:develfrom
njzjz:fix-finetune-memory
Sep 25, 2023
Merged

fix finetune RMSE and memory issue#2860
wanghan-iapcm merged 3 commits intodeepmodeling:develfrom
njzjz:fix-finetune-memory

Conversation

@njzjz
Copy link
Member

@njzjz njzjz commented Sep 24, 2023

Fix #2472. The previous implementation tried to allocate a (N, N) array and the RMSE result was actually MAE instead.

Fix deepmodeling#2472. The previous implementation tried to allocate a (N, N) array and the RMSE result was actually MAE instead.

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
@njzjz njzjz linked an issue Sep 24, 2023 that may be closed by this pull request
@njzjz njzjz changed the title fix fintune RMSE and memory issue fix finetune RMSE and memory issue Sep 24, 2023
njzjz added a commit to dptech-corp/deepmd-pytorch that referenced this pull request Sep 24, 2023
The previous RMSE result was actually MAE instead.

See also deepmodeling/deepmd-kit#2860.
@codecov
Copy link

codecov bot commented Sep 24, 2023

Codecov Report

Patch coverage: 100.00% and no project coverage change.

Comparison is base (c2c6476) 75.38% compared to head (3ca5714) 75.38%.
Report is 3 commits behind head on devel.

Additional details and impacted files
@@           Coverage Diff           @@
##            devel    #2860   +/-   ##
=======================================
  Coverage   75.38%   75.38%           
=======================================
  Files         242      242           
  Lines       24424    24424           
  Branches     1580     1580           
=======================================
  Hits        18411    18411           
  Misses       5082     5082           
  Partials      931      931           
Files Changed Coverage Δ
deepmd/fit/ener.py 90.13% <100.00%> (ø)

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

Co-authored-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Han Wang <92130845+wanghan-iapcm@users.noreply.github.com>
@wanghan-iapcm wanghan-iapcm enabled auto-merge (squash) September 25, 2023 06:04
njzjz added a commit to dptech-corp/deepmd-pytorch that referenced this pull request Sep 25, 2023
@wanghan-iapcm wanghan-iapcm merged commit 67f30e0 into deepmodeling:devel Sep 25, 2023
iProzd pushed a commit to dptech-corp/deepmd-pytorch that referenced this pull request Oct 13, 2023
* fix finetune RMSE result

The previous RMSE result was actually MAE instead.

See also deepmodeling/deepmd-kit#2860.

* apply changes in deepmodeling/deepmd-kit#2860
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] finetune OOM and killed

2 participants