Support TP-compatible Torch AMP and Update trainer API (#27)

* Add gradient accumulation, fix lr scheduler

* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)

* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes

* fixed trainer

* Revert "fixed trainer"

This reverts commit 2e0b0b7699.

* improved consistency between trainer, engine and schedule (#23)

Co-authored-by: 1SAA <c2h214748@gmail.com>

Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
This commit is contained in:
Frank Lee
2021-11-18 19:45:06 +08:00
committed by GitHub
parent 2b05de4c64
commit 3defa32aee
80 changed files with 2194 additions and 1584 deletions

View File

@@ -1,5 +1,5 @@
from .cosine import CosineAnnealingLR, CosineAnnealingWarmupLR, FlatAnnealingLR, FlatAnnealingWarmupLR
from .linear import LinearWarmupLR, LinearWarmupDecay
from .linear import LinearWarmupLR
from .multistep import MultiStepLR, MultiStepWarmupLR
from .onecycle import OneCycleLR
from .poly import PolynomialLR, PolynomialWarmupLR