File tree Expand file tree Collapse file tree 1 file changed +1
-1
lines changed Expand file tree Collapse file tree 1 file changed +1
-1
lines changed Original file line number Diff line number Diff line change @@ -464,7 +464,7 @@ def fused_gelu(x):
464
464
# perform the required gradient all-reduce.
465
465
466
466
###############################################################################
467
- # Match the order of layers in constructors and during the execution if using ``DistributedDataParallel`` (find_unused_parameters=True)
467
+ # Match the order of layers in constructors and during the execution if using ``DistributedDataParallel(find_unused_parameters=True)``
468
468
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
469
469
# `torch.nn.parallel.DistributedDataParallel <https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html#torch.nn.parallel.DistributedDataParallel>`_
470
470
# with ``find_unused_parameters=True`` uses the order of layers and parameters
You can’t perform that action at this time.
0 commit comments