Commit 8d0da202 authored by Jared Casper's avatar Jared Casper
Browse files

Merge branch 'patch-1' of https://github.com/nakosung/Megatron-LM into community-fixes

parents 5e934043 f63a8a12
...@@ -224,7 +224,7 @@ def model_parallel_cuda_manual_seed(seed): ...@@ -224,7 +224,7 @@ def model_parallel_cuda_manual_seed(seed):
# 2718 is just for fun and any POSITIVE value will work. # 2718 is just for fun and any POSITIVE value will work.
offset = seed + 2718 offset = seed + 2718
model_parallel_seed = offset + get_model_parallel_rank() model_parallel_seed = offset + get_model_parallel_rank()
# Data parallel gets the original sedd. # Data parallel gets the original seed.
data_parallel_seed = seed data_parallel_seed = seed
if torch.distributed.get_rank() == 0: if torch.distributed.get_rank() == 0:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment