add torchrun train script

2025-05-19 11:52:16 +08:00
parent be180dfb6a
commit 010580981e
1 changed files with 3 additions and 0 deletions
@@ -0,0 +1,3 @@
+python3 -m torch.distributed.launch --nproc_per_node=4 --master_port=12345 src_pretrain/pretrain_transformers.py
+# torchrun --nproc_per_node=4 src_pretrain/pretrain_transformers.py
+# CUDA_VISIBLE_DEVICES=1,2,3 torchrun --nproc_per_node=3 src_pretrain/pretrain_transformers.py