update examples

Former-commit-id: 38592faa258f7331afb95bc5db4b9bf37f08105d
2024-03-09 02:30:37 +08:00
parent 43b2ede0f8
commit 8ed1463236
6 changed files with 5 additions and 2 deletions
--- a/examples/full_multi_gpu/multi_node.sh
+++ b/examples/full_multi_gpu/multi_node.sh
@@ -33,5 +33,6 @@ python -m torch.distributed.run \
    --num_train_epochs 3.0 \
    --max_samples 3000 \
    --val_size 0.1 \
+    --ddp_timeout 1800000 \
    --plot_loss \
    --fp16
--- a/examples/full_multi_gpu/single_node.sh
+++ b/examples/full_multi_gpu/single_node.sh
@@ -27,5 +27,6 @@ deepspeed --num_gpus 4 ../../src/train_bash.py \
    --num_train_epochs 3.0 \
    --max_samples 3000 \
    --val_size 0.1 \
+    --ddp_timeout 1800000 \
    --plot_loss \
    --fp16