simplify readme

Former-commit-id: 0da6ec2d516326fe9c7583ba71cd1778eb838178
2024-04-02 20:07:43 +08:00
parent 117b67ea30
commit b12176d818
24 changed files with 244 additions and 890 deletions
--- a/examples/full_multi_gpu/multi_node.sh
+++ b/examples/full_multi_gpu/multi_node.sh
@@ -33,6 +33,6 @@ python -m torch.distributed.run \
    --num_train_epochs 3.0 \
    --max_samples 3000 \
    --val_size 0.1 \
-    --ddp_timeout 1800000 \
+    --ddp_timeout 180000000 \
    --plot_loss \
    --fp16
--- a/examples/full_multi_gpu/single_node.sh
+++ b/examples/full_multi_gpu/single_node.sh
@@ -27,6 +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 \
+    --ddp_timeout 180000000 \
    --plot_loss \
    --fp16