From 942022c309d8c303165fc0db162022d21d4dbeab Mon Sep 17 00:00:00 2001
From: chenyu <chenyu@fastmail.com>
Date: Wed, 8 Oct 2025 17:10:51 +0800
Subject: [PATCH] smaller LLAMA_LAYER in Test llama 3 training (#12516)

very slow now
---
 .github/workflows/test.yml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index 2740f62b7e..4138b17888 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -451,7 +451,8 @@ jobs:
       - name: Test Bert training
         run: NULL=1 DEFAULT_FLOAT=HALF BENCHMARK=10 BS=24 GPUS=4 BERT_LAYERS=2 MODEL=bert python3 examples/mlperf/model_train.py
       - name: Test llama 3 training
-        run: NULL=1 SAMPLES=300 BS=8 SEQLEN=512 GRADIENT_ACC_STEPS=8 FAKEDATA=1 DEFAULT_FLOAT=bfloat16 OPTIM_DTYPE=bfloat16 LLAMA3_SIZE=1B MODEL=llama3 python3 examples/mlperf/model_train.py
+        # TODO: remove LLAMA_LAYERS once it's fast
+        run: NULL=1 SAMPLES=300 BS=8 SEQLEN=512 GRADIENT_ACC_STEPS=8 LLAMA_LAYERS=4 FAKEDATA=1 DEFAULT_FLOAT=bfloat16 OPTIM_DTYPE=bfloat16 LLAMA3_SIZE=1B MODEL=llama3 python3 examples/mlperf/model_train.py
       - name: Run process replay tests
         uses: ./.github/actions/process-replay