diff --git a/tests/end_to_end/tpu/deepseek/v3.2-671b/2_test_deepseek.sh b/tests/end_to_end/tpu/deepseek/v3.2-671b/2_test_deepseek.sh
index 3bceff1860..ef7e017bda 100644
--- a/tests/end_to_end/tpu/deepseek/v3.2-671b/2_test_deepseek.sh
+++ b/tests/end_to_end/tpu/deepseek/v3.2-671b/2_test_deepseek.sh
@@ -53,7 +53,7 @@ python3 -m tests.utils.forward_pass_logit_checker ${MAXTEXT_CONFIGS_DIR:-${MAXTE
 
 # Run pre-training - tokamax_gmm implementation
 # Note: use sgd due to memory constraint
-python3 -m maxtext.trainers.pre_train.train ${MAXTEXT_CONFIGS_DIR:-${MAXTEXT_REPO_ROOT:-$PWD}/src/maxtext/configs}/base.yml base_output_directory=${BASE_OUTPUT_PATH} run_name=tokamax_gmm_pre_training model_name=${MODEL_NAME} tokenizer_type=huggingface tokenizer_path=${TOKENIZER_PATH} dataset_type=synthetic enable_checkpointing=false attention=flash use_tokamax_splash=True sparse_matmul=True use_tokamax_gmm=True dtype=bfloat16 weight_dtype=bfloat16 per_device_batch_size=1 steps=5 max_target_length=4096 ici_fsdp_parallelism=-1 opt_type=sgd
+python3 -m maxtext.trainers.pre_train.train ${MAXTEXT_CONFIGS_DIR:-${MAXTEXT_REPO_ROOT:-$PWD}/src/maxtext/configs}/base.yml base_output_directory=${BASE_OUTPUT_PATH} run_name=tokamax_gmm_pre_training model_name=${MODEL_NAME} tokenizer_type=huggingface tokenizer_path=${TOKENIZER_PATH} dataset_type=synthetic enable_checkpointing=false attention=flash use_tokamax_splash=True sparse_matmul=True use_tokamax_gmm=True dtype=bfloat16 weight_dtype=bfloat16 per_device_batch_size=1 steps=5 max_target_length=4096 ici_fsdp_parallelism=-1 opt_type=sgd use_indexer=True indexer_loss_scaling_factor=0.01 indexer_sparse_training=True
 
 # Run decoding - megablox implementation
 # Note: decode requires the access token for huggingface tokenizer even if the model is not gated