diff --git a/examples/tuning/1.5b/qwen2.5math-1.5b_grpo_1_h100_fsdp_vllm.sh b/examples/tuning/1.5b/qwen2.5math-1.5b_grpo_1_h100_fsdp_vllm.sh
new file mode 100644
index 00000000000..a0bbb12e382
--- /dev/null
+++ b/examples/tuning/1.5b/qwen2.5math-1.5b_grpo_1_h100_fsdp_vllm.sh
@@ -0,0 +1,59 @@
+PROJECT_NAME=qwen2.5_Math_1.5b_dr_grpo
+LR=1e-5
+MODEL_NAME=Qwen/Qwen2.5-Math-1.5B
+MAX_NEW_TOKENS=3000
+MAX_PROMPT_LENGTH=1024 #1024 #512
+MODEL_ALIAS=${MODEL_NAME##*/}
+GROUP_SIZE=8
+CHOSEN_DEVICE=0 #0,1
+TOTAL_EPOCHS=2
+LOG_N_VAL_GENERATIONS=40 
+ADVANTAGE_ESTIMATOR="grpo"
+
+
+TIMESTAMP=$(date +"%Y%m%d_%H%M%S")
+RUN_NAME=${MODEL_ALIAS}_${LR}_${GROUP_SIZE}_${MAX_NEW_TOKENS}_${ADVANTAGE_ESTIMATOR}_${TIMESTAMP}
+
+CUDA_VISIBLE_DEVICES=$CHOSEN_DEVICE python3 -m verl.trainer.main_ppo \
+        algorithm.adv_estimator=$ADVANTAGE_ESTIMATOR \
+        data.train_files=data/MATH/train.parquet \
+        data.val_files=data/MATH/test.parquet \
+        data.train_batch_size=256 \
+        data.max_prompt_length=$MAX_PROMPT_LENGTH \
+        data.max_response_length=$MAX_NEW_TOKENS \
+        data.filter_overlong_prompts=True \
+        data.truncation='error' \
+        actor_rollout_ref.model.path=$MODEL_NAME \
+        actor_rollout_ref.actor.optim.lr=$LR \
+        actor_rollout_ref.actor.loss_agg_mode=seq-mean-token-sum-norm \
+        actor_rollout_ref.model.use_remove_padding=True \
+        actor_rollout_ref.actor.ppo_mini_batch_size=256 \
+        actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=4 \
+        actor_rollout_ref.actor.use_kl_loss=False \
+        actor_rollout_ref.actor.kl_loss_coef=0.001 \
+        actor_rollout_ref.actor.kl_loss_type=low_var_kl \
+        actor_rollout_ref.actor.entropy_coeff=0 \
+        actor_rollout_ref.model.enable_gradient_checkpointing=True \
+        actor_rollout_ref.actor.fsdp_config.param_offload=False \
+        actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \
+        actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4 \
+        actor_rollout_ref.rollout.tensor_model_parallel_size=1 \
+        actor_rollout_ref.rollout.name=vllm \
+        actor_rollout_ref.rollout.gpu_memory_utilization=0.4 \
+        actor_rollout_ref.rollout.n=$GROUP_SIZE \
+        actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=4 \
+        actor_rollout_ref.ref.fsdp_config.param_offload=True \
+        actor_rollout_ref.rollout.temperature=1.0 \
+        actor_rollout_ref.rollout.top_p=1.0 \
+        algorithm.use_kl_in_reward=False \
+        algorithm.norm_adv_by_std_in_grpo=False \
+        trainer.critic_warmup=0 \
+        trainer.logger='["console","wandb"]' \
+        trainer.n_gpus_per_node=1 \
+        trainer.log_val_generations=$LOG_N_VAL_GENERATIONS \
+        trainer.nnodes=1 \
+        trainer.save_freq=20 \
+        trainer.test_freq=1 \
+        trainer.project_name=$PROJECT_NAME \
+        trainer.experiment_name=$RUN_NAME \
+        trainer.total_epochs=$TOTAL_EPOCHS