# returncode: 0

### 0
"python3"
"-m"
"sglang.launch_server"
"--model-path"
"/root/Qwen3-32B"
"--host"
"0.0.0.0"
"--port"
"13141"
"--tp"
"1"
"--chunked-prefill-size"
"4096"
"--mem-fraction-static"
"0.6"

### 1
"curl"
"-sf"
"http://127.0.0.1:13141/health_generate"

### 2
"curl"
"http://127.0.0.1:13141/get_model_info"

### 3
"sleep"
"10"

### 4
"nvidia-smi"
"topo"
"-m"

### 5
"python3"
"<REPO_ROOT>/examples/on_policy_distillation/../../miles/utils/external_utils/model_args_utils.py"
"qwen3-8B"

### 6
"ray"
"start"
"--head"
"--node-ip-address"
"127.0.0.1"
"--num-gpus"
"8"
"--disable-usage-stats"
"--dashboard-host=0.0.0.0"
"--dashboard-port=8265"

### 7
"ray"
"job"
"submit"
"--address=http://127.0.0.1:8265"
"--runtime-env-json={\n     \"env_vars\": {\n        \"PYTHONPATH\": \"/root/Megatron-LM/\",\n        \"CUDA_DEVICE_MAX_CONNECTIONS\": \"1\",\n        \"MILES_USE_LEGACY_ROLLOUT_V1\": \"1\"\n     }\n   }"
"--"
"python3"
"train.py"
"--actor-num-nodes"
"1"
"--actor-num-gpus-per-node"
"2"
"--rollout-num-gpus"
"4"
"--swiglu"
"--num-layers"
"36"
"--hidden-size"
"4096"
"--ffn-hidden-size"
"12288"
"--num-attention-heads"
"32"
"--group-query-attention"
"--num-query-groups"
"8"
"--use-rotary-position-embeddings"
"--disable-bias-linear"
"--normalization"
"RMSNorm"
"--norm-epsilon"
"1e-6"
"--rotary-base"
"1000000"
"--vocab-size"
"151936"
"--kv-channels"
"128"
"--qk-layernorm"
"--untie-embeddings-and-output-weights"
"--hf-checkpoint"
"/root/Qwen3-8B"
"--ref-load"
"/root/Qwen3-8B_torch_dist"
"--load"
"/root/Qwen3-8B_miles/"
"--save"
"/root/Qwen3-8B_miles/"
"--save-interval"
"20"
"--prompt-data"
"/root/dapo-math-17k/dapo-math-17k.jsonl"
"--input-key"
"prompt"
"--apply-chat-template"
"--rollout-shuffle"
"--num-rollout"
"300"
"--rollout-batch-size"
"16"
"--n-samples-per-prompt"
"4"
"--rollout-max-response-len"
"16384"
"--rollout-temperature"
"1"
"--global-batch-size"
"64"
"--balance-data"
"--optimizer"
"adam"
"--lr"
"1e-6"
"--lr-decay-style"
"constant"
"--weight-decay"
"0.1"
"--adam-beta1"
"0.9"
"--adam-beta2"
"0.98"
"--advantage-estimator"
"grpo"
"--use-opd"
"--opd-type"
"sglang"
"--opd-kl-coef"
"1.0"
"--opd-log-prob-top-k"
"16"
"--opd-top-k-strategy"
"only-student"
"--opd-reward-weight-mode"
"student_p"
"--use-kl-loss"
"--kl-loss-coef"
"0.00"
"--kl-loss-type"
"low_var_kl"
"--entropy-coef"
"0.00"
"--tensor-model-parallel-size"
"2"
"--sequence-parallel"
"--pipeline-model-parallel-size"
"1"
"--context-parallel-size"
"1"
"--expert-model-parallel-size"
"1"
"--expert-tensor-parallel-size"
"1"
"--recompute-granularity"
"full"
"--recompute-method"
"uniform"
"--recompute-num-layers"
"1"
"--use-dynamic-batch-size"
"--max-tokens-per-gpu"
"16384"
"--rollout-num-gpus-per-engine"
"1"
"--sglang-mem-fraction-static"
"0.4"
"--attention-dropout"
"0.0"
"--hidden-dropout"
"0.0"
"--accumulate-allreduce-grads-in-fp32"
"--attention-softmax-in-fp32"
"--attention-backend"
"flash"
"--custom-rm-path"
"miles.rollout.on_policy_distillation.reward_func"
"--custom-reward-post-process-path"
"miles.rollout.on_policy_distillation.post_process_rewards"
"--rm-url"
"http://127.0.0.1:13141/generate"

### 8
"pkill"
"-9"
"sglang"

### 9
"sleep"
"3"

### 10
"ray"
"stop"
"--force"

### 11
"pkill"
"-9"
"ray"

### 12
"pkill"
"-9"
"python"

### 13
"sleep"
"3"

### 14
"pkill"
"-9"
"ray"

### 15
"pkill"
"-9"
"python"
