# returncode: 0

### 0
"pkill"
"-9"
"sglang"

### 1
"sleep"
"3"

### 2
"ray"
"stop"
"--force"

### 3
"pkill"
"-9"
"ray"

### 4
"pkill"
"-9"
"python"

### 5
"sleep"
"3"

### 6
"pkill"
"-9"
"ray"

### 7
"pkill"
"-9"
"python"

### 8
"nvidia-smi"
"topo"
"-m"

### 9
"python3"
"<REPO_ROOT>/examples/infra_features/low_precision/../../../miles/utils/external_utils/model_args_utils.py"
"qwen3-4B"

### 10
"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"

### 11
"ray"
"job"
"submit"
"--address=http://127.0.0.1:8265"
"--runtime-env-json={\n  \"env_vars\": {\n    \"PYTHONPATH\": \"/root/Megatron-LM/:<REPO_ROOT>/examples/infra_features/low_precision\",\n    \"CUDA_DEVICE_MAX_CONNECTIONS\": \"1\",\n    \"NCCL_NVLS_ENABLE\": \"0\",\n    \"NVTE_FP8_BLOCK_SCALING_FP32_SCALES\": \"1\"\n  }\n}"
"--"
"python3"
"train.py"
"--actor-num-nodes"
"1"
"--actor-num-gpus-per-node"
"8"
"--colocate"
"--swiglu"
"--num-layers"
"36"
"--hidden-size"
"2560"
"--ffn-hidden-size"
"9728"
"--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"
"--hf-checkpoint"
"/root/Qwen3-4B-FP8"
"--ref-load"
"/root/Qwen3-4B_torch_dist"
"--load"
"/root/qwen3-4b_cp8_fp8"
"--save"
"/root/rl-model/qwen3-4b_cp8_fp8"
"--save-interval"
"20"
"--prompt-data"
"/root/dapo-math-17k/dapo-math-17k.jsonl"
"--input-key"
"prompt"
"--label-key"
"label"
"--apply-chat-template"
"--rollout-shuffle"
"--rm-type"
"deepscaler"
"--num-rollout"
"3000"
"--rollout-batch-size"
"32"
"--n-samples-per-prompt"
"8"
"--rollout-max-response-len"
"8192"
"--rollout-temperature"
"1"
"--global-batch-size"
"256"
"--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-kl-loss"
"--kl-loss-coef"
"0.00"
"--kl-loss-type"
"low_var_kl"
"--entropy-coef"
"0.00"
"--eps-clip"
"0.2"
"--eps-clip-high"
"0.28"
"--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"
"9216"
"--eval-interval"
"20"
"--eval-prompt-data"
"aime"
"/root/data/aime-2024.jsonl"
"--n-samples-per-eval-prompt"
"16"
"--eval-max-response-len"
"16384"
"--eval-top-p"
"1"
"--rollout-num-gpus-per-engine"
"2"
"--sglang-mem-fraction-static"
"0.7"
"--attention-dropout"
"0.0"
"--hidden-dropout"
"0.0"
"--accumulate-allreduce-grads-in-fp32"
"--attention-softmax-in-fp32"
"--attention-backend"
"flash"
