# 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/lora/../../miles/utils/external_utils/model_args_utils.py"
"kimi-k25"

### 10
"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    \"NCCL_NVLS_ENABLE\": \"0\",\n    \"NCCL_TIMEOUT\": \"3600\",\n    \"OPEN_TRAINING_INT4_FAKE_QAT_FLAG\": \"1\",\n    \"OPEN_TRAINING_INT4_GROUP_SIZE\": \"32\",\n    \"no_proxy\": \"\",\n    \"MASTER_ADDR\": \"127.0.0.1\"\n  }\n}"
"--"
"python3"
"train.py"
"--actor-num-nodes"
"16"
"--actor-num-gpus-per-node"
"8"
"--colocate"
"--update-weight-buffer-size"
"2147483648"
"--disable-bias-linear"
"--num-layers"
"61"
"--hidden-size"
"7168"
"--ffn-hidden-size"
"18432"
"--num-attention-heads"
"64"
"--kv-channels"
"64"
"--normalization"
"RMSNorm"
"--position-embedding-type"
"rope"
"--rope-type"
"yarn"
"--norm-epsilon"
"1e-5"
"--swiglu"
"--untie-embeddings-and-output-weights"
"--vocab-size"
"163840"
"--multi-latent-attention"
"--q-lora-rank"
"1536"
"--kv-lora-rank"
"512"
"--qk-head-dim"
"128"
"--qk-pos-emb-head-dim"
"64"
"--v-head-dim"
"128"
"--qk-layernorm"
"--rotary-scaling-factor"
"64.0"
"--rotary-base"
"50000"
"--original-max-position-embeddings"
"4096"
"--beta-fast"
"32"
"--beta-slow"
"1"
"--mscale"
"1.0"
"--mscale-all-dim"
"1.0"
"--attention-softmax-in-fp32"
"--no-rope-fusion"
"--num-experts"
"384"
"--moe-layer-freq"
"[0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]"
"--moe-ffn-hidden-size"
"2048"
"--moe-router-topk"
"8"
"--moe-shared-expert-intermediate-size"
"2048"
"--moe-router-pre-softmax"
"--moe-router-score-function"
"sigmoid"
"--moe-router-enable-expert-bias"
"--moe-router-load-balancing-type"
"seq_aux_loss"
"--moe-token-dispatcher-type"
"alltoall"
"--moe-aux-loss-coeff"
"0"
"--moe-router-bias-update-rate"
"0"
"--moe-router-group-topk"
"1"
"--moe-router-num-groups"
"1"
"--moe-grouped-gemm"
"--moe-router-topk-scaling-factor"
"2.827"
"--moe-router-dtype"
"fp32"
"--moe-permute-fusion"
"--hf-checkpoint"
"/Kimi-K2.5-int4"
"--ref-load"
"/Kimi-K2.5-bf16"
"--megatron-to-hf-mode"
"bridge"
"--model-name"
"kimi_k25"
"--lora-rank"
"32"
"--lora-alpha"
"32"
"--lora-dropout"
"0.0"
"--target-modules"
"q_a_proj,kv_a_proj_with_mqa,o_proj,gate_proj,up_proj,down_proj"
"--experts-shared-outer-loras"
"--lora-base-cpu-backup"
"--no-gradient-accumulation-fusion"
"--sglang-lora-backend"
"triton"
"--sglang-lora-use-virtual-experts"
"--prompt-data"
"/dapo-math-17k/dapo-math-17k.jsonl"
"--input-key"
"prompt"
"--label-key"
"label"
"--apply-chat-template"
"--rollout-shuffle"
"--balance-data"
"--rm-type"
"deepscaler"
"--num-rollout"
"20"
"--rollout-batch-size"
"32"
"--n-samples-per-prompt"
"8"
"--rollout-max-response-len"
"16384"
"--rollout-temperature"
"1"
"--global-batch-size"
"256"
"--filter-zero-reward-samples"
"--use-dynamic-global-batch-size"
"--optimizer"
"adam"
"--lr"
"1e-5"
"--lr-decay-style"
"constant"
"--weight-decay"
"0.1"
"--adam-beta1"
"0.9"
"--adam-beta2"
"0.98"
"--optimizer-cpu-offload"
"--overlap-cpu-optimizer-d2h-h2d"
"--use-precision-aware-optimizer"
"--use-distributed-optimizer"
"--advantage-estimator"
"grpo"
"--kl-loss-coef"
"0.00"
"--kl-loss-type"
"low_var_kl"
"--entropy-coef"
"0.00"
"--eps-clip"
"0.2"
"--eps-clip-high"
"0.28"
"--use-tis"
"--use-wandb"
"--wandb-project"
"miles-kimi-k25"
"--wandb-group"
"kimi-k25-lora"
"--disable-wandb-random-suffix"
"--tensor-model-parallel-size"
"8"
"--sequence-parallel"
"--pipeline-model-parallel-size"
"2"
"--context-parallel-size"
"8"
"--expert-model-parallel-size"
"64"
"--expert-tensor-parallel-size"
"1"
"--decoder-last-pipeline-num-layers"
"30"
"--recompute-granularity"
"full"
"--recompute-method"
"uniform"
"--recompute-num-layers"
"1"
"--use-dynamic-batch-size"
"--max-tokens-per-gpu"
"4096"
"--eval-interval"
"20"
"--eval-prompt-data"
"aime"
"/aime-2024.jsonl"
"--n-samples-per-eval-prompt"
"16"
"--eval-max-response-len"
"16384"
"--eval-top-p"
"1"
"--rollout-num-gpus-per-engine"
"8"
"--sglang-mem-fraction-static"
"0.7"
"--sglang-ep-size"
"8"
"--sglang-server-concurrency"
"1024"
"--sglang-cuda-graph-bs-decode"
"1"
"2"
"4"
"8"
"16"
"24"
"32"
"40"
"48"
"56"
"64"
"72"
"80"
"88"
"96"
"104"
"112"
"120"
"128"
"--use-rollout-routing-replay"
"--attention-dropout"
"0.0"
"--hidden-dropout"
"0.0"
"--accumulate-allreduce-grads-in-fp32"
"--attention-softmax-in-fp32"
"--attention-backend"
"flash"
"--no-check-for-nan-in-loss-and-grad"
