[Question] qwen3.5-9b 128k上下文下的sft设置该怎么做

Your Question

cp无效的情况下，不知该如何设置了

What I've Tried

SFT_ARGS=(
--rollout-function-path slime.rollout.sft_rollout.generate_rollout
--prompt-data "${SFT_DATA}"
--input-key messages
--rollout-shuffle
--num-epoch 3
--rollout-batch-size 32
--global-batch-size 32
--loss-type sft_loss
--calculate-per-token-loss
--disable-compute-advantages-and-returns
--debug-train-only
)

PERF_ARGS=(
--tensor-model-parallel-size 4
--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

)

OPTIMIZER_ARGS=(
--optimizer adam
--lr 1e-5
--lr-decay-style cosine
--min-lr 1e-6
--lr-warmup-fraction 0.1
--weight-decay 0.1
--adam-beta1 0.9
--adam-beta2 0.95
)

Environment (if relevant)

• slime version:
• Python version:
• PyTorch version:
• CUDA/ROCm version:
• GPU type and count:
• OS:

Additional Context

No response

Pre-submission Checklist

• I have read the CONTRIBUTING.md and understand the collaboration scope.
• I have read the documentation and FAQ and my question is not answered there.
• I have searched for existing issues and my question has not been asked before.

Start by reviewing the SFT_ARGS and PERF_ARGS shown in the issue, then consult the linked documentation and FAQ for context-parallel and SFT configuration. The issue would need complete environment details and a reproducible explanation of what “cp” failing means; done would be a documented, validated configuration for this 128k SFT setup.