shanjiaz/

qwen3-8b-peagle-speculators

CUDA_VISIBLE_DEVICES=2,3 torchrun \
      --standalone --nproc_per_node 2 \
      scripts/train.py \
      --verifier-name-or-path qwen/qwen3-8b \
      --data-path output \
      --vllm-endpoint http://localhost:8000/v1 \
      --hidden-states-path output/hidden_states \
      --save-path output/checkpoints \
      --epochs 5 \
      --lr 6e-4 \
      --total-seq-len 8192 \
      --speculator-type peagle \
      --num-layers 4 \
      --num-depths 7 \
      --down-sample-ratio 0.6 \
      --down-sample-ratio-min 0.2 \
      --no-norm-before-residual \
      --scheduler-type cosine \
      --on-missing generate \
      --on-generate delete