examples/train/megatron/moe.sh

# 8 * 65GiB
NPROC_PER_NODE=8 \
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
megatron sft \
    --load Qwen1.5-MoE-A2.7B-mcore \
    --dataset 'liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT' \
    --tensor_model_parallel_size 2 \
    --expert_model_parallel_size 4 \
    --moe_grouped_gemm true \
    --moe_shared_expert_overlap true \
    --moe_aux_loss_coeff 0.01 \
    --micro_batch_size 1 \
    --global_batch_size 16 \
    --packing true \
    --recompute_granularity selective \
    --train_iters 2000 \
    --eval_iters 50 \
    --finetune true \
    --cross_entropy_loss_fusion true \
    --lr 1e-5 \
    --lr_warmup_iters 100 \
    --min_lr 1e-6 \
    --save megatron_output/Qwen1.5-MoE-A2.7B \
    --eval_interval 200 \
    --save_interval 200 \
    --max_length 8192 \
    --num_workers 8 \
    --dataset_num_proc 8 \
    --no_save_optim true \
    --no_save_rng true \
    --sequence_parallel true \
    --use_flash_attn true