examples/train/megatron/sft.sh

# 2 * 80GiB
NPROC_PER_NODE=2 \
CUDA_VISIBLE_DEVICES=0,1 \
megatron sft \
    --load Qwen2.5-7B-Instruct-mcore \
    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \
              'AI-ModelScope/alpaca-gpt4-data-en#500' \
              'swift/self-cognition#500' \
    --tensor_model_parallel_size 2 \
    --micro_batch_size 4 \
    --global_batch_size 16 \
    --recompute_granularity selective \
    --train_iters 100 \
    --eval_iters 5 \
    --finetune true \
    --cross_entropy_loss_fusion true \
    --lr 1e-5 \
    --lr_warmup_iters 10 \
    --min_lr 1e-6 \
    --save megatron_output/Qwen2.5-7B-Instruct \
    --save_interval 100 \
    --max_length 2048 \
    --system 'You are a helpful assistant.' \
    --num_workers 4 \
    --no_save_optim true \
    --no_save_rng true \
    --dataset_num_proc 4 \
    --model_author swift \
    --model_name swift-robot