File size: 984 Bytes
cb2428f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
# For more information on multi-node training launch methods, refer to:
# https://github.com/modelscope/ms-swift/tree/main/examples/train/multi-node
CUDA_VISIBLE_DEVICES=0,1,2,3 \
NNODES=2 \
NODE_RANK=0 \
MASTER_ADDR=127.0.0.1 \
MASTER_PORT=29500 \
NPROC_PER_NODE=4 \
megatron sft \
--load Qwen2.5-14B-mcore \
--dataset 'liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT' \
--tensor_model_parallel_size 4 \
--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/Qwen2.5-14B \
--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
|