Files
modelscope--ms-swift/examples/train/multi-node/accelerate/multi_node.yaml
T
wehub-resource-sync a203934033
Lint test / lint (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:34:58 +08:00

18 lines
465 B
YAML

compute_environment: LOCAL_MACHINE
deepspeed_config:
deepspeed_multinode_launcher: standard
gradient_accumulation_steps: 16
offload_optimizer_device: none
offload_param_device: none
zero3_init_flag: false
zero_stage: 3
distributed_type: DEEPSPEED
main_process_ip: 'xxx.xxx.xxx.xxx'
main_process_port: 29500
main_training_function: main
mixed_precision: bf16
num_machines: 2
num_processes: 8 # world size
rdzv_backend: static
use_cpu: false