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