compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 1
main_process_ip: 192.168.0.1
main_process_port: 29555
main_training_function: main
mixed_precision: fp16
num_machines: 2 # the number of nodes
num_processes: 16 # the number of GPUs in all nodes
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false