compute_environment: LOCAL_MACHINE debug: false distributed_type: 'NO' downcast_bf16: 'no' machine_rank: 0 main_training_function: main mixed_precision: bf16 num_machines: 1 num_processes: 1 rdzv_backend: static same_network: true tpu_env: [] tpu_use_cluster: false tpu_use_sudo: false use_cpu: false