compute_environment: LOCAL_MACHINE debug: false deepspeed_config: offload_optimizer_device: none offload_param_device: none zero3_init_flag: false zero_stage: 2 distributed_type: DEEPSPEED downcast_bf16: 'no' machine_rank: 0 main_training_function: main mixed_precision: 'no' num_machines: 1 num_processes: 4 rdzv_backend: static same_network: true tpu_env: [] tpu_use_cluster: false tpu_use_sudo: false use_cpu: false