compute_environment: LOCAL_MACHINE debug: false deepspeed_config: gradient_accumulation_steps: 1 offload_optimizer_device: none offload_param_device: none zero3_init_flag: false zero3_save_16bit_model: false zero_stage: 3 distributed_type: DEEPSPEED downcast_bf16: 'no' enable_cpu_affinity: false machine_rank: 0 main_training_function: main mixed_precision: fp16 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