compute_environment: LOCAL_MACHINE debug: true deepspeed_config: deepspeed_hostfile: hostfile.txt deepspeed_multinode_launcher: pdsh gradient_accumulation_steps: 1 gradient_clipping: 1.0 offload_optimizer_device: none offload_param_device: none zero3_init_flag: true zero_stage: 3 distributed_type: DEEPSPEED downcast_bf16: 'yes' enable_cpu_affinity: true main_process_ip: 10.250.128.19 main_process_port: 12355 main_training_function: main mixed_precision: bf16 num_machines: 4 num_processes: 32 rdzv_backend: static same_network: true tpu_env: [] tpu_use_cluster: false tpu_use_sudo: false use_cpu: false