compute_environment: LOCAL_MACHINE deepspeed_config: deepspeed_multinode_launcher: standard gradient_clipping: 1.0 offload_optimizer_device: none offload_param_device: none zero3_init_flag: false zero_stage: 1 distributed_type: DEEPSPEED fsdp_config: {} machine_rank: 0 main_training_function: main mixed_precision: bf16 num_machines: 1 num_processes: 8 rdzv_backend: static same_network: true use_cpu: false