compute_environment: LOCAL_MACHINE
distributed_type: MULTI_GPU  
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 0 
main_process_ip: 'xx.xx.xx.xx' 
main_process_port: 36001         
main_training_function: main
mixed_precision: 'bf16'
num_machines: 2                  
num_processes: 16
rdzv_backend: static
same_network: true
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false
# Optional DeepSpeed ZeRO-0 (no sharding). Prefer MULTI_GPU DDP for single-node training.
deepspeed_config:
  zero_stage: 0
  gradient_accumulation_steps: 1
  zero3_init_flag: false