compute_environment: LOCAL_MACHINE
deepspeed_config:
  gradient_accumulation_steps: 1
  offload_optimizer_device: cpu
  offload_param_device: cpu
  zero3_init_flag: false
  zero_stage: 2
distributed_type: DEEPSPEED
downcast_bf16: 'no'
fsdp_config: {}
machine_rank: 0
main_process_ip: null
main_process_port: null
main_training_function: main
mixed_precision: 'no'
num_machines: 1
num_processes: 1
use_cpu: false