compute_environment: LOCAL_MACHINE
debug: false
deepspeed_config:
  gradient_accumulation_steps: 4
  gradient_clipping: 1.0
  offload_optimizer_device: none
  offload_param_device: none
  zero3_init_flag: false
  zero_stage: 2
  # deepspeed_multinode_launcher: standard
# main_process_ip: localhost
# main_process_port: 6000
machine_rank: 0
num_machines: 1
num_processes: 8
distributed_type: DEEPSPEED
downcast_bf16: 'no'
main_training_function: main
mixed_precision: bf16
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false