compute_environment: LOCAL_MACHINE
deepspeed_config:
  gradient_accumulation_steps: 4
  gradient_clipping: 1.0
  offload_optimizer_device: none
  offload_param_device: none
  zero3_init_flag: true
  zero3_save_16bit_model: true
  zero_stage: 3
distributed_type: DEEPSPEED
downcast_bf16: 'yes'
dynamo_config: {}
fsdp_config: {}
machine_rank: 0
main_training_function: main
megatron_lm_config: {}
num_machines: 1
num_processes: 4
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false