acc.yaml

compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
machine_rank: 0
main_training_function: main
mixed_precision: bf16
num_machines: 1
num_processes: 2
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false

#compute_environment: LOCAL_MACHINE
#deepspeed_config:
#  deepspeed_multinode_launcher: standard
#  gradient_accumulation_steps: 1
#  gradient_clipping: 1.0
#  offload_optimizer_device: none
#  offload_param_device: none
#  zero3_init_flag: false
#  zero3_save_16bit_model: true
#  zero_stage: 3
#distributed_type: stard
#downcast_bf16: 'no'
#dynamo_config: {}
#fsdp_config: {}
#machine_rank: 0
#main_training_function: main
#megatron_lm_config: {}
#mixed_precision: fp16
#num_machines: 2
#num_processes: 16
#tpu_env: []
#tpu_use_cluster: false
#tpu_use_sudo: false
#use_cpu: false