Files
hao-ai-lab-FastVideo/scripts/accelerate_configs/multi_node_example.yaml
T
sysuyy 330e46e9e8 [feat]: use accelerate on multi-node
Former-commit-id: 0b12fc31f1d2a63f9da38821174ab63d9b3a2d72
2024-03-11 14:45:23 +00:00

19 lines
453 B
YAML

compute_environment: LOCAL_MACHINE
distributed_type: DEEPSPEED
deepspeed_config:
deepspeed_config_file: scripts/accelerate_configs/zero3_offload.json
deepspeed_hostfile: # FullPath here
fsdp_config: {}
machine_rank: 0
main_process_ip: # main process ip
main_process_port: 29501
main_training_function: main
num_machines: 2
num_processes: 16
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false