Files
hao-ai-lab-FastVideo/scripts/accelerate_configs/multi_node_example.yaml
T
LinB203 ff36d291d8 train with image
Former-commit-id: 209b9a8ad2f19a50e46f9b7ec68dd781898e491a
2024-03-19 23:21:57 +08:00

19 lines
495 B
YAML

compute_environment: LOCAL_MACHINE
distributed_type: DEEPSPEED
deepspeed_config:
deepspeed_config_file: scripts/accelerate_configs/zero2.json
deepspeed_hostfile: /remote-home1/yeyang/Open-Sora-Plan/scripts/accelerate_configs/hostfile
fsdp_config: {}
machine_rank: 0
main_process_ip: 10.10.10.55
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