ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support DDP in webui

Browse Source 
Former-commit-id: d059262ff8dc857f597d2657546ec625726a664a
This commit is contained in:
hiyouga
2024-05-28 19:24:22 +08:00
parent 9912b43fcc
commit 9138a7a5ba
19 changed files with 78 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
examples/accelerate/master_config.yaml
View File

@@ -1,18 +0,0 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 0
main_process_ip: 192.168.0.1
main_process_port: 29555
main_training_function: main
mixed_precision: fp16
num_machines: 2 # the number of nodes
num_processes: 8 # the number of GPUs in all nodes
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false

16
examples/accelerate/single_config.yaml
View File

@@ -1,16 +0,0 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 0
main_training_function: main
mixed_precision: fp16
num_machines: 1 # the number of nodes
num_processes: 4 # the number of GPUs in all nodes
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false

18
examples/accelerate/slave_config.yaml
View File

@@ -1,18 +0,0 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 1
main_process_ip: 192.168.0.1
main_process_port: 29555
main_training_function: main
mixed_precision: fp16
num_machines: 2 # the number of nodes
num_processes: 8 # the number of GPUs in all nodes
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false