423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

[fix] fix the issue when using fsdp2 with gradient checkpointing. (#9541)

Browse Source 
Co-authored-by: jin-yongxu <jinyongxu@h-partners.com>
This commit is contained in:
xvxuopop
2025-12-06 16:04:51 +08:00
committed by GitHub
parent 165f3f073a
commit 109162dc56
2 changed files with 32 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
examples/accelerate/fsdp2_config.yaml Normal file
View File

@@ -0,0 +1,22 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: FSDP
downcast_bf16: 'no'
fsdp_config:
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_cpu_ram_efficient_loading: true
fsdp_offload_params: false
fsdp_reshard_after_forward: true
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_version: 2
machine_rank: 0
main_training_function: main
mixed_precision: bf16 # or fp16
num_machines: 1 # the number of nodes
num_processes: 2 # 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