423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-06 02:42:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

update project_kwargs for ppo config

Browse Source 
Former-commit-id: 14f106962fc0a87802ae9ecffff00d52f7f5f046
This commit is contained in:
stephen 2024-02-21 13:47:38 +08:00
parent 8fd6803294
commit 8bceef81c0
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/llmtuner/train/ppo/workflow.py
View File

@ -61,6 +61,7 @@ def run_ppo(
use_score_norm=finetuning_args.ppo_score_norm, use_score_norm=finetuning_args.ppo_score_norm,
whiten_rewards=finetuning_args.ppo_whiten_rewards, whiten_rewards=finetuning_args.ppo_whiten_rewards,
accelerator_kwargs={"step_scheduler_with_optimizer": False}, accelerator_kwargs={"step_scheduler_with_optimizer": False},
project_kwargs={"logging_dir": training_args.logging_dir},
) )
# Create optimizer and scheduler # Create optimizer and scheduler