ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update rl.py

Browse source
This commit is contained in:
Daniel Han 2025-06-21 22:26:46 -07:00
commit 2f2930ee50
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
unsloth/models/rl.py
View file

@ -531,7 +531,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
" mask_truncated_completions = True\n"\
" epsilon_high = 0.28\n"\
" beta = 0.0\n"\
" loss_type = 'bnpo'"
" loss_type = 'bnpo'\n"\
"\n"
extra_args += check_dr_grpo
pass