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 2025-02-05 05:36:51 -08:00
commit 6386de4cce
1 changed files with 4 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

7
unsloth/models/rl.py
View file

@ -151,15 +151,16 @@ def _PatchRLStatistics(metrics):
pass
def PatchRLStatistics(algorithm = "grpo"):
if algorithm == "grpo":
def PatchRLStatistics(algorithm = "GRPO"):
algorithm = algorithm.upper()
if algorithm == "GRPO":
metrics = [
"completion_length",
"reward",
"reward_std",
"kl",
]
elif algorithm == "dpo" or algorithm == "kto":
elif algorithm == "DPO" or algorithm == "KTO":
metrics = [
"rewards/chosen",
"rewards/rejected",