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

Update rl_replacements.py

Browse source
This commit is contained in:
Daniel Han 2025-06-25 20:13:17 -07:00
commit 6a8ebbac92
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
unsloth/models/rl_replacements.py
View file

@ -333,7 +333,8 @@ def grpo_trainer_compute_loss(function_name, function):
if self.beta != 0.0:
with torch.inference_mode(), model.disable_adapter():
ref_per_token_logps = self._get_per_token_logps(model, input_ids, attention_mask, logits_to_keep)
print("ref_per_token_logps Unsloth 320", ref_per_token_logps.shape)
if ref_per_token_logps is not None:
print("ref_per_token_logps Unsloth 320", ref_per_token_logps.shape)
else:
ref_per_token_logps = None
# per_token_kl = torch.exp(ref_per_token_logps - per_token_logps) - (ref_per_token_logps - per_token_logps) - 1