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 2025-02-16 23:49:20 -08:00
commit a83afa3622
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_replacements.py
View file

@ -239,7 +239,7 @@ def grpo_trainer_compute_loss(function_name, function):
if RL_REPLACEMENTS["count"] == 10: raise
else: RL_REPLACEMENTS["count"] = 1
RL_REPLACEMENTS["data"] = (
ref_per_token_logps, per_token_logps, _input_ids, completion_mask, self.beta, advantages,
ref_per_token_logps, per_token_logps.detach(), _input_ids, completion_mask, self.beta, advantages,
loss, completion_length, mean_kl, completion_ids, _logits_to_keep,
)
# Log the metrics