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 20:55:11 -08:00
commit fc3d136230
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/rl_replacements.py
View file

@ -235,11 +235,11 @@ def grpo_trainer_compute_loss(function_name, function):
from unsloth_zoo.rl_replacements import RL_REPLACEMENTS
if "count" in RL_REPLACEMENTS:
RL_REPLACEMENTS["count"] += 1
if RL_REPLACEMENTS["count"] == 10: raise
if RL_REPLACEMENTS["count"] == 20: raise
else: RL_REPLACEMENTS["count"] = 1
RL_REPLACEMENTS["data"] = (
ref_per_token_logps, per_token_logps, input_ids, completion_mask, self.beta, advantages,
loss, completion_length, mean_kl,
loss, completion_length, mean_kl, completion_ids,
)
# Log the metrics
# completion_length = self.accelerator.gather_for_metrics(completion_mask.sum(1)).float().mean().item()