From 834d3d69a14bae1e14ee3594dedafdcb9c62cb1d Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 16 Feb 2025 20:20:01 -0800 Subject: [PATCH] Update rl_replacements.py --- unsloth/models/rl_replacements.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index b058d0d271..bb41cff75b 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -235,7 +235,7 @@ 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"] == 5: raise + 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,