From 19d36655f7211a9fc7884a4dcf520fbe648c26a2 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 22 Jun 2025 05:32:38 -0700 Subject: [PATCH] Update rl_replacements.py --- unsloth/models/rl_replacements.py | 1 + 1 file changed, 1 insertion(+) diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index 8efaf3fd1f..f590958948 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -340,6 +340,7 @@ def grpo_trainer_compute_loss(function_name, function): print("$$$$$$$$$$$ input_ids", input_ids.shape) input_ids = input_ids[:, -logits_to_keep:] + print("$$$$$$$$$$$ input_ids", input_ids.shape) if per_token_logps is not None: if ref_per_token_logps is not None: