diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py
index 604323ac8c..3fd180bb27 100644
--- a/unsloth/models/rl.py
+++ b/unsloth/models/rl.py
@@ -741,6 +741,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
         "generation_kwargs": {},
         "bf16": False,
         "fp16": False,
+        "report_to" : "none",
         "include_tokens_per_second": False,
         "include_num_input_tokens_seen": False,
         "auto_find_batch_size": False,  # Auto /2 batch size - too many people complained so removing
@@ -907,8 +908,6 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
         for process_extra_arg in process_extra_args:
             extra_args += process_extra_arg(old_RLTrainer_source, old_RLConfig_source)
 
-    # Edit report_to and default it to nothing if max_steps is like 60
-
     # Create RLConfig args
     extra_args = extra_args.split("\n")
     extra_args = "\n".join(" " * 8 + x for x in extra_args)