diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 2334ae58aa..0c46d07588 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -985,9 +985,9 @@ class FastLlamaModel:
 
         debug_info = """debug_info = \\
         f"==((====))==  Unsloth - Free Apache OSS license | Num GPUs = {args.world_size}\\n"\\
-        f"   \\\   /|   Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\n"\\
-        f"O^O/ \_/ \\    Batch size per device = {self._train_batch_size:,} | Gradient Accumulation steps = {args.gradient_accumulation_steps}\\n"\\
-        f"\        /    Total batch size = {total_train_batch_size:,} | Total steps = {max_steps:,}\\n"\\
+        f"   \\\\   /|   Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\n"\\
+        f"O^O/ \\_/ \\    Batch size per device = {self._train_batch_size:,} | Gradient Accumulation steps = {args.gradient_accumulation_steps}\\n"\\
+        f"\\        /    Total batch size = {total_train_batch_size:,} | Total steps = {max_steps:,}\\n"\\
         f' "-____-"     Number of trainable parameters = {get_model_param_count(model, trainable_only=True):,}'
         logger.warning_once(debug_info)"""
 
diff --git a/unsloth/models/mistral.py b/unsloth/models/mistral.py
index 8a54e18357..28005eed0f 100644
--- a/unsloth/models/mistral.py
+++ b/unsloth/models/mistral.py
@@ -387,12 +387,12 @@ class FastMistralModel(FastLlamaModel):
         original_debug = inner_training_loop[start:end]
         spaces = re.search('\n([\s\t]{1,})', original_debug).group(0)[1:]
         front_spaces = re.match('([\s\t]{1,})', inner_training_loop).group(0)
-        
+
         debug_info = """debug_info = \\
         f"==((====))==  Unsloth - Free Apache OSS license | Num GPUs = {args.world_size}\\n"\\
-        f"   \\\   /|   Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\n"\\
-        f"O^O/ \_/ \\    Batch size per device = {self._train_batch_size:,} | Gradient Accumulation steps = {args.gradient_accumulation_steps}\\n"\\
-        f"\        /    Total batch size = {total_train_batch_size:,} | Total steps = {max_steps:,}\\n"\\
+        f"   \\\\   /|   Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\n"\\
+        f"O^O/ \\_/ \\    Batch size per device = {self._train_batch_size:,} | Gradient Accumulation steps = {args.gradient_accumulation_steps}\\n"\\
+        f"\\        /    Total batch size = {total_train_batch_size:,} | Total steps = {max_steps:,}\\n"\\
         f' "-____-"     Number of trainable parameters = {get_model_param_count(model, trainable_only=True):,}'
         logger.warning_once(debug_info)"""