Update README.md

README.md

@@ -197,8 +197,8 @@ docker run -p 7860:7860 exec-assist
 ```python
 GRPOConfig(
     learning_rate=1e-6,           # critical, 5e-6 caused collapse
-    per_device_train_batch_size=2,
-    gradient_accumulation_steps=4,
+    per_device_train_batch_size=1,
+    gradient_accumulation_steps=8,
     num_generations=8,            # diversity within group
     num_train_epochs=3,
     beta=0.1,                     # KL penalty, prevents mode collapse