cpt core 4

scripts/cpt_core_model_4.py

@@ -41,7 +41,8 @@ model = FastLanguageModel.get_peft_model(
     lora_dropout = 0, # Supports any, but = 0 is optimized
     bias = "none",    # Supports any, but = "none" is optimized
     # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
-    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
+    # use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
+    use_gradient_checkpointing = False,
     random_state = 3407,
     use_rslora = True,  # We support rank stabilized LoRA
     loftq_config = None, # And LoftQ