Update README.md

README.md

@@ -25,7 +25,7 @@ The primary goal of this model is to improve scores on the ko-CommonGen V2 task,
 - **Hidden Size**: 2,048
 - **FFN Size**: 5,632
 - **Maximum Length**: 4,096 tokens
-- **Training Time**: 112 GPU hours on NVIDIA A100
+- **Training Time**: 5 GPU hours on NVIDIA A100 (Google Colab Pro+)
 
 #### Limitations and Ethical Considerations
 Like other LLMs, the 42dot LLM-SFT-1.3B may produce hallucinated or biased content. Users should be aware of these limitations and take appropriate actions.