Update README.md

README.md

@@ -48,7 +48,7 @@ This approach to transfer learning not only showcases the ability to downscale t
 We initially attempted a full fine-tune using DeepSpeed on a 4-GPU A100 instance. However, the combination of dataset size and the scale of the model caused significant overfitting, leading to degraded narrative quality. This highlighted the need for a lighter, more targeted adaptation method.
 
 ### Transition to LoRA Fine-Tuning
-To address overfitting, we implemented LoRA fine-tuning (rank 8, DeepSpeed), targeting specific model components (`q_proj`, `k_proj`, `v_proj`, `o_proj`). This method allowed us to retain the base model's linguistic knowledge while specializing it for storytelling. The fine-tuning process lasted **12–18 hours on a 4-GPU A100 8GB instance**, effectively balancing performance and computational efficiency.
+To address overfitting, we implemented LoRA fine-tuning (rank 8, DeepSpeed), targeting specific model components (`q_proj`, `k_proj`, `v_proj`, `o_proj`). This method allowed us to retain the base model's linguistic knowledge while specializing it for storytelling. The fine-tuning process lasted **12–18 hours on a 4-GPU A100 80GB instance** via RunPod, effectively balancing performance and computational efficiency.
 
 ---