Update README.md

README.md

@@ -52,7 +52,7 @@ The optimizer used is AdaFactor with inverse square root learning rate schedule
 
 ### Fine-tuning
 
-This model was then fine-tuned on a single TPU Pod V2-8 for 80,000 steps in total, using sequence length 512 (batch size 256), using only the dataset only containing java code.
+This model was then fine-tuned on a single TPU Pod V3-8 for 80,000 steps in total, using sequence length 512 (batch size 256), using only the dataset only containing java code.
 
 
 ## Evaluation results