Updated README

Signed-off-by: sakundu <sakundu@ucsd.edu>

README.md

@@ -64,11 +64,10 @@ Google has stated this on a number of occasions. Of course, a key motivation for
 
 **6. Did you use pre-trained models? How much does pre-training matter?**  
 
-We did not use pre-trained models in our study. Note that it is impossible to replicate the pre-training described in the Nature paper, since the data set used for pre-training consists of 20 TPU blocks.
+We did not use pre-trained models in our study. Note that it is impossible to replicate the pre-training described in the Nature paper, since the data set used for pre-training consists of 20 TPU blocks which are not open-sourced.
 - In the Circuit Training repo, Google engineers write:  “Our results training from scratch are comparable or better than the reported results in the paper (on page 22) which used fine-tuning from a pre-trained model. We are training from scratch because we cannot publish the pre-trained model at this time and the released code can provide comparable results.” ([link](https://github.com/google-research/circuit_training/blob/main/docs/ARIANE.md#results))
 - The Stronger Baselines manuscript showed that a pre-trained model helped to improve proxy cost for the TPU blocks, but failed to improve HPWL and congestion for the ICCAD04 benchmarks. The SB authors pre-trained their model for 48 hours using 200 CPUs and 20 GPUs with a training dataset of 20 TPU blocks.
 - The Nature paper did not show benefits from pre-training for Table 1 metrics. The Nature paper only shows benefits (from the pre-trained model) in terms of runtime and final proxy cost.
-- Note. As mentioned, the Nature paper describes use of 20 TPU blocks as the training set for generation of the pre-trained model. However, the training dataset has not been open-sourced. A 48-hour runtime for pre-training is mentioned in the paper.
 
 **7. What are the runtimes (wall times) of different macro placers that you studied?**  
 
@@ -87,7 +86,7 @@ We did not use pre-trained models in our study. Note that it is impossible to re
   - CMP: Innovus launched with 8 threads
   - AutoDMP: run on NVIDIA DGX-A100 machine with two GPU workers
 
-**8. In your experiments are Simulated Annealing (SA) and Reinforcement Learning (i.e., Circuit Training) given comparable runtime and computational resources?**  
+**8. In your experiments how are the results of Simulated Annealing (SA) and Reinforcement Learning (i.e., Circuit Training) compared?**
 
 - The solutions typically produced by human experts and SA are superior to those generated by the RL framework in the majority of cases we tested.
 - Furthermore, in our experiments, SA in nearly all cases produces better results than Circuit Training, **using less computational resources**, across both benchmark sets that we studied.