Update README.md

README.md

@@ -171,7 +171,7 @@ python run_squad.py \
 --version_2_with_negative \
 --max_seq_length=384
 ```
-
+Experiment done on 4 x NVIDIA TITAN RTX 24 GB.
 #### Result
 ![SQuAD output image](img/squad_2.png)
 
@@ -198,4 +198,4 @@ End of sequence
 ## References
 1. TensorFlow offical implementation of [BERT](https://github.com/tensorflow/models/tree/master/official/nlp/bert) in TF 2.0 . Lot of parts of code in this repo adapted from the above repo.
 2. LAMB optimizer from TensorFlow [addons](https://github.com/tensorflow/addons/blob/master/tensorflow_addons/optimizers/lamb.py)
-3. TF-HUB weights to TF 2.0 weights conversion : [KPE](https://github.com/kpe/bert-for-tf2)
+3. TF-HUB weights to TF 2.0 weights conversion : [KPE](https://github.com/kpe/bert-for-tf2)