Update README.md

README.md

@@ -49,7 +49,7 @@ classifier(sequence_to_classify, candidate_labels, hypothesis_template=hypothesi
 
 
 ## Training 
-This model was pre-trained on a set of 100 languages and follwed further training on 198M multilingual tweets as described in the original [paper](https://arxiv.org/abs/2104.12250). Further it was trained on the training set of XNLI dataset in spanish which is a machine translated version of the MNLI dataset. It was trained on 5 epochs of the XNLI train set and evaluated on the XNLI eval dataset at the end of every to find the best performing model. The model which had the highest accuracy on the eval set was chosen at the end.
+This model was pre-trained on a set of 100 languages and follwed further training on 198M multilingual tweets as described in the original [paper](https://arxiv.org/abs/2104.12250). Further it was trained on the training set of XNLI dataset in spanish which is a machine translated version of the MNLI dataset. It was trained on 5 epochs of the XNLI train set and evaluated on the XNLI eval dataset at the end of every epoch to find the best performing model. The model which had the highest accuracy on the eval set was chosen at the end.
 
 ![Training Charts from wandb](screen_wandb.png)
 - learning rate:    2e-5
@@ -62,6 +62,6 @@ using a GPU (NVIDIA GeForce RTX 3090) resulting in a training time of 1h 47 mins
 
 The best performing model was evaluatated on the XNLI test set to get a comparable result
 ```
-predict_accuracy = 79.2 %
+predict_accuracy = 79.20 %
 ```