Update README.md

README.md

@@ -38,7 +38,7 @@ T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervis
 
 ### Tokenization
 Since, T5 is a text-to-text model, the labels of the dataset are converted as follows:
-For each example, a sentence as been formed as **"rte sentence1: " + rte_sent1 + "sentence 2" + rte_sent2** and fed to the tokenizer to get the **input_ids** and **attention_mask**.
+For each example, a sentence as been formed as **"rte sentence1: " + rte_sent1 + "sentence 2: " + rte_sent2** and fed to the tokenizer to get the **input_ids** and **attention_mask**.
 For each label, label is choosen as **"entailment"** if label is 1, else label is **"not_entailment"** and tokenized to get **input_ids** and **attention_mask** . 
   During training, these inputs_ids having **pad** token are replaced with -100 so that loss is not calculated for them. Then these input ids are given as labels, and above attention_mask of labels
   is given as decoder attention mask.