This model is T5 fine-tuned on GLUE RTE dataset. It acheives the following results on the validation set

T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format.

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 label, target is choosen as "entailment" if label is 0, 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.

The following hyperparameters were used during training: