The baseline NLI model is a fine-tuned version of bert-base-uncased for Text Classifacation
on the MNLI dataset , with entailments as label 0 and all others (neutral or contradiction)
as label 1.
Two classes:
entailment: 0
non-entailment: 1
Results on the validation set
MNLI: 90.07%
MNLI-mm: 90.08%
Training hyperparameters
The following hyperparameters were used during training:
