ishan/distilbert-base-uncased-mnli

We used the pretrained model from distilbert-base-uncased and finetuned it on MultiNLI dataset . The training parameters were kept the same as Devlin et al., 2019 (learning rate = 2e-5, training epochs = 3, max_sequence_len = 128 and batch_size = 32)Evaluation Results are mentioned in the table below . The evaluation results are mentioned as well as the results of the test and the test results are shown below . For example, the test was done using the model from the model that was used by the model-trained model from Distilbert Base-Uncased . The test results were shown below,