Code mixing is the mixing of language while writing text. The biggest problem in Malayalam-English code-mixing is that people switch between languages (e.g. Malayalam and English) and use English phonetic typing instead of writing Malayalam words using Dravidian scripts. Traditional NLP models are trained on extensive monolingual tools (e.g. Malayalam or English); code-mixing is challenging since they cannot handle data code-mixing. DravidianCodeMix FIRE 2020 is to classify comments into positive, negative, unknown_state, mixed_feelings and not-malayalam categories based on message-level polarity using Malayalam – English dataset. The classification model used for this challenging task is sentence-level BERT. Achieved an F1-score of 0.71 (ranked 4th) for the Malayalam-English (Manglish) comments dataset submitted under the username: CIA_NITT.