Overview of thing learned
Technical: I got to learn the implementation of distilBERT. Then I used distilBERT for training text for posts classification.
Tools: I learned to use the transformers package of python.
Soft Skills: I got to work on a team project which helped me learn teamwork, discussing ideas within members, effective communication.
- Successfully implemented distilBERT for post classification.
- Achieved accuracy of 83.5% for classification.
- Got to know and worked with some awesome people.
List of meetings/training attended
- distilBERT modeling.
- Subteam presentations.
Goals for upcoming weeks
- Continue for 3 more weeks.
- Learn React.
- Improve model.
- Deploy model using AWS.
Task: Preprocess data
Hurdles: The model was giving errors.
Checked the data and found some null values. Dropped those NaN values and then model worked well.
Task : Implemented distilBERT.
Hurdles: Colab crashing because of the large size of the input to tensor.
Had to reduce the size of tokens to 150.
Task: Classified trained data and tried various classifiers.