Top Answers

1. How should the learning rate change as the batch size change?
   23 votes
2. google colab setting a '^C' in the proccess
   4 votes
3. What loss function to use in Keras when metric is SparseTopKCategoricalAccuracy/TopKCategoricalAccuracy?
   3 votes
4. Fine-Tuning DistilBertForSequenceClassification: Is not learning, why is loss not changing? Weights not updated?
   2 votes
5. Why is there no pooler layer in huggingfaces' FlauBERT model?
   2 votes