JasonForJoy / IMN

CIKM 2019: Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
86 stars 12 forks source link

Batch Size impact on model performance #25

Open KJGithub2021 opened 8 months ago

KJGithub2021 commented 8 months ago

Hi @JasonForJoy can you please confirm if reducing the batch size (due to low-end GPU machine availability) can impact the performance values of the model ?

Secondly, every batch_size including the recommended (i.e. 96) is not a divisor of the total number of training, valid or test samples. As a result of which the last batch misses out on samples. Does this process contribute in lowering the recall and other metric values ?