BERTology of Molecular Property Prediction (Cross-validated Hyperparameter Search: Tiny-BERT, Part 1)

Read full text Summarise with VIRAT
Authors: Mohammad Mostafanejad, Paul W. Saxe, T. Daniel Crawford
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Cross-validated Hyperparameter Search Tiny-BERT (Part 1) This record pertains to Cross-validated Hyperparameter Search Experiments involving Tiny-BERT. It includes the following files: HLM-fold0-tiny-binidx-0-ms-1234-ds-1234.tar.gz HLM-fold1-tiny-binidx-0-ms-1234-ds-1234.tar.gz HLM-fold2-tiny-binidx-0-ms-1234-ds-1234.tar.gz hPPB-fold0-tiny-binidx-0-ms-1234-ds-1234.tar.gz hPPB-fold1-tiny-binidx-0-ms-1234-ds-1234.tar.gz hPPB-fold2-tiny-binidx-0-ms-1234-ds-1234.tar.gz SOL-fold0-tiny-binidx-0-ms-1234-ds-1234.tar.gz SOL-fold1-tiny-binidx-0-ms-1234-ds-1234.tar.gz SOL-fold2-tiny-binidx-0-ms-1234-ds-1234.tar.gz HLM-fold0-tiny-binidx-3-ms-1234-ds-1234.tar.gz HLM-fold1-tiny-binidx-3-ms-1234-ds-1234.tar.gz HLM-fold2-tiny-binidx-3-ms-1234-ds-1234.tar.gz hPPB-fold0-tiny-binidx-3-ms-1234-ds-1234.tar.gz hPPB-fold1-tiny-binidx-3-ms-1234-ds-1234.tar.gz hPPB-fold2-tiny-binidx-3-ms-1234-ds-1234.tar.gz SOL-fold0-tiny-binidx-3-ms-1234-ds-1234.tar.gz SOL-fold1-tiny-binidx-3-ms-1234-ds-1234.tar.gz SOL-fold2-tiny-binidx-3-ms-1234-ds-1234.tar.gz HLM-fold0-tiny-binidx-5-ms-1234-ds-1234.tar.gz HLM-fold1-tiny-binidx-5-ms-1234-ds-1234.tar.gz HLM-fold2-tiny-binidx-5-ms-1234-ds-1234.tar.gz hPPB-fold0-tiny-binidx-5-ms-1234-ds-1234.tar.gz hPPB-fold1-tiny-binidx-5-ms-1234-ds-1234.tar.gz hPPB-fold2-tiny-binidx-5-ms-1234-ds-1234.tar.gz SOL-fold0-tiny-binidx-5-ms-1234-ds-1234.tar.gz SOL-fold1-tiny-binidx-5-ms-1234-ds-1234.tar.gz SOL-fold2-tiny-binidx-5-ms-1234-ds-1234.tar.gz NOTE: The hyperparameter search and finetuning scripts are based on Biogen's codebases. As a result, the program design and many software development choices were not based on our own preferences or recommended best practices. Preprint: https://doi.org/10.48550/arXiv.2603.13627

Fields of Study & Subjects

Computational Drug Discovery Methods Machine Learning in Materials Science Machine Learning in Bioinformatics

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
27 March 2026
Language
EN