BERTology of Molecular Property Prediction (Cross-validated Hyperparameter Search: Small-BERT, Part 4)

Cross-validated Hyperparameter Search Small-BERT (Part 4) This record pertains to Cross-validated Hyperparameter Search Experiments involving Small-BERT. It includes the following files: HLM-fold0-small-binidx-3-ms-1234-ds-1234.tar.gz HLM-fold1-small-binidx-3-ms-1234-ds-1234.tar.gz HLM-fold2-small-binidx-3-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

Related Organizations

Molecular Sciences Software Institute
United States
Virginia Tech
United States

Keywords

Masked language modeling, Molecular property prediction, ADME, Pretraining, Finetuning, Chemical language models, BERT

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

0

Average