Dokumentdetails
ID
oai:arXiv.org:2409.05423
Thema
Computer Science - Computation and... I.2.7Autor
Hillier, Dylan Guertler, Leon Cheng, Bobby Tan, ChestonKategorie
Computer Science
Jahr
2024
Auflistungsdatum
11.09.2024
Schlüsselwörter
models language improvingZusammenfassung
In this work we explore the relevance of dropout for modern language models, particularly in the context of models on the scale of <100M parameters.
We explore it's relevance firstly in the regime of improving the sample efficiency of models given small, high quality datasets, and secondly in the regime of improving the quality of its fit on larger datasets where models may underfit.
We find that concordant with conventional wisdom, dropout remains effective in the overfitting scenario, and that furthermore it may have some relevance for improving the fit of models even in the case of excess data, as suggested by previous research.
In the process we find that the existing explanation for the mechanism behind this performance gain is not applicable in the case of language modelling.
;Comment: 6 pages, 3 figures, For code base see https://github.com/LeonGuertler/SuperTinyLanguageModels
Hillier, Dylan,Guertler, Leon,Cheng, Bobby,Tan, Cheston, 2024, STLM Engineering Report: Dropout
Projection-Specific Heterogeneity of the Axon Initial Segment of Pyramidal Neurons in the Prelimbic Cortex
heterogeneity projection-specific
