REVIEW 1 cited by
Measuring the Instability of Fine-Tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Fine-tuning pre-trained language models on downstream tasks with varying random seeds has been shown to be unstable, especially on small datasets. Many previous studies have investigated this instability and proposed methods to mitigate it. However, most studies only used the standard deviation of performance scores (SD) as their measure, which is a narrow characterization of instability. In this paper, we analyze SD and six other measures quantifying instability at different levels of granularity. Moreover, we propose a systematic framework to evaluate the validity of these measures. Finally, we analyze the consistency and difference between different measures by reassessing existing instability mitigation methods. We hope our results will inform the development of better measurements of fine-tuning instability.
Forward citations
Cited by 1 Pith paper
-
A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
Contrastive activation steering on about 30 Italian prompts matches or beats instruction fine-tuning for Italian on MMLU, HellaSwag, and ARC, with markedly higher Italian language consistency.
Discussion (0). Continue with ORCID to comment.