Critical Batch Size Scaling and Pass@1 Accuracy in WizardCoder and DeepSeek-R1

Abstract

Abstract: This report synthesises findings from 9 peer-reviewed papers addressing the following research question: How does the critical batch size scaling affect pass@1 accuracy on HumanEval+ for WizardCoder and DeepSeek-R1 when trained with mixed precision versus full precision. Training large-scale models under given resources requires careful design of parallelism strategies. In particular, the efficiency notion of critical batch size (CBS), concerning the compromise between time and compute, marks the threshold beyond which greater data parallelism. 11 claims were extracted from source literature; 1 was independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 4.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the critical batch size scaling affect pass@1 accuracy on HumanEval+ for WizardCoder and DeepSeek-R1 when trained with mixed precision versus full precision?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance