Dawid Kopiczko (@dawkopi) / X

Dawid Kopiczko

45 posts

Dawid Kopiczko

@dawkopi

PhD in progress

dkopi.github.io

Joined April 2020

Pinned
Dawid Kopiczko
@dawkopi
Feb 16
Replying to @dawkopi
Why repetition works so well is still an open question. There's a lot to uncover about training dynamics of SFT, and we hope this is a useful data point. Joint work with co-authors @Sagar_Vaze @TiRune @y_m_asano Paper: arxiv.org/abs/2602.11149 Code: github.com/dkopi/data-rep…
arxiv.org
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Supervised fine-tuning (SFT) on chain-of-thought data is an essential post-training step for reasoning language models. Standard machine learning intuition suggests that training with more unique...
Dawid Kopiczko
@dawkopi
Feb 16
Common knowledge in ML: more unique training data → better generalization. Turns out this doesn't hold for long-CoT SFT. Under a fixed update budget, repeating a small dataset multiple times beats training on more unique samples. And it's not even close.