Harsh1729/MixtureVitaev2-100BT-cooldown-nemotron_sft_competitive_programming_v2

MixtureVitaev2-100BT-cooldown-nemotronsftcompetitiveprogrammingv2

One arm of a 30-arm cooldown-data ablation on top of Qwen3-1.7B-Base, part of the MixtureVitae v2 scaling-experiment suite. Branches from a shared MixtureVitae-v1 100BT WSD base checkpoint (step 19,378 of the 24,222-step schedule, ~80BT seen, end of the constant-LR phase), then anneals for the final ~20BT (4,844 steps, LR decaying linearly to zero) on the dataset described below. Every arm starts from the identical base and spends the same ~20BT cooldown budget, so eval differences reflect the cooldown data only.

• —Architecture: Qwen3-1.7B-Base (28L, hidden 2048, GQA 16q/8kv, head_dim 128, RMSNorm eps 1e-6, RoPE theta 1e6, QK-norm, no biases, tied embeddings)
• —Tokenizer: Qwen3 tokenizer (Qwen2 BPE, vocab 151936)
• —Cooldown dataset (this arm): nemotron_sft_competitive_programming_v2 — nemotronsftcompetitiveprogrammingv2 : 21.6
• —Upstream source: `nvidia/Nemotron-SFT-Competitive-Programming-v2`

Eval results

Open-sci language suite (11-task mean, 0-shot) + reasoning suite (gsm8k 4-shot exact-match strict; ifeval 0-shot inst-level-strict; MATH500 0-shot accuracy; LiveCodeBench 0-shot accuracy_avg). All values are percentages.

Full 30-arm comparison table and methodology: see the MixtureVitae v2 scaling-experiment writeup (LAION).