Tag

#sft

Articles tagged "sft" — 5 entries.

Article №56 fine-tuning NeMo ~16 min read — synthesis of a two-day advisor build on one Spark
Machine that Builds Machines

The Refusal Floor Is Trainable — What a Frozen Curveball Proved About Prompts vs Weights

A 30B model with a hand-tuned prompt contract refused 3 of 9 adversarial pretexts and fabricated private-looking state 3 times. A 4B trained for 21 minutes refused 9 of 9. The bench that saw the difference was frozen before training — and that discipline is the whole method.

uses fieldkit.arenafieldkit.eval

Article №52 fine-tuning NeMo ~18 min read — synthesis of a multi-day greenfield-vertical build on one Spark
Machine that Builds Machines

The Gate Before the GPU — Deciding SFT vs RL vs RLVR Before You Spend the Run

Building Kepler — a numeric astrodynamics reasoner — from scratch on one Spark. The method choice (SFT vs RL vs RLVR) is decided by cheap gates before any GPU run: a base preflight, an SFT gate, and a Goldilocks headroom gate. A flawless RLVR run that changed nothing is the proof.

uses fieldkit.rlfieldkit.rewardfieldkit.eval

Article №44 fine-tuning NeMo ~16 hours wall (7h 34m Unsloth + 5h 38m NeMo + conversion + merge + probe)
Looking Beyond Spark

Two Trainers, One LoRA: NeMo Framework Beats Unsloth by 26% on a Patent-Strategist Fine-Tune

Same recipe, same R1-distilled base, same 5000-row patent corpus — once via Unsloth, once via NeMo Framework + Megatron-Bridge. NeMo finishes 26% faster and produces 44% longer patent-strategic chains. The cost is one YARN-defaults landmine and a stdout that lied for four hours.
Article №42 fine-tuning Foundation ~12 hours (2× 131-min trains + diagnosis)
Machine that Builds Machines

The Trainer Was Fine, the Corpus Wasn't: Three Misdiagnoses on a Patent-Specialist Fine-Tune

Five thousand rows of synthetic patent reasoning, two clean 131-minute LoRA trains, three rounds of confident diagnosis — and none of them found the bug. The bug was the corpus all along. A field report on the cheapest mistake to make on the Spark.
Article №32 fine-tuning NeMo ~3 days end-to-end (mostly waiting on rollouts)
Frontier Scout

ClawGym on Spark — A 7B Base, A LoRA Adapter, and the +15 pp the Adapter Earned

ClawGym shipped only a .github profile, so we built the substrate ourselves — persona task synth, sandbox harness, 200-task corpus, LoRA SFT, matched-base eval. The adapter earns +3.8 pp task pass and +15.0 pp per-assertion against its own base. The diagnostic is the lift.

uses fieldkit.nim