François Fleuret: 'unnatural' training tweaks turned a disastrous run into a promising reasoning model
francoisfleuret · x · 2026-11-15
AI researcher François Fleuret says v1.1 of his small language model used a training procedure strictly identical to baseline, but for v1.4 he "did things some would consider unnatural."
He previously described the v1.4 run as a disaster—loss spikes everywhere, bad pre-training and SFT CE—but believes he has found a promising class of models for reasoning. Specific changes are not yet disclosed.
Related event: Fleuret's Small Model v1.4 Training Falters as FCA Models Top GSM8K(2 posts)→
More from Models
- After a week with Carbon: smarter than Opus 5.5, but the best workflow pairs both — rudrank · 2026-11-15
- User builds entire single-file project with Gemini — no libraries, no assets — fofrAI · 2026-11-15
- GPT-6.2 rumor timeline: the rumor was late, not the model — lxfater · 2026-11-15
- OpenAI falling-behind narrative 'massively exaggerated', claims insider: Astra still competitive with Opus 5.5 — haider1 · 2026-11-15
- EU's Open Model EUROPA Eyes ~1T Params, Per-GPU Throughput Up 14x — mawcopolow · 2026-11-15
- RNN memory is set by recurrent matrix eigenvalues — LRU's ring init fixes it — RobertTLange · 2026-11-15