Giorgio Gilestro
e433e48860
Adds the "directed sex" operator (E10) the moe regime-flip pointed to: don't
commit to one a-priori blend — breed a population of recombinant offspring
(specialists merged at Dirichlet-sampled weights), score each on a held-out
validation split with the verifier, and keep the fittest, reported on a fresh
test split. Two breeding objectives: best-overall and best-worst-family.
src/llm/directed.py + kind llm_directed, reusing the cached specialists.
Result — refinements pay off in proportion to how far the uniform soup is from
optimal:
- 0.5B (soup dilutes): directed selection beats soup on the bred objective —
directed_overall 0.69 > soup 0.64; directed_balanced worst-family 0.37 > 0.26.
Riders: single-objective selection trades off the other axis (overall-breed
tanks lists to 0.17); a global blend still trails per-input routing (0.74).
- 7B (Imperial CX3, soup already composes to ceiling on near-saturated families,
strings/arith 1.00): directed ~= soup (0.868 ~ 0.873, marginally below via a
val/test overfit gap) — no fitter offspring to breed.
Through-line across all four LLM runs: "merge, don't average" and its refinements
(routing, directed selection) are weak-base / suboptimal-default phenomena — they
help at 0.5B and are inert at 7B. Honest limitation kept in the writeup: the 7B
families are near-saturated, which caps the headroom; a harder unsaturated
benchmark is the fair next test.
Also folds in the two llm_moe local manifest/config files missed in 8da0dac.
+3 directed unit tests (130 green). Results in results/llm_directed{,_hpc}/
(parquet gitignored).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
22 lines
991 B
Bash
22 lines
991 B
Bash
#!/bin/bash
|
|
# Directed sex (llm_directed) on an L40S (46 GB) — breed recombinant offspring + select on the verifier.
|
|
# Reuses the cached 7B specialist adapters (models/llm/spec_*) if present. Same env as the other LLM
|
|
# jobs (see hpc/README.md): uv sync --extra dev --extra neural --extra llm + pre-download the 7B base.
|
|
# submit: qsub hpc/llm_directed.pbs status: qstat -u $USER
|
|
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
|
|
#PBS -l walltime=02:00:00
|
|
#PBS -N lam_llm_directed
|
|
|
|
cd "$PBS_O_WORKDIR"
|
|
export HF_HOME="$EPHEMERAL/hf_cache"
|
|
export TOKENIZERS_PARALLELISM=false
|
|
export UV_CACHE_DIR="$EPHEMERAL/uvcache"
|
|
|
|
source .venv/bin/activate
|
|
nvidia-smi --query-gpu=name,memory.total,driver_version --format=csv,noheader
|
|
|
|
python -m llm.experiment configs/llm/directed_hpc.yaml
|
|
|
|
# results/llm_directed_hpc/ written in-place (parquet gitignored). Sync back to plot:
|
|
# rsync -avz hpc:'…/LamarckianAI/results/llm_directed_hpc/' results/llm_directed_hpc/
|
|
echo "done: $(date)"
|