Manuscript revision and pending experiment work, snapshot before restructuring
Clarity pass over the main text (36-item audit), Discussion rewrite and cut, acknowledgements, Souly et al. as ref 62, lettered SI panels, model section moved under Results; plus the untracked curriculum/society/compose/smol configs, runners, figures, stats and tests that the SI already cites. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
This commit is contained in:
parent
e4804adabc
commit
84124de143
450 changed files with 52813 additions and 1202 deletions
38
hpc/llm_7b_seeds.pbs
Executable file
38
hpc/llm_7b_seeds.pbs
Executable file
|
|
@ -0,0 +1,38 @@
|
|||
#!/bin/bash
|
||||
# Seeds 2-3 for the three single-seed 7B runs (manuscript review 2026-09-11): llm_merge_hpc
|
||||
# (Fisher-Muller), llm_moe_hard_hpc (union vs fusion, hard) and llm_directed_hard_hpc (directed
|
||||
# selection, hard). One element per seed; the hard pair stays sequential because directed reuses the
|
||||
# hard specialists moe trains (models/llm/spec_*_hard_s{seed}). Seed 1 took 8 + 24 min on one L40S.
|
||||
# Output lands in results/llm_<name>_hpc/s{seed}/ (seed 1 was moved to s1/).
|
||||
# submit: qsub hpc/llm_7b_seeds.pbs status: qstat -u $USER -t
|
||||
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
|
||||
#PBS -l walltime=01:30:00
|
||||
#PBS -N lam_7b_seeds
|
||||
#PBS -J 2-3
|
||||
|
||||
cd "$PBS_O_WORKDIR"
|
||||
export HF_HOME="$EPHEMERAL/hf_cache"
|
||||
export TOKENIZERS_PARALLELISM=false
|
||||
export UV_CACHE_DIR="$EPHEMERAL/uvcache"
|
||||
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
|
||||
|
||||
SEED=$PBS_ARRAY_INDEX
|
||||
source .venv/bin/activate
|
||||
nvidia-smi --query-gpu=name,memory.total,driver_version --format=csv,noheader
|
||||
echo "seed=$SEED start=$(date)"
|
||||
mkdir -p configs/llm/_gen
|
||||
|
||||
for NAME in merge moe_hard directed_hard; do
|
||||
CFG="configs/llm/_gen/${NAME}_hpc_s${SEED}.yaml"
|
||||
python - "$SEED" "$NAME" "$CFG" <<'PYEOF'
|
||||
import sys, yaml
|
||||
seed, name, out = int(sys.argv[1]), sys.argv[2], sys.argv[3]
|
||||
cfg = yaml.safe_load(open(f"configs/llm/{name}_hpc.yaml"))
|
||||
cfg["seed"] = seed
|
||||
cfg["output"] = {"dir": f"results/llm_{name}_hpc/s{seed}"}
|
||||
yaml.safe_dump(cfg, open(out, "w"), sort_keys=False)
|
||||
PYEOF
|
||||
echo "== $NAME seed=$SEED $(date)"
|
||||
python -m llm.experiment "$CFG"
|
||||
done
|
||||
echo "done: $(date)"
|
||||
Loading…
Add table
Add a link
Reference in a new issue