vh
265357efb2
Run 5 = the dependency-forcing corpus arm: airoboros-3.2 OUT of the 20% slot, govreport/clean-v1 (496) + qmsum/clean-v1 (97) IN, at run 4's lr 2e-04 with everything else held. kvasir byte-identical (survivors-r5 = survivors-r4 minus airoboros plus the two new roots whole). Operator authorized the launch to infra-ops directly; grant operator-2026-09-07-rnd-run5. Canonical copies of the config, launcher and survivors builder; runbook docs/runbooks/gx10-run-05.md. Launch gates all passed (7/7 root shas + shard hashes, survivor join 8,212 = recipe, holdout disjoint, window_count==1 on all 593 slot rows, realized [mix] slot loss 3.46% vs preregistered 3.4%). 524 steps. persistent-memory current-state updated: run 5 LAUNCHED + training.
73 lines
2.7 KiB
Bash
Executable File
73 lines
2.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Launch ERP-seat SFT run 5 on pfi-gx10 (NVIDIA GB10, aarch64, sm_121).
|
|
#
|
|
# Run this ON pfi-gx10 as infra-ops. It detaches the job from the invoking
|
|
# shell and logs to the box, so a reaped SSH session cannot take the run with
|
|
# it -- the failure mode that lost the first probe launch on 2026-09-01.
|
|
#
|
|
# Run 5 = the dependency-forcing slot: airoboros OUT, govreport + qmsum IN,
|
|
# everything else held. ~8,212 survivors -> ~520-525 optimizer steps.
|
|
# Checkpoints every 50 steps.
|
|
set -euo pipefail
|
|
|
|
ROOT=/home/infra-ops/erp-tune
|
|
HARNESS=$ROOT/eitri-smithy
|
|
VENV=/home/infra-ops/ml/.venv/bin/python
|
|
CONFIG=$ROOT/run-05-gx10.json
|
|
LOG=$ROOT/run-05.log
|
|
|
|
# --- Preconditions, asserted rather than assumed -----------------------------
|
|
|
|
# A stuck orphan holding unified memory while PyTorch reports zero allocated
|
|
# already doomed three relaunches on this box and got blamed on the new run
|
|
# each time. Assert the GPU is clear.
|
|
apps=$(nvidia-smi --query-compute-apps=pid --format=csv,noheader | tr -d '[:space:]')
|
|
if [ -n "$apps" ]; then
|
|
echo "REFUSING: GPU is not clear -- compute apps still resident:" >&2
|
|
nvidia-smi --query-compute-apps=pid,process_name,used_memory --format=csv >&2
|
|
exit 1
|
|
fi
|
|
|
|
# Deliberately NOT `pgrep -f erp_sft_harness`: run this over ssh and the
|
|
# pattern appears in the invoking shell's own argv, so the guard matches
|
|
# itself and refuses every launch. The pidfile is exact and cannot self-match;
|
|
# the GPU assertion above catches an orphan under any name.
|
|
if [ -f "$ROOT/run-05.pid" ] && kill -0 "$(cat "$ROOT/run-05.pid")" 2>/dev/null; then
|
|
echo "REFUSING: run-05.pid names a live process $(cat "$ROOT/run-05.pid"):" >&2
|
|
ps -p "$(cat "$ROOT/run-05.pid")" -o pid,etime,cmd >&2
|
|
exit 1
|
|
fi
|
|
|
|
if [ -e "$LOG" ]; then
|
|
echo "REFUSING: $LOG exists. Move it aside first so two runs cannot share a log." >&2
|
|
exit 1
|
|
fi
|
|
|
|
for p in "$HARNESS/erp_sft_harness/__main__.py" "$VENV" "$CONFIG"; do
|
|
[ -e "$p" ] || { echo "REFUSING: missing $p" >&2; exit 1; }
|
|
done
|
|
|
|
# Free space for checkpoints, with headroom.
|
|
avail=$(df --output=avail -BG "$ROOT" | tail -1 | tr -dc '0-9')
|
|
if [ "$avail" -lt 40 ]; then
|
|
echo "REFUSING: only ${avail}G free under $ROOT; want >=40G for checkpoints." >&2
|
|
exit 1
|
|
fi
|
|
|
|
# --- Launch ------------------------------------------------------------------
|
|
|
|
cd "$HARNESS"
|
|
{
|
|
echo "# launched $(date -Is) on $(hostname) by ${USER}"
|
|
echo "# harness $(git rev-parse --short HEAD) config $CONFIG"
|
|
} > "$LOG"
|
|
|
|
setsid nohup "$VENV" -m erp_sft_harness --config "$CONFIG" >> "$LOG" 2>&1 < /dev/null &
|
|
pid=$!
|
|
echo "$pid" > "$ROOT/run-05.pid"
|
|
|
|
echo "launched pid $pid -> $LOG"
|
|
echo
|
|
echo "watch: tail -f $LOG | tr '\\r' '\\n'"
|
|
echo "stop: kill \$(cat $ROOT/run-05.pid) # by PID -- never pkill -f over ssh"
|