#!/bin/bash
# FOUR-arm from-scratch reg study (FINDINGS 2026-07-03 verdict + the magic-s2000 hypothesis 2026-07-05):
#   arm0 abl_delay  — reg-FREE first 2000 steps then the proven pair (--reg_delay 2000).  Tests: the redx
#                     run (frozen jr 0.1, NO resreg) reached the stability EDGE by s2000 and that edge
#                     operator is the golden warm start; safe recipes over-damp early and plateau. If
#                     delay-then-leash reproduces an s2000-like operator from scratch, the magic ckpt
#                     becomes manufacturable.
#   arm1 abl_pair   — proven pair from step 0 (resreg 0.2 + FROZEN jr 0.1; ★2.09 recipe) = delay's control
#   arm2 abl_floss  — floss-only (graded finite-horizon LE penalty), --noadaptc (hidden damping feedback OFF)
#   arm3 abl_resreg — resreg-only, --noadaptc
# All arms share every other flag with the proven ep_resreg_scratch cmd (EP_BELOW210:97-101), same seed.
# Queue: poll GPUs 0/1/3 (GPU2 = japardi2 NV-Embed server, DO NOT TOUCH); a slot is free when
# mem.used < 38 GB AND util < 30% for 3 consecutive 60 s polls; launch the next arm per freed slot.
cd /home/yurenh2/ept/ep_run || exit 1
LOG=runs/abl3_queue.log
echo "[$(date)] queue runner v2 up (pid $$, 4 arms, delay-first)" >> "$LOG"

launch () {  # $1 = gpu id, $2 = arm index
  case $2 in
  0) CUDA_VISIBLE_DEVICES=$1 nohup python3 lt_ep_train.py --mode ep --attn_mode thick --B 24 --C 512 --H 16 --T 256 --c 1.0 --jacreg 0.1 --jr_floor 0.1 --jr_max 0.1 --resreg 0.2 --reg_delay 2000 --holo 2 --hr 0.02 --t2sel 40 --track --pema 0.999 --t1max 300 --res_est 1e-4 --res_gate 0 --qknorm --resinit 0.1 --warmup 800 --T1 150 --T2 20 --lr 6e-4 --wsd 0.25 --steps 32000 --log 200 --save_every 500 --abort_res 0.3 --data data/tinystories_bpe --ckpt runs/abl_delay.pt --state runs/abl_delay.state > runs/abl_delay.log 2>&1 &
     echo "[$(date)] abl_delay (reg-free 2k -> pair) -> GPU$1 pid $!" >> "$LOG" ;;
  1) CUDA_VISIBLE_DEVICES=$1 nohup python3 lt_ep_train.py --mode ep --attn_mode thick --B 24 --C 512 --H 16 --T 256 --c 1.0 --jacreg 0.1 --jr_floor 0.1 --jr_max 0.1 --resreg 0.2 --holo 2 --hr 0.02 --t2sel 40 --track --pema 0.999 --t1max 300 --res_est 1e-4 --res_gate 0 --qknorm --resinit 0.1 --warmup 800 --T1 150 --T2 20 --lr 6e-4 --wsd 0.25 --steps 32000 --log 200 --save_every 500 --abort_res 0.3 --data data/tinystories_bpe --ckpt runs/abl_pair.pt --state runs/abl_pair.state > runs/abl_pair.log 2>&1 &
     echo "[$(date)] abl_pair (proven pair, control) -> GPU$1 pid $!" >> "$LOG" ;;
  2) CUDA_VISIBLE_DEVICES=$1 nohup python3 lt_ep_train.py --mode ep --attn_mode thick --B 24 --C 512 --H 16 --T 256 --c 1.0 --jacreg 0 --resreg 0 --floss 0.2 --noadaptc --holo 2 --hr 0.02 --t2sel 40 --track --pema 0.999 --t1max 300 --res_est 1e-4 --res_gate 0 --qknorm --resinit 0.1 --warmup 800 --T1 150 --T2 20 --lr 6e-4 --wsd 0.25 --steps 32000 --log 200 --save_every 500 --abort_res 0.3 --data data/tinystories_bpe --ckpt runs/abl_floss.pt --state runs/abl_floss.state > runs/abl_floss.log 2>&1 &
     echo "[$(date)] abl_floss (floss-only, noadaptc) -> GPU$1 pid $!" >> "$LOG" ;;
  3) CUDA_VISIBLE_DEVICES=$1 nohup python3 lt_ep_train.py --mode ep --attn_mode thick --B 24 --C 512 --H 16 --T 256 --c 1.0 --jacreg 0 --resreg 0.2 --noadaptc --holo 2 --hr 0.02 --t2sel 40 --track --pema 0.999 --t1max 300 --res_est 1e-4 --res_gate 0 --qknorm --resinit 0.1 --warmup 800 --T1 150 --T2 20 --lr 6e-4 --wsd 0.25 --steps 32000 --log 200 --save_every 500 --abort_res 0.3 --data data/tinystories_bpe --ckpt runs/abl_resreg.pt --state runs/abl_resreg.state > runs/abl_resreg.log 2>&1 &
     echo "[$(date)] abl_resreg (resreg-only, noadaptc) -> GPU$1 pid $!" >> "$LOG" ;;
  esac
}

i=0
declare -A CNT USED
while [ $i -lt 4 ]; do
  for g in 0 1 3; do
    [ $i -ge 4 ] && break
    [ -n "${USED[$g]}" ] && continue
    read -r mem util <<< "$(nvidia-smi --query-gpu=memory.used,utilization.gpu --format=csv,noheader,nounits -i "$g" 2>/dev/null | awk -F',' '{gsub(/ /,""); print $1" "$2}')"
    if [ -n "$mem" ] && [ "$mem" -lt 38000 ] && [ "$util" -lt 30 ] 2>/dev/null; then
      CNT[$g]=$(( ${CNT[$g]:-0} + 1 ))
    else
      CNT[$g]=0
    fi
    if [ "${CNT[$g]:-0}" -ge 3 ]; then
      launch "$g" $i
      USED[$g]=1
      i=$((i + 1))
      sleep 120                                   # let nvidia-smi register the new job before next slot check
    fi
  done
  sleep 60
done
echo "[$(date)] all four arms launched — queue runner exiting" >> "$LOG"