#!/bin/bash
# Step 6: Preflossing experiments from step_13020 (epoch 10K, chaos onset)
# Baseline = original HRM training curve (already have 10 ckpts)
# Two conditions:
#   B: Engelken prefloss (500 steps Σλ_i²) → task training 3000 steps
#   C: CF prefloss (500 steps Σmax(0,λ_i)²) → task training 3000 steps
set -e
cd /home/yurenh2/rrm/research/flossing
source /home/yurenh2/miniconda3/etc/profile.d/conda.sh
conda activate rrm
export CUDA_VISIBLE_DEVICES=0

CKPT_ROOT="/home/yurenh2/rrm/hrm/checkpoints/Sudoku-extreme-1k-aug-1000 ACT-torch/HierarchicalReasoningModel_ACTV1 righteous-python"
SRC_CKPT="step_13020"

echo "[$(date '+%H:%M:%S')] Starting step6 prefloss experiments" >> step6_runner.log

# B: Engelken prefloss (Σλ_i², two-sided)
echo "[$(date '+%H:%M:%S')] Starting B (engelken prefloss)" >> step6_runner.log
python step6_prefloss.py \
  --ckpt-root "$CKPT_ROOT" --ckpt-name "$SRC_CKPT" \
  --prefloss-steps 500 --train-steps 3000 \
  --floss-mode engelken --floss-lr 1e-4 --train-lr 1e-5 \
  --batch-size 8 --k-lyap 2 --lyap-act-steps 16 \
  --eval-every 100 --eval-n 512 --eval-batch-size 32 \
  --out step6_B_engelken.json > step6_B.log 2>&1
echo "[$(date '+%H:%M:%S')] B done" >> step6_runner.log

# C: CF prefloss (Σmax(0,λ_i)², one-sided hinge)
echo "[$(date '+%H:%M:%S')] Starting C (CF prefloss)" >> step6_runner.log
python step6_prefloss.py \
  --ckpt-root "$CKPT_ROOT" --ckpt-name "$SRC_CKPT" \
  --prefloss-steps 500 --train-steps 3000 \
  --floss-mode cf --floss-lr 1e-4 --train-lr 1e-5 \
  --batch-size 8 --k-lyap 2 --lyap-act-steps 16 \
  --eval-every 100 --eval-n 512 --eval-batch-size 32 \
  --out step6_C_cf.json > step6_C.log 2>&1
echo "[$(date '+%H:%M:%S')] C done" >> step6_runner.log

echo "[$(date '+%H:%M:%S')] All step6 prefloss experiments complete" >> step6_runner.log