From 66e0d8b9fd4d0f7a2231d689c055e26fdf1cf04a Mon Sep 17 00:00:00 2001
From: YurenHao0426 <blackhao0426@gmail.com>
Date: Sat, 13 Jun 2026 12:35:36 -0500
Subject: rrm workspace: TRM/HRM/SRM code, Maze dataset, dynamical-analysis
 pipeline

Curated export for clone-and-run Maze training (2x A6000) + diagnostics.
trm/hrm pretrain.py carry trajectory-augmentation code (backward-compatible).
Heavy artifacts (checkpoints/wandb/npz) gitignored; see PROVENANCE.md.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---
 .../flossing/launch_hrm_multi4_perturb_ablation.sh | 60 ++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100755 research/flossing/launch_hrm_multi4_perturb_ablation.sh

(limited to 'research/flossing/launch_hrm_multi4_perturb_ablation.sh')

diff --git a/research/flossing/launch_hrm_multi4_perturb_ablation.sh b/research/flossing/launch_hrm_multi4_perturb_ablation.sh
new file mode 100755
index 0000000..07fba63
--- /dev/null
+++ b/research/flossing/launch_hrm_multi4_perturb_ablation.sh
@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+CASE="${1:?case required: h | l | joint | all}"
+GPU="${2:-0}"
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+run_case() {
+  local perturb="$1"
+  local suffix="$2"
+
+  source /home/yurenh2/miniconda3/etc/profile.d/conda.sh
+  conda activate rrm
+
+  cd /home/yurenh2/rrm/hrm
+  export WANDB_MODE=offline
+  export CUDA_VISIBLE_DEVICES="${GPU}"
+
+  python pretrain.py \
+    data_path=/home/yurenh2/rrm/data/sudoku-extreme-1k-aug-1000 \
+    +project_name='Sudoku-extreme-1k-aug-1000 ACT-torch' \
+    +run_name="HierarchicalReasoningModel_ACTV1 multi4-loguniform-${suffix}-repro" \
+    +checkpoint_path="checkpoints/Sudoku-extreme-1k-aug-1000 ACT-torch/HierarchicalReasoningModel_ACTV1 multi4-loguniform-${suffix}-repro" \
+    epochs=20000 eval_interval=2000 checkpoint_every_eval=true \
+    global_batch_size=768 \
+    lr=0.0001 lr_min_ratio=1.0 lr_warmup_steps=2000 \
+    beta1=0.9 beta2=0.95 weight_decay=1.0 \
+    puzzle_emb_lr=0.0001 puzzle_emb_weight_decay=1.0 \
+    +trajectory_augment=true \
+    +trajectory_n=4 \
+    +trajectory_noise_std=0.001 \
+    +trajectory_noise_min=0.00003 \
+    +trajectory_noise_max=0.003 \
+    +trajectory_noise_sampling=loguniform \
+    +trajectory_sigma_start=0.0 \
+    +trajectory_sigma_ramp_steps=5000 \
+    +trajectory_perturb="${perturb}"
+}
+
+case "${CASE}" in
+  h)
+    run_case h honly
+    ;;
+  l)
+    run_case l lonly
+    ;;
+  joint)
+    run_case joint jointnorm
+    ;;
+  all)
+    bash "${SCRIPT_DIR}/launch_hrm_multi4_perturb_ablation.sh" h "${GPU}"
+    bash "${SCRIPT_DIR}/launch_hrm_multi4_perturb_ablation.sh" l "${GPU}"
+    bash "${SCRIPT_DIR}/launch_hrm_multi4_perturb_ablation.sh" joint "${GPU}"
+    ;;
+  *)
+    echo "unknown case: ${CASE}" >&2
+    exit 2
+    ;;
+esac
-- 
cgit v1.2.3