1 files changed, 128 insertions, 0 deletions
diff --git a/research/flossing/launch_trajectory_sampling_long.sh b/research/flossing/launch_trajectory_sampling_long.sh
new file mode 100755
index 0000000..4a03650
--- /dev/null
+++ b/research/flossing/launch_trajectory_sampling_long.sh
@@ -0,0 +1,128 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+CASE="${1:?case required}"
+GPU="${2:-0}"
+
+source /home/yurenh2/miniconda3/etc/profile.d/conda.sh
+conda activate rrm
+cd /home/yurenh2/rrm/research/flossing
+
+HRM_ROOT="/home/yurenh2/rrm/hrm/checkpoints/Sudoku-extreme-1k-aug-1000 ACT-torch/HierarchicalReasoningModel_ACTV1 righteous-python"
+TRM_ROOT="/home/yurenh2/rrm/trm/checkpoints/Sudoku-extreme-1k-aug-1000-ACT-torch/pretrain_mlp_t_sudoku_singleGPU"
+
+run_one() {
+  local tag="$1"
+  shift
+  echo "[$(date -Is)] START ${tag} on GPU ${GPU}"
+  CUDA_VISIBLE_DEVICES="${GPU}" python step9_trajectory_perturb_train.py "$@" \
+    > "${tag}.log" 2>&1
+  echo "[$(date -Is)] DONE ${tag}"
+}
+
+case "${CASE}" in
+  hrm_baseline50k)
+    run_one step9_E_hrm_baseline_parallel_fixed_26040_50k \
+      --model hrm \
+      --ckpt-root "${HRM_ROOT}" \
+      --ckpt-name step_26040 \
+      --mode baseline_clean \
+      --rollout-impl parallel_fixed \
+      --train-steps 50000 \
+      --batch-size 8 \
+      --lr 1e-5 \
+      --seed 42 \
+      --eval-every 2500 \
+      --eval-n 1024 \
+      --eval-batch-size 32 \
+      --save-best \
+      --save-final \
+      --save-every-eval \
+      --save-train-state \
+      --out step9_E_hrm_baseline_parallel_fixed_26040_50k.json
+    ;;
+
+  hrm_multi4_loguniform50k)
+    run_one step9_F_hrm_multi4_loguniform_ramp_26040_50k \
+      --model hrm \
+      --ckpt-root "${HRM_ROOT}" \
+      --ckpt-name step_26040 \
+      --mode multi_perturbed_ce \
+      --rollout-impl parallel_fixed \
+      --n-trajectories 4 \
+      --train-steps 50000 \
+      --batch-size 8 \
+      --lr 1e-5 \
+      --noise-std 0.001 \
+      --noise-min 0.00003 \
+      --noise-max 0.003 \
+      --noise-sampling loguniform \
+      --sigma-start 0 \
+      --sigma-ramp-steps 5000 \
+      --perturb both \
+      --seed 42 \
+      --eval-every 2500 \
+      --eval-n 1024 \
+      --eval-batch-size 32 \
+      --save-best \
+      --save-final \
+      --save-every-eval \
+      --save-train-state \
+      --out step9_F_hrm_multi4_loguniform_ramp_26040_50k.json
+    ;;
+
+  trm_baseline50k)
+    run_one step9_G_trm_baseline_parallel_fixed_26041_batch4_50k \
+      --model trm \
+      --ckpt-root "${TRM_ROOT}" \
+      --ckpt-name step_26041 \
+      --mode baseline_clean \
+      --rollout-impl parallel_fixed \
+      --train-steps 50000 \
+      --batch-size 4 \
+      --lr 1e-5 \
+      --seed 42 \
+      --eval-every 2500 \
+      --eval-n 1024 \
+      --eval-batch-size 32 \
+      --save-best \
+      --save-final \
+      --save-every-eval \
+      --save-train-state \
+      --out step9_G_trm_baseline_parallel_fixed_26041_batch4_50k.json
+    ;;
+
+  trm_multi4_loguniform50k)
+    run_one step9_H_trm_multi4_loguniform_ramp_26041_batch4_50k \
+      --model trm \
+      --ckpt-root "${TRM_ROOT}" \
+      --ckpt-name step_26041 \
+      --mode multi_perturbed_ce \
+      --rollout-impl parallel_fixed \
+      --n-trajectories 4 \
+      --train-steps 50000 \
+      --batch-size 4 \
+      --lr 1e-5 \
+      --noise-std 0.001 \
+      --noise-min 0.00003 \
+      --noise-max 0.003 \
+      --noise-sampling loguniform \
+      --sigma-start 0 \
+      --sigma-ramp-steps 5000 \
+      --perturb both \
+      --seed 42 \
+      --eval-every 2500 \
+      --eval-n 1024 \
+      --eval-batch-size 32 \
+      --save-best \
+      --save-final \
+      --save-every-eval \
+      --save-train-state \
+      --out step9_H_trm_multi4_loguniform_ramp_26041_batch4_50k.json
+    ;;
+
+  *)
+    echo "unknown case: ${CASE}" >&2
+    exit 2
+    ;;
+esac