item 29 pre-registered (Nils's design): trajectory teacher-forcing — 10 waypoint transitions supervised independently (T[i-1]→T[i]), TF and TF+FR arms; job 1 d=1 step-span, job 2 answer-only full-CoT span

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Nils
2026-07-17 10:34:44 +02:00
co-authored by Claude Fable 5
parent deae500ad0
commit f1e6a628eb
4 changed files with 194 additions and 21 deletions
+15
View File
@@ -0,0 +1,15 @@
# gpuq-in: results-loop/star_data.json results-loop/gsm_cot_data.json results-loop/adapter_carrycot_e400.pt
# gpuq-out: results-loop/eval_gsm_carrycot_b1_tj*.json results-loop/train_carrycot_b1_*tj*_log.json results-loop/adapter_carrycot_b1_*tj*_e200.pt
git pull origin main -q 2>/dev/null
P=/home/nils/jspace/.venv/bin/python
export JLENS_MODEL=google/gemma-4-E2B-it LOOP_OUT=/home/nils/jspace/results-loop
cd /home/nils/jspace/scripts
for FR in 0.0 5.0; do
T=tjs50_$(echo $FR | tr -d .)
$P train_carry_cot.py --drop-steps 1 --traj-span step --traj-tf 5.0 --traj-fr $FR \
--pause-per-step 0 --base-pauses 0 --inner-iters 10 \
--warm-start $LOOP_OUT/adapter_carrycot_e400.pt --steps 200 --lr 3e-4
A=$LOOP_OUT/adapter_carrycot_b1_ii10_${T}_p0_e200.pt
$P eval_carry_cot.py --adapter $A --tag gsm_carrycot_b1_$T --grid 0:0,2:0 --n 256 --inner-iters 10
$P eval_carry_cot.py --adapter $A --tag gsm_carrycot_b1_${T}_ablate --grid 2:0 --n 256 --inner-iters 0
done
+15
View File
@@ -0,0 +1,15 @@
# gpuq-in: results-loop/star_data.json results-loop/gsm_cot_data.json results-loop/adapter_carrycot_e400.pt
# gpuq-out: results-loop/eval_gsm_carrycot_b99_tj*.json results-loop/train_carrycot_b99_*tj*_log.json results-loop/adapter_carrycot_b99_*tj*_e200.pt
git pull origin main -q 2>/dev/null
P=/home/nils/jspace/.venv/bin/python
export JLENS_MODEL=google/gemma-4-E2B-it LOOP_OUT=/home/nils/jspace/results-loop
cd /home/nils/jspace/scripts
for FR in 0.0 5.0; do
T=tjf50_$(echo $FR | tr -d .)
$P train_carry_cot.py --drop-steps 99 --traj-span full --traj-tf 5.0 --traj-fr $FR \
--pause-per-step 0 --base-pauses 0 --inner-iters 10 \
--warm-start $LOOP_OUT/adapter_carrycot_e400.pt --steps 200 --lr 3e-4
A=$LOOP_OUT/adapter_carrycot_b99_ii10_${T}_p0_e200.pt
$P eval_carry_cot.py --adapter $A --tag gsm_carrycot_b99_$T --grid 0:0,2:0 --n 256 --inner-iters 10
$P eval_carry_cot.py --adapter $A --tag gsm_carrycot_b99_${T}_ablate --grid 2:0 --n 256 --inner-iters 0
done