14 lines
1.2 KiB
Bash
14 lines
1.2 KiB
Bash
# 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_x600.json results-loop/eval_gsm_carrycot_b1_pp30.json results-loop/train_carrycot_b1_x600_log.json results-loop/train_carrycot_b1_pp30_log.json results-loop/adapter_carrycot_b1_x600_*.pt results-loop/adapter_carrycot_b1_pp30_*.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
|
|
WARM=$LOOP_OUT/adapter_carrycot_e400.pt
|
|
# arm A (undertrain control): d=1, 3x the training, same 10 pauses
|
|
$P train_carry_cot.py --drop-steps 1 --warm-start $WARM --steps 600 --lr 3e-4 --tag-suffix _x600
|
|
$P eval_carry_cot.py --adapter $LOOP_OUT/adapter_carrycot_b1_x600_e600.pt --tag gsm_carrycot_b1_x600 --grid 0:0,2:12,2:16 --n 256
|
|
# arm B (pause-bandwidth control): d=1, same 200 steps, 3x the pauses
|
|
$P train_carry_cot.py --drop-steps 1 --warm-start $WARM --steps 200 --lr 3e-4 --pause-per-step 30 --tag-suffix _pp30
|
|
$P eval_carry_cot.py --adapter $LOOP_OUT/adapter_carrycot_b1_pp30_e200.pt --tag gsm_carrycot_b1_pp30 --grid 0:0,2:32,2:36 --n 256
|