15 lines
906 B
Bash
15 lines
906 B
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_ii*.json results-loop/train_carrycot_b1_lt03_ii10_p0_log.json results-loop/adapter_carrycot_b1_lt03_ii10_p0_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
|
|
$P train_carry_cot.py --drop-steps 1 --pause-per-step 0 --base-pauses 0 \
|
|
--inner-iters 10 --lensteach 0.3 \
|
|
--warm-start $LOOP_OUT/adapter_carrycot_e400.pt --steps 200 --lr 3e-4
|
|
A=$LOOP_OUT/adapter_carrycot_b1_lt03_ii10_p0_e200.pt
|
|
$P eval_carry_cot.py --adapter $A --tag gsm_carrycot_b1_ii10 \
|
|
--grid 0:0,2:0 --n 256 --inner-iters 10
|
|
$P eval_carry_cot.py --adapter $A --tag gsm_carrycot_b1_ii10_ablate \
|
|
--grid 2:0 --n 256 --inner-iters 0
|