Files
jspace/scripts/jobs/zzz_x_kvmem.sh
T

14 lines
879 B
Bash

# gpuq-in: results-loop/star_data.json results-loop/gsm_cot_data.json results-loop/adapter_carrycot_b1_ii10_tjs50_00_p0_e200.pt
# gpuq-out: results-loop/eval_gsm_carrycot_b1_kvm*.json results-loop/train_carrycot_b1_ii10_kvm512_fm_p0_log.json results-loop/kvmem_carrycot_b1_ii10_kvm512_fm_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
A=$LOOP_OUT/adapter_carrycot_b1_ii10_tjs50_00_p0_e200.pt
$P train_carry_cot.py --drop-steps 1 --pause-per-step 0 --base-pauses 0 \
--inner-iters 10 --kvmem 512 --freeze-merge \
--warm-start $A --steps 200 --lr 1e-3
$P eval_carry_cot.py --adapter $A \
--kvmem $LOOP_OUT/kvmem_carrycot_b1_ii10_kvm512_fm_p0_e200.pt \
--tag gsm_carrycot_b1_kvm512 --grid 0:0,2:0 --n 256 --inner-iters 10