File size: 220 Bytes
47ea602 | 1 2 3 4 5 6 7 | #!/usr/bin/env bash
# On the pod: stop the training run (torchrun + workers) and its pod_dmad.sh wrapper.
pkill -f "scripts/pod_dmad.sh"
pkill -f "rapid_moss.train"
sleep 5
pgrep -fa "rapid_moss.train" | head -3 || true
|