#!/usr/bin/env bash # SUM Parts - look at the actual epoch lines, to check for interleaving or # a non-monotonic "best val miou" set -uo pipefail RUNROOT="$HOME/sum-parts/runs" D="${1:-$(cat "$RUNROOT/.latest" 2>/dev/null)}" LOG="$D/train.log" echo "run: $D" [ -f "$LOG" ] || { echo " no train.log"; exit 1; } echo echo "=== last 14 epoch lines ===" grep -aE 'Epoch [0-9]+ LR' "$LOG" | tail -14 echo echo "=== 'Find a better ckpt' events (last 8) ===" grep -aE 'Find a better ckpt' "$LOG" | tail -8 echo echo "=== how many distinct run_names wrote to this log ===" grep -aoE 'sumv2_triangle-train-pointnet-ngpus1-[0-9]{8}-[0-9]{6}-[A-Za-z0-9]+' "$LOG" \ | sort -u | sed 's/^/ /' echo echo "=== effective val_freq (Val: bars per epoch) ===" echo " epoch lines : $(grep -acE 'Epoch [0-9]+ LR' "$LOG")" echo " val passes : $(grep -aoc 'Val: 100%' "$LOG" 2>/dev/null || echo '?')" echo echo "=== processes ===" pgrep -af 'main.py --cfg' | awk '{print " pid " $1}' | head echo " count: $(pgrep -cf 'main.py --cfg')"