PRoH/test_query.sh at main · zaixjun/PRoH · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
#!/bin/bash
set -euo pipefail

DATA_SOURCE="${1:-}"
PART="${2:-}"


if [[ -z "$DATA_SOURCE" ]]; then
  echo "Usage: $0 <data_source> [part]"
  exit 1
fi


PART_TAG="${PART:-orig}"
RUN_ROOT="results/${DATA_SOURCE}"
if [[ -n "$PART" ]]; then
  RUN_ROOT="results/${DATA_SOURCE}_${PART}"
fi
RUN_TS=$(date +"%Y%m%d-%H%M%S")
RUN_DIR="${RUN_ROOT}/${RUN_TS}"
mkdir -p "$RUN_DIR"

echo "Run directory: $RUN_DIR"

# -------------------------
# 1) Generation
# -------------------------
echo "Starting test for data_source: $DATA_SOURCE Part: ${PART_TAG}"
nohup python script_query.py \
  --data_source "$DATA_SOURCE" \
  --part "$PART" \
  --ts "$RUN_TS" \
  >> "$RUN_DIR/nohup.out" 2>&1
echo "QA finished for $DATA_SOURCE Part: ${PART_TAG}"


# -------------------------
# 2) Evaluation
# -------------------------
EVAL_LOG="$RUN_DIR/eval_score.out"
SUMMARY_LOG="$RUN_DIR/eval_summary.out"

echo "Starting evaluation for data_source: $DATA_SOURCE Part: ${PART_TAG}"

CUDA_VISIBLE_DEVICES=0
python eval/get_score.py \
  --data_source "$DATA_SOURCE" \
  --part "$PART" \
  --ts "$RUN_TS" \
  >> "$EVAL_LOG" 2>&1
python eval/see_score.py \
  --data_source "$DATA_SOURCE" \
  --part "$PART" \
  --ts "$RUN_TS" \
  >> "$SUMMARY_LOG" 2>&1


echo "Evaluation finished for $DATA_SOURCE Part: ${PART_TAG}"
echo "Logs:"
echo "  generation: $RUN_DIR/nohup.out"
echo "  eval score: $EVAL_LOG"
echo "  summary   : $SUMMARY_LOG"