ineqmath/scripts/run_dev_data_gemini.sh at main · lupantech/ineqmath · 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
############## Configurations ###############
ENGINES=(
    "gemini-2.5-pro"
    "gemini-2.5-pro-preview-06-05"
    "gemini-2.5-pro-preview-05-06"
    "gemini-2.5-flash"
    "gemini-2.5-flash-preview-05-20"
    "gemini-2.5-flash-lite-preview-06-17"
    # You can add more models here
)
TOKENS=10000
SPLIT=dev
OUTPUT_PATH="../../results/models_results_${SPLIT}_data/"
MAX_WORKERS=16

############## Run the model ###############
# Change working directory to utils
cd ../models/utils

# Loop through each engine
for LLM in "${ENGINES[@]}"; do
    echo "Running tests for engine: $LLM"

    LABEL=${LLM}_tokens_${TOKENS}

    python solve.py \
    --data_path ../../data/json/${SPLIT}.json\
    --split $SPLIT\
    --output_path $OUTPUT_PATH\
    --llm_engine_name $LLM \
    --run_label $LABEL \
    --use_cache \
    --max_workers $MAX_WORKERS \
    --max_tokens $TOKENS \
    --test_num -1

    python generate_results.py \
    --result_dir $OUTPUT_PATH\
    --run_label $LABEL \
    --use_cache \
    --max_workers $MAX_WORKERS

    python compute_score.py \
    --result_dir $OUTPUT_PATH \
    --run_label $LABEL \
    --use_cache \
    --max_workers $MAX_WORKERS

    echo "Completed tests for engine: $LLM"
    echo "----------------------------------------"
done