File size: 1,447 Bytes
246d201 |
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 |
#!/bin/bash
set -eo pipefail
source "evaluation/utils/version_control.sh"
MODEL_CONFIG=$1
COMMIT_HASH=$2
AGENT=$3
EVAL_LIMIT=$4
MAX_ITERATIONS=$5
NUM_WORKERS=$6
EVAL_IDS=$7
if [ -z "$NUM_WORKERS" ]; then
NUM_WORKERS=1
echo "Number of workers not specified, use default $NUM_WORKERS"
fi
checkout_eval_branch
if [ -z "$AGENT" ]; then
echo "Agent not specified, use default CodeActAgent"
AGENT="CodeActAgent"
fi
get_openhands_version
echo "AGENT: $AGENT"
echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
echo "MODEL_CONFIG: $MODEL_CONFIG"
EVAL_NOTE=$OPENHANDS_VERSION
# Default to NOT use unit tests.
if [ -z "$USE_UNIT_TESTS" ]; then
export USE_UNIT_TESTS=false
fi
echo "USE_UNIT_TESTS: $USE_UNIT_TESTS"
# If use unit tests, set EVAL_NOTE to the commit hash
if [ "$USE_UNIT_TESTS" = true ]; then
EVAL_NOTE=$EVAL_NOTE-w-test
fi
# export PYTHONPATH=evaluation/integration_tests:\$PYTHONPATH
COMMAND="poetry run python evaluation/integration_tests/run_infer.py \
--agent-cls $AGENT \
--llm-config $MODEL_CONFIG \
--max-iterations ${MAX_ITERATIONS:-10} \
--eval-num-workers $NUM_WORKERS \
--eval-note $EVAL_NOTE"
if [ -n "$EVAL_LIMIT" ]; then
echo "EVAL_LIMIT: $EVAL_LIMIT"
COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
fi
if [ -n "$EVAL_IDS" ]; then
echo "EVAL_IDS: $EVAL_IDS"
COMMAND="$COMMAND --eval-ids $EVAL_IDS"
fi
# Run the command
eval $COMMAND
|