mini-agi-20230801081448

This commit is contained in:
Auto-GPT-Bot
2023-08-01 08:14:48 +00:00
parent 2cd4ffcd90
commit 4425ed6655
3 changed files with 71 additions and 52 deletions

View File

@@ -0,0 +1,13 @@
{
"command": "agbenchmark start",
"completion_time": "2023-08-01-08:14",
"benchmark_start_time": "2023-08-01-08:14",
"metrics": {
"run_time": "20.63 seconds",
"highest_difficulty": "No successful tests"
},
"tests": {},
"config": {
"workspace": "${os.path.join(Path.home(), 'miniagi')}"
}
}

View File

@@ -1 +1,6 @@
{}
{
"TestWriteFile": {
"difficulty": "interface",
"data_path": "agbenchmark/challenges/interface/write_file/data.json"
}
}

View File

@@ -1,64 +1,35 @@
{
"TestPlanCreation": [
true,
true
],
"TestWriteFile": [
true,
true
],
"TestGoalDivergence": [
"TestAdaptLink": [
false
],
"TestSearch": [
"TestAdaptSimpleTypoWithGuidance": [
true
],
"TestReadFile": [
true
],
"TestBasicRetrieval": [
true
"TestAdaptTeslaRevenue": [
false
],
"TestBasicContentGen": [
true
],
"TestReturnCode_Simple": [
false
],
"TestDebugSimpleTypoWithGuidance": [
true
],
"TestBasicMemory": [
false
],
"TestAdaptLink": [
false
],
"TestRevenueRetrieval_1.2": [
false
],
"TestRevenueRetrieval_1.1": [
false
],
"TestRevenueRetrieval_1.0": [
"TestBasicRetrieval": [
true
],
"TestReturnCode_Write": [
false
"TestDebugMultipleTypo": [
true
],
"TestDebugSimpleTypoWithGuidance": [
true
],
"TestDebugSimpleTypoWithoutGuidance": [
true
],
"TestAdaptSimpleTypoWithGuidance": [
true
],
"TestInstructionFollowing": [
"TestFunctionCodeGeneration": [
false
],
"TestGoalLoss_Simple": [
false
],
"TestGoalLoss_advanced": [
"TestGoalDivergence": [
false
],
"TestGoalLoss_Hard": [
@@ -67,34 +38,64 @@
"TestGoalLoss_Medium": [
false
],
"TestGoalLoss_Simple": [
false
],
"TestGoalLoss_advanced": [
false
],
"TestInstructionFollowing": [
false
],
"TestPlanCreation": [
true,
true
],
"TestReadFile": [
true
],
"TestRememberMultipleIds": [
false
],
"TestFunctionCodeGeneration": [
"TestRememberMultiplePhrasesWithNoise": [
false
],
"TestReturnCode_Modify": [
false
],
"TestDebugMultipleTypo": [
true
],
"TestRememberMultipleWithNoise": [
false
],
"TestRetrieval3": [
false
],
"TestAdaptTeslaRevenue": [
"TestReturnCode_Modify": [
false
],
"TestThreeSum": [
"TestReturnCode_Simple": [
false
],
"TestReturnCode_Tests": [
false
],
"TestRememberMultiplePhrasesWithNoise": [
"TestReturnCode_Write": [
false
],
"TestRevenueRetrieval_1.0": [
true
],
"TestRevenueRetrieval_1.1": [
false
],
"TestRevenueRetrieval_1.2": [
false
],
"TestSearch": [
true
],
"TestThreeSum": [
false
],
"TestWriteFile": [
true,
true,
true
]
}