Significant-Gravitas
/
AutoGPT
mirror of https://github.com/Significant-Gravitas/AutoGPT.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Auto-GPT-20230718002209

pull/5155/head
Auto-GPT-Bot 2023-07-18 00:22:09 +00:00
parent ed5fd3416a
commit cf14609b51
1 changed files with 177 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

177
reports/Auto-GPT/file1_07-18-00-18.json Normal file
View File

@ -0,0 +1,177 @@
{
"command": "agbenchmark start",
"completion_time": "2023-07-18-00:22",
"metrics": {
"run_time": "239.83 seconds",
"highest_difficulty": "interface: 1"
},
"tests": {
"TestWriteFile": {
"data_path": "agbenchmark/challenges/interface/write_file",
"is_regression": false,
"metrics": {
"difficulty": "interface",
"success": true,
"success_%": 100.0,
"run_time": "35.666 seconds"
}
},
"TestBasicCodeGeneration": {
"data_path": "agbenchmark/challenges/code/d4",
"is_regression": false,
"metrics": {
"difficulty": "novice",
"success": false,
"fail_reason": "assert 1 in [0.0]",
"success_%": 0.0,
"run_time": "15.512 seconds"
}
},
"TestSearch": {
"data_path": "agbenchmark/challenges/interface/search",
"is_regression": false,
"metrics": {
"difficulty": "interface",
"success": false,
"fail_reason": "assert 1 in [0.0, 0.0]",
"success_%": 0.0,
"run_time": "126.148 seconds"
}
},
"TestReadFile": {
"data_path": "agbenchmark/challenges/interface/read_file",
"is_regression": false,
"metrics": {
"difficulty": "interface",
"success": false,
"fail_reason": "assert 1 in [0.0]",
"success_%": 0.0,
"run_time": "62.169 seconds"
}
},
"TestThreeSum": {
"data_path": "agbenchmark/challenges/code/d5",
"is_regression": false,
"metrics": {
"difficulty": "intermediate",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestThreeSum::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestBasicCodeGeneration::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestBasicRetrieval": {
"data_path": "agbenchmark/challenges/retrieval/r1",
"is_regression": false,
"metrics": {
"difficulty": "basic",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestBasicRetrieval::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestSearch::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestDebugSimpleTypoWithGuidance": {
"data_path": "agbenchmark/challenges/code/d1",
"is_regression": false,
"metrics": {
"difficulty": "basic",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithGuidance::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestReadFile::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestBasicMemory": {
"data_path": "agbenchmark/challenges/memory/m1",
"is_regression": false,
"metrics": {
"difficulty": "basic",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestBasicMemory::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestReadFile::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestRetrieval2": {
"data_path": "agbenchmark/challenges/retrieval/r2",
"is_regression": false,
"metrics": {
"difficulty": "novice",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRetrieval2::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestBasicRetrieval::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestCreateSimpleWebServer": {
"data_path": "agbenchmark/challenges/code/d3",
"is_regression": false,
"metrics": {
"difficulty": "advanced",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestCreateSimpleWebServer::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithGuidance::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestDebugSimpleTypoWithoutGuidance": {
"data_path": "agbenchmark/challenges/code/d2",
"is_regression": false,
"metrics": {
"difficulty": "novice",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithoutGuidance::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithGuidance::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestRememberMultipleIds": {
"data_path": "agbenchmark/challenges/memory/m2",
"is_regression": false,
"metrics": {
"difficulty": "novice",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIds::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestBasicMemory::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestRetrieval3": {
"data_path": "agbenchmark/challenges/retrieval/r3",
"is_regression": false,
"metrics": {
"difficulty": "intermediate",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRetrieval3::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRetrieval2::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestRememberMultipleIdsWithNoise": {
"data_path": "agbenchmark/challenges/memory/m3",
"is_regression": false,
"metrics": {
"difficulty": "intermediate",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIdsWithNoise::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIds::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
},
"TestRememberMultiplePhrasesWithNoise": {
"data_path": "agbenchmark/challenges/memory/m4",
"is_regression": false,
"metrics": {
"difficulty": "advanced",
"success": false,
"fail_reason": "venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultiplePhrasesWithNoise::test_method[challenge_data0] depends on venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIdsWithNoise::test_method[challenge_data0]",
"success_%": 0.0,
"run_time": "0.001 seconds"
}
}
},
"config": {
"workspace": "autogpt/workspace/auto_gpt_workspace"
}
}