31 lines
823 B
JSON
31 lines
823 B
JSON
|
{
|
||
|
|
"command": "agbenchmark start --test TestRetrieval2.1",
|
||
|
|
"completion_time": "2023-07-17-14:03",
|
||
|
|
"metrics": {
|
||
|
|
"run_time": "68.39 seconds",
|
||
|
|
"highest_difficulty": "No successful tests"
|
||
|
|
},
|
||
|
|
"tests": {
|
||
|
|
"TestRetrieval2.1": {
|
||
|
|
"data_path": "agbenchmark/challenges/retrieval/r2.1_specific",
|
||
|
|
"is_regression": false,
|
||
|
|
"reached_cutoff": true,
|
||
|
|
"answer": "It was $81.462 billion in 2022.",
|
||
|
|
"description": "This one checks the accuracy of the information over r2",
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "novice",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "assert 1 in []",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "68.15 seconds"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"workspace": "${os.path.join(Path.home(), 'miniagi')}"
|
||
|
|
},
|
||
|
|
"additional": {
|
||
|
|
"model": "gpt-4"
|
||
|
|
}
|
||
|
|
}
|