68 lines
1.7 KiB
JSON
68 lines
1.7 KiB
JSON
{
|
|
"metadata": {
|
|
"model": "meta-llama/llama3-70b-instruct",
|
|
"model_provider": "mock",
|
|
"timestamp": "2026-04-29T21:58:18.864353",
|
|
"report_version": "3.0"
|
|
},
|
|
"statistics": {
|
|
"per_capability": {
|
|
"mini_standard": {
|
|
"capability": "mini (standard)",
|
|
"total_runs": 3,
|
|
"validated_runs": 3,
|
|
"success_runs": 0,
|
|
"failed_runs": 3,
|
|
"exception_runs": 0,
|
|
"no_validation_runs": 0,
|
|
"success_rate": 0.0,
|
|
"success_rate_std": 0.0,
|
|
"success_rate_sem": 0.0,
|
|
"pass_at_k": 0,
|
|
"pass_at_k_percent": 0.0,
|
|
"pass_k": 0,
|
|
"pass_k_percent": 0.0,
|
|
"total_scenarios": 1,
|
|
"avg_run_duration": 0.0,
|
|
"avg_run_duration_std": 0.0
|
|
}
|
|
},
|
|
"global": {
|
|
"total_runs": 3,
|
|
"validated_runs": 3,
|
|
"success_runs": 0,
|
|
"failed_runs": 3,
|
|
"exception_runs": 0,
|
|
"no_validation_runs": 0,
|
|
"pass_at_k": 0,
|
|
"pass_at_k_percent": 0.0,
|
|
"pass_k": 0,
|
|
"pass_k_percent": 0.0,
|
|
"total_scenarios": 1,
|
|
"macro_success_rate": 0.0,
|
|
"macro_success_rate_std": 0.0,
|
|
"macro_success_rate_sem": 0.0,
|
|
"micro_success_rate": 0.0,
|
|
"micro_success_rate_std": 0.0,
|
|
"micro_success_rate_sem": 0.0,
|
|
"avg_run_duration": 0.0,
|
|
"avg_run_duration_std": 0.0,
|
|
"job_duration": 31.784090518951416
|
|
}
|
|
},
|
|
"run_configurations": [
|
|
{
|
|
"phase_name": "standard",
|
|
"config": "mini",
|
|
"a2a_app_prop": "0.0",
|
|
"has_tool_augmentation": "False",
|
|
"has_env_events": "False",
|
|
"total_runs": 3,
|
|
"validated_runs": 3,
|
|
"success_runs": 0,
|
|
"failed_runs": 3,
|
|
"exception_runs": 0,
|
|
"no_validation_runs": 0
|
|
}
|
|
]
|
|
} |