89 lines
2.4 KiB
JSON
89 lines
2.4 KiB
JSON
{
|
|
"tasks": 30,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0.13333333333333333,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 16.385701761500968,
|
|
"latency_p95_seconds": 54.43225493735008,
|
|
"statuses": {
|
|
"budget_exhausted": 17,
|
|
"completed": 13
|
|
},
|
|
"total_tool_errors": 16,
|
|
"total_invalid_actions": 53,
|
|
"mean_rounds": 5.233333333333333,
|
|
"mean_tool_calls": 4.033333333333333,
|
|
"total_input_tokens": 361812,
|
|
"total_output_tokens": 7292,
|
|
"mean_returned_chars": 224.76666666666668,
|
|
"per_repository": {
|
|
"requests": {
|
|
"tasks": 10,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0.2,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 17.27006782099852,
|
|
"latency_p95_seconds": 21.234492207000223,
|
|
"statuses": {
|
|
"budget_exhausted": 6,
|
|
"completed": 4
|
|
},
|
|
"total_tool_errors": 10,
|
|
"total_invalid_actions": 12,
|
|
"mean_rounds": 5.6,
|
|
"mean_tool_calls": 5,
|
|
"total_input_tokens": 149348,
|
|
"total_output_tokens": 1865,
|
|
"mean_returned_chars": 259.1
|
|
},
|
|
"flask": {
|
|
"tasks": 10,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0.1,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 14.9863461620007,
|
|
"latency_p95_seconds": 57.56604749939506,
|
|
"statuses": {
|
|
"completed": 4,
|
|
"budget_exhausted": 6
|
|
},
|
|
"total_tool_errors": 3,
|
|
"total_invalid_actions": 29,
|
|
"mean_rounds": 5,
|
|
"mean_tool_calls": 2.7,
|
|
"total_input_tokens": 107622,
|
|
"total_output_tokens": 2444,
|
|
"mean_returned_chars": 348.9
|
|
},
|
|
"click": {
|
|
"tasks": 10,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0.1,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 16.385701761500968,
|
|
"latency_p95_seconds": 54.43225493735008,
|
|
"statuses": {
|
|
"budget_exhausted": 5,
|
|
"completed": 5
|
|
},
|
|
"total_tool_errors": 3,
|
|
"total_invalid_actions": 12,
|
|
"mean_rounds": 5.1,
|
|
"mean_tool_calls": 4.4,
|
|
"total_input_tokens": 104842,
|
|
"total_output_tokens": 2983,
|
|
"mean_returned_chars": 66.3
|
|
}
|
|
},
|
|
"sampled_peak_gpu_memory_mib": 2198,
|
|
"gpu_sampling_interval_seconds": 1
|
|
}
|