88 lines
2.4 KiB
JSON
88 lines
2.4 KiB
JSON
{
|
|
"tasks": 30,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0.26666666666666666,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 19.395455925499846,
|
|
"latency_p95_seconds": 39.98146147420266,
|
|
"statuses": {
|
|
"completed": 25,
|
|
"budget_exhausted": 5
|
|
},
|
|
"total_tool_errors": 14,
|
|
"total_invalid_actions": 13,
|
|
"mean_rounds": 3.8666666666666667,
|
|
"mean_tool_calls": 3.6,
|
|
"total_input_tokens": 304404,
|
|
"total_output_tokens": 3579,
|
|
"mean_returned_chars": 1342.1333333333334,
|
|
"per_repository": {
|
|
"requests": {
|
|
"tasks": 10,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0.5,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 18.327982628001337,
|
|
"latency_p95_seconds": 34.40433353035005,
|
|
"statuses": {
|
|
"completed": 8,
|
|
"budget_exhausted": 2
|
|
},
|
|
"total_tool_errors": 3,
|
|
"total_invalid_actions": 4,
|
|
"mean_rounds": 3.6,
|
|
"mean_tool_calls": 3.4,
|
|
"total_input_tokens": 95640,
|
|
"total_output_tokens": 1089,
|
|
"mean_returned_chars": 953.9
|
|
},
|
|
"flask": {
|
|
"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": 19.156648668500566,
|
|
"latency_p95_seconds": 38.20192200995334,
|
|
"statuses": {
|
|
"completed": 7,
|
|
"budget_exhausted": 3
|
|
},
|
|
"total_tool_errors": 7,
|
|
"total_invalid_actions": 6,
|
|
"mean_rounds": 4.2,
|
|
"mean_tool_calls": 3.9,
|
|
"total_input_tokens": 109394,
|
|
"total_output_tokens": 1297,
|
|
"mean_returned_chars": 1286
|
|
},
|
|
"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": 21.76824945649787,
|
|
"latency_p95_seconds": 42.4032184362477,
|
|
"statuses": {
|
|
"completed": 10
|
|
},
|
|
"total_tool_errors": 4,
|
|
"total_invalid_actions": 3,
|
|
"mean_rounds": 3.8,
|
|
"mean_tool_calls": 3.5,
|
|
"total_input_tokens": 99370,
|
|
"total_output_tokens": 1193,
|
|
"mean_returned_chars": 1786.5
|
|
}
|
|
},
|
|
"sampled_peak_gpu_memory_mib": 2376,
|
|
"gpu_sampling_interval_seconds": 1
|
|
}
|