89 lines
2.4 KiB
JSON
89 lines
2.4 KiB
JSON
{
|
|
"tasks": 30,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0.06666666666666667,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 4.832371773001796,
|
|
"latency_p95_seconds": 15.41486109450052,
|
|
"statuses": {
|
|
"budget_exhausted": 17,
|
|
"completed": 13
|
|
},
|
|
"total_tool_errors": 22,
|
|
"total_invalid_actions": 37,
|
|
"mean_rounds": 5.366666666666666,
|
|
"mean_tool_calls": 4.7,
|
|
"total_input_tokens": 376239,
|
|
"total_output_tokens": 9038,
|
|
"mean_returned_chars": 592.6,
|
|
"per_repository": {
|
|
"requests": {
|
|
"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": 4.516331323498889,
|
|
"latency_p95_seconds": 7.343977602400628,
|
|
"statuses": {
|
|
"budget_exhausted": 6,
|
|
"completed": 4
|
|
},
|
|
"total_tool_errors": 12,
|
|
"total_invalid_actions": 11,
|
|
"mean_rounds": 5.5,
|
|
"mean_tool_calls": 5,
|
|
"total_input_tokens": 117586,
|
|
"total_output_tokens": 1738,
|
|
"mean_returned_chars": 502.5
|
|
},
|
|
"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": 4.9962479714995425,
|
|
"latency_p95_seconds": 16.429801569399206,
|
|
"statuses": {
|
|
"budget_exhausted": 6,
|
|
"completed": 4
|
|
},
|
|
"total_tool_errors": 3,
|
|
"total_invalid_actions": 18,
|
|
"mean_rounds": 5.3,
|
|
"mean_tool_calls": 4.1,
|
|
"total_input_tokens": 134717,
|
|
"total_output_tokens": 3817,
|
|
"mean_returned_chars": 478.8
|
|
},
|
|
"click": {
|
|
"tasks": 10,
|
|
"target_hit_rate": 0,
|
|
"file_hit_rate": 0,
|
|
"macro_line_precision": 0.0,
|
|
"macro_line_recall": 0.0,
|
|
"macro_line_f1": 0.0,
|
|
"latency_median_seconds": 4.9123027345012815,
|
|
"latency_p95_seconds": 14.853568369802815,
|
|
"statuses": {
|
|
"budget_exhausted": 5,
|
|
"completed": 5
|
|
},
|
|
"total_tool_errors": 7,
|
|
"total_invalid_actions": 8,
|
|
"mean_rounds": 5.3,
|
|
"mean_tool_calls": 5,
|
|
"total_input_tokens": 123936,
|
|
"total_output_tokens": 3483,
|
|
"mean_returned_chars": 796.5
|
|
}
|
|
},
|
|
"sampled_peak_gpu_memory_mib": 1213,
|
|
"gpu_sampling_interval_seconds": 1
|
|
}
|