Files
aituner/runs/intervention-response-v2/failed-three-load-controller-state-v2.json

50 lines
1.2 KiB
JSON

{
"completed_sessions": 0,
"failures": [
{
"failure": "TimeoutError('client timeout: tp4_mns16 high')",
"session": "rep1-mns16"
}
],
"gpu_hours_total": 1.3580546813540988,
"hard_cap_h20_hours": 8.0,
"schema": "intervention-response-phase-aware-pilot-state-v2",
"sessions": {
"rep1-mns16": {
"burnin": {
"elapsed_s": 64.469448031,
"feasible": false,
"pass_rate": 0.5137254901960784
},
"failure": "TimeoutError('client timeout: tp4_mns16 high')",
"gpu_hours": 1.3580546813540988,
"mns": 16,
"replicate": 1,
"runs": [
{
"early_stopped": false,
"elapsed_s": 301.114789132,
"feasible": true,
"level": "low",
"offered_req_s_per_gpu": 1.5,
"pass_rate": 1.0,
"selected_count": 1800
},
{
"early_stopped": false,
"elapsed_s": 313.040655133,
"feasible": false,
"level": "mid",
"offered_req_s_per_gpu": 2.125,
"pass_rate": 0.5631372549019608,
"selected_count": 2550
}
],
"started_at": 1784021277.1191542,
"status": "failed"
}
},
"started_at": 1784021276.8224819,
"status": "failed"
}