Files
aituner/runs/active-intervention-v0/trace13-results.json

152 lines
5.3 KiB
JSON

{
"schema": "active-intervention-trace13-result-summary-v0",
"status": "STOP_NO_PROSPECTIVE_GPU_COST_SIGNAL",
"provenance": {
"aituner_commit": "39b767e384fc49da53b99ad06a3e2ca1b6ac37d6",
"vllm_commit": "4b253fd8619764b6971a7f2e3a3aa7545f6ace05",
"manifest_sha256": "3bd25ae0ca040729a6351635f14447b3c789d4d86fb0fe4d65940735ad225a78",
"policy_sha256": "4f096d3a5f8c38771e956dfd576dd6cd5d5691286ab258028dbddbe07b20078c",
"decision_sha256": "86b7089151c480e18b5ae6ed65c4e4a3e11159dd0c16d5851312d4d9196d5ca2",
"controller_state_sha256": "d10d3cbe5ce20eacc1392f52e79d16ae23b5e15301123d5e85e48d53ae676cda",
"audit_sha256": "bd95b45e5d4cb93b5ad2f722b7dc96553d64eb8a5d5aae3a82f29c2d015fe3f6",
"remote_root": "/home/admin/cpfs/wjh/active-intervention-prospective-20260715"
},
"cost": {
"annotation_campaign_h20_hours": 5.0379046784506905,
"hard_cap_h20_hours": 6.0,
"outcome_only_cost_to_acceptable_h20_hours_lower_bound": 2.4284364508172893,
"telemetry_cost_to_acceptable_h20_hours_lower_bound": 2.4284364508172893,
"telemetry_gpu_cost_reduction_fraction": 0.0,
"session_h20_hours": {
"source_mns32_mbbt4096": 1.3566088432735868,
"mns64_mbbt4096": 1.256969277858734,
"mns32_mbbt8192": 1.254111782974667,
"joint_mns64_mbbt8192": 1.1702147743437026
}
},
"policy_comparison": {
"outcome_only": {
"measurement_cutoff_s": 300.0,
"selected_action": "joint",
"intervention_order": ["joint", "mns", "mbbt", "noop"]
},
"telemetry": {
"measurement_cutoff_s": 300.0,
"selected_action": "joint",
"intervention_order": ["joint", "mns", "mbbt", "noop"]
},
"action_changed": false,
"measurement_changed": false,
"confirmation_trigger": false,
"contribution_gate": false
},
"surface": {
"source_mns32_mbbt4096": {
"normalized_slo_goodput": [
0.40090909090909094,
0.3978787878787879,
0.42060606060606065
],
"median": 0.40090909090909094
},
"mns64_mbbt4096": {
"normalized_slo_goodput": [1.0, 0.9996969696969698, 1.0],
"median": 1.0
},
"mns32_mbbt8192": {
"normalized_slo_goodput": [
0.44393939393939397,
0.41515151515151516,
0.4260606060606061
],
"median": 0.42606060606060603
},
"joint_mns64_mbbt8192": {
"normalized_slo_goodput": [1.0, 1.0, 1.0],
"median": 1.0
}
},
"selected_checkpoint_prediction": {
"actual_median_effect": {
"noop": 0.0,
"mns": 0.5990909090909091,
"mbbt": 0.02515151515151509,
"joint": 0.5990909090909091
},
"outcome_only_predicted_effect": {
"noop": 0.0,
"mns": 0.2886250281729182,
"mbbt": 0.17933598309437812,
"joint": 0.3205015384324615
},
"telemetry_predicted_effect": {
"noop": 0.0,
"mns": 0.26117798146236215,
"mbbt": 0.09686132563074483,
"joint": 0.35190199346536294
},
"actual_joint_minus_mns": 0.0,
"outcome_only_joint_minus_mns": 0.0318765102595433,
"telemetry_joint_minus_mns": 0.09072401200300079
},
"engine_mechanism": {
"source_mns32_mbbt4096": {
"scheduler_records": 41086,
"waiting_fraction": 0.9312174463320839,
"mns_exclusive_fraction": 0.8536484447256973,
"mbbt_exclusive_fraction": 0.01114734946210388,
"both_fraction": 0.06642165214428272,
"running_utilization_mean": 0.9738878510928297,
"token_utilization_mean": 0.15694342925509905,
"kv_usage_mean": 0.027507593814715858,
"preemptions": 0
},
"mns64_mbbt4096": {
"scheduler_records": 37001,
"waiting_fraction": 0.053809356503878275,
"mns_exclusive_fraction": 0.0,
"mbbt_exclusive_fraction": 0.053809356503878275,
"running_utilization_mean": 0.5410364753655307,
"token_utilization_mean": 0.17425695631536986,
"kv_usage_mean": 0.030549112146415616,
"preemptions": 0
},
"mns32_mbbt8192": {
"scheduler_records": 41348,
"waiting_fraction": 0.9119425365192996,
"mns_exclusive_fraction": 0.9108542130211861,
"mbbt_exclusive_fraction": 0.0003627744993711909,
"running_utilization_mean": 0.9652567838831383,
"token_utilization_mean": 0.0779606414231039,
"kv_usage_mean": 0.027355900366122385,
"preemptions": 0
},
"joint_mns64_mbbt8192": {
"scheduler_records": 40416,
"waiting_fraction": 0.0088826207442597,
"mns_exclusive_fraction": 0.0,
"mbbt_exclusive_fraction": 0.0088826207442597,
"running_utilization_mean": 0.49403392220902614,
"token_utilization_mean": 0.07978070546782215,
"kv_usage_mean": 0.028003770774946098,
"preemptions": 0
}
},
"sanity": {
"surface_outcomes": {"n": 12, "min": 0.3978787878787879, "max": 1.0, "distinct_n": 8},
"session_h20_hours": {"n": 4, "min": 1.1702147743437026, "max": 1.3566088432735868, "distinct_n": 4},
"scheduler_records": {"n": 4, "min": 37001, "max": 41348, "distinct_n": 4},
"invariants": {
"controller_complete": true,
"four_sessions_complete": true,
"twelve_surface_outcomes": true,
"ratios_bounded": true,
"nonnegative_counts_and_costs": true,
"surface_not_all_identical": true,
"request_hashes_match": true,
"no_censored_runs": true
},
"red_flags": []
}
}