state: generation 9816 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T13:20:00.692050+00:00",
|
||||
"generatedAt": "2026-09-19T13:22:53.701373+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 716,
|
||||
"listingErrors": 717,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T13:20:00.668369+00:00",
|
||||
"updatedAt": "2026-09-19T13:22:53.677917+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,165 +416,165 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T13:18:25.758260+00:00",
|
||||
"generatedAt": "2026-09-19T13:21:12.167275+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 480.59589041095893,
|
||||
"backlogHours": 477.3265306122449,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.281680584907668,
|
||||
"queueFactor": 0.805050436721843,
|
||||
"queueWeight": 0.805050436721843,
|
||||
"qualityFactor": 0.26525285135102566,
|
||||
"queueFactor": 0.8056265097779283,
|
||||
"queueWeight": 0.8056265097779283,
|
||||
"recentSuccess": 41,
|
||||
"recentSuccessRate": 0.1404109589041096,
|
||||
"recentTerminal": 292,
|
||||
"recentWilsonLowerBound": 0.10521711703615653,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2267670778959823,
|
||||
"recentSuccessRate": 0.13945578231292516,
|
||||
"recentTerminal": 294,
|
||||
"recentWilsonLowerBound": 0.10448917640552996,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.21369472884257043,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 48.666666666666664,
|
||||
"throughputPerHour": 49.0,
|
||||
"waiting": 23389
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 290.8695652173913,
|
||||
"backlogHours": 289.3910034602076,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.11358672103982279,
|
||||
"queueFactor": 0.8680312402085324,
|
||||
"queueWeight": 0.8680312402085324,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.09043478260869565,
|
||||
"recentTerminal": 575,
|
||||
"recentWilsonLowerBound": 0.06963063074113451,
|
||||
"qualityFactor": 0.11801730173611148,
|
||||
"queueFactor": 0.8684270265849894,
|
||||
"queueWeight": 0.8684270265849894,
|
||||
"recentSuccess": 54,
|
||||
"recentSuccessRate": 0.09342560553633218,
|
||||
"recentTerminal": 578,
|
||||
"recentWilsonLowerBound": 0.07231046149772258,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.09859682233541797,
|
||||
"selectionWeight": 0.1024894144322748,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 95.83333333333333,
|
||||
"waiting": 27875
|
||||
"throughputPerHour": 96.33333333333333,
|
||||
"waiting": 27878
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 37.42820181112548,
|
||||
"backlogHours": 37.203084832904885,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.1806203193651215,
|
||||
"queueWeight": 1.1806203193651215,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.03363518758085381,
|
||||
"recentTerminal": 773,
|
||||
"recentWilsonLowerBound": 0.023055187535188204,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.05903101596825608,
|
||||
"queueFactor": 1.1813245835225885,
|
||||
"queueWeight": 1.1813245835225885,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.03470437017994859,
|
||||
"recentTerminal": 778,
|
||||
"recentWilsonLowerBound": 0.023958730686895482,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.05906622917612943,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 128.83333333333334,
|
||||
"waiting": 4822
|
||||
"throughputPerHour": 129.66666666666666,
|
||||
"waiting": 4824
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 98.75475923852183,
|
||||
"backlogHours": 98.98316498316498,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0207194553294272,
|
||||
"queueWeight": 1.0207194553294272,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.020156774916013438,
|
||||
"recentTerminal": 893,
|
||||
"recentWilsonLowerBound": 0.012787450727466036,
|
||||
"queueFactor": 1.020050995965719,
|
||||
"queueWeight": 1.020050995965719,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.017957351290684626,
|
||||
"recentTerminal": 891,
|
||||
"recentWilsonLowerBound": 0.011083071644518503,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.051035972766471364,
|
||||
"selectionWeight": 0.051002549798285945,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 148.83333333333334,
|
||||
"waiting": 14698
|
||||
"throughputPerHour": 148.5,
|
||||
"waiting": 14699
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 84.40186915887851,
|
||||
"backlogHours": 84.58034321372855,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0450505259766616,
|
||||
"queueWeight": 1.0450505259766616,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.037383177570093455,
|
||||
"recentTerminal": 642,
|
||||
"recentWilsonLowerBound": 0.02524793252791448,
|
||||
"queueFactor": 1.044397126351973,
|
||||
"queueWeight": 1.044397126351973,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.0343213728549142,
|
||||
"recentTerminal": 641,
|
||||
"recentWilsonLowerBound": 0.02277269924291493,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.052252526298833084,
|
||||
"selectionWeight": 0.05221985631759865,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 107.0,
|
||||
"waiting": 9031
|
||||
"throughputPerHour": 106.83333333333333,
|
||||
"waiting": 9036
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 61.29921259842519,
|
||||
"backlogHours": 61.22834645669291,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 24,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0964071611767128,
|
||||
"queueWeight": 1.0964071611767128,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.03543307086614173,
|
||||
"queueFactor": 1.0962590837675226,
|
||||
"queueWeight": 1.0962590837675226,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.03937007874015748,
|
||||
"recentTerminal": 254,
|
||||
"recentWilsonLowerBound": 0.018751238499998702,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.054820358058835644,
|
||||
"recentWilsonLowerBound": 0.021523035467193637,
|
||||
"running": 25,
|
||||
"selectionWeight": 0.05481295418837613,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 42.333333333333336,
|
||||
"waiting": 2595
|
||||
"waiting": 2592
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 116.75294117647059,
|
||||
"backlogHours": 116.2734375,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.201272283155946,
|
||||
"queueFactor": 0.9954052417331174,
|
||||
"queueWeight": 0.9954052417331174,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.12549019607843137,
|
||||
"recentTerminal": 255,
|
||||
"recentWilsonLowerBound": 0.09030983757298855,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.20034748566902089,
|
||||
"qualityFactor": 0.17564046879323267,
|
||||
"queueFactor": 0.9957126114884126,
|
||||
"queueWeight": 0.9957126114884126,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.12109375,
|
||||
"recentTerminal": 256,
|
||||
"recentWilsonLowerBound": 0.0866346340727023,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.17488742986515873,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 42.5,
|
||||
"waiting": 4962
|
||||
"throughputPerHour": 42.666666666666664,
|
||||
"waiting": 4961
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2241.348837209302,
|
||||
"backlogHours": 2141.4666666666667,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
@@ -583,82 +583,82 @@
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.4186046511627907,
|
||||
"recentTerminal": 43,
|
||||
"recentWilsonLowerBound": 0.28384334337485234,
|
||||
"running": 2,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.4222222222222222,
|
||||
"recentTerminal": 45,
|
||||
"recentWilsonLowerBound": 0.2896848798168782,
|
||||
"running": 3,
|
||||
"selectionWeight": 1.75,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.166666666666667,
|
||||
"waiting": 16063
|
||||
"throughputPerHour": 7.5,
|
||||
"waiting": 16061
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 152.97115384615387,
|
||||
"backlogHours": 152.66187050359713,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9558696368406733,
|
||||
"queueWeight": 0.9558696368406733,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.06490384615384616,
|
||||
"recentTerminal": 416,
|
||||
"recentWilsonLowerBound": 0.044985598880732613,
|
||||
"queueFactor": 0.9558648635760326,
|
||||
"queueWeight": 0.9558648635760326,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.0671462829736211,
|
||||
"recentTerminal": 417,
|
||||
"recentWilsonLowerBound": 0.0468613536780215,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.047793481842033664,
|
||||
"selectionWeight": 0.04779324317880163,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 69.33333333333333,
|
||||
"waiting": 10606
|
||||
"throughputPerHour": 69.5,
|
||||
"waiting": 10610
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 154.06451612903226,
|
||||
"backlogHours": 154.4341801385681,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9548490145435514,
|
||||
"queueWeight": 0.9548490145435514,
|
||||
"queueFactor": 0.9542113337537893,
|
||||
"queueWeight": 0.9542113337537893,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.05069124423963134,
|
||||
"recentTerminal": 434,
|
||||
"recentWilsonLowerBound": 0.03371079210895234,
|
||||
"recentSuccessRate": 0.050808314087759814,
|
||||
"recentTerminal": 433,
|
||||
"recentWilsonLowerBound": 0.03378919772673746,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.047742450727177574,
|
||||
"selectionWeight": 0.04771056668768947,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 72.33333333333333,
|
||||
"waiting": 11144
|
||||
"throughputPerHour": 72.16666666666667,
|
||||
"waiting": 11145
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 109.69270833333333,
|
||||
"backlogHours": 109.70685169124025,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0047625372471858,
|
||||
"queueWeight": 1.0047625372471858,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.0234375,
|
||||
"recentTerminal": 1152,
|
||||
"recentWilsonLowerBound": 0.016156836859528272,
|
||||
"queueFactor": 1.0044331135786393,
|
||||
"queueWeight": 1.0044331135786393,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.02168256721595837,
|
||||
"recentTerminal": 1153,
|
||||
"recentWilsonLowerBound": 0.014729022840018344,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.05023812686235929,
|
||||
"selectionWeight": 0.05022165567893197,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 192.0,
|
||||
"waiting": 21061
|
||||
"throughputPerHour": 192.16666666666666,
|
||||
"waiting": 21082
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
@@ -668,7 +668,7 @@
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.5887131751762857,
|
||||
"qualityFactor": 1.5190841992249347,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"recentSuccess": 7,
|
||||
@@ -676,7 +676,7 @@
|
||||
"recentTerminal": 16,
|
||||
"recentWilsonLowerBound": 0.2309836333518552,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.1120992226233999,
|
||||
"selectionWeight": 1.063358939457454,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 2.6666666666666665,
|
||||
@@ -684,52 +684,52 @@
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 71.93205574912892,
|
||||
"backlogHours": 71.98432055749129,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0704138679162178,
|
||||
"queueWeight": 1.0704138679162178,
|
||||
"queueFactor": 1.0699670365656124,
|
||||
"queueWeight": 1.0699670365656124,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.005226480836236934,
|
||||
"recentTerminal": 1148,
|
||||
"recentWilsonLowerBound": 0.0023974458969481744,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.05352069339581089,
|
||||
"running": 17,
|
||||
"selectionWeight": 0.053498351828280624,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 191.33333333333334,
|
||||
"waiting": 13763
|
||||
"waiting": 13773
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 68.20830070477682,
|
||||
"backlogHours": 68.48389630793402,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.078982779360689,
|
||||
"queueWeight": 1.078982779360689,
|
||||
"queueFactor": 1.0779976534866162,
|
||||
"queueWeight": 1.0779976534866162,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.018010963194988253,
|
||||
"recentTerminal": 1277,
|
||||
"recentWilsonLowerBound": 0.012031169875021895,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.05394913896803445,
|
||||
"recentSuccessRate": 0.018067556952081697,
|
||||
"recentTerminal": 1273,
|
||||
"recentWilsonLowerBound": 0.01206906617017304,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.05389988267433082,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 212.83333333333334,
|
||||
"waiting": 14517
|
||||
"throughputPerHour": 212.16666666666666,
|
||||
"waiting": 14530
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T13:10:17.681001+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T13:21:12.167275+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T13:10:17.681001+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T13:21:12.167275+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user