state: generation 9638 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T04:37:42.873590+00:00",
|
||||
"generatedAt": "2026-09-19T04:40:25.902446+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"11": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 702,
|
||||
"listingErrors": 703,
|
||||
"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": 11,
|
||||
"nextAccountIndex": 0,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T04:37:42.848990+00:00",
|
||||
"updatedAt": "2026-09-19T04:40:25.878036+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T04:36:00.796956+00:00",
|
||||
"generatedAt": "2026-09-19T04:38:51.086283+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 900.3870967741935,
|
||||
"backlogHours": 906.4675324675325,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7335679565822285,
|
||||
"queueFactor": 1.013288917364626,
|
||||
"queueWeight": 1.013288917364626,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.2967741935483871,
|
||||
"recentTerminal": 155,
|
||||
"recentWilsonLowerBound": 0.23047427118231806,
|
||||
"qualityFactor": 0.749401788655022,
|
||||
"queueFactor": 1.0135255595879216,
|
||||
"queueWeight": 1.0135255595879216,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.3051948051948052,
|
||||
"recentTerminal": 154,
|
||||
"recentWilsonLowerBound": 0.2379399006813244,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.7433162805385873,
|
||||
"selectionWeight": 0.7595378672027705,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.833333333333332,
|
||||
"waiting": 23260
|
||||
"throughputPerHour": 25.666666666666668,
|
||||
"waiting": 23266
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1552.9345794392525,
|
||||
"backlogHours": 1552.8785046728974,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9337373001400401,
|
||||
"queueWeight": 0.9337373001400401,
|
||||
"recentSuccess": 53,
|
||||
"recentSuccessRate": 0.4953271028037383,
|
||||
"queueFactor": 0.9349037927768287,
|
||||
"queueWeight": 0.9349037927768287,
|
||||
"recentSuccess": 54,
|
||||
"recentSuccessRate": 0.5046728971962616,
|
||||
"recentTerminal": 107,
|
||||
"recentWilsonLowerBound": 0.40240905867272797,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.3343432503501003,
|
||||
"recentWilsonLowerBound": 0.41143094215329845,
|
||||
"running": 11,
|
||||
"selectionWeight": 2.3372594819420716,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.833333333333332,
|
||||
"waiting": 27694
|
||||
"waiting": 27693
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 177.5686274509804,
|
||||
"backlogHours": 173.12101910828025,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.20728789187782826,
|
||||
"queueFactor": 1.292685110163441,
|
||||
"queueWeight": 1.292685110163441,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.1830065359477124,
|
||||
"recentTerminal": 153,
|
||||
"recentWilsonLowerBound": 0.12975906724694125,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2679579713476378,
|
||||
"qualityFactor": 0.20431220114791618,
|
||||
"queueFactor": 1.2992271079887654,
|
||||
"queueWeight": 1.2992271079887654,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.18471337579617833,
|
||||
"recentTerminal": 157,
|
||||
"recentWilsonLowerBound": 0.13179912844996683,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.26544795022422607,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.5,
|
||||
"waiting": 4528
|
||||
"throughputPerHour": 26.166666666666668,
|
||||
"waiting": 4530
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1373.7142857142858,
|
||||
"backlogHours": 1374.7619047619048,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5510840059737425,
|
||||
"queueFactor": 0.9510716142110361,
|
||||
"queueWeight": 0.9510716142110361,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.30158730158730157,
|
||||
"qualityFactor": 0.4517066978403199,
|
||||
"queueFactor": 0.9521457210832583,
|
||||
"queueWeight": 0.9521457210832583,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.2857142857142857,
|
||||
"recentTerminal": 63,
|
||||
"recentWilsonLowerBound": 0.20237537048735993,
|
||||
"recentWilsonLowerBound": 0.18903043457341692,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5241203551273316,
|
||||
"selectionWeight": 0.4300905995333089,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.5,
|
||||
"waiting": 14424
|
||||
"waiting": 14435
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 528.36,
|
||||
"backlogHours": 513.5533980582524,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.40254413228332564,
|
||||
"queueFactor": 1.0976356205250852,
|
||||
"queueWeight": 1.0976356205250852,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 100,
|
||||
"recentWilsonLowerBound": 0.17545094003724265,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.4418467784275401,
|
||||
"qualityFactor": 0.3980781314324336,
|
||||
"queueFactor": 1.1036965940366046,
|
||||
"queueWeight": 1.1036965940366046,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.2524271844660194,
|
||||
"recentTerminal": 103,
|
||||
"recentWilsonLowerBound": 0.17847711876706254,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.4393574778224328,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.666666666666668,
|
||||
"waiting": 8806
|
||||
"throughputPerHour": 17.166666666666668,
|
||||
"waiting": 8816
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 69.99107142857143,
|
||||
"backlogHours": 69.80357142857143,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -543,193 +543,193 @@
|
||||
"recentSuccessRate": 0.017857142857142856,
|
||||
"recentTerminal": 224,
|
||||
"recentWilsonLowerBound": 0.006965542540871424,
|
||||
"running": 24,
|
||||
"running": 26,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 37.333333333333336,
|
||||
"waiting": 2613
|
||||
"waiting": 2606
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 208.9090909090909,
|
||||
"backlogHours": 208.36363636363637,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.2649540353741555,
|
||||
"queueFactor": 1.2615488765760225,
|
||||
"queueWeight": 1.2615488765760225,
|
||||
"qualityFactor": 0.2523401139622311,
|
||||
"queueFactor": 1.263613491527999,
|
||||
"queueWeight": 1.263613491527999,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.20279720279720279,
|
||||
"recentTerminal": 143,
|
||||
"recentWilsonLowerBound": 0.1450743778152789,
|
||||
"running": 0,
|
||||
"selectionWeight": 0.3342524656705496,
|
||||
"running": 11,
|
||||
"selectionWeight": 0.31886037245638804,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.833333333333332,
|
||||
"waiting": 4979
|
||||
"waiting": 4966
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3094.451612903226,
|
||||
"backlogHours": 3199.6,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.7824232548788866,
|
||||
"queueFactor": 0.8419961925285907,
|
||||
"queueWeight": 0.8419961925285907,
|
||||
"qualityFactor": 0.8056952493125176,
|
||||
"queueFactor": 0.8388285243054638,
|
||||
"queueWeight": 0.8388285243054638,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.3870967741935484,
|
||||
"recentTerminal": 31,
|
||||
"recentWilsonLowerBound": 0.23732875351271562,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.6587974015538496,
|
||||
"recentSuccessRate": 0.4,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.24590394326083398,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.6758401570207418,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.166666666666667,
|
||||
"waiting": 15988
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 15998
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 514.5245901639345,
|
||||
"backlogHours": 531.9661016949152,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.20475598074117504,
|
||||
"queueFactor": 1.1020131116784284,
|
||||
"queueWeight": 1.1020131116784284,
|
||||
"qualityFactor": 0.210295650242305,
|
||||
"queueFactor": 1.0978801920181454,
|
||||
"queueWeight": 1.0978801920181454,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.1885245901639344,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.12903622583107396,
|
||||
"recentSuccessRate": 0.19491525423728814,
|
||||
"recentTerminal": 118,
|
||||
"recentWilsonLowerBound": 0.1335397978223456,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.22564377547135067,
|
||||
"selectionWeight": 0.23087942886860255,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"throughputPerHour": 19.666666666666668,
|
||||
"waiting": 10462
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 919.75,
|
||||
"backlogHours": 920.4166666666666,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.6057462979061491,
|
||||
"queueFactor": 1.0100600927957433,
|
||||
"queueWeight": 1.0100600927957433,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.3055555555555556,
|
||||
"qualityFactor": 0.6513996292215067,
|
||||
"queueFactor": 1.0112065459029154,
|
||||
"queueWeight": 1.0112065459029154,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.3194444444444444,
|
||||
"recentTerminal": 72,
|
||||
"recentWilsonLowerBound": 0.2112648204592105,
|
||||
"recentWilsonLowerBound": 0.2232545704855647,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.6118401618737629,
|
||||
"selectionWeight": 0.6586995690675196,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.0,
|
||||
"waiting": 11037
|
||||
"waiting": 11045
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1571.064935064935,
|
||||
"backlogHours": 1553.3846153846155,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.5522885704981924,
|
||||
"queueFactor": 0.9321129928797698,
|
||||
"queueWeight": 0.9321129928797698,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"recentTerminal": 77,
|
||||
"recentWilsonLowerBound": 0.32403475215621097,
|
||||
"qualityFactor": 1.2125674752523623,
|
||||
"queueFactor": 0.9348580960751044,
|
||||
"queueWeight": 0.9348580960751044,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.3974358974358974,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.29611695255788584,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.4469083452601297,
|
||||
"selectionWeight": 1.1335785212770197,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.833333333333334,
|
||||
"waiting": 20162
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 20194
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 8560.909090909092,
|
||||
"backlogHours": 8565.818181818182,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.8833432525589875,
|
||||
"queueFactor": 0.7228025886454317,
|
||||
"queueWeight": 0.7228025886454317,
|
||||
"qualityFactor": 1.793681120235132,
|
||||
"queueFactor": 0.7236394179559162,
|
||||
"queueWeight": 0.7236394179559162,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.6363636363636364,
|
||||
"recentTerminal": 11,
|
||||
"recentWilsonLowerBound": 0.35379677689163724,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.3612853782575431,
|
||||
"selectionWeight": 1.2979783618454668,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 1.8333333333333333,
|
||||
"waiting": 15695
|
||||
"waiting": 15704
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 2493.5625,
|
||||
"backlogHours": 2422.5454545454545,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.8697103598487315,
|
||||
"queueWeight": 0.8697103598487315,
|
||||
"queueFactor": 0.8745743847774777,
|
||||
"queueWeight": 0.8745743847774777,
|
||||
"recentSuccess": 4,
|
||||
"recentSuccessRate": 0.125,
|
||||
"recentTerminal": 32,
|
||||
"recentWilsonLowerBound": 0.049700538444743,
|
||||
"recentSuccessRate": 0.12121212121212122,
|
||||
"recentTerminal": 33,
|
||||
"recentWilsonLowerBound": 0.0481608326758423,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04348551799243658,
|
||||
"selectionWeight": 0.04372871923887389,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 5.333333333333333,
|
||||
"waiting": 13299
|
||||
"throughputPerHour": 5.5,
|
||||
"waiting": 13324
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1046.6923076923076,
|
||||
"backlogHours": 1062.3896103896104,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.1657736170286925,
|
||||
"queueFactor": 0.9906604548611343,
|
||||
"queueWeight": 0.9906604548611343,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.38461538461538464,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.28448876404744494,
|
||||
"qualityFactor": 1.0444834547127135,
|
||||
"queueFactor": 0.9896804040203732,
|
||||
"queueWeight": 0.9896804040203732,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.37662337662337664,
|
||||
"recentTerminal": 77,
|
||||
"recentWilsonLowerBound": 0.27669846411806526,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.1548858217107543,
|
||||
"selectionWeight": 1.0337048074526736,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 13607
|
||||
"throughputPerHour": 12.833333333333334,
|
||||
"waiting": 13634
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T04:27:16.855402+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T04:38:51.086283+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T04:27:16.855402+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T04:38:51.086283+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