state: generation 10015 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T22:03:41.547638+00:00",
|
||||
"generatedAt": "2026-09-19T22:06:56.241097+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"11": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 730,
|
||||
"listingErrors": 731,
|
||||
"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": "2026-09-19T22:03:41.520562+00:00",
|
||||
"updatedAt": "2026-09-19T22:06:56.217707+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T22:01:23.904453+00:00",
|
||||
"generatedAt": "2026-09-19T22:04:50.216541+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1176.655462184874,
|
||||
"backlogHours": 1227.8947368421052,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.455908037150637,
|
||||
"queueFactor": 0.9834129396515783,
|
||||
"queueWeight": 0.9834129396515783,
|
||||
"qualityFactor": 1.5082235943887348,
|
||||
"queueFactor": 0.9771950232702784,
|
||||
"queueWeight": 0.9771950232702784,
|
||||
"recentSuccess": 38,
|
||||
"recentSuccessRate": 0.31932773109243695,
|
||||
"recentTerminal": 119,
|
||||
"recentWilsonLowerBound": 0.2423382718811776,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 114,
|
||||
"recentWilsonLowerBound": 0.2534794722358529,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.4317588026766672,
|
||||
"selectionWeight": 1.4738285904154826,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.833333333333332,
|
||||
"waiting": 23337
|
||||
"throughputPerHour": 19.0,
|
||||
"waiting": 23330
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1358.8292682926829,
|
||||
"backlogHours": 1369.8688524590166,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.3463898208331893,
|
||||
"queueFactor": 0.9624065758857102,
|
||||
"queueWeight": 0.9624065758857102,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.3821138211382114,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.30104673808099086,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9612881053447928,
|
||||
"queueWeight": 0.9612881053447928,
|
||||
"recentSuccess": 49,
|
||||
"recentSuccessRate": 0.4016393442622951,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.3189362104743908,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.258180993161155,
|
||||
"selectionWeight": 2.403220263361982,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.5,
|
||||
"waiting": 27856
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"waiting": 27854
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 167.0742857142857,
|
||||
"backlogHours": 169.91860465116278,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.3864187899100375,
|
||||
"qualityFactor": 0.31838213055992937,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.18285714285714286,
|
||||
"recentTerminal": 175,
|
||||
"recentWilsonLowerBound": 0.1326079045186423,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5023444268830487,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.1744186046511628,
|
||||
"recentTerminal": 172,
|
||||
"recentWilsonLowerBound": 0.12499412236734236,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.4138967697279082,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 29.166666666666668,
|
||||
"waiting": 4873
|
||||
"throughputPerHour": 28.666666666666668,
|
||||
"waiting": 4871
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1555.6842105263158,
|
||||
"backlogHours": 1583.4642857142856,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5242213613383502,
|
||||
"queueFactor": 0.9430725392843254,
|
||||
"queueWeight": 0.9430725392843254,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.24561403508771928,
|
||||
"recentTerminal": 57,
|
||||
"recentWilsonLowerBound": 0.15232700465447838,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.49437877038444383,
|
||||
"qualityFactor": 0.6228283425494908,
|
||||
"queueFactor": 0.9406199297702386,
|
||||
"queueWeight": 0.9406199297702386,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.26785714285714285,
|
||||
"recentTerminal": 56,
|
||||
"recentWilsonLowerBound": 0.16957158661894964,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5858447518278161,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.5,
|
||||
"throughputPerHour": 9.333333333333334,
|
||||
"waiting": 14779
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 437.56451612903226,
|
||||
"backlogHours": 455.8487394957983,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.7761721123443976,
|
||||
"queueFactor": 1.1407146030237352,
|
||||
"queueWeight": 1.1407146030237352,
|
||||
"qualityFactor": 0.8000743411942279,
|
||||
"queueFactor": 1.1337891678207186,
|
||||
"queueWeight": 1.1337891678207186,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 124,
|
||||
"recentWilsonLowerBound": 0.18207534390170776,
|
||||
"recentSuccessRate": 0.2605042016806723,
|
||||
"recentTerminal": 119,
|
||||
"recentWilsonLowerBound": 0.19001607594151526,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.8853908630110335,
|
||||
"selectionWeight": 0.9071156214973134,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.666666666666668,
|
||||
"waiting": 9043
|
||||
"throughputPerHour": 19.833333333333332,
|
||||
"waiting": 9041
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 43.53008595988539,
|
||||
"backlogHours": 43.26495726495727,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,197 +539,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.03724928366762178,
|
||||
"recentTerminal": 349,
|
||||
"recentWilsonLowerBound": 0.021895552585493805,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.03418803418803419,
|
||||
"recentTerminal": 351,
|
||||
"recentWilsonLowerBound": 0.019663050672568818,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 58.166666666666664,
|
||||
"waiting": 2532
|
||||
"throughputPerHour": 58.5,
|
||||
"waiting": 2531
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 95.43870967741935,
|
||||
"backlogHours": 96.31270358306189,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.15615941301276898,
|
||||
"qualityFactor": 0.14975604228518521,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 37,
|
||||
"recentSuccessRate": 0.11935483870967742,
|
||||
"recentTerminal": 310,
|
||||
"recentWilsonLowerBound": 0.08784363331389716,
|
||||
"recentSuccessRate": 0.12052117263843648,
|
||||
"recentTerminal": 307,
|
||||
"recentWilsonLowerBound": 0.0887149299644267,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.20300723691659966,
|
||||
"selectionWeight": 0.19468285497074078,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 51.666666666666664,
|
||||
"waiting": 4931
|
||||
"throughputPerHour": 51.166666666666664,
|
||||
"waiting": 4928
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2746.285714285714,
|
||||
"backlogHours": 2912.7272727272725,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.9981056318165886,
|
||||
"queueFactor": 0.8660071107543563,
|
||||
"queueWeight": 0.8660071107543563,
|
||||
"qualityFactor": 2.159907159038669,
|
||||
"queueFactor": 0.858440984279694,
|
||||
"queueWeight": 0.858440984279694,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"recentTerminal": 35,
|
||||
"recentWilsonLowerBound": 0.27984333081678914,
|
||||
"recentSuccessRate": 0.45454545454545453,
|
||||
"recentTerminal": 33,
|
||||
"recentWilsonLowerBound": 0.298426891258915,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.7303736851914915,
|
||||
"selectionWeight": 1.8541528275579124,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.833333333333333,
|
||||
"throughputPerHour": 5.5,
|
||||
"waiting": 16020
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 601.2452830188679,
|
||||
"backlogHours": 601.0754716981131,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.9308952361982354,
|
||||
"queueFactor": 1.0876159385060258,
|
||||
"queueWeight": 1.0876159385060258,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.27358490566037735,
|
||||
"qualityFactor": 0.9558900020629915,
|
||||
"queueFactor": 1.0877173758999974,
|
||||
"queueWeight": 1.0877173758999974,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.2830188679245283,
|
||||
"recentTerminal": 106,
|
||||
"recentWilsonLowerBound": 0.19775807122187763,
|
||||
"recentWilsonLowerBound": 0.20602338401321438,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.0124564959685325,
|
||||
"selectionWeight": 1.0397381646930002,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.666666666666668,
|
||||
"waiting": 10622
|
||||
"waiting": 10619
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 804.433734939759,
|
||||
"backlogHours": 749.8651685393259,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7758673513825998,
|
||||
"queueFactor": 1.0411415397605692,
|
||||
"queueWeight": 1.0411415397605692,
|
||||
"qualityFactor": 0.6204839188844649,
|
||||
"queueFactor": 1.052223362089124,
|
||||
"queueWeight": 1.052223362089124,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.26506024096385544,
|
||||
"recentTerminal": 83,
|
||||
"recentWilsonLowerBound": 0.18204284443216528,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.8077877288684345,
|
||||
"recentSuccessRate": 0.24719101123595505,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.16928115452187478,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.6528876752508469,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.833333333333334,
|
||||
"waiting": 11128
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 11123
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1781.0833333333333,
|
||||
"backlogHours": 1780.75,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9241249159787269,
|
||||
"queueWeight": 0.9241249159787269,
|
||||
"qualityFactor": 2.3459894942697037,
|
||||
"queueFactor": 0.924197893322153,
|
||||
"queueWeight": 0.924197893322153,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.4166666666666667,
|
||||
"recentTerminal": 72,
|
||||
"recentWilsonLowerBound": 0.30985038222496447,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.3103122899468174,
|
||||
"selectionWeight": 2.1681585483599632,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.0,
|
||||
"waiting": 21373
|
||||
"waiting": 21369
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 11901.0,
|
||||
"backlogHours": 13601.142857142857,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.121280143806504,
|
||||
"qualityFactor": 0.5347466023307929,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"recentSuccess": 4,
|
||||
"recentSuccessRate": 0.5,
|
||||
"recentTerminal": 8,
|
||||
"recentWilsonLowerBound": 0.2152125268244419,
|
||||
"recentSuccess": 3,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"recentTerminal": 7,
|
||||
"recentWilsonLowerBound": 0.1582169222626268,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.7848961006645528,
|
||||
"selectionWeight": 0.374322621631555,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 1.3333333333333333,
|
||||
"throughputPerHour": 1.1666666666666667,
|
||||
"waiting": 15868
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 2460.3529411764703,
|
||||
"backlogHours": 2534.7272727272725,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.13963195499109002,
|
||||
"queueFactor": 0.8804074399084878,
|
||||
"queueWeight": 0.8804074399084878,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.17647058823529413,
|
||||
"recentTerminal": 34,
|
||||
"recentWilsonLowerBound": 0.08348855603569687,
|
||||
"qualityFactor": 0.0794421187447209,
|
||||
"queueFactor": 0.8765278742062852,
|
||||
"queueWeight": 0.8765278742062852,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.15151515151515152,
|
||||
"recentTerminal": 33,
|
||||
"recentWilsonLowerBound": 0.06650359257960956,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.12293301202312276,
|
||||
"selectionWeight": 0.0696332314657535,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.666666666666667,
|
||||
"waiting": 13942
|
||||
"throughputPerHour": 5.5,
|
||||
"waiting": 13941
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1052.5,
|
||||
"backlogHours": 1052.857142857143,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.3134868829233746,
|
||||
"qualityFactor": 1.359187757196717,
|
||||
"queueFactor": 1.0,
|
||||
"queueWeight": 1.0,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.32142857142857145,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 84,
|
||||
"recentWilsonLowerBound": 0.23125977350162447,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.3134868829233746,
|
||||
"recentWilsonLowerBound": 0.24177064973177226,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.359187757196717,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.0,
|
||||
"waiting": 14735
|
||||
"waiting": 14740
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T21:54:11.879727+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T22:04:50.216541+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T21:54:11.879727+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T22:04:50.216541+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