state: generation 10046 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T23:49:56.655398+00:00",
|
||||
"generatedAt": "2026-09-19T23:53:08.042398+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -67,7 +67,7 @@
|
||||
"6": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 733,
|
||||
"listingErrors": 734,
|
||||
"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": 6,
|
||||
"nextAccountIndex": 7,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T23:49:56.630953+00:00",
|
||||
"updatedAt": "2026-09-19T23:53:08.019600+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T23:47:09.853243+00:00",
|
||||
"generatedAt": "2026-09-19T23:51:05.886880+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1227.7894736842106,
|
||||
"backlogHours": 1229.2631578947369,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.6711496601114806,
|
||||
"queueFactor": 0.9906710831734079,
|
||||
"queueWeight": 0.9906710831734079,
|
||||
"qualityFactor": 1.6059335544847506,
|
||||
"queueFactor": 0.9906065720111741,
|
||||
"queueWeight": 0.9906065720111741,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.34210526315789475,
|
||||
"recentTerminal": 114,
|
||||
"recentWilsonLowerBound": 0.26144067569416146,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.6555596439275129,
|
||||
"selectionWeight": 1.590848333285859,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.0,
|
||||
"waiting": 23328
|
||||
"waiting": 23356
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1336.4640000000002,
|
||||
"backlogHours": 1286.076923076923,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.8502941061983567,
|
||||
"queueFactor": 0.9781478003739736,
|
||||
"queueWeight": 0.9781478003739736,
|
||||
"recentSuccess": 44,
|
||||
"recentSuccessRate": 0.352,
|
||||
"recentTerminal": 125,
|
||||
"recentWilsonLowerBound": 0.27382659191147585,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.80986111002285,
|
||||
"qualityFactor": 1.822623617909126,
|
||||
"queueFactor": 0.9839157054852856,
|
||||
"queueWeight": 0.9839157054852856,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.35384615384615387,
|
||||
"recentTerminal": 130,
|
||||
"recentWilsonLowerBound": 0.2769231466844021,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.7933080028492014,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.833333333333332,
|
||||
"waiting": 27843
|
||||
"throughputPerHour": 21.666666666666668,
|
||||
"waiting": 27865
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 160.70718232044197,
|
||||
"backlogHours": 166.32,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.24508402708625918,
|
||||
"qualityFactor": 0.20888551118251725,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.15469613259668508,
|
||||
"recentTerminal": 181,
|
||||
"recentWilsonLowerBound": 0.10924924858609739,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.14857142857142858,
|
||||
"recentTerminal": 175,
|
||||
"recentWilsonLowerBound": 0.10344941553276563,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.31860923521213697,
|
||||
"selectionWeight": 0.2715511645372724,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 30.166666666666668,
|
||||
"waiting": 4848
|
||||
"throughputPerHour": 29.166666666666668,
|
||||
"waiting": 4851
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1886.1702127659576,
|
||||
"backlogHours": 2016.5454545454547,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 1.1624140832364835,
|
||||
"queueFactor": 0.9288828403653016,
|
||||
"queueWeight": 0.9288828403653016,
|
||||
"qualityFactor": 1.3040872481917234,
|
||||
"queueFactor": 0.9197223331884085,
|
||||
"queueWeight": 0.9197223331884085,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.3404255319148936,
|
||||
"recentTerminal": 47,
|
||||
"recentWilsonLowerBound": 0.2216726071376219,
|
||||
"recentSuccessRate": 0.36363636363636365,
|
||||
"recentTerminal": 44,
|
||||
"recentWilsonLowerBound": 0.23783334127491426,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.0797464953173328,
|
||||
"selectionWeight": 1.199398166588143,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.833333333333333,
|
||||
"waiting": 14775
|
||||
"throughputPerHour": 7.333333333333333,
|
||||
"waiting": 14788
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 516.2285714285714,
|
||||
"backlogHours": 521.5384615384615,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.6905545102921746,
|
||||
"queueFactor": 1.128162777937474,
|
||||
"queueWeight": 1.128162777937474,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.24761904761904763,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.17494869705401506,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.7790578946484717,
|
||||
"qualityFactor": 0.6106016568564031,
|
||||
"queueFactor": 1.126561703078606,
|
||||
"queueWeight": 1.126561703078606,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.2403846153846154,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.16845266546271026,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.6878804424507681,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 9034
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 9040
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 50.05940594059406,
|
||||
"backlogHours": 50.31229235880399,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -540,196 +540,196 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.039603960396039604,
|
||||
"recentTerminal": 303,
|
||||
"recentWilsonLowerBound": 0.022797659414812314,
|
||||
"running": 24,
|
||||
"recentSuccessRate": 0.03986710963455149,
|
||||
"recentTerminal": 301,
|
||||
"recentWilsonLowerBound": 0.022950103141283904,
|
||||
"running": 27,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 50.5,
|
||||
"waiting": 2528
|
||||
"throughputPerHour": 50.166666666666664,
|
||||
"waiting": 2524
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 135.76036866359448,
|
||||
"backlogHours": 137.69158878504675,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.23139918972428644,
|
||||
"qualityFactor": 0.21118736925066278,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.14746543778801843,
|
||||
"recentTerminal": 217,
|
||||
"recentWilsonLowerBound": 0.10643295175202402,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.3008189466415724,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.14485981308411214,
|
||||
"recentTerminal": 214,
|
||||
"recentWilsonLowerBound": 0.10396604096484628,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2745435800258616,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 36.166666666666664,
|
||||
"waiting": 4910
|
||||
"throughputPerHour": 35.666666666666664,
|
||||
"waiting": 4911
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3195.4,
|
||||
"backlogHours": 3092.1290322580644,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.3005175635675252,
|
||||
"queueFactor": 0.858260820965659,
|
||||
"queueWeight": 0.858260820965659,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.4666666666666667,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.3023212722412823,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8625996815733769,
|
||||
"queueWeight": 0.8625996815733769,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.4838709677419355,
|
||||
"recentTerminal": 31,
|
||||
"recentWilsonLowerBound": 0.3196998603127883,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.974444092753382,
|
||||
"selectionWeight": 2.1564992039334423,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 15977
|
||||
"throughputPerHour": 5.166666666666667,
|
||||
"waiting": 15976
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 636.66,
|
||||
"backlogHours": 656.2268041237113,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.2342247809528426,
|
||||
"queueFactor": 1.0932309985636086,
|
||||
"queueWeight": 1.0932309985636086,
|
||||
"qualityFactor": 1.2723591805019083,
|
||||
"queueFactor": 1.0884032750607027,
|
||||
"queueWeight": 1.0884032750607027,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.31,
|
||||
"recentTerminal": 100,
|
||||
"recentWilsonLowerBound": 0.22779563206132378,
|
||||
"recentSuccessRate": 0.31958762886597936,
|
||||
"recentTerminal": 97,
|
||||
"recentWilsonLowerBound": 0.23518547734357254,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.3492927897330271,
|
||||
"selectionWeight": 1.3848398991118287,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.666666666666668,
|
||||
"waiting": 10611
|
||||
"throughputPerHour": 16.166666666666668,
|
||||
"waiting": 10609
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 823.4814814814815,
|
||||
"backlogHours": 823.5555555555555,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7970778004568271,
|
||||
"queueFactor": 1.0518407614035614,
|
||||
"queueWeight": 1.0518407614035614,
|
||||
"qualityFactor": 0.7659720824783149,
|
||||
"queueFactor": 1.0519473394961976,
|
||||
"queueWeight": 1.0519473394961976,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.2716049382716049,
|
||||
"recentTerminal": 81,
|
||||
"recentWilsonLowerBound": 0.1867368992369412,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.838398920530385,
|
||||
"selectionWeight": 0.8057622942914254,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.5,
|
||||
"waiting": 11117
|
||||
"waiting": 11118
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2033.2380952380952,
|
||||
"backlogHours": 2033.4285714285713,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9184802806304319,
|
||||
"queueWeight": 0.9184802806304319,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"qualityFactor": 2.1669240514007853,
|
||||
"queueFactor": 0.9185728321910102,
|
||||
"queueWeight": 0.9185728321910102,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.4126984126984127,
|
||||
"recentTerminal": 63,
|
||||
"recentWilsonLowerBound": 0.3139672637328724,
|
||||
"recentWilsonLowerBound": 0.2995827804043615,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.2962007015760797,
|
||||
"selectionWeight": 1.9904775630380374,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.5,
|
||||
"waiting": 21349
|
||||
"waiting": 21351
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 9315.0,
|
||||
"backlogHours": 9315.6,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.05785701590398116,
|
||||
"queueFactor": 0.7310054981762005,
|
||||
"queueWeight": 0.7310054981762005,
|
||||
"qualityFactor": 0.05559916351020468,
|
||||
"queueFactor": 0.7310823681004675,
|
||||
"queueWeight": 0.7310823681004675,
|
||||
"recentSuccess": 2,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 10,
|
||||
"recentWilsonLowerBound": 0.05668094798069332,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.042293796733878106,
|
||||
"selectionWeight": 0.040647568123445534,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 1.6666666666666667,
|
||||
"waiting": 15525
|
||||
"waiting": 15526
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1858.5333333333333,
|
||||
"backlogHours": 1822.695652173913,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9309417748152088,
|
||||
"queueWeight": 0.9309417748152088,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.1111111111111111,
|
||||
"recentTerminal": 45,
|
||||
"recentWilsonLowerBound": 0.04840400437825557,
|
||||
"qualityFactor": 0.06576722804036364,
|
||||
"queueFactor": 0.9337719226691952,
|
||||
"queueWeight": 0.9337719226691952,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.13043478260869565,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.06117757137492025,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04654708874076044,
|
||||
"selectionWeight": 0.06141159097587376,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 7.5,
|
||||
"waiting": 13939
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
"waiting": 13974
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1079.0487804878048,
|
||||
"backlogHours": 1079.3414634146343,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.349103890336736,
|
||||
"queueFactor": 1.010047761811509,
|
||||
"queueWeight": 1.010047761811509,
|
||||
"qualityFactor": 1.2964555226209664,
|
||||
"queueFactor": 1.010122641140451,
|
||||
"queueWeight": 1.010122641140451,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.32926829268292684,
|
||||
"recentTerminal": 82,
|
||||
"recentWilsonLowerBound": 0.2371996746292997,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.3626593648858196,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.3095790766310142,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.666666666666666,
|
||||
"waiting": 14747
|
||||
"waiting": 14751
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T23:40:38.326632+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T23:51:05.886880+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T23:40:38.326632+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T23:51:05.886880+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