state: generation 9808 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T12:58:02.585256+00:00",
|
||||
"generatedAt": "2026-09-19T13:01:08.923148+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
"0": {
|
||||
"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": 0,
|
||||
"nextAccountIndex": 1,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T12:58:02.561923+00:00",
|
||||
"updatedAt": "2026-09-19T13:01:08.896704+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,165 +416,165 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T12:56:40.240316+00:00",
|
||||
"generatedAt": "2026-09-19T12:59:17.192374+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 477.38775510204084,
|
||||
"backlogHours": 478.97610921501706,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.32631115986275594,
|
||||
"queueFactor": 0.804720380798742,
|
||||
"queueWeight": 0.804720380798742,
|
||||
"recentSuccess": 41,
|
||||
"recentSuccessRate": 0.13945578231292516,
|
||||
"recentTerminal": 294,
|
||||
"recentWilsonLowerBound": 0.10448917640552996,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2625892408236361,
|
||||
"qualityFactor": 0.2624104137760753,
|
||||
"queueFactor": 0.8051715309106076,
|
||||
"queueWeight": 0.8051715309106076,
|
||||
"recentSuccess": 40,
|
||||
"recentSuccessRate": 0.13651877133105803,
|
||||
"recentTerminal": 293,
|
||||
"recentWilsonLowerBound": 0.10188197990533657,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.21128539458696854,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 49.0,
|
||||
"waiting": 23392
|
||||
"throughputPerHour": 48.833333333333336,
|
||||
"waiting": 23390
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 288.76683937823833,
|
||||
"backlogHours": 288.3310344827586,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.1315671208480616,
|
||||
"queueFactor": 0.8677479453501664,
|
||||
"queueWeight": 0.8677479453501664,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.08981001727115717,
|
||||
"recentTerminal": 579,
|
||||
"recentWilsonLowerBound": 0.06914489862007774,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.1141670987915425,
|
||||
"qualityFactor": 0.11687712569635987,
|
||||
"queueFactor": 0.8688639534916123,
|
||||
"queueWeight": 0.8688639534916123,
|
||||
"recentSuccess": 53,
|
||||
"recentSuccessRate": 0.09137931034482759,
|
||||
"recentTerminal": 580,
|
||||
"recentWilsonLowerBound": 0.07054034570078613,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.10155032150527535,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 96.5,
|
||||
"waiting": 27866
|
||||
"throughputPerHour": 96.66666666666667,
|
||||
"waiting": 27872
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 37.43005181347151,
|
||||
"backlogHours": 37.412677878395854,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.1789425100984,
|
||||
"queueWeight": 1.1789425100984,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.03367875647668394,
|
||||
"recentTerminal": 772,
|
||||
"recentWilsonLowerBound": 0.023085184053386568,
|
||||
"queueFactor": 1.1802735355828793,
|
||||
"queueWeight": 1.1802735355828793,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.03492884864165589,
|
||||
"recentTerminal": 773,
|
||||
"recentWilsonLowerBound": 0.02411440762114535,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.05894712550492,
|
||||
"selectionWeight": 0.059013676779143966,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 128.66666666666666,
|
||||
"waiting": 4816
|
||||
"throughputPerHour": 128.83333333333334,
|
||||
"waiting": 4820
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 98.68085106382978,
|
||||
"backlogHours": 98.7077267637178,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0193909155315415,
|
||||
"queueWeight": 1.0193909155315415,
|
||||
"queueFactor": 1.0204290552718334,
|
||||
"queueWeight": 1.0204290552718334,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.020156774916013438,
|
||||
"recentTerminal": 893,
|
||||
"recentWilsonLowerBound": 0.012787450727466036,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.05096954577657708,
|
||||
"selectionWeight": 0.05102145276359167,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 148.83333333333334,
|
||||
"waiting": 14687
|
||||
"waiting": 14691
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 84.553125,
|
||||
"backlogHours": 84.027950310559,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0432928773822252,
|
||||
"queueWeight": 1.0432928773822252,
|
||||
"queueFactor": 1.0453745505616638,
|
||||
"queueWeight": 1.0453745505616638,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.0390625,
|
||||
"recentTerminal": 640,
|
||||
"recentWilsonLowerBound": 0.02659655474602655,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.052164643869111266,
|
||||
"recentSuccessRate": 0.03881987577639751,
|
||||
"recentTerminal": 644,
|
||||
"recentWilsonLowerBound": 0.026430502751230194,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.052268727528083196,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 106.66666666666667,
|
||||
"throughputPerHour": 107.33333333333333,
|
||||
"waiting": 9019
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 61.56521739130435,
|
||||
"backlogHours": 60.75,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 24,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0941462578484729,
|
||||
"queueWeight": 1.0941462578484729,
|
||||
"queueFactor": 1.0974975166701697,
|
||||
"queueWeight": 1.0974975166701697,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.043478260869565216,
|
||||
"recentTerminal": 253,
|
||||
"recentWilsonLowerBound": 0.024448065140738544,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.05470731289242364,
|
||||
"recentSuccessRate": 0.04296875,
|
||||
"recentTerminal": 256,
|
||||
"recentWilsonLowerBound": 0.024159562780836395,
|
||||
"running": 28,
|
||||
"selectionWeight": 0.05487487583350849,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 42.166666666666664,
|
||||
"waiting": 2596
|
||||
"throughputPerHour": 42.666666666666664,
|
||||
"waiting": 2592
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 115.08880308880309,
|
||||
"backlogHours": 116.3671875,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.2884647308038784,
|
||||
"queueFactor": 0.9961408059487004,
|
||||
"queueWeight": 0.9961408059487004,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.13513513513513514,
|
||||
"recentTerminal": 259,
|
||||
"recentWilsonLowerBound": 0.09879507690356609,
|
||||
"qualityFactor": 0.2335199630259016,
|
||||
"queueFactor": 0.9955450283557267,
|
||||
"queueWeight": 0.9955450283557267,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.1328125,
|
||||
"recentTerminal": 256,
|
||||
"recentWilsonLowerBound": 0.09662098110089375,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.28735148943075034,
|
||||
"selectionWeight": 0.23247963821224946,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 43.166666666666664,
|
||||
"waiting": 4968
|
||||
"throughputPerHour": 42.666666666666664,
|
||||
"waiting": 4965
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2241.767441860465,
|
||||
"backlogHours": 2241.348837209302,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
@@ -583,92 +583,92 @@
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.3953488372093023,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.4186046511627907,
|
||||
"recentTerminal": 43,
|
||||
"recentWilsonLowerBound": 0.263651061984564,
|
||||
"recentWilsonLowerBound": 0.28384334337485234,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.75,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.166666666666667,
|
||||
"waiting": 16066
|
||||
"waiting": 16063
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 151.81861575179,
|
||||
"backlogHours": 151.8615751789976,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.06622125140702059,
|
||||
"queueFactor": 0.9556017531631489,
|
||||
"queueWeight": 0.9556017531631489,
|
||||
"qualityFactor": 0.05629750761864047,
|
||||
"queueFactor": 0.956573407724597,
|
||||
"queueWeight": 0.956573407724597,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.07159904534606205,
|
||||
"recentTerminal": 419,
|
||||
"recentWilsonLowerBound": 0.05061012648046582,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.06328114394120651,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.05385269870916437,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 69.83333333333333,
|
||||
"waiting": 10602
|
||||
"waiting": 10605
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 153.27522935779817,
|
||||
"backlogHours": 153.64137931034483,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9542340198517159,
|
||||
"queueWeight": 0.9542340198517159,
|
||||
"queueFactor": 0.9549030026504502,
|
||||
"queueWeight": 0.9549030026504502,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.052752293577981654,
|
||||
"recentTerminal": 436,
|
||||
"recentWilsonLowerBound": 0.03540545563616003,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.047711700992585794,
|
||||
"recentSuccessRate": 0.052873563218390804,
|
||||
"recentTerminal": 435,
|
||||
"recentWilsonLowerBound": 0.03548744100362372,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.047745150132522514,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 72.66666666666667,
|
||||
"waiting": 11138
|
||||
"throughputPerHour": 72.5,
|
||||
"waiting": 11139
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 109.23116883116883,
|
||||
"backlogHours": 109.54166666666667,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0039768638200492,
|
||||
"queueWeight": 1.0039768638200492,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.025108225108225107,
|
||||
"recentTerminal": 1155,
|
||||
"recentWilsonLowerBound": 0.01753793960754816,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.050198843191002464,
|
||||
"queueFactor": 1.0046125215043784,
|
||||
"queueWeight": 1.0046125215043784,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.0234375,
|
||||
"recentTerminal": 1152,
|
||||
"recentWilsonLowerBound": 0.016156836859528272,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.05023062607521892,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 192.5,
|
||||
"waiting": 21027
|
||||
"throughputPerHour": 192.0,
|
||||
"waiting": 21032
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 5938.125,
|
||||
"backlogHours": 5938.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.8687607859954392,
|
||||
"qualityFactor": 1.5887131751762857,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"recentSuccess": 7,
|
||||
@@ -676,60 +676,60 @@
|
||||
"recentTerminal": 16,
|
||||
"recentWilsonLowerBound": 0.2309836333518552,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.3081325501968073,
|
||||
"selectionWeight": 1.1120992226233999,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 2.6666666666666665,
|
||||
"waiting": 15835
|
||||
"waiting": 15836
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 71.91630340017437,
|
||||
"backlogHours": 71.87979094076654,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0689357167231361,
|
||||
"queueWeight": 1.0689357167231361,
|
||||
"queueFactor": 1.0701495366237568,
|
||||
"queueWeight": 1.0701495366237568,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.0052310374891020054,
|
||||
"recentTerminal": 1147,
|
||||
"recentWilsonLowerBound": 0.0023995379524277753,
|
||||
"recentSuccessRate": 0.005226480836236934,
|
||||
"recentTerminal": 1148,
|
||||
"recentWilsonLowerBound": 0.0023974458969481744,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.05344678583615681,
|
||||
"selectionWeight": 0.05350747683118784,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 191.16666666666666,
|
||||
"waiting": 13748
|
||||
"throughputPerHour": 191.33333333333334,
|
||||
"waiting": 13753
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 68.12539184952978,
|
||||
"backlogHours": 68.10963194988254,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0776539868161208,
|
||||
"queueWeight": 1.0776539868161208,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.018808777429467086,
|
||||
"recentTerminal": 1276,
|
||||
"recentWilsonLowerBound": 0.012671501947191393,
|
||||
"queueFactor": 1.0788329654788056,
|
||||
"queueWeight": 1.0788329654788056,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.018010963194988253,
|
||||
"recentTerminal": 1277,
|
||||
"recentWilsonLowerBound": 0.012031169875021895,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.05388269934080604,
|
||||
"selectionWeight": 0.05394164827394028,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 212.66666666666666,
|
||||
"waiting": 14488
|
||||
"throughputPerHour": 212.83333333333334,
|
||||
"waiting": 14496
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T12:48:19.799326+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T12:59:17.192374+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T12:48:19.799326+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T12:59:17.192374+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