state: generation 10079 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T01:43:18.657566+00:00",
|
||||
"generatedAt": "2026-09-20T01:46:43.946888+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -43,7 +43,7 @@
|
||||
"3": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 736,
|
||||
"listingErrors": 737,
|
||||
"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": 3,
|
||||
"nextAccountIndex": 4,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-20T01:43:18.631441+00:00",
|
||||
"updatedAt": "2026-09-20T01:46:43.920601+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T01:41:02.410263+00:00",
|
||||
"generatedAt": "2026-09-20T01:44:25.642419+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1143.7073170731708,
|
||||
"backlogHours": 1116.2857142857142,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.7242332831828948,
|
||||
"queueFactor": 0.9900884518471254,
|
||||
"queueWeight": 0.9900884518471254,
|
||||
"recentSuccess": 41,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.2561872178643666,
|
||||
"qualityFactor": 1.7890574027597195,
|
||||
"queueFactor": 0.9942149899223116,
|
||||
"queueWeight": 0.9942149899223116,
|
||||
"recentSuccess": 43,
|
||||
"recentSuccessRate": 0.3412698412698413,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.2642758158775134,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.7071434619698385,
|
||||
"selectionWeight": 1.7787076876551915,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.5,
|
||||
"waiting": 23446
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 23442
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1300.4186046511627,
|
||||
"backlogHours": 1280.6564885496184,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.3256356310909307,
|
||||
"queueFactor": 0.9712001791633734,
|
||||
"queueWeight": 0.9712001791633734,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.37209302325581395,
|
||||
"recentTerminal": 129,
|
||||
"recentWilsonLowerBound": 0.29351051285070046,
|
||||
"qualityFactor": 2.2938261695186206,
|
||||
"queueFactor": 0.9739389030835843,
|
||||
"queueWeight": 0.9739389030835843,
|
||||
"recentSuccess": 49,
|
||||
"recentSuccessRate": 0.37404580152671757,
|
||||
"recentTerminal": 131,
|
||||
"recentWilsonLowerBound": 0.29588254392287383,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.258657741584237,
|
||||
"selectionWeight": 2.2340465434053853,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.5,
|
||||
"waiting": 27959
|
||||
"throughputPerHour": 21.833333333333332,
|
||||
"waiting": 27961
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 179.33333333333334,
|
||||
"backlogHours": 180.59627329192548,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.20126672404549673,
|
||||
"qualityFactor": 0.15493260953619414,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.1419753086419753,
|
||||
"recentTerminal": 162,
|
||||
"recentWilsonLowerBound": 0.09650426940997234,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.13043478260869565,
|
||||
"recentTerminal": 161,
|
||||
"recentWilsonLowerBound": 0.08691831797877285,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2616467412591458,
|
||||
"selectionWeight": 0.2014123923970524,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.0,
|
||||
"waiting": 4842
|
||||
"throughputPerHour": 26.833333333333332,
|
||||
"waiting": 4846
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 2118.714285714286,
|
||||
"backlogHours": 2170.2439024390246,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 1.9421281346664874,
|
||||
"queueFactor": 0.9026312616094001,
|
||||
"queueWeight": 0.9026312616094001,
|
||||
"qualityFactor": 1.9929411188606294,
|
||||
"queueFactor": 0.8998504332656039,
|
||||
"queueWeight": 0.8998504332656039,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.40476190476190477,
|
||||
"recentTerminal": 42,
|
||||
"recentWilsonLowerBound": 0.2704264767120908,
|
||||
"recentSuccessRate": 0.4146341463414634,
|
||||
"recentTerminal": 41,
|
||||
"recentWilsonLowerBound": 0.2775633082533015,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.7530255684011224,
|
||||
"selectionWeight": 1.7933489292795748,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.0,
|
||||
"waiting": 14831
|
||||
"throughputPerHour": 6.833333333333333,
|
||||
"waiting": 14830
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 489.4594594594595,
|
||||
"backlogHours": 498.3853211009174,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.47243055418985613,
|
||||
"queueFactor": 1.1245110335654398,
|
||||
"queueWeight": 1.1245110335654398,
|
||||
"qualityFactor": 0.47708647457732156,
|
||||
"queueFactor": 1.1220490061818162,
|
||||
"queueWeight": 1.1220490061818162,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.2072072072072072,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.14222816865850865,
|
||||
"recentSuccessRate": 0.21100917431192662,
|
||||
"recentTerminal": 109,
|
||||
"recentWilsonLowerBound": 0.1449225546231727,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5312533707799286,
|
||||
"selectionWeight": 0.53531440466227,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.5,
|
||||
"waiting": 9055
|
||||
"throughputPerHour": 18.166666666666668,
|
||||
"waiting": 9054
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 52.57839721254355,
|
||||
"backlogHours": 57.48091603053435,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,197 +539,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.03832752613240418,
|
||||
"recentTerminal": 287,
|
||||
"recentWilsonLowerBound": 0.021533763383764695,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.03816793893129771,
|
||||
"recentTerminal": 262,
|
||||
"recentWilsonLowerBound": 0.0208617114039803,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 47.833333333333336,
|
||||
"waiting": 2515
|
||||
"throughputPerHour": 43.666666666666664,
|
||||
"waiting": 2510
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 133.46606334841627,
|
||||
"backlogHours": 161.96703296703296,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.20247906479646474,
|
||||
"qualityFactor": 0.3592215834785861,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.13574660633484162,
|
||||
"recentTerminal": 221,
|
||||
"recentWilsonLowerBound": 0.09676806330542623,
|
||||
"running": 12,
|
||||
"selectionWeight": 0.2632227842354042,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.17582417582417584,
|
||||
"recentTerminal": 182,
|
||||
"recentWilsonLowerBound": 0.12738556469467538,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.46698805852216196,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 36.833333333333336,
|
||||
"waiting": 4916
|
||||
"throughputPerHour": 30.333333333333332,
|
||||
"waiting": 4913
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2457.230769230769,
|
||||
"backlogHours": 2589.7297297297296,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.6183371950333394,
|
||||
"queueFactor": 0.8827837663277115,
|
||||
"queueWeight": 0.8827837663277115,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.38461538461538464,
|
||||
"recentTerminal": 39,
|
||||
"recentWilsonLowerBound": 0.24891162547007062,
|
||||
"qualityFactor": 1.1743974586803485,
|
||||
"queueFactor": 0.8763113675873454,
|
||||
"queueWeight": 0.8763113675873454,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.35135135135135137,
|
||||
"recentTerminal": 37,
|
||||
"recentWilsonLowerBound": 0.21825406631100872,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.4286418042197555,
|
||||
"selectionWeight": 1.029137843107279,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.5,
|
||||
"waiting": 15972
|
||||
"throughputPerHour": 6.166666666666667,
|
||||
"waiting": 15970
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 655.6082474226804,
|
||||
"backlogHours": 662.1875,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.8038264336930596,
|
||||
"queueFactor": 1.0762782619492481,
|
||||
"queueWeight": 1.0762782619492481,
|
||||
"qualityFactor": 0.7976125135663115,
|
||||
"queueFactor": 1.0752252759520884,
|
||||
"queueWeight": 1.0752252759520884,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.25773195876288657,
|
||||
"recentTerminal": 97,
|
||||
"recentWilsonLowerBound": 0.18109470708719705,
|
||||
"recentSuccessRate": 0.2604166666666667,
|
||||
"recentTerminal": 96,
|
||||
"recentWilsonLowerBound": 0.18305777843717666,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.8651409169640287,
|
||||
"selectionWeight": 0.8576131350021761,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.166666666666668,
|
||||
"waiting": 10599
|
||||
"throughputPerHour": 16.0,
|
||||
"waiting": 10595
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 783.6705882352942,
|
||||
"backlogHours": 793.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.0885229518750281,
|
||||
"queueFactor": 1.0478550187909124,
|
||||
"queueWeight": 1.0478550187909124,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.29411764705882354,
|
||||
"recentTerminal": 85,
|
||||
"recentWilsonLowerBound": 0.20785389608177998,
|
||||
"qualityFactor": 0.9706785084689942,
|
||||
"queueFactor": 1.0465395215787394,
|
||||
"queueWeight": 1.0465395215787394,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.2857142857142857,
|
||||
"recentTerminal": 84,
|
||||
"recentWilsonLowerBound": 0.20014898610655452,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.1406142381913469,
|
||||
"selectionWeight": 1.0158534218599056,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.166666666666666,
|
||||
"throughputPerHour": 14.0,
|
||||
"waiting": 11102
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2380.5555555555557,
|
||||
"backlogHours": 2295.964285714286,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8869915485550494,
|
||||
"queueWeight": 0.8869915485550494,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.42592592592592593,
|
||||
"recentTerminal": 54,
|
||||
"recentWilsonLowerBound": 0.30331621798657443,
|
||||
"queueFactor": 0.8922814052403417,
|
||||
"queueWeight": 0.8922814052403417,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"recentTerminal": 56,
|
||||
"recentWilsonLowerBound": 0.3076876241309292,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.2174788713876232,
|
||||
"selectionWeight": 2.2307035131008544,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.0,
|
||||
"waiting": 21425
|
||||
"throughputPerHour": 9.333333333333334,
|
||||
"waiting": 21429
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 7167.2307692307695,
|
||||
"backlogHours": 7169.538461538462,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.13987959280263654,
|
||||
"queueFactor": 0.7518280447533651,
|
||||
"queueWeight": 0.7518280447533651,
|
||||
"qualityFactor": 0.13554474593656948,
|
||||
"queueFactor": 0.7521819923623451,
|
||||
"queueWeight": 0.7521819923623451,
|
||||
"recentSuccess": 3,
|
||||
"recentSuccessRate": 0.23076923076923078,
|
||||
"recentTerminal": 13,
|
||||
"recentWilsonLowerBound": 0.08179379092465712,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.1051654007577031,
|
||||
"selectionWeight": 0.10195431705281671,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 2.1666666666666665,
|
||||
"waiting": 15529
|
||||
"waiting": 15534
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 2419.8857142857146,
|
||||
"backlogHours": 2289.4054054054054,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.1370045644321008,
|
||||
"queueFactor": 0.8848140325196124,
|
||||
"queueWeight": 0.8848140325196124,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.17142857142857143,
|
||||
"recentTerminal": 35,
|
||||
"recentWilsonLowerBound": 0.08102529944856719,
|
||||
"qualityFactor": 0.2806377979292184,
|
||||
"queueFactor": 0.8926643815661428,
|
||||
"queueWeight": 0.8926643815661428,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.21621621621621623,
|
||||
"recentTerminal": 37,
|
||||
"recentWilsonLowerBound": 0.11386376851955585,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.12122356112876018,
|
||||
"selectionWeight": 0.2505153663325699,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.833333333333333,
|
||||
"waiting": 14116
|
||||
"throughputPerHour": 6.166666666666667,
|
||||
"waiting": 14118
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 996.7415730337078,
|
||||
"backlogHours": 1031.581395348837,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.327903037837922,
|
||||
"queueFactor": 1.0107269458362962,
|
||||
"queueWeight": 1.0107269458362962,
|
||||
"qualityFactor": 1.392898003998393,
|
||||
"queueFactor": 1.0060535240225934,
|
||||
"queueWeight": 1.0060535240225934,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.3146067415730337,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.22750896837627055,
|
||||
"recentSuccessRate": 0.32558139534883723,
|
||||
"recentTerminal": 86,
|
||||
"recentWilsonLowerBound": 0.23585553745183332,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.3421473818006626,
|
||||
"selectionWeight": 1.4013299455266195,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 14785
|
||||
"throughputPerHour": 14.333333333333334,
|
||||
"waiting": 14786
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-20T01:34:03.467333+00:00",
|
||||
"queueAttemptedAt": "2026-09-20T01:44:25.642419+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-20T01:34:03.467333+00:00",
|
||||
"queueUpdatedAt": "2026-09-20T01:44:25.642419+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