state: generation 10082 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T01:54:01.045872+00:00",
|
||||
"generatedAt": "2026-09-20T01:57:15.660853+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -67,7 +67,7 @@
|
||||
"6": {
|
||||
"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": 6,
|
||||
"nextAccountIndex": 7,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-20T01:54:01.019796+00:00",
|
||||
"updatedAt": "2026-09-20T01:57:15.635612+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T01:51:25.171456+00:00",
|
||||
"generatedAt": "2026-09-20T01:55:09.984849+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1116.2857142857142,
|
||||
"backlogHours": 1125.2640000000001,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.7890574027597195,
|
||||
"queueFactor": 0.9942149899223116,
|
||||
"queueWeight": 0.9942149899223116,
|
||||
"recentSuccess": 43,
|
||||
"recentSuccessRate": 0.3412698412698413,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.2642758158775134,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.7787076876551915,
|
||||
"qualityFactor": 1.8364587650777615,
|
||||
"queueFactor": 0.9936570325830414,
|
||||
"queueWeight": 0.9936570325830414,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.336,
|
||||
"recentTerminal": 125,
|
||||
"recentWilsonLowerBound": 0.25918260494074635,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.8248101669682852,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 23442
|
||||
"throughputPerHour": 20.833333333333332,
|
||||
"waiting": 23443
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1280.6564885496184,
|
||||
"backlogHours": 1261.578947368421,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.2938261695186206,
|
||||
"queueFactor": 0.9739389030835843,
|
||||
"queueWeight": 0.9739389030835843,
|
||||
"recentSuccess": 49,
|
||||
"recentSuccessRate": 0.37404580152671757,
|
||||
"recentTerminal": 131,
|
||||
"recentWilsonLowerBound": 0.29588254392287383,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9767591974791724,
|
||||
"queueWeight": 0.9767591974791724,
|
||||
"recentSuccess": 50,
|
||||
"recentSuccessRate": 0.37593984962406013,
|
||||
"recentTerminal": 133,
|
||||
"recentWilsonLowerBound": 0.29819216386268604,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.2340465434053853,
|
||||
"selectionWeight": 2.441897993697931,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.833333333333332,
|
||||
"waiting": 27961
|
||||
"throughputPerHour": 22.166666666666668,
|
||||
"waiting": 27965
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 180.59627329192548,
|
||||
"backlogHours": 187.58709677419355,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.15493260953619414,
|
||||
"qualityFactor": 0.18075912574795627,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.13043478260869565,
|
||||
"recentTerminal": 161,
|
||||
"recentWilsonLowerBound": 0.08691831797877285,
|
||||
"recentSuccessRate": 0.13548387096774195,
|
||||
"recentTerminal": 155,
|
||||
"recentWilsonLowerBound": 0.09035094342918001,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2014123923970524,
|
||||
"selectionWeight": 0.23498686347234315,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 26.833333333333332,
|
||||
"throughputPerHour": 25.833333333333332,
|
||||
"waiting": 4846
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 2170.2439024390246,
|
||||
"backlogHours": 2225.85,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 1.9929411188606294,
|
||||
"queueFactor": 0.8998504332656039,
|
||||
"queueWeight": 0.8998504332656039,
|
||||
"qualityFactor": 2.2647189966140684,
|
||||
"queueFactor": 0.8970162079174665,
|
||||
"queueWeight": 0.8970162079174665,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.4146341463414634,
|
||||
"recentTerminal": 41,
|
||||
"recentWilsonLowerBound": 0.2775633082533015,
|
||||
"recentSuccessRate": 0.425,
|
||||
"recentTerminal": 40,
|
||||
"recentWilsonLowerBound": 0.2850916852481588,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.7933489292795748,
|
||||
"selectionWeight": 2.0314896463414014,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.833333333333333,
|
||||
"waiting": 14830
|
||||
"throughputPerHour": 6.666666666666667,
|
||||
"waiting": 14839
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 498.3853211009174,
|
||||
"backlogHours": 517.4857142857143,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.47708647457732156,
|
||||
"queueFactor": 1.1220490061818162,
|
||||
"queueWeight": 1.1220490061818162,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.21100917431192662,
|
||||
"recentTerminal": 109,
|
||||
"recentWilsonLowerBound": 0.1449225546231727,
|
||||
"qualityFactor": 0.49356276986850794,
|
||||
"queueFactor": 1.1164516491539613,
|
||||
"queueWeight": 1.1164516491539613,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.20952380952380953,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.1426344996383833,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.53531440466227,
|
||||
"selectionWeight": 0.5510389683806928,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.166666666666668,
|
||||
"waiting": 9054
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 9056
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 57.48091603053435,
|
||||
"backlogHours": 56.86363636363637,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,197 +539,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.03816793893129771,
|
||||
"recentTerminal": 262,
|
||||
"recentWilsonLowerBound": 0.0208617114039803,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.03409090909090909,
|
||||
"recentTerminal": 264,
|
||||
"recentWilsonLowerBound": 0.01803692222215706,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 43.666666666666664,
|
||||
"waiting": 2510
|
||||
"throughputPerHour": 44.0,
|
||||
"waiting": 2502
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 161.96703296703296,
|
||||
"backlogHours": 161.34426229508196,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.3592215834785861,
|
||||
"qualityFactor": 0.4119357312765005,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.17582417582417584,
|
||||
"recentTerminal": 182,
|
||||
"recentWilsonLowerBound": 0.12738556469467538,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.46698805852216196,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.18032786885245902,
|
||||
"recentTerminal": 183,
|
||||
"recentWilsonLowerBound": 0.131382308387537,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5355164506594506,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 30.333333333333332,
|
||||
"waiting": 4913
|
||||
"throughputPerHour": 30.5,
|
||||
"waiting": 4921
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2589.7297297297296,
|
||||
"backlogHours": 2456.6153846153848,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.1743974586803485,
|
||||
"queueFactor": 0.8763113675873454,
|
||||
"queueWeight": 0.8763113675873454,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.35135135135135137,
|
||||
"recentTerminal": 37,
|
||||
"recentWilsonLowerBound": 0.21825406631100872,
|
||||
"qualityFactor": 1.3774203899526452,
|
||||
"queueFactor": 0.8838409090409954,
|
||||
"queueWeight": 0.8838409090409954,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.358974358974359,
|
||||
"recentTerminal": 39,
|
||||
"recentWilsonLowerBound": 0.22741884696491108,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.029137843107279,
|
||||
"selectionWeight": 1.2174204895873484,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.166666666666667,
|
||||
"waiting": 15970
|
||||
"throughputPerHour": 6.5,
|
||||
"waiting": 15968
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 662.1875,
|
||||
"backlogHours": 690.8478260869565,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7976125135663115,
|
||||
"queueFactor": 1.0752252759520884,
|
||||
"queueWeight": 1.0752252759520884,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.2604166666666667,
|
||||
"recentTerminal": 96,
|
||||
"recentWilsonLowerBound": 0.18305777843717666,
|
||||
"qualityFactor": 0.7522730183414474,
|
||||
"queueFactor": 1.0690975025907534,
|
||||
"queueWeight": 1.0690975025907534,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 92,
|
||||
"recentWilsonLowerBound": 0.17275134731188044,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.8576131350021761,
|
||||
"selectionWeight": 0.8042532051752495,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.0,
|
||||
"waiting": 10595
|
||||
"throughputPerHour": 15.333333333333334,
|
||||
"waiting": 10593
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 793.0,
|
||||
"backlogHours": 802.4819277108434,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.9706785084689942,
|
||||
"queueFactor": 1.0465395215787394,
|
||||
"queueWeight": 1.0465395215787394,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.2857142857142857,
|
||||
"recentTerminal": 84,
|
||||
"recentWilsonLowerBound": 0.20014898610655452,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.0158534218599056,
|
||||
"qualityFactor": 1.193868556890326,
|
||||
"queueFactor": 1.0453443716140984,
|
||||
"queueWeight": 1.0453443716140984,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.30120481927710846,
|
||||
"recentTerminal": 83,
|
||||
"recentWilsonLowerBound": 0.21310549002452867,
|
||||
"running": 5,
|
||||
"selectionWeight": 1.2480037763923484,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.0,
|
||||
"waiting": 11102
|
||||
"throughputPerHour": 13.833333333333334,
|
||||
"waiting": 11101
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2295.964285714286,
|
||||
"backlogHours": 2426.0377358490564,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8922814052403417,
|
||||
"queueWeight": 0.8922814052403417,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"recentTerminal": 56,
|
||||
"recentWilsonLowerBound": 0.3076876241309292,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.2307035131008544,
|
||||
"qualityFactor": 2.3981422855929626,
|
||||
"queueFactor": 0.8855030095508157,
|
||||
"queueWeight": 0.8855030095508157,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.41509433962264153,
|
||||
"recentTerminal": 53,
|
||||
"recentWilsonLowerBound": 0.2926070830912865,
|
||||
"running": 5,
|
||||
"selectionWeight": 2.12356221122364,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.333333333333334,
|
||||
"waiting": 21429
|
||||
"throughputPerHour": 8.833333333333334,
|
||||
"waiting": 21430
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 7169.538461538462,
|
||||
"backlogHours": 7171.384615384616,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.13554474593656948,
|
||||
"queueFactor": 0.7521819923623451,
|
||||
"queueWeight": 0.7521819923623451,
|
||||
"qualityFactor": 0.14522221342659863,
|
||||
"queueFactor": 0.7526346732989496,
|
||||
"queueWeight": 0.7526346732989496,
|
||||
"recentSuccess": 3,
|
||||
"recentSuccessRate": 0.23076923076923078,
|
||||
"recentTerminal": 13,
|
||||
"recentWilsonLowerBound": 0.08179379092465712,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.10195431705281671,
|
||||
"selectionWeight": 0.1092992731580784,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 2.1666666666666665,
|
||||
"waiting": 15534
|
||||
"waiting": 15538
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 2289.4054054054054,
|
||||
"backlogHours": 2230.421052631579,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.2806377979292184,
|
||||
"queueFactor": 0.8926643815661428,
|
||||
"queueWeight": 0.8926643815661428,
|
||||
"qualityFactor": 0.28286240200477497,
|
||||
"queueFactor": 0.8967402140070748,
|
||||
"queueWeight": 0.8967402140070748,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.21621621621621623,
|
||||
"recentTerminal": 37,
|
||||
"recentWilsonLowerBound": 0.11386376851955585,
|
||||
"recentSuccessRate": 0.21052631578947367,
|
||||
"recentTerminal": 38,
|
||||
"recentWilsonLowerBound": 0.11074660352095932,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.2505153663325699,
|
||||
"selectionWeight": 0.25365409090831714,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.166666666666667,
|
||||
"waiting": 14118
|
||||
"throughputPerHour": 6.333333333333333,
|
||||
"waiting": 14126
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1031.581395348837,
|
||||
"backlogHours": 1031.7906976744187,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.392898003998393,
|
||||
"queueFactor": 1.0060535240225934,
|
||||
"queueWeight": 1.0060535240225934,
|
||||
"qualityFactor": 1.4923465297046494,
|
||||
"queueFactor": 1.0066672342948153,
|
||||
"queueWeight": 1.0066672342948153,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.32558139534883723,
|
||||
"recentTerminal": 86,
|
||||
"recentWilsonLowerBound": 0.23585553745183332,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.4013299455266195,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.502296353667245,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.333333333333334,
|
||||
"waiting": 14786
|
||||
"waiting": 14789
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-20T01:44:25.642419+00:00",
|
||||
"queueAttemptedAt": "2026-09-20T01:55:09.984849+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-20T01:44:25.642419+00:00",
|
||||
"queueUpdatedAt": "2026-09-20T01:55:09.984849+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