state: generation 10040 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T23:29:29.981234+00:00",
|
||||
"generatedAt": "2026-09-19T23:32:56.161747+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
"0": {
|
||||
"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": 0,
|
||||
"nextAccountIndex": 1,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T23:29:29.955825+00:00",
|
||||
"updatedAt": "2026-09-19T23:32:56.136529+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T23:27:18.307743+00:00",
|
||||
"generatedAt": "2026-09-19T23:30:36.258474+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1260.3783783783783,
|
||||
"backlogHours": 1271.7272727272727,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.3494372766790432,
|
||||
"queueFactor": 0.9751948162823254,
|
||||
"queueWeight": 0.9751948162823254,
|
||||
"recentSuccess": 37,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.2525100321955306,
|
||||
"qualityFactor": 1.632392362878571,
|
||||
"queueFactor": 0.9866252177865985,
|
||||
"queueWeight": 0.9866252177865985,
|
||||
"recentSuccess": 38,
|
||||
"recentSuccessRate": 0.34545454545454546,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.26316254590275023,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.3159642371155411,
|
||||
"selectionWeight": 1.6105594705382502,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.5,
|
||||
"waiting": 23317
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 23315
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1368.8852459016393,
|
||||
"backlogHours": 1380.2479338842975,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.5114648435501206,
|
||||
"queueFactor": 0.9631889006853398,
|
||||
"queueWeight": 0.9631889006853398,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.3442622950819672,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.2658660516578213,
|
||||
"qualityFactor": 1.597969933547606,
|
||||
"queueFactor": 0.974580558505192,
|
||||
"queueWeight": 0.974580558505192,
|
||||
"recentSuccess": 41,
|
||||
"recentSuccessRate": 0.33884297520661155,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.2606254540535897,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.4558261610835797,
|
||||
"selectionWeight": 1.5573504303113304,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"waiting": 27834
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 27835
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 161.63333333333333,
|
||||
"backlogHours": 163.4494382022472,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.2593207220284051,
|
||||
"qualityFactor": 0.22258730154388373,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.16666666666666666,
|
||||
"recentTerminal": 180,
|
||||
"recentWilsonLowerBound": 0.11931105652108458,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.15168539325842698,
|
||||
"recentTerminal": 178,
|
||||
"recentWilsonLowerBound": 0.10638855522742541,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.33711693863692666,
|
||||
"selectionWeight": 0.28936349200704886,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 30.0,
|
||||
"throughputPerHour": 29.666666666666668,
|
||||
"waiting": 4849
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1846.75,
|
||||
"backlogHours": 1885.9148936170213,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.9645401742915045,
|
||||
"queueFactor": 0.920884810520577,
|
||||
"queueWeight": 0.920884810520577,
|
||||
"qualityFactor": 1.119175112620843,
|
||||
"queueFactor": 0.9300001013662774,
|
||||
"queueWeight": 0.9300001013662774,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 48,
|
||||
"recentWilsonLowerBound": 0.21676601370896784,
|
||||
"recentSuccessRate": 0.3404255319148936,
|
||||
"recentTerminal": 47,
|
||||
"recentWilsonLowerBound": 0.2216726071376219,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.8882303956419165,
|
||||
"selectionWeight": 1.040832968183999,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.0,
|
||||
"waiting": 14774
|
||||
"throughputPerHour": 7.833333333333333,
|
||||
"waiting": 14773
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 516.3428571428572,
|
||||
"backlogHours": 506.41121495327104,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.6019262289538612,
|
||||
"queueFactor": 1.1148740316192838,
|
||||
"queueWeight": 1.1148740316192838,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.24761904761904763,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.17494869705401506,
|
||||
"qualityFactor": 0.5733561614394117,
|
||||
"queueFactor": 1.132754541848893,
|
||||
"queueWeight": 1.132754541848893,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.2336448598130841,
|
||||
"recentTerminal": 107,
|
||||
"recentWilsonLowerBound": 0.1635605614587961,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.6710719216111832,
|
||||
"selectionWeight": 0.6494717959675407,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 9036
|
||||
"throughputPerHour": 17.833333333333332,
|
||||
"waiting": 9031
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 44.767857142857146,
|
||||
"backlogHours": 45.722891566265055,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -540,196 +540,196 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.03571428571428571,
|
||||
"recentTerminal": 336,
|
||||
"recentWilsonLowerBound": 0.020545856432680327,
|
||||
"recentSuccessRate": 0.03614457831325301,
|
||||
"recentTerminal": 332,
|
||||
"recentWilsonLowerBound": 0.020794822036012173,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 56.0,
|
||||
"waiting": 2507
|
||||
"throughputPerHour": 55.333333333333336,
|
||||
"waiting": 2530
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 122.19087136929461,
|
||||
"backlogHours": 123.38912133891213,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.14679276154454085,
|
||||
"qualityFactor": 0.151641588982021,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.12863070539419086,
|
||||
"recentTerminal": 241,
|
||||
"recentWilsonLowerBound": 0.09211867867416446,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.19083059000790312,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.12552301255230125,
|
||||
"recentTerminal": 239,
|
||||
"recentWilsonLowerBound": 0.08935736205295211,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.19713406567662728,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 40.166666666666664,
|
||||
"waiting": 4908
|
||||
"throughputPerHour": 39.833333333333336,
|
||||
"waiting": 4915
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3195.6,
|
||||
"backlogHours": 3195.4,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.0052607593489453,
|
||||
"queueFactor": 0.8481714775940568,
|
||||
"queueWeight": 0.8481714775940568,
|
||||
"qualityFactor": 2.2149439175093977,
|
||||
"queueFactor": 0.8592756891666785,
|
||||
"queueWeight": 0.8592756891666785,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.4666666666666667,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.3023212722412823,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.7008049812183752,
|
||||
"selectionWeight": 1.9032474611834305,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 15978
|
||||
"waiting": 15977
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 589.6666666666666,
|
||||
"backlogHours": 600.6792452830189,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.901357902294274,
|
||||
"queueFactor": 1.0928877020787369,
|
||||
"queueWeight": 1.0928877020787369,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.28703703703703703,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.21019243295848952,
|
||||
"qualityFactor": 1.1304289600425634,
|
||||
"queueFactor": 1.104116539175424,
|
||||
"queueWeight": 1.104116539175424,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.3018867924528302,
|
||||
"recentTerminal": 106,
|
||||
"recentWilsonLowerBound": 0.22268303619470342,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.9850829665888998,
|
||||
"selectionWeight": 1.2481253111458688,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.0,
|
||||
"waiting": 10614
|
||||
"throughputPerHour": 17.666666666666668,
|
||||
"waiting": 10612
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 844.632911392405,
|
||||
"backlogHours": 855.2307692307693,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7358859893260001,
|
||||
"queueFactor": 1.0355386805428506,
|
||||
"queueWeight": 1.0355386805428506,
|
||||
"qualityFactor": 0.8370194132968033,
|
||||
"queueFactor": 1.0471256832361735,
|
||||
"queueWeight": 1.0471256832361735,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.27848101265822783,
|
||||
"recentTerminal": 79,
|
||||
"recentWilsonLowerBound": 0.19168037554546477,
|
||||
"recentSuccessRate": 0.28205128205128205,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.1942519701528857,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.7620384064166165,
|
||||
"selectionWeight": 0.8764645250303562,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.166666666666666,
|
||||
"waiting": 11121
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 11118
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2064.3870967741937,
|
||||
"backlogHours": 2065.1612903225805,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9056238583916081,
|
||||
"queueWeight": 0.9056238583916081,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.45161290322580644,
|
||||
"queueFactor": 0.9174200198591738,
|
||||
"queueWeight": 0.9174200198591738,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.43548387096774194,
|
||||
"recentTerminal": 62,
|
||||
"recentWilsonLowerBound": 0.3341951476826002,
|
||||
"recentWilsonLowerBound": 0.3194239439101423,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.26405964597902,
|
||||
"selectionWeight": 2.2935500496479344,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.333333333333334,
|
||||
"waiting": 21332
|
||||
"waiting": 21340
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 11644.5,
|
||||
"backlogHours": 9315.6,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.08400687017624642,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"qualityFactor": 0.05570487593367424,
|
||||
"queueFactor": 0.7318628197525974,
|
||||
"queueWeight": 0.7318628197525974,
|
||||
"recentSuccess": 2,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 8,
|
||||
"recentWilsonLowerBound": 0.07147768885802765,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 10,
|
||||
"recentWilsonLowerBound": 0.05668094798069332,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.058804809123372485,
|
||||
"selectionWeight": 0.04076832757478743,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 1.3333333333333333,
|
||||
"throughputPerHour": 1.6666666666666667,
|
||||
"waiting": 15526
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1817.4782608695652,
|
||||
"backlogHours": 1858.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9230944546217519,
|
||||
"queueWeight": 0.9230944546217519,
|
||||
"queueFactor": 0.9320827122183138,
|
||||
"queueWeight": 0.9320827122183138,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.10869565217391304,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.047330760827426877,
|
||||
"recentSuccessRate": 0.1111111111111111,
|
||||
"recentTerminal": 45,
|
||||
"recentWilsonLowerBound": 0.04840400437825557,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.046154722731087595,
|
||||
"selectionWeight": 0.0466041356109157,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
"waiting": 13934
|
||||
"throughputPerHour": 7.5,
|
||||
"waiting": 13935
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1066.0481927710844,
|
||||
"backlogHours": 1053.357142857143,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.2609182390443097,
|
||||
"queueFactor": 1.0,
|
||||
"queueWeight": 1.0,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.3373493975903614,
|
||||
"recentTerminal": 83,
|
||||
"recentWilsonLowerBound": 0.2448415401300969,
|
||||
"qualityFactor": 1.4884480005600818,
|
||||
"queueFactor": 1.0149039966527178,
|
||||
"queueWeight": 1.0149039966527178,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.34523809523809523,
|
||||
"recentTerminal": 84,
|
||||
"recentWilsonLowerBound": 0.2523486284686916,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.2609182390443097,
|
||||
"selectionWeight": 1.5106318245781738,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.833333333333334,
|
||||
"throughputPerHour": 14.0,
|
||||
"waiting": 14747
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T23:17:49.456139+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T23:30:36.258474+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T23:17:49.456139+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T23:30:36.258474+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