state: generation 5953 (cycle)
This commit is contained in:
@@ -1307,7 +1307,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T01:08:06.669799+00:00",
|
||||
"generatedAt": "2026-09-12T01:11:21.663802+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
"2": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 427,
|
||||
"listingErrors": 428,
|
||||
"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": 2,
|
||||
"nextAccountIndex": 3,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-12T01:08:06.644427+00:00",
|
||||
"updatedAt": "2026-09-12T01:11:21.640059+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-12T01:06:37.490563+00:00",
|
||||
"generatedAt": "2026-09-12T01:09:16.774832+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 944.6577181208054,
|
||||
"backlogHours": 908.0516129032259,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7846906317107544,
|
||||
"queueFactor": 0.9973610633760447,
|
||||
"queueWeight": 0.9973610633760447,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.28187919463087246,
|
||||
"recentTerminal": 149,
|
||||
"recentWilsonLowerBound": 0.21582227454485578,
|
||||
"qualityFactor": 0.8567999850269815,
|
||||
"queueFactor": 1.0024401165761976,
|
||||
"queueWeight": 1.0024401165761976,
|
||||
"recentSuccess": 45,
|
||||
"recentSuccessRate": 0.2903225806451613,
|
||||
"recentTerminal": 155,
|
||||
"recentWilsonLowerBound": 0.22462146597970195,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.7826198828642582,
|
||||
"selectionWeight": 0.8588906768729317,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.833333333333332,
|
||||
"waiting": 23459
|
||||
"throughputPerHour": 25.833333333333332,
|
||||
"waiting": 23458
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1060.141935483871,
|
||||
"backlogHours": 1033.5471698113208,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.8677892245782903,
|
||||
"queueFactor": 0.980254803186324,
|
||||
"queueWeight": 0.980254803186324,
|
||||
"recentSuccess": 61,
|
||||
"recentSuccessRate": 0.3935483870967742,
|
||||
"recentTerminal": 155,
|
||||
"recentWilsonLowerBound": 0.32010425430460776,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.8309093587325287,
|
||||
"qualityFactor": 1.8354815049657893,
|
||||
"queueFactor": 0.9831628801088097,
|
||||
"queueWeight": 0.9831628801088097,
|
||||
"recentSuccess": 62,
|
||||
"recentSuccessRate": 0.389937106918239,
|
||||
"recentTerminal": 159,
|
||||
"recentWilsonLowerBound": 0.31757548319624335,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.804577282808618,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.833333333333332,
|
||||
"waiting": 27387
|
||||
"throughputPerHour": 26.5,
|
||||
"waiting": 27389
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 192.38028169014083,
|
||||
"backlogHours": 188.60689655172413,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.3966377321716501,
|
||||
"queueFactor": 1.266250114526178,
|
||||
"queueWeight": 1.266250114526178,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.21830985915492956,
|
||||
"recentTerminal": 142,
|
||||
"recentWilsonLowerBound": 0.158275038652959,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5022425737877555,
|
||||
"qualityFactor": 0.445707094741677,
|
||||
"queueFactor": 1.2689408634528647,
|
||||
"queueWeight": 1.2689408634528647,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.22758620689655173,
|
||||
"recentTerminal": 145,
|
||||
"recentWilsonLowerBound": 0.16689282461508925,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.5655759456485714,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.666666666666668,
|
||||
"waiting": 4553
|
||||
"throughputPerHour": 24.166666666666668,
|
||||
"waiting": 4558
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1457.8983050847457,
|
||||
"backlogHours": 1483.5517241379312,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 1.8857546950944746,
|
||||
"queueFactor": 0.9345111692818692,
|
||||
"queueWeight": 0.9345111692818692,
|
||||
"qualityFactor": 1.9639995341099485,
|
||||
"queueFactor": 0.9312785811633294,
|
||||
"queueWeight": 0.9312785811633294,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.4406779661016949,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.3215001223396273,
|
||||
"recentSuccessRate": 0.4482758620689655,
|
||||
"recentTerminal": 58,
|
||||
"recentWilsonLowerBound": 0.32749651292941145,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.762258825091512,
|
||||
"selectionWeight": 1.8290306995313528,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 14336
|
||||
"throughputPerHour": 9.666666666666666,
|
||||
"waiting": 14341
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 478.9189189189189,
|
||||
"backlogHours": 479.02702702702703,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5826072408769696,
|
||||
"queueFactor": 1.1043437612634988,
|
||||
"queueWeight": 1.1043437612634988,
|
||||
"queueFactor": 1.103369604426535,
|
||||
"queueWeight": 1.103369604426535,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.26126126126126126,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.18850083133789378,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.6433986717294218,
|
||||
"selectionWeight": 0.642831120902457,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.5,
|
||||
"waiting": 8860
|
||||
"waiting": 8862
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 58.5,
|
||||
"backlogHours": 55.808510638297875,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,103 +539,103 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.029850746268656716,
|
||||
"recentTerminal": 268,
|
||||
"recentWilsonLowerBound": 0.01520172178972306,
|
||||
"running": 24,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.03900709219858156,
|
||||
"recentTerminal": 282,
|
||||
"recentWilsonLowerBound": 0.021917982367853424,
|
||||
"running": 25,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 44.666666666666664,
|
||||
"waiting": 2613
|
||||
"throughputPerHour": 47.0,
|
||||
"waiting": 2623
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 175.08270676691728,
|
||||
"backlogHours": 178.98461538461538,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.12429860774738974,
|
||||
"queueFactor": 1.2842722342183117,
|
||||
"queueWeight": 1.2842722342183117,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.14285714285714285,
|
||||
"recentTerminal": 133,
|
||||
"recentWilsonLowerBound": 0.09340160831673865,
|
||||
"qualityFactor": 0.08173173833055351,
|
||||
"queueFactor": 1.27894734011548,
|
||||
"queueWeight": 1.27894734011548,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.12307692307692308,
|
||||
"recentTerminal": 130,
|
||||
"recentWilsonLowerBound": 0.07719563620964336,
|
||||
"running": 11,
|
||||
"selectionWeight": 0.15963325068196577,
|
||||
"selectionWeight": 0.10453058934087585,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.166666666666668,
|
||||
"waiting": 3881
|
||||
"throughputPerHour": 21.666666666666668,
|
||||
"waiting": 3878
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2262.0,
|
||||
"backlogHours": 2261.8536585365855,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.6322876213875649,
|
||||
"queueFactor": 0.8749227130825962,
|
||||
"queueWeight": 0.8749227130825962,
|
||||
"queueFactor": 0.8741890113234072,
|
||||
"queueWeight": 0.8741890113234072,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.3170731707317073,
|
||||
"recentTerminal": 41,
|
||||
"recentWilsonLowerBound": 0.19564433205311735,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.5532028011529496,
|
||||
"selectionWeight": 0.5527388906128242,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.833333333333333,
|
||||
"waiting": 15457
|
||||
"waiting": 15456
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 911.6666666666666,
|
||||
"backlogHours": 937.8000000000001,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.949373413783572,
|
||||
"queueFactor": 1.002693430926928,
|
||||
"queueWeight": 1.002693430926928,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 72,
|
||||
"recentWilsonLowerBound": 0.2353448606571184,
|
||||
"qualityFactor": 0.7991532511126906,
|
||||
"queueFactor": 0.9976046945693812,
|
||||
"queueWeight": 0.9976046945693812,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.3142857142857143,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.21762136964668136,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.9519304854974598,
|
||||
"selectionWeight": 0.7972390349904037,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.0,
|
||||
"waiting": 10940
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 10941
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 1006.0588235294117,
|
||||
"backlogHours": 977.3142857142858,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7522693659622268,
|
||||
"queueFactor": 0.9879843719967987,
|
||||
"queueWeight": 0.9879843719967987,
|
||||
"qualityFactor": 0.7034655212610453,
|
||||
"queueFactor": 0.9914478638798334,
|
||||
"queueWeight": 0.9914478638798334,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.3088235294117647,
|
||||
"recentTerminal": 68,
|
||||
"recentWilsonLowerBound": 0.21172233668927842,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.7432303771026206,
|
||||
"recentSuccessRate": 0.3,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.20536456738510148,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.6974493883673769,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.333333333333334,
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 11402
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -647,14 +647,14 @@
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.3458661682378459,
|
||||
"queueFactor": 0.8747301704879821,
|
||||
"queueWeight": 0.8747301704879821,
|
||||
"queueFactor": 0.8739881483985451,
|
||||
"queueWeight": 0.8739881483985451,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.39285714285714285,
|
||||
"recentTerminal": 56,
|
||||
"recentWilsonLowerBound": 0.27580225617512844,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.177269742796698,
|
||||
"selectionWeight": 1.1762710803704397,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.333333333333334,
|
||||
@@ -662,74 +662,74 @@
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 4090.0,
|
||||
"backlogHours": 4089.4285714285716,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8005437751464903,
|
||||
"queueWeight": 0.8005437751464903,
|
||||
"queueFactor": 0.7998814485411189,
|
||||
"queueWeight": 0.7998814485411189,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.5714285714285714,
|
||||
"recentTerminal": 21,
|
||||
"recentWilsonLowerBound": 0.3654621629703245,
|
||||
"running": 2,
|
||||
"selectionWeight": 2.001359437866226,
|
||||
"selectionWeight": 1.9997036213527972,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 3.5,
|
||||
"waiting": 14315
|
||||
"waiting": 14313
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 801.7974683544304,
|
||||
"backlogHours": 812.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 1.8062255933841662,
|
||||
"queueFactor": 1.0221952982030877,
|
||||
"queueWeight": 1.0221952982030877,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.4177215189873418,
|
||||
"recentTerminal": 79,
|
||||
"recentWilsonLowerBound": 0.3152645504906468,
|
||||
"running": 16,
|
||||
"selectionWeight": 1.8463153090513769,
|
||||
"qualityFactor": 1.7136867359232881,
|
||||
"queueFactor": 1.0193929226222604,
|
||||
"queueWeight": 1.0193929226222604,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.41025641025641024,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.3078173313444522,
|
||||
"running": 17,
|
||||
"selectionWeight": 1.7469201301918424,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.166666666666666,
|
||||
"waiting": 10557
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 10556
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 567.0,
|
||||
"backlogHours": 566.8695652173913,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.9703603617628915,
|
||||
"queueFactor": 1.0767282860034912,
|
||||
"queueWeight": 1.0767282860034912,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.42391304347826086,
|
||||
"qualityFactor": 2.106811605412198,
|
||||
"queueFactor": 1.0758520391505615,
|
||||
"queueWeight": 1.0758520391505615,
|
||||
"recentSuccess": 40,
|
||||
"recentSuccessRate": 0.43478260869565216,
|
||||
"recentTerminal": 92,
|
||||
"recentWilsonLowerBound": 0.3279782090086152,
|
||||
"running": 6,
|
||||
"selectionWeight": 2.121542735130177,
|
||||
"recentWilsonLowerBound": 0.3381140282933585,
|
||||
"running": 7,
|
||||
"selectionWeight": 2.2666175617887814,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.333333333333334,
|
||||
"waiting": 8694
|
||||
"waiting": 8692
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-12T00:57:55.213863+00:00",
|
||||
"queueAttemptedAt": "2026-09-12T01:09:16.774832+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-12T00:57:55.213863+00:00",
|
||||
"queueUpdatedAt": "2026-09-12T01:09:16.774832+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user