state: generation 9964 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T19:09:37.486957+00:00",
|
||||
"generatedAt": "2026-09-19T19:13:01.764249+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 726,
|
||||
"listingErrors": 727,
|
||||
"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": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T19:09:37.463687+00:00",
|
||||
"updatedAt": "2026-09-19T19:13:01.736339+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T19:07:39.561342+00:00",
|
||||
"generatedAt": "2026-09-19T19:10:47.660829+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1177.310924369748,
|
||||
"backlogHours": 1148.409836065574,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.9708603312611168,
|
||||
"queueFactor": 0.9680568743625104,
|
||||
"queueWeight": 0.9680568743625104,
|
||||
"recentSuccess": 37,
|
||||
"recentSuccessRate": 0.31092436974789917,
|
||||
"recentTerminal": 119,
|
||||
"recentWilsonLowerBound": 0.23476920298350337,
|
||||
"qualityFactor": 1.1169565816685574,
|
||||
"queueFactor": 0.9864212433809189,
|
||||
"queueWeight": 0.9864212433809189,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.319672131147541,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.24351046547889818,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.9398480177231882,
|
||||
"selectionWeight": 1.1017897000919992,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.833333333333332,
|
||||
"waiting": 23350
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"waiting": 23351
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1442.5862068965519,
|
||||
"backlogHours": 1406.1176470588236,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9389950072747899,
|
||||
"queueWeight": 0.9389950072747899,
|
||||
"queueFactor": 0.9569157511915647,
|
||||
"queueWeight": 0.9569157511915647,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.4482758620689655,
|
||||
"recentTerminal": 116,
|
||||
"recentWilsonLowerBound": 0.3608783144793255,
|
||||
"recentSuccessRate": 0.4369747899159664,
|
||||
"recentTerminal": 119,
|
||||
"recentWilsonLowerBound": 0.35120830331317215,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.3474875181869748,
|
||||
"selectionWeight": 2.3922893779789116,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.333333333333332,
|
||||
"waiting": 27890
|
||||
"throughputPerHour": 19.833333333333332,
|
||||
"waiting": 27888
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 167.82758620689654,
|
||||
"backlogHours": 169.88372093023256,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.216226950259675,
|
||||
"queueFactor": 1.2965971036859245,
|
||||
"queueWeight": 1.2965971036859245,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.16666666666666666,
|
||||
"recentTerminal": 174,
|
||||
"recentWilsonLowerBound": 0.11862200125956367,
|
||||
"qualityFactor": 0.2575458789658392,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.1744186046511628,
|
||||
"recentTerminal": 172,
|
||||
"recentWilsonLowerBound": 0.12499412236734236,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2803592374455351,
|
||||
"selectionWeight": 0.334809642655591,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 29.0,
|
||||
"waiting": 4867
|
||||
"throughputPerHour": 28.666666666666668,
|
||||
"waiting": 4870
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1342.8181818181818,
|
||||
"backlogHours": 1266.1714285714286,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.32545417509550284,
|
||||
"queueFactor": 0.9491436956873586,
|
||||
"queueWeight": 0.9491436956873586,
|
||||
"qualityFactor": 0.30204756911835046,
|
||||
"queueFactor": 0.9720823901566868,
|
||||
"queueWeight": 0.9720823901566868,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.22727272727272727,
|
||||
"recentTerminal": 66,
|
||||
"recentWilsonLowerBound": 0.1428510508724467,
|
||||
"recentSuccessRate": 0.21428571428571427,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.13438585667978445,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.30890277852702624,
|
||||
"selectionWeight": 0.2936151229295832,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.0,
|
||||
"waiting": 14771
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 14772
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 408.45112781954884,
|
||||
"backlogHours": 399.5735294117647,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3968303135546109,
|
||||
"queueFactor": 1.134654224620025,
|
||||
"queueWeight": 1.134654224620025,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.21804511278195488,
|
||||
"recentTerminal": 133,
|
||||
"recentWilsonLowerBound": 0.15632434518405217,
|
||||
"qualityFactor": 0.4379696691358582,
|
||||
"queueFactor": 1.155679595851832,
|
||||
"queueWeight": 1.155679595851832,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.22058823529411764,
|
||||
"recentTerminal": 136,
|
||||
"recentWilsonLowerBound": 0.15911201250331414,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.45026519173202845,
|
||||
"selectionWeight": 0.5061526102222892,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.166666666666668,
|
||||
"waiting": 9054
|
||||
"throughputPerHour": 22.666666666666668,
|
||||
"waiting": 9057
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 42.01634877384196,
|
||||
"backlogHours": 41.98365122615804,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -548,188 +548,188 @@
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 61.166666666666664,
|
||||
"waiting": 2570
|
||||
"waiting": 2568
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 107.2202166064982,
|
||||
"backlogHours": 105.45907473309607,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.09863981036252195,
|
||||
"qualityFactor": 0.11867953367214609,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.11552346570397112,
|
||||
"recentTerminal": 277,
|
||||
"recentWilsonLowerBound": 0.08302903235830981,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.12823175347127855,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.12099644128113879,
|
||||
"recentTerminal": 281,
|
||||
"recentWilsonLowerBound": 0.08789105839303797,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.1542833937737899,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 46.166666666666664,
|
||||
"waiting": 4950
|
||||
"throughputPerHour": 46.833333333333336,
|
||||
"waiting": 4939
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3316.137931034483,
|
||||
"backlogHours": 3205.8,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.838907631650255,
|
||||
"queueFactor": 0.8287807619390722,
|
||||
"queueWeight": 0.8287807619390722,
|
||||
"qualityFactor": 1.797747353242499,
|
||||
"queueFactor": 0.8456418904479845,
|
||||
"queueWeight": 0.8456418904479845,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.4827586206896552,
|
||||
"recentTerminal": 29,
|
||||
"recentWilsonLowerBound": 0.3138581933079522,
|
||||
"recentSuccessRate": 0.4666666666666667,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.3023212722412823,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.5240512680946732,
|
||||
"selectionWeight": 1.5202504703438475,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.833333333333333,
|
||||
"waiting": 16028
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 16029
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 614.3653846153846,
|
||||
"backlogHours": 596.8598130841121,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.6333029985414027,
|
||||
"queueFactor": 1.0672607518358688,
|
||||
"queueWeight": 1.0672607518358688,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.2692307692307692,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.19333139862414106,
|
||||
"qualityFactor": 0.756767562289744,
|
||||
"queueFactor": 1.0881683782327773,
|
||||
"queueWeight": 1.0881683782327773,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.2803738317757009,
|
||||
"recentTerminal": 107,
|
||||
"recentWilsonLowerBound": 0.20401679054167657,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.6758994343632075,
|
||||
"selectionWeight": 0.823490530956003,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 10649
|
||||
"throughputPerHour": 17.833333333333332,
|
||||
"waiting": 10644
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 661.8415841584159,
|
||||
"backlogHours": 642.9807692307693,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.3123486040081962,
|
||||
"queueFactor": 1.0554105759006926,
|
||||
"queueWeight": 1.0554105759006926,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.2079207920792079,
|
||||
"recentTerminal": 101,
|
||||
"recentWilsonLowerBound": 0.14020699355070068,
|
||||
"qualityFactor": 0.3519125064744689,
|
||||
"queueFactor": 1.0760866771942306,
|
||||
"queueWeight": 1.0760866771942306,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.21153846153846154,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.14405120914153324,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.32965602003806777,
|
||||
"selectionWeight": 0.37868835975520443,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.833333333333332,
|
||||
"waiting": 11141
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 11145
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1707.28,
|
||||
"backlogHours": 1707.6,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.2219817547968475,
|
||||
"queueFactor": 0.9155642711376972,
|
||||
"queueWeight": 0.9155642711376972,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.36,
|
||||
"qualityFactor": 1.4312228716695221,
|
||||
"queueFactor": 0.9294350157982144,
|
||||
"queueWeight": 0.9294350157982144,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.37333333333333335,
|
||||
"recentTerminal": 75,
|
||||
"recentWilsonLowerBound": 0.26064766399338823,
|
||||
"recentWilsonLowerBound": 0.27255803135314144,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.1188028346741399,
|
||||
"selectionWeight": 1.3302286523409281,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.5,
|
||||
"waiting": 21341
|
||||
"waiting": 21345
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 10577.333333333334,
|
||||
"backlogHours": 7932.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.3993077131979383,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"qualityFactor": 1.2231983318153894,
|
||||
"queueFactor": 0.738185380656324,
|
||||
"queueWeight": 0.738185380656324,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.6666666666666666,
|
||||
"recentTerminal": 9,
|
||||
"recentWilsonLowerBound": 0.35419734749908977,
|
||||
"recentSuccessRate": 0.5,
|
||||
"recentTerminal": 12,
|
||||
"recentWilsonLowerBound": 0.2537781703934222,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.6795153992385567,
|
||||
"selectionWeight": 0.9029471261893237,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 1.5,
|
||||
"waiting": 15866
|
||||
"throughputPerHour": 2.0,
|
||||
"waiting": 15865
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1606.9615384615386,
|
||||
"backlogHours": 1606.7307692307693,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9239186357200114,
|
||||
"queueWeight": 0.9239186357200114,
|
||||
"queueFactor": 0.9379625216024374,
|
||||
"queueWeight": 0.9379625216024374,
|
||||
"recentSuccess": 3,
|
||||
"recentSuccessRate": 0.057692307692307696,
|
||||
"recentTerminal": 52,
|
||||
"recentWilsonLowerBound": 0.0198138126905732,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04619593178600057,
|
||||
"selectionWeight": 0.04689812608012187,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 8.666666666666666,
|
||||
"waiting": 13927
|
||||
"waiting": 13925
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 948.1935483870968,
|
||||
"backlogHours": 948.3225806451613,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.8186705266980894,
|
||||
"queueFactor": 1.0,
|
||||
"queueWeight": 1.0,
|
||||
"qualityFactor": 0.8690812471936071,
|
||||
"queueFactor": 1.0151577589944931,
|
||||
"queueWeight": 1.0151577589944931,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.3010752688172043,
|
||||
"recentTerminal": 93,
|
||||
"recentWilsonLowerBound": 0.21726167583661848,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.8186705266980894,
|
||||
"selectionWeight": 0.8822545712852013,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.5,
|
||||
"waiting": 14697
|
||||
"waiting": 14699
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T19:00:27.719369+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T19:10:47.660829+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T19:00:27.719369+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T19:10:47.660829+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