CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 18919 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-11-01 21:00:46 +00:00
parent a036dfb71b
commit 68fc9c47de
9 changed files with 1041 additions and 1038 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-11-01T20:50:57.612596+00:00",
"lastSyncTime": "2026-11-01T20:50:57.358677+00:00",
"generatedAt": "2026-11-01T21:00:36.353103+00:00",
"lastSyncTime": "2026-11-01T21:00:36.112004+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -24,16 +24,16 @@
"unresolvedFailureCount": 3
},
"unknown": {
"attributableFailureCount": 142,
"decisionFailureRate": 0.9467,
"decisionSuccessRate": 0.0533,
"decisionTotal": 150,
"attributableFailureCount": 143,
"decisionFailureRate": 0.947,
"decisionSuccessRate": 0.053,
"decisionTotal": 151,
"failureBreakdown": {
"ambiguous_runtime": 59,
"backend_operator": 5,
"configuration_launch": 33,
"context_length": 5,
"framework_architecture_unsupported": 63,
"framework_architecture_unsupported": 64,
"memory_capacity": 1,
"model_load": 17,
"platform_storage": 1,
@@ -43,14 +43,14 @@
"任务失败_原因未确认": 146,
"参数/模板问题": 114
},
"failureCount": 462,
"failureCount": 463,
"failureRate": 0.983,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.017,
"total": 470,
"total": 471,
"unresolvedFailureCount": 319
}
},
@@ -754,17 +754,19 @@
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-25T10:43:51+00:00",
"evidenceCount": 2,
"expiresAt": "2026-12-01T21:00:36.112004+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-10-26T10:43:51+00:00",
"latestFailureAt": "2026-11-01T21:00:36.112004+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-decay-g16-v2_B",
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B"
],
"sourceTaskIds": [
"5009297",
"5010580"
],
"targetGpu": "Sunrise_pt-200-x1",
@@ -2868,14 +2870,14 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 188,
"attributableFailureCount": 189,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 188,
"decisionTotal": 189,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 12,
"framework_architecture_unsupported": 68,
"framework_architecture_unsupported": 69,
"memory_capacity": 1,
"platform_infrastructure": 2,
"platform_storage": 1,
@@ -2883,7 +2885,7 @@
"runtime_memory": 1,
"tokenizer_compatibility": 105
},
"failureCount": 196,
"failureCount": 197,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2893,7 +2895,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 196,
"total": 197,
"unresolvedFailureCount": 5
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -3410,14 +3412,14 @@
"unresolvedFailureCount": 1595
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 197,
"attributableFailureCount": 198,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 197,
"decisionTotal": 198,
"failureBreakdown": {
"ambiguous_runtime": 56,
"backend_operator": 12,
"framework_architecture_unsupported": 68,
"framework_architecture_unsupported": 69,
"memory_capacity": 10,
"platform_infrastructure": 2,
"platform_storage": 1,
@@ -3425,14 +3427,14 @@
"runtime_memory": 1,
"tokenizer_compatibility": 105
},
"failureCount": 256,
"failureCount": 257,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"total": 256,
"total": 257,
"unresolvedFailureCount": 56
},
"vllm_tokenizer_patch": {
@@ -3455,7 +3457,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-11-01T20:50:57.607495+00:00",
"generatedAt": "2026-11-01T21:00:36.348216+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3796,16 +3798,16 @@
"unresolvedFailureCount": 338
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 1044,
"decisionFailureRate": 0.9062,
"decisionSuccessRate": 0.0938,
"decisionTotal": 1152,
"attributableFailureCount": 1045,
"decisionFailureRate": 0.9063,
"decisionSuccessRate": 0.0937,
"decisionTotal": 1153,
"failureBreakdown": {
"ambiguous_runtime": 119,
"architecture_compatibility": 13,
"backend_operator": 45,
"context_length": 44,
"framework_architecture_unsupported": 390,
"framework_architecture_unsupported": 391,
"memory_capacity": 114,
"platform_infrastructure": 79,
"platform_storage": 3,
@@ -3815,14 +3817,14 @@
"任务失败_原因未确认": 8,
"参数/模板问题": 239
},
"failureCount": 1492,
"failureCount": 1493,
"failureRate": 0.9325,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 82,
"successCount": 108,
"successRate": 0.0675,
"total": 1600,
"total": 1601,
"unresolvedFailureCount": 366
},
"Vastai_va16": {
@@ -4122,13 +4124,13 @@
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 1,
"任务失败_原因未确认": 8,
"参数/模板问题": 3
},
"failureCount": 16,
"failureRate": 0.9412,
"failureCount": 15,
"failureRate": 0.9375,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-30T20:02:51.541944+00:00",
@@ -4136,11 +4138,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0588,
"successRate": 0.0625,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 15
"total": 16,
"unresolvedFailureCount": 14
},
"Iluvatar_bi-150|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4386,24 +4388,24 @@
"unresolvedFailureCount": 12
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 5,
"platform_storage": 1,
"tokenizer_compatibility": 7
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-10-31T12:05:02.739582+00:00",
"lastTerminalAt": "2026-11-01T20:07:11.761145+00:00",
"lastTerminalAt": "2026-11-01T21:00:36.112004+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4411,7 +4413,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -4622,13 +4624,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17618,
"totalRecords": 17618,
"terminalRecords": 17619,
"totalRecords": 17619,
"totals": {
"attributableFailureCount": 7895,
"attributableFailureCount": 7896,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8863,
"decisionTotal": 8864,
"failureBreakdown": {
"ambiguous_runtime": 3521,
"architecture_compatibility": 62,
@@ -4636,7 +4638,7 @@
"backend_operator": 136,
"configuration_launch": 489,
"context_length": 408,
"framework_architecture_unsupported": 3154,
"framework_architecture_unsupported": 3155,
"memory_capacity": 1208,
"model_load": 586,
"platform_infrastructure": 652,
@@ -4650,14 +4652,14 @@
"参数/模板问题": 3675,
"日志缺失": 719
},
"failureCount": 16650,
"failureCount": 16651,
"failureRate": 0.9451,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 694,
"successCount": 968,
"successRate": 0.0549,
"total": 17618,
"total": 17619,
"unresolvedFailureCount": 8061
},
"warnings": [
@@ -4707,6 +4709,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17618,
"summarizedRecords": 17619,
"version": 1
}