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

state: generation 7361 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-14 20:41:42 +00:00
parent b32f90ab6f
commit 865521cbdb
8 changed files with 860 additions and 859 deletions
Download Patch File Download Diff File Expand all files Collapse all files

147
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-14T19:41:18.806767+00:00",
"lastSyncTime": "2026-09-14T19:41:18.606689+00:00",
"generatedAt": "2026-09-14T20:39:18.720855+00:00",
"lastSyncTime": "2026-09-14T20:39:18.216520+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1779,29 +1779,29 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 22,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 24,
"attributableFailureCount": 23,
"decisionFailureRate": 0.92,
"decisionSuccessRate": 0.08,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 98,
"failureRate": 0.98,
"failureCount": 99,
"failureRate": 0.9802,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.02,
"successRate": 0.0198,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 100,
"total": 101,
"unresolvedFailureCount": 76
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -1989,25 +1989,25 @@
"decisionSuccessRate": 0.1875,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"backend_operator": 4,
"framework_architecture_unsupported": 5,
"model_load": 2,
"runtime_memory": 2,
"参数/模板问题": 1
},
"failureCount": 20,
"failureRate": 0.8696,
"failureCount": 21,
"failureRate": 0.875,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.1304,
"successRate": 0.125,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 23,
"unresolvedFailureCount": 7
"total": 24,
"unresolvedFailureCount": 8
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 26,
@@ -2564,10 +2564,10 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 161,
"decisionFailureRate": 0.7419,
"decisionSuccessRate": 0.2581,
"decisionTotal": 217,
"attributableFailureCount": 162,
"decisionFailureRate": 0.7431,
"decisionSuccessRate": 0.2569,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 151,
"backend_operator": 4,
@@ -2575,18 +2575,18 @@
"memory_capacity": 5,
"model_load": 45,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"tokenizer_compatibility": 4,
"参数/模板问题": 66,
"验证失败": 673
},
"failureCount": 1052,
"failureCount": 1053,
"failureRate": 0.9495,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 56,
"successRate": 0.0505,
"total": 1108,
"total": 1109,
"unresolvedFailureCount": 890
},
"vllm": {
@@ -2662,22 +2662,22 @@
"decisionSuccessRate": 0.1875,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"backend_operator": 4,
"framework_architecture_unsupported": 5,
"model_load": 2,
"runtime_memory": 2,
"参数/模板问题": 1
},
"failureCount": 20,
"failureRate": 0.8696,
"failureCount": 21,
"failureRate": 0.875,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.1304,
"total": 23,
"unresolvedFailureCount": 7
"successRate": 0.125,
"total": 24,
"unresolvedFailureCount": 8
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 53,
@@ -2722,7 +2722,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-14T19:41:18.800840+00:00",
"generatedAt": "2026-09-14T20:39:18.716063+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 36,
@@ -2798,26 +2798,26 @@
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 22,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 24,
"attributableFailureCount": 23,
"decisionFailureRate": 0.92,
"decisionSuccessRate": 0.08,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 98,
"failureRate": 0.98,
"failureCount": 99,
"failureRate": 0.9802,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.02,
"total": 100,
"successRate": 0.0198,
"total": 101,
"unresolvedFailureCount": 76
},
"Cambricon_mlu-370-x8": {
@@ -2868,7 +2868,7 @@
"decisionSuccessRate": 0.1837,
"decisionTotal": 49,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"backend_operator": 7,
"framework_architecture_unsupported": 19,
"model_load": 9,
@@ -2877,15 +2877,15 @@
"参数/模板问题": 3,
"验证失败": 30
},
"failureCount": 87,
"failureRate": 0.9062,
"failureCount": 88,
"failureRate": 0.9072,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0938,
"total": 96,
"unresolvedFailureCount": 47
"successRate": 0.0928,
"total": 97,
"unresolvedFailureCount": 48
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 101,
@@ -3766,10 +3766,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"runtime_memory": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
@@ -3781,8 +3782,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
"total": 3,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha": {
"attributableFailureCount": 1,
@@ -5365,22 +5366,23 @@
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T18:50:27.851919+00:00",
"lastTerminalAt": "2026-09-14T20:39:18.216520+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5389,7 +5391,7 @@
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 18
"unresolvedFailureCount": 17
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -6801,9 +6803,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"runtime_memory": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
@@ -6816,8 +6819,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha|33": {
"attributableFailureCount": 1,
@@ -8929,15 +8932,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1866,
"totalRecords": 1959,
"terminalRecords": 1868,
"totalRecords": 1961,
"totals": {
"attributableFailureCount": 564,
"decisionFailureRate": 0.8995,
"decisionSuccessRate": 0.1005,
"decisionTotal": 627,
"attributableFailureCount": 565,
"decisionFailureRate": 0.8997,
"decisionSuccessRate": 0.1003,
"decisionTotal": 628,
"failureBreakdown": {
"ambiguous_runtime": 444,
"ambiguous_runtime": 445,
"backend_operator": 44,
"framework_architecture_unsupported": 361,
"memory_capacity": 12,
@@ -8945,19 +8948,19 @@
"platform_infrastructure": 6,
"repository_structure": 8,
"runtime_memory": 8,
"tokenizer_compatibility": 53,
"tokenizer_compatibility": 54,
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1803,
"failureRate": 0.9662,
"failureCount": 1805,
"failureRate": 0.9663,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 63,
"successRate": 0.0338,
"total": 1866,
"unresolvedFailureCount": 1233
"successRate": 0.0337,
"total": 1868,
"unresolvedFailureCount": 1234
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -8995,6 +8998,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1959,
"summarizedRecords": 1961,
"version": 1
}