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

state: generation 11841 (cycle_no_slots)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 22:36:47 +00:00
parent 8148a07cc0
commit 9fe28f26fa
7 changed files with 2049 additions and 2075 deletions
Download Patch File Download Diff File Expand all files Collapse all files

151
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T22:33:35.651361+00:00",
"lastSyncTime": "2026-09-21T22:33:35.352115+00:00",
"generatedAt": "2026-09-21T22:36:34.275044+00:00",
"lastSyncTime": "2026-09-21T22:36:33.961892+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4158,17 +4158,17 @@
"unresolvedFailureCount": 35
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 3,
"model_load": 2,
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -4178,7 +4178,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm|reinforcement_learning": {
@@ -5671,10 +5671,10 @@
"unresolvedFailureCount": 222
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 78,
"decisionFailureRate": 0.9512,
"decisionSuccessRate": 0.0488,
"decisionTotal": 82,
"attributableFailureCount": 79,
"decisionFailureRate": 0.9518,
"decisionSuccessRate": 0.0482,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 92,
"backend_operator": 2,
@@ -5684,21 +5684,21 @@
"model_load": 2,
"platform_infrastructure": 1,
"repository_structure": 3,
"tokenizer_compatibility": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 28
},
"failureCount": 199,
"failureRate": 0.9803,
"failureCount": 200,
"failureRate": 0.9804,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0197,
"total": 203,
"successRate": 0.0196,
"total": 204,
"unresolvedFailureCount": 120
}
},
"generatedAt": "2026-09-21T22:33:35.637691+00:00",
"generatedAt": "2026-09-21T22:36:34.263803+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5861,10 +5861,10 @@
"unresolvedFailureCount": 568
},
"Iluvatar_bi-150": {
"attributableFailureCount": 750,
"decisionFailureRate": 0.8343,
"decisionSuccessRate": 0.1657,
"decisionTotal": 899,
"attributableFailureCount": 751,
"decisionFailureRate": 0.8344,
"decisionSuccessRate": 0.1656,
"decisionTotal": 900,
"failureBreakdown": {
"ambiguous_runtime": 625,
"architecture_compatibility": 15,
@@ -5876,19 +5876,19 @@
"platform_infrastructure": 21,
"repository_structure": 99,
"runtime_memory": 12,
"tokenizer_compatibility": 59,
"tokenizer_compatibility": 60,
"参数/模板问题": 320,
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1901,
"failureRate": 0.9273,
"failureCount": 1902,
"failureRate": 0.9274,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0727,
"total": 2050,
"successRate": 0.0726,
"total": 2051,
"unresolvedFailureCount": 1130
},
"Iluvatar_mrv-100": {
@@ -13361,14 +13361,14 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "mpt",
@@ -13380,7 +13380,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
@@ -18169,23 +18169,23 @@
"unresolvedFailureCount": 19
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 3,
"model_load": 2,
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T20:22:53.859282+00:00",
"lastTerminalAt": "2026-09-21T22:36:33.961892+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -18193,7 +18193,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -20185,31 +20185,6 @@
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-20T12:21:49.902066+00:00",
"modelType": "hrm_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|lfm2_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -21290,18 +21265,18 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T21:06:45.850258+00:00",
"lastTerminalAt": "2026-09-21T22:36:33.961892+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -21311,7 +21286,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
@@ -31998,14 +31973,14 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mpt|none|33": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
@@ -32018,7 +31993,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|34": {
@@ -38505,13 +38480,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16432,
"totalRecords": 16626,
"terminalRecords": 16433,
"totalRecords": 16627,
"totals": {
"attributableFailureCount": 5922,
"attributableFailureCount": 5923,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6871,
"decisionTotal": 6872,
"failureBreakdown": {
"ambiguous_runtime": 4051,
"architecture_compatibility": 212,
@@ -38524,36 +38499,36 @@
"platform_infrastructure": 925,
"repository_structure": 739,
"runtime_memory": 85,
"tokenizer_compatibility": 666,
"tokenizer_compatibility": 667,
"参数/模板问题": 3192,
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15483,
"failureRate": 0.9422,
"failureCount": 15484,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0578,
"total": 16432,
"successRate": 0.0577,
"total": 16433,
"unresolvedFailureCount": 8636
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -38593,6 +38568,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16626,
"summarizedRecords": 16627,
"version": 1
}