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

state: generation 6099 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 07:46:34 +00:00
parent 9799a210c0
commit 2aa388e3e4
9 changed files with 2377 additions and 2377 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T07:35:30.629329+00:00",
"lastSyncTime": "2026-09-12T07:35:30.412992+00:00",
"generatedAt": "2026-09-12T07:44:41.124320+00:00",
"lastSyncTime": "2026-09-12T07:44:40.913717+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1545,30 +1545,30 @@
"unresolvedFailureCount": 34
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 26,
"decisionFailureRate": 0.963,
"decisionSuccessRate": 0.037,
"decisionTotal": 27,
"attributableFailureCount": 27,
"decisionFailureRate": 0.9643,
"decisionSuccessRate": 0.0357,
"decisionTotal": 28,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 4,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"memory_capacity": 1,
"model_load": 2,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 79,
"failureRate": 0.9875,
"failureCount": 80,
"failureRate": 0.9877,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0125,
"successRate": 0.0123,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 80,
"total": 81,
"unresolvedFailureCount": 53
},
"Biren_166m|vllm|text-generation": {
@@ -2370,14 +2370,14 @@
"unresolvedFailureCount": 7
},
"unknown": {
"attributableFailureCount": 142,
"decisionFailureRate": 0.7358,
"decisionSuccessRate": 0.2642,
"decisionTotal": 193,
"attributableFailureCount": 143,
"decisionFailureRate": 0.7371,
"decisionSuccessRate": 0.2629,
"decisionTotal": 194,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
"framework_architecture_unsupported": 90,
"framework_architecture_unsupported": 91,
"memory_capacity": 5,
"model_load": 40,
"platform_infrastructure": 1,
@@ -2385,14 +2385,14 @@
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1005,
"failureRate": 0.9517,
"failureCount": 1006,
"failureRate": 0.9518,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 51,
"successRate": 0.0483,
"total": 1056,
"successRate": 0.0482,
"total": 1057,
"unresolvedFailureCount": 862
},
"vllm": {
@@ -2524,7 +2524,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T07:35:30.625131+00:00",
"generatedAt": "2026-09-12T07:44:41.120022+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2575,27 +2575,27 @@
"unresolvedFailureCount": 222
},
"Biren_166m": {
"attributableFailureCount": 27,
"decisionFailureRate": 0.9643,
"decisionSuccessRate": 0.0357,
"decisionTotal": 28,
"attributableFailureCount": 28,
"decisionFailureRate": 0.9655,
"decisionSuccessRate": 0.0345,
"decisionTotal": 29,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 4,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"memory_capacity": 1,
"model_load": 3,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 80,
"failureRate": 0.9877,
"failureCount": 81,
"failureRate": 0.9878,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0123,
"total": 81,
"successRate": 0.0122,
"total": 82,
"unresolvedFailureCount": 53
},
"Cambricon_mlu-370-x4": {
@@ -4305,23 +4305,23 @@
"unresolvedFailureCount": 18
},
"Biren_166m|unknown|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": 9,
"backend_operator": 4,
"framework_architecture_unsupported": 1,
"framework_architecture_unsupported": 2,
"model_load": 1
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T13:55:40.785120+00:00",
"lastTerminalAt": "2026-09-12T07:44:40.913717+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4329,7 +4329,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 15,
"total": 16,
"unresolvedFailureCount": 9
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -7185,17 +7185,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1697,
"totalRecords": 1784,
"terminalRecords": 1698,
"totalRecords": 1785,
"totals": {
"attributableFailureCount": 466,
"decisionFailureRate": 0.8927,
"decisionSuccessRate": 0.1073,
"decisionTotal": 522,
"attributableFailureCount": 467,
"decisionFailureRate": 0.8929,
"decisionSuccessRate": 0.1071,
"decisionTotal": 523,
"failureBreakdown": {
"ambiguous_runtime": 397,
"backend_operator": 41,
"framework_architecture_unsupported": 285,
"framework_architecture_unsupported": 286,
"memory_capacity": 11,
"model_load": 68,
"platform_infrastructure": 4,
@@ -7205,20 +7205,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1641,
"failureCount": 1642,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.033,
"total": 1697,
"total": 1698,
"unresolvedFailureCount": 1171
},
"warnings": [
"GPU Ascend_910-b3 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 Mthreads_s4000 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 hygon_k100-ai 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_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7227,7 +7228,6 @@
"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-150 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。",
"组合 hygon_k100-ai|vllm-patch-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 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7249,6 +7249,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1784,
"summarizedRecords": 1785,
"version": 1
}