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

state: generation 21508 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-06 19:02:38 +00:00
parent d6b9257a4d
commit 4b05e2108a
9 changed files with 2637 additions and 2649 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-06T18:06:37.274502+00:00",
"lastSyncTime": "2026-10-06T18:06:36.953125+00:00",
"generatedAt": "2026-10-06T19:00:42.555850+00:00",
"lastSyncTime": "2026-10-06T19:00:42.266417+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3217,10 +3217,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 123,
"ambiguous_runtime": 124,
"memory_capacity": 1
},
"failureCount": 124,
"failureCount": 125,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3230,8 +3230,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 124,
"unresolvedFailureCount": 123
"total": 125,
"unresolvedFailureCount": 124
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50,
@@ -5608,7 +5608,7 @@
"decisionSuccessRate": 0.0281,
"decisionTotal": 178,
"failureBreakdown": {
"ambiguous_runtime": 356,
"ambiguous_runtime": 357,
"backend_operator": 9,
"framework_architecture_unsupported": 47,
"memory_capacity": 10,
@@ -5617,15 +5617,15 @@
"tokenizer_compatibility": 95,
"参数/模板问题": 13
},
"failureCount": 567,
"failureCount": 568,
"failureRate": 0.9913,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0087,
"total": 572,
"unresolvedFailureCount": 369
"total": 573,
"unresolvedFailureCount": 370
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 150,
@@ -5656,7 +5656,7 @@
"unresolvedFailureCount": 235
}
},
"generatedAt": "2026-10-06T18:06:37.205006+00:00",
"generatedAt": "2026-10-06T19:00:42.537107+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5719,7 +5719,7 @@
"decisionSuccessRate": 0.1147,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 267,
"ambiguous_runtime": 268,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 125,
@@ -5733,15 +5733,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 765,
"failureCount": 766,
"failureRate": 0.9684,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0316,
"total": 790,
"unresolvedFailureCount": 570
"total": 791,
"unresolvedFailureCount": 571
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 759,
@@ -8948,6 +8948,29 @@
"total": 5,
"unresolvedFailureCount": 5
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|hrm_text|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -24996,13 +25019,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 10
"ambiguous_runtime": 11
},
"failureCount": 10,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-23T05:38:14.666257+00:00",
"lastTerminalAt": "2026-10-06T19:00:42.266417+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -25010,8 +25033,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 10
"total": 11,
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -26143,6 +26166,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-06T19:00:42.266417+00:00",
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -33588,6 +33636,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|hrm_text|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -57474,15 +57546,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17341,
"totalRecords": 17565,
"terminalRecords": 17342,
"totalRecords": 17566,
"totals": {
"attributableFailureCount": 6235,
"decisionFailureRate": 0.8644,
"decisionSuccessRate": 0.1356,
"decisionTotal": 7213,
"failureBreakdown": {
"ambiguous_runtime": 4548,
"ambiguous_runtime": 4549,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -57498,15 +57570,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16363,
"failureCount": 16364,
"failureRate": 0.9436,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0564,
"total": 17341,
"unresolvedFailureCount": 9176
"total": 17342,
"unresolvedFailureCount": 9177
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -57515,14 +57587,14 @@
"GPU hygon_k100-ai 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 Ascend_910-b3 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。",
"GPU Mthreads_s4000 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 Cambricon_mlu-370-x8 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-b4 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-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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Vastai_va16|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-b3|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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57566,6 +57638,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17565,
"summarizedRecords": 17566,
"version": 1
}