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

state: generation 18863 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-30 17:25:36 +00:00
parent 3255bfb1a7
commit 3ca3fa3ba1
8 changed files with 1525 additions and 1479 deletions
Download Patch File Download Diff File Expand all files Collapse all files

99
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-30T16:41:39.516083+00:00",
"lastSyncTime": "2026-09-30T16:41:39.256307+00:00",
"generatedAt": "2026-09-30T17:21:20.789157+00:00",
"lastSyncTime": "2026-09-30T17:21:20.559656+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3759,10 +3759,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 114,
"ambiguous_runtime": 115,
"memory_capacity": 1
},
"failureCount": 115,
"failureCount": 116,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3772,8 +3772,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 115,
"unresolvedFailureCount": 114
"total": 116,
"unresolvedFailureCount": 115
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 45,
@@ -6148,7 +6148,7 @@
"decisionSuccessRate": 0.0311,
"decisionTotal": 161,
"failureBreakdown": {
"ambiguous_runtime": 334,
"ambiguous_runtime": 335,
"backend_operator": 9,
"framework_architecture_unsupported": 37,
"memory_capacity": 10,
@@ -6157,15 +6157,15 @@
"tokenizer_compatibility": 91,
"参数/模板问题": 13
},
"failureCount": 525,
"failureCount": 526,
"failureRate": 0.9906,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0094,
"total": 530,
"unresolvedFailureCount": 347
"total": 531,
"unresolvedFailureCount": 348
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 137,
@@ -6196,7 +6196,7 @@
"unresolvedFailureCount": 217
}
},
"generatedAt": "2026-09-30T16:41:39.502112+00:00",
"generatedAt": "2026-09-30T17:21:20.773013+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 109,
@@ -6259,7 +6259,7 @@
"decisionSuccessRate": 0.1174,
"decisionTotal": 213,
"failureBreakdown": {
"ambiguous_runtime": 257,
"ambiguous_runtime": 258,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 121,
@@ -6273,15 +6273,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 750,
"failureRate": 0.9677,
"failureCount": 751,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0323,
"total": 775,
"unresolvedFailureCount": 560
"successRate": 0.0322,
"total": 776,
"unresolvedFailureCount": 561
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 750,
@@ -9924,6 +9924,29 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|torchao": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -33082,6 +33105,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|torchao|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -53766,15 +53813,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17166,
"totalRecords": 17387,
"terminalRecords": 17167,
"totalRecords": 17388,
"totals": {
"attributableFailureCount": 6152,
"decisionFailureRate": 0.8632,
"decisionSuccessRate": 0.1368,
"decisionTotal": 7127,
"failureBreakdown": {
"ambiguous_runtime": 4473,
"ambiguous_runtime": 4474,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -53790,30 +53837,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16191,
"failureCount": 16192,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 943,
"successCount": 975,
"successRate": 0.0568,
"total": 17166,
"unresolvedFailureCount": 9096
"total": 17167,
"unresolvedFailureCount": 9097
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 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 hygon_k100-ai 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 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 Vastai_va16 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 Iluvatar_bi-150 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 MetaX_c-500 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。",
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -53858,6 +53905,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17387,
"summarizedRecords": 17388,
"version": 1
}