Record machine load with every latency number
Latency measured while another job hogs the cores is not comparable: the scale curve moved from 1.315s to 0.809s at 50,000 sources between two runs of the same code. - bench/systems.py: machine_facts() reports cpus plus the 1/5/15 minute load average. - bench/run.py, bench/run_external.py: both reports carry it, and BASELINE.md labels the latency table a ceiling when the machine was busy. Verification: pytest bench/tests -q -> 60 passed; ruff check bench/ -> all checks passed; mypy (fresh cache) -> no issues in 25 source files.
This commit is contained in:
1 parent
61f6506104
commit
c4e2982506
6 files changed
+62
-27
No files matched your search
+20
-20
@@ -564,9 +564,9 @@
|
||||
"min": 1
|
||||
},
|
||||
"identical_top10": 0.0,
|
||||
"max": 63.2751505510023,
|
||||
"mean": 21.701527132049886,
|
||||
"p50": 21.831516211001144,
|
||||
"max": 48.895113198996114,
|
||||
"mean": 20.665571158625244,
|
||||
"p50": 20.157494062004844,
|
||||
"queries": 40,
|
||||
"top10_overlap_with_bm25_only": 0.0,
|
||||
"top_k": 10
|
||||
@@ -575,7 +575,7 @@
|
||||
"answerable": 2928,
|
||||
"corpus_manifest_sha256": "8fc1ed861c891d778853d41107630869f9eb267a669c5d1038e389de80114347",
|
||||
"corpus_sources": 50278,
|
||||
"generated_at": "2026-10-07T14:38:12+00:00",
|
||||
"generated_at": "2026-10-07T15:33:42+00:00",
|
||||
"git_commit": "29163632af7418758e79a79a748f68050ca1e0b6",
|
||||
"limit_per_modality": null,
|
||||
"machine": {
|
||||
@@ -602,12 +602,12 @@
|
||||
{
|
||||
"atoms": 500,
|
||||
"bm25_only": {
|
||||
"p50": 0.0007463944966730196,
|
||||
"p95": 0.0026389723490865425
|
||||
"p50": 0.0006466769991675392,
|
||||
"p95": 0.00181096804953995
|
||||
},
|
||||
"dense_only": {
|
||||
"p50": 2.053756675497425,
|
||||
"p95": 3.7252893005985244
|
||||
"p50": 1.3797472870028287,
|
||||
"p95": 1.5762464397041183
|
||||
},
|
||||
"note": "latency only: a source prefix drops most gold sources, so recall at these sizes is meaningless",
|
||||
"queries": 40,
|
||||
@@ -616,12 +616,12 @@
|
||||
{
|
||||
"atoms": 2000,
|
||||
"bm25_only": {
|
||||
"p50": 0.00923213200076134,
|
||||
"p95": 0.023986968196186332
|
||||
"p50": 0.008334371003002161,
|
||||
"p95": 0.015740483100307734
|
||||
},
|
||||
"dense_only": {
|
||||
"p50": 2.2580291965023207,
|
||||
"p95": 4.0939969898456186
|
||||
"p50": 1.3979396294998878,
|
||||
"p95": 2.595364080850413
|
||||
},
|
||||
"note": "latency only: a source prefix drops most gold sources, so recall at these sizes is meaningless",
|
||||
"queries": 40,
|
||||
@@ -630,12 +630,12 @@
|
||||
{
|
||||
"atoms": 10000,
|
||||
"bm25_only": {
|
||||
"p50": 0.11317921599766123,
|
||||
"p95": 0.2961666731029253
|
||||
"p50": 0.05245087000002968,
|
||||
"p95": 0.12780161215196129
|
||||
},
|
||||
"dense_only": {
|
||||
"p50": 2.269751224499487,
|
||||
"p95": 3.6929099251963633
|
||||
"p50": 1.3382894579990534,
|
||||
"p95": 2.2659613330957646
|
||||
},
|
||||
"note": "latency only: a source prefix drops most gold sources, so recall at these sizes is meaningless",
|
||||
"queries": 40,
|
||||
@@ -644,12 +644,12 @@
|
||||
{
|
||||
"atoms": 165695,
|
||||
"bm25_only": {
|
||||
"p50": 1.3151575949996186,
|
||||
"p95": 3.7234880074014645
|
||||
"p50": 0.8085095155001909,
|
||||
"p95": 2.273631770645442
|
||||
},
|
||||
"dense_only": {
|
||||
"p50": 2.3852021460043034,
|
||||
"p95": 4.008884304698221
|
||||
"p50": 1.4964509784986149,
|
||||
"p95": 2.4635968941045574
|
||||
},
|
||||
"note": "latency only: a source prefix drops most gold sources, so recall at these sizes is meaningless",
|
||||
"queries": 40,
|
||||
|
||||
Reference in new issue
Block a user