Merge pull request #53 from SeeleVolle/mlperf-inference-results-scc24

Mlperf inference results scc24 for scc104 with cpu and gpu
mlcommons · Oct 21, 2024 · 9b87073 · 9b87073
2 parents c77698c + 3d060cf
commit 9b87073
Show file tree

Hide file tree

Showing 40 changed files with 1,871 additions and 0 deletions.
diff --git a/open/scc104-ZJUSCT/code/bert-99/README.md b/open/scc104-ZJUSCT/code/bert-99/README.md
@@ -0,0 +1 @@
+TBD
diff --git a/...nts/scc104_cpu1.novalocal-reference-cpu-pytorch_v2.5.0-default_config/README.md b/...nts/scc104_cpu1.novalocal-reference-cpu-pytorch_v2.5.0-default_config/README.md
@@ -0,0 +1,3 @@
+| Model   | Scenario   |   Accuracy |   Throughput | Latency (in ms)   |
+|---------|------------|------------|--------------|-------------------|
+| bert-99 | offline    |    90.8749 |        2.356 | -                 |
diff --git a/...novalocal-reference-cpu-pytorch_v2.5.0-default_config/bert-99/offline/README.md b/...novalocal-reference-cpu-pytorch_v2.5.0-default_config/bert-99/offline/README.md
@@ -0,0 +1,53 @@
+This experiment is generated using the [MLCommons Collective Mind automation framework (CM)](https://github.com/mlcommons/cm4mlops).
+
+*Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.*
+
+## Host platform
+
+* OS version: Linux-6.1.110-1.el9.elrepo.x86_64-x86_64-with-glibc2.34
+* CPU version: x86_64
+* Python version: 3.10.15 (main, Oct  3 2024, 07:27:34) [GCC 11.2.0]
+* MLCommons CM version: 3.2.4
+
+## CM Run Command
+
+See [CM installation guide](https://docs.mlcommons.org/inference/install/).
+
+```bash
+pip install -U cmind
+
+cm rm cache -f
+
+cm pull repo mlcommons@cm4mlops --checkout=5aeaffdca72142871dcde95ebf8a37e65fe3e06e
+
+cm run script \
+	--tags=run-mlperf,inference,_r4.1-dev \
+	--model=bert-99 \
+	--implementation=reference \
+	--framework=pytorch \
+	--category=edge \
+	--scenario=Offline \
+	--execution_mode=valid \
+	--device=cpu
+```
+*Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf (CM scripts),
+ you should simply reload mlcommons@cm4mlops without checkout and clean CM cache as follows:*
+
+```bash
+cm rm repo mlcommons@cm4mlops
+cm pull repo mlcommons@cm4mlops
+cm rm cache -f
+
+```
+
+## Results
+
+Platform: scc104_cpu1.novalocal-reference-cpu-pytorch_v2.5.0-default_config
+
+Model Precision: fp32
+
+### Accuracy Results 
+`F1`: `90.87487`, Required accuracy for closed division `>= 89.96526`
+
+### Performance Results 
+`Samples per second`: `2.35587`
diff --git a/...ovalocal-reference-cpu-pytorch_v2.5.0-default_config/bert-99/offline/accuracy_console.out b/...ovalocal-reference-cpu-pytorch_v2.5.0-default_config/bert-99/offline/accuracy_console.out