Merge pull request #56 from o-krussow/mlperf-inference-results-scc24

scc132 submission
mlcommons · Oct 23, 2024 · f593b16 · f593b16
2 parents 043eeeb + 4bf16b9
commit f593b16
Show file tree

Hide file tree

Showing 21 changed files with 905 additions and 0 deletions.
diff --git a/open/scc132/code/bert-99/README.md b/open/scc132/code/bert-99/README.md
@@ -0,0 +1 @@
+TBD
diff --git a/...nts/scc132_gpu0.novalocal-reference-cpu-pytorch_v2.5.0-default_config/README.md b/...nts/scc132_gpu0.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 |         1.97 | -                 |
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 +1,54 @@
+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: 3.11.7 (main, Oct 21 2024, 23:35:59) [GCC 11.4.1 20231218 (Red Hat 11.4.1-3)]
+* MLCommons CM version: 3.2.6
+
+## 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=6dbb26a3da6b8ebdbc96be3be3a0e9817d3b6d26
+
+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 \
+	--quiet
+```
+*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: scc132_gpu0.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`: `1.96994`
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