Merge pull request #71 from Xeygy/mlperf-inference-results-scc24

Results on system scc102

open/scc102/code/bert-99/README.md

@@ -0,0 +1 @@
+TBD

open/scc102/measurements/scc102_gpu0.novalocal-reference-gpu-pytorch-cu118/README.md

@@ -0,0 +1,3 @@
+| Model   | Scenario   |   Accuracy |   Throughput | Latency (in ms)   |
+|---------|------------|------------|--------------|-------------------|
+| bert-99 | offline    |    88.7443 |       46.279 | -                 |

open/scc102/measurements/scc102_gpu0.novalocal-reference-gpu-pytorch-cu118/bert-99/offline/README.md

@@ -0,0 +1,70 @@
+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: 3.9.18 (main, Aug 23 2024, 00:00:00) 
+[GCC 11.4.1 20231218 (Red Hat 11.4.1-3)]
+* MLCommons CM version: 3.2.8
+
+## 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=944c032d0381c97ab0fd0bbb622f1e53e63ab525
+
+cm run script \
+	- \
+	- \
+	a \
+	d \
+	r \
+	. \
+	p \
+	y \
+	t \
+	h \
+	o \
+	n \
+	. \
+	n \
+	a \
+	m \
+	e \
+	= \
+	m \
+	l \
+	p \
+	e \
+	r \
+	f
+```
+*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: scc102_gpu0.novalocal-reference-gpu-pytorch-cu118
+
+Model Precision: fp32
+
+### Accuracy Results 
+`F1`: `88.74429`, Required accuracy for closed division `>= 89.96526`
+
+### Performance Results 
+`Samples per second`: `46.2795`