Results from PACE-ICE cluster for TESTING

Author: AnanthVivekanand

open/scc-133/code/bert-99/README.md

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

open/scc-133/measurements/atl1_1_02_010_5_1.pace.gatech.edu-reference-cpu-pytorch-v2.4.1-default_config/README.md

@@ -0,0 +1,3 @@
+| Model   | Scenario   |   Accuracy |   Throughput | Latency (in ms)   |
+|---------|------------|------------|--------------|-------------------|
+| bert-99 | offline    |    90.8749 |        4.462 | -                 |

open/scc-133/measurements/atl1_1_02_010_5_1.pace.gatech.edu-reference-cpu-pytorch-v2.4.1-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-5.14.0-427.26.1.el9_4.x86_64-x86_64-with-glibc2.34
+* CPU version: x86_64
+* Python version: 3.12.6 | packaged by Anaconda, Inc. | (main, Oct  3 2024, 07:30:27) [GCC 11.2.0]
+* MLCommons CM version: 3.4.1
+
+## 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=b32ded2a4c3039ad16dadc734bee03dd1a97f228
+
+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: atl1_1_02_010_5_1.pace.gatech.edu-reference-cpu-pytorch-v2.4.1-default_config
+
+Model Precision: fp32
+
+### Accuracy Results 
+`F1`: `90.87487`, Required accuracy for closed division `>= 89.96526`
+
+### Performance Results 
+`Samples per second`: `4.46232`

open/scc-133/measurements/atl1_1_02_010_5_1.pace.gatech.edu-reference-cpu-pytorch-v2.4.1-default_config/bert-99/offline/accuracy_console.out

@@ -0,0 +1,19 @@
+/home/hice1/avivekanand3/CM/repos/local/cache/c88e5ba6fd9a4a86/inference/language/bert/pytorch_SUT.py:77: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
+  self.model.load_state_dict(torch.load(model_file), strict=False)
+
+No warnings encountered during test.
+
+No errors encountered during test.
+Loading BERT configs...
+Loading PyTorch model...
+Constructing SUT...
+Finished constructing SUT.
+Constructing QSL...
+Loading cached features from 'eval_features.pickle'...
+Finished constructing QSL.
+Running LoadGen test...
+Done!
+Destroying SUT...
+Destroying QSL...
+Finished destroying SUT.
+Finished destroying QSL.

open/scc-133/measurements/atl1_1_02_010_5_1.pace.gatech.edu-reference-cpu-pytorch-v2.4.1-default_config/bert-99/offline/atl1_1_02_010_5_1.pace.gatech.edu-reference-cpu-pytorch-v2.4.1-default_config.json

@@ -0,0 +1,7 @@
+{
+  "starting_weights_filename": "https://armi.in/files/fp32/model.pytorch",
+  "retraining": "no",
+  "input_data_types": "fp32",
+  "weight_data_types": "fp32",
+  "weight_transformations": "none"
+}