Change benchmarks --> examples in code (#48)

* Change benchmarks --> examples in README

* Change benchmarks --> examples in all files

* Change benchmarks --> examples in automatic file header

* Fix capitalization

.ci/FILE_HEADER

@@ -1,2 +1,2 @@
-Copyright 2022 MosaicML Benchmarks authors
+Copyright 2022 MosaicML Examples authors
 SPDX-License-Identifier: Apache-2.0

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2022 MosaicML Benchmarks authors
+   Copyright 2022 MosaicML Examples authors
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

README.md

@@ -1,6 +1,6 @@
-# benchmarks
+# Examples
 
-Fast reference benchmarks for training ML models with recipes. Designed to be easily forked and modified.
+Fast reference examples for training ML models with recipes. Designed to be easily forked and modified.
 ## ResNet-50 + ImageNet
 <img src="https://assets-global.website-files.com/61fd4eb76a8d78bc0676b47d/62a12d1e4eb9b83915be37a6_r50_overall_pareto.png" alt="drawing" width="500"/>
 

bert/README.md

@@ -49,7 +49,7 @@ This recommended Docker image comes pre-configured with the following dependenci
 To get started, clone this repo and install the requirements:
 
 ```bash
-git clone https://github.com/mosaicml/benchmarks.git
+git clone https://github.com/mosaicml/examples.git
 cd bert
 pip install -r requirements.txt
 ```

bert/convert_c4.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """C4 streaming dataset conversion script."""

bert/glue.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import copy

bert/main.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os

bert/src/__init__.py

@@ -1,2 +1,2 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0

bert/src/bert_layers.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 # Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.

bert/src/bert_padding.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 # Adapted from https://github.com/HazyResearch/flash-attention/blob/main/flash_attn/bert_padding.py

bert/src/data_c4.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """Build a StreamingC4 dataset and dataloader for training."""

bert/src/flash_attn_triton.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """Triton implementation of Flash Attention.

bert/src/glue/data.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import logging

bert/src/glue/finetuning_jobs.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 # """Contains GLUE job objects for the simple_glue_trainer."""

bert/src/hf_bert.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """Implements a Hugging Face BERT wrapped inside a :class:`.ComposerModel`."""

bert/src/mosaic_bert.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """Implements a Mosaic BERT wrapper around a :class:`.ComposerTransformer`."""

bert/yamls/glue/mcloud_run.yaml

@@ -15,9 +15,9 @@ gpu_num: 8  # Number of GPUs to use
 image: mosaicml/pytorch:1.12.1_cu116-python3.9-ubuntu20.04
 integrations:
 - integration_type: git_repo
-  git_repo: mosaicml/benchmarks
+  git_repo: mosaicml/examples
 command: |
-  cd benchmarks/bert
+  cd examples/bert
   pip install -r requirements.txt
   python glue.py /mnt/config/parameters.yaml
 

bert/yamls/main/mcloud_run.yaml

@@ -15,9 +15,9 @@ gpu_num: 8  # Number of GPUs to use
 image: mosaicml/pytorch:1.12.1_cu116-python3.9-ubuntu20.04
 integrations:
 - integration_type: git_repo
-  git_repo: mosaicml/benchmarks
+  git_repo: mosaicml/examples
 command: |
-  cd benchmarks/bert
+  cd examples/bert
   pip install -r requirements.txt
   composer main.py /mnt/config/parameters.yaml
 

bert/yamls/test/glue.yaml

@@ -1,5 +1,5 @@
 # Use this YAML to verify that GLUE fine-tuning works. Runs on CPU or GPUs (if available).
-# From `benchmarks/bert`, run:
+# From `examples/bert`, run:
 #   `python glue.py yamls/test/glue.yaml` to run using the HuggingFace BERT
 #   `python glue.py yamls/test/glue.yaml model.name=mosaic_bert` to run using the Mosaic BERT
 

bert/yamls/test/main.yaml

@@ -1,5 +1,5 @@
 # Use this YAML to verify that MLM pre-training works. Runs on CPU or GPUs (if available).
-# From `benchmarks/bert`, run:
+# From `examples/bert`, run:
 #   `composer main.py yamls/test/main.yaml` to run using the HuggingFace BERT
 #   `composer main.py yamls/test/main.yaml model.name=mosaic_bert` to run using the Mosaic BERT
 

cifar/README.md

@@ -19,7 +19,7 @@
     <a href="https://join.slack.com/t/mosaicml-community/shared_invite/zt-w0tiddn9-WGTlRpfjcO9J5jyrMub1dg">
         <img alt="Chat @ Slack" src="https://img.shields.io/badge/slack-chat-2eb67d.svg?logo=slack">
     </a>
-    <a href="https://github.com/mosaicml/benchmarks/blob/main/LICENSE">
+    <a href="https://github.com/mosaicml/examples/blob/main/LICENSE">
         <img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-green.svg?logo=slack">
     </a>
 </p>

cifar/__init__.py

@@ -1,2 +1,2 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0

cifar/data.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """CIFAR image classification dataset.

cifar/main.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os

cifar/model.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """The CIFAR ResNet torch module.

cifar/tests/__init__.py

@@ -1,2 +1,2 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0

cifar/tests/test_data.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import pytest

cifar/tests/test_model.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import pytest

cifar/tests/test_trainer.py

@@ -1,12 +1,12 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os
 import sys
 
 import pytest
 
-# TODO: this should be removed when benchmarks has a setup.py i.e. installable
+# TODO: this should be removed when examples has a setup.py i.e. installable
 sys.path.append('.')
 
 import torch

cifar/tests/utils.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os

cifar/yamls/mcloud_run.yaml

@@ -5,9 +5,9 @@ gpu_num: 8          # Number of GPUs to use
 image: mosaicml/pytorch:1.12.1_cu116-python3.9-ubuntu20.04
 integrations:
 - integration_type: git_repo
-  git_repo: mosaicml/benchmarks
+  git_repo: mosaicml/examples
   git_branch: landan/cifar_benchmark
 command: |
-  cd benchmarks/cifar
+  cd examples/cifar
   pip install -r requirements.txt
   composer main.py yamls/resnet56.yaml

deeplab/README.md

@@ -16,7 +16,7 @@
     <a href="https://join.slack.com/t/mosaicml-community/shared_invite/zt-w0tiddn9-WGTlRpfjcO9J5jyrMub1dg">
         <img alt="Chat @ Slack" src="https://img.shields.io/badge/slack-chat-2eb67d.svg?logo=slack">
     </a>
-    <a href="https://github.com/mosaicml/benchmarks/blob/main/LICENSE">
+    <a href="https://github.com/mosaicml/examples/blob/main/LICENSE">
         <img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-green.svg?logo=slack">
     </a>
 </p>
@@ -98,7 +98,7 @@ But if you really must try this manually on your own cluster, then just provide
 either directly via CLI, or via environment variables that can be read. Then launch the appropriate command on each node:
 
 ### Overriding Arguments
-Composer benchmarks uses [`omegaconf`](https://github.com/omry/omegaconf) to manage configs. OmegaConf allows us to override YAML configs from the command line for quick experimentation.
+Composer examples uses [`omegaconf`](https://github.com/omry/omegaconf) to manage configs. OmegaConf allows us to override YAML configs from the command line for quick experimentation.
 
 Common examples include:
 

deeplab/__init__.py

@@ -1,2 +1,2 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0

deeplab/data.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """ADE20K Semantic segmentation and scene parsing dataset.

deeplab/download_ade20k.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """ADE20K Semantic segmentation and scene parsing dataset.

deeplab/main.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """Example script to train a DeepLabv3 model on ADE20k."""

deeplab/model.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """DeepLabV3 model extending :class:`.ComposerClassifier`."""

deeplab/tests/__init__.py

@@ -1,2 +1,2 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0

deeplab/tests/test_data.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os

deeplab/tests/test_model.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import pytest

deeplab/tests/test_trainer.py

@@ -1,12 +1,12 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os
 import sys
 
 import pytest
 
-# TODO: this should be removed when benchmarks has a setup.py i.e. installable
+# TODO: this should be removed when examples has a setup.py i.e. installable
 sys.path.append('.')
 
 import torch

deeplab/transforms.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """ADE20K Semantic segmentation and scene parsing dataset.

deeplab/yamls/mcloud_run.yaml

@@ -5,9 +5,9 @@ gpu_num: 8  # Number of GPUs to use specified as an integer
 image: mosaicml/pytorch_vision:1.12.1_cu116-python3.9-ubuntu20.04
 integrations:
 - integration_type: git_repo
-  git_repo: mosaicml/benchmarks
+  git_repo: mosaicml/examples
 command: |
-  cd benchmarks/deeplab
+  cd examples/deeplab
   pip install -r requirements.txt
   composer main.py /mnt/config/parameters.yaml
 # Configuration copied from baseline.yaml

llm/convert_c4.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """C4 streaming dataset conversion scripts."""

llm/main.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os

llm/src/__init__.py

@@ -1,2 +1,2 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0

llm/src/data_c4.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """Build a StreamingC4 dataset and dataloader for training."""

llm/src/evaluation/eval.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import argparse
@@ -110,7 +110,7 @@ def log_results_to_tsv(results: JsonResults, outfile: str) -> None:
 
 
 if __name__ == '__main__':
-    """Example usage from benchmarks/llm directory:
+    """Example usage from examples/llm directory:
 
     python -m src.evaluation.eval --experiment_name opt_1.3b \
         --model_type pretrained_hf \

llm/src/evaluation/model_loading.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os

llm/src/hf_causal_lm.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import torch

llm/src/model_registry.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 from src.hf_causal_lm import ComposerHFCausalLM

llm/src/mosaic_gpt.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 """A simple, flexible implementation of a GPT model.

llm/src/tokenizer.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 from abc import ABC, abstractmethod

llm/tests/__init__.py

@@ -1,2 +1,2 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0

llm/tests/c4_data_prep_script.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import os

llm/tests/compare_hf_v_mosaic_gpt.py

@@ -1,4 +1,4 @@
-# Copyright 2022 MosaicML Benchmarks authors
+# Copyright 2022 MosaicML Examples authors
 # SPDX-License-Identifier: Apache-2.0
 
 import warnings