edit estimator from PyTorch to HuggingFace

aws · Sep 10, 2022 · 952b68e · 952b68e
1 parent da266d9
commit 952b68e
Show file tree

Hide file tree

Showing 6 changed files with 36 additions and 52 deletions.
diff --git a/...g-compiler/huggingface/pytorch_single_gpu_single_node/albert-base-v2/albert-base-v2.ipynb b/...g-compiler/huggingface/pytorch_single_gpu_single_node/albert-base-v2/albert-base-v2.ipynb
@@ -58,7 +58,7 @@
    "source": [
     "### Installation\n",
     "\n",
-    "This example notebook requires the **SageMaker Python SDK v2.70.0** and **transformers v4.11.0**."
+    "This example notebook requires the **SageMaker Python SDK v2.108.0** and **transformers v4.21**."
    ]
   },
   {
@@ -67,7 +67,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install sagemaker botocore boto3 awscli s3fs typing-extensions --upgrade"
+    "!pip install \"sagemaker>=2.108.0\" botocore boto3 awscli s3fs typing-extensions --upgrade"
    ]
   },
   {
@@ -76,7 +76,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install transformers datasets --upgrade"
+    "!pip install \"transformers==4.21\" datasets --upgrade"
    ]
   },
   {
@@ -563,11 +563,11 @@
    "source": [
     "## SageMaker Training Job\n",
     "\n",
-    "To create a SageMaker training job, we use a `PyTorch` estimator. Using the estimator, you can define which fine-tuning script should SageMaker use through `entry_point`, which `instance_type` to use for training, which `hyperparameters` to pass, and so on.\n",
+    "To create a SageMaker training job, we use a `HuggingFace`/`PyTorch` estimator. Using the estimator, you can define which fine-tuning script should SageMaker use through `entry_point`, which `instance_type` to use for training, which `hyperparameters` to pass, and so on.\n",
     "\n",
-    "When a SageMaker training job starts, SageMaker takes care of starting and managing all the required machine learning instances, picks up the `PyTorch` Deep Learning Container, uploads your training script, and downloads the data from `sagemaker_session_bucket` into the container at `/opt/ml/input/data`.\n",
+    "When a SageMaker training job starts, SageMaker takes care of starting and managing all the required machine learning instances, picks up the `HuggingFace` Deep Learning Container, uploads your training script, and downloads the data from `sagemaker_session_bucket` into the container at `/opt/ml/input/data`.\n",
     "\n",
-    "In the following section, you learn how to set up two versions of the SageMaker `PyTorch` estimator, a native one without the compiler and an optimized one with the compiler."
+    "In the following section, you learn how to set up two versions of the SageMaker `HuggingFace`/`PyTorch` estimator, a native one without the compiler and an optimized one with the compiler."
    ]
   },
   {
@@ -668,8 +668,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sagemaker.pytorch import PyTorch\n",
-    "from sagemaker.training_compiler.config import TrainingCompilerConfig\n",
+    "from sagemaker.huggingface import HuggingFace, TrainingCompilerConfig\n",
     "# an updated max batch size that can fit into GPU memory with compiler\n",
     "batch_size = 52\n",
     "\n",
@@ -697,7 +696,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "compile_estimator = PyTorch(\n",
+    "compile_estimator = HuggingFace(\n",
     "    entry_point=\"qa_trainer_huggingface.py\",\n",
     "    compiler_config=TrainingCompilerConfig(),\n",
     "    source_dir=\"./scripts\",\n",
@@ -706,7 +705,7 @@
     "    role=role,\n",
     "    py_version=\"py38\",\n",
     "    transformers_version=\"4.21.1\",\n",
-    "    framework_version=\"1.11.0\",\n",
+    "    pytorch_version=\"1.11.0\",\n",
     "    volume_size=volume_size,\n",
     "    hyperparameters=hyperparameters,\n",
     "    disable_profiler=True,\n",

diff --git a/...mpiler/huggingface/pytorch_single_gpu_single_node/albert-base-v2/scripts/requirements.txt b/...mpiler/huggingface/pytorch_single_gpu_single_node/albert-base-v2/scripts/requirements.txt
@@ -1,7 +1,2 @@
 transformers == 4.21.1
-accelerate
-torch >= 1.3
-datasets >= 1.8.0
-sentencepiece != 0.1.92
-protobuf
-evaluate
+datasets == 1.18.4
diff --git a/...torch_single_gpu_single_node/bert-base-cased/bert-base-cased-single-node-single-gpu.ipynb b/...torch_single_gpu_single_node/bert-base-cased/bert-base-cased-single-node-single-gpu.ipynb
@@ -72,7 +72,7 @@
    "source": [
     "### Installation\n",
     "\n",
-    "This example notebook requires the **SageMaker Python SDK v2.70.0** and **transformers v4.11.0**."
+    "This example notebook requires the **SageMaker Python SDK v2.108.0** and **transformers v4.21**."
    ]
   },
   {
@@ -81,7 +81,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install sagemaker botocore boto3 awscli s3fs typing-extensions --upgrade"
+    "!pip install \"sagemaker>=2.108.0\" botocore boto3 awscli s3fs typing-extensions --upgrade"
    ]
   },
   {
@@ -90,7 +90,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install transformers datasets --upgrade"
+    "!pip install \"transformers==4.21\" datasets --upgrade"
    ]
   },
   {
@@ -375,11 +375,11 @@
    "source": [
     "## SageMaker Training Job\n",
     "\n",
-    "To create a SageMaker training job, we use a `HuggingFace` estimator. Using the estimator, you can define which fine-tuning script should SageMaker use through `entry_point`, which `instance_type` to use for training, which `hyperparameters` to pass, and so on.\n",
+    "To create a SageMaker training job, we use a `HuggingFace/PyTorch` estimator. Using the estimator, you can define which fine-tuning script should SageMaker use through `entry_point`, which `instance_type` to use for training, which `hyperparameters` to pass, and so on.\n",
     "\n",
     "When a SageMaker training job starts, SageMaker takes care of starting and managing all the required machine learning instances, picks up the `HuggingFace` Deep Learning Container, uploads your training script, and downloads the data from `sagemaker_session_bucket` into the container at `/opt/ml/input/data`.\n",
     "\n",
-    "In the following section, you learn how to set up two versions of the SageMaker `HuggingFace` estimator, a native one without the compiler and an optimized one with the compiler."
+    "In the following section, you learn how to set up two versions of the SageMaker `HuggingFace/PyTorch` estimator, a native one without the compiler and an optimized one with the compiler."
    ]
   },
   {
@@ -472,8 +472,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sagemaker.pytorch import PyTorch\n",
-    "from sagemaker.training_compiler.config import TrainingCompilerConfig\n",
+    "from sagemaker.huggingface import HuggingFace, TrainingCompilerConfig\n",
     "\n",
     "hyperparameters = {\n",
     "    \"epochs\": 5,\n",
@@ -500,7 +499,7 @@
     "\n",
     "# Importantly, the TrainingCompilerConfig() is passed below to enable the SageMaker Training Compiler\n",
     "\n",
-    "sm_training_compiler_estimator = PyTorch(\n",
+    "sm_training_compiler_estimator = HuggingFace(\n",
     "    entry_point=\"train.py\",\n",
     "    source_dir=\"./scripts\",\n",
     "    instance_type=\"ml.p3.2xlarge\",\n",
@@ -510,7 +509,7 @@
     "    base_job_name=\"sm-compiled-sst-bert-base-cased-p3-2x-pytorch-190\",\n",
     "    volume_size=volume_size,\n",
     "    transformers_version=\"4.21.1\",\n",
-    "    framework_version=\"1.11.0\",\n",
+    "    pytorch_version=\"1.11.0\",\n",
     "    compiler_config=TrainingCompilerConfig(),\n",
     "    hyperparameters=hyperparameters,\n",
     "    disable_profiler=True,\n",

diff --git a/...piler/huggingface/pytorch_single_gpu_single_node/bert-base-cased/scripts/requirements.txt b/...piler/huggingface/pytorch_single_gpu_single_node/bert-base-cased/scripts/requirements.txt
@@ -1,7 +1,2 @@
 transformers == 4.21.1
-accelerate
-torch >= 1.3
-datasets >= 1.8.0
-sentencepiece != 0.1.92
-protobuf
-evaluate
+datasets == 1.18.4
diff --git a/...ining-compiler/huggingface/pytorch_single_gpu_single_node/roberta-base/roberta-base.ipynb b/...ining-compiler/huggingface/pytorch_single_gpu_single_node/roberta-base/roberta-base.ipynb
@@ -58,7 +58,7 @@
    "source": [
     "### Installation\n",
     "\n",
-    "This example notebook requires the **SageMaker Python SDK v2.70.0** and **transformers v4.11.0**."
+    "This example notebook requires the **SageMaker Python SDK v2.108.0** and **transformers v4.21**."
    ]
   },
   {
@@ -67,7 +67,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install sagemaker botocore boto3 awscli --upgrade"
+    "!pip install \"sagemaker>=2.108.0\" botocore boto3 awscli --upgrade"
    ]
   },
   {
@@ -76,7 +76,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install -U transformers datasets --upgrade"
+    "!pip install -U \"transformers==4.21.1\" datasets --upgrade"
    ]
   },
   {
@@ -284,11 +284,11 @@
    "source": [
     "## SageMaker Training Job\n",
     "\n",
-    "To create a SageMaker training job, we use a `HuggingFace` estimator. Using the estimator, you can define which fine-tuning script should SageMaker use through `entry_point`, which `instance_type` to use for training, which `hyperparameters` to pass, and so on.\n",
+    "To create a SageMaker training job, we use a `HuggingFace/PyTorch` estimator. Using the estimator, you can define which fine-tuning script should SageMaker use through `entry_point`, which `instance_type` to use for training, which `hyperparameters` to pass, and so on.\n",
     "\n",
     "When a SageMaker training job starts, SageMaker takes care of starting and managing all the required machine learning instances, picks up the `HuggingFace` Deep Learning Container, uploads your training script, and downloads the data from `sagemaker_session_bucket` into the container at `/opt/ml/input/data`.\n",
     "\n",
-    "In the following section, you learn how to set up two versions of the SageMaker `HuggingFace` estimator, a native one without the compiler and an optimized one with the compiler."
+    "In the following section, you learn how to set up two versions of the SageMaker `HuggingFace/PyTorch` estimator, a native one without the compiler and an optimized one with the compiler."
    ]
   },
   {
@@ -349,7 +349,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#from sagemaker.huggingface import HuggingFace, TrainingCompilerConfig\n",
     "from sagemaker.pytorch import PyTorch\n",
     "\n",
     "# hyperparameters, which are passed into the training job\n",
@@ -420,9 +419,7 @@
     "# If checkpointing is enabled with higher epoch numbers, your disk requirements will increase as well\n",
     "volume_size = 60 + 2 * hyperparameters[\"epochs\"]\n",
     "\n",
-    "from sagemaker.training_compiler.config import TrainingCompilerConfig\n",
-    "\n",
-    "hyperparameters[TrainingCompilerConfig.HP_ENABLE_COMPILER] = True"
+    "from sagemaker.huggingface import HuggingFace, TrainingCompilerConfig"
    ]
   },
   {
@@ -431,24 +428,21 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "TRCOMP_IMAGE_URI = '669063966089.dkr.ecr.us-west-2.amazonaws.com/pr-huggingface-pytorch-trcomp-training:1.11.0-transformers4.21.1-gpu-py38-cu113-ubuntu20.04-pr-2032'\n",
-    "\n",
     "# configure the training job\n",
-    "optimized_estimator = PyTorch(\n",
+    "optimized_estimator = HuggingFace(\n",
     "    entry_point=TRAINING_SCRIPT,\n",
-    "    #compiler_config=TrainingCompilerConfig(),\n",
+    "    compiler_config=TrainingCompilerConfig(),\n",
     "    source_dir=\"./scripts\",\n",
     "    instance_type=INSTANCE_TYPE,\n",
     "    instance_count=1,\n",
     "    role=role,\n",
     "    py_version=\"py38\",\n",
     "    transformers_version=\"4.21.1\",\n",
-    "    framework_version=\"1.11.0\",\n",
+    "    pytorch_version=\"1.11.0\",\n",
     "    volume_size=volume_size,\n",
     "    hyperparameters=hyperparameters,\n",
     "    disable_profiler=True,\n",
     "    debugger_hook_config=False,\n",
-    "    image_uri=TRCOMP_IMAGE_URI,\n",
     ")\n",
     "\n",
     "# start training with our uploaded datasets as input\n",
@@ -841,6 +835,13 @@
    "source": [
     "Also, to find instructions on cleaning up resources, see [Clean Up](https://docs.aws.amazon.com/sagemaker/latest/dg/ex1-cleanup.html) in the *Amazon SageMaker Developer Guide*."
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

diff --git a/...compiler/huggingface/pytorch_single_gpu_single_node/roberta-base/scripts/requirements.txt b/...compiler/huggingface/pytorch_single_gpu_single_node/roberta-base/scripts/requirements.txt
@@ -1,7 +1,2 @@
 transformers == 4.21.1
-accelerate
-torch >= 1.3
-datasets >= 1.8.0
-sentencepiece != 0.1.92
-protobuf
-evaluate
+datasets == 1.18.4