Skip to content

Update Ray Train examples for new public API #210

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 7, 2025
Merged

Update Ray Train examples for new public API #210

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4057b2a
Update Ray Train examples for new public API
Lothiraldan Feb 6, 2025
4fff205
Fix github action
Lothiraldan Feb 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions .github/workflows/test-examples.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,10 +92,9 @@ jobs:
COMET_INTERNAL_SENTRY_DSN: ${{ secrets.COMET_INTERNAL_SENTRY_DSN }}
COMET_WORKSPACE: cometexamples-tests
- name: debugging-save-logs
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
if: runner.debug == '1' && failure()
with:
name: debug-logs
path: ${{ env.COMET_LOG_DIR }}

test-scripts:
Expand Down
132 changes: 62 additions & 70 deletions ...ns/model-training/ray-train/notebooks/Comet_with_ray_train_huggingface_transformers.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@
},
"outputs": [],
"source": [
"%pip install \"comet_ml>=3.31.5\" \"ray[air]>=2.1.0\" \"transformers>=4.43.0\" \"accelerate>=0.12.0\" \"datasets\" \"sentencepiece\" scipy \"scikit-learn\" protobuf \"torch>=1.3\" evaluate"
"%pip install \"comet_ml>=3.49.0\" \"ray[air]>=2.1.0\" \"transformers>=4.43.0\" \"accelerate>=0.12.0\" \"datasets\" \"sentencepiece\" scipy \"scikit-learn\" protobuf \"torch>=1.3\" evaluate"
]
},
{
Expand All @@ -62,7 +62,6 @@
"outputs": [],
"source": [
"import comet_ml\n",
"import comet_ml.integration.ray\n",
"\n",
"comet_ml.init()"
]
Expand Down Expand Up @@ -101,7 +100,9 @@
"\n",
"import ray.train.huggingface.transformers\n",
"from ray.train import ScalingConfig, RunConfig\n",
"from ray.train.torch import TorchTrainer"
"from ray.train.torch import TorchTrainer\n",
"import comet_ml.integration.ray\n",
"from comet_ml.integration.ray import comet_worker"
]
},
{
Expand Down Expand Up @@ -164,63 +165,62 @@
"metadata": {},
"outputs": [],
"source": [
"@comet_worker\n",
"def train_func(config):\n",
" from comet_ml import get_running_experiment\n",
" from comet_ml.integration.ray import comet_worker_logger\n",
"\n",
" with comet_worker_logger(config) as experiment:\n",
" small_train_dataset, small_eval_dataset = get_dataset()\n",
"\n",
" # Model\n",
" model = AutoModelForSequenceClassification.from_pretrained(\n",
" \"google-bert/bert-base-cased\", num_labels=5\n",
" )\n",
"\n",
" # Evaluation Metrics\n",
" metric = evaluate.load(\"accuracy\")\n",
"\n",
" def compute_metrics(eval_pred):\n",
" logits, labels = eval_pred\n",
" predictions = np.argmax(logits, axis=-1)\n",
"\n",
" experiment = comet_ml.get_running_experiment()\n",
" if experiment:\n",
" experiment.log_confusion_matrix(predictions, labels)\n",
"\n",
" return metric.compute(predictions=predictions, references=labels)\n",
"\n",
" # Hugging Face Trainer\n",
" training_args = TrainingArguments(\n",
" do_eval=True,\n",
" do_train=True,\n",
" eval_strategy=\"epoch\",\n",
" num_train_epochs=config[\"epochs\"],\n",
" output_dir=\"./results\",\n",
" overwrite_output_dir=True,\n",
" per_device_eval_batch_size=4,\n",
" per_device_train_batch_size=4,\n",
" report_to=[\"comet_ml\"],\n",
" seed=SEED,\n",
" )\n",
" trainer = Trainer(\n",
" model=model,\n",
" args=training_args,\n",
" train_dataset=small_train_dataset,\n",
" eval_dataset=small_eval_dataset,\n",
" compute_metrics=compute_metrics,\n",
" )\n",
"\n",
" # Report Metrics and Checkpoints to Ray Train\n",
" callback = ray.train.huggingface.transformers.RayTrainReportCallback()\n",
" trainer.add_callback(callback)\n",
"\n",
" # Prepare Transformers Trainer\n",
" trainer = ray.train.huggingface.transformers.prepare_trainer(trainer)\n",
"\n",
" # Start Training\n",
" trainer.train()\n",
"\n",
" comet_ml.get_running_experiment().end()"
"\n",
" small_train_dataset, small_eval_dataset = get_dataset()\n",
"\n",
" # Model\n",
" model = AutoModelForSequenceClassification.from_pretrained(\n",
" \"google-bert/bert-base-cased\", num_labels=5\n",
" )\n",
"\n",
" # Evaluation Metrics\n",
" metric = evaluate.load(\"accuracy\")\n",
"\n",
" def compute_metrics(eval_pred):\n",
" logits, labels = eval_pred\n",
" predictions = np.argmax(logits, axis=-1)\n",
"\n",
" experiment = comet_ml.get_running_experiment()\n",
" if experiment:\n",
" experiment.log_confusion_matrix(predictions, labels)\n",
"\n",
" return metric.compute(predictions=predictions, references=labels)\n",
"\n",
" # Hugging Face Trainer\n",
" training_args = TrainingArguments(\n",
" do_eval=True,\n",
" do_train=True,\n",
" eval_strategy=\"epoch\",\n",
" num_train_epochs=config[\"epochs\"],\n",
" output_dir=\"./results\",\n",
" overwrite_output_dir=True,\n",
" per_device_eval_batch_size=4,\n",
" per_device_train_batch_size=4,\n",
" report_to=[\"comet_ml\"],\n",
" seed=SEED,\n",
" )\n",
" trainer = Trainer(\n",
" model=model,\n",
" args=training_args,\n",
" train_dataset=small_train_dataset,\n",
" eval_dataset=small_eval_dataset,\n",
" compute_metrics=compute_metrics,\n",
" )\n",
"\n",
" # Report Metrics and Checkpoints to Ray Train\n",
" callback = ray.train.huggingface.transformers.RayTrainReportCallback()\n",
" trainer.add_callback(callback)\n",
"\n",
" # Prepare Transformers Trainer\n",
" trainer = ray.train.huggingface.transformers.prepare_trainer(trainer)\n",
"\n",
" # Start Training\n",
" trainer.train()\n",
"\n",
" comet_ml.end()"
]
},
{
Expand All @@ -240,16 +240,15 @@
" scaling_config = ScalingConfig(num_workers=num_workers, use_gpu=use_gpu)\n",
" config = {\"use_gpu\": use_gpu, \"epochs\": 2}\n",
"\n",
" callback = comet_ml.integration.ray.CometTrainLoggerCallback(\n",
" config, project_name=\"comet-example-ray-train-hugginface-transformers\"\n",
" )\n",
"\n",
" ray_trainer = TorchTrainer(\n",
" train_func,\n",
" scaling_config=scaling_config,\n",
" train_loop_config=config,\n",
" run_config=RunConfig(callbacks=[callback]),\n",
" )\n",
" comet_ml.integration.ray.comet_ray_train_logger(\n",
" ray_trainer, project_name=\"comet-example-ray-train-hugginface-transformers\"\n",
" )\n",
"\n",
" result = ray_trainer.fit()"
]
},
Expand Down Expand Up @@ -278,13 +277,6 @@
"\n",
"train(num_workers, use_gpu=False, epochs=5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
Expand Down
73 changes: 41 additions & 32 deletions integrations/model-training/ray-train/notebooks/Comet_with_ray_train_keras.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@
},
"outputs": [],
"source": [
"%pip install -U \"comet_ml>=3.44.0\" \"ray[air]>=2.1.0\" \"keras<3\" \"tensorflow<2.16.0\""
"%pip install -U \"comet_ml>=3.49.0\" \"ray[air]>=2.1.0\" \"keras<3\" \"tensorflow<2.16.0\""
]
},
{
Expand Down Expand Up @@ -88,6 +88,7 @@
"import os\n",
"\n",
"import comet_ml.integration.ray\n",
"from comet_ml.integration.ray import comet_worker\n",
"\n",
"import numpy as np\n",
"import ray\n",
Expand Down Expand Up @@ -172,45 +173,43 @@
},
"outputs": [],
"source": [
"@comet_worker\n",
"def train_func(config: dict):\n",
" from comet_ml.integration.ray import comet_worker_logger\n",
" from ray.air import session\n",
"\n",
" per_worker_batch_size = config.get(\"batch_size\", 64)\n",
" epochs = config.get(\"epochs\", 3)\n",
" steps_per_epoch = config.get(\"steps_per_epoch\", 70)\n",
"\n",
" with comet_worker_logger(config) as experiment:\n",
" tf_config = json.loads(os.environ[\"TF_CONFIG\"])\n",
" num_workers = len(tf_config[\"cluster\"][\"worker\"])\n",
"\n",
" tf_config = json.loads(os.environ[\"TF_CONFIG\"])\n",
" num_workers = len(tf_config[\"cluster\"][\"worker\"])\n",
" strategy = tf.distribute.MultiWorkerMirroredStrategy()\n",
"\n",
" strategy = tf.distribute.MultiWorkerMirroredStrategy()\n",
" global_batch_size = per_worker_batch_size * num_workers\n",
" multi_worker_dataset = mnist_dataset(global_batch_size)\n",
"\n",
" global_batch_size = per_worker_batch_size * num_workers\n",
" multi_worker_dataset = mnist_dataset(global_batch_size)\n",
"\n",
" with strategy.scope():\n",
" # Model building/compiling need to be within `strategy.scope()`.\n",
" multi_worker_model = build_cnn_model()\n",
" learning_rate = config.get(\"lr\", 0.001)\n",
" multi_worker_model.compile(\n",
" loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
" optimizer=tf.keras.optimizers.SGD(learning_rate=learning_rate),\n",
" metrics=[\"accuracy\"],\n",
" )\n",
" with strategy.scope():\n",
" # Model building/compiling need to be within `strategy.scope()`.\n",
" multi_worker_model = build_cnn_model()\n",
" learning_rate = config.get(\"lr\", 0.001)\n",
" multi_worker_model.compile(\n",
" loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
" optimizer=tf.keras.optimizers.SGD(learning_rate=learning_rate),\n",
" metrics=[\"accuracy\"],\n",
" )\n",
"\n",
" callbacks = []\n",
" if session.get_world_rank() == 0:\n",
" callbacks.append(experiment.get_callback(\"tf-keras\"))\n",
" callbacks = []\n",
" if session.get_world_rank() == 0:\n",
" callbacks.append(comet_ml.get_running_experiment().get_callback(\"tf-keras\"))\n",
"\n",
" history = multi_worker_model.fit(\n",
" multi_worker_dataset,\n",
" epochs=epochs,\n",
" steps_per_epoch=steps_per_epoch,\n",
" callbacks=callbacks,\n",
" )\n",
" results = history.history\n",
" history = multi_worker_model.fit(\n",
" multi_worker_dataset,\n",
" epochs=epochs,\n",
" steps_per_epoch=steps_per_epoch,\n",
" callbacks=callbacks,\n",
" )\n",
" results = history.history\n",
"\n",
" return results"
]
Expand All @@ -233,14 +232,15 @@
") -> Result:\n",
" config = {\"lr\": 1e-3, \"batch_size\": 64, \"epochs\": epochs}\n",
"\n",
" callback = comet_ml.integration.ray.CometTrainLoggerCallback(config)\n",
"\n",
" trainer = TensorflowTrainer(\n",
" train_loop_per_worker=train_func,\n",
" train_loop_config=config,\n",
" scaling_config=ScalingConfig(num_workers=num_workers, use_gpu=use_gpu),\n",
" run_config=RunConfig(callbacks=[callback]),\n",
" )\n",
" comet_ml.integration.ray.comet_ray_train_logger(\n",
" trainer, project_name=\"comet-example-ray-train-keras\"\n",
" )\n",
"\n",
" results = trainer.fit()\n",
" return results"
]
Expand Down Expand Up @@ -270,6 +270,15 @@
"\n",
"train_tensorflow_mnist(num_workers, use_gpu=False, epochs=10)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"comet_ml.end()"
]
}
],
"metadata": {
Expand All @@ -291,7 +300,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
"version": "3.9.1"
}
},
"nbformat": 4,
Expand Down
Loading
Loading