chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,55 @@
|
||||
load("//bazel:python.bzl", "py_test_run_all_notebooks")
|
||||
|
||||
filegroup(
|
||||
name = "tune_examples",
|
||||
srcs = glob(["*.ipynb"]),
|
||||
visibility = ["//doc:__subpackages__"],
|
||||
)
|
||||
|
||||
# --------------------------------------------------------------------
|
||||
# Test all doc/source/tune/examples notebooks.
|
||||
# --------------------------------------------------------------------
|
||||
|
||||
# pbt_ppo_example.ipynb is not tested right now due to large resource
|
||||
# requirements
|
||||
|
||||
py_test_run_all_notebooks(
|
||||
size = "medium",
|
||||
include = ["*.ipynb"],
|
||||
data = ["//doc/source/tune/examples:tune_examples"],
|
||||
exclude = [
|
||||
"pbt_ppo_example.ipynb",
|
||||
"tune-xgboost.ipynb",
|
||||
"pbt_transformers.ipynb", # Transformers uses legacy Tune APIs.
|
||||
"tune-aim.ipynb", # CI does not have `aim`
|
||||
"bohb_example.ipynb", # CI does not have bohb requirements
|
||||
],
|
||||
tags = [
|
||||
"exclusive",
|
||||
"team:ml",
|
||||
],
|
||||
env = {"RAY_TRAIN_V2_ENABLED": "1"},
|
||||
)
|
||||
|
||||
# GPU tests
|
||||
py_test_run_all_notebooks(
|
||||
size = "large",
|
||||
include = ["tune-xgboost.ipynb"],
|
||||
data = ["//doc/source/tune/examples:tune_examples"],
|
||||
exclude = [],
|
||||
tags = [
|
||||
"exclusive",
|
||||
"gpu",
|
||||
"team:ml",
|
||||
],
|
||||
env = {"RAY_TRAIN_V2_ENABLED": "1"},
|
||||
)
|
||||
|
||||
filegroup(
|
||||
name = "tune_examples_ci_configs",
|
||||
srcs = glob([
|
||||
"**/ci/aws.yaml",
|
||||
"**/ci/gce.yaml",
|
||||
]),
|
||||
visibility = ["//doc:__pkg__"],
|
||||
)
|
||||
@@ -0,0 +1,928 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "47de02e1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Running Tune experiments with AxSearch\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-ray-tune-ax_example\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=ray-tune-ax_example\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"In this tutorial we introduce Ax, while running a simple Ray Tune experiment. Tune’s Search Algorithms integrate with Ax and, as a result, allow you to seamlessly scale up a Ax optimization process - without sacrificing performance.\n",
|
||||
"\n",
|
||||
"Ax is a platform for optimizing any kind of experiment, including machine learning experiments, A/B tests, and simulations. Ax can optimize discrete configurations (e.g., variants of an A/B test) using multi-armed bandit optimization, and continuous/ordered configurations (e.g. float/int parameters) using Bayesian optimization. Results of A/B tests and simulations with reinforcement learning agents often exhibit high amounts of noise. Ax supports state-of-the-art algorithms which work better than traditional Bayesian optimization in high-noise settings. Ax also supports multi-objective and constrained optimization which are common to real-world problems (e.g. improving load time without increasing data use). Ax belongs to the domain of \"derivative-free\" and \"black-box\" optimization.\n",
|
||||
"\n",
|
||||
"In this example we minimize a simple objective to briefly demonstrate the usage of AxSearch with Ray Tune via `AxSearch`. It's useful to keep in mind that despite the emphasis on machine learning experiments, Ray Tune optimizes any implicit or explicit objective. Here we assume `ax-platform==0.2.4` library is installed withe python version >= 3.7. To learn more, please refer to the [Ax website](https://ax.dev/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "297d8b18",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Requirement already satisfied: ax-platform==0.2.4 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (0.2.4)\n",
|
||||
"Requirement already satisfied: botorch==0.6.2 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from ax-platform==0.2.4) (0.6.2)\n",
|
||||
"Requirement already satisfied: jinja2 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from ax-platform==0.2.4) (3.0.3)\n",
|
||||
"Requirement already satisfied: pandas in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from ax-platform==0.2.4) (1.3.5)\n",
|
||||
"Requirement already satisfied: scipy in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from ax-platform==0.2.4) (1.4.1)\n",
|
||||
"Requirement already satisfied: plotly in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from ax-platform==0.2.4) (5.6.0)\n",
|
||||
"Requirement already satisfied: scikit-learn in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from ax-platform==0.2.4) (0.24.2)\n",
|
||||
"Requirement already satisfied: typeguard in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from ax-platform==0.2.4) (2.13.3)\n",
|
||||
"Requirement already satisfied: gpytorch>=1.6 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from botorch==0.6.2->ax-platform==0.2.4) (1.6.0)\n",
|
||||
"Requirement already satisfied: torch>=1.9 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from botorch==0.6.2->ax-platform==0.2.4) (1.9.0)\n",
|
||||
"Requirement already satisfied: multipledispatch in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from botorch==0.6.2->ax-platform==0.2.4) (0.6.0)\n",
|
||||
"Requirement already satisfied: MarkupSafe>=2.0 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from jinja2->ax-platform==0.2.4) (2.0.1)\n",
|
||||
"Requirement already satisfied: pytz>=2017.3 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from pandas->ax-platform==0.2.4) (2022.1)\n",
|
||||
"Requirement already satisfied: numpy>=1.17.3 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from pandas->ax-platform==0.2.4) (1.21.6)\n",
|
||||
"Requirement already satisfied: python-dateutil>=2.7.3 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from pandas->ax-platform==0.2.4) (2.8.2)\n",
|
||||
"Requirement already satisfied: tenacity>=6.2.0 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from plotly->ax-platform==0.2.4) (8.0.1)\n",
|
||||
"Requirement already satisfied: six in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from plotly->ax-platform==0.2.4) (1.16.0)\n",
|
||||
"Requirement already satisfied: joblib>=0.11 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from scikit-learn->ax-platform==0.2.4) (1.1.0)\n",
|
||||
"Requirement already satisfied: threadpoolctl>=2.0.0 in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from scikit-learn->ax-platform==0.2.4) (3.0.0)\n",
|
||||
"Requirement already satisfied: typing-extensions in ~/.pyenv/versions/3.7.7/lib/python3.7/site-packages (from torch>=1.9->botorch==0.6.2->ax-platform==0.2.4) (4.1.1)\n",
|
||||
"\u001b[33mWARNING: There was an error checking the latest version of pip.\u001b[0m\u001b[33m\n",
|
||||
"\u001b[0m"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# !pip install ray[tune]\n",
|
||||
"!pip install ax-platform==0.2.4"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "59b1e0d1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Click below to see all the imports we need for this example."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "cbae6dbe",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-input"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import time\n",
|
||||
"\n",
|
||||
"import ray\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.search.ax import AxSearch"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "7b2b6af7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's start by defining a classic benchmark for global optimization.\n",
|
||||
"The form here is explicit for demonstration, yet it is typically a black-box.\n",
|
||||
"We artificially sleep for a bit (`0.02` seconds) to simulate a long-running ML experiment.\n",
|
||||
"This setup assumes that we're running multiple `step`s of an experiment and try to tune 6-dimensions of the `x` hyperparameter."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "0f7fbe0f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def landscape(x):\n",
|
||||
" \"\"\"\n",
|
||||
" Hartmann 6D function containing 6 local minima.\n",
|
||||
" It is a classic benchmark for developing global optimization algorithms.\n",
|
||||
" \"\"\"\n",
|
||||
" alpha = np.array([1.0, 1.2, 3.0, 3.2])\n",
|
||||
" A = np.array(\n",
|
||||
" [\n",
|
||||
" [10, 3, 17, 3.5, 1.7, 8],\n",
|
||||
" [0.05, 10, 17, 0.1, 8, 14],\n",
|
||||
" [3, 3.5, 1.7, 10, 17, 8],\n",
|
||||
" [17, 8, 0.05, 10, 0.1, 14],\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
" P = 10 ** (-4) * np.array(\n",
|
||||
" [\n",
|
||||
" [1312, 1696, 5569, 124, 8283, 5886],\n",
|
||||
" [2329, 4135, 8307, 3736, 1004, 9991],\n",
|
||||
" [2348, 1451, 3522, 2883, 3047, 6650],\n",
|
||||
" [4047, 8828, 8732, 5743, 1091, 381],\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
" y = 0.0\n",
|
||||
" for j, alpha_j in enumerate(alpha):\n",
|
||||
" t = 0\n",
|
||||
" for k in range(6):\n",
|
||||
" t += A[j, k] * ((x[k] - P[j, k]) ** 2)\n",
|
||||
" y -= alpha_j * np.exp(-t)\n",
|
||||
" return y"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "0b1ae9df",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next, our `objective` function takes a Tune `config`, evaluates the `landscape` of our experiment in a training loop,\n",
|
||||
"and uses `tune.report` to report the `landscape` back to Tune."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "8c3f252e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def objective(config):\n",
|
||||
" for i in range(config[\"iterations\"]):\n",
|
||||
" x = np.array([config.get(\"x{}\".format(i + 1)) for i in range(6)])\n",
|
||||
" tune.report(\n",
|
||||
" {\"timesteps_total\": i, \"landscape\": landscape(x), \"l2norm\": np.sqrt((x ** 2).sum())}\n",
|
||||
" )\n",
|
||||
" time.sleep(0.02)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "d9982d95",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next we define a search space. The critical assumption is that the optimal hyperparameters live within this space. Yet, if the space is very large, then those hyperparameters may be difficult to find in a short amount of time."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "30f75f5a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search_space = {\n",
|
||||
" \"iterations\":100,\n",
|
||||
" \"x1\": tune.uniform(0.0, 1.0),\n",
|
||||
" \"x2\": tune.uniform(0.0, 1.0),\n",
|
||||
" \"x3\": tune.uniform(0.0, 1.0),\n",
|
||||
" \"x4\": tune.uniform(0.0, 1.0),\n",
|
||||
" \"x5\": tune.uniform(0.0, 1.0),\n",
|
||||
" \"x6\": tune.uniform(0.0, 1.0)\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "106d8578",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ray.init(configure_logging=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "932f74e6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we define the search algorithm from `AxSearch`. If you want to constrain your parameters or even the space of outcomes, that can be easily done by passing the argumentsas below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "34dd5c95",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"algo = AxSearch(\n",
|
||||
" parameter_constraints=[\"x1 + x2 <= 2.0\"],\n",
|
||||
" outcome_constraints=[\"l2norm <= 1.25\"],\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "f6d18a99",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We also use `ConcurrencyLimiter` to constrain to 4 concurrent trials. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "dcd905ef",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"algo = tune.search.ConcurrencyLimiter(algo, max_concurrent=4)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "10fd5427",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The number of samples is the number of hyperparameter combinations that will be tried out. This Tune run is set to `1000` samples.\n",
|
||||
"You can decrease this if it takes too long on your machine, or you can set a time limit easily through `stop` argument in the `RunConfig()` as we will show here."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "c53349a5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"num_samples = 100\n",
|
||||
"stop_timesteps = 200"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "6c661045",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Reducing samples for smoke tests\n",
|
||||
"num_samples = 10"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "91076c5a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Finally, we run the experiment to find the global minimum of the provided landscape (which contains 5 false minima). The argument to metric, `\"landscape\"`, is provided via the `objective` function's `tune.report`. The experiment `\"min\"`imizes the \"mean_loss\" of the `landscape` by searching within `search_space` via `algo`, `num_samples` times or when `\"timesteps_total\": stop_timesteps`. This previous sentence is fully characterizes the search problem we aim to solve. With this in mind, notice how efficient it is to execute `tuner.fit()`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "2f519d63",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[INFO 07-22 15:04:18] ax.service.ax_client: Starting optimization with verbose logging. To disable logging, set the `verbose_logging` argument to `False`. Note that float values in the logs are rounded to 6 decimal points.\n",
|
||||
"[INFO 07-22 15:04:18] ax.service.utils.instantiation: Created search space: SearchSpace(parameters=[FixedParameter(name='iterations', parameter_type=INT, value=100), RangeParameter(name='x1', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x2', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x3', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x4', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x5', parameter_type=FLOAT, range=[0.0, 1.0]), RangeParameter(name='x6', parameter_type=FLOAT, range=[0.0, 1.0])], parameter_constraints=[ParameterConstraint(1.0*x1 + 1.0*x2 <= 2.0)]).\n",
|
||||
"[INFO 07-22 15:04:18] ax.modelbridge.dispatch_utils: Using Bayesian optimization since there are more ordered parameters than there are categories for the unordered categorical parameters.\n",
|
||||
"[INFO 07-22 15:04:18] ax.modelbridge.dispatch_utils: Using Bayesian Optimization generation strategy: GenerationStrategy(name='Sobol+GPEI', steps=[Sobol for 12 trials, GPEI for subsequent trials]). Iterations after 12 will take longer to generate due to model-fitting.\n",
|
||||
"Detected sequential enforcement. Be sure to use a ConcurrencyLimiter.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"== Status ==<br>Current time: 2022-07-22 15:04:35 (running for 00:00:16.56)<br>Memory usage on this node: 9.9/16.0 GiB<br>Using FIFO scheduling algorithm.<br>Resources requested: 0/16 CPUs, 0/0 GPUs, 0.0/5.13 GiB heap, 0.0/2.0 GiB objects<br>Current best trial: 34b7abda with landscape=-1.6624439263544026 and parameters={'iterations': 100, 'x1': 0.26526361983269453, 'x2': 0.9248840995132923, 'x3': 0.15171580761671066, 'x4': 0.43602637108415365, 'x5': 0.8573104059323668, 'x6': 0.08981018699705601}<br>Result logdir: ~/ray_results/ax<br>Number of trials: 10/10 (10 TERMINATED)<br><table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> iterations</th><th style=\"text-align: right;\"> x1</th><th style=\"text-align: right;\"> x2</th><th style=\"text-align: right;\"> x3</th><th style=\"text-align: right;\"> x4</th><th style=\"text-align: right;\"> x5</th><th style=\"text-align: right;\"> x6</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> ts</th><th style=\"text-align: right;\"> landscape</th><th style=\"text-align: right;\"> l2norm</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>objective_2dfbe86a</td><td>TERMINATED</td><td>127.0.0.1:44721</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.0558336</td><td style=\"text-align: right;\">0.0896192</td><td style=\"text-align: right;\">0.958956 </td><td style=\"text-align: right;\">0.234474 </td><td style=\"text-align: right;\">0.174516 </td><td style=\"text-align: right;\">0.970311 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.57372</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.805233 </td><td style=\"text-align: right;\"> 1.39917</td></tr>\n",
|
||||
"<tr><td>objective_2fa776c0</td><td>TERMINATED</td><td>127.0.0.1:44726</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.744772 </td><td style=\"text-align: right;\">0.754537 </td><td style=\"text-align: right;\">0.0950125</td><td style=\"text-align: right;\">0.273877 </td><td style=\"text-align: right;\">0.0966829</td><td style=\"text-align: right;\">0.368943 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.6361 </td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.11286 </td><td style=\"text-align: right;\"> 1.16341</td></tr>\n",
|
||||
"<tr><td>objective_2fabaa1a</td><td>TERMINATED</td><td>127.0.0.1:44727</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.405704 </td><td style=\"text-align: right;\">0.374626 </td><td style=\"text-align: right;\">0.935628 </td><td style=\"text-align: right;\">0.222185 </td><td style=\"text-align: right;\">0.787212 </td><td style=\"text-align: right;\">0.00812439</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.62393</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.11348 </td><td style=\"text-align: right;\"> 1.35995</td></tr>\n",
|
||||
"<tr><td>objective_2faee7c0</td><td>TERMINATED</td><td>127.0.0.1:44728</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.664728 </td><td style=\"text-align: right;\">0.207519 </td><td style=\"text-align: right;\">0.359514 </td><td style=\"text-align: right;\">0.704578 </td><td style=\"text-align: right;\">0.755882 </td><td style=\"text-align: right;\">0.812402 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.62069</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.0119837 </td><td style=\"text-align: right;\"> 1.53035</td></tr>\n",
|
||||
"<tr><td>objective_313d3d3a</td><td>TERMINATED</td><td>127.0.0.1:44747</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.0418746</td><td style=\"text-align: right;\">0.992783 </td><td style=\"text-align: right;\">0.906027 </td><td style=\"text-align: right;\">0.594429 </td><td style=\"text-align: right;\">0.825393 </td><td style=\"text-align: right;\">0.646362 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 3.16233</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.00677976</td><td style=\"text-align: right;\"> 1.80573</td></tr>\n",
|
||||
"<tr><td>objective_32c9acd8</td><td>TERMINATED</td><td>127.0.0.1:44726</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.126064 </td><td style=\"text-align: right;\">0.703408 </td><td style=\"text-align: right;\">0.344681 </td><td style=\"text-align: right;\">0.337363 </td><td style=\"text-align: right;\">0.401396 </td><td style=\"text-align: right;\">0.679202 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 3.12119</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.904622 </td><td style=\"text-align: right;\"> 1.16864</td></tr>\n",
|
||||
"<tr><td>objective_32cf8ca2</td><td>TERMINATED</td><td>127.0.0.1:44756</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.0910936</td><td style=\"text-align: right;\">0.304138 </td><td style=\"text-align: right;\">0.869848 </td><td style=\"text-align: right;\">0.405435 </td><td style=\"text-align: right;\">0.567922 </td><td style=\"text-align: right;\">0.228608 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.70791</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.146532 </td><td style=\"text-align: right;\"> 1.18178</td></tr>\n",
|
||||
"<tr><td>objective_32d8dd20</td><td>TERMINATED</td><td>127.0.0.1:44758</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.603178 </td><td style=\"text-align: right;\">0.409057 </td><td style=\"text-align: right;\">0.729056 </td><td style=\"text-align: right;\">0.0825984</td><td style=\"text-align: right;\">0.572948 </td><td style=\"text-align: right;\">0.508304 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.64158</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.247223 </td><td style=\"text-align: right;\"> 1.28691</td></tr>\n",
|
||||
"<tr><td>objective_34adf04a</td><td>TERMINATED</td><td>127.0.0.1:44768</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.454189 </td><td style=\"text-align: right;\">0.271772 </td><td style=\"text-align: right;\">0.530871 </td><td style=\"text-align: right;\">0.991841 </td><td style=\"text-align: right;\">0.691843 </td><td style=\"text-align: right;\">0.472366 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.70327</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-0.0132915 </td><td style=\"text-align: right;\"> 1.49917</td></tr>\n",
|
||||
"<tr><td>objective_34b7abda</td><td>TERMINATED</td><td>127.0.0.1:44771</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">0.265264 </td><td style=\"text-align: right;\">0.924884 </td><td style=\"text-align: right;\">0.151716 </td><td style=\"text-align: right;\">0.436026 </td><td style=\"text-align: right;\">0.85731 </td><td style=\"text-align: right;\">0.0898102 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 2.68521</td><td style=\"text-align: right;\"> 99</td><td style=\"text-align: right;\">-1.66244 </td><td style=\"text-align: right;\"> 1.37185</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table><br><br>"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[INFO 07-22 15:04:19] ax.service.ax_client: Generated new trial 0 with parameters {'x1': 0.055834, 'x2': 0.089619, 'x3': 0.958956, 'x4': 0.234474, 'x5': 0.174516, 'x6': 0.970311, 'iterations': 100}.\n",
|
||||
"[INFO 07-22 15:04:22] ax.service.ax_client: Generated new trial 1 with parameters {'x1': 0.744772, 'x2': 0.754537, 'x3': 0.095012, 'x4': 0.273877, 'x5': 0.096683, 'x6': 0.368943, 'iterations': 100}.\n",
|
||||
"[INFO 07-22 15:04:22] ax.service.ax_client: Generated new trial 2 with parameters {'x1': 0.405704, 'x2': 0.374626, 'x3': 0.935628, 'x4': 0.222185, 'x5': 0.787212, 'x6': 0.008124, 'iterations': 100}.\n",
|
||||
"[INFO 07-22 15:04:22] ax.service.ax_client: Generated new trial 3 with parameters {'x1': 0.664728, 'x2': 0.207519, 'x3': 0.359514, 'x4': 0.704578, 'x5': 0.755882, 'x6': 0.812402, 'iterations': 100}.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Result for objective_2dfbe86a:\n",
|
||||
" date: 2022-07-22_15-04-22\n",
|
||||
" done: false\n",
|
||||
" experiment_id: 4ef8a12ac94a4f4fa483ec18e347967f\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.3991721132671366\n",
|
||||
" landscape: -0.8052333562869153\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44721\n",
|
||||
" time_since_restore: 0.00022912025451660156\n",
|
||||
" time_this_iter_s: 0.00022912025451660156\n",
|
||||
" time_total_s: 0.00022912025451660156\n",
|
||||
" timestamp: 1658498662\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 2dfbe86a\n",
|
||||
" warmup_time: 0.0035619735717773438\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[INFO 07-22 15:04:24] ax.service.ax_client: Completed trial 0 with data: {'landscape': (-0.805233, None), 'l2norm': (1.399172, None)}.\n",
|
||||
"[INFO 07-22 15:04:24] ax.service.ax_client: Generated new trial 4 with parameters {'x1': 0.041875, 'x2': 0.992783, 'x3': 0.906027, 'x4': 0.594429, 'x5': 0.825393, 'x6': 0.646362, 'iterations': 100}.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Result for objective_2faee7c0:\n",
|
||||
" date: 2022-07-22_15-04-24\n",
|
||||
" done: false\n",
|
||||
" experiment_id: 3699644e85ac439cb7c1a36ed0976307\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.530347488145437\n",
|
||||
" landscape: -0.011983676977099367\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44728\n",
|
||||
" time_since_restore: 0.00022292137145996094\n",
|
||||
" time_this_iter_s: 0.00022292137145996094\n",
|
||||
" time_total_s: 0.00022292137145996094\n",
|
||||
" timestamp: 1658498664\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 2faee7c0\n",
|
||||
" warmup_time: 0.0027179718017578125\n",
|
||||
" \n",
|
||||
"Result for objective_2fa776c0:\n",
|
||||
" date: 2022-07-22_15-04-24\n",
|
||||
" done: false\n",
|
||||
" experiment_id: c555bfed13ac43e5b8c8e9f6d4b9b2f7\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.1634068454629019\n",
|
||||
" landscape: -0.11285961764770336\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44726\n",
|
||||
" time_since_restore: 0.000225067138671875\n",
|
||||
" time_this_iter_s: 0.000225067138671875\n",
|
||||
" time_total_s: 0.000225067138671875\n",
|
||||
" timestamp: 1658498664\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 2fa776c0\n",
|
||||
" warmup_time: 0.0026290416717529297\n",
|
||||
" \n",
|
||||
"Result for objective_2dfbe86a:\n",
|
||||
" date: 2022-07-22_15-04-24\n",
|
||||
" done: true\n",
|
||||
" experiment_id: 4ef8a12ac94a4f4fa483ec18e347967f\n",
|
||||
" experiment_tag: 1_iterations=100,x1=0.0558,x2=0.0896,x3=0.9590,x4=0.2345,x5=0.1745,x6=0.9703\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.3991721132671366\n",
|
||||
" landscape: -0.8052333562869153\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44721\n",
|
||||
" time_since_restore: 2.573719024658203\n",
|
||||
" time_this_iter_s: 0.0251619815826416\n",
|
||||
" time_total_s: 2.573719024658203\n",
|
||||
" timestamp: 1658498664\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 2dfbe86a\n",
|
||||
" warmup_time: 0.0035619735717773438\n",
|
||||
" \n",
|
||||
"Result for objective_2fabaa1a:\n",
|
||||
" date: 2022-07-22_15-04-24\n",
|
||||
" done: false\n",
|
||||
" experiment_id: eb9287e4fe5f44c7868dc943e2642312\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.3599537840291782\n",
|
||||
" landscape: -0.11348012497414121\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44727\n",
|
||||
" time_since_restore: 0.00022077560424804688\n",
|
||||
" time_this_iter_s: 0.00022077560424804688\n",
|
||||
" time_total_s: 0.00022077560424804688\n",
|
||||
" timestamp: 1658498664\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 2fabaa1a\n",
|
||||
" warmup_time: 0.0025510787963867188\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[INFO 07-22 15:04:27] ax.service.ax_client: Completed trial 3 with data: {'landscape': (-0.011984, None), 'l2norm': (1.530347, None)}.\n",
|
||||
"[INFO 07-22 15:04:27] ax.service.ax_client: Generated new trial 5 with parameters {'x1': 0.126064, 'x2': 0.703408, 'x3': 0.344681, 'x4': 0.337363, 'x5': 0.401396, 'x6': 0.679202, 'iterations': 100}.\n",
|
||||
"[INFO 07-22 15:04:27] ax.service.ax_client: Completed trial 1 with data: {'landscape': (-0.11286, None), 'l2norm': (1.163407, None)}.\n",
|
||||
"[INFO 07-22 15:04:27] ax.service.ax_client: Generated new trial 6 with parameters {'x1': 0.091094, 'x2': 0.304138, 'x3': 0.869848, 'x4': 0.405435, 'x5': 0.567922, 'x6': 0.228608, 'iterations': 100}.\n",
|
||||
"[INFO 07-22 15:04:27] ax.service.ax_client: Completed trial 2 with data: {'landscape': (-0.11348, None), 'l2norm': (1.359954, None)}.\n",
|
||||
"[INFO 07-22 15:04:27] ax.service.ax_client: Generated new trial 7 with parameters {'x1': 0.603178, 'x2': 0.409057, 'x3': 0.729056, 'x4': 0.082598, 'x5': 0.572948, 'x6': 0.508304, 'iterations': 100}.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Result for objective_313d3d3a:\n",
|
||||
" date: 2022-07-22_15-04-27\n",
|
||||
" done: false\n",
|
||||
" experiment_id: fa7afd557e154fbebe4f54d8eedb3573\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.805729990121368\n",
|
||||
" landscape: -0.006779757704679272\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44747\n",
|
||||
" time_since_restore: 0.00021076202392578125\n",
|
||||
" time_this_iter_s: 0.00021076202392578125\n",
|
||||
" time_total_s: 0.00021076202392578125\n",
|
||||
" timestamp: 1658498667\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 313d3d3a\n",
|
||||
" warmup_time: 0.0029790401458740234\n",
|
||||
" \n",
|
||||
"Result for objective_2faee7c0:\n",
|
||||
" date: 2022-07-22_15-04-27\n",
|
||||
" done: true\n",
|
||||
" experiment_id: 3699644e85ac439cb7c1a36ed0976307\n",
|
||||
" experiment_tag: 4_iterations=100,x1=0.6647,x2=0.2075,x3=0.3595,x4=0.7046,x5=0.7559,x6=0.8124\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.530347488145437\n",
|
||||
" landscape: -0.011983676977099367\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44728\n",
|
||||
" time_since_restore: 2.6206929683685303\n",
|
||||
" time_this_iter_s: 0.027359962463378906\n",
|
||||
" time_total_s: 2.6206929683685303\n",
|
||||
" timestamp: 1658498667\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 2faee7c0\n",
|
||||
" warmup_time: 0.0027179718017578125\n",
|
||||
" \n",
|
||||
"Result for objective_2fa776c0:\n",
|
||||
" date: 2022-07-22_15-04-27\n",
|
||||
" done: true\n",
|
||||
" experiment_id: c555bfed13ac43e5b8c8e9f6d4b9b2f7\n",
|
||||
" experiment_tag: 2_iterations=100,x1=0.7448,x2=0.7545,x3=0.0950,x4=0.2739,x5=0.0967,x6=0.3689\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.1634068454629019\n",
|
||||
" landscape: -0.11285961764770336\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44726\n",
|
||||
" time_since_restore: 2.6361019611358643\n",
|
||||
" time_this_iter_s: 0.0264589786529541\n",
|
||||
" time_total_s: 2.6361019611358643\n",
|
||||
" timestamp: 1658498667\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 2fa776c0\n",
|
||||
" warmup_time: 0.0026290416717529297\n",
|
||||
" \n",
|
||||
"Result for objective_32c9acd8:\n",
|
||||
" date: 2022-07-22_15-04-27\n",
|
||||
" done: false\n",
|
||||
" experiment_id: c555bfed13ac43e5b8c8e9f6d4b9b2f7\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.1686440476629836\n",
|
||||
" landscape: -0.9046216637367911\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44726\n",
|
||||
" time_since_restore: 0.00020194053649902344\n",
|
||||
" time_this_iter_s: 0.00020194053649902344\n",
|
||||
" time_total_s: 0.00020194053649902344\n",
|
||||
" timestamp: 1658498667\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 32c9acd8\n",
|
||||
" warmup_time: 0.0026290416717529297\n",
|
||||
" \n",
|
||||
"Result for objective_2fabaa1a:\n",
|
||||
" date: 2022-07-22_15-04-27\n",
|
||||
" done: true\n",
|
||||
" experiment_id: eb9287e4fe5f44c7868dc943e2642312\n",
|
||||
" experiment_tag: 3_iterations=100,x1=0.4057,x2=0.3746,x3=0.9356,x4=0.2222,x5=0.7872,x6=0.0081\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.3599537840291782\n",
|
||||
" landscape: -0.11348012497414121\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44727\n",
|
||||
" time_since_restore: 2.623929977416992\n",
|
||||
" time_this_iter_s: 0.032716989517211914\n",
|
||||
" time_total_s: 2.623929977416992\n",
|
||||
" timestamp: 1658498667\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 2fabaa1a\n",
|
||||
" warmup_time: 0.0025510787963867188\n",
|
||||
" \n",
|
||||
"Result for objective_32d8dd20:\n",
|
||||
" date: 2022-07-22_15-04-30\n",
|
||||
" done: false\n",
|
||||
" experiment_id: 171527593b0f4cbf941c0a03faaf0953\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.2869105702896437\n",
|
||||
" landscape: -0.24722262157458608\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44758\n",
|
||||
" time_since_restore: 0.00021886825561523438\n",
|
||||
" time_this_iter_s: 0.00021886825561523438\n",
|
||||
" time_total_s: 0.00021886825561523438\n",
|
||||
" timestamp: 1658498670\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 32d8dd20\n",
|
||||
" warmup_time: 0.002732992172241211\n",
|
||||
" \n",
|
||||
"Result for objective_32cf8ca2:\n",
|
||||
" date: 2022-07-22_15-04-29\n",
|
||||
" done: false\n",
|
||||
" experiment_id: 37610500f6df493aae4e7e46bb21bf09\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.1817810425508524\n",
|
||||
" landscape: -0.14653248187442922\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44756\n",
|
||||
" time_since_restore: 0.00025081634521484375\n",
|
||||
" time_this_iter_s: 0.00025081634521484375\n",
|
||||
" time_total_s: 0.00025081634521484375\n",
|
||||
" timestamp: 1658498669\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 32cf8ca2\n",
|
||||
" warmup_time: 0.0032138824462890625\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[INFO 07-22 15:04:30] ax.service.ax_client: Completed trial 4 with data: {'landscape': (-0.00678, None), 'l2norm': (1.80573, None)}.\n",
|
||||
"[INFO 07-22 15:04:30] ax.service.ax_client: Generated new trial 8 with parameters {'x1': 0.454189, 'x2': 0.271772, 'x3': 0.530871, 'x4': 0.991841, 'x5': 0.691843, 'x6': 0.472366, 'iterations': 100}.\n",
|
||||
"[INFO 07-22 15:04:30] ax.service.ax_client: Completed trial 5 with data: {'landscape': (-0.904622, None), 'l2norm': (1.168644, None)}.\n",
|
||||
"[INFO 07-22 15:04:30] ax.service.ax_client: Generated new trial 9 with parameters {'x1': 0.265264, 'x2': 0.924884, 'x3': 0.151716, 'x4': 0.436026, 'x5': 0.85731, 'x6': 0.08981, 'iterations': 100}.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Result for objective_313d3d3a:\n",
|
||||
" date: 2022-07-22_15-04-30\n",
|
||||
" done: true\n",
|
||||
" experiment_id: fa7afd557e154fbebe4f54d8eedb3573\n",
|
||||
" experiment_tag: 5_iterations=100,x1=0.0419,x2=0.9928,x3=0.9060,x4=0.5944,x5=0.8254,x6=0.6464\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.805729990121368\n",
|
||||
" landscape: -0.006779757704679272\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44747\n",
|
||||
" time_since_restore: 3.1623308658599854\n",
|
||||
" time_this_iter_s: 0.02911996841430664\n",
|
||||
" time_total_s: 3.1623308658599854\n",
|
||||
" timestamp: 1658498670\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 313d3d3a\n",
|
||||
" warmup_time: 0.0029790401458740234\n",
|
||||
" \n",
|
||||
"Result for objective_32c9acd8:\n",
|
||||
" date: 2022-07-22_15-04-30\n",
|
||||
" done: true\n",
|
||||
" experiment_id: c555bfed13ac43e5b8c8e9f6d4b9b2f7\n",
|
||||
" experiment_tag: 6_iterations=100,x1=0.1261,x2=0.7034,x3=0.3447,x4=0.3374,x5=0.4014,x6=0.6792\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.1686440476629836\n",
|
||||
" landscape: -0.9046216637367911\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44726\n",
|
||||
" time_since_restore: 3.1211891174316406\n",
|
||||
" time_this_iter_s: 0.02954697608947754\n",
|
||||
" time_total_s: 3.1211891174316406\n",
|
||||
" timestamp: 1658498670\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 32c9acd8\n",
|
||||
" warmup_time: 0.0026290416717529297\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[INFO 07-22 15:04:32] ax.service.ax_client: Completed trial 7 with data: {'landscape': (-0.247223, None), 'l2norm': (1.286911, None)}.\n",
|
||||
"[INFO 07-22 15:04:32] ax.service.ax_client: Completed trial 6 with data: {'landscape': (-0.146532, None), 'l2norm': (1.181781, None)}.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Result for objective_32d8dd20:\n",
|
||||
" date: 2022-07-22_15-04-32\n",
|
||||
" done: true\n",
|
||||
" experiment_id: 171527593b0f4cbf941c0a03faaf0953\n",
|
||||
" experiment_tag: 8_iterations=100,x1=0.6032,x2=0.4091,x3=0.7291,x4=0.0826,x5=0.5729,x6=0.5083\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.2869105702896437\n",
|
||||
" landscape: -0.24722262157458608\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44758\n",
|
||||
" time_since_restore: 2.6415798664093018\n",
|
||||
" time_this_iter_s: 0.026781082153320312\n",
|
||||
" time_total_s: 2.6415798664093018\n",
|
||||
" timestamp: 1658498672\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 32d8dd20\n",
|
||||
" warmup_time: 0.002732992172241211\n",
|
||||
" \n",
|
||||
"Result for objective_32cf8ca2:\n",
|
||||
" date: 2022-07-22_15-04-32\n",
|
||||
" done: true\n",
|
||||
" experiment_id: 37610500f6df493aae4e7e46bb21bf09\n",
|
||||
" experiment_tag: 7_iterations=100,x1=0.0911,x2=0.3041,x3=0.8698,x4=0.4054,x5=0.5679,x6=0.2286\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.1817810425508524\n",
|
||||
" landscape: -0.14653248187442922\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44756\n",
|
||||
" time_since_restore: 2.707913875579834\n",
|
||||
" time_this_iter_s: 0.027456998825073242\n",
|
||||
" time_total_s: 2.707913875579834\n",
|
||||
" timestamp: 1658498672\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 32cf8ca2\n",
|
||||
" warmup_time: 0.0032138824462890625\n",
|
||||
" \n",
|
||||
"Result for objective_34adf04a:\n",
|
||||
" date: 2022-07-22_15-04-33\n",
|
||||
" done: false\n",
|
||||
" experiment_id: 4f65c5b68f5c49d98fda388e37c83deb\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.4991655675380078\n",
|
||||
" landscape: -0.01329150870283869\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44768\n",
|
||||
" time_since_restore: 0.00021600723266601562\n",
|
||||
" time_this_iter_s: 0.00021600723266601562\n",
|
||||
" time_total_s: 0.00021600723266601562\n",
|
||||
" timestamp: 1658498673\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 34adf04a\n",
|
||||
" warmup_time: 0.0027239322662353516\n",
|
||||
" \n",
|
||||
"Result for objective_34b7abda:\n",
|
||||
" date: 2022-07-22_15-04-33\n",
|
||||
" done: false\n",
|
||||
" experiment_id: f135a2c40f5644ba9d2ae096a9dd10e0\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 1\n",
|
||||
" l2norm: 1.3718451333547932\n",
|
||||
" landscape: -1.6624439263544026\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44771\n",
|
||||
" time_since_restore: 0.0002338886260986328\n",
|
||||
" time_this_iter_s: 0.0002338886260986328\n",
|
||||
" time_total_s: 0.0002338886260986328\n",
|
||||
" timestamp: 1658498673\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 0\n",
|
||||
" training_iteration: 1\n",
|
||||
" trial_id: 34b7abda\n",
|
||||
" warmup_time: 0.002721071243286133\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[INFO 07-22 15:04:35] ax.service.ax_client: Completed trial 8 with data: {'landscape': (-0.013292, None), 'l2norm': (1.499166, None)}.\n",
|
||||
"[INFO 07-22 15:04:35] ax.service.ax_client: Completed trial 9 with data: {'landscape': (-1.662444, None), 'l2norm': (1.371845, None)}.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Result for objective_34adf04a:\n",
|
||||
" date: 2022-07-22_15-04-35\n",
|
||||
" done: true\n",
|
||||
" experiment_id: 4f65c5b68f5c49d98fda388e37c83deb\n",
|
||||
" experiment_tag: 9_iterations=100,x1=0.4542,x2=0.2718,x3=0.5309,x4=0.9918,x5=0.6918,x6=0.4724\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.4991655675380078\n",
|
||||
" landscape: -0.01329150870283869\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44768\n",
|
||||
" time_since_restore: 2.7032668590545654\n",
|
||||
" time_this_iter_s: 0.029300928115844727\n",
|
||||
" time_total_s: 2.7032668590545654\n",
|
||||
" timestamp: 1658498675\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 34adf04a\n",
|
||||
" warmup_time: 0.0027239322662353516\n",
|
||||
" \n",
|
||||
"Result for objective_34b7abda:\n",
|
||||
" date: 2022-07-22_15-04-35\n",
|
||||
" done: true\n",
|
||||
" experiment_id: f135a2c40f5644ba9d2ae096a9dd10e0\n",
|
||||
" experiment_tag: 10_iterations=100,x1=0.2653,x2=0.9249,x3=0.1517,x4=0.4360,x5=0.8573,x6=0.0898\n",
|
||||
" hostname: Kais-MacBook-Pro.local\n",
|
||||
" iterations_since_restore: 100\n",
|
||||
" l2norm: 1.3718451333547932\n",
|
||||
" landscape: -1.6624439263544026\n",
|
||||
" node_ip: 127.0.0.1\n",
|
||||
" pid: 44771\n",
|
||||
" time_since_restore: 2.6852078437805176\n",
|
||||
" time_this_iter_s: 0.029579877853393555\n",
|
||||
" time_total_s: 2.6852078437805176\n",
|
||||
" timestamp: 1658498675\n",
|
||||
" timesteps_since_restore: 0\n",
|
||||
" timesteps_total: 99\n",
|
||||
" training_iteration: 100\n",
|
||||
" trial_id: 34b7abda\n",
|
||||
" warmup_time: 0.002721071243286133\n",
|
||||
" \n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tuner = tune.Tuner(\n",
|
||||
" objective,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"landscape\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" search_alg=algo,\n",
|
||||
" num_samples=num_samples,\n",
|
||||
" ),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" name=\"ax\",\n",
|
||||
" stop={\"timesteps_total\": stop_timesteps}\n",
|
||||
" ),\n",
|
||||
" param_space=search_space,\n",
|
||||
")\n",
|
||||
"results = tuner.fit()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "860b53b0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"And now we have the hyperparameters found to minimize the mean loss."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "12906421",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best hyperparameters found were: {'iterations': 100, 'x1': 0.26526361983269453, 'x2': 0.9248840995132923, 'x3': 0.15171580761671066, 'x4': 0.43602637108415365, 'x5': 0.8573104059323668, 'x6': 0.08981018699705601}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\"Best hyperparameters found were: \", results.get_best_result().config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "68872424",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ray.shutdown()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.13"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,689 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "58fc50bc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Running Tune experiments with HyperOpt\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-ray-tune-hyperopt_example\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=ray-tune-hyperopt_example\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"In this tutorial we introduce HyperOpt, while running a simple Ray Tune experiment. Tune’s Search Algorithms integrate with HyperOpt and, as a result, allow you to seamlessly scale up a Hyperopt optimization process - without sacrificing performance.\n",
|
||||
"\n",
|
||||
"HyperOpt provides gradient/derivative-free optimization able to handle noise over the objective landscape, including evolutionary, bandit, and Bayesian optimization algorithms. HyperOpt internally supports search spaces which are continuous, discrete or a mixture of thereof. It also provides a library of functions on which to test the optimization algorithms and compare with other benchmarks.\n",
|
||||
"\n",
|
||||
"In this example we minimize a simple objective to briefly demonstrate the usage of HyperOpt with Ray Tune via `HyperOptSearch`. It's useful to keep in mind that despite the emphasis on machine learning experiments, Ray Tune optimizes any implicit or explicit objective. Here we assume `hyperopt==0.2.5` library is installed. To learn more, please refer to [HyperOpt website](http://hyperopt.github.io/hyperopt).\n",
|
||||
"\n",
|
||||
"We include a important example on conditional search spaces (stringing together relationships among hyperparameters)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "e4586d28",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Background information:\n",
|
||||
"- [HyperOpt website](http://hyperopt.github.io/hyperopt)\n",
|
||||
"\n",
|
||||
"Necessary requirements:\n",
|
||||
"- `pip install \"ray[tune]\" hyperopt==0.2.5`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "6567f2dc",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Requirement already satisfied: hyperopt==0.2.5 in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (0.2.5)\n",
|
||||
"Requirement already satisfied: numpy in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (from hyperopt==0.2.5) (2.2.3)\n",
|
||||
"Requirement already satisfied: scipy in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (from hyperopt==0.2.5) (1.15.2)\n",
|
||||
"Requirement already satisfied: six in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (from hyperopt==0.2.5) (1.17.0)\n",
|
||||
"Requirement already satisfied: networkx>=2.2 in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (from hyperopt==0.2.5) (3.4.2)\n",
|
||||
"Requirement already satisfied: future in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (from hyperopt==0.2.5) (1.0.0)\n",
|
||||
"Requirement already satisfied: tqdm in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (from hyperopt==0.2.5) (4.67.1)\n",
|
||||
"Requirement already satisfied: cloudpickle in /opt/miniconda3/envs/hyperopt_example/lib/python3.11/site-packages (from hyperopt==0.2.5) (3.1.1)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# install in a hidden cell\n",
|
||||
"# !pip install \"ray[tune]\"\n",
|
||||
"!pip install hyperopt==0.2.5"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "b8e9e0cd",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Click below to see all the imports we need for this example."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "6592315e",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-input",
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import time\n",
|
||||
"\n",
|
||||
"import ray\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.search import ConcurrencyLimiter\n",
|
||||
"from ray.tune.search.hyperopt import HyperOptSearch\n",
|
||||
"from hyperopt import hp"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "d4b6d1d5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's start by defining a simple evaluation function.\n",
|
||||
"We artificially sleep for a bit (`0.1` seconds) to simulate a long-running ML experiment.\n",
|
||||
"This setup assumes that we're running multiple `step`s of an experiment and try to tune two hyperparameters,\n",
|
||||
"namely `width` and `height`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "12d4efc8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def evaluate(step, width, height):\n",
|
||||
" time.sleep(0.1)\n",
|
||||
" return (0.1 + width * step / 100) ** (-1) + height * 0.1"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "4f4f5aa2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next, our ``objective`` function takes a Tune ``config``, evaluates the `score` of your experiment in a training loop,\n",
|
||||
"and uses `tune.report` to report the `score` back to Tune."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "c9818009",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def objective(config):\n",
|
||||
" for step in range(config[\"steps\"]):\n",
|
||||
" score = evaluate(step, config[\"width\"], config[\"height\"])\n",
|
||||
" tune.report({\"iterations\": step, \"mean_loss\": score})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "33eddcb9",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "59f8090dd37c473cb24b97b6b28d109b",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/html": [
|
||||
"<div class=\"lm-Widget p-Widget lm-Panel p-Panel jp-Cell-outputWrapper\">\n",
|
||||
" <div style=\"margin-left: 50px;display: flex;flex-direction: row;align-items: center\">\n",
|
||||
" <div class=\"jp-RenderedHTMLCommon\" style=\"display: flex; flex-direction: row;\">\n",
|
||||
" <svg viewBox=\"0 0 567 224\" fill=\"none\" xmlns=\"http://www.w3.org/2000/svg\" style=\"height: 3em;\">\n",
|
||||
" <g clip-path=\"url(#clip0_4338_178347)\">\n",
|
||||
" <path d=\"M341.29 165.561H355.29L330.13 129.051C345.63 123.991 354.21 112.051 354.21 94.2307C354.21 71.3707 338.72 58.1807 311.88 58.1807H271V165.561H283.27V131.661H311.8C314.25 131.661 316.71 131.501 319.01 131.351L341.25 165.561H341.29ZM283.29 119.851V70.0007H311.82C331.3 70.0007 342.34 78.2907 342.34 94.5507C342.34 111.271 331.34 119.861 311.82 119.861L283.29 119.851ZM451.4 138.411L463.4 165.561H476.74L428.74 58.1807H416L367.83 165.561H380.83L392.83 138.411H451.4ZM446.19 126.601H398L422 72.1407L446.24 126.601H446.19ZM526.11 128.741L566.91 58.1807H554.35L519.99 114.181L485.17 58.1807H472.44L514.01 129.181V165.541H526.13V128.741H526.11Z\" fill=\"var(--jp-ui-font-color0)\"/>\n",
|
||||
" <path d=\"M82.35 104.44C84.0187 97.8827 87.8248 92.0678 93.1671 87.9146C98.5094 83.7614 105.083 81.5067 111.85 81.5067C118.617 81.5067 125.191 83.7614 130.533 87.9146C135.875 92.0678 139.681 97.8827 141.35 104.44H163.75C164.476 101.562 165.622 98.8057 167.15 96.2605L127.45 56.5605C121.071 60.3522 113.526 61.6823 106.235 60.3005C98.9443 58.9187 92.4094 54.9203 87.8602 49.0574C83.3109 43.1946 81.0609 35.8714 81.5332 28.4656C82.0056 21.0599 85.1679 14.0819 90.4252 8.8446C95.6824 3.60726 102.672 0.471508 110.08 0.0272655C117.487 -0.416977 124.802 1.86091 130.647 6.4324C136.493 11.0039 140.467 17.5539 141.821 24.8501C143.175 32.1463 141.816 39.6859 138 46.0505L177.69 85.7505C182.31 82.9877 187.58 81.4995 192.962 81.4375C198.345 81.3755 203.648 82.742 208.33 85.3976C213.012 88.0532 216.907 91.9029 219.616 96.5544C222.326 101.206 223.753 106.492 223.753 111.875C223.753 117.258 222.326 122.545 219.616 127.197C216.907 131.848 213.012 135.698 208.33 138.353C203.648 141.009 198.345 142.375 192.962 142.313C187.58 142.251 182.31 140.763 177.69 138L138 177.7C141.808 184.071 143.155 191.614 141.79 198.91C140.424 206.205 136.44 212.75 130.585 217.313C124.731 221.875 117.412 224.141 110.004 223.683C102.596 223.226 95.6103 220.077 90.3621 214.828C85.1139 209.58 81.9647 202.595 81.5072 195.187C81.0497 187.779 83.3154 180.459 87.878 174.605C92.4405 168.751 98.9853 164.766 106.281 163.401C113.576 162.035 121.119 163.383 127.49 167.19L167.19 127.49C165.664 124.941 164.518 122.182 163.79 119.3H141.39C139.721 125.858 135.915 131.673 130.573 135.826C125.231 139.98 118.657 142.234 111.89 142.234C105.123 142.234 98.5494 139.98 93.2071 135.826C87.8648 131.673 84.0587 125.858 82.39 119.3H60C58.1878 126.495 53.8086 132.78 47.6863 136.971C41.5641 141.163 34.1211 142.972 26.7579 142.059C19.3947 141.146 12.6191 137.574 7.70605 132.014C2.79302 126.454 0.0813599 119.29 0.0813599 111.87C0.0813599 104.451 2.79302 97.2871 7.70605 91.7272C12.6191 86.1673 19.3947 82.5947 26.7579 81.6817C34.1211 80.7686 41.5641 82.5781 47.6863 86.7696C53.8086 90.9611 58.1878 97.2456 60 104.44H82.35ZM100.86 204.32C103.407 206.868 106.759 208.453 110.345 208.806C113.93 209.159 117.527 208.258 120.522 206.256C123.517 204.254 125.725 201.276 126.771 197.828C127.816 194.38 127.633 190.677 126.253 187.349C124.874 184.021 122.383 181.274 119.205 179.577C116.027 177.88 112.359 177.337 108.826 178.042C105.293 178.746 102.113 180.654 99.8291 183.44C97.5451 186.226 96.2979 189.718 96.3 193.32C96.2985 195.364 96.7006 197.388 97.4831 199.275C98.2656 201.163 99.4132 202.877 100.86 204.32ZM204.32 122.88C206.868 120.333 208.453 116.981 208.806 113.396C209.159 109.811 208.258 106.214 206.256 103.219C204.254 100.223 201.275 98.0151 197.827 96.97C194.38 95.9249 190.676 96.1077 187.348 97.4873C184.02 98.8669 181.274 101.358 179.577 104.536C177.879 107.714 177.337 111.382 178.041 114.915C178.746 118.448 180.653 121.627 183.439 123.911C186.226 126.195 189.717 127.443 193.32 127.44C195.364 127.443 197.388 127.042 199.275 126.259C201.163 125.476 202.878 124.328 204.32 122.88ZM122.88 19.4205C120.333 16.8729 116.981 15.2876 113.395 14.9347C109.81 14.5817 106.213 15.483 103.218 17.4849C100.223 19.4868 98.0146 22.4654 96.9696 25.9131C95.9245 29.3608 96.1073 33.0642 97.4869 36.3922C98.8665 39.7202 101.358 42.4668 104.535 44.1639C107.713 45.861 111.381 46.4036 114.914 45.6992C118.447 44.9949 121.627 43.0871 123.911 40.301C126.195 37.515 127.442 34.0231 127.44 30.4205C127.44 28.3772 127.038 26.3539 126.255 24.4664C125.473 22.5788 124.326 20.8642 122.88 19.4205ZM19.42 100.86C16.8725 103.408 15.2872 106.76 14.9342 110.345C14.5813 113.93 15.4826 117.527 17.4844 120.522C19.4863 123.518 22.4649 125.726 25.9127 126.771C29.3604 127.816 33.0638 127.633 36.3918 126.254C39.7198 124.874 42.4664 122.383 44.1635 119.205C45.8606 116.027 46.4032 112.359 45.6988 108.826C44.9944 105.293 43.0866 102.114 40.3006 99.8296C37.5145 97.5455 34.0227 96.2983 30.42 96.3005C26.2938 96.3018 22.337 97.9421 19.42 100.86ZM100.86 100.86C98.3125 103.408 96.7272 106.76 96.3742 110.345C96.0213 113.93 96.9226 117.527 98.9244 120.522C100.926 123.518 103.905 125.726 107.353 126.771C110.8 127.816 114.504 127.633 117.832 126.254C121.16 124.874 123.906 122.383 125.604 119.205C127.301 116.027 127.843 112.359 127.139 108.826C126.434 105.293 124.527 102.114 121.741 99.8296C118.955 97.5455 115.463 96.2983 111.86 96.3005C109.817 96.299 107.793 96.701 105.905 97.4835C104.018 98.2661 102.303 99.4136 100.86 100.86Z\" fill=\"#00AEEF\"/>\n",
|
||||
" </g>\n",
|
||||
" <defs>\n",
|
||||
" <clipPath id=\"clip0_4338_178347\">\n",
|
||||
" <rect width=\"566.93\" height=\"223.75\" fill=\"white\"/>\n",
|
||||
" </clipPath>\n",
|
||||
" </defs>\n",
|
||||
" </svg>\n",
|
||||
"</div>\n",
|
||||
"\n",
|
||||
" <table class=\"jp-RenderedHTMLCommon\" style=\"border-collapse: collapse;color: var(--jp-ui-font-color1);font-size: var(--jp-ui-font-size1);\">\n",
|
||||
" <tr>\n",
|
||||
" <td style=\"text-align: left\"><b>Python version:</b></td>\n",
|
||||
" <td style=\"text-align: left\"><b>3.11.11</b></td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <td style=\"text-align: left\"><b>Ray version:</b></td>\n",
|
||||
" <td style=\"text-align: left\"><b>2.42.1</b></td>\n",
|
||||
" </tr>\n",
|
||||
" \n",
|
||||
"</table>\n",
|
||||
"\n",
|
||||
" </div>\n",
|
||||
"</div>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"RayContext(dashboard_url='', python_version='3.11.11', ray_version='2.42.1', ray_commit='c2e38f7b75be223c0c033986472daada8622d64f')"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ray.init(configure_logging=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "5be35d5e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"While defining the search algorithm, we may choose to provide an initial set of hyperparameters that we believe are especially promising or informative, and\n",
|
||||
"pass this information as a helpful starting point for the `HyperOptSearch` object.\n",
|
||||
"\n",
|
||||
"We also set the maximum concurrent trials to `4` with a `ConcurrencyLimiter`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "d4615bed",
|
||||
"metadata": {
|
||||
"lines_to_next_cell": 0
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"initial_params = [\n",
|
||||
" {\"width\": 1, \"height\": 2, \"activation\": \"relu\"},\n",
|
||||
" {\"width\": 4, \"height\": 2, \"activation\": \"tanh\"},\n",
|
||||
"]\n",
|
||||
"algo = HyperOptSearch(points_to_evaluate=initial_params)\n",
|
||||
"algo = ConcurrencyLimiter(algo, max_concurrent=4)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "2a51e7c1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The number of samples is the number of hyperparameter combinations that will be tried out. This Tune run is set to `1000` samples.\n",
|
||||
"(you can decrease this if it takes too long on your machine)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "2dbb2be0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"num_samples = 1000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "950558ed",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# If 1000 samples take too long, you can reduce this number.\n",
|
||||
"# We override this number here for our smoke tests.\n",
|
||||
"num_samples = 10"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "6e3629cb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next we define a search space. The critical assumption is that the optimal hyperparameters live within this space. Yet, if the space is very large, then those hyperparameters may be difficult to find in a short amount of time."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "65189946",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search_config = {\n",
|
||||
" \"steps\": 100,\n",
|
||||
" \"width\": tune.uniform(0, 20),\n",
|
||||
" \"height\": tune.uniform(-100, 100),\n",
|
||||
" \"activation\": tune.choice([\"relu\", \"tanh\"])\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "1b94c93b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Finally, we run the experiment to `\"min\"`imize the \"mean_loss\" of the `objective` by searching `search_config` via `algo`, `num_samples` times. This previous sentence is fully characterizes the search problem we aim to solve. With this in mind, notice how efficient it is to execute `tuner.fit()`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "9a99a3a7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2025-02-18 13:14:59</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:36.03 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>22.1/36.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Logical resource usage: 1.0/12 CPUs, 0/0 GPUs\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th>activation </th><th style=\"text-align: right;\"> height</th><th style=\"text-align: right;\"> steps</th><th style=\"text-align: right;\"> width</th><th style=\"text-align: right;\"> loss</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> iterations</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>objective_5b05c00a</td><td>TERMINATED</td><td>127.0.0.1:50205</td><td>relu </td><td style=\"text-align: right;\"> 2 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 1 </td><td style=\"text-align: right;\"> 1.11743 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.335 </td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_b813f49d</td><td>TERMINATED</td><td>127.0.0.1:50207</td><td>tanh </td><td style=\"text-align: right;\"> 2 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 4 </td><td style=\"text-align: right;\"> 0.446305</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3299</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_6dadd2bd</td><td>TERMINATED</td><td>127.0.0.1:50212</td><td>tanh </td><td style=\"text-align: right;\">-40.9318</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 6.20615 </td><td style=\"text-align: right;\">-3.93303 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3213</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_9faffc0f</td><td>TERMINATED</td><td>127.0.0.1:50217</td><td>tanh </td><td style=\"text-align: right;\"> 91.9688</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 9.25147 </td><td style=\"text-align: right;\"> 9.30488 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.353 </td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_7834e74c</td><td>TERMINATED</td><td>127.0.0.1:50266</td><td>tanh </td><td style=\"text-align: right;\">-17.9521</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">11.436 </td><td style=\"text-align: right;\">-1.70766 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3753</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_741253c7</td><td>TERMINATED</td><td>127.0.0.1:50271</td><td>tanh </td><td style=\"text-align: right;\"> 58.1279</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 0.737879</td><td style=\"text-align: right;\"> 7.01689 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3565</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_39682bcf</td><td>TERMINATED</td><td>127.0.0.1:50272</td><td>tanh </td><td style=\"text-align: right;\">-31.2589</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 4.89265 </td><td style=\"text-align: right;\">-2.92361 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3225</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_bfc7e150</td><td>TERMINATED</td><td>127.0.0.1:50274</td><td>tanh </td><td style=\"text-align: right;\">-14.7877</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 7.36477 </td><td style=\"text-align: right;\">-1.34347 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3744</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_e1f1a193</td><td>TERMINATED</td><td>127.0.0.1:50314</td><td>tanh </td><td style=\"text-align: right;\"> 50.9579</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">17.4499 </td><td style=\"text-align: right;\"> 5.15334 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3675</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_1192dd4e</td><td>TERMINATED</td><td>127.0.0.1:50316</td><td>tanh </td><td style=\"text-align: right;\"> 66.5306</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">16.9549 </td><td style=\"text-align: right;\"> 6.71228 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.3478</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tuner = tune.Tuner(\n",
|
||||
" objective,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"mean_loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" search_alg=algo,\n",
|
||||
" num_samples=num_samples,\n",
|
||||
" ),\n",
|
||||
" param_space=search_config,\n",
|
||||
")\n",
|
||||
"results = tuner.fit()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "49be6f01",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Here are the hyperparameters found to minimize the mean loss of the defined objective."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "7036798c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best hyperparameters found were: {'steps': 100, 'width': 6.206149011253133, 'height': -40.93182668460948, 'activation': 'tanh'}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\"Best hyperparameters found were: \", results.get_best_result().config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "504e9d2a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Conditional search spaces\n",
|
||||
"\n",
|
||||
"Sometimes we may want to build a more complicated search space that has conditional dependencies on other hyperparameters. In this case, we pass a nested dictionary to `objective_two`, which has been slightly adjusted from `objective` to deal with the conditional search space."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "2f7b5449",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def evaluation_fn(step, width, height, mult=1):\n",
|
||||
" return (0.1 + width * step / 100) ** (-1) + height * 0.1 * mult"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "4b83b81c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def objective_two(config):\n",
|
||||
" width, height = config[\"width\"], config[\"height\"]\n",
|
||||
" sub_dict = config[\"activation\"]\n",
|
||||
" mult = sub_dict.get(\"mult\", 1)\n",
|
||||
" \n",
|
||||
" for step in range(config[\"steps\"]):\n",
|
||||
" intermediate_score = evaluation_fn(step, width, height, mult)\n",
|
||||
" tune.report({\"iterations\": step, \"mean_loss\": intermediate_score})\n",
|
||||
" time.sleep(0.1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "75cea99e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"conditional_space = {\n",
|
||||
" \"activation\": hp.choice(\n",
|
||||
" \"activation\",\n",
|
||||
" [\n",
|
||||
" {\"activation\": \"relu\", \"mult\": hp.uniform(\"mult\", 1, 2)},\n",
|
||||
" {\"activation\": \"tanh\"},\n",
|
||||
" ],\n",
|
||||
" ),\n",
|
||||
" \"width\": hp.uniform(\"width\", 0, 20),\n",
|
||||
" \"height\": hp.uniform(\"height\", -100, 100),\n",
|
||||
" \"steps\": 100,\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "7df282c1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we the define the search algorithm built from `HyperOptSearch` constrained by `ConcurrencyLimiter`. When the hyperparameter search space is conditional, we pass it (`conditional_space`) into `HyperOptSearch`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "ea2c71a6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"algo = HyperOptSearch(space=conditional_space, metric=\"mean_loss\", mode=\"min\")\n",
|
||||
"algo = ConcurrencyLimiter(algo, max_concurrent=4)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "630f84ab",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we run the experiment, this time with an empty `config` because we instead provided `space` to the `HyperOptSearch` `search_alg`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "14111e9e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2025-02-18 13:15:34</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:34.71 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>22.9/36.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Logical resource usage: 1.0/12 CPUs, 0/0 GPUs\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th>activation/activatio\n",
|
||||
"n </th><th style=\"text-align: right;\"> activation/mult</th><th style=\"text-align: right;\"> height</th><th style=\"text-align: right;\"> steps</th><th style=\"text-align: right;\"> width</th><th style=\"text-align: right;\"> loss</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> iterations</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>objective_two_13de5867</td><td>TERMINATED</td><td>127.0.0.1:50350</td><td>tanh</td><td style=\"text-align: right;\"> </td><td style=\"text-align: right;\">-35.0329 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">13.2254 </td><td style=\"text-align: right;\"> -3.42749 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2102</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_3100f5ee</td><td>TERMINATED</td><td>127.0.0.1:50355</td><td>relu</td><td style=\"text-align: right;\"> 1.44584</td><td style=\"text-align: right;\"> 76.2581 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 0.123165</td><td style=\"text-align: right;\"> 15.5316 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2683</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_6b4044aa</td><td>TERMINATED</td><td>127.0.0.1:50356</td><td>relu</td><td style=\"text-align: right;\"> 1.67475</td><td style=\"text-align: right;\"> 57.9612 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">19.4794 </td><td style=\"text-align: right;\"> 9.75866 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2724</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_4aa1269b</td><td>TERMINATED</td><td>127.0.0.1:50357</td><td>tanh</td><td style=\"text-align: right;\"> </td><td style=\"text-align: right;\"> -9.95686</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">12.9749 </td><td style=\"text-align: right;\"> -0.918437</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2373</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_d8c42c9f</td><td>TERMINATED</td><td>127.0.0.1:50402</td><td>tanh</td><td style=\"text-align: right;\"> </td><td style=\"text-align: right;\">-96.6184 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 8.03869 </td><td style=\"text-align: right;\"> -9.53774 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2407</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_de956d10</td><td>TERMINATED</td><td>127.0.0.1:50404</td><td>relu</td><td style=\"text-align: right;\"> 1.06986</td><td style=\"text-align: right;\"> 9.64996</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 0.672962</td><td style=\"text-align: right;\"> 2.3375 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2427</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_0e2b2751</td><td>TERMINATED</td><td>127.0.0.1:50413</td><td>tanh</td><td style=\"text-align: right;\"> </td><td style=\"text-align: right;\">-82.9292 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">17.4889 </td><td style=\"text-align: right;\"> -8.2355 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.293 </td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_dad93a03</td><td>TERMINATED</td><td>127.0.0.1:50415</td><td>relu</td><td style=\"text-align: right;\"> 1.85364</td><td style=\"text-align: right;\">-63.6309 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\">16.6414 </td><td style=\"text-align: right;\">-11.7345 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.285 </td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_e472727a</td><td>TERMINATED</td><td>127.0.0.1:50442</td><td>relu</td><td style=\"text-align: right;\"> 1.2359 </td><td style=\"text-align: right;\">-75.2253 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 7.49782 </td><td style=\"text-align: right;\"> -9.16415 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2506</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"<tr><td>objective_two_5d1eacff</td><td>TERMINATED</td><td>127.0.0.1:50449</td><td>tanh</td><td style=\"text-align: right;\"> </td><td style=\"text-align: right;\">-20.158 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 6.18643 </td><td style=\"text-align: right;\"> -1.85514 </td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 10.2566</td><td style=\"text-align: right;\"> 99</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tuner = tune.Tuner(\n",
|
||||
" objective_two,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"mean_loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" search_alg=algo,\n",
|
||||
" num_samples=num_samples,\n",
|
||||
" ),\n",
|
||||
")\n",
|
||||
"results = tuner.fit()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "e6172afa",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Finally, we again show the hyperparameters that minimize the mean loss defined by the score of the objective function above. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "03c3fc49",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best hyperparameters found were: {'activation': {'activation': 'relu', 'mult': 1.8536380640438768}, 'height': -63.630920754630125, 'steps': 100, 'width': 16.641403933591928}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\"Best hyperparameters found were: \", results.get_best_result().config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"id": "2f7b72d3",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ray.shutdown()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "hyperopt_example",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.11"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
:orphan:
|
||||
|
||||
Asynchronous HyperBand Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
This example demonstrates how to use Ray Tune's Asynchronous Successive Halving Algorithm (ASHA) scheduler
|
||||
to efficiently optimize hyperparameters for a machine learning model. ASHA is particularly useful for
|
||||
large-scale hyperparameter optimization as it can adaptively allocate resources and end
|
||||
poorly performing trials early.
|
||||
|
||||
Requirements: `pip install "ray[tune]"`
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/async_hyperband_example.py
|
||||
|
||||
|
||||
See Also
|
||||
--------
|
||||
|
||||
- `ASHA Paper <https://arxiv.org/abs/1810.05934>`_
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
AX Example
|
||||
~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/ax_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
BayesOpt Example
|
||||
~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/bayesopt_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
BOHB Example
|
||||
~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/bohb_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
Custom Checkpointing Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/custom_func_checkpointing.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
HyperBand Example
|
||||
=================
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/hyperband_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
HyperBand Function Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/hyperband_function_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
Hyperopt Conditional Search Space Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/hyperopt_conditional_search_space_example.py
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 97 KiB |
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
Logging Example
|
||||
~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/logging_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
MLflow PyTorch Lightning Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/mlflow_ptl.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
MNIST PyTorch Lightning Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/mnist_ptl_mini.py
|
||||
@@ -0,0 +1,10 @@
|
||||
:orphan:
|
||||
|
||||
MNIST PyTorch Example
|
||||
~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/mnist_pytorch.py
|
||||
|
||||
If you consider switching to PyTorch Lightning to get rid of some of your boilerplate
|
||||
training code, please know that we also have a walkthrough on :doc:`how to use Tune with
|
||||
PyTorch Lightning models </tune/examples/tune-pytorch-lightning>`.
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
MNIST PyTorch Trainable Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/mnist_pytorch_trainable.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
Nevergrad Example
|
||||
~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/nevergrad_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
PB2 Example
|
||||
~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/pb2_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
PB2 PPO Example
|
||||
~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/pb2_ppo_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
PBT ConvNet Example
|
||||
~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/pbt_convnet_function_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
PBT Example
|
||||
~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/pbt_example.py
|
||||
@@ -0,0 +1,11 @@
|
||||
:orphan:
|
||||
|
||||
PBT Function Example
|
||||
~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
The following script produces the following results. For a population of 8 trials,
|
||||
the PBT learning rate schedule roughly matches the optimal learning rate schedule.
|
||||
|
||||
.. image:: images/pbt_function_results.png
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/pbt_function.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
Memory NN Example
|
||||
~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/pbt_memnn_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
Keras Cifar10 Example
|
||||
~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/pbt_tune_cifar10_with_keras.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
TensorFlow MNIST Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/tf_mnist_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
tune_basic_example
|
||||
~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/tune_basic_example.py
|
||||
@@ -0,0 +1,6 @@
|
||||
:orphan:
|
||||
|
||||
XGBoost Dynamic Resources Example
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. literalinclude:: /../../python/ray/tune/examples/xgboost_dynamic_resources_example.py
|
||||
@@ -0,0 +1,158 @@
|
||||
.. _tune-examples-ref:
|
||||
.. _tune-recipes:
|
||||
|
||||
=================
|
||||
Ray Tune Examples
|
||||
=================
|
||||
|
||||
.. tip::
|
||||
See :ref:`tune-main` to learn more about Tune features.
|
||||
|
||||
|
||||
Below are examples for using Ray Tune for a variety of use cases and sorted by categories:
|
||||
|
||||
* `ML frameworks`_
|
||||
* `Experiment tracking tools`_
|
||||
* `Hyperparameter optimization frameworks`_
|
||||
* `Others`_
|
||||
* `Exercises`_
|
||||
|
||||
.. _ml-frameworks:
|
||||
|
||||
ML frameworks
|
||||
-------------
|
||||
|
||||
.. toctree::
|
||||
:hidden:
|
||||
|
||||
PyTorch Example <tune-pytorch-cifar>
|
||||
PyTorch Lightning Example <tune-pytorch-lightning>
|
||||
XGBoost Example <tune-xgboost>
|
||||
LightGBM Example <lightgbm_example>
|
||||
Hugging Face Transformers Example <pbt_transformers>
|
||||
Ray RLlib Example <pbt_ppo_example>
|
||||
Keras Example <tune_mnist_keras>
|
||||
PyTorch with ASHA </_collections/tune/examples/tune_pytorch_asha/README>
|
||||
|
||||
Ray Tune integrates with many popular machine learning frameworks. Here you find a few practical examples showing you how to tune your models. At the end of these guides you will often find links to even more examples.
|
||||
|
||||
.. list-table::
|
||||
|
||||
* - :doc:`How to use Tune with Keras and TensorFlow models <tune_mnist_keras>`
|
||||
* - :doc:`How to use Tune with PyTorch models <tune-pytorch-cifar>`
|
||||
* - :doc:`How to tune PyTorch Lightning models <tune-pytorch-lightning>`
|
||||
* - :doc:`Tuning RL experiments with Ray Tune and Ray Serve <pbt_ppo_example>`
|
||||
* - :doc:`Tuning XGBoost parameters with Tune <tune-xgboost>`
|
||||
* - :doc:`Tuning LightGBM parameters with Tune <lightgbm_example>`
|
||||
* - :doc:`Tuning Hugging Face Transformers with Tune <pbt_transformers>`
|
||||
* - :doc:`Hyperparameter tuning with PyTorch and ASHA </_collections/tune/examples/tune_pytorch_asha/README>`
|
||||
|
||||
.. _experiment-tracking-tools:
|
||||
|
||||
Experiment tracking tools
|
||||
-------------------------
|
||||
|
||||
.. toctree::
|
||||
:hidden:
|
||||
|
||||
Weights & Biases Example <tune-wandb>
|
||||
MLflow Example <tune-mlflow>
|
||||
Aim Example <tune-aim>
|
||||
Comet Example <tune-comet>
|
||||
|
||||
Ray Tune integrates with some popular Experiment tracking and management tools,
|
||||
such as CometML, or Weights & Biases. For how
|
||||
to use Ray Tune with Tensorboard, see
|
||||
:ref:`Guide to logging and outputs <tune-logging>`.
|
||||
|
||||
.. list-table::
|
||||
|
||||
* - :doc:`Using Aim with Ray Tune for experiment management <tune-aim>`
|
||||
* - :doc:`Using Comet with Ray Tune for experiment management <tune-comet>`
|
||||
* - :doc:`Tracking your experiment process Weights & Biases <tune-wandb>`
|
||||
* - :doc:`Using MLflow tracking and auto logging with Tune <tune-mlflow>`
|
||||
|
||||
.. _hyperparameter-optimization-frameworks:
|
||||
|
||||
Hyperparameter optimization frameworks
|
||||
--------------------------------------
|
||||
|
||||
.. toctree::
|
||||
:hidden:
|
||||
|
||||
Ax Example <ax_example>
|
||||
HyperOpt Example <hyperopt_example>
|
||||
Bayesopt Example <bayesopt_example>
|
||||
BOHB Example <bohb_example>
|
||||
Nevergrad Example <nevergrad_example>
|
||||
Optuna Example <optuna_example>
|
||||
|
||||
Tune integrates with a wide variety of hyperparameter optimization frameworks
|
||||
and their respective search algorithms. See the following detailed examples
|
||||
for each integration:
|
||||
|
||||
.. list-table::
|
||||
|
||||
* - :doc:`ax_example`
|
||||
* - :doc:`hyperopt_example`
|
||||
* - :doc:`bayesopt_example`
|
||||
* - :doc:`bohb_example`
|
||||
* - :doc:`nevergrad_example`
|
||||
* - :doc:`optuna_example`
|
||||
|
||||
.. _tune-examples-others:
|
||||
|
||||
Others
|
||||
------
|
||||
|
||||
.. list-table::
|
||||
|
||||
* - :doc:`Simple example for doing a basic random and grid search <includes/tune_basic_example>`
|
||||
* - :doc:`Example of using a simple tuning function with AsyncHyperBandScheduler <includes/async_hyperband_example>`
|
||||
* - :doc:`Example of using a trainable function with HyperBandScheduler and the AsyncHyperBandScheduler <includes/hyperband_function_example>`
|
||||
* - :doc:`Configuring and running (synchronous) PBT and understanding the underlying algorithm behavior with a simple example <pbt_visualization/pbt_visualization>`
|
||||
* - :doc:`includes/pbt_function`
|
||||
* - :doc:`includes/pb2_example`
|
||||
* - :doc:`includes/logging_example`
|
||||
|
||||
.. _tune-examples-exercises:
|
||||
|
||||
Exercises
|
||||
---------
|
||||
|
||||
Learn how to use Tune in your browser with the following Colab-based exercises.
|
||||
|
||||
.. list-table::
|
||||
:widths: 50 30 20
|
||||
:header-rows: 1
|
||||
|
||||
* - Description
|
||||
- Library
|
||||
- Colab link
|
||||
* - Basics of using Tune
|
||||
- PyTorch
|
||||
- .. image:: https://colab.research.google.com/assets/colab-badge.svg
|
||||
:target: https://colab.research.google.com/github/ray-project/tutorial/blob/master/tune_exercises/exercise_1_basics.ipynb
|
||||
:alt: Open in Colab
|
||||
* - Using search algorithms and trial schedulers to optimize your model
|
||||
- PyTorch
|
||||
- .. image:: https://colab.research.google.com/assets/colab-badge.svg
|
||||
:target: https://colab.research.google.com/github/ray-project/tutorial/blob/master/tune_exercises/exercise_2_optimize.ipynb
|
||||
:alt: Open in Colab
|
||||
* - Using Population-Based Training (PBT)
|
||||
- PyTorch
|
||||
- .. image:: https://colab.research.google.com/assets/colab-badge.svg
|
||||
:target: https://colab.research.google.com/github/ray-project/tutorial/blob/master/tune_exercises/exercise_3_pbt.ipynb" target="_parent
|
||||
:alt: Open in Colab
|
||||
* - Fine-tuning Hugging Face Transformers with PBT
|
||||
- Hugging Face Transformers and PyTorch
|
||||
- .. image:: https://colab.research.google.com/assets/colab-badge.svg
|
||||
:target: https://colab.research.google.com/drive/1tQgAKgcKQzheoh503OzhS4N9NtfFgmjF?usp=sharing
|
||||
:alt: Open in Colab
|
||||
* - Logging Tune runs to Comet ML
|
||||
- Comet
|
||||
- .. image:: https://colab.research.google.com/assets/colab-badge.svg
|
||||
:target: https://colab.research.google.com/drive/1dp3VwVoAH1acn_kG7RuT62mICnOqxU1z?usp=sharing
|
||||
:alt: Open in Colab
|
||||
|
||||
Tutorial source files are on `GitHub <https://github.com/ray-project/tutorial>`_.
|
||||
@@ -0,0 +1,259 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "12ada6c3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"(tune-lightgbm-example)=\n",
|
||||
"\n",
|
||||
"# Using LightGBM with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-ray-tune-lightgbm_example\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=ray-tune-lightgbm_example\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"```{image} /images/lightgbm_logo.png\n",
|
||||
":align: center\n",
|
||||
":alt: LightGBM Logo\n",
|
||||
":height: 120px\n",
|
||||
":target: https://lightgbm.readthedocs.io\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"This tutorial shows how to use Ray Tune to optimize hyperparameters for a LightGBM model. We'll use the breast cancer classification dataset from scikit-learn to demonstrate how to:\n",
|
||||
"\n",
|
||||
"1. Set up a LightGBM training function with Ray Tune\n",
|
||||
"2. Configure hyperparameter search spaces\n",
|
||||
"3. Use the ASHA scheduler for efficient hyperparameter tuning\n",
|
||||
"4. Report and checkpoint training progress\n",
|
||||
"\n",
|
||||
"## Installation\n",
|
||||
"\n",
|
||||
"First, let's install the required dependencies:\n",
|
||||
"\n",
|
||||
"```bash\n",
|
||||
"pip install \"ray[tune]\" lightgbm scikit-learn numpy\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## Training script\n",
|
||||
"\n",
|
||||
"The script below defines a `train_breast_cancer` training function, configures the search space, and runs the tuner with the {class}`~ray.tune.schedulers.ASHAScheduler`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "b4c3f1e1",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
},
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2025-02-18 17:33:55</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:01.27 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>25.8/36.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using AsyncHyperBand: num_stopped=4<br>Bracket: Iter 64.000: -0.1048951048951049 | Iter 16.000: -0.3076923076923077 | Iter 4.000: -0.3076923076923077 | Iter 1.000: -0.32342657342657344<br>Logical resource usage: 1.0/12 CPUs, 0/0 GPUs\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th>boosting_type </th><th style=\"text-align: right;\"> learning_rate</th><th style=\"text-align: right;\"> num_leaves</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> binary_error</th><th style=\"text-align: right;\"> binary_logloss</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_breast_cancer_945ea_00000</td><td>TERMINATED</td><td>127.0.0.1:26189</td><td>gbdt </td><td style=\"text-align: right;\"> 0.00372129 </td><td style=\"text-align: right;\"> 622</td><td style=\"text-align: right;\"> 100</td><td style=\"text-align: right;\"> 0.0507247 </td><td style=\"text-align: right;\"> 0.104895</td><td style=\"text-align: right;\"> 0.45487 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_945ea_00001</td><td>TERMINATED</td><td>127.0.0.1:26191</td><td>dart </td><td style=\"text-align: right;\"> 0.0065691 </td><td style=\"text-align: right;\"> 998</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.013751 </td><td style=\"text-align: right;\"> 0.391608</td><td style=\"text-align: right;\"> 0.665636</td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_945ea_00002</td><td>TERMINATED</td><td>127.0.0.1:26190</td><td>gbdt </td><td style=\"text-align: right;\"> 1.17012e-07</td><td style=\"text-align: right;\"> 995</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.0146749 </td><td style=\"text-align: right;\"> 0.412587</td><td style=\"text-align: right;\"> 0.68387 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_945ea_00003</td><td>TERMINATED</td><td>127.0.0.1:26192</td><td>dart </td><td style=\"text-align: right;\"> 0.000194983</td><td style=\"text-align: right;\"> 53</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.00605583</td><td style=\"text-align: right;\"> 0.328671</td><td style=\"text-align: right;\"> 0.6405 </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2025-02-18 17:33:55,300\tINFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '~/ray_results/train_breast_cancer_2025-02-18_17-33-54' in 0.0035s.\n",
|
||||
"2025-02-18 17:33:55,302\tINFO tune.py:1041 -- Total run time: 1.28 seconds (1.27 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best hyperparameters found were: {'objective': 'binary', 'metric': ['binary_error', 'binary_logloss'], 'verbose': -1, 'boosting_type': 'gbdt', 'num_leaves': 622, 'learning_rate': 0.003721286118355498}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import lightgbm as lgb\n",
|
||||
"import numpy as np\n",
|
||||
"import sklearn.datasets\n",
|
||||
"import sklearn.metrics\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.schedulers import ASHAScheduler\n",
|
||||
"from ray.tune.integration.lightgbm import TuneReportCheckpointCallback\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_breast_cancer(config):\n",
|
||||
"\n",
|
||||
" data, target = sklearn.datasets.load_breast_cancer(return_X_y=True)\n",
|
||||
" train_x, test_x, train_y, test_y = train_test_split(data, target, test_size=0.25)\n",
|
||||
" train_set = lgb.Dataset(train_x, label=train_y)\n",
|
||||
" test_set = lgb.Dataset(test_x, label=test_y)\n",
|
||||
" gbm = lgb.train(\n",
|
||||
" config,\n",
|
||||
" train_set,\n",
|
||||
" valid_sets=[test_set],\n",
|
||||
" valid_names=[\"eval\"],\n",
|
||||
" callbacks=[\n",
|
||||
" TuneReportCheckpointCallback(\n",
|
||||
" {\n",
|
||||
" \"binary_error\": \"eval-binary_error\",\n",
|
||||
" \"binary_logloss\": \"eval-binary_logloss\",\n",
|
||||
" }\n",
|
||||
" )\n",
|
||||
" ],\n",
|
||||
" )\n",
|
||||
" preds = gbm.predict(test_x)\n",
|
||||
" pred_labels = np.rint(preds)\n",
|
||||
" tune.report(\n",
|
||||
" {\n",
|
||||
" \"mean_accuracy\": sklearn.metrics.accuracy_score(test_y, pred_labels),\n",
|
||||
" \"done\": True,\n",
|
||||
" }\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"if __name__ == \"__main__\":\n",
|
||||
" config = {\n",
|
||||
" \"objective\": \"binary\",\n",
|
||||
" \"metric\": [\"binary_error\", \"binary_logloss\"],\n",
|
||||
" \"verbose\": -1,\n",
|
||||
" \"boosting_type\": tune.grid_search([\"gbdt\", \"dart\"]),\n",
|
||||
" \"num_leaves\": tune.randint(10, 1000),\n",
|
||||
" \"learning_rate\": tune.loguniform(1e-8, 1e-1),\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" train_breast_cancer,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"binary_error\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" scheduler=ASHAScheduler(),\n",
|
||||
" num_samples=2,\n",
|
||||
" ),\n",
|
||||
" param_space=config,\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n",
|
||||
"\n",
|
||||
" print(f\"Best hyperparameters found were: {results.get_best_result().config}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "01d74c39",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Expected output\n",
|
||||
"\n",
|
||||
"This should give an output like:\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"Best hyperparameters found were: {'objective': 'binary', 'metric': ['binary_error', 'binary_logloss'], 'verbose': -1, 'boosting_type': 'gbdt', 'num_leaves': 622, 'learning_rate': 0.003721286118355498}\n",
|
||||
"```"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "lightgbm_example",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.11"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
@@ -0,0 +1,241 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "aa1c2614",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"(tune-rllib-example)=\n",
|
||||
"\n",
|
||||
"# Using RLlib with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-ray-tune-pbt_ppo_example\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=ray-tune-pbt_ppo_example\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"```{image} /rllib/images/rllib-logo.png\n",
|
||||
":align: center\n",
|
||||
":alt: RLlib Logo\n",
|
||||
":height: 120px\n",
|
||||
":target: https://docs.ray.io\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## Example\n",
|
||||
"\n",
|
||||
"Example of using a Tune scheduler ([Population Based Training](tune-scheduler-pbt)) with RLlib.\n",
|
||||
"\n",
|
||||
"This example specifies `num_workers=4`, `num_cpus=1`, and `num_gpus=0`, which means that each\n",
|
||||
"PPO trial will use 5 CPUs: 1 (for training) + 4 (for sample collection).\n",
|
||||
"This example runs 2 trials, so at least 10 CPUs must be available in the cluster resources\n",
|
||||
"in order to run both trials concurrently. Otherwise, the PBT scheduler will round-robin\n",
|
||||
"between training each trial, which is less efficient.\n",
|
||||
"\n",
|
||||
"If you want to run this example with GPUs, you can set `num_gpus` accordingly."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f4621a1a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import random\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.rllib.algorithms.ppo import PPOConfig\n",
|
||||
"from ray.rllib.core.rl_module.default_model_config import DefaultModelConfig\n",
|
||||
"from ray.tune.schedulers import PopulationBasedTraining\n",
|
||||
"\n",
|
||||
"if __name__ == \"__main__\":\n",
|
||||
" import argparse\n",
|
||||
"\n",
|
||||
" parser = argparse.ArgumentParser()\n",
|
||||
" parser.add_argument(\n",
|
||||
" \"--smoke-test\", action=\"store_true\", help=\"Finish quickly for testing\"\n",
|
||||
" )\n",
|
||||
" args, _ = parser.parse_known_args()\n",
|
||||
"\n",
|
||||
" # Postprocess the perturbed config to ensure it's still valid\n",
|
||||
" def explore(config):\n",
|
||||
" # ensure we collect enough timesteps to do sgd\n",
|
||||
" if config[\"train_batch_size\"] < config[\"sgd_minibatch_size\"] * 2:\n",
|
||||
" config[\"train_batch_size\"] = config[\"sgd_minibatch_size\"] * 2\n",
|
||||
" # ensure we run at least one sgd iter\n",
|
||||
" if config[\"num_sgd_iter\"] < 1:\n",
|
||||
" config[\"num_sgd_iter\"] = 1\n",
|
||||
" return config\n",
|
||||
"\n",
|
||||
" hyperparam_mutations = {\n",
|
||||
" \"clip_param\": lambda: random.uniform(0.01, 0.5),\n",
|
||||
" \"lr\": [1e-3, 5e-4, 1e-4, 5e-5, 1e-5],\n",
|
||||
" \"num_epochs\": lambda: random.randint(1, 30),\n",
|
||||
" \"minibatch_size\": lambda: random.randint(128, 16384),\n",
|
||||
" \"train_batch_size_per_learner\": lambda: random.randint(2000, 160000),\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" pbt = PopulationBasedTraining(\n",
|
||||
" time_attr=\"time_total_s\",\n",
|
||||
" perturbation_interval=120,\n",
|
||||
" resample_probability=0.25,\n",
|
||||
" # Specifies the mutations of these hyperparams\n",
|
||||
" hyperparam_mutations=hyperparam_mutations,\n",
|
||||
" custom_explore_fn=explore,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" # Stop when we've either reached 100 training iterations or reward=300\n",
|
||||
" stopping_criteria = {\"training_iteration\": 100, \"episode_reward_mean\": 300}\n",
|
||||
"\n",
|
||||
" config = (\n",
|
||||
" PPOConfig()\n",
|
||||
" .environment(\"Humanoid-v2\")\n",
|
||||
" .env_runners(num_env_runners=4)\n",
|
||||
" .training(\n",
|
||||
" # These params are tuned from a fixed starting value.\n",
|
||||
" kl_coeff=1.0,\n",
|
||||
" lambda_=0.95,\n",
|
||||
" clip_param=0.2,\n",
|
||||
" lr=1e-4,\n",
|
||||
" # These params start off randomly drawn from a set.\n",
|
||||
" num_epochs=tune.choice([10, 20, 30]),\n",
|
||||
" minibatch_size=tune.choice([128, 512, 2048]),\n",
|
||||
" train_batch_size_per_learner=tune.choice([10000, 20000, 40000]),\n",
|
||||
" )\n",
|
||||
" .rl_module(\n",
|
||||
" model_config=DefaultModelConfig(free_log_std=True),\n",
|
||||
" )\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" \"PPO\",\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"env_runners/episode_return_mean\",\n",
|
||||
" mode=\"max\",\n",
|
||||
" scheduler=pbt,\n",
|
||||
" num_samples=1 if args.smoke_test else 2,\n",
|
||||
" ),\n",
|
||||
" param_space=config,\n",
|
||||
" run_config=tune.RunConfig(stop=stopping_criteria),\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"id": "8cd3cc70",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best performing trial's final set of hyperparameters:\n",
|
||||
"\n",
|
||||
"{'clip_param': 0.2,\n",
|
||||
" 'lambda': 0.95,\n",
|
||||
" 'lr': 0.0001,\n",
|
||||
" 'num_sgd_iter': 30,\n",
|
||||
" 'sgd_minibatch_size': 2048,\n",
|
||||
" 'train_batch_size': 20000}\n",
|
||||
"\n",
|
||||
"Best performing trial's final reported metrics:\n",
|
||||
"\n",
|
||||
"{'episode_len_mean': 61.09146341463415,\n",
|
||||
" 'episode_reward_max': 567.4424113245353,\n",
|
||||
" 'episode_reward_mean': 310.36948184391935,\n",
|
||||
" 'episode_reward_min': 87.74736189944105}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import pprint\n",
|
||||
"\n",
|
||||
"best_result = results.get_best_result()\n",
|
||||
"\n",
|
||||
"print(\"Best performing trial's final set of hyperparameters:\\n\")\n",
|
||||
"pprint.pprint(\n",
|
||||
" {k: v for k, v in best_result.config.items() if k in hyperparam_mutations}\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(\"\\nBest performing trial's final reported metrics:\\n\")\n",
|
||||
"\n",
|
||||
"metrics_to_print = [\n",
|
||||
" \"episode_reward_mean\",\n",
|
||||
" \"episode_reward_max\",\n",
|
||||
" \"episode_reward_min\",\n",
|
||||
" \"episode_len_mean\",\n",
|
||||
"]\n",
|
||||
"pprint.pprint({k: v for k, v in best_result.metrics.items() if k in metrics_to_print})\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e4cc4685",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from ray.rllib.algorithms.algorithm import Algorithm\n",
|
||||
"\n",
|
||||
"loaded_ppo = Algorithm.from_checkpoint(best_result.checkpoint)\n",
|
||||
"loaded_policy = loaded_ppo.get_policy()\n",
|
||||
"\n",
|
||||
"# See your trained policy in action\n",
|
||||
"# loaded_policy.compute_single_action(...)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "db534c4e",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## More RLlib Examples\n",
|
||||
"\n",
|
||||
"- {doc}`/tune/examples/includes/pb2_ppo_example`:\n",
|
||||
" Example of optimizing a distributed RLlib algorithm (PPO) with the PB2 scheduler.\n",
|
||||
" Uses a small population size of 4, so can train on a laptop."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a3d4fb61",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.13"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,307 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3b05af3b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"(tune-huggingface-example)=\n",
|
||||
"\n",
|
||||
"# Using Huggingface Transformers with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-ray-tune-pbt_transformers\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=ray-tune-pbt_transformers\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"```{image} /images/hugging.png\n",
|
||||
":align: center\n",
|
||||
":alt: Huggingface Logo\n",
|
||||
":height: 120px\n",
|
||||
":target: https://huggingface.com\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"This example tunes a Hugging Face Transformers model with Ray Tune's Population Based Training (PBT) scheduler, using Hugging Face's official `hyperparameter_search` API.\n",
|
||||
"\n",
|
||||
"The example is split into two parts:\n",
|
||||
"\n",
|
||||
"- A **training script** that defines the `tune_transformer` entry point and wires together the model, dataset, scheduler, and reporter.\n",
|
||||
"- A **utility module** (`ray.tune.examples.pbt_transformers.utils`) that provides the data download and metrics helpers imported by the training script.\n",
|
||||
"\n",
|
||||
"## Training script"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "19e3c389",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\"\"\"\n",
|
||||
"This example is uses the official\n",
|
||||
"huggingface transformers `hyperparameter_search` API.\n",
|
||||
"\"\"\"\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"import ray\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune import CLIReporter\n",
|
||||
"from ray.tune.examples.pbt_transformers.utils import (\n",
|
||||
" download_data,\n",
|
||||
" build_compute_metrics_fn,\n",
|
||||
")\n",
|
||||
"from ray.tune.schedulers import PopulationBasedTraining\n",
|
||||
"from transformers import (\n",
|
||||
" glue_tasks_num_labels,\n",
|
||||
" AutoConfig,\n",
|
||||
" AutoModelForSequenceClassification,\n",
|
||||
" AutoTokenizer,\n",
|
||||
" Trainer,\n",
|
||||
" GlueDataset,\n",
|
||||
" GlueDataTrainingArguments,\n",
|
||||
" TrainingArguments,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def tune_transformer(num_samples=8, gpus_per_trial=0, smoke_test=False):\n",
|
||||
" data_dir_name = \"./data\" if not smoke_test else \"./test_data\"\n",
|
||||
" data_dir = os.path.abspath(os.path.join(os.getcwd(), data_dir_name))\n",
|
||||
" if not os.path.exists(data_dir):\n",
|
||||
" os.mkdir(data_dir, 0o755)\n",
|
||||
"\n",
|
||||
" # Change these as needed.\n",
|
||||
" model_name = (\n",
|
||||
" \"bert-base-uncased\" if not smoke_test else \"sshleifer/tiny-distilroberta-base\"\n",
|
||||
" )\n",
|
||||
" task_name = \"rte\"\n",
|
||||
"\n",
|
||||
" task_data_dir = os.path.join(data_dir, task_name.upper())\n",
|
||||
"\n",
|
||||
" num_labels = glue_tasks_num_labels[task_name]\n",
|
||||
"\n",
|
||||
" config = AutoConfig.from_pretrained(\n",
|
||||
" model_name, num_labels=num_labels, finetuning_task=task_name\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" # Download and cache tokenizer, model, and features\n",
|
||||
" print(\"Downloading and caching Tokenizer\")\n",
|
||||
" tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
|
||||
"\n",
|
||||
" # Triggers tokenizer download to cache\n",
|
||||
" print(\"Downloading and caching pre-trained model\")\n",
|
||||
" AutoModelForSequenceClassification.from_pretrained(\n",
|
||||
" model_name,\n",
|
||||
" config=config,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" def get_model():\n",
|
||||
" return AutoModelForSequenceClassification.from_pretrained(\n",
|
||||
" model_name,\n",
|
||||
" config=config,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" # Download data.\n",
|
||||
" download_data(task_name, data_dir)\n",
|
||||
"\n",
|
||||
" data_args = GlueDataTrainingArguments(task_name=task_name, data_dir=task_data_dir)\n",
|
||||
"\n",
|
||||
" train_dataset = GlueDataset(\n",
|
||||
" data_args, tokenizer=tokenizer, mode=\"train\", cache_dir=task_data_dir\n",
|
||||
" )\n",
|
||||
" eval_dataset = GlueDataset(\n",
|
||||
" data_args, tokenizer=tokenizer, mode=\"dev\", cache_dir=task_data_dir\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" training_args = TrainingArguments(\n",
|
||||
" output_dir=\".\",\n",
|
||||
" learning_rate=1e-5, # config\n",
|
||||
" do_train=True,\n",
|
||||
" do_eval=True,\n",
|
||||
" use_cpu=gpus_per_trial <= 0,\n",
|
||||
" eval_strategy=\"epoch\",\n",
|
||||
" save_strategy=\"epoch\",\n",
|
||||
" load_best_model_at_end=True,\n",
|
||||
" num_train_epochs=2, # config\n",
|
||||
" max_steps=-1,\n",
|
||||
" per_device_train_batch_size=16, # config\n",
|
||||
" per_device_eval_batch_size=16, # config\n",
|
||||
" warmup_steps=0,\n",
|
||||
" weight_decay=0.1, # config\n",
|
||||
" logging_dir=\"./logs\",\n",
|
||||
" skip_memory_metrics=True,\n",
|
||||
" report_to=\"none\",\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" trainer = Trainer(\n",
|
||||
" model_init=get_model,\n",
|
||||
" args=training_args,\n",
|
||||
" train_dataset=train_dataset,\n",
|
||||
" eval_dataset=eval_dataset,\n",
|
||||
" compute_metrics=build_compute_metrics_fn(task_name),\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" tune_config = {\n",
|
||||
" \"per_device_train_batch_size\": 32,\n",
|
||||
" \"per_device_eval_batch_size\": 32,\n",
|
||||
" \"num_train_epochs\": tune.choice([2, 3, 4, 5]),\n",
|
||||
" \"max_steps\": 1 if smoke_test else -1, # Used for smoke test.\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" scheduler = PopulationBasedTraining(\n",
|
||||
" time_attr=\"training_iteration\",\n",
|
||||
" metric=\"eval_acc\",\n",
|
||||
" mode=\"max\",\n",
|
||||
" perturbation_interval=1,\n",
|
||||
" hyperparam_mutations={\n",
|
||||
" \"weight_decay\": tune.uniform(0.0, 0.3),\n",
|
||||
" \"learning_rate\": tune.uniform(1e-5, 5e-5),\n",
|
||||
" \"per_device_train_batch_size\": [16, 32, 64],\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" reporter = CLIReporter(\n",
|
||||
" parameter_columns={\n",
|
||||
" \"weight_decay\": \"w_decay\",\n",
|
||||
" \"learning_rate\": \"lr\",\n",
|
||||
" \"per_device_train_batch_size\": \"train_bs/gpu\",\n",
|
||||
" \"num_train_epochs\": \"num_epochs\",\n",
|
||||
" },\n",
|
||||
" metric_columns=[\"eval_acc\", \"eval_loss\", \"epoch\", \"training_iteration\"],\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" trainer.hyperparameter_search(\n",
|
||||
" hp_space=lambda _: tune_config,\n",
|
||||
" backend=\"ray\",\n",
|
||||
" n_trials=num_samples,\n",
|
||||
" resources_per_trial={\"cpu\": 1, \"gpu\": gpus_per_trial},\n",
|
||||
" scheduler=scheduler,\n",
|
||||
" keep_checkpoints_num=1,\n",
|
||||
" checkpoint_score_attr=\"training_iteration\",\n",
|
||||
" stop={\"training_iteration\": 1} if smoke_test else None,\n",
|
||||
" progress_reporter=reporter,\n",
|
||||
" local_dir=\"~/ray_results/\",\n",
|
||||
" name=\"tune_transformer_pbt\",\n",
|
||||
" log_to_file=True,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"if __name__ == \"__main__\":\n",
|
||||
" import argparse\n",
|
||||
"\n",
|
||||
" parser = argparse.ArgumentParser()\n",
|
||||
" parser.add_argument(\n",
|
||||
" \"--smoke-test\",\n",
|
||||
" default=True,\n",
|
||||
" action=\"store_true\",\n",
|
||||
" help=\"Finish quickly for testing\",\n",
|
||||
" )\n",
|
||||
" args, _ = parser.parse_known_args()\n",
|
||||
"\n",
|
||||
" ray.init()\n",
|
||||
"\n",
|
||||
" if args.smoke_test:\n",
|
||||
" tune_transformer(num_samples=1, gpus_per_trial=0, smoke_test=True)\n",
|
||||
" else:\n",
|
||||
" # You can change the number of GPUs here:\n",
|
||||
" tune_transformer(num_samples=8, gpus_per_trial=1)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "42b27553",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Utility module\n",
|
||||
"\n",
|
||||
"The training script above imports the following helpers from `ray.tune.examples.pbt_transformers.utils`. They handle GLUE data download and define the `compute_metrics` function passed to the Hugging Face `Trainer`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b5639782",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\"\"\"Utilities to load and cache data.\"\"\"\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"from typing import Callable, Dict\n",
|
||||
"import numpy as np\n",
|
||||
"from transformers import EvalPrediction\n",
|
||||
"from transformers import glue_compute_metrics, glue_output_modes\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def build_compute_metrics_fn(task_name: str) -> Callable[[EvalPrediction], Dict]:\n",
|
||||
" \"\"\"Function from transformers/examples/text-classification/run_glue.py\"\"\"\n",
|
||||
" output_mode = glue_output_modes[task_name]\n",
|
||||
"\n",
|
||||
" def compute_metrics_fn(p: EvalPrediction):\n",
|
||||
" if output_mode == \"classification\":\n",
|
||||
" preds = np.argmax(p.predictions, axis=1)\n",
|
||||
" elif output_mode == \"regression\":\n",
|
||||
" preds = np.squeeze(p.predictions)\n",
|
||||
" metrics = glue_compute_metrics(task_name, preds, p.label_ids)\n",
|
||||
" return metrics\n",
|
||||
"\n",
|
||||
" return compute_metrics_fn\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def download_data(task_name, data_dir=\"./data\"):\n",
|
||||
" # Download RTE training data\n",
|
||||
" print(\"Downloading dataset.\")\n",
|
||||
" import urllib\n",
|
||||
" import zipfile\n",
|
||||
"\n",
|
||||
" if task_name == \"rte\":\n",
|
||||
" url = \"https://dl.fbaipublicfiles.com/glue/data/RTE.zip\"\n",
|
||||
" else:\n",
|
||||
" raise ValueError(\"Unknown task: {}\".format(task_name))\n",
|
||||
" data_file = os.path.join(data_dir, \"{}.zip\".format(task_name))\n",
|
||||
" if not os.path.exists(data_file):\n",
|
||||
" urllib.request.urlretrieve(url, data_file)\n",
|
||||
" with zipfile.ZipFile(data_file) as zip_ref:\n",
|
||||
" zip_ref.extractall(data_dir)\n",
|
||||
" print(\"Downloaded data for task {} to {}\".format(task_name, data_dir))\n",
|
||||
" else:\n",
|
||||
" print(\n",
|
||||
" \"Data already exists. Using downloaded data for task {} from {}\".format(\n",
|
||||
" task_name, data_dir\n",
|
||||
" )\n",
|
||||
" )\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.13"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 780 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 319 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 458 KiB |
File diff suppressed because one or more lines are too long
@@ -0,0 +1,173 @@
|
||||
import matplotlib.pyplot as plt
|
||||
from matplotlib.animation import FuncAnimation, PillowWriter
|
||||
import numpy as np
|
||||
|
||||
|
||||
def get_init_theta():
|
||||
return np.array([0.9, 0.9])
|
||||
|
||||
|
||||
def Q_batch(theta):
|
||||
"""Returns the true function value for a batch of parameters with size (B, 2)"""
|
||||
return 1.2 - (3 / 4 * theta[:, 0] ** 2 + theta[:, 1] ** 2)
|
||||
|
||||
|
||||
def get_arrows(theta_history, perturbation_interval):
|
||||
"""
|
||||
Computes the start points and deltas for arrows showing parameter perturbations.
|
||||
|
||||
Args:
|
||||
theta_history: History of parameter values of shape (iterations, 2)
|
||||
perturbation_interval: Number of iterations between perturbations
|
||||
|
||||
Returns:
|
||||
Tuple[np.ndarray, np.ndarray]: Arrow start points and deltas
|
||||
"""
|
||||
theta_history = theta_history[1:, :]
|
||||
arrow_start = theta_history[
|
||||
np.arange(perturbation_interval - 1, len(theta_history), perturbation_interval)
|
||||
]
|
||||
arrow_end = theta_history[
|
||||
np.arange(perturbation_interval, len(theta_history), perturbation_interval)
|
||||
]
|
||||
if len(arrow_end) > len(arrow_start):
|
||||
arrow_end = arrow_end[: len(arrow_start)]
|
||||
else:
|
||||
arrow_start = arrow_start[: len(arrow_end)]
|
||||
deltas = arrow_end - arrow_start
|
||||
return arrow_start, deltas
|
||||
|
||||
|
||||
def plot_parameter_history(
|
||||
results,
|
||||
colors,
|
||||
labels,
|
||||
perturbation_interval=None,
|
||||
fig=None,
|
||||
ax=None,
|
||||
plot_until_iter=None,
|
||||
include_colorbar=True,
|
||||
):
|
||||
"""
|
||||
Plot parameter history overlaid on the true reward contour.
|
||||
|
||||
Args:
|
||||
results: List of result objects containing metrics dataframes
|
||||
colors: List of colors for each result
|
||||
labels: List of labels for each result
|
||||
perturbation_interval: Interval at which parameter perturbations occur
|
||||
fig: Existing figure to plot on (creates new if None)
|
||||
ax: Existing axes to plot on (creates new if None)
|
||||
plot_until_iter: Maximum iteration to plot (plots all if None)
|
||||
include_colorbar: Whether to include a colorbar for the contour plot
|
||||
|
||||
Returns:
|
||||
List of scatter plot objects
|
||||
"""
|
||||
if fig is None or ax is None:
|
||||
fig, ax = plt.subplots()
|
||||
|
||||
theta_0 = get_init_theta()
|
||||
|
||||
x = np.linspace(-0.2, 1.0, 50)
|
||||
y = np.linspace(-0.2, 1.0, 50)
|
||||
xx, yy = np.meshgrid(x, y)
|
||||
xys = np.transpose(np.stack((xx, yy)).reshape(2, -1))
|
||||
contour = ax.contourf(xx, yy, Q_batch(xys).reshape(xx.shape), 20)
|
||||
ax.set_xlabel("theta0")
|
||||
ax.set_ylabel("theta1")
|
||||
ax.set_title("Parameter History and True Reward Q(theta) Contour")
|
||||
|
||||
scatters = []
|
||||
for i in range(len(results)):
|
||||
df = results[i].metrics_dataframe
|
||||
|
||||
# Append the initial theta values to the history
|
||||
theta0_history = np.concatenate([[theta_0[0]], df["theta0"].to_numpy()])
|
||||
theta1_history = np.concatenate([[theta_0[1]], df["theta1"].to_numpy()])
|
||||
training_iters = np.concatenate([[0], df["training_iteration"].to_numpy()])
|
||||
|
||||
if plot_until_iter is None:
|
||||
plot_until_iter = len(training_iters)
|
||||
|
||||
scatter = ax.scatter(
|
||||
theta0_history[:plot_until_iter],
|
||||
theta1_history[:plot_until_iter],
|
||||
# Size of scatter point decreases as training iteration increases
|
||||
s=100 / ((training_iters[:plot_until_iter] + 1) ** 1 / 3),
|
||||
alpha=0.5,
|
||||
c=colors[i],
|
||||
label=labels[i],
|
||||
)
|
||||
scatters.append(scatter)
|
||||
for i, theta0, theta1 in zip(training_iters, theta0_history, theta1_history):
|
||||
if i % (perturbation_interval or 1) == 0 and i < plot_until_iter:
|
||||
ax.annotate(i, (theta0, theta1))
|
||||
|
||||
if perturbation_interval is not None:
|
||||
theta_history = np.hstack(
|
||||
(theta0_history.reshape(-1, 1), theta1_history.reshape(-1, 1))
|
||||
)[:plot_until_iter, :]
|
||||
arrow_starts, deltas = get_arrows(theta_history, perturbation_interval)
|
||||
for arrow_start, delta in zip(arrow_starts, deltas):
|
||||
ax.arrow(
|
||||
arrow_start[0],
|
||||
arrow_start[1],
|
||||
delta[0],
|
||||
delta[1],
|
||||
head_width=0.01,
|
||||
length_includes_head=True,
|
||||
alpha=0.25,
|
||||
)
|
||||
ax.legend(loc="upper left", title="Trial Initial Parameters")
|
||||
if include_colorbar:
|
||||
cbar = fig.colorbar(contour, ax=ax, orientation="vertical")
|
||||
cbar.set_label("Reward Q(theta)")
|
||||
return scatters
|
||||
|
||||
|
||||
def plot_Q_history(results, colors, labels, ax=None):
|
||||
"""
|
||||
Plot the history of true reward values over training iterations.
|
||||
|
||||
Args:
|
||||
results: List of result objects containing metrics dataframes
|
||||
colors: List of colors for each result
|
||||
labels: List of labels for each result
|
||||
ax: Existing axes to plot on (creates new if None)
|
||||
"""
|
||||
if ax is None:
|
||||
fig, ax = plt.subplots()
|
||||
ax.set_title("True Reward (Q) Value Over Training Iterations")
|
||||
ax.set_xlabel("Training Iteration")
|
||||
ax.set_ylabel("Reward Q(theta)")
|
||||
for i in range(len(results)):
|
||||
df = results[i].metrics_dataframe
|
||||
ax.plot(df["Q"], label=labels[i], color=colors[i])
|
||||
ax.legend(title="Trial Initial Parameters")
|
||||
|
||||
|
||||
def make_animation(
|
||||
results, colors, labels, perturbation_interval=None, filename="pbt.gif", fps=5
|
||||
):
|
||||
fig, ax = plt.subplots(figsize=(8, 8))
|
||||
|
||||
def animate(i):
|
||||
ax.clear()
|
||||
ax.set_title("Parameter Evolution Over Iterations")
|
||||
return plot_parameter_history(
|
||||
results,
|
||||
colors,
|
||||
labels,
|
||||
perturbation_interval=perturbation_interval,
|
||||
fig=fig,
|
||||
ax=ax,
|
||||
plot_until_iter=i,
|
||||
include_colorbar=False,
|
||||
)
|
||||
|
||||
ani = FuncAnimation(
|
||||
fig, animate, interval=1000 // fps, blit=True, repeat=True, frames=range(1, 101)
|
||||
)
|
||||
ani.save(filename, writer=PillowWriter(fps=fps))
|
||||
plt.close()
|
||||
@@ -0,0 +1,8 @@
|
||||
:orphan:
|
||||
|
||||
PBT Visualization Helper File
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Used in :doc:`/tune/examples/pbt_visualization/pbt_visualization`.
|
||||
|
||||
.. literalinclude:: ./pbt_visualization_utils.py
|
||||
@@ -0,0 +1,412 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ecad719c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"(tune-aim-ref)=\n",
|
||||
"\n",
|
||||
"# Using Aim with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-aim\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-aim\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"[Aim](https://aimstack.io) is an easy-to-use and supercharged open-source experiment tracker.\n",
|
||||
"Aim logs your training runs, enables a well-designed UI to compare them, and provides an API to query them programmatically.\n",
|
||||
"\n",
|
||||
"```{image} /images/aim_logo_full.png\n",
|
||||
":align: center\n",
|
||||
":alt: Aim\n",
|
||||
":width: 100%\n",
|
||||
":target: https://aimstack.io\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Ray Tune currently offers built-in integration with Aim.\n",
|
||||
"The {ref}`AimLoggerCallback <tune-aim-logger>` automatically logs metrics that are reported to Tune by using the Aim API.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## Logging Tune Hyperparameter Configurations and Results to Aim\n",
|
||||
"\n",
|
||||
"The following example demonstrates how the `AimLoggerCallback` can be used in a Tune experiment.\n",
|
||||
"Begin by installing and importing the necessary modules:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1290b5b5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install aim\n",
|
||||
"%pip install ray[tune]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "100bcf8a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"import ray\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.logger.aim import AimLoggerCallback"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "9346c0f6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next, define a simple `train_function`, which is a [`Trainable`](trainable-docs) that reports a loss to Tune.\n",
|
||||
"The objective function itself is not important for this example, as our main focus is on the integration with Aim."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "e8b4fc4d",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_function(config):\n",
|
||||
" for _ in range(50):\n",
|
||||
" loss = config[\"mean\"] + config[\"sd\"] * np.random.randn()\n",
|
||||
" tune.report({\"loss\": loss})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "831eed42",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Here is an example of how you can use the `AimLoggerCallback` with simple grid-search Tune experiment.\n",
|
||||
"The logger will log each of the 9 grid-search trials as separate Aim runs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "52988599",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2023-02-07 00:04:11,228\tINFO worker.py:1544 -- Started a local Ray instance. View the dashboard at \u001b[1m\u001b[32mhttp://127.0.0.1:8265 \u001b[39m\u001b[22m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2023-02-07 00:04:19</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:06.86 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>32.8/64.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Resources requested: 0/10 CPUs, 0/0 GPUs, 0.0/26.93 GiB heap, 0.0/2.0 GiB objects\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> mean</th><th style=\"text-align: right;\"> sd</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> loss</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_01a3b_00000</td><td>TERMINATED</td><td>127.0.0.1:10277</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">0.385428</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 4.48031</td><td style=\"text-align: right;\">1.01928</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00001</td><td>TERMINATED</td><td>127.0.0.1:10296</td><td style=\"text-align: right;\"> 2</td><td style=\"text-align: right;\">0.819716</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 2.97272</td><td style=\"text-align: right;\">3.01491</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00002</td><td>TERMINATED</td><td>127.0.0.1:10301</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\">0.769197</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 2.39572</td><td style=\"text-align: right;\">3.87155</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00003</td><td>TERMINATED</td><td>127.0.0.1:10307</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\">0.29466 </td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 2.41568</td><td style=\"text-align: right;\">4.1507 </td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00004</td><td>TERMINATED</td><td>127.0.0.1:10313</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\">0.152208</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 1.68383</td><td style=\"text-align: right;\">5.10225</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00005</td><td>TERMINATED</td><td>127.0.0.1:10321</td><td style=\"text-align: right;\"> 6</td><td style=\"text-align: right;\">0.879814</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 1.54015</td><td style=\"text-align: right;\">6.20238</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00006</td><td>TERMINATED</td><td>127.0.0.1:10329</td><td style=\"text-align: right;\"> 7</td><td style=\"text-align: right;\">0.487499</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 1.44706</td><td style=\"text-align: right;\">7.79551</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00007</td><td>TERMINATED</td><td>127.0.0.1:10333</td><td style=\"text-align: right;\"> 8</td><td style=\"text-align: right;\">0.639783</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 1.4261 </td><td style=\"text-align: right;\">7.94189</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00008</td><td>TERMINATED</td><td>127.0.0.1:10341</td><td style=\"text-align: right;\"> 9</td><td style=\"text-align: right;\">0.12285 </td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 1.07701</td><td style=\"text-align: right;\">8.82304</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"trialProgress\">\n",
|
||||
" <h3>Trial Progress</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>date </th><th>done </th><th>episodes_total </th><th>experiment_id </th><th>experiment_tag </th><th>hostname </th><th style=\"text-align: right;\"> iterations_since_restore</th><th style=\"text-align: right;\"> loss</th><th>node_ip </th><th style=\"text-align: right;\"> pid</th><th style=\"text-align: right;\"> time_since_restore</th><th style=\"text-align: right;\"> time_this_iter_s</th><th style=\"text-align: right;\"> time_total_s</th><th style=\"text-align: right;\"> timestamp</th><th style=\"text-align: right;\"> timesteps_since_restore</th><th>timesteps_total </th><th style=\"text-align: right;\"> training_iteration</th><th>trial_id </th><th style=\"text-align: right;\"> warmup_time</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_01a3b_00000</td><td>2023-02-07_00-04-18</td><td>True </td><td> </td><td>c8447fdceea6436c9edd6f030a5b1d82</td><td>0_mean=1,sd=0.3854</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">1.01928</td><td>127.0.0.1</td><td style=\"text-align: right;\">10277</td><td style=\"text-align: right;\"> 4.48031</td><td style=\"text-align: right;\"> 0.013865 </td><td style=\"text-align: right;\"> 4.48031</td><td style=\"text-align: right;\"> 1675757058</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00000</td><td style=\"text-align: right;\"> 0.00264072</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00001</td><td>2023-02-07_00-04-18</td><td>True </td><td> </td><td>7dd6d3ee24244a0885b354c285064728</td><td>1_mean=2,sd=0.8197</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">3.01491</td><td>127.0.0.1</td><td style=\"text-align: right;\">10296</td><td style=\"text-align: right;\"> 2.97272</td><td style=\"text-align: right;\"> 0.0584073 </td><td style=\"text-align: right;\"> 2.97272</td><td style=\"text-align: right;\"> 1675757058</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00001</td><td style=\"text-align: right;\"> 0.0316792 </td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00002</td><td>2023-02-07_00-04-18</td><td>True </td><td> </td><td>e3da49ebad034c4b8fdaf0aa87927b1a</td><td>2_mean=3,sd=0.7692</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">3.87155</td><td>127.0.0.1</td><td style=\"text-align: right;\">10301</td><td style=\"text-align: right;\"> 2.39572</td><td style=\"text-align: right;\"> 0.0695491 </td><td style=\"text-align: right;\"> 2.39572</td><td style=\"text-align: right;\"> 1675757058</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00002</td><td style=\"text-align: right;\"> 0.0315411 </td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00003</td><td>2023-02-07_00-04-18</td><td>True </td><td> </td><td>95c60c4f67c4481ebccff25b0a49e75d</td><td>3_mean=4,sd=0.2947</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">4.1507 </td><td>127.0.0.1</td><td style=\"text-align: right;\">10307</td><td style=\"text-align: right;\"> 2.41568</td><td style=\"text-align: right;\"> 0.0175381 </td><td style=\"text-align: right;\"> 2.41568</td><td style=\"text-align: right;\"> 1675757058</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00003</td><td style=\"text-align: right;\"> 0.0310779 </td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00004</td><td>2023-02-07_00-04-18</td><td>True </td><td> </td><td>a216253cb41e47caa229e65488deb019</td><td>4_mean=5,sd=0.1522</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">5.10225</td><td>127.0.0.1</td><td style=\"text-align: right;\">10313</td><td style=\"text-align: right;\"> 1.68383</td><td style=\"text-align: right;\"> 0.064441 </td><td style=\"text-align: right;\"> 1.68383</td><td style=\"text-align: right;\"> 1675757058</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00004</td><td style=\"text-align: right;\"> 0.00450182</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00005</td><td>2023-02-07_00-04-18</td><td>True </td><td> </td><td>23834104277f476cb99d9c696281fceb</td><td>5_mean=6,sd=0.8798</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">6.20238</td><td>127.0.0.1</td><td style=\"text-align: right;\">10321</td><td style=\"text-align: right;\"> 1.54015</td><td style=\"text-align: right;\"> 0.00910306</td><td style=\"text-align: right;\"> 1.54015</td><td style=\"text-align: right;\"> 1675757058</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00005</td><td style=\"text-align: right;\"> 0.0480251 </td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00006</td><td>2023-02-07_00-04-18</td><td>True </td><td> </td><td>15f650121df747c3bd2720481d47b265</td><td>6_mean=7,sd=0.4875</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">7.79551</td><td>127.0.0.1</td><td style=\"text-align: right;\">10329</td><td style=\"text-align: right;\"> 1.44706</td><td style=\"text-align: right;\"> 0.00600386</td><td style=\"text-align: right;\"> 1.44706</td><td style=\"text-align: right;\"> 1675757058</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00006</td><td style=\"text-align: right;\"> 0.00202489</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00007</td><td>2023-02-07_00-04-19</td><td>True </td><td> </td><td>78b1673cf2034ed99135b80a0cb31e0e</td><td>7_mean=8,sd=0.6398</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">7.94189</td><td>127.0.0.1</td><td style=\"text-align: right;\">10333</td><td style=\"text-align: right;\"> 1.4261 </td><td style=\"text-align: right;\"> 0.00225306</td><td style=\"text-align: right;\"> 1.4261 </td><td style=\"text-align: right;\"> 1675757059</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00007</td><td style=\"text-align: right;\"> 0.00209713</td></tr>\n",
|
||||
"<tr><td>train_function_01a3b_00008</td><td>2023-02-07_00-04-19</td><td>True </td><td> </td><td>c7f5d86154cb46b6aa27bef523edcd6f</td><td>8_mean=9,sd=0.1228</td><td>Justins-MacBook-Pro-16</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\">8.82304</td><td>127.0.0.1</td><td style=\"text-align: right;\">10341</td><td style=\"text-align: right;\"> 1.07701</td><td style=\"text-align: right;\"> 0.00291467</td><td style=\"text-align: right;\"> 1.07701</td><td style=\"text-align: right;\"> 1675757059</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 50</td><td>01a3b_00008</td><td style=\"text-align: right;\"> 0.00240111</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".trialProgress {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".trialProgress h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".trialProgress td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2023-02-07 00:04:19,366\tINFO tune.py:798 -- Total run time: 7.38 seconds (6.85 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<ray.tune.result_grid.ResultGrid at 0x137de07c0>"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tuner = tune.Tuner(\n",
|
||||
" train_function,\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" callbacks=[AimLoggerCallback()],\n",
|
||||
" storage_path=\"/tmp/ray_results\",\n",
|
||||
" name=\"aim_example\",\n",
|
||||
" ),\n",
|
||||
" param_space={\n",
|
||||
" \"mean\": tune.grid_search([1, 2, 3, 4, 5, 6, 7, 8, 9]),\n",
|
||||
" \"sd\": tune.uniform(0.1, 0.9),\n",
|
||||
" },\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" ),\n",
|
||||
")\n",
|
||||
"tuner.fit()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "941f25f2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"When the script executes, a grid-search is carried out and the results are saved to the Aim repo,\n",
|
||||
"stored at the default location -- the experiment log directory (in this case, it's at `/tmp/ray_results/aim_example`).\n",
|
||||
"\n",
|
||||
"### More Configuration Options for Aim\n",
|
||||
"\n",
|
||||
"In the example above, we used the default configuration for the `AimLoggerCallback`.\n",
|
||||
"There are a few options that can be configured as arguments to the callback. For example,\n",
|
||||
"setting `AimLoggerCallback(repo=\"/path/to/repo\")` will log results to the Aim repo at that\n",
|
||||
"filepath, which could be useful if you have a central location where the results of multiple\n",
|
||||
"Tune experiments are stored. Relative paths to the working directory where Tune script is\n",
|
||||
"launched can be used as well. By default, the repo will be set to the experiment log\n",
|
||||
"directory. See [the API reference](tune-aim-logger) for more configurations.\n",
|
||||
"\n",
|
||||
"## Launching the Aim UI\n",
|
||||
"\n",
|
||||
"Now that we have logged our results to the Aim repository, we can view it in Aim's web UI.\n",
|
||||
"To do this, we first find the directory where the Aim repository lives, then we use\n",
|
||||
"the Aim CLI to launch the web interface."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "880f55aa",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"--------------------------------------------------------------------------\n",
|
||||
" Aim UI collects anonymous usage analytics. \n",
|
||||
" Read how to opt-out here: \n",
|
||||
" https://aimstack.readthedocs.io/en/latest/community/telemetry.html \n",
|
||||
"--------------------------------------------------------------------------\n",
|
||||
"\u001b[33mRunning Aim UI on repo `<Repo#-5734997863388805469 path=/tmp/ray_results/aim_example/.aim read_only=None>`\u001b[0m\n",
|
||||
"Open http://127.0.0.1:43800\n",
|
||||
"Press Ctrl+C to exit\n",
|
||||
"^C\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Uncomment the following line to launch the Aim UI!\n",
|
||||
"#!aim up --repo=/tmp/ray_results/aim_example"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "adbe661a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"After launching the Aim UI, we can open the web interface at `localhost:43800`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "7bb97157",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```{image} /images/aim_example_metrics_page.png\n",
|
||||
":align: center\n",
|
||||
":alt: Aim Metrics Explorer\n",
|
||||
":target: https://aimstack.readthedocs.io/en/latest/ui/pages/explorers.html#metrics-explorer\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "2f6e9138",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The next sections contain more in-depth information on the API of the Tune-Aim integration.\n",
|
||||
"\n",
|
||||
"## Tune Aim Logger API\n",
|
||||
"\n",
|
||||
"(tune-aim-logger)=\n",
|
||||
"\n",
|
||||
"```{eval-rst}\n",
|
||||
".. autoclass:: ray.tune.logger.aim.AimLoggerCallback\n",
|
||||
" :noindex:\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "0ebd1904",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "ray_dev_py38",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.13"
|
||||
},
|
||||
"orphan": true,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "265d195fda5292fe8f69c6e37c435a5634a1ed3b6799724e66a975f68fa21517"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,177 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "3b05af3b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"(tune-comet-ref)=\n",
|
||||
"\n",
|
||||
"# Using Comet with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-comet\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-comet\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"[Comet](https://www.comet.ml/site/) is a tool to manage and optimize the\n",
|
||||
"entire ML lifecycle, from experiment tracking, model optimization and dataset\n",
|
||||
"versioning to model production monitoring.\n",
|
||||
"\n",
|
||||
"```{image} /images/comet_logo_full.png\n",
|
||||
":align: center\n",
|
||||
":alt: Comet\n",
|
||||
":height: 120px\n",
|
||||
":target: https://www.comet.ml/site/\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## Example\n",
|
||||
"\n",
|
||||
"To illustrate logging your trial results to Comet, we'll define a simple training function\n",
|
||||
"that simulates a `loss` metric:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "19e3c389",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"from ray import tune\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_function(config):\n",
|
||||
" for i in range(30):\n",
|
||||
" loss = config[\"mean\"] + config[\"sd\"] * np.random.randn()\n",
|
||||
" tune.report({\"loss\": loss})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "6fb69a24",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now, given that you provide your Comet API key and your project name like so:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "993d5be6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"api_key = \"YOUR_COMET_API_KEY\"\n",
|
||||
"project_name = \"YOUR_COMET_PROJECT_NAME\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "e9ce0d76",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This cell is hidden from the rendered notebook. It makes the \n",
|
||||
"from unittest.mock import MagicMock\n",
|
||||
"from ray.air.integrations.comet import CometLoggerCallback\n",
|
||||
"\n",
|
||||
"CometLoggerCallback._logger_process_cls = MagicMock\n",
|
||||
"api_key = \"abc\"\n",
|
||||
"project_name = \"test\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "d792a1b0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can add a Comet logger by specifying the `callbacks` argument in your `RunConfig()` accordingly:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "dbb761e7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from ray.air.integrations.comet import CometLoggerCallback\n",
|
||||
"\n",
|
||||
"tuner = tune.Tuner(\n",
|
||||
" train_function,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" ),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" callbacks=[\n",
|
||||
" CometLoggerCallback(\n",
|
||||
" api_key=api_key, project_name=project_name, tags=[\"comet_example\"]\n",
|
||||
" )\n",
|
||||
" ],\n",
|
||||
" ),\n",
|
||||
" param_space={\"mean\": tune.grid_search([1, 2, 3]), \"sd\": tune.uniform(0.2, 0.8)},\n",
|
||||
")\n",
|
||||
"results = tuner.fit()\n",
|
||||
"\n",
|
||||
"print(results.get_best_result().config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "d7e46189",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Tune Comet Logger\n",
|
||||
"\n",
|
||||
"Ray Tune offers an integration with Comet through the `CometLoggerCallback`,\n",
|
||||
"which automatically logs metrics and parameters reported to Tune to the Comet UI.\n",
|
||||
"\n",
|
||||
"Click on the following dropdown to see this callback API in detail:\n",
|
||||
"\n",
|
||||
"```{eval-rst}\n",
|
||||
".. autoclass:: ray.air.integrations.comet.CometLoggerCallback\n",
|
||||
" :noindex:\n",
|
||||
"```"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.7"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,600 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "6df76a1f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Using MLflow with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-mlflow\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-mlflow\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"(tune-mlflow-ref)=\n",
|
||||
"\n",
|
||||
"[MLflow](https://mlflow.org/) is an open source platform to manage the ML lifecycle, including experimentation,\n",
|
||||
"reproducibility, deployment, and a central model registry. It currently offers four components, including\n",
|
||||
"MLflow Tracking to record and query experiments, including code, data, config, and results.\n",
|
||||
"\n",
|
||||
"```{image} /images/mlflow.png\n",
|
||||
":align: center\n",
|
||||
":alt: MLflow\n",
|
||||
":height: 80px\n",
|
||||
":target: https://www.mlflow.org/\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Ray Tune currently offers two lightweight integrations for MLflow Tracking.\n",
|
||||
"One is the {ref}`MLflowLoggerCallback <tune-mlflow-logger>`, which automatically logs\n",
|
||||
"metrics reported to Tune to the MLflow Tracking API.\n",
|
||||
"\n",
|
||||
"The other one is the {ref}`setup_mlflow <tune-mlflow-setup>` function, which can be\n",
|
||||
"used with the function API. It automatically\n",
|
||||
"initializes the MLflow API with Tune's training information and creates a run for each Tune trial.\n",
|
||||
"Then within your training function, you can just use the\n",
|
||||
"MLflow like you would normally do, e.g. using `mlflow.log_metrics()` or even `mlflow.autolog()`\n",
|
||||
"to log to your training process.\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## Running an MLflow Example\n",
|
||||
"\n",
|
||||
"In the following example we're going to use both of the above methods, namely the `MLflowLoggerCallback` and\n",
|
||||
"the `setup_mlflow` function to log metrics.\n",
|
||||
"Let's start with a few crucial imports:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "b0e47339",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import tempfile\n",
|
||||
"import time\n",
|
||||
"\n",
|
||||
"import mlflow\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.air.integrations.mlflow import MLflowLoggerCallback, setup_mlflow\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "618b6935",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"Next, let's define an easy training function (a Tune `Trainable`) that iteratively computes steps and evaluates\n",
|
||||
"intermediate scores that we report to Tune."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "f449538e",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def evaluation_fn(step, width, height):\n",
|
||||
" return (0.1 + width * step / 100) ** (-1) + height * 0.1\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_function(config):\n",
|
||||
" width, height = config[\"width\"], config[\"height\"]\n",
|
||||
"\n",
|
||||
" for step in range(config.get(\"steps\", 100)):\n",
|
||||
" # Iterative training function - can be any arbitrary training procedure\n",
|
||||
" intermediate_score = evaluation_fn(step, width, height)\n",
|
||||
" # Feed the score back to Tune.\n",
|
||||
" tune.report({\"iterations\": step, \"mean_loss\": intermediate_score})\n",
|
||||
" time.sleep(0.1)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "722e5d2f",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"Given an MLFlow tracking URI, you can now simply use the `MLflowLoggerCallback` as a `callback` argument to\n",
|
||||
"your `RunConfig()`:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "8e0b9ab7",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_with_callback(mlflow_tracking_uri, finish_fast=False):\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" train_function,\n",
|
||||
" tune_config=tune.TuneConfig(num_samples=5),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" name=\"mlflow\",\n",
|
||||
" callbacks=[\n",
|
||||
" MLflowLoggerCallback(\n",
|
||||
" tracking_uri=mlflow_tracking_uri,\n",
|
||||
" experiment_name=\"mlflow_callback_example\",\n",
|
||||
" save_artifact=True,\n",
|
||||
" )\n",
|
||||
" ],\n",
|
||||
" ),\n",
|
||||
" param_space={\n",
|
||||
" \"width\": tune.randint(10, 100),\n",
|
||||
" \"height\": tune.randint(0, 100),\n",
|
||||
" \"steps\": 5 if finish_fast else 100,\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "e086f110",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To use the `setup_mlflow` utility, you simply call this function in your training function.\n",
|
||||
"Note that we also use `mlflow.log_metrics(...)` to log metrics to MLflow.\n",
|
||||
"Otherwise, this version of our training function is identical to its original."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "144b8f39",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_function_mlflow(config):\n",
|
||||
" tracking_uri = config.pop(\"tracking_uri\", None)\n",
|
||||
" setup_mlflow(\n",
|
||||
" config,\n",
|
||||
" experiment_name=\"setup_mlflow_example\",\n",
|
||||
" tracking_uri=tracking_uri,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" # Hyperparameters\n",
|
||||
" width, height = config[\"width\"], config[\"height\"]\n",
|
||||
"\n",
|
||||
" for step in range(config.get(\"steps\", 100)):\n",
|
||||
" # Iterative training function - can be any arbitrary training procedure\n",
|
||||
" intermediate_score = evaluation_fn(step, width, height)\n",
|
||||
" # Log the metrics to mlflow\n",
|
||||
" mlflow.log_metrics(dict(mean_loss=intermediate_score), step=step)\n",
|
||||
" # Feed the score back to Tune.\n",
|
||||
" tune.report({\"iterations\": step, \"mean_loss\": intermediate_score})\n",
|
||||
" time.sleep(0.1)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "dc480366",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"With this new objective function ready, you can now create a Tune run with it as follows:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "4b9fe6be",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_with_setup(mlflow_tracking_uri, finish_fast=False):\n",
|
||||
" # Set the experiment, or create a new one if does not exist yet.\n",
|
||||
" mlflow.set_tracking_uri(mlflow_tracking_uri)\n",
|
||||
" mlflow.set_experiment(experiment_name=\"setup_mlflow_example\")\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" train_function_mlflow,\n",
|
||||
" tune_config=tune.TuneConfig(num_samples=5),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" name=\"mlflow\",\n",
|
||||
" ),\n",
|
||||
" param_space={\n",
|
||||
" \"width\": tune.randint(10, 100),\n",
|
||||
" \"height\": tune.randint(0, 100),\n",
|
||||
" \"steps\": 5 if finish_fast else 100,\n",
|
||||
" \"tracking_uri\": mlflow.get_tracking_uri(),\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "915dfd30",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you hapen to have an MLFlow tracking URI, you can set it below in the `mlflow_tracking_uri` variable and set\n",
|
||||
"`smoke_test=False`.\n",
|
||||
"Otherwise, you can just run a quick test of the `tune_function` and `tune_decorated` functions without using MLflow."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "05d11774",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2022-12-22 10:37:53,580\tINFO worker.py:1542 -- Started a local Ray instance. View the dashboard at \u001b[1m\u001b[32mhttp://127.0.0.1:8265 \u001b[39m\u001b[22m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2022-12-22 10:38:04</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:06.73 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>10.4/16.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Resources requested: 0/16 CPUs, 0/0 GPUs, 0.0/4.03 GiB heap, 0.0/2.0 GiB objects\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> height</th><th style=\"text-align: right;\"> width</th><th style=\"text-align: right;\"> loss</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> iterations</th><th style=\"text-align: right;\"> neg_mean_loss</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_b275b_00000</td><td>TERMINATED</td><td>127.0.0.1:801</td><td style=\"text-align: right;\"> 66</td><td style=\"text-align: right;\"> 36</td><td style=\"text-align: right;\">7.24935</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.587302</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -7.24935</td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00001</td><td>TERMINATED</td><td>127.0.0.1:813</td><td style=\"text-align: right;\"> 33</td><td style=\"text-align: right;\"> 35</td><td style=\"text-align: right;\">3.96667</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.507423</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -3.96667</td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00002</td><td>TERMINATED</td><td>127.0.0.1:814</td><td style=\"text-align: right;\"> 75</td><td style=\"text-align: right;\"> 29</td><td style=\"text-align: right;\">8.29365</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.518995</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -8.29365</td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00003</td><td>TERMINATED</td><td>127.0.0.1:815</td><td style=\"text-align: right;\"> 28</td><td style=\"text-align: right;\"> 63</td><td style=\"text-align: right;\">3.18168</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.567739</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -3.18168</td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00004</td><td>TERMINATED</td><td>127.0.0.1:816</td><td style=\"text-align: right;\"> 20</td><td style=\"text-align: right;\"> 18</td><td style=\"text-align: right;\">3.21951</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.526536</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -3.21951</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"trialProgress\">\n",
|
||||
" <h3>Trial Progress</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>date </th><th>done </th><th>episodes_total </th><th>experiment_id </th><th>experiment_tag </th><th>hostname </th><th style=\"text-align: right;\"> iterations</th><th style=\"text-align: right;\"> iterations_since_restore</th><th style=\"text-align: right;\"> mean_loss</th><th style=\"text-align: right;\"> neg_mean_loss</th><th>node_ip </th><th style=\"text-align: right;\"> pid</th><th style=\"text-align: right;\"> time_since_restore</th><th style=\"text-align: right;\"> time_this_iter_s</th><th style=\"text-align: right;\"> time_total_s</th><th style=\"text-align: right;\"> timestamp</th><th style=\"text-align: right;\"> timesteps_since_restore</th><th>timesteps_total </th><th style=\"text-align: right;\"> training_iteration</th><th>trial_id </th><th style=\"text-align: right;\"> warmup_time</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_b275b_00000</td><td>2022-12-22_10-38-01</td><td>True </td><td> </td><td>28feaa4dd8ab4edab810e8109e77502e</td><td>0_height=66,width=36</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 7.24935</td><td style=\"text-align: right;\"> -7.24935</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 801</td><td style=\"text-align: right;\"> 0.587302</td><td style=\"text-align: right;\"> 0.126818</td><td style=\"text-align: right;\"> 0.587302</td><td style=\"text-align: right;\"> 1671705481</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b275b_00000</td><td style=\"text-align: right;\"> 0.00293493</td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00001</td><td>2022-12-22_10-38-04</td><td>True </td><td> </td><td>245010d0c3d0439ebfb664764ae9db3c</td><td>1_height=33,width=35</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 3.96667</td><td style=\"text-align: right;\"> -3.96667</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 813</td><td style=\"text-align: right;\"> 0.507423</td><td style=\"text-align: right;\"> 0.122086</td><td style=\"text-align: right;\"> 0.507423</td><td style=\"text-align: right;\"> 1671705484</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b275b_00001</td><td style=\"text-align: right;\"> 0.00553799</td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00002</td><td>2022-12-22_10-38-04</td><td>True </td><td> </td><td>898afbf9b906448c980f399c72a2324c</td><td>2_height=75,width=29</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 8.29365</td><td style=\"text-align: right;\"> -8.29365</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 814</td><td style=\"text-align: right;\"> 0.518995</td><td style=\"text-align: right;\"> 0.123554</td><td style=\"text-align: right;\"> 0.518995</td><td style=\"text-align: right;\"> 1671705484</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b275b_00002</td><td style=\"text-align: right;\"> 0.0040431 </td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00003</td><td>2022-12-22_10-38-04</td><td>True </td><td> </td><td>03a4476f82734642b6ab0a5040ca58f8</td><td>3_height=28,width=63</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 3.18168</td><td style=\"text-align: right;\"> -3.18168</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 815</td><td style=\"text-align: right;\"> 0.567739</td><td style=\"text-align: right;\"> 0.125471</td><td style=\"text-align: right;\"> 0.567739</td><td style=\"text-align: right;\"> 1671705484</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b275b_00003</td><td style=\"text-align: right;\"> 0.00406194</td></tr>\n",
|
||||
"<tr><td>train_function_b275b_00004</td><td>2022-12-22_10-38-04</td><td>True </td><td> </td><td>ff8c7c55ce6e404f9b0552c17f7a0c40</td><td>4_height=20,width=18</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 3.21951</td><td style=\"text-align: right;\"> -3.21951</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 816</td><td style=\"text-align: right;\"> 0.526536</td><td style=\"text-align: right;\"> 0.123327</td><td style=\"text-align: right;\"> 0.526536</td><td style=\"text-align: right;\"> 1671705484</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b275b_00004</td><td style=\"text-align: right;\"> 0.00332022</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".trialProgress {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".trialProgress h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".trialProgress td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2022-12-22 10:38:04,477\tINFO tune.py:772 -- Total run time: 7.99 seconds (6.71 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2022-12-22 10:38:11</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:07.00 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>10.7/16.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Resources requested: 0/16 CPUs, 0/0 GPUs, 0.0/4.03 GiB heap, 0.0/2.0 GiB objects\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> height</th><th style=\"text-align: right;\"> width</th><th style=\"text-align: right;\"> loss</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> iterations</th><th style=\"text-align: right;\"> neg_mean_loss</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00000</td><td>TERMINATED</td><td>127.0.0.1:842</td><td style=\"text-align: right;\"> 37</td><td style=\"text-align: right;\"> 68</td><td style=\"text-align: right;\">4.05461</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.750435</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -4.05461</td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00001</td><td>TERMINATED</td><td>127.0.0.1:853</td><td style=\"text-align: right;\"> 50</td><td style=\"text-align: right;\"> 20</td><td style=\"text-align: right;\">6.11111</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.652748</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -6.11111</td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00002</td><td>TERMINATED</td><td>127.0.0.1:854</td><td style=\"text-align: right;\"> 38</td><td style=\"text-align: right;\"> 83</td><td style=\"text-align: right;\">4.0924 </td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.6513 </td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -4.0924 </td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00003</td><td>TERMINATED</td><td>127.0.0.1:855</td><td style=\"text-align: right;\"> 15</td><td style=\"text-align: right;\"> 93</td><td style=\"text-align: right;\">1.76178</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.650586</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -1.76178</td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00004</td><td>TERMINATED</td><td>127.0.0.1:856</td><td style=\"text-align: right;\"> 75</td><td style=\"text-align: right;\"> 43</td><td style=\"text-align: right;\">8.04945</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 0.656046</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> -8.04945</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"trialProgress\">\n",
|
||||
" <h3>Trial Progress</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>date </th><th>done </th><th>episodes_total </th><th>experiment_id </th><th>experiment_tag </th><th>hostname </th><th style=\"text-align: right;\"> iterations</th><th style=\"text-align: right;\"> iterations_since_restore</th><th style=\"text-align: right;\"> mean_loss</th><th style=\"text-align: right;\"> neg_mean_loss</th><th>node_ip </th><th style=\"text-align: right;\"> pid</th><th style=\"text-align: right;\"> time_since_restore</th><th style=\"text-align: right;\"> time_this_iter_s</th><th style=\"text-align: right;\"> time_total_s</th><th style=\"text-align: right;\"> timestamp</th><th style=\"text-align: right;\"> timesteps_since_restore</th><th>timesteps_total </th><th style=\"text-align: right;\"> training_iteration</th><th>trial_id </th><th style=\"text-align: right;\"> warmup_time</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00000</td><td>2022-12-22_10-38-08</td><td>True </td><td> </td><td>62703cfe82e54d74972377fbb525b000</td><td>0_height=37,width=68</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 4.05461</td><td style=\"text-align: right;\"> -4.05461</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 842</td><td style=\"text-align: right;\"> 0.750435</td><td style=\"text-align: right;\"> 0.108625</td><td style=\"text-align: right;\"> 0.750435</td><td style=\"text-align: right;\"> 1671705488</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b73bd_00000</td><td style=\"text-align: right;\"> 0.0030272 </td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00001</td><td>2022-12-22_10-38-11</td><td>True </td><td> </td><td>03ea89852115465392ed318db8021614</td><td>1_height=50,width=20</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 6.11111</td><td style=\"text-align: right;\"> -6.11111</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 853</td><td style=\"text-align: right;\"> 0.652748</td><td style=\"text-align: right;\"> 0.110796</td><td style=\"text-align: right;\"> 0.652748</td><td style=\"text-align: right;\"> 1671705491</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b73bd_00001</td><td style=\"text-align: right;\"> 0.00303078</td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00002</td><td>2022-12-22_10-38-11</td><td>True </td><td> </td><td>3731fc2966f9453ba58c650d89035ab4</td><td>2_height=38,width=83</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 4.0924 </td><td style=\"text-align: right;\"> -4.0924 </td><td>127.0.0.1</td><td style=\"text-align: right;\"> 854</td><td style=\"text-align: right;\"> 0.6513 </td><td style=\"text-align: right;\"> 0.108578</td><td style=\"text-align: right;\"> 0.6513 </td><td style=\"text-align: right;\"> 1671705491</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b73bd_00002</td><td style=\"text-align: right;\"> 0.00310016</td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00003</td><td>2022-12-22_10-38-11</td><td>True </td><td> </td><td>fb35841742b348b9912d10203c730f1e</td><td>3_height=15,width=93</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 1.76178</td><td style=\"text-align: right;\"> -1.76178</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 855</td><td style=\"text-align: right;\"> 0.650586</td><td style=\"text-align: right;\"> 0.109097</td><td style=\"text-align: right;\"> 0.650586</td><td style=\"text-align: right;\"> 1671705491</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b73bd_00003</td><td style=\"text-align: right;\"> 0.0576491 </td></tr>\n",
|
||||
"<tr><td>train_function_mlflow_b73bd_00004</td><td>2022-12-22_10-38-11</td><td>True </td><td> </td><td>6d3cbf9ecc3446369e607ff78c67bc29</td><td>4_height=75,width=43</td><td>kais-macbook-pro.anyscale.com.beta.tailscale.net</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 8.04945</td><td style=\"text-align: right;\"> -8.04945</td><td>127.0.0.1</td><td style=\"text-align: right;\"> 856</td><td style=\"text-align: right;\"> 0.656046</td><td style=\"text-align: right;\"> 0.109869</td><td style=\"text-align: right;\"> 0.656046</td><td style=\"text-align: right;\"> 1671705491</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 5</td><td>b73bd_00004</td><td style=\"text-align: right;\"> 0.00265694</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".trialProgress {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".trialProgress h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".trialProgress td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2022-12-22 10:38:11,514\tINFO tune.py:772 -- Total run time: 7.01 seconds (6.98 seconds for the tuning loop).\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"smoke_test = True\n",
|
||||
"\n",
|
||||
"if smoke_test:\n",
|
||||
" mlflow_tracking_uri = os.path.join(tempfile.gettempdir(), \"mlruns\")\n",
|
||||
"else:\n",
|
||||
" mlflow_tracking_uri = \"<MLFLOW_TRACKING_URI>\"\n",
|
||||
"\n",
|
||||
"tune_with_callback(mlflow_tracking_uri, finish_fast=smoke_test)\n",
|
||||
"if not smoke_test:\n",
|
||||
" df = mlflow.search_runs(\n",
|
||||
" [mlflow.get_experiment_by_name(\"mlflow_callback_example\").experiment_id]\n",
|
||||
" )\n",
|
||||
" print(df)\n",
|
||||
"\n",
|
||||
"tune_with_setup(mlflow_tracking_uri, finish_fast=smoke_test)\n",
|
||||
"if not smoke_test:\n",
|
||||
" df = mlflow.search_runs(\n",
|
||||
" [mlflow.get_experiment_by_name(\"setup_mlflow_example\").experiment_id]\n",
|
||||
" )\n",
|
||||
" print(df)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "f0df0817",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This completes our Tune and MLflow walk-through.\n",
|
||||
"In the following sections you can find more details on the API of the Tune-MLflow integration.\n",
|
||||
"\n",
|
||||
"## MLflow AutoLogging\n",
|
||||
"\n",
|
||||
"You can also check out {doc}`here </tune/examples/includes/mlflow_ptl_example>` for an example on how you can\n",
|
||||
"leverage MLflow auto-logging, in this case with Pytorch Lightning\n",
|
||||
"\n",
|
||||
"## MLflow Logger API\n",
|
||||
"\n",
|
||||
"(tune-mlflow-logger)=\n",
|
||||
"\n",
|
||||
"```{eval-rst}\n",
|
||||
".. autoclass:: ray.air.integrations.mlflow.MLflowLoggerCallback\n",
|
||||
" :noindex:\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## MLflow setup API\n",
|
||||
"\n",
|
||||
"(tune-mlflow-setup)=\n",
|
||||
"\n",
|
||||
"```{eval-rst}\n",
|
||||
".. autofunction:: ray.air.integrations.mlflow.setup_mlflow\n",
|
||||
" :noindex:\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## More MLflow Examples\n",
|
||||
"\n",
|
||||
"- {doc}`/tune/examples/includes/mlflow_ptl_example`: Example for using [MLflow](https://github.com/mlflow/mlflow/)\n",
|
||||
" and [Pytorch Lightning](https://github.com/PyTorchLightning/pytorch-lightning) with Ray Tune."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.7"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,555 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "586737af",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# How to use Tune with PyTorch\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-pytorch-cifar\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-pytorch-cifar\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"(tune-pytorch-cifar-ref)=\n",
|
||||
"\n",
|
||||
"In this walkthrough, we will show you how to integrate Tune into your PyTorch\n",
|
||||
"training workflow. We will follow [this tutorial from the PyTorch documentation](https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html)\n",
|
||||
"for training a CIFAR10 image classifier.\n",
|
||||
"\n",
|
||||
"```{image} /images/pytorch_logo.png\n",
|
||||
":align: center\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Hyperparameter tuning can make the difference between an average model and a highly\n",
|
||||
"accurate one. Often simple things like choosing a different learning rate or changing\n",
|
||||
"a network layer size can have a dramatic impact on your model performance. Fortunately,\n",
|
||||
"Tune makes exploring these optimal parameter combinations easy - and works nicely\n",
|
||||
"together with PyTorch.\n",
|
||||
"\n",
|
||||
"As you will see, we only need to add some slight modifications. In particular, we\n",
|
||||
"need to\n",
|
||||
"\n",
|
||||
"1. wrap data loading and training in functions,\n",
|
||||
"2. make some network parameters configurable,\n",
|
||||
"3. add checkpointing (optional),\n",
|
||||
"4. and define the search space for the model tuning\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "7e8650d1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup / Imports\n",
|
||||
"\n",
|
||||
"First, the requirements (uncomment to install):"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "89728f69",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install -Uq \"ray[tune]\" torch torchvision pandas ipywidgets"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0cda8ce7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next, the imports:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "55529285",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import tempfile\n",
|
||||
"\n",
|
||||
"import numpy as np\n",
|
||||
"import torch\n",
|
||||
"import torch.nn as nn\n",
|
||||
"import torch.nn.functional as F\n",
|
||||
"import torch.optim as optim\n",
|
||||
"import torchvision\n",
|
||||
"import torchvision.transforms as transforms\n",
|
||||
"from filelock import FileLock\n",
|
||||
"from torch.utils.data import random_split\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.schedulers import ASHAScheduler"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "f59e551d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Most of the imports are needed for building the PyTorch model. Only the last two\n",
|
||||
"imports are for Ray Tune.\n",
|
||||
"\n",
|
||||
"## Data loaders\n",
|
||||
"\n",
|
||||
"We wrap the data loaders in their own function and pass a global data directory.\n",
|
||||
"This way we can share a data directory between different trials."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "01471556",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def load_data(data_dir=\"./data\"):\n",
|
||||
" \"\"\"Create dataloaders for normalized CIFAR10 training/test subsets.\"\"\"\n",
|
||||
" transform = transforms.Compose([\n",
|
||||
" transforms.ToTensor(),\n",
|
||||
" transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),\n",
|
||||
" ])\n",
|
||||
"\n",
|
||||
" # We add FileLock here because multiple workers will want to\n",
|
||||
" # download data, and this may cause overwrites since\n",
|
||||
" # DataLoader is not threadsafe.\n",
|
||||
" with FileLock(os.path.expanduser(\"~/.data.lock\")):\n",
|
||||
" trainset = torchvision.datasets.CIFAR10(\n",
|
||||
" root=data_dir, train=True, download=True, transform=transform)\n",
|
||||
"\n",
|
||||
" testset = torchvision.datasets.CIFAR10(\n",
|
||||
" root=data_dir, train=False, download=True, transform=transform)\n",
|
||||
"\n",
|
||||
" return trainset, testset\n",
|
||||
"\n",
|
||||
"def create_dataloaders(trainset, batch_size, num_workers=8):\n",
|
||||
" \"\"\"Create train/val splits and dataloaders.\"\"\"\n",
|
||||
" train_size = int(len(trainset) * 0.8)\n",
|
||||
" train_subset, val_subset = random_split(\n",
|
||||
" trainset, [train_size, len(trainset) - train_size])\n",
|
||||
"\n",
|
||||
" train_loader = torch.utils.data.DataLoader(\n",
|
||||
" train_subset,\n",
|
||||
" batch_size=batch_size, \n",
|
||||
" shuffle=True,\n",
|
||||
" num_workers=num_workers\n",
|
||||
" )\n",
|
||||
" val_loader = torch.utils.data.DataLoader(\n",
|
||||
" val_subset,\n",
|
||||
" batch_size=batch_size,\n",
|
||||
" shuffle=False, \n",
|
||||
" num_workers=num_workers\n",
|
||||
" )\n",
|
||||
" return train_loader, val_loader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def load_test_data():\n",
|
||||
" # Load fake data for running a quick smoke-test.\n",
|
||||
" trainset = torchvision.datasets.FakeData(\n",
|
||||
" 128, (3, 32, 32), num_classes=10, transform=transforms.ToTensor()\n",
|
||||
" )\n",
|
||||
" testset = torchvision.datasets.FakeData(\n",
|
||||
" 16, (3, 32, 32), num_classes=10, transform=transforms.ToTensor()\n",
|
||||
" )\n",
|
||||
" return trainset, testset"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "80958cf3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Configurable neural network\n",
|
||||
"\n",
|
||||
"We can only tune those parameters that are configurable. In this example, we can specify\n",
|
||||
"the layer sizes of the fully connected layers:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "fff6bd0d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class Net(nn.Module):\n",
|
||||
" def __init__(self, l1=120, l2=84):\n",
|
||||
" super(Net, self).__init__()\n",
|
||||
" self.conv1 = nn.Conv2d(3, 6, 5)\n",
|
||||
" self.pool = nn.MaxPool2d(2, 2)\n",
|
||||
" self.conv2 = nn.Conv2d(6, 16, 5)\n",
|
||||
" self.fc1 = nn.Linear(16 * 5 * 5, l1)\n",
|
||||
" self.fc2 = nn.Linear(l1, l2)\n",
|
||||
" self.fc3 = nn.Linear(l2, 10)\n",
|
||||
"\n",
|
||||
" def forward(self, x):\n",
|
||||
" x = self.pool(F.relu(self.conv1(x)))\n",
|
||||
" x = self.pool(F.relu(self.conv2(x)))\n",
|
||||
" x = x.view(-1, 16 * 5 * 5)\n",
|
||||
" x = F.relu(self.fc1(x))\n",
|
||||
" x = F.relu(self.fc2(x))\n",
|
||||
" x = self.fc3(x)\n",
|
||||
" return x"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "fb619875",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## The train function\n",
|
||||
"\n",
|
||||
"Now it gets interesting, because we introduce some changes to the example [from the PyTorch\n",
|
||||
"documentation](https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html).\n",
|
||||
"\n",
|
||||
"(communicating-with-ray-tune)=\n",
|
||||
"\n",
|
||||
"The full code example looks like this:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "fa0bdae0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_cifar(config):\n",
|
||||
" net = Net(config[\"l1\"], config[\"l2\"])\n",
|
||||
" device = config[\"device\"]\n",
|
||||
" if device == \"cuda\":\n",
|
||||
" net = nn.DataParallel(net)\n",
|
||||
" net.to(device)\n",
|
||||
"\n",
|
||||
" criterion = nn.CrossEntropyLoss()\n",
|
||||
" optimizer = optim.SGD(net.parameters(), lr=config[\"lr\"], momentum=0.9, weight_decay=5e-5)\n",
|
||||
"\n",
|
||||
" # Load existing checkpoint through `get_checkpoint()` API.\n",
|
||||
" if tune.get_checkpoint():\n",
|
||||
" loaded_checkpoint = tune.get_checkpoint()\n",
|
||||
" with loaded_checkpoint.as_directory() as loaded_checkpoint_dir:\n",
|
||||
" model_state, optimizer_state = torch.load(\n",
|
||||
" os.path.join(loaded_checkpoint_dir, \"checkpoint.pt\")\n",
|
||||
" )\n",
|
||||
" net.load_state_dict(model_state)\n",
|
||||
" optimizer.load_state_dict(optimizer_state)\n",
|
||||
"\n",
|
||||
" # Data setup\n",
|
||||
" if config[\"smoke_test\"]:\n",
|
||||
" trainset, _ = load_test_data()\n",
|
||||
" else:\n",
|
||||
" trainset, _ = load_data()\n",
|
||||
" train_loader, val_loader = create_dataloaders(\n",
|
||||
" trainset, \n",
|
||||
" config[\"batch_size\"],\n",
|
||||
" num_workers=0 if config[\"smoke_test\"] else 8\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" for epoch in range(config[\"max_num_epochs\"]): # loop over the dataset multiple times\n",
|
||||
" net.train()\n",
|
||||
" running_loss = 0.0\n",
|
||||
" for inputs, labels in train_loader:\n",
|
||||
" inputs, labels = inputs.to(device), labels.to(device)\n",
|
||||
"\n",
|
||||
" # forward + backward + optimize\n",
|
||||
" optimizer.zero_grad() # reset gradients\n",
|
||||
" outputs = net(inputs)\n",
|
||||
" loss = criterion(outputs, labels)\n",
|
||||
" loss.backward()\n",
|
||||
" optimizer.step()\n",
|
||||
" \n",
|
||||
" running_loss += loss.item()\n",
|
||||
"\n",
|
||||
" # Validation\n",
|
||||
" net.eval()\n",
|
||||
" val_loss = 0.0\n",
|
||||
" correct = total = 0\n",
|
||||
" with torch.no_grad():\n",
|
||||
" for inputs, labels in val_loader:\n",
|
||||
" inputs, labels = inputs.to(device), labels.to(device)\n",
|
||||
" outputs = net(inputs)\n",
|
||||
" val_loss += criterion(outputs, labels).item()\n",
|
||||
" _, predicted = outputs.max(1)\n",
|
||||
" total += labels.size(0)\n",
|
||||
" correct += predicted.eq(labels).sum().item()\n",
|
||||
"\n",
|
||||
" # Report metrics\n",
|
||||
" metrics = {\n",
|
||||
" \"loss\": val_loss / len(val_loader),\n",
|
||||
" \"accuracy\": correct / total,\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" # Here we save a checkpoint. It is automatically registered with\n",
|
||||
" # Ray Tune and will potentially be accessed through in ``get_checkpoint()``\n",
|
||||
" # in future iterations.\n",
|
||||
" # Note to save a file-like checkpoint, you still need to put it under a directory\n",
|
||||
" # to construct a checkpoint.\n",
|
||||
" with tempfile.TemporaryDirectory() as temp_checkpoint_dir:\n",
|
||||
" path = os.path.join(temp_checkpoint_dir, \"checkpoint.pt\")\n",
|
||||
" torch.save(\n",
|
||||
" (net.state_dict(), optimizer.state_dict()), path\n",
|
||||
" )\n",
|
||||
" checkpoint = tune.Checkpoint.from_directory(temp_checkpoint_dir)\n",
|
||||
" tune.report(metrics, checkpoint=checkpoint)\n",
|
||||
" print(\"Finished Training!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "918d8baf",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As you can see, most of the code is adapted directly from the example.\n",
|
||||
"\n",
|
||||
"## Test set accuracy\n",
|
||||
"\n",
|
||||
"Commonly the performance of a machine learning model is tested on a hold-out test\n",
|
||||
"set with data that has not been used for training the model. We also wrap this in a\n",
|
||||
"function:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "93b5b4af",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def test_best_model(best_result, smoke_test=False):\n",
|
||||
" best_trained_model = Net(best_result.config[\"l1\"], best_result.config[\"l2\"])\n",
|
||||
" device = best_result.config[\"device\"]\n",
|
||||
" if device == \"cuda\":\n",
|
||||
" best_trained_model = nn.DataParallel(best_trained_model)\n",
|
||||
" best_trained_model.to(device)\n",
|
||||
"\n",
|
||||
" checkpoint_path = os.path.join(best_result.checkpoint.to_directory(), \"checkpoint.pt\")\n",
|
||||
"\n",
|
||||
" model_state, _optimizer_state = torch.load(checkpoint_path)\n",
|
||||
" best_trained_model.load_state_dict(model_state)\n",
|
||||
"\n",
|
||||
" if smoke_test:\n",
|
||||
" _trainset, testset = load_test_data()\n",
|
||||
" else:\n",
|
||||
" _trainset, testset = load_data()\n",
|
||||
"\n",
|
||||
" testloader = torch.utils.data.DataLoader(\n",
|
||||
" testset, batch_size=4, shuffle=False, num_workers=2\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" correct = 0\n",
|
||||
" total = 0\n",
|
||||
" with torch.no_grad():\n",
|
||||
" for data in testloader:\n",
|
||||
" images, labels = data\n",
|
||||
" images, labels = images.to(device), labels.to(device)\n",
|
||||
" outputs = best_trained_model(images)\n",
|
||||
" _, predicted = outputs.max(1)\n",
|
||||
" total += labels.size(0)\n",
|
||||
" correct += predicted.eq(labels).sum().item()\n",
|
||||
"\n",
|
||||
" print(f\"Best trial test set accuracy: {correct / total}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "85f8230e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As you can see, the function also expects a `device` parameter, so we can do the\n",
|
||||
"test set validation on a GPU."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "980720e3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"## Configuring the search space\n",
|
||||
"\n",
|
||||
"Lastly, we need to define Tune's search space. Here is an example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "564eab65",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Set this to True for a smoke test that runs with a small synthetic dataset.\n",
|
||||
"SMOKE_TEST = False"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "18d94d85",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# For CI testing:\n",
|
||||
"SMOKE_TEST = True"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "5416cece",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"config = {\n",
|
||||
" \"l1\": tune.sample_from(lambda _: 2**np.random.randint(2, 9)),\n",
|
||||
" \"l2\": tune.sample_from(lambda _: 2**np.random.randint(2, 9)),\n",
|
||||
" \"lr\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
" \"batch_size\": tune.choice([2, 4, 8, 16]),\n",
|
||||
" \"smoke_test\": SMOKE_TEST,\n",
|
||||
" \"num_trials\": 10 if not SMOKE_TEST else 2,\n",
|
||||
" \"max_num_epochs\": 10 if not SMOKE_TEST else 2,\n",
|
||||
" \"device\": \"cuda\" if torch.cuda.is_available() else \"cpu\",\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "20af95cc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The `tune.sample_from()` function makes it possible to define your own sample\n",
|
||||
"methods to obtain hyperparameters. In this example, the layer sizes `l1` and `l2` \n",
|
||||
"should be powers of 2 between 4 and 256, so either 4, 8, 16, 32, 64, 128, or 256.\n",
|
||||
"The `lr` (learning rate) should be uniformly sampled between 0.0001 and 0.1. Lastly,\n",
|
||||
"the batch size is a choice between 2, 4, 8, and 16.\n",
|
||||
"\n",
|
||||
"At each trial, Tune will now randomly sample a combination of parameters from these\n",
|
||||
"search spaces. It will then train a number of models in parallel and find the best\n",
|
||||
"performing one among these. We also use the `ASHAScheduler` which will terminate badly\n",
|
||||
"performing trials early.\n",
|
||||
"\n",
|
||||
"You can specify the number of CPUs, which are then available e.g.\n",
|
||||
"to increase the `num_workers` of the PyTorch `DataLoader` instances. The selected\n",
|
||||
"number of GPUs are made visible to PyTorch in each trial. Trials do not have access to\n",
|
||||
"GPUs that haven't been requested for them - so you don't have to care about two trials\n",
|
||||
"using the same set of resources.\n",
|
||||
"\n",
|
||||
"Here we can also specify fractional GPUs, so something like `gpus_per_trial=0.5` is\n",
|
||||
"completely valid. The trials will then share GPUs among each other.\n",
|
||||
"You just have to make sure that the models still fit in the GPU memory.\n",
|
||||
"\n",
|
||||
"After training the models, we will find the best performing one and load the trained\n",
|
||||
"network from the checkpoint file. We then obtain the test set accuracy and report\n",
|
||||
"everything by printing.\n",
|
||||
"\n",
|
||||
"The full main function looks like this:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "91d83380",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def main(config, gpus_per_trial=1):\n",
|
||||
" scheduler = ASHAScheduler(\n",
|
||||
" time_attr=\"training_iteration\",\n",
|
||||
" max_t=config[\"max_num_epochs\"],\n",
|
||||
" grace_period=1,\n",
|
||||
" reduction_factor=2)\n",
|
||||
" \n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" tune.with_resources(\n",
|
||||
" tune.with_parameters(train_cifar),\n",
|
||||
" resources={\"cpu\": 2, \"gpu\": gpus_per_trial}\n",
|
||||
" ),\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" scheduler=scheduler,\n",
|
||||
" num_samples=config[\"num_trials\"],\n",
|
||||
" ),\n",
|
||||
" param_space=config,\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n",
|
||||
" \n",
|
||||
" best_result = results.get_best_result(\"loss\", \"min\")\n",
|
||||
"\n",
|
||||
" print(f\"Best trial config: {best_result.config}\")\n",
|
||||
" print(f\"Best trial final validation loss: {best_result.metrics['loss']}\")\n",
|
||||
" print(f\"Best trial final validation accuracy: {best_result.metrics['accuracy']}\")\n",
|
||||
"\n",
|
||||
" test_best_model(best_result, smoke_test=config[\"smoke_test\"])\n",
|
||||
"\n",
|
||||
"main(config, gpus_per_trial=1 if torch.cuda.is_available() else 0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "b702b4ce",
|
||||
"metadata": {},
|
||||
"source": "If you run the code, an example output could look like this:\n\n```{code-block} bash\n:emphasize-lines: 7\n\n Number of trials: 10 (10 TERMINATED)\n +-------------------------+------------+-------+------+------+-------------+--------------+---------+------------+----------------------+\n | Trial name | status | loc | l1 | l2 | lr | batch_size | loss | accuracy | training_iteration |\n |-------------------------+------------+-------+------+------+-------------+--------------+---------+------------+----------------------|\n | train_cifar_87d1f_00000 | TERMINATED | | 64 | 4 | 0.00011629 | 2 | 1.87273 | 0.244 | 2 |\n | train_cifar_87d1f_00001 | TERMINATED | | 32 | 64 | 0.000339763 | 8 | 1.23603 | 0.567 | 8 |\n | train_cifar_87d1f_00002 | TERMINATED | | 8 | 16 | 0.00276249 | 16 | 1.1815 | 0.5836 | 10 |\n | train_cifar_87d1f_00003 | TERMINATED | | 4 | 64 | 0.000648721 | 4 | 1.31131 | 0.5224 | 8 |\n | train_cifar_87d1f_00004 | TERMINATED | | 32 | 16 | 0.000340753 | 8 | 1.26454 | 0.5444 | 8 |\n | train_cifar_87d1f_00005 | TERMINATED | | 8 | 4 | 0.000699775 | 8 | 1.99594 | 0.1983 | 2 |\n | train_cifar_87d1f_00006 | TERMINATED | | 256 | 8 | 0.0839654 | 16 | 2.3119 | 0.0993 | 1 |\n | train_cifar_87d1f_00007 | TERMINATED | | 16 | 128 | 0.0758154 | 16 | 2.33575 | 0.1327 | 1 |\n | train_cifar_87d1f_00008 | TERMINATED | | 16 | 8 | 0.0763312 | 16 | 2.31129 | 0.1042 | 4 |\n | train_cifar_87d1f_00009 | TERMINATED | | 128 | 16 | 0.000124903 | 4 | 2.26917 | 0.1945 | 1 |\n +-------------------------+------------+-------+------+------+-------------+--------------+---------+------------+----------------------+\n\n\n Best trial config: {'l1': 8, 'l2': 16, 'lr': 0.0027624906698231976, 'batch_size': 16, 'data_dir': '...'}\n Best trial final validation loss: 1.1815014744281769\n Best trial final validation accuracy: 0.5836\n Best trial test set accuracy: 0.5806\n```\n\nAs you can see, most trials have been stopped early in order to avoid wasting resources.\nThe best performing trial achieved a validation accuracy of about 58%, which could\nbe confirmed on the test set.\n\nSo that's it! You can now tune the parameters of your PyTorch models.\n\n## See More PyTorch Examples\n\n- {doc}`/tune/examples/includes/mnist_pytorch`: Converts the PyTorch MNIST example to use Tune with the function-based API.\n Also shows how to easily convert something relying on argparse to use Tune.\n- {doc}`/tune/examples/includes/pbt_convnet_function_example`: Example training a ConvNet with checkpointing in function API.\n- {doc}`/tune/examples/includes/mnist_pytorch_trainable`: Converts the PyTorch MNIST example to use Tune with Trainable API.\n Also uses the HyperBandScheduler and checkpoints the model at the end.\n- {doc}`/_collections/tune/examples/tune_pytorch_asha/README`: End-to-end tutorial with PyTorch covering search spaces, ASHA scheduling, checkpoint/resume logic, and best model evaluation on CIFAR-10."
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "tune-pytorch-cifar",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.11"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,506 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"# Using PyTorch Lightning with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-pytorch-lightning\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-pytorch-lightning\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"(tune-pytorch-lightning-ref)=\n",
|
||||
"\n",
|
||||
"PyTorch Lightning is a framework which brings structure into training PyTorch models. It aims to avoid boilerplate code, so you don't have to write the same training loops all over again when building a new model.\n",
|
||||
"\n",
|
||||
"```{image} /images/pytorch_lightning_full.png\n",
|
||||
":align: center\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"The main abstraction of PyTorch Lightning is the `LightningModule` class, which should be extended by your application. There is [a great post on how to transfer your models from vanilla PyTorch to Lightning](https://towardsdatascience.com/from-pytorch-to-pytorch-lightning-a-gentle-introduction-b371b7caaf09).\n",
|
||||
"\n",
|
||||
"The class structure of PyTorch Lightning makes it very easy to define and tune model parameters. This tutorial will show you how to use Tune with PyTorch Lightning. Notably, the `LightningModule` does not have to be altered at all for this - so you can use it plug and play for your existing models, assuming their parameters are configurable!\n",
|
||||
"\n",
|
||||
":::{note}\n",
|
||||
"To run this example, you will need to install the following:\n",
|
||||
"\n",
|
||||
"```bash\n",
|
||||
"$ pip install -q \"ray[tune]\" torch torchvision lightning\n",
|
||||
"```\n",
|
||||
":::\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## PyTorch Lightning classifier for MNIST\n",
|
||||
"\n",
|
||||
"Let's first start with the basic PyTorch Lightning implementation of an MNIST classifier. This classifier does not include any tuning code at this point.\n",
|
||||
"\n",
|
||||
"First, we run some imports:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/home/ray/anaconda3/lib/python3.11/site-packages/lightning_utilities/core/imports.py:14: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.\n",
|
||||
" import pkg_resources\n",
|
||||
"/home/ray/anaconda3/lib/python3.11/site-packages/transformers/utils/generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n",
|
||||
" _torch_pytree._register_pytree_node(\n",
|
||||
"/home/ray/anaconda3/lib/python3.11/site-packages/transformers/utils/generic.py:309: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n",
|
||||
" _torch_pytree._register_pytree_node(\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import torch\n",
|
||||
"import tempfile\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" import lightning.pytorch as pl\n",
|
||||
"except ModuleNotFoundError:\n",
|
||||
" import pytorch_lightning as pl\n",
|
||||
"\n",
|
||||
"import torch.nn.functional as F\n",
|
||||
"from filelock import FileLock\n",
|
||||
"from torchmetrics import Accuracy\n",
|
||||
"from torch.utils.data import DataLoader, random_split\n",
|
||||
"from torchvision.datasets import MNIST\n",
|
||||
"from torchvision import transforms"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# If you want to run full test, please set SMOKE_TEST to False\n",
|
||||
"SMOKE_TEST = True"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Our example builds on the MNIST example from the [blog post](https://towardsdatascience.com/from-pytorch-to-pytorch-lightning-a-gentle-introduction-b371b7caaf09) we mentioned before. We adapted the original model and dataset definitions into `MNISTClassifier` and `MNISTDataModule`. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class MNISTClassifier(pl.LightningModule):\n",
|
||||
" def __init__(self, config):\n",
|
||||
" super(MNISTClassifier, self).__init__()\n",
|
||||
" self.accuracy = Accuracy(task=\"multiclass\", num_classes=10, top_k=1)\n",
|
||||
" self.layer_1_size = config[\"layer_1_size\"]\n",
|
||||
" self.layer_2_size = config[\"layer_2_size\"]\n",
|
||||
" self.lr = config[\"lr\"]\n",
|
||||
"\n",
|
||||
" # mnist images are (1, 28, 28) (channels, width, height)\n",
|
||||
" self.layer_1 = torch.nn.Linear(28 * 28, self.layer_1_size)\n",
|
||||
" self.layer_2 = torch.nn.Linear(self.layer_1_size, self.layer_2_size)\n",
|
||||
" self.layer_3 = torch.nn.Linear(self.layer_2_size, 10)\n",
|
||||
" self.eval_loss = []\n",
|
||||
" self.eval_accuracy = []\n",
|
||||
"\n",
|
||||
" def cross_entropy_loss(self, logits, labels):\n",
|
||||
" return F.nll_loss(logits, labels)\n",
|
||||
"\n",
|
||||
" def forward(self, x):\n",
|
||||
" batch_size, channels, width, height = x.size()\n",
|
||||
" x = x.view(batch_size, -1)\n",
|
||||
"\n",
|
||||
" x = self.layer_1(x)\n",
|
||||
" x = torch.relu(x)\n",
|
||||
"\n",
|
||||
" x = self.layer_2(x)\n",
|
||||
" x = torch.relu(x)\n",
|
||||
"\n",
|
||||
" x = self.layer_3(x)\n",
|
||||
" x = torch.log_softmax(x, dim=1)\n",
|
||||
"\n",
|
||||
" return x\n",
|
||||
"\n",
|
||||
" def training_step(self, train_batch, batch_idx):\n",
|
||||
" x, y = train_batch\n",
|
||||
" logits = self.forward(x)\n",
|
||||
" loss = self.cross_entropy_loss(logits, y)\n",
|
||||
" accuracy = self.accuracy(logits, y)\n",
|
||||
"\n",
|
||||
" self.log(\"ptl/train_loss\", loss)\n",
|
||||
" self.log(\"ptl/train_accuracy\", accuracy)\n",
|
||||
" return loss\n",
|
||||
"\n",
|
||||
" def validation_step(self, val_batch, batch_idx):\n",
|
||||
" x, y = val_batch\n",
|
||||
" logits = self.forward(x)\n",
|
||||
" loss = self.cross_entropy_loss(logits, y)\n",
|
||||
" accuracy = self.accuracy(logits, y)\n",
|
||||
" self.eval_loss.append(loss)\n",
|
||||
" self.eval_accuracy.append(accuracy)\n",
|
||||
" return {\"val_loss\": loss, \"val_accuracy\": accuracy}\n",
|
||||
"\n",
|
||||
" def on_validation_epoch_end(self):\n",
|
||||
" avg_loss = torch.stack(self.eval_loss).mean()\n",
|
||||
" avg_acc = torch.stack(self.eval_accuracy).mean()\n",
|
||||
" self.log(\"ptl/val_loss\", avg_loss, sync_dist=True)\n",
|
||||
" self.log(\"ptl/val_accuracy\", avg_acc, sync_dist=True)\n",
|
||||
" self.eval_loss.clear()\n",
|
||||
" self.eval_accuracy.clear()\n",
|
||||
"\n",
|
||||
" def configure_optimizers(self):\n",
|
||||
" optimizer = torch.optim.Adam(self.parameters(), lr=self.lr)\n",
|
||||
" return optimizer\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"class MNISTDataModule(pl.LightningDataModule):\n",
|
||||
" def __init__(self, batch_size=128):\n",
|
||||
" super().__init__()\n",
|
||||
" self.data_dir = tempfile.mkdtemp()\n",
|
||||
" self.batch_size = batch_size\n",
|
||||
" self.transform = transforms.Compose(\n",
|
||||
" [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" def setup(self, stage=None):\n",
|
||||
" with FileLock(f\"{self.data_dir}.lock\"):\n",
|
||||
" mnist = MNIST(\n",
|
||||
" self.data_dir, train=True, download=True, transform=self.transform\n",
|
||||
" )\n",
|
||||
" self.mnist_train, self.mnist_val = random_split(mnist, [55000, 5000])\n",
|
||||
"\n",
|
||||
" self.mnist_test = MNIST(\n",
|
||||
" self.data_dir, train=False, download=True, transform=self.transform\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" def train_dataloader(self):\n",
|
||||
" return DataLoader(self.mnist_train, batch_size=self.batch_size, num_workers=4)\n",
|
||||
"\n",
|
||||
" def val_dataloader(self):\n",
|
||||
" return DataLoader(self.mnist_val, batch_size=self.batch_size, num_workers=4)\n",
|
||||
"\n",
|
||||
" def test_dataloader(self):\n",
|
||||
" return DataLoader(self.mnist_test, batch_size=self.batch_size, num_workers=4)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"default_config = {\n",
|
||||
" \"layer_1_size\": 128,\n",
|
||||
" \"layer_2_size\": 256,\n",
|
||||
" \"lr\": 1e-3,\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Define a training function that creates model, `DataModule`, and the PyTorch Lightning `Trainer`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from ray.tune.integration.pytorch_lightning import TuneReportCheckpointCallback\n",
|
||||
"\n",
|
||||
"def train_func(config):\n",
|
||||
" dm = MNISTDataModule(batch_size=config[\"batch_size\"])\n",
|
||||
" model = MNISTClassifier(config)\n",
|
||||
"\n",
|
||||
" trainer = pl.Trainer(\n",
|
||||
" devices=\"auto\",\n",
|
||||
" accelerator=\"auto\",\n",
|
||||
" callbacks=[TuneReportCheckpointCallback()],\n",
|
||||
" enable_progress_bar=False,\n",
|
||||
" )\n",
|
||||
" trainer.fit(model, datamodule=dm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Tuning the model parameters\n",
|
||||
"\n",
|
||||
"The parameters above should give you a good accuracy of over 90% already. However, we might improve on this simply by changing some of the hyperparameters. For instance, maybe we get an even higher accuracy if we used a smaller learning rate and larger middle layer size.\n",
|
||||
"\n",
|
||||
"Instead of manually loop through all the parameter combinitions, let's use Tune to systematically try out parameter combinations and find the best performing set.\n",
|
||||
"\n",
|
||||
"First, we need some additional imports:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.schedulers import ASHAScheduler"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Configuring the search space\n",
|
||||
"\n",
|
||||
"Now we configure the parameter search space. We would like to choose between different layer dimensions, learning rate, and batch sizes. The learning rate should be sampled uniformly between `0.0001` and `0.1`. The `tune.loguniform()` function is syntactic sugar to make sampling between these different orders of magnitude easier, specifically we are able to also sample small values. Similarly for `tune.choice()`, which samples from all the provided options."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search_space = {\n",
|
||||
" \"layer_1_size\": tune.choice([32, 64, 128]),\n",
|
||||
" \"layer_2_size\": tune.choice([64, 128, 256]),\n",
|
||||
" \"lr\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
" \"batch_size\": tune.choice([32, 64]),\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Selecting a scheduler\n",
|
||||
"\n",
|
||||
"In this example, we use an [Asynchronous Hyperband](https://blog.ml.cmu.edu/2018/12/12/massively-parallel-hyperparameter-optimization/)\n",
|
||||
"scheduler. This scheduler decides at each iteration which trials are likely to perform\n",
|
||||
"badly, and stops these trials. This way we don't waste any resources on bad hyperparameter\n",
|
||||
"configurations."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# The maximum training epochs\n",
|
||||
"num_epochs = 5\n",
|
||||
"\n",
|
||||
"# Number of samples from parameter space\n",
|
||||
"num_samples = 10"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"If you have more resources available, you can modify the above parameters accordingly. e.g. more epochs, more parameter samples."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if SMOKE_TEST:\n",
|
||||
" num_epochs = 1\n",
|
||||
" num_samples = 3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"scheduler = ASHAScheduler(max_t=num_epochs, grace_period=1, reduction_factor=2)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Training with GPUs\n",
|
||||
"\n",
|
||||
"We can specify the number of resources, including GPUs, that Tune should request for each trial."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"train_fn_with_resources = tune.with_resources(train_func, resources={\"CPU\": 1, \"GPU\": 1})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"remove-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if SMOKE_TEST:\n",
|
||||
" train_fn_with_resources = tune.with_resources(train_func, resources={\"CPU\": 1})\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Putting it together\n",
|
||||
"\n",
|
||||
"Lastly, we need to create a `Tuner()` object and start Ray Tune with `tuner.fit()`. The full code looks like this:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_mnist_asha(num_samples=10):\n",
|
||||
" scheduler = ASHAScheduler(max_t=num_epochs, grace_period=1, reduction_factor=2)\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" train_fn_with_resources,\n",
|
||||
" param_space=search_space,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"ptl/val_accuracy\",\n",
|
||||
" mode=\"max\",\n",
|
||||
" num_samples=num_samples,\n",
|
||||
" scheduler=scheduler,\n",
|
||||
" ),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" checkpoint_config=tune.CheckpointConfig(\n",
|
||||
" num_to_keep=2,\n",
|
||||
" checkpoint_score_attribute=\"ptl/val_accuracy\",\n",
|
||||
" checkpoint_score_order=\"max\",\n",
|
||||
" ),\n",
|
||||
" ),\n",
|
||||
" )\n",
|
||||
" return tuner.fit()\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"results = tune_mnist_asha(num_samples=num_samples)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"Result(\n",
|
||||
" metrics={'ptl/train_loss': 0.001267582061700523, 'ptl/train_accuracy': 1.0, 'ptl/val_loss': 0.1036270260810852, 'ptl/val_accuracy': 0.9721123576164246},\n",
|
||||
" path='/home/ray/ray_results/train_func_2025-09-23_13-37-55/train_func_2f534_00006_6_batch_size=64,layer_1_size=64,layer_2_size=64,lr=0.0020_2025-09-23_13-37-55',\n",
|
||||
" filesystem='local',\n",
|
||||
" checkpoint=Checkpoint(filesystem=local, path=/home/ray/ray_results/train_func_2025-09-23_13-37-55/train_func_2f534_00006_6_batch_size=64,layer_1_size=64,layer_2_size=64,lr=0.0020_2025-09-23_13-37-55/checkpoint_000004)\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results.get_best_result(metric=\"ptl/val_accuracy\", mode=\"max\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In the example above, Tune runs 10 trials with different hyperparameter configurations.\n",
|
||||
"\n",
|
||||
"As you can see in the `training_iteration` column, trials with a high loss (and low accuracy) have been terminated early. The best performing trial used\n",
|
||||
"`batch_size=64`, `layer_1_size=128`, `layer_2_size=256`, and `lr=0.0037`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## More PyTorch Lightning Examples\n",
|
||||
"\n",
|
||||
"- For running distributed PyTorch Lightning training with Ray Train, see the {ref}`quickstart <train-pytorch-lightning>`.\n",
|
||||
"- {doc}`[Basic] Train a PyTorch Lightning Image Classifier with Ray Train <../../train/examples/lightning/lightning_mnist_example>`.\n",
|
||||
"- {doc}`[Intermediate] Fine-tune a BERT Text Classifier with PyTorch Lightning and Ray Train <../../train/examples/lightning/lightning_cola_advanced>`\n",
|
||||
"- {doc}`[Advanced] Fine-tune dolly-v2-7b with PyTorch Lightning and FSDP <../../train/examples/lightning/dolly_lightning_fsdp_finetuning>`\n",
|
||||
"- {doc}`/tune/examples/includes/mlflow_ptl_example`: Example for using [MLflow](https://github.com/mlflow/mlflow/)\n",
|
||||
" and [Pytorch Lightning](https://github.com/PyTorchLightning/pytorch-lightning) with Ray Tune.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.11"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -0,0 +1,845 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "aa6af4d3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Using PyTorch Lightning with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-vanilla-pytorch-lightning\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-vanilla-pytorch-lightning\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"(tune-vanilla-pytorch-lightning-ref)=\n",
|
||||
"\n",
|
||||
"PyTorch Lightning is a framework which brings structure into training PyTorch models. It\n",
|
||||
"aims to avoid boilerplate code, so you don't have to write the same training\n",
|
||||
"loops all over again when building a new model.\n",
|
||||
"\n",
|
||||
"```{image} /images/pytorch_lightning_full.png\n",
|
||||
":align: center\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"The main abstraction of PyTorch Lightning is the `LightningModule` class, which\n",
|
||||
"should be extended by your application. There is [a great post on how to transfer your models from vanilla PyTorch to Lightning](https://towardsdatascience.com/from-pytorch-to-pytorch-lightning-a-gentle-introduction-b371b7caaf09).\n",
|
||||
"\n",
|
||||
"The class structure of PyTorch Lightning makes it very easy to define and tune model\n",
|
||||
"parameters. This tutorial will show you how to use Tune to find the best set of\n",
|
||||
"parameters for your application on the example of training a MNIST classifier. Notably,\n",
|
||||
"the `LightningModule` does not have to be altered at all for this - so you can\n",
|
||||
"use it plug and play for your existing models, assuming their parameters are configurable!\n",
|
||||
"\n",
|
||||
":::{note}\n",
|
||||
"To run this example, you will need to install the following:\n",
|
||||
"\n",
|
||||
"```bash\n",
|
||||
"$ pip install \"ray[tune]\" torch torchvision lightning\n",
|
||||
"```\n",
|
||||
":::\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## PyTorch Lightning classifier for MNIST\n",
|
||||
"\n",
|
||||
"Let's first start with the basic PyTorch Lightning implementation of an MNIST classifier.\n",
|
||||
"This classifier does not include any tuning code at this point.\n",
|
||||
"\n",
|
||||
"Our example builds on the MNIST example from the [blog post we talked about\n",
|
||||
"earlier](https://towardsdatascience.com/from-pytorch-to-pytorch-lightning-a-gentle-introduction-b371b7caaf09).\n",
|
||||
"\n",
|
||||
"First, we run some imports:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "e6e77570",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import math\n",
|
||||
"\n",
|
||||
"import torch\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" import lightning.pytorch as pl\n",
|
||||
"except ModuleNotFoundError:\n",
|
||||
" import pytorch_lightning as pl\n",
|
||||
"\n",
|
||||
"from filelock import FileLock\n",
|
||||
"from torch.utils.data import DataLoader, random_split\n",
|
||||
"from torch.nn import functional as F\n",
|
||||
"from torchvision.datasets import MNIST\n",
|
||||
"from torchvision import transforms\n",
|
||||
"import os\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3c442e73",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"And then there is the Lightning model adapted from the blog post.\n",
|
||||
"Note that we left out the test set validation and made the model parameters\n",
|
||||
"configurable through a `config` dict that is passed on initialization.\n",
|
||||
"Also, we specify a `data_dir` where the MNIST data will be stored. Note that\n",
|
||||
"we use a `FileLock` for downloading data so that the dataset is only downloaded\n",
|
||||
"once per node.\n",
|
||||
"Lastly, we added a new metric, the validation accuracy, to the logs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "48b20f48",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class LightningMNISTClassifier(pl.LightningModule):\n",
|
||||
" \"\"\"\n",
|
||||
" This has been adapted from\n",
|
||||
" https://towardsdatascience.com/from-pytorch-to-pytorch-lightning-a-gentle-introduction-b371b7caaf09\n",
|
||||
" \"\"\"\n",
|
||||
"\n",
|
||||
" def __init__(self, config, data_dir=None):\n",
|
||||
" super(LightningMNISTClassifier, self).__init__()\n",
|
||||
"\n",
|
||||
" self.data_dir = data_dir or os.getcwd()\n",
|
||||
"\n",
|
||||
" self.layer_1_size = config[\"layer_1_size\"]\n",
|
||||
" self.layer_2_size = config[\"layer_2_size\"]\n",
|
||||
" self.lr = config[\"lr\"]\n",
|
||||
" self.batch_size = config[\"batch_size\"]\n",
|
||||
"\n",
|
||||
" # mnist images are (1, 28, 28) (channels, width, height)\n",
|
||||
" self.layer_1 = torch.nn.Linear(28 * 28, self.layer_1_size)\n",
|
||||
" self.layer_2 = torch.nn.Linear(self.layer_1_size, self.layer_2_size)\n",
|
||||
" self.layer_3 = torch.nn.Linear(self.layer_2_size, 10)\n",
|
||||
"\n",
|
||||
" def forward(self, x):\n",
|
||||
" batch_size, channels, width, height = x.size()\n",
|
||||
" x = x.view(batch_size, -1)\n",
|
||||
"\n",
|
||||
" x = self.layer_1(x)\n",
|
||||
" x = torch.relu(x)\n",
|
||||
"\n",
|
||||
" x = self.layer_2(x)\n",
|
||||
" x = torch.relu(x)\n",
|
||||
"\n",
|
||||
" x = self.layer_3(x)\n",
|
||||
" x = torch.log_softmax(x, dim=1)\n",
|
||||
"\n",
|
||||
" return x\n",
|
||||
"\n",
|
||||
" def cross_entropy_loss(self, logits, labels):\n",
|
||||
" return F.nll_loss(logits, labels)\n",
|
||||
"\n",
|
||||
" def accuracy(self, logits, labels):\n",
|
||||
" _, predicted = torch.max(logits.data, 1)\n",
|
||||
" correct = (predicted == labels).sum().item()\n",
|
||||
" accuracy = correct / len(labels)\n",
|
||||
" return torch.tensor(accuracy)\n",
|
||||
"\n",
|
||||
" def training_step(self, train_batch, batch_idx):\n",
|
||||
" x, y = train_batch\n",
|
||||
" logits = self.forward(x)\n",
|
||||
" loss = self.cross_entropy_loss(logits, y)\n",
|
||||
" accuracy = self.accuracy(logits, y)\n",
|
||||
"\n",
|
||||
" self.log(\"ptl/train_loss\", loss)\n",
|
||||
" self.log(\"ptl/train_accuracy\", accuracy)\n",
|
||||
" return loss\n",
|
||||
"\n",
|
||||
" def validation_step(self, val_batch, batch_idx):\n",
|
||||
" x, y = val_batch\n",
|
||||
" logits = self.forward(x)\n",
|
||||
" loss = self.cross_entropy_loss(logits, y)\n",
|
||||
" accuracy = self.accuracy(logits, y)\n",
|
||||
" return {\"val_loss\": loss, \"val_accuracy\": accuracy}\n",
|
||||
"\n",
|
||||
" def validation_epoch_end(self, outputs):\n",
|
||||
" avg_loss = torch.stack([x[\"val_loss\"] for x in outputs]).mean()\n",
|
||||
" avg_acc = torch.stack([x[\"val_accuracy\"] for x in outputs]).mean()\n",
|
||||
" self.log(\"ptl/val_loss\", avg_loss)\n",
|
||||
" self.log(\"ptl/val_accuracy\", avg_acc)\n",
|
||||
"\n",
|
||||
" @staticmethod\n",
|
||||
" def download_data(data_dir):\n",
|
||||
" transform = transforms.Compose(\n",
|
||||
" [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]\n",
|
||||
" )\n",
|
||||
" with FileLock(os.path.expanduser(\"~/.data.lock\")):\n",
|
||||
" return MNIST(data_dir, train=True, download=True, transform=transform)\n",
|
||||
"\n",
|
||||
" def prepare_data(self):\n",
|
||||
" mnist_train = self.download_data(self.data_dir)\n",
|
||||
"\n",
|
||||
" self.mnist_train, self.mnist_val = random_split(mnist_train, [55000, 5000])\n",
|
||||
"\n",
|
||||
" def train_dataloader(self):\n",
|
||||
" return DataLoader(self.mnist_train, batch_size=int(self.batch_size))\n",
|
||||
"\n",
|
||||
" def val_dataloader(self):\n",
|
||||
" return DataLoader(self.mnist_val, batch_size=int(self.batch_size))\n",
|
||||
"\n",
|
||||
" def configure_optimizers(self):\n",
|
||||
" optimizer = torch.optim.Adam(self.parameters(), lr=self.lr)\n",
|
||||
" return optimizer\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_mnist(config):\n",
|
||||
" model = LightningMNISTClassifier(config)\n",
|
||||
" trainer = pl.Trainer(max_epochs=10, enable_progress_bar=False)\n",
|
||||
"\n",
|
||||
" trainer.fit(model)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "da1c3632",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"And that's it! You can now run `train_mnist(config)` to train the classifier, e.g.\n",
|
||||
"like so:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "86df3d39",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_mnist_no_tune():\n",
|
||||
" config = {\"layer_1_size\": 128, \"layer_2_size\": 256, \"lr\": 1e-3, \"batch_size\": 64}\n",
|
||||
" train_mnist(config)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "edcc0991",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Tuning the model parameters\n",
|
||||
"\n",
|
||||
"The parameters above should give you a good accuracy of over 90% already. However,\n",
|
||||
"we might improve on this simply by changing some of the hyperparameters. For instance,\n",
|
||||
"maybe we get an even higher accuracy if we used a larger batch size.\n",
|
||||
"\n",
|
||||
"Instead of guessing the parameter values, let's use Tune to systematically try out\n",
|
||||
"parameter combinations and find the best performing set.\n",
|
||||
"\n",
|
||||
"First, we need some additional imports:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "34faeb3b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"try:\n",
|
||||
" from lightning.pytorch.loggers import TensorBoardLogger\n",
|
||||
"except ModuleNotFoundError:\n",
|
||||
" from pytorch_lightning.loggers import TensorBoardLogger\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune import CLIReporter\n",
|
||||
"from ray.tune.schedulers import ASHAScheduler, PopulationBasedTraining\n",
|
||||
"from ray.tune.integration.pytorch_lightning import (\n",
|
||||
" TuneReportCallback,\n",
|
||||
" TuneReportCheckpointCallback,\n",
|
||||
")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f65b9c5f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Talking to Tune with a PyTorch Lightning callback\n",
|
||||
"\n",
|
||||
"PyTorch Lightning introduced [Callbacks](https://pytorch-lightning.readthedocs.io/en/latest/extensions/callbacks.html)\n",
|
||||
"that can be used to plug custom functions into the training loop. This way the original\n",
|
||||
"`LightningModule` does not have to be altered at all. Also, we could use the same\n",
|
||||
"callback for multiple modules.\n",
|
||||
"\n",
|
||||
"Ray Tune comes with ready-to-use PyTorch Lightning callbacks. To report metrics\n",
|
||||
"back to Tune after each validation epoch, we will use the `TuneReportCallback`:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "4bab80bc",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<ray.tune.integration.pytorch_lightning.TuneReportCallback at 0x17b305710>"
|
||||
]
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"TuneReportCallback(\n",
|
||||
" {\"loss\": \"ptl/val_loss\", \"mean_accuracy\": \"ptl/val_accuracy\"}, on=\"validation_end\"\n",
|
||||
")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "286a1070",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This callback will take the `val_loss` and `val_accuracy` values\n",
|
||||
"from the PyTorch Lightning trainer and report them to Tune as the `loss`\n",
|
||||
"and `mean_accuracy`, respectively.\n",
|
||||
"\n",
|
||||
"### Adding the Tune training function\n",
|
||||
"\n",
|
||||
"Then we specify our training function. Note that we added the `data_dir` as a\n",
|
||||
"parameter here to avoid\n",
|
||||
"that each training run downloads the full MNIST dataset. Instead, we want to access\n",
|
||||
"a shared data location.\n",
|
||||
"\n",
|
||||
"We are also able to specify the number of epochs to train each model, and the number\n",
|
||||
"of GPUs we want to use for training. We also create a TensorBoard logger that writes\n",
|
||||
"logfiles directly into Tune's root trial directory - if we didn't do that PyTorch\n",
|
||||
"Lightning would create subdirectories, and each trial would thus be shown twice in\n",
|
||||
"TensorBoard, one time for Tune's logs, and another time for PyTorch Lightning's logs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "74e7d1c2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_mnist_tune(config, num_epochs=10, num_gpus=0, data_dir=\"~/data\"):\n",
|
||||
" data_dir = os.path.expanduser(data_dir)\n",
|
||||
" model = LightningMNISTClassifier(config, data_dir)\n",
|
||||
" trainer = pl.Trainer(\n",
|
||||
" max_epochs=num_epochs,\n",
|
||||
" # If fractional GPUs passed in, convert to int.\n",
|
||||
" gpus=math.ceil(num_gpus),\n",
|
||||
" logger=TensorBoardLogger(save_dir=os.getcwd(), name=\"\", version=\".\"),\n",
|
||||
" enable_progress_bar=False,\n",
|
||||
" callbacks=[\n",
|
||||
" TuneReportCallback(\n",
|
||||
" {\"loss\": \"ptl/val_loss\", \"mean_accuracy\": \"ptl/val_accuracy\"},\n",
|
||||
" on=\"validation_end\",\n",
|
||||
" )\n",
|
||||
" ],\n",
|
||||
" )\n",
|
||||
" trainer.fit(model)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cf0f6d6e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Configuring the search space\n",
|
||||
"\n",
|
||||
"Now we configure the parameter search space. We would like to choose between three\n",
|
||||
"different layer and batch sizes. The learning rate should be sampled uniformly between\n",
|
||||
"`0.0001` and `0.1`. The `tune.loguniform()` function is syntactic sugar to make\n",
|
||||
"sampling between these different orders of magnitude easier, specifically\n",
|
||||
"we are able to also sample small values."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "a50645e9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"config = {\n",
|
||||
" \"layer_1_size\": tune.choice([32, 64, 128]),\n",
|
||||
" \"layer_2_size\": tune.choice([64, 128, 256]),\n",
|
||||
" \"lr\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
" \"batch_size\": tune.choice([32, 64, 128]),\n",
|
||||
"}\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b1fb9ecd",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Selecting a scheduler\n",
|
||||
"\n",
|
||||
"In this example, we use an [Asynchronous Hyperband](https://blog.ml.cmu.edu/2018/12/12/massively-parallel-hyperparameter-optimization/)\n",
|
||||
"scheduler. This scheduler decides at each iteration which trials are likely to perform\n",
|
||||
"badly, and stops these trials. This way we don't waste any resources on bad hyperparameter\n",
|
||||
"configurations."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "a2596b01",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"num_epochs = 10\n",
|
||||
"\n",
|
||||
"scheduler = ASHAScheduler(max_t=num_epochs, grace_period=1, reduction_factor=2)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9a49ae58",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Changing the CLI output\n",
|
||||
"\n",
|
||||
"We instantiate a `CLIReporter` to specify which metrics we would like to see in our\n",
|
||||
"output tables in the command line. This is optional, but can be used to make sure our\n",
|
||||
"output tables only include information we would like to see."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "cd605a16",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reporter = CLIReporter(\n",
|
||||
" parameter_columns=[\"layer_1_size\", \"layer_2_size\", \"lr\", \"batch_size\"],\n",
|
||||
" metric_columns=[\"loss\", \"mean_accuracy\", \"training_iteration\"],\n",
|
||||
")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5ec9a305",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Passing constants to the train function\n",
|
||||
"\n",
|
||||
"The `data_dir`, `num_epochs` and `num_gpus` we pass to the training function\n",
|
||||
"are constants. To avoid including them as non-configurable parameters in the `config`\n",
|
||||
"specification, we can use `tune.with_parameters` to wrap around the training function."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "332668dc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"gpus_per_trial = 0\n",
|
||||
"data_dir = \"~/data\"\n",
|
||||
"\n",
|
||||
"train_fn_with_parameters = tune.with_parameters(\n",
|
||||
" train_mnist_tune, num_epochs=num_epochs, num_gpus=gpus_per_trial, data_dir=data_dir\n",
|
||||
")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "feef8c39",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Training with GPUs\n",
|
||||
"\n",
|
||||
"We can specify how many resources Tune should request for each trial.\n",
|
||||
"This also includes GPUs.\n",
|
||||
"\n",
|
||||
"PyTorch Lightning takes care of moving the training to the GPUs. We\n",
|
||||
"already made sure that our code is compatible with that, so there's\n",
|
||||
"nothing more to do here other than to specify the number of GPUs\n",
|
||||
"we would like to use:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "dc402716",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"resources_per_trial = {\"cpu\": 1, \"gpu\": gpus_per_trial}\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ca050dfa",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can also specify {ref}`fractional GPUs for Tune <tune-parallelism>`,\n",
|
||||
"allowing multiple trials to share GPUs and thus increase concurrency under resource constraints.\n",
|
||||
"While the `gpus_per_trial` passed into\n",
|
||||
"Tune is a decimal value, the `gpus` passed into the `pl.Trainer` should still be an integer.\n",
|
||||
"Please note that if using fractional GPUs, it is the user's responsibility to\n",
|
||||
"make sure multiple trials can share GPUs and there is enough memory to do so.\n",
|
||||
"Ray does not automatically handle this for you.\n",
|
||||
"\n",
|
||||
"If you want to use multiple GPUs per trial, you should check out {ref}`Getting Start with Lightning and Ray TorchTrainer <train-pytorch-lightning>`.\n",
|
||||
"\n",
|
||||
"### Putting it together\n",
|
||||
"\n",
|
||||
"Lastly, we need to create a `Tuner()` object and start Ray Tune with `tuner.fit()`.\n",
|
||||
"\n",
|
||||
"The full code looks like this:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "ea182330",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_mnist_asha(num_samples=10, num_epochs=10, gpus_per_trial=0, data_dir=\"~/data\"):\n",
|
||||
" config = {\n",
|
||||
" \"layer_1_size\": tune.choice([32, 64, 128]),\n",
|
||||
" \"layer_2_size\": tune.choice([64, 128, 256]),\n",
|
||||
" \"lr\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
" \"batch_size\": tune.choice([32, 64, 128]),\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" scheduler = ASHAScheduler(max_t=num_epochs, grace_period=1, reduction_factor=2)\n",
|
||||
"\n",
|
||||
" reporter = CLIReporter(\n",
|
||||
" parameter_columns=[\"layer_1_size\", \"layer_2_size\", \"lr\", \"batch_size\"],\n",
|
||||
" metric_columns=[\"loss\", \"mean_accuracy\", \"training_iteration\"],\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" train_fn_with_parameters = tune.with_parameters(\n",
|
||||
" train_mnist_tune,\n",
|
||||
" num_epochs=num_epochs,\n",
|
||||
" num_gpus=gpus_per_trial,\n",
|
||||
" data_dir=data_dir,\n",
|
||||
" )\n",
|
||||
" resources_per_trial = {\"cpu\": 1, \"gpu\": gpus_per_trial}\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" tune.with_resources(train_fn_with_parameters, resources=resources_per_trial),\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" scheduler=scheduler,\n",
|
||||
" num_samples=num_samples,\n",
|
||||
" ),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" name=\"tune_mnist_asha\",\n",
|
||||
" progress_reporter=reporter,\n",
|
||||
" ),\n",
|
||||
" param_space=config,\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n",
|
||||
"\n",
|
||||
" print(\"Best hyperparameters found were: \", results.get_best_result().config)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1fb96b6c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In the example above, Tune runs 10 trials with different hyperparameter configurations.\n",
|
||||
"An example output could look like so:\n",
|
||||
"\n",
|
||||
"```{code-block} bash\n",
|
||||
":emphasize-lines: 12\n",
|
||||
"\n",
|
||||
" +------------------------------+------------+-------+----------------+----------------+-------------+--------------+----------+-----------------+----------------------+\n",
|
||||
" | Trial name | status | loc | layer_1_size | layer_2_size | lr | batch_size | loss | mean_accuracy | training_iteration |\n",
|
||||
" |------------------------------+------------+-------+----------------+----------------+-------------+--------------+----------+-----------------+----------------------|\n",
|
||||
" | train_mnist_tune_63ecc_00000 | TERMINATED | | 128 | 64 | 0.00121197 | 128 | 0.120173 | 0.972461 | 10 |\n",
|
||||
" | train_mnist_tune_63ecc_00001 | TERMINATED | | 64 | 128 | 0.0301395 | 128 | 0.454836 | 0.868164 | 4 |\n",
|
||||
" | train_mnist_tune_63ecc_00002 | TERMINATED | | 64 | 128 | 0.0432097 | 128 | 0.718396 | 0.718359 | 1 |\n",
|
||||
" | train_mnist_tune_63ecc_00003 | TERMINATED | | 32 | 128 | 0.000294669 | 32 | 0.111475 | 0.965764 | 10 |\n",
|
||||
" | train_mnist_tune_63ecc_00004 | TERMINATED | | 32 | 256 | 0.000386664 | 64 | 0.133538 | 0.960839 | 8 |\n",
|
||||
" | train_mnist_tune_63ecc_00005 | TERMINATED | | 128 | 128 | 0.0837395 | 32 | 2.32628 | 0.0991242 | 1 |\n",
|
||||
" | train_mnist_tune_63ecc_00006 | TERMINATED | | 64 | 128 | 0.000158761 | 128 | 0.134595 | 0.959766 | 10 |\n",
|
||||
" | train_mnist_tune_63ecc_00007 | TERMINATED | | 64 | 64 | 0.000672126 | 64 | 0.118182 | 0.972903 | 10 |\n",
|
||||
" | train_mnist_tune_63ecc_00008 | TERMINATED | | 128 | 64 | 0.000502428 | 32 | 0.11082 | 0.975518 | 10 |\n",
|
||||
" | train_mnist_tune_63ecc_00009 | TERMINATED | | 64 | 256 | 0.00112894 | 32 | 0.13472 | 0.971935 | 8 |\n",
|
||||
" +------------------------------+------------+-------+----------------+----------------+-------------+--------------+----------+-----------------+----------------------+\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"As you can see in the `training_iteration` column, trials with a high loss\n",
|
||||
"(and low accuracy) have been terminated early. The best performing trial used\n",
|
||||
"`layer_1_size=128`, `layer_2_size=64`, `lr=0.000502428` and\n",
|
||||
"`batch_size=32`.\n",
|
||||
"\n",
|
||||
"## Using Population Based Training to find the best parameters\n",
|
||||
"\n",
|
||||
"The `ASHAScheduler` terminates those trials early that show bad performance.\n",
|
||||
"Sometimes, this stops trials that would get better after more training steps,\n",
|
||||
"and which might eventually even show better performance than other configurations.\n",
|
||||
"\n",
|
||||
"Another popular method for hyperparameter tuning, called\n",
|
||||
"[Population Based Training](https://deepmind.com/blog/article/population-based-training-neural-networks),\n",
|
||||
"instead perturbs hyperparameters during the training run. Tune implements PBT, and\n",
|
||||
"we only need to make some slight adjustments to our code.\n",
|
||||
"\n",
|
||||
"### Adding checkpoints to the PyTorch Lightning module\n",
|
||||
"\n",
|
||||
"First, we need to introduce\n",
|
||||
"another callback to save model checkpoints. Since Tune requires a call to\n",
|
||||
"`tune.report()` after creating a new checkpoint to register it, we will use\n",
|
||||
"a combined reporting and checkpointing callback:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "7f86e4d8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<ray.tune.integration.pytorch_lightning.TuneReportCheckpointCallback at 0x17a626090>"
|
||||
]
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"TuneReportCheckpointCallback(\n",
|
||||
" metrics={\"loss\": \"ptl/val_loss\", \"mean_accuracy\": \"ptl/val_accuracy\"},\n",
|
||||
" filename=\"checkpoint\",\n",
|
||||
" on=\"validation_end\",\n",
|
||||
")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "33a76d5b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The `checkpoint` value is the name of the checkpoint file within the\n",
|
||||
"checkpoint directory.\n",
|
||||
"\n",
|
||||
"We also include checkpoint loading in our training function:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "746e962a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_mnist_tune_checkpoint(config, num_epochs=10, num_gpus=0, data_dir=\"~/data\"):\n",
|
||||
" data_dir = os.path.expanduser(data_dir)\n",
|
||||
" kwargs = {\n",
|
||||
" \"max_epochs\": num_epochs,\n",
|
||||
" # If fractional GPUs passed in, convert to int.\n",
|
||||
" \"gpus\": math.ceil(num_gpus),\n",
|
||||
" \"logger\": TensorBoardLogger(save_dir=os.getcwd(), name=\"\", version=\".\"),\n",
|
||||
" \"enable_progress_bar\": False,\n",
|
||||
" \"callbacks\": [\n",
|
||||
" TuneReportCheckpointCallback(\n",
|
||||
" metrics={\"loss\": \"ptl/val_loss\", \"mean_accuracy\": \"ptl/val_accuracy\"},\n",
|
||||
" filename=\"checkpoint\",\n",
|
||||
" on=\"validation_end\",\n",
|
||||
" )\n",
|
||||
" ],\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" checkpoint = tune.get_checkpoint()\n",
|
||||
" if checkpoint:\n",
|
||||
" with checkpoint.as_directory() as checkpoint_dir:\n",
|
||||
" kwargs[\"resume_from_checkpoint\"] = os.path.join(checkpoint_dir, \"checkpoint\")\n",
|
||||
"\n",
|
||||
" model = LightningMNISTClassifier(config=config, data_dir=data_dir)\n",
|
||||
" trainer = pl.Trainer(**kwargs)\n",
|
||||
"\n",
|
||||
" trainer.fit(model)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "39dc7b46",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Configuring and running Population Based Training\n",
|
||||
"\n",
|
||||
"We need to call Tune slightly differently:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "e12a1bd5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_mnist_pbt(num_samples=10, num_epochs=10, gpus_per_trial=0, data_dir=\"~/data\"):\n",
|
||||
" config = {\n",
|
||||
" \"layer_1_size\": tune.choice([32, 64, 128]),\n",
|
||||
" \"layer_2_size\": tune.choice([64, 128, 256]),\n",
|
||||
" \"lr\": 1e-3,\n",
|
||||
" \"batch_size\": 64,\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" scheduler = PopulationBasedTraining(\n",
|
||||
" perturbation_interval=4,\n",
|
||||
" hyperparam_mutations={\n",
|
||||
" \"lr\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
" \"batch_size\": [32, 64, 128],\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" reporter = CLIReporter(\n",
|
||||
" parameter_columns=[\"layer_1_size\", \"layer_2_size\", \"lr\", \"batch_size\"],\n",
|
||||
" metric_columns=[\"loss\", \"mean_accuracy\", \"training_iteration\"],\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" tune.with_resources(\n",
|
||||
" tune.with_parameters(\n",
|
||||
" train_mnist_tune_checkpoint,\n",
|
||||
" num_epochs=num_epochs,\n",
|
||||
" num_gpus=gpus_per_trial,\n",
|
||||
" data_dir=data_dir,\n",
|
||||
" ),\n",
|
||||
" resources={\"cpu\": 1, \"gpu\": gpus_per_trial},\n",
|
||||
" ),\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" scheduler=scheduler,\n",
|
||||
" num_samples=num_samples,\n",
|
||||
" ),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" name=\"tune_mnist_asha\",\n",
|
||||
" progress_reporter=reporter,\n",
|
||||
" ),\n",
|
||||
" param_space=config,\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n",
|
||||
"\n",
|
||||
" print(\"Best hyperparameters found were: \", results.get_best_result().config)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6087f807",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Instead of passing tune parameters to the `config` dict, we start\n",
|
||||
"with fixed values, though we are also able to sample some of them, like the\n",
|
||||
"layer sizes. Additionally, we have to tell PBT how to perturb the hyperparameters.\n",
|
||||
"Note that the layer sizes are not tuned right here. This is because we cannot simply\n",
|
||||
"change layer sizes during a training run - which is what would happen in PBT.\n",
|
||||
"\n",
|
||||
"To test running both of our main scripts (`tune_mnist_asha` and `tune_mnist_pbt`), all you have to do is specify\n",
|
||||
"a `data_dir` folder and run the scripts with reasonable parameters:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "eb9faf3e",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data_dir = \"~/data/\"\n",
|
||||
"\n",
|
||||
"tune_mnist_asha(num_samples=1, num_epochs=6, gpus_per_trial=0, data_dir=data_dir)\n",
|
||||
"tune_mnist_pbt(num_samples=1, num_epochs=6, gpus_per_trial=0, data_dir=data_dir)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3ae0eea6",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"If you have more resources available (e.g. a GPU), you can modify the above parameters accordingly.\n",
|
||||
"\n",
|
||||
"An example output of a run could look like this:\n",
|
||||
"\n",
|
||||
"```bash\n",
|
||||
"+-----------------------------------------+------------+-------+----------------+----------------+-----------+--------------+-----------+-----------------+----------------------+\n",
|
||||
"| Trial name | status | loc | layer_1_size | layer_2_size | lr | batch_size | loss | mean_accuracy | training_iteration |\n",
|
||||
"|-----------------------------------------+------------+-------+----------------+----------------+-----------+--------------+-----------+-----------------+----------------------|\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00000 | TERMINATED | | 128 | 128 | 0.001 | 64 | 0.108734 | 0.973101 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00001 | TERMINATED | | 128 | 128 | 0.001 | 64 | 0.093577 | 0.978639 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00002 | TERMINATED | | 128 | 256 | 0.0008 | 32 | 0.0922348 | 0.979299 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00003 | TERMINATED | | 64 | 256 | 0.001 | 64 | 0.124648 | 0.973892 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00004 | TERMINATED | | 128 | 64 | 0.001 | 64 | 0.101717 | 0.975079 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00005 | TERMINATED | | 64 | 64 | 0.001 | 64 | 0.121467 | 0.969146 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00006 | TERMINATED | | 128 | 256 | 0.00064 | 32 | 0.053446 | 0.987062 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00007 | TERMINATED | | 128 | 256 | 0.001 | 64 | 0.129804 | 0.973497 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00008 | TERMINATED | | 64 | 256 | 0.0285125 | 128 | 0.363236 | 0.913867 | 10 |\n",
|
||||
"| train_mnist_tune_checkpoint_85489_00009 | TERMINATED | | 32 | 256 | 0.001 | 64 | 0.150946 | 0.964201 | 10 |\n",
|
||||
"+-----------------------------------------+------------+-------+----------------+----------------+-----------+--------------+-----------+-----------------+----------------------+\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"As you can see, each sample ran the full number of 10 iterations.\n",
|
||||
"All trials ended with quite good parameter combinations and showed relatively good performances.\n",
|
||||
"In some runs, the parameters have been perturbed. And the best configuration even reached a\n",
|
||||
"mean validation accuracy of `0.987062`!\n",
|
||||
"\n",
|
||||
"In summary, PyTorch Lightning Modules are easy to extend to use with Tune. It just took\n",
|
||||
"us importing one or two callbacks and a small wrapper function to get great performing\n",
|
||||
"parameter configurations.\n",
|
||||
"\n",
|
||||
"## More PyTorch Lightning Examples\n",
|
||||
"\n",
|
||||
"- {doc}`/tune/examples/includes/mnist_ptl_mini`:\n",
|
||||
" A minimal example of using [Pytorch Lightning](https://github.com/PyTorchLightning/pytorch-lightning)\n",
|
||||
" to train a MNIST model. This example utilizes the Ray Tune-provided\n",
|
||||
" {ref}`PyTorch Lightning callbacks <tune-integration-pytorch-lightning>`.\n",
|
||||
" See also {ref}`this tutorial for a full walkthrough <tune-pytorch-lightning-ref>`.\n",
|
||||
"- {ref}`A walkthrough tutorial for using Ray Tune with Pytorch-Lightning <tune-pytorch-lightning-ref>`.\n",
|
||||
"- {doc}`/tune/examples/includes/mlflow_ptl_example`: Example for using [MLflow](https://github.com/mlflow/mlflow/)\n",
|
||||
" and [Pytorch Lightning](https://github.com/PyTorchLightning/pytorch-lightning) with Ray Tune."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.16"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,790 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ecad719c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Using Weights & Biases with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-wandb\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-wandb\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"(tune-wandb-ref)=\n",
|
||||
"\n",
|
||||
"[Weights & Biases](https://www.wandb.ai/) (Wandb) is a tool for experiment\n",
|
||||
"tracking, model optimizaton, and dataset versioning. It is very popular\n",
|
||||
"in the machine learning and data science community for its superb visualization\n",
|
||||
"tools.\n",
|
||||
"\n",
|
||||
"```{image} /images/wandb_logo_full.png\n",
|
||||
":align: center\n",
|
||||
":alt: Weights & Biases\n",
|
||||
":height: 80px\n",
|
||||
":target: https://www.wandb.ai/\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Ray Tune currently offers two lightweight integrations for Weights & Biases.\n",
|
||||
"One is the {ref}`WandbLoggerCallback <air-wandb-logger>`, which automatically logs\n",
|
||||
"metrics reported to Tune to the Wandb API.\n",
|
||||
"\n",
|
||||
"The other one is the {ref}`setup_wandb() <air-wandb-setup>` function, which can be\n",
|
||||
"used with the function API. It automatically\n",
|
||||
"initializes the Wandb API with Tune's training information. You can just use the\n",
|
||||
"Wandb API like you would normally do, e.g. using `wandb.log()` to log your training\n",
|
||||
"process.\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## Running A Weights & Biases Example\n",
|
||||
"\n",
|
||||
"In the following example we're going to use both of the above methods, namely the `WandbLoggerCallback` and\n",
|
||||
"the `setup_wandb` function to log metrics.\n",
|
||||
"\n",
|
||||
"As the very first step, make sure you're logged in into wandb on all machines you're running your training on:\n",
|
||||
"\n",
|
||||
" wandb login\n",
|
||||
"\n",
|
||||
"We can then start with a few crucial imports:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "100bcf8a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"import ray\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.air.integrations.wandb import WandbLoggerCallback, setup_wandb\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "9346c0f6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next, let's define an easy `train_function` function (a Tune `Trainable`) that reports a random loss to Tune.\n",
|
||||
"The objective function itself is not important for this example, since we want to focus on the Weights & Biases\n",
|
||||
"integration primarily."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "e8b4fc4d",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_function(config):\n",
|
||||
" for i in range(30):\n",
|
||||
" loss = config[\"mean\"] + config[\"sd\"] * np.random.randn()\n",
|
||||
" tune.report({\"loss\": loss})\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "831eed42",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can define a\n",
|
||||
"simple grid-search Tune run using the `WandbLoggerCallback` as follows:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "52988599",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_with_callback():\n",
|
||||
" \"\"\"Example for using a WandbLoggerCallback with the function API\"\"\"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" train_function,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" ),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" callbacks=[WandbLoggerCallback(project=\"Wandb_example\")]\n",
|
||||
" ),\n",
|
||||
" param_space={\n",
|
||||
" \"mean\": tune.grid_search([1, 2, 3, 4, 5]),\n",
|
||||
" \"sd\": tune.uniform(0.2, 0.8),\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
" tuner.fit()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "e24c05fa",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To use the `setup_wandb` utility, you simply call this function in your objective.\n",
|
||||
"Note that we also use `wandb.log(...)` to log the `loss` to Weights & Biases as a dictionary.\n",
|
||||
"Otherwise, this version of our objective is identical to its original."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "5e30d5e7",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def train_function_wandb(config):\n",
|
||||
" wandb = setup_wandb(config, project=\"Wandb_example\")\n",
|
||||
"\n",
|
||||
" for i in range(30):\n",
|
||||
" loss = config[\"mean\"] + config[\"sd\"] * np.random.randn()\n",
|
||||
" tune.report({\"loss\": loss})\n",
|
||||
" wandb.log(dict(loss=loss))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "04040bcb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"With the `train_function_wandb` defined, your Tune experiment will set up `wandb` in each trial once it starts!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "d4fbd368",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_with_setup():\n",
|
||||
" \"\"\"Example for using the setup_wandb utility with the function API\"\"\"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" train_function_wandb,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" ),\n",
|
||||
" param_space={\n",
|
||||
" \"mean\": tune.grid_search([1, 2, 3, 4, 5]),\n",
|
||||
" \"sd\": tune.uniform(0.2, 0.8),\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
" tuner.fit()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "f9521481",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Finally, you can also define a class-based Tune `Trainable` by using the `setup_wandb` in the `setup()` method and storing the run object as an attribute. Please note that with the class trainable, you have to pass the trial id, name, and group separately:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "d27a7a35",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class WandbTrainable(tune.Trainable):\n",
|
||||
" def setup(self, config):\n",
|
||||
" self.wandb = setup_wandb(\n",
|
||||
" config,\n",
|
||||
" trial_id=self.trial_id,\n",
|
||||
" trial_name=self.trial_name,\n",
|
||||
" group=\"Example\",\n",
|
||||
" project=\"Wandb_example\",\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" def step(self):\n",
|
||||
" for i in range(30):\n",
|
||||
" loss = self.config[\"mean\"] + self.config[\"sd\"] * np.random.randn()\n",
|
||||
" self.wandb.log({\"loss\": loss})\n",
|
||||
" return {\"loss\": loss, \"done\": True}\n",
|
||||
"\n",
|
||||
" def save_checkpoint(self, checkpoint_dir: str):\n",
|
||||
" pass\n",
|
||||
"\n",
|
||||
" def load_checkpoint(self, checkpoint_dir: str):\n",
|
||||
" pass\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "fa189bb2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Running Tune with this `WandbTrainable` works exactly the same as with the function API.\n",
|
||||
"The below `tune_trainable` function differs from `tune_decorated` above only in the first argument we pass to\n",
|
||||
"`Tuner()`:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "6e546cc2",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tune_trainable():\n",
|
||||
" \"\"\"Example for using a WandTrainableMixin with the class API\"\"\"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" WandbTrainable,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"loss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" ),\n",
|
||||
" param_space={\n",
|
||||
" \"mean\": tune.grid_search([1, 2, 3, 4, 5]),\n",
|
||||
" \"sd\": tune.uniform(0.2, 0.8),\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n",
|
||||
"\n",
|
||||
" return results.get_best_result().config\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "0b736172",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Since you may not have an API key for Wandb, we can _mock_ the Wandb logger and test all three of our training\n",
|
||||
"functions as follows.\n",
|
||||
"If you are logged in into wandb, you can set `mock_api = False` to actually upload your results to Weights & Biases."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "e0e7f481",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2022-11-02 16:02:45,355\tINFO worker.py:1534 -- Started a local Ray instance. View the dashboard at \u001b[1m\u001b[32mhttp://127.0.0.1:8266 \u001b[39m\u001b[22m\n",
|
||||
"2022-11-02 16:02:46,513\tINFO wandb.py:282 -- Already logged into W&B.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2022-11-02 16:03:13</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:27.28 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>10.8/16.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Resources requested: 0/16 CPUs, 0/0 GPUs, 0.0/3.44 GiB heap, 0.0/1.72 GiB objects\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> mean</th><th style=\"text-align: right;\"> sd</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> loss</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_7676d_00000</td><td>TERMINATED</td><td>127.0.0.1:14578</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">0.411212</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 0.236137</td><td style=\"text-align: right;\">0.828527</td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00001</td><td>TERMINATED</td><td>127.0.0.1:14591</td><td style=\"text-align: right;\"> 2</td><td style=\"text-align: right;\">0.756339</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 5.57185 </td><td style=\"text-align: right;\">3.13156 </td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00002</td><td>TERMINATED</td><td>127.0.0.1:14593</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\">0.436643</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 5.50237 </td><td style=\"text-align: right;\">3.26679 </td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00003</td><td>TERMINATED</td><td>127.0.0.1:14595</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\">0.295929</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 5.60986 </td><td style=\"text-align: right;\">3.70388 </td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00004</td><td>TERMINATED</td><td>127.0.0.1:14596</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\">0.335292</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 5.61385 </td><td style=\"text-align: right;\">4.74294 </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"trialProgress\">\n",
|
||||
" <h3>Trial Progress</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>date </th><th>done </th><th>episodes_total </th><th>experiment_id </th><th>experiment_tag </th><th>hostname </th><th style=\"text-align: right;\"> iterations_since_restore</th><th style=\"text-align: right;\"> loss</th><th>node_ip </th><th style=\"text-align: right;\"> pid</th><th style=\"text-align: right;\"> time_since_restore</th><th style=\"text-align: right;\"> time_this_iter_s</th><th style=\"text-align: right;\"> time_total_s</th><th style=\"text-align: right;\"> timestamp</th><th style=\"text-align: right;\"> timesteps_since_restore</th><th>timesteps_total </th><th style=\"text-align: right;\"> training_iteration</th><th>trial_id </th><th style=\"text-align: right;\"> warmup_time</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_7676d_00000</td><td>2022-11-02_16-02-53</td><td>True </td><td> </td><td>a9f242fa70184d9dadd8952b16fb0ecc</td><td>0_mean=1,sd=0.4112</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">0.828527</td><td>127.0.0.1</td><td style=\"text-align: right;\">14578</td><td style=\"text-align: right;\"> 0.236137</td><td style=\"text-align: right;\"> 0.00381589</td><td style=\"text-align: right;\"> 0.236137</td><td style=\"text-align: right;\"> 1667430173</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>7676d_00000</td><td style=\"text-align: right;\"> 0.00366998</td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00001</td><td>2022-11-02_16-03-03</td><td>True </td><td> </td><td>f57118365bcb4c229fe41c5911f05ad6</td><td>1_mean=2,sd=0.7563</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">3.13156 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14591</td><td style=\"text-align: right;\"> 5.57185 </td><td style=\"text-align: right;\"> 0.00627518</td><td style=\"text-align: right;\"> 5.57185 </td><td style=\"text-align: right;\"> 1667430183</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>7676d_00001</td><td style=\"text-align: right;\"> 0.0027349 </td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00002</td><td>2022-11-02_16-03-03</td><td>True </td><td> </td><td>394021d4515d4616bae7126668f73b2b</td><td>2_mean=3,sd=0.4366</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">3.26679 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14593</td><td style=\"text-align: right;\"> 5.50237 </td><td style=\"text-align: right;\"> 0.00494576</td><td style=\"text-align: right;\"> 5.50237 </td><td style=\"text-align: right;\"> 1667430183</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>7676d_00002</td><td style=\"text-align: right;\"> 0.00286222</td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00003</td><td>2022-11-02_16-03-03</td><td>True </td><td> </td><td>a575e79c9d95485fa37deaa86267aea4</td><td>3_mean=4,sd=0.2959</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">3.70388 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14595</td><td style=\"text-align: right;\"> 5.60986 </td><td style=\"text-align: right;\"> 0.00689816</td><td style=\"text-align: right;\"> 5.60986 </td><td style=\"text-align: right;\"> 1667430183</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>7676d_00003</td><td style=\"text-align: right;\"> 0.00299597</td></tr>\n",
|
||||
"<tr><td>train_function_7676d_00004</td><td>2022-11-02_16-03-03</td><td>True </td><td> </td><td>91ce57dcdbb54536b1874666b711350d</td><td>4_mean=5,sd=0.3353</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">4.74294 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14596</td><td style=\"text-align: right;\"> 5.61385 </td><td style=\"text-align: right;\"> 0.00672579</td><td style=\"text-align: right;\"> 5.61385 </td><td style=\"text-align: right;\"> 1667430183</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>7676d_00004</td><td style=\"text-align: right;\"> 0.00323987</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".trialProgress {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".trialProgress h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".trialProgress td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2022-11-02 16:03:13,913\tINFO tune.py:788 -- Total run time: 28.53 seconds (27.28 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2022-11-02 16:03:22</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:08.49 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>9.9/16.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Resources requested: 0/16 CPUs, 0/0 GPUs, 0.0/3.44 GiB heap, 0.0/1.72 GiB objects\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> mean</th><th style=\"text-align: right;\"> sd</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> loss</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00000</td><td>TERMINATED</td><td>127.0.0.1:14647</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">0.738281</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 1.61319</td><td style=\"text-align: right;\">0.555153</td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00001</td><td>TERMINATED</td><td>127.0.0.1:14660</td><td style=\"text-align: right;\"> 2</td><td style=\"text-align: right;\">0.321178</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 1.72447</td><td style=\"text-align: right;\">2.52109 </td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00002</td><td>TERMINATED</td><td>127.0.0.1:14661</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\">0.202487</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 1.8159 </td><td style=\"text-align: right;\">2.45412 </td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00003</td><td>TERMINATED</td><td>127.0.0.1:14662</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\">0.515434</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 1.715 </td><td style=\"text-align: right;\">4.51413 </td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00004</td><td>TERMINATED</td><td>127.0.0.1:14663</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\">0.216098</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\"> 1.72827</td><td style=\"text-align: right;\">5.2814 </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[2m\u001b[36m(train_function_wandb pid=14647)\u001b[0m 2022-11-02 16:03:17,149\tINFO wandb.py:282 -- Already logged into W&B.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"trialProgress\">\n",
|
||||
" <h3>Trial Progress</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>date </th><th>done </th><th>episodes_total </th><th>experiment_id </th><th>experiment_tag </th><th>hostname </th><th style=\"text-align: right;\"> iterations_since_restore</th><th style=\"text-align: right;\"> loss</th><th>node_ip </th><th style=\"text-align: right;\"> pid</th><th style=\"text-align: right;\"> time_since_restore</th><th style=\"text-align: right;\"> time_this_iter_s</th><th style=\"text-align: right;\"> time_total_s</th><th style=\"text-align: right;\"> timestamp</th><th style=\"text-align: right;\"> timesteps_since_restore</th><th>timesteps_total </th><th style=\"text-align: right;\"> training_iteration</th><th>trial_id </th><th style=\"text-align: right;\"> warmup_time</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00000</td><td>2022-11-02_16-03-18</td><td>True </td><td> </td><td>7b250c9f31ab484dad1a1fd29823afdf</td><td>0_mean=1,sd=0.7383</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">0.555153</td><td>127.0.0.1</td><td style=\"text-align: right;\">14647</td><td style=\"text-align: right;\"> 1.61319</td><td style=\"text-align: right;\"> 0.00232315</td><td style=\"text-align: right;\"> 1.61319</td><td style=\"text-align: right;\"> 1667430198</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>877eb_00000</td><td style=\"text-align: right;\"> 0.00391102</td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00001</td><td>2022-11-02_16-03-22</td><td>True </td><td> </td><td>5172868368074557a3044ea3a9146673</td><td>1_mean=2,sd=0.3212</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">2.52109 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14660</td><td style=\"text-align: right;\"> 1.72447</td><td style=\"text-align: right;\"> 0.0152011 </td><td style=\"text-align: right;\"> 1.72447</td><td style=\"text-align: right;\"> 1667430202</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>877eb_00001</td><td style=\"text-align: right;\"> 0.00901699</td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00002</td><td>2022-11-02_16-03-22</td><td>True </td><td> </td><td>b13d9bccb1964b4b95e1a858a3ea64c7</td><td>2_mean=3,sd=0.2025</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">2.45412 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14661</td><td style=\"text-align: right;\"> 1.8159 </td><td style=\"text-align: right;\"> 0.00437403</td><td style=\"text-align: right;\"> 1.8159 </td><td style=\"text-align: right;\"> 1667430202</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>877eb_00002</td><td style=\"text-align: right;\"> 0.00844812</td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00003</td><td>2022-11-02_16-03-22</td><td>True </td><td> </td><td>869d7ec7a3544a8387985103e626818f</td><td>3_mean=4,sd=0.5154</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">4.51413 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14662</td><td style=\"text-align: right;\"> 1.715 </td><td style=\"text-align: right;\"> 0.00247812</td><td style=\"text-align: right;\"> 1.715 </td><td style=\"text-align: right;\"> 1667430202</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>877eb_00003</td><td style=\"text-align: right;\"> 0.00282907</td></tr>\n",
|
||||
"<tr><td>train_function_wandb_877eb_00004</td><td>2022-11-02_16-03-22</td><td>True </td><td> </td><td>84d3112d66f64325bc469e44b8447ef5</td><td>4_mean=5,sd=0.2161</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 30</td><td style=\"text-align: right;\">5.2814 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14663</td><td style=\"text-align: right;\"> 1.72827</td><td style=\"text-align: right;\"> 0.00517201</td><td style=\"text-align: right;\"> 1.72827</td><td style=\"text-align: right;\"> 1667430202</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 30</td><td>877eb_00004</td><td style=\"text-align: right;\"> 0.00272107</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".trialProgress {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".trialProgress h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".trialProgress td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[2m\u001b[36m(train_function_wandb pid=14660)\u001b[0m 2022-11-02 16:03:20,600\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"\u001b[2m\u001b[36m(train_function_wandb pid=14661)\u001b[0m 2022-11-02 16:03:20,600\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"\u001b[2m\u001b[36m(train_function_wandb pid=14663)\u001b[0m 2022-11-02 16:03:20,628\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"\u001b[2m\u001b[36m(train_function_wandb pid=14662)\u001b[0m 2022-11-02 16:03:20,723\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"2022-11-02 16:03:22,565\tINFO tune.py:788 -- Total run time: 8.60 seconds (8.48 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2022-11-02 16:03:31</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:09.28 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>9.9/16.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Resources requested: 0/16 CPUs, 0/0 GPUs, 0.0/3.44 GiB heap, 0.0/1.72 GiB objects\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> mean</th><th style=\"text-align: right;\"> sd</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> loss</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00000</td><td>TERMINATED</td><td>127.0.0.1:14718</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">0.397894</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.000187159</td><td style=\"text-align: right;\">0.742345</td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00001</td><td>TERMINATED</td><td>127.0.0.1:14737</td><td style=\"text-align: right;\"> 2</td><td style=\"text-align: right;\">0.386883</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.000151873</td><td style=\"text-align: right;\">2.5709 </td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00002</td><td>TERMINATED</td><td>127.0.0.1:14738</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\">0.290693</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.00014019 </td><td style=\"text-align: right;\">2.99601 </td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00003</td><td>TERMINATED</td><td>127.0.0.1:14739</td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\">0.33333 </td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.00015831 </td><td style=\"text-align: right;\">3.91276 </td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00004</td><td>TERMINATED</td><td>127.0.0.1:14740</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\">0.645479</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.000150919</td><td style=\"text-align: right;\">5.47779 </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[2m\u001b[36m(WandbTrainable pid=14718)\u001b[0m 2022-11-02 16:03:25,742\tINFO wandb.py:282 -- Already logged into W&B.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"trialProgress\">\n",
|
||||
" <h3>Trial Progress</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>date </th><th>done </th><th>episodes_total </th><th>experiment_id </th><th>hostname </th><th style=\"text-align: right;\"> iterations_since_restore</th><th style=\"text-align: right;\"> loss</th><th>node_ip </th><th style=\"text-align: right;\"> pid</th><th style=\"text-align: right;\"> time_since_restore</th><th style=\"text-align: right;\"> time_this_iter_s</th><th style=\"text-align: right;\"> time_total_s</th><th style=\"text-align: right;\"> timestamp</th><th style=\"text-align: right;\"> timesteps_since_restore</th><th>timesteps_total </th><th style=\"text-align: right;\"> training_iteration</th><th>trial_id </th><th style=\"text-align: right;\"> warmup_time</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00000</td><td>2022-11-02_16-03-27</td><td>True </td><td> </td><td>3adb4d0ae0d74d1c9ddd07924b5653b0</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">0.742345</td><td>127.0.0.1</td><td style=\"text-align: right;\">14718</td><td style=\"text-align: right;\"> 0.000187159</td><td style=\"text-align: right;\"> 0.000187159</td><td style=\"text-align: right;\"> 0.000187159</td><td style=\"text-align: right;\"> 1667430207</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 1</td><td>8ca33_00000</td><td style=\"text-align: right;\"> 1.31382</td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00001</td><td>2022-11-02_16-03-31</td><td>True </td><td> </td><td>f1511cfd51f94b3d9cf192181ccc08a9</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">2.5709 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14737</td><td style=\"text-align: right;\"> 0.000151873</td><td style=\"text-align: right;\"> 0.000151873</td><td style=\"text-align: right;\"> 0.000151873</td><td style=\"text-align: right;\"> 1667430211</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 1</td><td>8ca33_00001</td><td style=\"text-align: right;\"> 1.31668</td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00002</td><td>2022-11-02_16-03-31</td><td>True </td><td> </td><td>a7528ec6adf74de0b73aa98ebedab66d</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">2.99601 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14738</td><td style=\"text-align: right;\"> 0.00014019 </td><td style=\"text-align: right;\"> 0.00014019 </td><td style=\"text-align: right;\"> 0.00014019 </td><td style=\"text-align: right;\"> 1667430211</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 1</td><td>8ca33_00002</td><td style=\"text-align: right;\"> 1.32008</td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00003</td><td>2022-11-02_16-03-31</td><td>True </td><td> </td><td>b7af756ca586449ba2d4c44141b53b06</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">3.91276 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14739</td><td style=\"text-align: right;\"> 0.00015831 </td><td style=\"text-align: right;\"> 0.00015831 </td><td style=\"text-align: right;\"> 0.00015831 </td><td style=\"text-align: right;\"> 1667430211</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 1</td><td>8ca33_00003</td><td style=\"text-align: right;\"> 1.31879</td></tr>\n",
|
||||
"<tr><td>WandbTrainable_8ca33_00004</td><td>2022-11-02_16-03-31</td><td>True </td><td> </td><td>196624f42bcc45c18a26778573a43a2c</td><td>Kais-MBP.local.meter</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\">5.47779 </td><td>127.0.0.1</td><td style=\"text-align: right;\">14740</td><td style=\"text-align: right;\"> 0.000150919</td><td style=\"text-align: right;\"> 0.000150919</td><td style=\"text-align: right;\"> 0.000150919</td><td style=\"text-align: right;\"> 1667430211</td><td style=\"text-align: right;\"> 0</td><td> </td><td style=\"text-align: right;\"> 1</td><td>8ca33_00004</td><td style=\"text-align: right;\"> 1.31945</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".trialProgress {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".trialProgress h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".trialProgress td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[2m\u001b[36m(WandbTrainable pid=14739)\u001b[0m 2022-11-02 16:03:30,360\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"\u001b[2m\u001b[36m(WandbTrainable pid=14740)\u001b[0m 2022-11-02 16:03:30,393\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"\u001b[2m\u001b[36m(WandbTrainable pid=14737)\u001b[0m 2022-11-02 16:03:30,454\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"\u001b[2m\u001b[36m(WandbTrainable pid=14738)\u001b[0m 2022-11-02 16:03:30,510\tINFO wandb.py:282 -- Already logged into W&B.\n",
|
||||
"2022-11-02 16:03:31,985\tINFO tune.py:788 -- Total run time: 9.40 seconds (9.27 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'mean': 1, 'sd': 0.3978937765393781, 'wandb': {'project': 'Wandb_example'}}"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"mock_api = True\n",
|
||||
"\n",
|
||||
"if mock_api:\n",
|
||||
" os.environ.setdefault(\"WANDB_MODE\", \"disabled\")\n",
|
||||
" os.environ.setdefault(\"WANDB_API_KEY\", \"abcd\")\n",
|
||||
" ray.init(\n",
|
||||
" runtime_env={\"env_vars\": {\"WANDB_MODE\": \"disabled\", \"WANDB_API_KEY\": \"abcd\"}}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"tune_with_callback()\n",
|
||||
"tune_with_setup()\n",
|
||||
"tune_trainable()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "2f6e9138",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This completes our Tune and Wandb walk-through.\n",
|
||||
"In the following sections you can find more details on the API of the Tune-Wandb integration.\n",
|
||||
"\n",
|
||||
"## Tune Wandb API Reference\n",
|
||||
"\n",
|
||||
"### WandbLoggerCallback\n",
|
||||
"\n",
|
||||
"(air-wandb-logger)=\n",
|
||||
"\n",
|
||||
"```{eval-rst}\n",
|
||||
".. autoclass:: ray.air.integrations.wandb.WandbLoggerCallback\n",
|
||||
" :noindex:\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"### setup_wandb\n",
|
||||
"\n",
|
||||
"(air-wandb-setup)=\n",
|
||||
"\n",
|
||||
"```{eval-rst}\n",
|
||||
".. autofunction:: ray.air.integrations.wandb.setup_wandb\n",
|
||||
" :noindex:\n",
|
||||
"```"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.7"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,940 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "edce67b9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Tuning XGBoost hyperparameters with Ray Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune-xgboost\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune-xgboost\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"(tune-xgboost-ref)=\n",
|
||||
"\n",
|
||||
"This tutorial demonstrates how to optimize XGBoost models using Ray Tune. You'll learn:\n",
|
||||
"- The basics of XGBoost and its key hyperparameters\n",
|
||||
"- How to train a simple XGBoost classifier (without hyperparameter tuning)\n",
|
||||
"- How to use Ray Tune to find optimal hyperparameters\n",
|
||||
"- Advanced techniques like early stopping and GPU acceleration\n",
|
||||
"\n",
|
||||
"XGBoost is currently one of the most popular machine learning algorithms. It performs\n",
|
||||
"very well on a large selection of tasks, and was the key to success in many Kaggle\n",
|
||||
"competitions.\n",
|
||||
"\n",
|
||||
"```{image} /images/xgboost_logo.png\n",
|
||||
":align: center\n",
|
||||
":alt: XGBoost\n",
|
||||
":target: https://xgboost.readthedocs.io/en/latest/\n",
|
||||
":width: 200px\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":depth: 2\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
":::{note}\n",
|
||||
"To run this tutorial, you will need to install the following:\n",
|
||||
"\n",
|
||||
"```bash\n",
|
||||
"$ pip install -q \"ray[tune]\" scikit-learn xgboost\n",
|
||||
"```\n",
|
||||
":::\n",
|
||||
"\n",
|
||||
"## What is XGBoost\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"XGBoost (e**X**treme **G**radient **Boost**ing) is a powerful and efficient implementation of gradient boosted [decision trees](https://en.wikipedia.org/wiki/Decision_tree). It has become one of the most popular machine learning algorithms due to its:\n",
|
||||
"\n",
|
||||
"1. Performance: Consistently strong results across many types of problems\n",
|
||||
"2. Speed: Highly optimized implementation that can leverage GPU acceleration \n",
|
||||
"3. Flexibility: Works with many types of prediction problems (classification, regression, ranking)\n",
|
||||
"\n",
|
||||
"Key Concepts:\n",
|
||||
"- Uses an ensemble of simple decision trees\n",
|
||||
"- Trees are built sequentially, with each tree correcting errors from previous trees\n",
|
||||
"- Employs gradient descent to minimize a loss function\n",
|
||||
"- Even though single trees can have high bias, using a boosted ensemble can result in better predictions and reduced bias\n",
|
||||
"\n",
|
||||
"\n",
|
||||
":::{figure} /images/tune-xgboost-ensemble.svg\n",
|
||||
":alt: Single vs. ensemble learning\n",
|
||||
"\n",
|
||||
"A single decision tree (left) might be able to get to an accuracy of 70%\n",
|
||||
"for a binary classification task. By combining the output of several small\n",
|
||||
"decision trees, an ensemble learner (right) might end up with a higher accuracy\n",
|
||||
"of 90%.\n",
|
||||
":::\n",
|
||||
"\n",
|
||||
"Boosting algorithms start with a single small decision tree and evaluate how well\n",
|
||||
"it predicts the given examples. When building the next tree, those samples that have\n",
|
||||
"been misclassified before have a higher chance of being used to generate the tree.\n",
|
||||
"This is useful because it avoids overfitting to samples that can be easily classified\n",
|
||||
"and instead tries to come up with models that are able to classify hard examples, too.\n",
|
||||
"Please see [here for a more thorough introduction to bagging and boosting algorithms](https://towardsdatascience.com/ensemble-methods-bagging-boosting-and-stacking-c9214a10a205).\n",
|
||||
"\n",
|
||||
"There are many boosting algorithms. In their core, they are all very similar. XGBoost\n",
|
||||
"uses second-level derivatives to find splits that maximize the *gain* (the inverse of\n",
|
||||
"the *loss*) - hence the name. In practice, XGBoost usually shows the best performance\n",
|
||||
"against other boosting algorithms, although LightGBM tends to be [faster and more\n",
|
||||
"memory efficient](https://xgboosting.com/xgboost-vs-lightgbm/), especially for large datasets.\n",
|
||||
"\n",
|
||||
"## Training a simple XGBoost classifier\n",
|
||||
"\n",
|
||||
"Let's first see how a simple XGBoost classifier can be trained. We'll use the\n",
|
||||
"`breast_cancer`-Dataset included in the `sklearn` dataset collection. This is\n",
|
||||
"a binary classification dataset. Given 30 different input features, our task is to\n",
|
||||
"learn to identify subjects with breast cancer and those without.\n",
|
||||
"\n",
|
||||
"Here is the full code to train a simple XGBoost model:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "63611b7f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"SMOKE_TEST = False"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "be0b8321",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-cell"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"SMOKE_TEST = True"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "77b3c71c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Accuracy: 0.9650\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import sklearn.datasets\n",
|
||||
"import sklearn.metrics\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"import xgboost as xgb\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_breast_cancer(config):\n",
|
||||
" # Load dataset\n",
|
||||
" data, labels = sklearn.datasets.load_breast_cancer(return_X_y=True)\n",
|
||||
" # Split into train and test set\n",
|
||||
" train_x, test_x, train_y, test_y = train_test_split(data, labels, test_size=0.25)\n",
|
||||
" # Build input matrices for XGBoost\n",
|
||||
" train_set = xgb.DMatrix(train_x, label=train_y)\n",
|
||||
" test_set = xgb.DMatrix(test_x, label=test_y)\n",
|
||||
" # Train the classifier\n",
|
||||
" results = {}\n",
|
||||
" bst = xgb.train(\n",
|
||||
" config,\n",
|
||||
" train_set,\n",
|
||||
" evals=[(test_set, \"eval\")],\n",
|
||||
" evals_result=results,\n",
|
||||
" verbose_eval=False,\n",
|
||||
" )\n",
|
||||
" return results\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"results = train_breast_cancer(\n",
|
||||
" {\"objective\": \"binary:logistic\", \"eval_metric\": [\"logloss\", \"error\"]}\n",
|
||||
")\n",
|
||||
"accuracy = 1.0 - results[\"eval\"][\"error\"][-1]\n",
|
||||
"print(f\"Accuracy: {accuracy:.4f}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ec2a13f8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As you can see, the code is quite simple. First, the dataset is loaded and split\n",
|
||||
"into a `test` and `train` set. The XGBoost model is trained with `xgb.train()`.\n",
|
||||
"XGBoost automatically evaluates metrics we specified on the test set. In our case\n",
|
||||
"it calculates the *logloss* and the prediction *error*, which is the percentage of\n",
|
||||
"misclassified examples. To calculate the accuracy, we just have to subtract the error\n",
|
||||
"from `1.0`. Even in this simple example, most runs result\n",
|
||||
"in a good accuracy of over `0.90`.\n",
|
||||
"\n",
|
||||
"Maybe you have noticed the `config` parameter we pass to the XGBoost algorithm. This\n",
|
||||
"is a {class}`dict` in which you can specify parameters for the XGBoost algorithm. In this\n",
|
||||
"simple example, the only parameters we passed are the `objective` and `eval_metric` parameters.\n",
|
||||
"The value `binary:logistic` tells XGBoost that we aim to train a logistic regression model for\n",
|
||||
"a binary classification task. You can find an overview over all valid objectives\n",
|
||||
"[here in the XGBoost documentation](https://xgboost.readthedocs.io/en/latest/parameter.html#learning-task-parameters).\n",
|
||||
"\n",
|
||||
"## Scaling XGBoost Training with Ray Train\n",
|
||||
"\n",
|
||||
"In {doc}`/train/getting-started-xgboost`, we covered how to scale XGBoost single-model training with *Ray Train*.\n",
|
||||
"For the rest of this tutorial, we will focus on how to optimize the hyperparameters of the XGBoost model using *Ray Tune*.\n",
|
||||
"\n",
|
||||
"## XGBoost Hyperparameters\n",
|
||||
"\n",
|
||||
"Even with the default settings, XGBoost was able to get to a good accuracy on the\n",
|
||||
"breast cancer dataset. However, as in many machine learning algorithms, there are\n",
|
||||
"many knobs to tune which might lead to even better performance. Let's explore some of\n",
|
||||
"them below.\n",
|
||||
"\n",
|
||||
"### Maximum tree depth\n",
|
||||
"\n",
|
||||
"Remember that XGBoost internally uses many decision tree models to come up with\n",
|
||||
"predictions. When training a decision tree, we need to tell the algorithm how\n",
|
||||
"large the tree may get. The parameter for this is called the tree *depth*.\n",
|
||||
"\n",
|
||||
":::{figure} /images/tune-xgboost-depth.svg\n",
|
||||
":align: center\n",
|
||||
":alt: Decision tree depth\n",
|
||||
"\n",
|
||||
"In this image, the left tree has a depth of 2, and the right tree a depth of 3.\n",
|
||||
"Note that with each level, $2^{(d-1)}$ splits are added, where *d* is the depth\n",
|
||||
"of the tree.\n",
|
||||
":::\n",
|
||||
"\n",
|
||||
"Tree depth is a property that concerns the model complexity. If you only allow short\n",
|
||||
"trees, the models are likely not very precise - they underfit the data. If you allow\n",
|
||||
"very large trees, the single models are likely to overfit to the data. In practice,\n",
|
||||
"a number between `2` and `6` is often a good starting point for this parameter.\n",
|
||||
"\n",
|
||||
"XGBoost's default value is `3`.\n",
|
||||
"\n",
|
||||
"### Minimum child weight\n",
|
||||
"\n",
|
||||
"When a decision tree creates new leaves, it splits up the remaining data at one node\n",
|
||||
"into two groups. If there are only few samples in one of these groups, it often\n",
|
||||
"doesn't make sense to split it further. One of the reasons for this is that the\n",
|
||||
"model is harder to train when we have fewer samples.\n",
|
||||
"\n",
|
||||
":::{figure} /images/tune-xgboost-weight.svg\n",
|
||||
":align: center\n",
|
||||
":alt: Minimum child weight\n",
|
||||
"\n",
|
||||
"In this example, we start with 100 examples. At the first node, they are split\n",
|
||||
"into 4 and 96 samples, respectively. In the next step, our model might find\n",
|
||||
"that it doesn't make sense to split the 4 examples more. It thus only continues\n",
|
||||
"to add leaves on the right side.\n",
|
||||
":::\n",
|
||||
"\n",
|
||||
"The parameter used by the model to decide if it makes sense to split a node is called\n",
|
||||
"the *minimum child weight*. In the case of linear regression, this is just the absolute\n",
|
||||
"number of nodes requried in each child. In other objectives, this value is determined\n",
|
||||
"using the weights of the examples, hence the name.\n",
|
||||
"\n",
|
||||
"The larger the value, the more constrained the trees are and the less deep they will be.\n",
|
||||
"This parameter thus also affects the model complexity. Thus, for noisy or small datasets, \n",
|
||||
"smaller values are preferred. Values can range between 0 and infinity and are dependent on\n",
|
||||
"the sample size. For our case with only 500 examples in the breast cancer dataset, values \n",
|
||||
"between `0` and `10` should be sensible.\n",
|
||||
"\n",
|
||||
"XGBoost's default value is `1`.\n",
|
||||
"\n",
|
||||
"### Subsample size\n",
|
||||
"\n",
|
||||
"Each decision tree we add is trained on a subsample of the total training dataset.\n",
|
||||
"The probabilities for the samples are weighted according to the XGBoost algorithm,\n",
|
||||
"but we can decide on which fraction of the samples we want to train each decision\n",
|
||||
"tree on.\n",
|
||||
"\n",
|
||||
"Setting this value to `0.7` would mean that we randomly sample `70%` of the\n",
|
||||
"training dataset before each training iteration. Lower values lead to more\n",
|
||||
"diverse trees and higher values to more similar trees. Lower values help\n",
|
||||
"prevent overfitting.\n",
|
||||
"\n",
|
||||
"XGBoost's default value is `1`.\n",
|
||||
"\n",
|
||||
"### Learning rate / Eta\n",
|
||||
"\n",
|
||||
"Remember that XGBoost sequentially trains many decision trees, and that later trees\n",
|
||||
"are more likely trained on data that has been misclassified by prior trees. In effect\n",
|
||||
"this means that earlier trees make decisions for easy samples (i.e. those samples that\n",
|
||||
"can easily be classified) and later trees make decisions for harder samples. It is then\n",
|
||||
"sensible to assume that the later trees are less accurate than earlier trees.\n",
|
||||
"\n",
|
||||
"To address this fact, XGBoost uses a parameter called *Eta*, which is sometimes called\n",
|
||||
"the *learning rate*. Don't confuse this with learning rates from gradient descent!\n",
|
||||
"The original [paper on stochastic gradient boosting](https://www.researchgate.net/publication/222573328_Stochastic_Gradient_Boosting)\n",
|
||||
"introduces this parameter like so:\n",
|
||||
"\n",
|
||||
"$$\n",
|
||||
"F_m(x) = F_{m-1}(x) + \\eta \\cdot \\gamma_{lm} \\textbf{1}(x \\in R_{lm})\n",
|
||||
"$$\n",
|
||||
"\n",
|
||||
"This is just a complicated way to say that when we train we new decision tree,\n",
|
||||
"represented by $\\gamma_{lm} \\textbf{1}(x \\in R_{lm})$, we want to dampen\n",
|
||||
"its effect on the previous prediction $F_{m-1}(x)$ with a factor\n",
|
||||
"$\\eta$.\n",
|
||||
"\n",
|
||||
"Typical values for this parameter are between `0.01` and `` 0.3` ``.\n",
|
||||
"\n",
|
||||
"XGBoost's default value is `0.3`.\n",
|
||||
"\n",
|
||||
"### Number of boost rounds\n",
|
||||
"\n",
|
||||
"Lastly, we can decide on how many boosting rounds we perform, which means how\n",
|
||||
"many decision trees we ultimately train. When we do heavy subsampling or use small\n",
|
||||
"learning rate, it might make sense to increase the number of boosting rounds.\n",
|
||||
"\n",
|
||||
"XGBoost's default value is `10`.\n",
|
||||
"\n",
|
||||
"### Putting it together\n",
|
||||
"\n",
|
||||
"Let's see how this looks like in code! We just need to adjust our `config` dict:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "35073e88",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Accuracy: 0.9231\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"config = {\n",
|
||||
" \"objective\": \"binary:logistic\",\n",
|
||||
" \"eval_metric\": [\"logloss\", \"error\"],\n",
|
||||
" \"max_depth\": 2,\n",
|
||||
" \"min_child_weight\": 0,\n",
|
||||
" \"subsample\": 0.8,\n",
|
||||
" \"eta\": 0.2,\n",
|
||||
"}\n",
|
||||
"results = train_breast_cancer(config)\n",
|
||||
"accuracy = 1.0 - results[\"eval\"][\"error\"][-1]\n",
|
||||
"print(f\"Accuracy: {accuracy:.4f}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "69cf0c13",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The rest stays the same. Please note that we do not adjust the `num_boost_rounds` here.\n",
|
||||
"The result should also show a high accuracy of over 90%.\n",
|
||||
"\n",
|
||||
"## Tuning the configuration parameters\n",
|
||||
"\n",
|
||||
"XGBoosts default parameters already lead to a good accuracy, and even our guesses in the\n",
|
||||
"last section should result in accuracies well above 90%. However, our guesses were\n",
|
||||
"just that: guesses. Often we do not know what combination of parameters would actually\n",
|
||||
"lead to the best results on a machine learning task.\n",
|
||||
"\n",
|
||||
"Unfortunately, there are infinitely many combinations of hyperparameters we could try\n",
|
||||
"out. Should we combine `max_depth=3` with `subsample=0.8` or with `subsample=0.9`?\n",
|
||||
"What about the other parameters?\n",
|
||||
"\n",
|
||||
"This is where hyperparameter tuning comes into play. By using tuning libraries such as\n",
|
||||
"Ray Tune we can try out combinations of hyperparameters. Using sophisticated search\n",
|
||||
"strategies, these parameters can be selected so that they are likely to lead to good\n",
|
||||
"results (avoiding an expensive *exhaustive search*). Also, trials that do not perform\n",
|
||||
"well can be preemptively stopped to reduce waste of computing resources. Lastly, Ray Tune\n",
|
||||
"also takes care of training these runs in parallel, greatly increasing search speed.\n",
|
||||
"\n",
|
||||
"Let's start with a basic example on how to use Tune for this. We just need to make\n",
|
||||
"a few changes to our code-block:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "ff856a82",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2025-02-11 16:13:34</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:01.87 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>22.5/36.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using FIFO scheduling algorithm.<br>Logical resource usage: 1.0/12 CPUs, 0/0 GPUs\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> eta</th><th style=\"text-align: right;\"> max_depth</th><th style=\"text-align: right;\"> min_child_weight</th><th style=\"text-align: right;\"> subsample</th><th style=\"text-align: right;\"> acc</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00000</td><td>TERMINATED</td><td>127.0.0.1:89735</td><td style=\"text-align: right;\">0.0434196 </td><td style=\"text-align: right;\"> 8</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.530351</td><td style=\"text-align: right;\">0.909091</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.0114911 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00001</td><td>TERMINATED</td><td>127.0.0.1:89734</td><td style=\"text-align: right;\">0.0115669 </td><td style=\"text-align: right;\"> 6</td><td style=\"text-align: right;\"> 2</td><td style=\"text-align: right;\"> 0.996519</td><td style=\"text-align: right;\">0.615385</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.01138 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00002</td><td>TERMINATED</td><td>127.0.0.1:89740</td><td style=\"text-align: right;\">0.00124339 </td><td style=\"text-align: right;\"> 7</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 0.536078</td><td style=\"text-align: right;\">0.629371</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.0096581 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00003</td><td>TERMINATED</td><td>127.0.0.1:89742</td><td style=\"text-align: right;\">0.000400434</td><td style=\"text-align: right;\"> 6</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 0.90014 </td><td style=\"text-align: right;\">0.601399</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.0103199 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00004</td><td>TERMINATED</td><td>127.0.0.1:89738</td><td style=\"text-align: right;\">0.0121308 </td><td style=\"text-align: right;\"> 6</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 0.843156</td><td style=\"text-align: right;\">0.629371</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.00843 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00005</td><td>TERMINATED</td><td>127.0.0.1:89733</td><td style=\"text-align: right;\">0.0344144 </td><td style=\"text-align: right;\"> 2</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 0.513071</td><td style=\"text-align: right;\">0.895105</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.00800109</td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00006</td><td>TERMINATED</td><td>127.0.0.1:89737</td><td style=\"text-align: right;\">0.0530037 </td><td style=\"text-align: right;\"> 7</td><td style=\"text-align: right;\"> 2</td><td style=\"text-align: right;\"> 0.920801</td><td style=\"text-align: right;\">0.965035</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.0117419 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00007</td><td>TERMINATED</td><td>127.0.0.1:89741</td><td style=\"text-align: right;\">0.000230442</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 0.946852</td><td style=\"text-align: right;\">0.608392</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.00917387</td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00008</td><td>TERMINATED</td><td>127.0.0.1:89739</td><td style=\"text-align: right;\">0.00166323 </td><td style=\"text-align: right;\"> 4</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.588879</td><td style=\"text-align: right;\">0.636364</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.011095 </td></tr>\n",
|
||||
"<tr><td>train_breast_cancer_31c9f_00009</td><td>TERMINATED</td><td>127.0.0.1:89736</td><td style=\"text-align: right;\">0.0753618 </td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 3</td><td style=\"text-align: right;\"> 0.55103 </td><td style=\"text-align: right;\">0.909091</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.00776482</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2025-02-11 16:13:34,649\tINFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '~/ray_results/train_breast_cancer_2025-02-11_16-13-31' in 0.0057s.\n",
|
||||
"2025-02-11 16:13:34,652\tINFO tune.py:1041 -- Total run time: 1.88 seconds (1.86 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000000)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000001)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000002)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000003)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000004)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000005)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000006)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000007)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000008)\n",
|
||||
"\u001b[36m(train_breast_cancer pid=90413)\u001b[0m Checkpoint successfully created at: Checkpoint(filesystem=local, path=~/ray_results/train_breast_cancer_2025-02-11_16-17-11/train_breast_cancer_b412c_00000_0_eta=0.0200,max_depth=4,min_child_weight=2,subsample=0.7395_2025-02-11_16-17-11/checkpoint_000009)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import sklearn.datasets\n",
|
||||
"import sklearn.metrics\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_breast_cancer(config):\n",
|
||||
" # Load dataset\n",
|
||||
" data, labels = sklearn.datasets.load_breast_cancer(return_X_y=True)\n",
|
||||
" # Split into train and test set\n",
|
||||
" train_x, test_x, train_y, test_y = train_test_split(data, labels, test_size=0.25)\n",
|
||||
" # Build input matrices for XGBoost\n",
|
||||
" train_set = xgb.DMatrix(train_x, label=train_y)\n",
|
||||
" test_set = xgb.DMatrix(test_x, label=test_y)\n",
|
||||
" # Train the classifier\n",
|
||||
" results = {}\n",
|
||||
" xgb.train(\n",
|
||||
" config,\n",
|
||||
" train_set,\n",
|
||||
" evals=[(test_set, \"eval\")],\n",
|
||||
" evals_result=results,\n",
|
||||
" verbose_eval=False,\n",
|
||||
" )\n",
|
||||
" # Return prediction accuracy\n",
|
||||
" accuracy = 1.0 - results[\"eval\"][\"error\"][-1]\n",
|
||||
" tune.report({\"mean_accuracy\": accuracy, \"done\": True})\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"config = {\n",
|
||||
" \"objective\": \"binary:logistic\",\n",
|
||||
" \"eval_metric\": [\"logloss\", \"error\"],\n",
|
||||
" \"max_depth\": tune.randint(1, 9),\n",
|
||||
" \"min_child_weight\": tune.choice([1, 2, 3]),\n",
|
||||
" \"subsample\": tune.uniform(0.5, 1.0),\n",
|
||||
" \"eta\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
"}\n",
|
||||
"tuner = tune.Tuner(\n",
|
||||
" train_breast_cancer,\n",
|
||||
" tune_config=tune.TuneConfig(num_samples=10),\n",
|
||||
" param_space=config,\n",
|
||||
")\n",
|
||||
"results = tuner.fit()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "4999e858",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As you can see, the changes in the actual training function are minimal. Instead of\n",
|
||||
"returning the accuracy value, we report it back to Tune using `tune.report()`.\n",
|
||||
"Our `config` dictionary only changed slightly. Instead of passing hard-coded\n",
|
||||
"parameters, we tell Tune to choose values from a range of valid options. There are\n",
|
||||
"a number of options we have here, all of which are explained in\n",
|
||||
"{ref}`the Tune docs <tune-search-space>`.\n",
|
||||
"\n",
|
||||
"For a brief explanation, this is what they do:\n",
|
||||
"\n",
|
||||
"- `tune.randint(min, max)` chooses a random integer value between *min* and *max*.\n",
|
||||
" Note that *max* is exclusive, so it will not be sampled.\n",
|
||||
"- `tune.choice([a, b, c])` chooses one of the items of the list at random. Each item\n",
|
||||
" has the same chance to be sampled.\n",
|
||||
"- `tune.uniform(min, max)` samples a floating point number between *min* and *max*.\n",
|
||||
" Note that *max* is exclusive here, too.\n",
|
||||
"- `tune.loguniform(min, max)` samples a floating point number between *min* and *max*,\n",
|
||||
" but applies a logarithmic transformation to these boundaries first. Thus, this makes\n",
|
||||
" it easy to sample values from different orders of magnitude.\n",
|
||||
"\n",
|
||||
"The `num_samples=10` option we pass to the `TuneConfig()` means that we sample 10 different\n",
|
||||
"hyperparameter configurations from this search space.\n",
|
||||
"\n",
|
||||
"The output of our training run coud look like this:\n",
|
||||
"\n",
|
||||
"```{code-block} bash\n",
|
||||
":emphasize-lines: 14\n",
|
||||
"\n",
|
||||
" Number of trials: 10/10 (10 TERMINATED)\n",
|
||||
" +---------------------------------+------------+-------+-------------+-------------+--------------------+-------------+----------+--------+------------------+\n",
|
||||
" | Trial name | status | loc | eta | max_depth | min_child_weight | subsample | acc | iter | total time (s) |\n",
|
||||
" |---------------------------------+------------+-------+-------------+-------------+--------------------+-------------+----------+--------+------------------|\n",
|
||||
" | train_breast_cancer_b63aa_00000 | TERMINATED | | 0.000117625 | 2 | 2 | 0.616347 | 0.916084 | 1 | 0.0306492 |\n",
|
||||
" | train_breast_cancer_b63aa_00001 | TERMINATED | | 0.0382954 | 8 | 2 | 0.581549 | 0.937063 | 1 | 0.0357082 |\n",
|
||||
" | train_breast_cancer_b63aa_00002 | TERMINATED | | 0.000217926 | 1 | 3 | 0.528428 | 0.874126 | 1 | 0.0264609 |\n",
|
||||
" | train_breast_cancer_b63aa_00003 | TERMINATED | | 0.000120929 | 8 | 1 | 0.634508 | 0.958042 | 1 | 0.036406 |\n",
|
||||
" | train_breast_cancer_b63aa_00004 | TERMINATED | | 0.00839715 | 5 | 1 | 0.730624 | 0.958042 | 1 | 0.0389378 |\n",
|
||||
" | train_breast_cancer_b63aa_00005 | TERMINATED | | 0.000732948 | 8 | 2 | 0.915863 | 0.958042 | 1 | 0.0382841 |\n",
|
||||
" | train_breast_cancer_b63aa_00006 | TERMINATED | | 0.000856226 | 4 | 1 | 0.645209 | 0.916084 | 1 | 0.0357089 |\n",
|
||||
" | train_breast_cancer_b63aa_00007 | TERMINATED | | 0.00769908 | 7 | 1 | 0.729443 | 0.909091 | 1 | 0.0390737 |\n",
|
||||
" | train_breast_cancer_b63aa_00008 | TERMINATED | | 0.00186339 | 5 | 3 | 0.595744 | 0.944056 | 1 | 0.0343912 |\n",
|
||||
" | train_breast_cancer_b63aa_00009 | TERMINATED | | 0.000950272 | 3 | 2 | 0.835504 | 0.965035 | 1 | 0.0348201 |\n",
|
||||
" +---------------------------------+------------+-------+-------------+-------------+--------------------+-------------+----------+--------+------------------+\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"The best configuration we found used `eta=0.000950272`, `max_depth=3`,\n",
|
||||
"`min_child_weight=2`, `subsample=0.835504` and reached an accuracy of\n",
|
||||
"`0.965035`.\n",
|
||||
"\n",
|
||||
"## Early stopping\n",
|
||||
"\n",
|
||||
"Currently, Tune samples 10 different hyperparameter configurations and trains a full\n",
|
||||
"XGBoost on all of them. In our small example, training is very fast. However,\n",
|
||||
"if training takes longer, a significant amount of computer resources is spent on trials\n",
|
||||
"that will eventually show a bad performance, e.g. a low accuracy. It would be good\n",
|
||||
"if we could identify these trials early and stop them, so we don't waste any resources.\n",
|
||||
"\n",
|
||||
"This is where Tune's *Schedulers* shine. A Tune `TrialScheduler` is responsible\n",
|
||||
"for starting and stopping trials. Tune implements a number of different schedulers, each\n",
|
||||
"described {ref}`in the Tune documentation <tune-schedulers>`.\n",
|
||||
"For our example, we will use the `AsyncHyperBandScheduler` or `ASHAScheduler`.\n",
|
||||
"\n",
|
||||
"The basic idea of this scheduler: We sample a number of hyperparameter configurations.\n",
|
||||
"Each of these configurations is trained for a specific number of iterations.\n",
|
||||
"After these iterations, only the best performing hyperparameters are retained. These\n",
|
||||
"are selected according to some loss metric, usually an evaluation loss. This cycle is\n",
|
||||
"repeated until we end up with the best configuration.\n",
|
||||
"\n",
|
||||
"The `ASHAScheduler` needs to know three things:\n",
|
||||
"\n",
|
||||
"1. Which metric should be used to identify badly performing trials?\n",
|
||||
"2. Should this metric be maximized or minimized?\n",
|
||||
"3. How many iterations does each trial train for?\n",
|
||||
"\n",
|
||||
"There are more parameters, which are explained in the\n",
|
||||
"{ref}`documentation <tune-scheduler-hyperband>`.\n",
|
||||
"\n",
|
||||
"Lastly, we have to report the loss metric to Tune. We do this with a `Callback` that\n",
|
||||
"XGBoost accepts and calls after each evaluation round. Ray Tune comes\n",
|
||||
"with {ref}`two XGBoost callbacks <tune-integration-xgboost>`\n",
|
||||
"we can use for this. The `TuneReportCallback` just reports the evaluation\n",
|
||||
"metrics back to Tune. The `TuneReportCheckpointCallback` also saves\n",
|
||||
"checkpoints after each evaluation round. We will just use the latter in this\n",
|
||||
"example so that we can retrieve the saved model later.\n",
|
||||
"\n",
|
||||
"These parameters from the `eval_metrics` configuration setting are then automatically\n",
|
||||
"reported to Tune via the callback. Here, the raw error will be reported, not the accuracy.\n",
|
||||
"To display the best reached accuracy, we will inverse it later.\n",
|
||||
"\n",
|
||||
"We will also load the best checkpointed model so that we can use it for predictions.\n",
|
||||
"The best model is selected with respect to the `metric` and `mode` parameters we\n",
|
||||
"pass to the `TunerConfig()`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "d08b5b0a",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2025-02-11 16:13:35</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:01.05 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>22.5/36.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using AsyncHyperBand: num_stopped=1<br>Bracket: Iter 8.000: -0.6414526407118444 | Iter 4.000: -0.6439705872452343 | Iter 2.000: -0.6452721030145259 | Iter 1.000: -0.6459394399519567<br>Logical resource usage: 1.0/12 CPUs, 0/0 GPUs\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> eta</th><th style=\"text-align: right;\"> max_depth</th><th style=\"text-align: right;\"> min_child_weight</th><th style=\"text-align: right;\"> subsample</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> eval-logloss</th><th style=\"text-align: right;\"> eval-error</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_breast_cancer_32eb5_00000</td><td>TERMINATED</td><td>127.0.0.1:89763</td><td style=\"text-align: right;\">0.000830475</td><td style=\"text-align: right;\"> 5</td><td style=\"text-align: right;\"> 1</td><td style=\"text-align: right;\"> 0.675899</td><td style=\"text-align: right;\"> 10</td><td style=\"text-align: right;\"> 0.0169384</td><td style=\"text-align: right;\"> 0.640195</td><td style=\"text-align: right;\"> 0.342657</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2025-02-11 16:13:35,717\tINFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '~/ray_results/train_breast_cancer_2025-02-11_16-13-34' in 0.0018s.\n",
|
||||
"2025-02-11 16:13:35,719\tINFO tune.py:1041 -- Total run time: 1.05 seconds (1.04 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best model parameters: {'objective': 'binary:logistic', 'eval_metric': ['logloss', 'error'], 'max_depth': 5, 'min_child_weight': 1, 'subsample': 0.675899175238225, 'eta': 0.0008304750981897656}\n",
|
||||
"Best model total accuracy: 0.6573\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import sklearn.datasets\n",
|
||||
"import sklearn.metrics\n",
|
||||
"from ray.tune.schedulers import ASHAScheduler\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"import xgboost as xgb\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.integration.xgboost import TuneReportCheckpointCallback\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_breast_cancer(config: dict):\n",
|
||||
" # This is a simple training function to be passed into Tune\n",
|
||||
" # Load dataset\n",
|
||||
" data, labels = sklearn.datasets.load_breast_cancer(return_X_y=True)\n",
|
||||
" # Split into train and test set\n",
|
||||
" train_x, test_x, train_y, test_y = train_test_split(data, labels, test_size=0.25)\n",
|
||||
" # Build input matrices for XGBoost\n",
|
||||
" train_set = xgb.DMatrix(train_x, label=train_y)\n",
|
||||
" test_set = xgb.DMatrix(test_x, label=test_y)\n",
|
||||
" # Train the classifier, using the Tune callback\n",
|
||||
" xgb.train(\n",
|
||||
" config,\n",
|
||||
" train_set,\n",
|
||||
" evals=[(test_set, \"eval\")],\n",
|
||||
" verbose_eval=False,\n",
|
||||
" # `TuneReportCheckpointCallback` defines the checkpointing frequency and format.\n",
|
||||
" callbacks=[TuneReportCheckpointCallback(frequency=1)],\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def get_best_model_checkpoint(results):\n",
|
||||
" best_result = results.get_best_result()\n",
|
||||
"\n",
|
||||
" # `TuneReportCheckpointCallback` provides a helper method to retrieve the\n",
|
||||
" # model from a checkpoint.\n",
|
||||
" best_bst = TuneReportCheckpointCallback.get_model(best_result.checkpoint)\n",
|
||||
"\n",
|
||||
" accuracy = 1.0 - best_result.metrics[\"eval-error\"]\n",
|
||||
" print(f\"Best model parameters: {best_result.config}\")\n",
|
||||
" print(f\"Best model total accuracy: {accuracy:.4f}\")\n",
|
||||
" return best_bst\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def tune_xgboost(smoke_test=False):\n",
|
||||
" search_space = {\n",
|
||||
" # You can mix constants with search space objects.\n",
|
||||
" \"objective\": \"binary:logistic\",\n",
|
||||
" \"eval_metric\": [\"logloss\", \"error\"],\n",
|
||||
" \"max_depth\": tune.randint(1, 9),\n",
|
||||
" \"min_child_weight\": tune.choice([1, 2, 3]),\n",
|
||||
" \"subsample\": tune.uniform(0.5, 1.0),\n",
|
||||
" \"eta\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
" }\n",
|
||||
" # This will enable aggressive early stopping of bad trials.\n",
|
||||
" scheduler = ASHAScheduler(\n",
|
||||
" max_t=10, grace_period=1, reduction_factor=2 # 10 training iterations\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" train_breast_cancer,\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"eval-logloss\",\n",
|
||||
" mode=\"min\",\n",
|
||||
" scheduler=scheduler,\n",
|
||||
" num_samples=1 if smoke_test else 10,\n",
|
||||
" ),\n",
|
||||
" param_space=search_space,\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n",
|
||||
" return results\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"results = tune_xgboost(smoke_test=SMOKE_TEST)\n",
|
||||
"\n",
|
||||
"# Load the best model checkpoint.\n",
|
||||
"best_bst = get_best_model_checkpoint(results)\n",
|
||||
"\n",
|
||||
"# You could now do further predictions with\n",
|
||||
"# best_bst.predict(...)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "20732fe4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The output of our run could look like this:\n",
|
||||
"\n",
|
||||
"```{code-block} bash\n",
|
||||
":emphasize-lines: 7\n",
|
||||
"\n",
|
||||
" Number of trials: 10/10 (10 TERMINATED)\n",
|
||||
" +---------------------------------+------------+-------+-------------+-------------+--------------------+-------------+--------+------------------+----------------+--------------+\n",
|
||||
" | Trial name | status | loc | eta | max_depth | min_child_weight | subsample | iter | total time (s) | eval-logloss | eval-error |\n",
|
||||
" |---------------------------------+------------+-------+-------------+-------------+--------------------+-------------+--------+------------------+----------------+--------------|\n",
|
||||
" | train_breast_cancer_ba275_00000 | TERMINATED | | 0.00205087 | 2 | 1 | 0.898391 | 10 | 0.380619 | 0.678039 | 0.090909 |\n",
|
||||
" | train_breast_cancer_ba275_00001 | TERMINATED | | 0.000183834 | 4 | 3 | 0.924939 | 1 | 0.0228798 | 0.693009 | 0.111888 |\n",
|
||||
" | train_breast_cancer_ba275_00002 | TERMINATED | | 0.0242721 | 7 | 2 | 0.501551 | 10 | 0.376154 | 0.54472 | 0.06993 |\n",
|
||||
" | train_breast_cancer_ba275_00003 | TERMINATED | | 0.000449692 | 5 | 3 | 0.890212 | 1 | 0.0234981 | 0.692811 | 0.090909 |\n",
|
||||
" | train_breast_cancer_ba275_00004 | TERMINATED | | 0.000376393 | 7 | 2 | 0.883609 | 1 | 0.0231569 | 0.692847 | 0.062937 |\n",
|
||||
" | train_breast_cancer_ba275_00005 | TERMINATED | | 0.00231942 | 3 | 3 | 0.877464 | 2 | 0.104867 | 0.689541 | 0.083916 |\n",
|
||||
" | train_breast_cancer_ba275_00006 | TERMINATED | | 0.000542326 | 1 | 2 | 0.578584 | 1 | 0.0213971 | 0.692765 | 0.083916 |\n",
|
||||
" | train_breast_cancer_ba275_00007 | TERMINATED | | 0.0016801 | 1 | 2 | 0.975302 | 1 | 0.02226 | 0.691999 | 0.083916 |\n",
|
||||
" | train_breast_cancer_ba275_00008 | TERMINATED | | 0.000595756 | 8 | 3 | 0.58429 | 1 | 0.0221152 | 0.692657 | 0.06993 |\n",
|
||||
" | train_breast_cancer_ba275_00009 | TERMINATED | | 0.000357845 | 8 | 1 | 0.637776 | 1 | 0.022635 | 0.692859 | 0.090909 |\n",
|
||||
" +---------------------------------+------------+-------+-------------+-------------+--------------------+-------------+--------+------------------+----------------+--------------+\n",
|
||||
"\n",
|
||||
"\n",
|
||||
" Best model parameters: {'objective': 'binary:logistic', 'eval_metric': ['logloss', 'error'], 'max_depth': 7, 'min_child_weight': 2, 'subsample': 0.5015513240240503, 'eta': 0.024272050872920895}\n",
|
||||
" Best model total accuracy: 0.9301\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"As you can see, most trials have been stopped only after a few iterations. Only the\n",
|
||||
"two most promising trials were run for the full 10 iterations.\n",
|
||||
"\n",
|
||||
"You can also ensure that all available resources are being used as the scheduler\n",
|
||||
"terminates trials, freeing them up. This can be done through the\n",
|
||||
"`ResourceChangingScheduler`. An example of this can be found here:\n",
|
||||
"{doc}`/tune/examples/includes/xgboost_dynamic_resources_example`.\n",
|
||||
"\n",
|
||||
"## Using fractional GPUs\n",
|
||||
"\n",
|
||||
"You can often accelerate your training by using GPUs in addition to CPUs. However,\n",
|
||||
"you usually don't have as many GPUs as you have trials to run. For instance, if you\n",
|
||||
"run 10 Tune trials in parallel, you usually don't have access to 10 separate GPUs.\n",
|
||||
"\n",
|
||||
"Tune supports *fractional GPUs*. This means that each task is assigned a fraction\n",
|
||||
"of the GPU memory for training. For 10 tasks, this could look like this:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "7d1b20a3",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"config = {\n",
|
||||
" \"objective\": \"binary:logistic\",\n",
|
||||
" \"eval_metric\": [\"logloss\", \"error\"],\n",
|
||||
" \"tree_method\": \"gpu_hist\",\n",
|
||||
" \"max_depth\": tune.randint(1, 9),\n",
|
||||
" \"min_child_weight\": tune.choice([1, 2, 3]),\n",
|
||||
" \"subsample\": tune.uniform(0.5, 1.0),\n",
|
||||
" \"eta\": tune.loguniform(1e-4, 1e-1),\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"tuner = tune.Tuner(\n",
|
||||
" tune.with_resources(train_breast_cancer, resources={\"cpu\": 1, \"gpu\": 0.1}),\n",
|
||||
" tune_config=tune.TuneConfig(num_samples=1 if SMOKE_TEST else 10),\n",
|
||||
" param_space=config,\n",
|
||||
")\n",
|
||||
"results = tuner.fit()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ee131861",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Each task thus works with 10% of the available GPU memory. You also have to tell\n",
|
||||
"XGBoost to use the `gpu_hist` tree method, so it knows it should use the GPU.\n",
|
||||
"\n",
|
||||
"## Conclusion\n",
|
||||
"\n",
|
||||
"You should now have a basic understanding on how to train XGBoost models and on how\n",
|
||||
"to tune the hyperparameters to yield the best results. In our simple example,\n",
|
||||
"Tuning the parameters didn't make a huge difference for the accuracy.\n",
|
||||
"But in larger applications, intelligent hyperparameter tuning can make the\n",
|
||||
"difference between a model that doesn't seem to learn at all, and a model\n",
|
||||
"that outperforms all the other ones.\n",
|
||||
"\n",
|
||||
"## More XGBoost Examples\n",
|
||||
"\n",
|
||||
"- {doc}`/tune/examples/includes/xgboost_dynamic_resources_example`:\n",
|
||||
" Trains a basic XGBoost model with Tune with the class-based API and a ResourceChangingScheduler, ensuring all resources are being used at all time.\n",
|
||||
"- {doc}`/train/getting-started-xgboost`: Shows how to scale XGBoost single-model training with *Ray Train* (as opposed to hyperparameter tuning with Ray Tune).\n",
|
||||
"\n",
|
||||
"## Learn More\n",
|
||||
"\n",
|
||||
"- [XGBoost Hyperparameter Tuning - A Visual Guide](https://kevinvecmanis.io/machine%20learning/hyperparameter%20tuning/dataviz/python/2019/05/11/XGBoost-Tuning-Visual-Guide.html)\n",
|
||||
"- [Notes on XGBoost Parameter Tuning](https://xgboost.readthedocs.io/en/latest/tutorials/param_tuning.html)\n",
|
||||
"- [Doing XGBoost Hyperparameter Tuning the smart way](https://towardsdatascience.com/doing-xgboost-hyper-parameter-tuning-the-smart-way-part-1-of-2-f6d255a45dde)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "xgboost-tune",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.11"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,271 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "3b05af3b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"(tune-mnist-keras)=\n",
|
||||
"\n",
|
||||
"# Using Keras & TensorFlow with Tune\n",
|
||||
"\n",
|
||||
"<a id=\"try-anyscale-quickstart-tune_mnist_keras\" href=\"https://console.anyscale.com/register/ha?render_flow=ray&utm_source=ray_docs&utm_medium=docs&utm_campaign=tune_mnist_keras\">\n",
|
||||
" <img src=\"../../_static/img/run-on-anyscale.svg\" alt=\"try-anyscale-quickstart\">\n",
|
||||
"</a>\n",
|
||||
"<br></br>\n",
|
||||
"\n",
|
||||
"```{image} /images/tf_keras_logo.jpeg\n",
|
||||
":align: center\n",
|
||||
":alt: Keras & TensorFlow Logo\n",
|
||||
":height: 120px\n",
|
||||
":target: https://keras.io\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"```{contents}\n",
|
||||
":backlinks: none\n",
|
||||
":local: true\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## Prerequisites\n",
|
||||
"\n",
|
||||
"- `pip install \"ray[tune]\" tensorflow==2.18.0 filelock`\n",
|
||||
"\n",
|
||||
"## Example"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "19e3c389",
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"hide-output"
|
||||
]
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div class=\"tuneStatus\">\n",
|
||||
" <div style=\"display: flex;flex-direction: row\">\n",
|
||||
" <div style=\"display: flex;flex-direction: column;\">\n",
|
||||
" <h3>Tune Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>Current time:</td><td>2025-02-13 15:22:41</td></tr>\n",
|
||||
"<tr><td>Running for: </td><td>00:00:41.76 </td></tr>\n",
|
||||
"<tr><td>Memory: </td><td>21.4/36.0 GiB </td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
" <div class=\"vDivider\"></div>\n",
|
||||
" <div class=\"systemInfo\">\n",
|
||||
" <h3>System Info</h3>\n",
|
||||
" Using AsyncHyperBand: num_stopped=0<br>Bracket: Iter 320.000: None | Iter 80.000: None | Iter 20.000: None<br>Logical resource usage: 2.0/12 CPUs, 0/0 GPUs\n",
|
||||
" </div>\n",
|
||||
" \n",
|
||||
" </div>\n",
|
||||
" <div class=\"hDivider\"></div>\n",
|
||||
" <div class=\"trialStatus\">\n",
|
||||
" <h3>Trial Status</h3>\n",
|
||||
" <table>\n",
|
||||
"<thead>\n",
|
||||
"<tr><th>Trial name </th><th>status </th><th>loc </th><th style=\"text-align: right;\"> hidden</th><th style=\"text-align: right;\"> learning_rate</th><th style=\"text-align: right;\"> momentum</th><th style=\"text-align: right;\"> iter</th><th style=\"text-align: right;\"> total time (s)</th><th style=\"text-align: right;\"> accuracy</th></tr>\n",
|
||||
"</thead>\n",
|
||||
"<tbody>\n",
|
||||
"<tr><td>train_mnist_533a2_00000</td><td>TERMINATED</td><td>127.0.0.1:36365</td><td style=\"text-align: right;\"> 371</td><td style=\"text-align: right;\"> 0.0799367 </td><td style=\"text-align: right;\"> 0.588387</td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 20.8515</td><td style=\"text-align: right;\"> 0.984583</td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00001</td><td>TERMINATED</td><td>127.0.0.1:36364</td><td style=\"text-align: right;\"> 266</td><td style=\"text-align: right;\"> 0.0457424 </td><td style=\"text-align: right;\"> 0.22303 </td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 19.5277</td><td style=\"text-align: right;\"> 0.96495 </td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00002</td><td>TERMINATED</td><td>127.0.0.1:36368</td><td style=\"text-align: right;\"> 157</td><td style=\"text-align: right;\"> 0.0190286 </td><td style=\"text-align: right;\"> 0.537132</td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 16.6606</td><td style=\"text-align: right;\"> 0.95385 </td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00003</td><td>TERMINATED</td><td>127.0.0.1:36363</td><td style=\"text-align: right;\"> 451</td><td style=\"text-align: right;\"> 0.0433488 </td><td style=\"text-align: right;\"> 0.18925 </td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 22.0514</td><td style=\"text-align: right;\"> 0.966283</td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00004</td><td>TERMINATED</td><td>127.0.0.1:36367</td><td style=\"text-align: right;\"> 276</td><td style=\"text-align: right;\"> 0.0336728 </td><td style=\"text-align: right;\"> 0.430171</td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 20.0884</td><td style=\"text-align: right;\"> 0.964767</td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00005</td><td>TERMINATED</td><td>127.0.0.1:36366</td><td style=\"text-align: right;\"> 208</td><td style=\"text-align: right;\"> 0.071015 </td><td style=\"text-align: right;\"> 0.419166</td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 17.933 </td><td style=\"text-align: right;\"> 0.976083</td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00006</td><td>TERMINATED</td><td>127.0.0.1:36475</td><td style=\"text-align: right;\"> 312</td><td style=\"text-align: right;\"> 0.00692959</td><td style=\"text-align: right;\"> 0.714595</td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 13.058 </td><td style=\"text-align: right;\"> 0.944017</td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00007</td><td>TERMINATED</td><td>127.0.0.1:36479</td><td style=\"text-align: right;\"> 169</td><td style=\"text-align: right;\"> 0.0694114 </td><td style=\"text-align: right;\"> 0.664904</td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 10.7991</td><td style=\"text-align: right;\"> 0.9803 </td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00008</td><td>TERMINATED</td><td>127.0.0.1:36486</td><td style=\"text-align: right;\"> 389</td><td style=\"text-align: right;\"> 0.0370836 </td><td style=\"text-align: right;\"> 0.665592</td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 14.018 </td><td style=\"text-align: right;\"> 0.977833</td></tr>\n",
|
||||
"<tr><td>train_mnist_533a2_00009</td><td>TERMINATED</td><td>127.0.0.1:36487</td><td style=\"text-align: right;\"> 389</td><td style=\"text-align: right;\"> 0.0676138 </td><td style=\"text-align: right;\"> 0.52372 </td><td style=\"text-align: right;\"> 12</td><td style=\"text-align: right;\"> 14.0043</td><td style=\"text-align: right;\"> 0.981833</td></tr>\n",
|
||||
"</tbody>\n",
|
||||
"</table>\n",
|
||||
" </div>\n",
|
||||
"</div>\n",
|
||||
"<style>\n",
|
||||
".tuneStatus {\n",
|
||||
" color: var(--jp-ui-font-color1);\n",
|
||||
"}\n",
|
||||
".tuneStatus .systemInfo {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus td {\n",
|
||||
" white-space: nowrap;\n",
|
||||
"}\n",
|
||||
".tuneStatus .trialStatus {\n",
|
||||
" display: flex;\n",
|
||||
" flex-direction: column;\n",
|
||||
"}\n",
|
||||
".tuneStatus h3 {\n",
|
||||
" font-weight: bold;\n",
|
||||
"}\n",
|
||||
".tuneStatus .hDivider {\n",
|
||||
" border-bottom-width: var(--jp-border-width);\n",
|
||||
" border-bottom-color: var(--jp-border-color0);\n",
|
||||
" border-bottom-style: solid;\n",
|
||||
"}\n",
|
||||
".tuneStatus .vDivider {\n",
|
||||
" border-left-width: var(--jp-border-width);\n",
|
||||
" border-left-color: var(--jp-border-color0);\n",
|
||||
" border-left-style: solid;\n",
|
||||
" margin: 0.5em 1em 0.5em 1em;\n",
|
||||
"}\n",
|
||||
"</style>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2025-02-13 15:22:41,843\tINFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '~/ray_results/exp' in 0.0048s.\n",
|
||||
"2025-02-13 15:22:41,846\tINFO tune.py:1041 -- Total run time: 41.77 seconds (41.75 seconds for the tuning loop).\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best hyperparameters found were: {'threads': 2, 'learning_rate': 0.07993666231835218, 'momentum': 0.5883866709655042, 'hidden': 371} | Accuracy: 0.98458331823349\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"from filelock import FileLock\n",
|
||||
"from tensorflow.keras.datasets import mnist\n",
|
||||
"\n",
|
||||
"from ray import tune\n",
|
||||
"from ray.tune.schedulers import AsyncHyperBandScheduler\n",
|
||||
"from ray.tune.integration.keras import TuneReportCheckpointCallback\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_mnist(config):\n",
|
||||
" # https://github.com/tensorflow/tensorflow/issues/32159\n",
|
||||
" import tensorflow as tf\n",
|
||||
"\n",
|
||||
" batch_size = 128\n",
|
||||
" num_classes = 10\n",
|
||||
" epochs = 12\n",
|
||||
"\n",
|
||||
" with FileLock(os.path.expanduser(\"~/.data.lock\")):\n",
|
||||
" (x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
|
||||
" x_train, x_test = x_train / 255.0, x_test / 255.0\n",
|
||||
" model = tf.keras.models.Sequential(\n",
|
||||
" [\n",
|
||||
" tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
|
||||
" tf.keras.layers.Dense(config[\"hidden\"], activation=\"relu\"),\n",
|
||||
" tf.keras.layers.Dropout(0.2),\n",
|
||||
" tf.keras.layers.Dense(num_classes, activation=\"softmax\"),\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" model.compile(\n",
|
||||
" loss=\"sparse_categorical_crossentropy\",\n",
|
||||
" optimizer=tf.keras.optimizers.SGD(learning_rate=config[\"learning_rate\"], momentum=config[\"momentum\"]),\n",
|
||||
" metrics=[\"accuracy\"],\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" model.fit(\n",
|
||||
" x_train,\n",
|
||||
" y_train,\n",
|
||||
" batch_size=batch_size,\n",
|
||||
" epochs=epochs,\n",
|
||||
" verbose=0,\n",
|
||||
" validation_data=(x_test, y_test),\n",
|
||||
" callbacks=[TuneReportCheckpointCallback(metrics={\"accuracy\": \"accuracy\"})],\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def tune_mnist():\n",
|
||||
" sched = AsyncHyperBandScheduler(\n",
|
||||
" time_attr=\"training_iteration\", max_t=400, grace_period=20\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" tuner = tune.Tuner(\n",
|
||||
" tune.with_resources(train_mnist, resources={\"cpu\": 2, \"gpu\": 0}),\n",
|
||||
" tune_config=tune.TuneConfig(\n",
|
||||
" metric=\"accuracy\",\n",
|
||||
" mode=\"max\",\n",
|
||||
" scheduler=sched,\n",
|
||||
" num_samples=10,\n",
|
||||
" ),\n",
|
||||
" run_config=tune.RunConfig(\n",
|
||||
" name=\"exp\",\n",
|
||||
" stop={\"accuracy\": 0.99},\n",
|
||||
" ),\n",
|
||||
" param_space={\n",
|
||||
" \"threads\": 2,\n",
|
||||
" \"learning_rate\": tune.uniform(0.001, 0.1),\n",
|
||||
" \"momentum\": tune.uniform(0.1, 0.9),\n",
|
||||
" \"hidden\": tune.randint(32, 512),\n",
|
||||
" },\n",
|
||||
" )\n",
|
||||
" results = tuner.fit()\n",
|
||||
" return results\n",
|
||||
"\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"results = tune_mnist()\n",
|
||||
"print(f\"Best hyperparameters found were: {results.get_best_result().config} | Accuracy: {results.get_best_result().metrics['accuracy']}\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "d7e46189",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This should output something like:\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"Best hyperparameters found were: {'threads': 2, 'learning_rate': 0.07607440973606909, 'momentum': 0.7715363277240616, 'hidden': 452} | Accuracy: 0.98458331823349\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"## More Keras and TensorFlow Examples\n",
|
||||
"\n",
|
||||
"- {doc}`/tune/examples/includes/pbt_memnn_example`: Example of training a Memory NN on bAbI with Keras using PBT.\n",
|
||||
"- {doc}`/tune/examples/includes/tf_mnist_example`: Converts the Advanced TF2.0 MNIST example to use Tune\n",
|
||||
" with the Trainable. This uses `tf.function`.\n",
|
||||
" Original code from tensorflow: https://www.tensorflow.org/tutorials/quickstart/advanced\n",
|
||||
"- {doc}`/tune/examples/includes/pbt_tune_cifar10_with_keras`:\n",
|
||||
" A contributed example of tuning a Keras model on CIFAR10 with the PopulationBasedTraining scheduler.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "tune-keras",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.11"
|
||||
},
|
||||
"orphan": true
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user