Trial-level early stopping
Trial-level early stopping aims to monitor the results of expensive evaluations with timeseries-like data and terminate those that are unlikely to produce promising results prior to completing that evaluation. This reduces computational waste, and enables the same amount of resources to explore more configurations. Early stopping is useful for expensive to evaluate problems where stepwise information is available on the way to the final measurement.
Like the Getting Started tutorial we'll be minimizing the Hartmann6 function, but this time we've modified it to incorporate a new parameter which allows the function to produce timeseries-like data where the value returned is closer and closer to Hartmann6's true value as increases. At the function will simply return Hartmann6's unaltered value.
While the function is synthetic, the workflow captures the intended principles for this tutorial and is similar to the process of training typical machine learning models.
Learning Objectives
- Understand when time-series-like data can be used in an optimization experiment
- Run a simple optimization experiment with early stopping
- Configure details of an early stopping strategy
- Analyze the results of the optimization
Prerequisites
- Familiarity with Python and basic programming concepts
- Understanding of adaptive experimentation and Bayesian optimization
- Getting Started with Ax
Step 1: Import Necessary Modules
First, ensure you have all the necessary imports:
import numpy as np
from ax.api.client import Client
from ax.api.configs import RangeParameterConfig
Step 2: Initialize the Client
Create an instance of the Client
to manage the state of your experiment.
client = Client()
Step 3: Configure the Experiment
The Client
instance can be configured with a series of Config
s that define how the
experiment will be run.
The Hartmann6 problem is usually evaluated on the hypercube , so we will
define six identical RangeParameterConfig
s with these bounds.
You may specify additional features like parameter constraints to further refine the search space and parameter scaling to help navigate parameters with nonuniform effects.
# Define six float parameters for the Hartmann6 function
parameters = [
RangeParameterConfig(
name=f"x{i + 1}", parameter_type="float", bounds=(0, 1)
)
for i in range(6)
]
client.configure_experiment(parameters=parameters)
Step 4: Configure Optimization
Now, we must configure the objective for this optimization, which we do using
Client.configure_optimization
. This method expects a string objective
, an expression
containing either a single metric to maximize, a linear combination of metrics to
maximize, or a tuple of multiple metrics to jointly maximize. These expressions are
parsed using SymPy. For example:
"score"
would direct Ax to maximize a metric named score"-loss"
would direct Ax to Ax to minimize a metric named loss"task_0 + 0.5 * task_1"
would direct Ax to maximize the sum of two task scores, downweighting task_1 by a factor of 0.5"score, -flops"
would direct Ax to simultaneously maximize score while minimizing flops
See these recipes for more information on configuring objectives and outcome constraints.
client.configure_optimization(objective="-hartmann6")
Step 5: Run Trials with early stopping
Here, we will configure the ask-tell loop.
We begin by defining our Hartmann6 function as written above. Remember, this is just an example problem and any Python function can be substituted here.
Then we will iteratively do the following:
- Call
client.get_next_trials
to "ask" Ax for a parameterization to evaluate - Evaluate
hartmann6_curve
using those parameters in an inner loop to simulate the generation of timeseries data - "Tell" Ax the partial result using
client.attach_data
- Query whether the trial should be stopped via
client.should_stop_trial_early
- Stop the underperforming trial and report back to Ax that is has been stopped
This loop will run multiple trials to optimize the function.
Ax will configure an EarlyStoppingStrategy when should_stop_trial_early
is called for
the first time. By default Ax uses a Percentile early stopping strategy which will
terminate a trial early if its performance falls below a percentile threshold when
compared to other trials at the same step. Early stopping can only occur after a minimum
number of progressions
to prevent premature early stopping. This validates that both
enough data is gathered to make a decision and there is a minimum number of completed
trials with curve data; these completed trials establish a baseline.
# Hartmann6 function
def hartmann6(x1, x2, x3, x4, x5, x6):
alpha = np.array([1.0, 1.2, 3.0, 3.2])
A = np.array(
[
[10, 3, 17, 3.5, 1.7, 8],
[0.05, 10, 17, 0.1, 8, 14],
[3, 3.5, 1.7, 10, 17, 8],
[17, 8, 0.05, 10, 0.1, 14],
]
)
P = 10**-4 * np.array(
[
[1312, 1696, 5569, 124, 8283, 5886],
[2329, 4135, 8307, 3736, 1004, 9991],
[2348, 1451, 3522, 2883, 3047, 6650],
[4047, 8828, 8732, 5743, 1091, 381],
]
)
outer = 0.0
for i in range(4):
inner = 0.0
for j, x in enumerate([x1, x2, x3, x4, x5, x6]):
inner += A[i, j] * (x - P[i, j]) ** 2
outer += alpha[i] * np.exp(-inner)
return -outer
# Hartmann6 function with additional t term such that
# hartmann6(X) == hartmann6_curve(X, t=100)
def hartmann6_curve(x1, x2, x3, x4, x5, x6, t):
return hartmann6(x1, x2, x3, x4, x5, x6) - np.log2(t / 100)
(
hartmann6(0.1, 0.45, 0.8, 0.25, 0.552, 1.0),
hartmann6_curve(0.1, 0.45, 0.8, 0.25, 0.552, 1.0, 100),
)
(np.float64(-0.4878737485613134), np.float64(-0.4878737485613134))
maximum_progressions = 100 # Observe hartmann6_curve over 100 progressions
for _ in range(30): # Run 30 rounds of trials
trials = client.get_next_trials(max_trials=3)
for trial_index, parameters in trials.items():
for t in range(1, maximum_progressions + 1):
raw_data = {"hartmann6": hartmann6_curve(t=t, **parameters)}
# On the final reading call complete_trial and break, else call attach_data
if t == maximum_progressions:
client.complete_trial(
trial_index=trial_index, raw_data=raw_data, progression=t
)
break
client.attach_data(
trial_index=trial_index, raw_data=raw_data, progression=t
)
# If the trial is underperforming, stop it
if client.should_stop_trial_early(trial_index=trial_index):
client.mark_trial_early_stopped(trial_index=trial_index)
break
[INFO 08-21 05:05:44] ax.api.client: GenerationStrategy(name='Center+Sobol+MBM:fast', nodes=[CenterGenerationNode(next_node_name='Sobol'), GenerationNode(node_name='Sobol', generator_specs=[GeneratorSpec(generator_enum=Sobol, model_key_override=None)], transition_criteria=[MinTrials(transition_to='MBM'), MinTrials(transition_to='MBM')]), GenerationNode(node_name='MBM', generator_specs=[GeneratorSpec(generator_enum=BoTorch, model_key_override=None)], transition_criteria=[])]) chosen based on user input and problem structure.
[INFO 08-21 05:05:44] ax.api.client: Generated new trial 0 with parameters {'x1': 0.5, 'x2': 0.5, 'x3': 0.5, 'x4': 0.5, 'x5': 0.5, 'x6': 0.5}using GenerationNode CenterOfSearchSpace.
[INFO 08-21 05:05:44] ax.api.client: Generated new trial 1 with parameters {'x1': 0.684849, 'x2': 0.957862, 'x3': 0.471241, 'x4': 0.256039, 'x5': 0.296428, 'x6': 0.179191}using GenerationNode Sobol.
[INFO 08-21 05:05:44] ax.api.client: Generated new trial 2 with parameters {'x1': 0.15185, 'x2': 0.185658, 'x3': 0.894246, 'x4': 0.576811, 'x5': 0.843578, 'x6': 0.56053}using GenerationNode Sobol.
[INFO 08-21 05:05:46] ax.api.client: Trial 0 marked COMPLETED.
[INFO 08-21 05:05:47] ax.api.client: Trial 1 marked COMPLETED.
[INFO 08-21 05:05:49] ax.api.client: Trial 2 marked COMPLETED.
[INFO 08-21 05:05:49] ax.api.client: Generated new trial 3 with parameters {'x1': 0.258363, 'x2': 0.556372, 'x3': 0.112227, 'x4': 0.217706, 'x5': 0.567069, 'x6': 0.772171}using GenerationNode Sobol.
[INFO 08-21 05:05:49] ax.api.client: Generated new trial 4 with parameters {'x1': 0.795556, 'x2': 0.331534, 'x3': 0.503732, 'x4': 0.896874, 'x5': 0.051719, 'x6': 0.402548}using GenerationNode Sobol.
[WARNING 08-21 05:05:49] ax.api.client: 3 trials requested but only 2 could be generated.
[INFO 08-21 05:05:50] ax.api.client: Trial 3 marked COMPLETED.
[INFO 08-21 05:05:52] ax.api.client: Trial 4 marked COMPLETED.
[INFO 08-21 05:05:53] ax.api.client: Generated new trial 5 with parameters {'x1': 0.829076, 'x2': 0.549916, 'x3': 0.146747, 'x4': 0.579718, 'x5': 0.509187, 'x6': 0.688558}using GenerationNode MBM.
[WARNING 08-21 05:05:53] ax.api.client: 3 trials requested but only 1 could be generated.
[INFO 08-21 05:05:53] ax.early_stopping.strategies.percentile: Early stoppinging trial 5: Trial objective value 3.207582079252523 is worse than 50.0-th percentile (3.143085354674401) across comparable trials..
[INFO 08-21 05:05:53] ax.api.client: Trial 5 should be stopped early: Trial objective value 3.207582079252523 is worse than 50.0-th percentile (3.143085354674401) across comparable trials.
[INFO 08-21 05:05:53] ax.api.client: Trial 5 marked EARLY_STOPPED.
[INFO 08-21 05:05:55] ax.api.client: Generated new trial 6 with parameters {'x1': 1.0, 'x2': 0.795894, 'x3': 0.170744, 'x4': 0.508533, 'x5': 1.0, 'x6': 0.88035}using GenerationNode MBM.
[INFO 08-21 05:05:55] ax.api.client: Generated new trial 7 with parameters {'x1': 0.526266, 'x2': 0.0, 'x3': 0.0, 'x4': 0.0, 'x5': 0.570103, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:05:55] ax.api.client: Generated new trial 8 with parameters {'x1': 0.222481, 'x2': 1.0, 'x3': 0.878602, 'x4': 0.462305, 'x5': 0.188877, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:05:55] ax.early_stopping.strategies.percentile: Early stoppinging trial 6: Trial objective value 3.3219122229136215 is worse than 50.0-th percentile (3.207582079252523) across comparable trials..
[INFO 08-21 05:05:55] ax.api.client: Trial 6 should be stopped early: Trial objective value 3.3219122229136215 is worse than 50.0-th percentile (3.207582079252523) across comparable trials.
[INFO 08-21 05:05:55] ax.api.client: Trial 6 marked EARLY_STOPPED.
[INFO 08-21 05:05:56] ax.early_stopping.strategies.percentile: Early stoppinging trial 7: Trial objective value 3.3150170604709572 is worse than 50.0-th percentile (3.23830532127623) across comparable trials..
[INFO 08-21 05:05:56] ax.api.client: Trial 7 should be stopped early: Trial objective value 3.3150170604709572 is worse than 50.0-th percentile (3.23830532127623) across comparable trials.
[INFO 08-21 05:05:56] ax.api.client: Trial 7 marked EARLY_STOPPED.
[INFO 08-21 05:05:56] ax.early_stopping.strategies.percentile: Early stoppinging trial 8: Trial objective value 3.1136623799629564 is worse than 50.0-th percentile (3.0273737431546506) across comparable trials..
[INFO 08-21 05:05:56] ax.api.client: Trial 8 should be stopped early: Trial objective value 3.1136623799629564 is worse than 50.0-th percentile (3.0273737431546506) across comparable trials.
[INFO 08-21 05:05:56] ax.api.client: Trial 8 marked EARLY_STOPPED.
[INFO 08-21 05:05:58] ax.api.client: Generated new trial 9 with parameters {'x1': 1.0, 'x2': 1.0, 'x3': 0.0, 'x4': 0.0, 'x5': 1.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:05:58] ax.api.client: Generated new trial 10 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 0.0, 'x4': 1.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:05:58] ax.api.client: Generated new trial 11 with parameters {'x1': 1.0, 'x2': 0.0, 'x3': 0.0, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:05:58] ax.early_stopping.strategies.percentile: Early stoppinging trial 9: Trial objective value 3.321926455465507 is worse than 50.0-th percentile (3.2600972335064142) across comparable trials..
[INFO 08-21 05:05:58] ax.api.client: Trial 9 should be stopped early: Trial objective value 3.321926455465507 is worse than 50.0-th percentile (3.2600972335064142) across comparable trials.
[INFO 08-21 05:05:58] ax.api.client: Trial 9 marked EARLY_STOPPED.
[INFO 08-21 05:05:58] ax.early_stopping.strategies.percentile: Early stoppinging trial 10: Trial objective value 3.2967305906390476 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials..
[INFO 08-21 05:05:58] ax.api.client: Trial 10 should be stopped early: Trial objective value 3.2967305906390476 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials.
[INFO 08-21 05:05:58] ax.api.client: Trial 10 marked EARLY_STOPPED.
[INFO 08-21 05:05:58] ax.early_stopping.strategies.percentile: Early stoppinging trial 11: Trial objective value 3.32192612848736 is worse than 50.0-th percentile (3.2828795769694925) across comparable trials..
[INFO 08-21 05:05:58] ax.api.client: Trial 11 should be stopped early: Trial objective value 3.32192612848736 is worse than 50.0-th percentile (3.2828795769694925) across comparable trials.
[INFO 08-21 05:05:58] ax.api.client: Trial 11 marked EARLY_STOPPED.
[WARNING 08-21 05:06:01] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:06:01] ax.api.client: Generated new trial 12 with parameters {'x1': 0.190051, 'x2': 0.366905, 'x3': 0.461172, 'x4': 0.772098, 'x5': 0.758677, 'x6': 0.202457}using GenerationNode MBM.
[INFO 08-21 05:06:01] ax.api.client: Generated new trial 13 with parameters {'x1': 0.642382, 'x2': 0.838664, 'x3': 0.880475, 'x4': 0.162049, 'x5': 0.014087, 'x6': 0.597448}using GenerationNode MBM.
[INFO 08-21 05:06:01] ax.api.client: Generated new trial 14 with parameters {'x1': 0.954625, 'x2': 0.213013, 'x3': 0.045724, 'x4': 0.725149, 'x5': 0.42277, 'x6': 0.826285}using GenerationNode MBM.
[INFO 08-21 05:06:01] ax.early_stopping.strategies.percentile: Early stoppinging trial 12: Trial objective value 2.9516700177254247 is worse than 50.0-th percentile (2.883612120993955) across comparable trials..
[INFO 08-21 05:06:01] ax.api.client: Trial 12 should be stopped early: Trial objective value 2.9516700177254247 is worse than 50.0-th percentile (2.883612120993955) across comparable trials.
[INFO 08-21 05:06:01] ax.api.client: Trial 12 marked EARLY_STOPPED.
[INFO 08-21 05:06:02] ax.early_stopping.strategies.percentile: Early stoppinging trial 13: Trial objective value 3.1211614962369825 is worse than 50.0-th percentile (3.0954316398861197) across comparable trials..
[INFO 08-21 05:06:02] ax.api.client: Trial 13 should be stopped early: Trial objective value 3.1211614962369825 is worse than 50.0-th percentile (3.0954316398861197) across comparable trials.
[INFO 08-21 05:06:02] ax.api.client: Trial 13 marked EARLY_STOPPED.
[INFO 08-21 05:06:02] ax.early_stopping.strategies.percentile: Early stoppinging trial 14: Trial objective value 3.271386978514906 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials..
[INFO 08-21 05:06:02] ax.api.client: Trial 14 should be stopped early: Trial objective value 3.271386978514906 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials.
[INFO 08-21 05:06:02] ax.api.client: Trial 14 marked EARLY_STOPPED.
[WARNING 08-21 05:06:05] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:06:05] ax.api.client: Generated new trial 15 with parameters {'x1': 0.377782, 'x2': 0.741574, 'x3': 0.61275, 'x4': 0.333854, 'x5': 0.678119, 'x6': 0.471208}using GenerationNode MBM.
[INFO 08-21 05:06:05] ax.api.client: Generated new trial 16 with parameters {'x1': 0.369573, 'x2': 0.014036, 'x3': 0.798482, 'x4': 0.444049, 'x5': 0.519587, 'x6': 0.024796}using GenerationNode MBM.
[INFO 08-21 05:06:05] ax.api.client: Generated new trial 17 with parameters {'x1': 0.790167, 'x2': 0.534303, 'x3': 0.355484, 'x4': 0.615128, 'x5': 0.26807, 'x6': 0.677727}using GenerationNode MBM.
[INFO 08-21 05:06:09] ax.api.client: Trial 15 marked COMPLETED.
[INFO 08-21 05:06:10] ax.early_stopping.strategies.percentile: Early stoppinging trial 16: Trial objective value 3.2832291096484547 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials..
[INFO 08-21 05:06:10] ax.api.client: Trial 16 should be stopped early: Trial objective value 3.2832291096484547 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials.
[INFO 08-21 05:06:10] ax.api.client: Trial 16 marked EARLY_STOPPED.
[INFO 08-21 05:06:10] ax.early_stopping.strategies.percentile: Early stoppinging trial 17: Trial objective value 2.819035910837949 is worse than 50.0-th percentile (2.8172950675502175) across comparable trials..
[INFO 08-21 05:06:10] ax.api.client: Trial 17 should be stopped early: Trial objective value 2.819035910837949 is worse than 50.0-th percentile (2.8172950675502175) across comparable trials.
[INFO 08-21 05:06:10] ax.api.client: Trial 17 marked EARLY_STOPPED.
[INFO 08-21 05:06:14] ax.api.client: Generated new trial 18 with parameters {'x1': 1.0, 'x2': 1.0, 'x3': 0.0, 'x4': 0.0, 'x5': 1.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:14] ax.api.client: Generated new trial 19 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 0.0, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:06:14] ax.api.client: Generated new trial 20 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 0.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:14] ax.early_stopping.strategies.percentile: Early stoppinging trial 18: Trial objective value 3.321926455465507 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials..
[INFO 08-21 05:06:14] ax.api.client: Trial 18 should be stopped early: Trial objective value 3.321926455465507 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials.
[INFO 08-21 05:06:14] ax.api.client: Trial 18 marked EARLY_STOPPED.
[INFO 08-21 05:06:14] ax.early_stopping.strategies.percentile: Early stoppinging trial 19: Trial objective value 3.3161937420969143 is worse than 50.0-th percentile (3.2702077709074215) across comparable trials..
[INFO 08-21 05:06:14] ax.api.client: Trial 19 should be stopped early: Trial objective value 3.3161937420969143 is worse than 50.0-th percentile (3.2702077709074215) across comparable trials.
[INFO 08-21 05:06:14] ax.api.client: Trial 19 marked EARLY_STOPPED.
[INFO 08-21 05:06:14] ax.early_stopping.strategies.percentile: Early stoppinging trial 20: Trial objective value 3.3160433700713705 is worse than 50.0-th percentile (3.271386978514906) across comparable trials..
[INFO 08-21 05:06:14] ax.api.client: Trial 20 should be stopped early: Trial objective value 3.3160433700713705 is worse than 50.0-th percentile (3.271386978514906) across comparable trials.
[INFO 08-21 05:06:14] ax.api.client: Trial 20 marked EARLY_STOPPED.
[WARNING 08-21 05:06:19] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:06:19] ax.api.client: Generated new trial 21 with parameters {'x1': 0.602923, 'x2': 0.409953, 'x3': 0.694622, 'x4': 0.05332, 'x5': 0.167994, 'x6': 0.898595}using GenerationNode MBM.
[INFO 08-21 05:06:19] ax.api.client: Generated new trial 22 with parameters {'x1': 0.056841, 'x2': 0.889365, 'x3': 0.151291, 'x4': 0.880652, 'x5': 0.916537, 'x6': 0.301455}using GenerationNode MBM.
[INFO 08-21 05:06:19] ax.api.client: Generated new trial 23 with parameters {'x1': 0.114533, 'x2': 0.173386, 'x3': 0.645406, 'x4': 0.511408, 'x5': 0.096033, 'x6': 0.40169}using GenerationNode MBM.
[INFO 08-21 05:06:24] ax.api.client: Trial 21 marked COMPLETED.
[INFO 08-21 05:06:24] ax.early_stopping.strategies.percentile: Early stoppinging trial 22: Trial objective value 3.128676298493151 is worse than 50.0-th percentile (3.0108838463655454) across comparable trials..
[INFO 08-21 05:06:24] ax.api.client: Trial 22 should be stopped early: Trial objective value 3.128676298493151 is worse than 50.0-th percentile (3.0108838463655454) across comparable trials.
[INFO 08-21 05:06:24] ax.api.client: Trial 22 marked EARLY_STOPPED.
[INFO 08-21 05:06:29] ax.api.client: Trial 23 marked COMPLETED.
[INFO 08-21 05:06:32] ax.api.client: Generated new trial 24 with parameters {'x1': 0.746022, 'x2': 0.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:32] ax.api.client: Generated new trial 25 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:32] ax.api.client: Generated new trial 26 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:32] ax.early_stopping.strategies.percentile: Early stoppinging trial 24: Trial objective value 3.0418102290562565 is worse than 50.0-th percentile (2.9931885109890324) across comparable trials..
[INFO 08-21 05:06:32] ax.api.client: Trial 24 should be stopped early: Trial objective value 3.0418102290562565 is worse than 50.0-th percentile (2.9931885109890324) across comparable trials.
[INFO 08-21 05:06:32] ax.api.client: Trial 24 marked EARLY_STOPPED.
[INFO 08-21 05:06:32] ax.early_stopping.strategies.percentile: Early stoppinging trial 25: Trial objective value 2.8933263994685623 is worse than 50.0-th percentile (2.8155542242624856) across comparable trials..
[INFO 08-21 05:06:32] ax.api.client: Trial 25 should be stopped early: Trial objective value 2.8933263994685623 is worse than 50.0-th percentile (2.8155542242624856) across comparable trials.
[INFO 08-21 05:06:32] ax.api.client: Trial 25 marked EARLY_STOPPED.
[INFO 08-21 05:06:33] ax.early_stopping.strategies.percentile: Early stoppinging trial 26: Trial objective value 3.296641996002944 is worse than 50.0-th percentile (3.266179822243086) across comparable trials..
[INFO 08-21 05:06:33] ax.api.client: Trial 26 should be stopped early: Trial objective value 3.296641996002944 is worse than 50.0-th percentile (3.266179822243086) across comparable trials.
[INFO 08-21 05:06:33] ax.api.client: Trial 26 marked EARLY_STOPPED.
/opt/hostedtoolcache/Python/3.12.11/x64/lib/python3.12/site-packages/linear_operator/utils/cholesky.py:40: NumericalWarning:
A not p.d., added jitter of 1.0e-08 to the diagonal
/opt/hostedtoolcache/Python/3.12.11/x64/lib/python3.12/site-packages/linear_operator/utils/cholesky.py:40: NumericalWarning:
A not p.d., added jitter of 1.0e-08 to the diagonal
[INFO 08-21 05:06:39] ax.api.client: Generated new trial 27 with parameters {'x1': 0.421539, 'x2': 0.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:39] ax.api.client: Generated new trial 28 with parameters {'x1': 1.0, 'x2': 0.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:39] ax.api.client: Generated new trial 29 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:40] ax.early_stopping.strategies.percentile: Early stoppinging trial 27: Trial objective value 2.891635572828797 is worse than 50.0-th percentile (2.8172950675502175) across comparable trials..
[INFO 08-21 05:06:40] ax.api.client: Trial 27 should be stopped early: Trial objective value 2.891635572828797 is worse than 50.0-th percentile (2.8172950675502175) across comparable trials.
[INFO 08-21 05:06:40] ax.api.client: Trial 27 marked EARLY_STOPPED.
[INFO 08-21 05:06:40] ax.early_stopping.strategies.percentile: Early stoppinging trial 28: Trial objective value 3.0579951885797723 is worse than 50.0-th percentile (3.018857281552421) across comparable trials..
[INFO 08-21 05:06:40] ax.api.client: Trial 28 should be stopped early: Trial objective value 3.0579951885797723 is worse than 50.0-th percentile (3.018857281552421) across comparable trials.
[INFO 08-21 05:06:40] ax.api.client: Trial 28 marked EARLY_STOPPED.
[INFO 08-21 05:06:40] ax.early_stopping.strategies.percentile: Early stoppinging trial 29: Trial objective value 3.296641996002944 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials..
[INFO 08-21 05:06:40] ax.api.client: Trial 29 should be stopped early: Trial objective value 3.296641996002944 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials.
[INFO 08-21 05:06:40] ax.api.client: Trial 29 marked EARLY_STOPPED.
[WARNING 08-21 05:06:46] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:06:46] ax.api.client: Generated new trial 30 with parameters {'x1': 0.66921, 'x2': 0.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:46] ax.api.client: Generated new trial 31 with parameters {'x1': 0.537202, 'x2': 0.653271, 'x3': 0.196548, 'x4': 0.430659, 'x5': 0.848481, 'x6': 0.804493}using GenerationNode MBM.
[INFO 08-21 05:06:46] ax.api.client: Generated new trial 32 with parameters {'x1': 0.849968, 'x2': 0.277443, 'x3': 0.845745, 'x4': 0.995621, 'x5': 0.71325, 'x6': 0.525489}using GenerationNode MBM.
[INFO 08-21 05:06:47] ax.early_stopping.strategies.percentile: Early stoppinging trial 30: Trial objective value 3.0357299582842163 is worse than 50.0-th percentile (3.0272936199183187) across comparable trials..
[INFO 08-21 05:06:47] ax.api.client: Trial 30 should be stopped early: Trial objective value 3.0357299582842163 is worse than 50.0-th percentile (3.0272936199183187) across comparable trials.
[INFO 08-21 05:06:47] ax.api.client: Trial 30 marked EARLY_STOPPED.
[INFO 08-21 05:06:47] ax.early_stopping.strategies.percentile: Early stoppinging trial 31: Trial objective value 3.3136332954793013 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials..
[INFO 08-21 05:06:47] ax.api.client: Trial 31 should be stopped early: Trial objective value 3.3136332954793013 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials.
[INFO 08-21 05:06:47] ax.api.client: Trial 31 marked EARLY_STOPPED.
[INFO 08-21 05:06:47] ax.early_stopping.strategies.percentile: Early stoppinging trial 32: Trial objective value 3.319638488303413 is worse than 50.0-th percentile (3.266179822243086) across comparable trials..
[INFO 08-21 05:06:47] ax.api.client: Trial 32 should be stopped early: Trial objective value 3.319638488303413 is worse than 50.0-th percentile (3.266179822243086) across comparable trials.
[INFO 08-21 05:06:47] ax.api.client: Trial 32 marked EARLY_STOPPED.
[WARNING 08-21 05:06:53] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:06:53] ax.api.client: Generated new trial 33 with parameters {'x1': 0.588495, 'x2': 0.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:06:53] ax.api.client: Generated new trial 34 with parameters {'x1': 0.30181, 'x2': 0.798244, 'x3': 0.31218, 'x4': 0.071118, 'x5': 0.465638, 'x6': 0.178224}using GenerationNode MBM.
[INFO 08-21 05:06:53] ax.api.client: Generated new trial 35 with parameters {'x1': 0.450828, 'x2': 0.445704, 'x3': 0.122549, 'x4': 0.214578, 'x5': 0.373758, 'x6': 0.325562}using GenerationNode MBM.
[INFO 08-21 05:06:54] ax.early_stopping.strategies.percentile: Early stoppinging trial 33: Trial objective value 2.903667479705232 is worse than 50.0-th percentile (2.819035910837949) across comparable trials..
[INFO 08-21 05:06:54] ax.api.client: Trial 33 should be stopped early: Trial objective value 2.903667479705232 is worse than 50.0-th percentile (2.819035910837949) across comparable trials.
[INFO 08-21 05:06:54] ax.api.client: Trial 33 marked EARLY_STOPPED.
[INFO 08-21 05:06:54] ax.early_stopping.strategies.percentile: Early stoppinging trial 34: Trial objective value 2.853734341134861 is worse than 50.0-th percentile (2.8363851259864052) across comparable trials..
[INFO 08-21 05:06:54] ax.api.client: Trial 34 should be stopped early: Trial objective value 2.853734341134861 is worse than 50.0-th percentile (2.8363851259864052) across comparable trials.
[INFO 08-21 05:06:54] ax.api.client: Trial 34 marked EARLY_STOPPED.
[INFO 08-21 05:07:01] ax.api.client: Trial 35 marked COMPLETED.
[INFO 08-21 05:07:05] ax.api.client: Generated new trial 36 with parameters {'x1': 1.0, 'x2': 0.275884, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:07:05] ax.api.client: Generated new trial 37 with parameters {'x1': 1.0, 'x2': 0.28943, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:07:05] ax.api.client: Generated new trial 38 with parameters {'x1': 1.0, 'x2': 0.030526, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:07:11] ax.api.client: Trial 36 marked COMPLETED.
[INFO 08-21 05:07:12] ax.early_stopping.strategies.percentile: Early stoppinging trial 37: Trial objective value 3.3212941169068797 is worse than 50.0-th percentile (3.254915461849904) across comparable trials..
[INFO 08-21 05:07:12] ax.api.client: Trial 37 should be stopped early: Trial objective value 3.3212941169068797 is worse than 50.0-th percentile (3.254915461849904) across comparable trials.
[INFO 08-21 05:07:12] ax.api.client: Trial 37 marked EARLY_STOPPED.
[INFO 08-21 05:07:12] ax.early_stopping.strategies.percentile: Early stoppinging trial 38: Trial objective value 3.0253303726661085 is worse than 50.0-th percentile (3.018857281552421) across comparable trials..
[INFO 08-21 05:07:12] ax.api.client: Trial 38 should be stopped early: Trial objective value 3.0253303726661085 is worse than 50.0-th percentile (3.018857281552421) across comparable trials.
[INFO 08-21 05:07:12] ax.api.client: Trial 38 marked EARLY_STOPPED.
[WARNING 08-21 05:07:20] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:07:20] ax.api.client: Generated new trial 39 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.0, 'x4': 0.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:07:20] ax.api.client: Generated new trial 40 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.0, 'x4': 0.0, 'x5': 0.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:07:20] ax.api.client: Generated new trial 41 with parameters {'x1': 0.905235, 'x2': 0.973731, 'x3': 0.532087, 'x4': 0.852458, 'x5': 0.617386, 'x6': 0.970679}using GenerationNode MBM.
[INFO 08-21 05:07:21] ax.early_stopping.strategies.percentile: Early stoppinging trial 39: Trial objective value 3.2515638531064117 is worse than 50.0-th percentile (3.2513648784096514) across comparable trials..
[INFO 08-21 05:07:21] ax.api.client: Trial 39 should be stopped early: Trial objective value 3.2515638531064117 is worse than 50.0-th percentile (3.2513648784096514) across comparable trials.
[INFO 08-21 05:07:21] ax.api.client: Trial 39 marked EARLY_STOPPED.
[INFO 08-21 05:07:21] ax.early_stopping.strategies.percentile: Early stoppinging trial 40: Trial objective value 3.3168389820036976 is worse than 50.0-th percentile (3.2515638531064117) across comparable trials..
[INFO 08-21 05:07:21] ax.api.client: Trial 40 should be stopped early: Trial objective value 3.3168389820036976 is worse than 50.0-th percentile (3.2515638531064117) across comparable trials.
[INFO 08-21 05:07:21] ax.api.client: Trial 40 marked EARLY_STOPPED.
[INFO 08-21 05:07:21] ax.early_stopping.strategies.percentile: Early stoppinging trial 41: Trial objective value 3.320398947623149 is worse than 50.0-th percentile (3.2551144365466644) across comparable trials..
[INFO 08-21 05:07:21] ax.api.client: Trial 41 should be stopped early: Trial objective value 3.320398947623149 is worse than 50.0-th percentile (3.2551144365466644) across comparable trials.
[INFO 08-21 05:07:21] ax.api.client: Trial 41 marked EARLY_STOPPED.
[WARNING 08-21 05:07:28] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:07:28] ax.api.client: Generated new trial 42 with parameters {'x1': 0.717468, 'x2': 0.099562, 'x3': 0.3863, 'x4': 0.292572, 'x5': 0.94404, 'x6': 0.699392}using GenerationNode MBM.
[INFO 08-21 05:07:28] ax.api.client: Generated new trial 43 with parameters {'x1': 0.138551, 'x2': 0.570848, 'x3': 0.959185, 'x4': 0.649197, 'x5': 0.18773, 'x6': 0.09444}using GenerationNode MBM.
[INFO 08-21 05:07:28] ax.api.client: Generated new trial 44 with parameters {'x1': 0.162852, 'x2': 0.074814, 'x3': 0.245514, 'x4': 0.030784, 'x5': 0.63846, 'x6': 0.94991}using GenerationNode MBM.
[INFO 08-21 05:07:28] ax.early_stopping.strategies.percentile: Early stoppinging trial 42: Trial objective value 3.3074981290683354 is worse than 50.0-th percentile (3.258665019986917) across comparable trials..
[INFO 08-21 05:07:28] ax.api.client: Trial 42 should be stopped early: Trial objective value 3.3074981290683354 is worse than 50.0-th percentile (3.258665019986917) across comparable trials.
[INFO 08-21 05:07:28] ax.api.client: Trial 42 marked EARLY_STOPPED.
[INFO 08-21 05:07:29] ax.early_stopping.strategies.percentile: Early stoppinging trial 43: Trial objective value 2.531474672280392 is worse than 50.0-th percentile (2.5276405287795742) across comparable trials..
[INFO 08-21 05:07:29] ax.api.client: Trial 43 should be stopped early: Trial objective value 2.531474672280392 is worse than 50.0-th percentile (2.5276405287795742) across comparable trials.
[INFO 08-21 05:07:29] ax.api.client: Trial 43 marked EARLY_STOPPED.
[INFO 08-21 05:07:29] ax.early_stopping.strategies.percentile: Early stoppinging trial 44: Trial objective value 2.8821504845955896 is worse than 50.0-th percentile (2.8172950675502175) across comparable trials..
[INFO 08-21 05:07:29] ax.api.client: Trial 44 should be stopped early: Trial objective value 2.8821504845955896 is worse than 50.0-th percentile (2.8172950675502175) across comparable trials.
[INFO 08-21 05:07:29] ax.api.client: Trial 44 marked EARLY_STOPPED.
[WARNING 08-21 05:07:36] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:07:36] ax.api.client: Generated new trial 45 with parameters {'x1': 0.739817, 'x2': 0.595593, 'x3': 0.662846, 'x4': 0.918781, 'x5': 0.386013, 'x6': 0.34392}using GenerationNode MBM.
[INFO 08-21 05:07:36] ax.api.client: Generated new trial 46 with parameters {'x1': 0.92758, 'x2': 0.469764, 'x3': 0.263215, 'x4': 0.484041, 'x5': 0.052493, 'x6': 0.076143}using GenerationNode MBM.
[INFO 08-21 05:07:36] ax.api.client: Generated new trial 47 with parameters {'x1': 0.475126, 'x2': 0.949672, 'x3': 0.828304, 'x4': 0.590792, 'x5': 0.800105, 'x6': 0.7201}using GenerationNode MBM.
[INFO 08-21 05:07:36] ax.early_stopping.strategies.percentile: Early stoppinging trial 45: Trial objective value 3.296691892509696 is worse than 50.0-th percentile (3.2551144365466644) across comparable trials..
[INFO 08-21 05:07:36] ax.api.client: Trial 45 should be stopped early: Trial objective value 3.296691892509696 is worse than 50.0-th percentile (3.2551144365466644) across comparable trials.
[INFO 08-21 05:07:36] ax.api.client: Trial 45 marked EARLY_STOPPED.
[INFO 08-21 05:07:36] ax.early_stopping.strategies.percentile: Early stoppinging trial 46: Trial objective value 3.3079815441979132 is worse than 50.0-th percentile (3.258665019986917) across comparable trials..
[INFO 08-21 05:07:36] ax.api.client: Trial 46 should be stopped early: Trial objective value 3.3079815441979132 is worse than 50.0-th percentile (3.258665019986917) across comparable trials.
[INFO 08-21 05:07:36] ax.api.client: Trial 46 marked EARLY_STOPPED.
[INFO 08-21 05:07:36] ax.early_stopping.strategies.percentile: Early stoppinging trial 47: Trial objective value 3.312590326384613 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials..
[INFO 08-21 05:07:36] ax.api.client: Trial 47 should be stopped early: Trial objective value 3.312590326384613 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials.
[INFO 08-21 05:07:36] ax.api.client: Trial 47 marked EARLY_STOPPED.
[WARNING 08-21 05:07:43] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:07:43] ax.api.client: Generated new trial 48 with parameters {'x1': 0.279478, 'x2': 0.30221, 'x3': 0.518552, 'x4': 0.702705, 'x5': 0.891741, 'x6': 0.775885}using GenerationNode MBM.
[INFO 08-21 05:07:43] ax.api.client: Generated new trial 49 with parameters {'x1': 0.825681, 'x2': 0.773474, 'x3': 0.07749, 'x4': 0.37183, 'x5': 0.148113, 'x6': 0.427826}using GenerationNode MBM.
[INFO 08-21 05:07:43] ax.api.client: Generated new trial 50 with parameters {'x1': 0.512919, 'x2': 0.149305, 'x3': 0.972719, 'x4': 0.812242, 'x5': 0.29021, 'x6': 0.152148}using GenerationNode MBM.
[INFO 08-21 05:07:44] ax.early_stopping.strategies.percentile: Early stoppinging trial 48: Trial objective value 3.077387947039961 is worse than 50.0-th percentile (3.0180118682325383) across comparable trials..
[INFO 08-21 05:07:44] ax.api.client: Trial 48 should be stopped early: Trial objective value 3.077387947039961 is worse than 50.0-th percentile (3.0180118682325383) across comparable trials.
[INFO 08-21 05:07:44] ax.api.client: Trial 48 marked EARLY_STOPPED.
[INFO 08-21 05:07:44] ax.early_stopping.strategies.percentile: Early stoppinging trial 49: Trial objective value 3.082342701102292 is worse than 50.0-th percentile (3.018857281552421) across comparable trials..
[INFO 08-21 05:07:44] ax.api.client: Trial 49 should be stopped early: Trial objective value 3.082342701102292 is worse than 50.0-th percentile (3.018857281552421) across comparable trials.
[INFO 08-21 05:07:44] ax.api.client: Trial 49 marked EARLY_STOPPED.
[INFO 08-21 05:07:44] ax.early_stopping.strategies.percentile: Early stoppinging trial 50: Trial objective value 3.2953870991160272 is worse than 50.0-th percentile (3.258665019986917) across comparable trials..
[INFO 08-21 05:07:44] ax.api.client: Trial 50 should be stopped early: Trial objective value 3.2953870991160272 is worse than 50.0-th percentile (3.258665019986917) across comparable trials.
[INFO 08-21 05:07:44] ax.api.client: Trial 50 marked EARLY_STOPPED.
[WARNING 08-21 05:07:52] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:07:52] ax.api.client: Generated new trial 51 with parameters {'x1': 0.092204, 'x2': 0.677354, 'x3': 0.43136, 'x4': 0.137621, 'x5': 0.546519, 'x6': 0.554037}using GenerationNode MBM.
[INFO 08-21 05:07:52] ax.api.client: Generated new trial 52 with parameters {'x1': 0.016686, 'x2': 0.385399, 'x3': 0.929441, 'x4': 0.252484, 'x5': 0.47606, 'x6': 0.649114}using GenerationNode MBM.
[INFO 08-21 05:07:52] ax.api.client: Generated new trial 53 with parameters {'x1': 0.56472, 'x2': 0.913921, 'x3': 0.478613, 'x4': 0.673689, 'x5': 0.72065, 'x6': 0.050937}using GenerationNode MBM.
[INFO 08-21 05:08:00] ax.api.client: Trial 51 marked COMPLETED.
[INFO 08-21 05:08:09] ax.api.client: Trial 52 marked COMPLETED.
[INFO 08-21 05:08:17] ax.api.client: Trial 53 marked COMPLETED.
[INFO 08-21 05:08:23] ax.api.client: Generated new trial 54 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.0, 'x4': 1.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:23] ax.api.client: Generated new trial 55 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 1.0, 'x4': 1.0, 'x5': 0.864158, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:23] ax.api.client: Generated new trial 56 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 1.0, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:24] ax.early_stopping.strategies.percentile: Early stoppinging trial 54: Trial objective value 3.321865109848851 is worse than 50.0-th percentile (3.2515638531064117) across comparable trials..
[INFO 08-21 05:08:24] ax.api.client: Trial 54 should be stopped early: Trial objective value 3.321865109848851 is worse than 50.0-th percentile (3.2515638531064117) across comparable trials.
[INFO 08-21 05:08:24] ax.api.client: Trial 54 marked EARLY_STOPPED.
[INFO 08-21 05:08:24] ax.early_stopping.strategies.percentile: Early stoppinging trial 55: Trial objective value 3.3218121738014728 is worse than 50.0-th percentile (3.2551144365466644) across comparable trials..
[INFO 08-21 05:08:24] ax.api.client: Trial 55 should be stopped early: Trial objective value 3.3218121738014728 is worse than 50.0-th percentile (3.2551144365466644) across comparable trials.
[INFO 08-21 05:08:24] ax.api.client: Trial 55 marked EARLY_STOPPED.
[INFO 08-21 05:08:24] ax.early_stopping.strategies.percentile: Early stoppinging trial 56: Trial objective value 3.320279965560053 is worse than 50.0-th percentile (3.258665019986917) across comparable trials..
[INFO 08-21 05:08:24] ax.api.client: Trial 56 should be stopped early: Trial objective value 3.320279965560053 is worse than 50.0-th percentile (3.258665019986917) across comparable trials.
[INFO 08-21 05:08:24] ax.api.client: Trial 56 marked EARLY_STOPPED.
[WARNING 08-21 05:08:35] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:08:35] ax.api.client: Generated new trial 57 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.876251, 'x4': 0.283037, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:35] ax.api.client: Generated new trial 58 with parameters {'x1': 0.751968, 'x2': 0.038269, 'x3': 0.563784, 'x4': 0.236964, 'x5': 0.843217, 'x6': 0.275376}using GenerationNode MBM.
[INFO 08-21 05:08:35] ax.api.client: Generated new trial 59 with parameters {'x1': 0.329422, 'x2': 0.510068, 'x3': 0.028283, 'x4': 0.814415, 'x5': 0.087868, 'x6': 0.927145}using GenerationNode MBM.
[INFO 08-21 05:08:35] ax.early_stopping.strategies.percentile: Early stoppinging trial 57: Trial objective value 3.3154854434040497 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials..
[INFO 08-21 05:08:35] ax.api.client: Trial 57 should be stopped early: Trial objective value 3.3154854434040497 is worse than 50.0-th percentile (3.2624224211150015) across comparable trials.
[INFO 08-21 05:08:35] ax.api.client: Trial 57 marked EARLY_STOPPED.
[INFO 08-21 05:08:36] ax.early_stopping.strategies.percentile: Early stoppinging trial 58: Trial objective value 3.311547070936001 is worse than 50.0-th percentile (3.266179822243086) across comparable trials..
[INFO 08-21 05:08:36] ax.api.client: Trial 58 should be stopped early: Trial objective value 3.311547070936001 is worse than 50.0-th percentile (3.266179822243086) across comparable trials.
[INFO 08-21 05:08:36] ax.api.client: Trial 58 marked EARLY_STOPPED.
[INFO 08-21 05:08:36] ax.early_stopping.strategies.percentile: Early stoppinging trial 59: Trial objective value 3.29685776748415 is worse than 50.0-th percentile (3.2676041927715116) across comparable trials..
[INFO 08-21 05:08:36] ax.api.client: Trial 59 should be stopped early: Trial objective value 3.29685776748415 is worse than 50.0-th percentile (3.2676041927715116) across comparable trials.
[INFO 08-21 05:08:36] ax.api.client: Trial 59 marked EARLY_STOPPED.
[WARNING 08-21 05:08:50] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:08:50] ax.api.client: Generated new trial 60 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.74696, 'x4': 0.387537, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:50] ax.api.client: Generated new trial 61 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.0, 'x4': 1.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:50] ax.api.client: Generated new trial 62 with parameters {'x1': 0.416, 'x2': 0.237608, 'x3': 0.341949, 'x4': 0.955686, 'x5': 0.245668, 'x6': 0.576683}using GenerationNode MBM.
[INFO 08-21 05:08:50] ax.early_stopping.strategies.percentile: Early stoppinging trial 60: Trial objective value 3.306472827851021 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials..
[INFO 08-21 05:08:50] ax.api.client: Trial 60 should be stopped early: Trial objective value 3.306472827851021 is worse than 50.0-th percentile (3.2690285632999374) across comparable trials.
[INFO 08-21 05:08:50] ax.api.client: Trial 60 marked EARLY_STOPPED.
[INFO 08-21 05:08:51] ax.early_stopping.strategies.percentile: Early stoppinging trial 61: Trial objective value 3.321865109848851 is worse than 50.0-th percentile (3.2702077709074215) across comparable trials..
[INFO 08-21 05:08:51] ax.api.client: Trial 61 should be stopped early: Trial objective value 3.321865109848851 is worse than 50.0-th percentile (3.2702077709074215) across comparable trials.
[INFO 08-21 05:08:51] ax.api.client: Trial 61 marked EARLY_STOPPED.
[INFO 08-21 05:08:51] ax.early_stopping.strategies.percentile: Early stoppinging trial 62: Trial objective value 3.288312629539149 is worse than 50.0-th percentile (3.271386978514906) across comparable trials..
[INFO 08-21 05:08:51] ax.api.client: Trial 62 should be stopped early: Trial objective value 3.288312629539149 is worse than 50.0-th percentile (3.271386978514906) across comparable trials.
[INFO 08-21 05:08:51] ax.api.client: Trial 62 marked EARLY_STOPPED.
[INFO 08-21 05:08:58] ax.api.client: Generated new trial 63 with parameters {'x1': 1.0, 'x2': 1.0, 'x3': 1.0, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:58] ax.api.client: Generated new trial 64 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 1.0, 'x4': 0.0, 'x5': 0.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:08:58] ax.api.client: Generated new trial 65 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 1.0, 'x4': 1.0, 'x5': 1.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:08:58] ax.early_stopping.strategies.percentile: Early stoppinging trial 63: Trial objective value 3.3216961560059537 is worse than 50.0-th percentile (3.27730804408168) across comparable trials..
[INFO 08-21 05:08:58] ax.api.client: Trial 63 should be stopped early: Trial objective value 3.3216961560059537 is worse than 50.0-th percentile (3.27730804408168) across comparable trials.
[INFO 08-21 05:08:58] ax.api.client: Trial 63 marked EARLY_STOPPED.
[INFO 08-21 05:08:59] ax.early_stopping.strategies.percentile: Early stoppinging trial 64: Trial objective value 3.315202943497908 is worse than 50.0-th percentile (3.2832291096484547) across comparable trials..
[INFO 08-21 05:08:59] ax.api.client: Trial 64 should be stopped early: Trial objective value 3.315202943497908 is worse than 50.0-th percentile (3.2832291096484547) across comparable trials.
[INFO 08-21 05:08:59] ax.api.client: Trial 64 marked EARLY_STOPPED.
[INFO 08-21 05:08:59] ax.early_stopping.strategies.percentile: Early stoppinging trial 65: Trial objective value 3.3218624512812904 is worse than 50.0-th percentile (3.2857708695938017) across comparable trials..
[INFO 08-21 05:08:59] ax.api.client: Trial 65 should be stopped early: Trial objective value 3.3218624512812904 is worse than 50.0-th percentile (3.2857708695938017) across comparable trials.
[INFO 08-21 05:08:59] ax.api.client: Trial 65 marked EARLY_STOPPED.
[INFO 08-21 05:09:07] ax.api.client: Generated new trial 66 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 1.0, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:09:07] ax.api.client: Generated new trial 67 with parameters {'x1': 1.0, 'x2': 1.0, 'x3': 1.0, 'x4': 0.0, 'x5': 1.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:09:07] ax.api.client: Generated new trial 68 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 1.0, 'x4': 1.0, 'x5': 0.0, 'x6': 1.0}using GenerationNode MBM.
[INFO 08-21 05:09:07] ax.early_stopping.strategies.percentile: Early stoppinging trial 66: Trial objective value 3.3157849427224875 is worse than 50.0-th percentile (3.288312629539149) across comparable trials..
[INFO 08-21 05:09:07] ax.api.client: Trial 66 should be stopped early: Trial objective value 3.3157849427224875 is worse than 50.0-th percentile (3.288312629539149) across comparable trials.
[INFO 08-21 05:09:07] ax.api.client: Trial 66 marked EARLY_STOPPED.
[INFO 08-21 05:09:07] ax.early_stopping.strategies.percentile: Early stoppinging trial 67: Trial objective value 3.3218916513095396 is worse than 50.0-th percentile (3.291849864327588) across comparable trials..
[INFO 08-21 05:09:07] ax.api.client: Trial 67 should be stopped early: Trial objective value 3.3218916513095396 is worse than 50.0-th percentile (3.291849864327588) across comparable trials.
[INFO 08-21 05:09:07] ax.api.client: Trial 67 marked EARLY_STOPPED.
[INFO 08-21 05:09:08] ax.early_stopping.strategies.percentile: Early stoppinging trial 68: Trial objective value 3.3009534184327247 is worse than 50.0-th percentile (3.2953870991160272) across comparable trials..
[INFO 08-21 05:09:08] ax.api.client: Trial 68 should be stopped early: Trial objective value 3.3009534184327247 is worse than 50.0-th percentile (3.2953870991160272) across comparable trials.
[INFO 08-21 05:09:08] ax.api.client: Trial 68 marked EARLY_STOPPED.
[WARNING 08-21 05:09:27] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:09:27] ax.api.client: Generated new trial 69 with parameters {'x1': 0.0, 'x2': 1.0, 'x3': 1.0, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:09:27] ax.api.client: Generated new trial 70 with parameters {'x1': 0.994797, 'x2': 0.716981, 'x3': 0.753422, 'x4': 0.095519, 'x5': 0.997185, 'x6': 0.220811}using GenerationNode MBM.
[INFO 08-21 05:09:27] ax.api.client: Generated new trial 71 with parameters {'x1': 0.682549, 'x2': 0.342631, 'x3': 0.164826, 'x4': 0.533885, 'x5': 0.566011, 'x6': 0.452914}using GenerationNode MBM.
[INFO 08-21 05:09:27] ax.early_stopping.strategies.percentile: Early stoppinging trial 69: Trial objective value 3.3157849427224875 is worse than 50.0-th percentile (3.2960145475594853) across comparable trials..
[INFO 08-21 05:09:27] ax.api.client: Trial 69 should be stopped early: Trial objective value 3.3157849427224875 is worse than 50.0-th percentile (3.2960145475594853) across comparable trials.
[INFO 08-21 05:09:27] ax.api.client: Trial 69 marked EARLY_STOPPED.
[INFO 08-21 05:09:27] ax.early_stopping.strategies.percentile: Early stoppinging trial 70: Trial objective value 3.3214809813109487 is worse than 50.0-th percentile (3.296641996002944) across comparable trials..
[INFO 08-21 05:09:27] ax.api.client: Trial 70 should be stopped early: Trial objective value 3.3214809813109487 is worse than 50.0-th percentile (3.296641996002944) across comparable trials.
[INFO 08-21 05:09:27] ax.api.client: Trial 70 marked EARLY_STOPPED.
[INFO 08-21 05:09:28] ax.early_stopping.strategies.percentile: Early stoppinging trial 71: Trial objective value 2.889329061619732 is worse than 50.0-th percentile (2.8017307546052215) across comparable trials..
[INFO 08-21 05:09:28] ax.api.client: Trial 71 should be stopped early: Trial objective value 2.889329061619732 is worse than 50.0-th percentile (2.8017307546052215) across comparable trials.
[INFO 08-21 05:09:28] ax.api.client: Trial 71 marked EARLY_STOPPED.
[WARNING 08-21 05:09:42] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:09:42] ax.api.client: Generated new trial 72 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 1.0, 'x4': 0.386096, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:09:42] ax.api.client: Generated new trial 73 with parameters {'x1': 0.228264, 'x2': 0.862937, 'x3': 0.739681, 'x4': 0.392464, 'x5': 0.317467, 'x6': 0.846989}using GenerationNode MBM.
[INFO 08-21 05:09:42] ax.api.client: Generated new trial 74 with parameters {'x1': 0.249611, 'x2': 0.197513, 'x3': 0.85985, 'x4': 0.15517, 'x5': 0.932343, 'x6': 0.918754}using GenerationNode MBM.
[INFO 08-21 05:09:42] ax.early_stopping.strategies.percentile: Early stoppinging trial 72: Trial objective value 3.320672834595601 is worse than 50.0-th percentile (3.296641996002944) across comparable trials..
[INFO 08-21 05:09:42] ax.api.client: Trial 72 should be stopped early: Trial objective value 3.320672834595601 is worse than 50.0-th percentile (3.296641996002944) across comparable trials.
[INFO 08-21 05:09:42] ax.api.client: Trial 72 marked EARLY_STOPPED.
[INFO 08-21 05:09:43] ax.early_stopping.strategies.percentile: Early stoppinging trial 73: Trial objective value 2.584241000799531 is worse than 50.0-th percentile (2.438101479931399) across comparable trials..
[INFO 08-21 05:09:43] ax.api.client: Trial 73 should be stopped early: Trial objective value 2.584241000799531 is worse than 50.0-th percentile (2.438101479931399) across comparable trials.
[INFO 08-21 05:09:43] ax.api.client: Trial 73 marked EARLY_STOPPED.
[INFO 08-21 05:09:43] ax.early_stopping.strategies.percentile: Early stoppinging trial 74: Trial objective value 3.110952998311255 is worse than 50.0-th percentile (3.014859943703591) across comparable trials..
[INFO 08-21 05:09:43] ax.api.client: Trial 74 should be stopped early: Trial objective value 3.110952998311255 is worse than 50.0-th percentile (3.014859943703591) across comparable trials.
[INFO 08-21 05:09:43] ax.api.client: Trial 74 marked EARLY_STOPPED.
[WARNING 08-21 05:09:57] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:09:57] ax.api.client: Generated new trial 75 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.726104, 'x4': 0.069952, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:09:57] ax.api.client: Generated new trial 76 with parameters {'x1': 0.66874, 'x2': 0.72583, 'x3': 0.29478, 'x4': 0.794632, 'x5': 0.183801, 'x6': 0.250322}using GenerationNode MBM.
[INFO 08-21 05:09:57] ax.api.client: Generated new trial 77 with parameters {'x1': 0.981017, 'x2': 0.351399, 'x3': 0.631423, 'x4': 0.35819, 'x5': 0.252625, 'x6': 0.044436}using GenerationNode MBM.
[INFO 08-21 05:09:58] ax.early_stopping.strategies.percentile: Early stoppinging trial 75: Trial objective value 3.156469006306182 is worse than 50.0-th percentile (3.016013199308123) across comparable trials..
[INFO 08-21 05:09:58] ax.api.client: Trial 75 should be stopped early: Trial objective value 3.156469006306182 is worse than 50.0-th percentile (3.016013199308123) across comparable trials.
[INFO 08-21 05:09:58] ax.api.client: Trial 75 marked EARLY_STOPPED.
[INFO 08-21 05:09:58] ax.early_stopping.strategies.percentile: Early stoppinging trial 76: Trial objective value 2.792218860129878 is worse than 50.0-th percentile (2.790063072538918) across comparable trials..
[INFO 08-21 05:09:58] ax.api.client: Trial 76 should be stopped early: Trial objective value 2.792218860129878 is worse than 50.0-th percentile (2.790063072538918) across comparable trials.
[INFO 08-21 05:09:58] ax.api.client: Trial 76 marked EARLY_STOPPED.
[INFO 08-21 05:09:59] ax.early_stopping.strategies.percentile: Early stoppinging trial 77: Trial objective value 3.303380605022213 is worse than 50.0-th percentile (3.294679814586072) across comparable trials..
[INFO 08-21 05:09:59] ax.api.client: Trial 77 should be stopped early: Trial objective value 3.303380605022213 is worse than 50.0-th percentile (3.294679814586072) across comparable trials.
[INFO 08-21 05:09:59] ax.api.client: Trial 77 marked EARLY_STOPPED.
[WARNING 08-21 05:10:13] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:10:13] ax.api.client: Generated new trial 78 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.621625, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:10:13] ax.api.client: Generated new trial 79 with parameters {'x1': 0.437378, 'x2': 0.822914, 'x3': 0.214071, 'x4': 0.716406, 'x5': 0.504144, 'x6': 0.626072}using GenerationNode MBM.
[INFO 08-21 05:10:13] ax.api.client: Generated new trial 80 with parameters {'x1': 0.319793, 'x2': 0.425455, 'x3': 0.400287, 'x4': 0.577091, 'x5': 0.66243, 'x6': 0.870092}using GenerationNode MBM.
[INFO 08-21 05:10:14] ax.early_stopping.strategies.percentile: Early stoppinging trial 78: Trial objective value 3.1416337369118152 is worse than 50.0-th percentile (3.016013199308123) across comparable trials..
[INFO 08-21 05:10:14] ax.api.client: Trial 78 should be stopped early: Trial objective value 3.1416337369118152 is worse than 50.0-th percentile (3.016013199308123) across comparable trials.
[INFO 08-21 05:10:14] ax.api.client: Trial 78 marked EARLY_STOPPED.
[INFO 08-21 05:10:14] ax.early_stopping.strategies.percentile: Early stoppinging trial 79: Trial objective value 3.1219148476190077 is worse than 50.0-th percentile (3.0171664549126556) across comparable trials..
[INFO 08-21 05:10:14] ax.api.client: Trial 79 should be stopped early: Trial objective value 3.1219148476190077 is worse than 50.0-th percentile (3.0171664549126556) across comparable trials.
[INFO 08-21 05:10:14] ax.api.client: Trial 79 marked EARLY_STOPPED.
[INFO 08-21 05:10:15] ax.early_stopping.strategies.percentile: Early stoppinging trial 80: Trial objective value 3.0399971490536633 is worse than 50.0-th percentile (3.0180118682325383) across comparable trials..
[INFO 08-21 05:10:15] ax.api.client: Trial 80 should be stopped early: Trial objective value 3.0399971490536633 is worse than 50.0-th percentile (3.0180118682325383) across comparable trials.
[INFO 08-21 05:10:15] ax.api.client: Trial 80 marked EARLY_STOPPED.
[WARNING 08-21 05:10:32] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:10:32] ax.api.client: Generated new trial 81 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.662321, 'x4': 0.690091, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:10:32] ax.api.client: Generated new trial 82 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.0, 'x4': 0.0, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:10:32] ax.api.client: Generated new trial 83 with parameters {'x1': 0.769683, 'x2': 0.905111, 'x3': 0.941658, 'x4': 0.497681, 'x5': 0.407083, 'x6': 0.459354}using GenerationNode MBM.
[INFO 08-21 05:10:33] ax.early_stopping.strategies.percentile: Early stoppinging trial 81: Trial objective value 3.313995301909999 is worse than 50.0-th percentile (3.291142579797633) across comparable trials..
[INFO 08-21 05:10:33] ax.api.client: Trial 81 should be stopped early: Trial objective value 3.313995301909999 is worse than 50.0-th percentile (3.291142579797633) across comparable trials.
[INFO 08-21 05:10:33] ax.api.client: Trial 81 marked EARLY_STOPPED.
[INFO 08-21 05:10:33] ax.early_stopping.strategies.percentile: Early stoppinging trial 82: Trial objective value 3.321673405666465 is worse than 50.0-th percentile (3.293972530056117) across comparable trials..
[INFO 08-21 05:10:33] ax.api.client: Trial 82 should be stopped early: Trial objective value 3.321673405666465 is worse than 50.0-th percentile (3.293972530056117) across comparable trials.
[INFO 08-21 05:10:33] ax.api.client: Trial 82 marked EARLY_STOPPED.
[INFO 08-21 05:10:33] ax.early_stopping.strategies.percentile: Early stoppinging trial 83: Trial objective value 3.1219704320247135 is worse than 50.0-th percentile (3.018857281552421) across comparable trials..
[INFO 08-21 05:10:33] ax.api.client: Trial 83 should be stopped early: Trial objective value 3.1219704320247135 is worse than 50.0-th percentile (3.018857281552421) across comparable trials.
[INFO 08-21 05:10:33] ax.api.client: Trial 83 marked EARLY_STOPPED.
[WARNING 08-21 05:10:49] ax.generation_strategy.generation_node: gen failed with error GenerationStrategy exceeded MAX_GEN_ATTEMPTS of 5 while trying to generate a unique parameterization. This indicates that the search space has likely been fully explored, or that the sweep has converged., switching to fallback model with generator_enum Generators.SOBOL
[INFO 08-21 05:10:49] ax.api.client: Generated new trial 84 with parameters {'x1': 0.0, 'x2': 0.0, 'x3': 0.565892, 'x4': 0.072425, 'x5': 1.0, 'x6': 0.0}using GenerationNode MBM.
[INFO 08-21 05:10:49] ax.api.client: Generated new trial 85 with parameters {'x1': 0.582406, 'x2': 0.02954, 'x3': 0.108441, 'x4': 0.936391, 'x5': 0.029648, 'x6': 0.245804}using GenerationNode MBM.
[INFO 08-21 05:10:49] ax.api.client: Generated new trial 86 with parameters {'x1': 0.007027, 'x2': 0.550051, 'x3': 0.549491, 'x4': 0.013235, 'x5': 0.77424, 'x6': 0.585135}using GenerationNode MBM.
[INFO 08-21 05:10:49] ax.early_stopping.strategies.percentile: Early stoppinging trial 84: Trial objective value 3.1390712268685865 is worse than 50.0-th percentile (3.0220938271092646) across comparable trials..
[INFO 08-21 05:10:49] ax.api.client: Trial 84 should be stopped early: Trial objective value 3.1390712268685865 is worse than 50.0-th percentile (3.0220938271092646) across comparable trials.
[INFO 08-21 05:10:49] ax.api.client: Trial 84 marked EARLY_STOPPED.
[INFO 08-21 05:10:50] ax.early_stopping.strategies.percentile: Early stoppinging trial 85: Trial objective value 3.3192815284390322 is worse than 50.0-th percentile (3.291142579797633) across comparable trials..
[INFO 08-21 05:10:50] ax.api.client: Trial 85 should be stopped early: Trial objective value 3.3192815284390322 is worse than 50.0-th percentile (3.291142579797633) across comparable trials.
[INFO 08-21 05:10:50] ax.api.client: Trial 85 marked EARLY_STOPPED.
[INFO 08-21 05:11:02] ax.api.client: Trial 86 marked COMPLETED.
Step 6: Analyze Results
After running trials, you can analyze the results. Most commonly this means extracting the parameterization from the best performing trial you conducted.
best_parameters, prediction, index, name = client.get_best_parameterization()
print("Best Parameters:", best_parameters)
print("Prediction (mean, variance):", prediction)
Best Parameters: {'x1': 0.5647202311083674, 'x2': 0.9139208532869816, 'x3': 0.4786133347079158, 'x4': 0.6736893076449633, 'x5': 0.7206500573083758, 'x6': 0.05093718133866787}
Prediction (mean, variance): {'hartmann6': (-1.775737073760956, nan)}
Step 7: Compute Analyses
Ax can also produce a number of analyses to help interpret the results of the experiment
via client.compute_analyses
. Users can manually select which analyses to run, or can
allow Ax to select which would be most relevant. In this case Ax selects the following:
- Arm Effects Plots show the metric value for each arm on the experiment. Ax produces one plot using values from its internal surrogate model (this can be helpful for seeing the true effect of an arm when evaluations are noisy) and another using the raw metric values as observed.
- Summary lists all trials generated along with their parameterizations, observations, and miscellaneous metadata
- Sensitivity Analysis Plot shows which parameters have the largest affect on the objective using Sobol Indicies
- Slice Plot shows how the model predicts a single parameter effects the objective along with a confidence interval
- Contour Plot shows how the model predicts a pair of parameters effects the objective as a 2D surface
- Cross Validation helps to visualize how well the surrogate model is able to predict out of sample points
# display=True instructs Ax to sort then render the resulting analyses
cards = client.compute_analyses(display=True)
[INFO 08-21 05:11:02] ax.analysis.utils: Provided adapter is unable to model effects. Using Empirical Bayes as falback.
[ERROR 08-21 05:11:03] ax.analysis.analysis: Failed to compute ArmEffectsPlot
[ERROR 08-21 05:11:03] ax.analysis.analysis: Traceback (most recent call last):
File "/home/runner/work/Ax/Ax/ax/analysis/analysis.py", line 73, in compute_result
card = self.compute(
^^^^^^^^^^^^^
File "/home/runner/work/Ax/Ax/ax/analysis/plotly/arm_effects.py", line 220, in compute
fig=_prepare_figure(
^^^^^^^^^^^^^^^^
File "/home/runner/work/Ax/Ax/ax/analysis/plotly/arm_effects.py", line 401, in _prepare_figure
max_label_len = max(len(label) for label in arm_label)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: max() iterable argument is empty
[ERROR 08-21 05:11:03] ax.analysis.analysis: Failed to compute TopSurfacesAnalysis
[ERROR 08-21 05:11:03] ax.analysis.analysis: Traceback (most recent call last):
File "/home/runner/work/Ax/Ax/ax/analysis/analysis.py", line 73, in compute_result
card = self.compute(
^^^^^^^^^^^^^
File "/home/runner/work/Ax/Ax/ax/analysis/plotly/top_surfaces.py", line 87, in compute
).compute(
^^^^^^^^
File "/home/runner/work/Ax/Ax/ax/analysis/plotly/sensitivity.py", line 98, in compute
raise UserInputError(
ax.exceptions.core.UserInputError: SensitivityAnalysisPlot requires a TorchAdapter, found <class 'NoneType'>.
[ERROR 08-21 05:11:03] ax.analysis.analysis: Failed to compute CrossValidationPlot
[ERROR 08-21 05:11:03] ax.analysis.analysis: Traceback (most recent call last):
File "/home/runner/work/Ax/Ax/ax/analysis/analysis.py", line 73, in compute_result
card = self.compute(
^^^^^^^^^^^^^
File "/home/runner/work/Ax/Ax/ax/analysis/plotly/cross_validation.py", line 127, in compute
cv_results = cross_validate(
^^^^^^^^^^^^^^^
File "/home/runner/work/Ax/Ax/ax/adapter/cross_validation.py", line 169, in cross_validate
cv_test_predictions = model._cross_validate(
^^^^^^^^^^^^^^^^^^^^^^
File "/home/runner/work/Ax/Ax/ax/adapter/base.py", line 987, in _cross_validate
raise AdapterMethodNotImplementedError(
ax.exceptions.model.AdapterMethodNotImplementedError: RandomAdapter does not implement _cross_validate.
ArmEffectsPlot Error
ValueError encountered while computing ArmEffectsPlot.
Observed Arm Effects on hartmann6
Observed effects on hartmann6. This plot visualizes the effects from previously-run arms on a specific metric, providing insights into their performance. This plot allows one to compare and contrast the effectiveness of different arms, highlighting which configurations have yielded the most favorable outcomes.
Summary for Experiment
High-level summary of the Trial
-s in this Experiment
trial_index | arm_name | trial_status | generation_node | hartmann6 | x1 | x2 | x3 | x4 | x5 | x6 | |
---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 0_0 | COMPLETED | CenterOfSearchSpace | -0.505315 | 0.500000 | 0.500000 | 0.500000 | 0.500000 | 0.500000 | 0.500000 |
1 | 1 | 1_0 | COMPLETED | Sobol | -0.243339 | 0.684849 | 0.957862 | 0.471241 | 0.256039 | 0.296428 | 0.179191 |
2 | 2 | 2_0 | COMPLETED | Sobol | -0.052900 | 0.151850 | 0.185658 | 0.894246 | 0.576811 | 0.843578 | 0.560530 |
3 | 3 | 3_0 | COMPLETED | Sobol | -0.415776 | 0.258363 | 0.556372 | 0.112227 | 0.217706 | 0.567069 | 0.772171 |
4 | 4 | 4_0 | COMPLETED | Sobol | -0.007265 | 0.795556 | 0.331534 | 0.503732 | 0.896874 | 0.051719 | 0.402548 |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
82 | 82 | 82_0 | EARLY_STOPPED | MBM | 3.321673 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 1.000000 | 0.000000 |
83 | 83 | 83_0 | EARLY_STOPPED | MBM | 3.121970 | 0.769683 | 0.905111 | 0.941658 | 0.497681 | 0.407083 | 0.459354 |
84 | 84 | 84_0 | EARLY_STOPPED | MBM | 3.139071 | 0.000000 | 0.000000 | 0.565892 | 0.072425 | 1.000000 | 0.000000 |
85 | 85 | 85_0 | EARLY_STOPPED | MBM | 3.319282 | 0.582406 | 0.029540 | 0.108441 | 0.936391 | 0.029648 | 0.245804 |
86 | 86 | 86_0 | COMPLETED | MBM | -0.566778 | 0.007027 | 0.550051 | 0.549491 | 0.013235 | 0.774240 | 0.585135 |
CrossValidationPlot Error
AdapterMethodNotImplementedError encountered while computing CrossValidationPlot.
Conclusion
This tutorial demonstates Ax's early stopping capabilities, which utilize timeseries-like data to monitor the results of expensive evaluations and terminate those that are unlikely to produce promising results, freeing up resources to explore more configurations. This can be used in a number of applications, and is especially useful in machine learning contexts.